diff options
Diffstat (limited to 'include/linux')
247 files changed, 6735 insertions, 1875 deletions
diff --git a/include/linux/adi-axi-common.h b/include/linux/adi-axi-common.h index f64f4ad4beda..37962ba530df 100644 --- a/include/linux/adi-axi-common.h +++ b/include/linux/adi-axi-common.h @@ -8,6 +8,8 @@ * https://wiki.analog.com/resources/fpga/docs/hdl/regmap */ +#include <linux/types.h> + #ifndef ADI_AXI_COMMON_H_ #define ADI_AXI_COMMON_H_ @@ -21,6 +23,25 @@ #define ADI_AXI_PCORE_VER_MINOR(version) (((version) >> 8) & 0xff) #define ADI_AXI_PCORE_VER_PATCH(version) ((version) & 0xff) +/** + * adi_axi_pcore_ver_gteq() - check if a version is satisfied + * @version: the full version read from the hardware + * @major: the major version to compare against + * @minor: the minor version to compare against + * + * ADI AXI IP Cores use semantic versioning, so this can be used to check for + * feature availability. + * + * Return: true if the version is greater than or equal to the specified + * major and minor version, false otherwise. + */ +static inline bool adi_axi_pcore_ver_gteq(u32 version, u32 major, u32 minor) +{ + return ADI_AXI_PCORE_VER_MAJOR(version) > (major) || + (ADI_AXI_PCORE_VER_MAJOR(version) == (major) && + ADI_AXI_PCORE_VER_MINOR(version) >= (minor)); +} + #define ADI_AXI_INFO_FPGA_TECH(info) (((info) >> 24) & 0xff) #define ADI_AXI_INFO_FPGA_FAMILY(info) (((info) >> 16) & 0xff) #define ADI_AXI_INFO_FPGA_SPEED_GRADE(info) (((info) >> 8) & 0xff) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 9ef2633e2c08..d40ac39bfbe8 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -221,6 +221,16 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) ref->ct = NULL; } +static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag) +{ + tag->ct.flags |= CODETAG_FLAG_INACCURATE; +} + +static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) +{ + return !!(tag->ct.flags & CODETAG_FLAG_INACCURATE); +} + #define alloc_tag_record(p) ((p) = current->alloc_tag) #else /* CONFIG_MEM_ALLOC_PROFILING */ @@ -230,6 +240,8 @@ static inline bool mem_alloc_profiling_enabled(void) { return false; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} +static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag) {} +static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) { return false; } #define alloc_tag_record(p) do {} while (0) #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 45f2f278b50a..70807c679f1a 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */ int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd, void __user *arg); #endif + int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); diff --git a/include/linux/audit.h b/include/linux/audit.h index a394614ccd0b..536f8ee8da81 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -37,6 +37,8 @@ struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; +struct lsm_id; +struct lsm_prop; struct audit_krule { u32 pflags; @@ -147,6 +149,10 @@ extern unsigned compat_signal_class[]; #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) +/* bit values for audit_cfg_lsm */ +#define AUDIT_CFG_LSM_SECCTX_SUBJECT BIT(0) +#define AUDIT_CFG_LSM_SECCTX_OBJECT BIT(1) + struct filename; #define AUDIT_OFF 0 @@ -185,6 +191,8 @@ extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); +extern int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); +extern int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); @@ -210,6 +218,8 @@ extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); +extern void audit_cfg_lsm(const struct lsm_id *lsmid, int flags); + #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, @@ -245,6 +255,16 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } +static inline int audit_log_subj_ctx(struct audit_buffer *ab, + struct lsm_prop *prop) +{ + return 0; +} +static inline int audit_log_obj_ctx(struct audit_buffer *ab, + struct lsm_prop *prop) +{ + return 0; +} static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; @@ -269,6 +289,9 @@ static inline int audit_signal_info(int sig, struct task_struct *t) return 0; } +static inline void audit_cfg_lsm(const struct lsm_id *lsmid, int flags) +{ } + #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC @@ -527,7 +550,7 @@ static inline void audit_log_kern_module(const char *name) static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { - if (!audit_dummy_context()) + if (audit_enabled) __audit_fanotify(response, friar); } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 2ad261082bba..c5c9d89c73ed 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -152,6 +152,10 @@ struct bdi_writeback { struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ + struct work_struct switch_work; /* work used to perform inode switching + * to this wb */ + struct llist_head switch_wbs_ctxs; /* queued contexts for + * writeback switching */ union { struct work_struct release_work; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 9be2d50da09a..ea7898cc5903 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -267,7 +267,7 @@ static inline int parity8(u8 val) * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -static inline unsigned int __ffs64(u64 word) +static inline __attribute_const__ unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 066e5309bd45..dad5cb5b3812 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -199,7 +199,7 @@ struct gendisk { unsigned int zone_wplugs_hash_bits; atomic_t nr_zone_wplugs; spinlock_t zone_wplugs_lock; - struct mempool_s *zone_wplugs_pool; + struct mempool *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ diff --git a/include/linux/bnxt/hsi.h b/include/linux/bnxt/hsi.h index 549231703bce..47c34990cf23 100644 --- a/include/linux/bnxt/hsi.h +++ b/include/linux/bnxt/hsi.h @@ -276,6 +276,10 @@ struct cmd_nums { #define HWRM_REG_POWER_QUERY 0xe1UL #define HWRM_CORE_FREQUENCY_QUERY 0xe2UL #define HWRM_REG_POWER_HISTOGRAM 0xe3UL + #define HWRM_MONITOR_PAX_HISTOGRAM_START 0xe4UL + #define HWRM_MONITOR_PAX_HISTOGRAM_COLLECT 0xe5UL + #define HWRM_STAT_QUERY_ROCE_STATS 0xe6UL + #define HWRM_STAT_QUERY_ROCE_STATS_EXT 0xe7UL #define HWRM_WOL_FILTER_ALLOC 0xf0UL #define HWRM_WOL_FILTER_FREE 0xf1UL #define HWRM_WOL_FILTER_QCFG 0xf2UL @@ -407,9 +411,8 @@ struct cmd_nums { #define HWRM_FUNC_LAG_UPDATE 0x1b1UL #define HWRM_FUNC_LAG_FREE 0x1b2UL #define HWRM_FUNC_LAG_QCFG 0x1b3UL - #define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD 0x1c2UL - #define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE 0x1c3UL - #define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY 0x1c4UL + #define HWRM_FUNC_TTX_PACING_RATE_PROF_QUERY 0x1c3UL + #define HWRM_FUNC_TTX_PACING_RATE_QUERY 0x1c4UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -441,6 +444,7 @@ struct cmd_nums { #define HWRM_MFG_WRITE_CERT_NVM 0x21cUL #define HWRM_PORT_POE_CFG 0x230UL #define HWRM_PORT_POE_QCFG 0x231UL + #define HWRM_PORT_PHY_FDRSTAT 0x232UL #define HWRM_UDCC_QCAPS 0x258UL #define HWRM_UDCC_CFG 0x259UL #define HWRM_UDCC_QCFG 0x25aUL @@ -453,6 +457,8 @@ struct cmd_nums { #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x261UL #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x262UL #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x263UL + #define HWRM_QUEUE_ADPTV_QOS_RX_QCFG 0x264UL + #define HWRM_QUEUE_ADPTV_QOS_TX_QCFG 0x265UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -551,6 +557,8 @@ struct cmd_nums { #define HWRM_DBG_COREDUMP_CAPTURE 0xff2cUL #define HWRM_DBG_PTRACE 0xff2dUL #define HWRM_DBG_SIM_CABLE_STATE 0xff2eUL + #define HWRM_DBG_TOKEN_QUERY_AUTH_IDS 0xff2fUL + #define HWRM_DBG_TOKEN_CFG 0xff30UL #define HWRM_NVM_GET_VPD_FIELD_INFO 0xffeaUL #define HWRM_NVM_SET_VPD_FIELD_INFO 0xffebUL #define HWRM_NVM_DEFRAG 0xffecUL @@ -632,8 +640,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 3 -#define HWRM_VERSION_RSVD 97 -#define HWRM_VERSION_STR "1.10.3.97" +#define HWRM_VERSION_RSVD 133 +#define HWRM_VERSION_STR "1.10.3.133" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -688,6 +696,7 @@ struct hwrm_ver_get_output { #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED 0x4000UL #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE 0x8000UL #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE 0x10000UL + #define VER_GET_RESP_DEV_CAPS_CFG_DEBUG_TOKEN_SUPPORTED 0x20000UL u8 roce_fw_maj_8b; u8 roce_fw_min_8b; u8 roce_fw_bld_8b; @@ -872,7 +881,8 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE 0x4eUL #define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE 0x4fUL #define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP 0x50UL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x51UL + #define ASYNC_EVENT_CMPL_EVENT_ID_ADPTV_QOS 0x51UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x52UL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1344,7 +1354,8 @@ struct hwrm_async_event_cmpl_dbg_buf_producer { #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA2_TRACE 0x9UL #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP1_TRACE 0xaUL #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE 0xbUL - #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE + #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ERR_QPC_TRACE 0xcUL + #define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ERR_QPC_TRACE }; /* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */ @@ -1401,7 +1412,11 @@ struct hwrm_async_event_cmpl_error_report_base { #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD 0x5UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED 0x6UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUP_UDCC_SES 0x7UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DB_DROP 0x8UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MD_TEMP 0x9UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_VNIC_ERR 0xaUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_VNIC_ERR }; /* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */ @@ -1914,6 +1929,12 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED 0x8UL #define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED 0x10UL #define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED 0x20UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_ROCE_VF_DYN_ALLOC_SUPPORT 0x40UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_CHANGE_UDP_SRCPORT_SUPPORT 0x80UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_PCIE_COMPLIANCE_SUPPORTED 0x100UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_MULTI_L2_DB_SUPPORTED 0x200UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_PCIE_SECURE_ATS_SUPPORTED 0x400UL + #define FUNC_QCAPS_RESP_FLAGS_EXT3_MBUF_STATS_SUPPORTED 0x800UL __le16 max_roce_vfs; __le16 max_crypto_rx_flow_filters; u8 unused_3[3]; @@ -1931,7 +1952,7 @@ struct hwrm_func_qcfg_input { u8 unused_0[6]; }; -/* hwrm_func_qcfg_output (size:1344b/168B) */ +/* hwrm_func_qcfg_output (size:1408b/176B) */ struct hwrm_func_qcfg_output { __le16 error_code; __le16 req_type; @@ -2124,7 +2145,43 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK 0x1UL #define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK 0x2UL __le16 mirror_vnic_id; - u8 unused_7[7]; + u8 max_link_width; + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_UNKNOWN 0x0UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X1 0x1UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X2 0x2UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X4 0x4UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X8 0x8UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X16 0x10UL + #define FUNC_QCFG_RESP_MAX_LINK_WIDTH_LAST FUNC_QCFG_RESP_MAX_LINK_WIDTH_X16 + u8 max_link_speed; + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_UNKNOWN 0x0UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_G1 0x1UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_G2 0x2UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_G3 0x3UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_G4 0x4UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_G5 0x5UL + #define FUNC_QCFG_RESP_MAX_LINK_SPEED_LAST FUNC_QCFG_RESP_MAX_LINK_SPEED_G5 + u8 negotiated_link_width; + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_UNKNOWN 0x0UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X1 0x1UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X2 0x2UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X4 0x4UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X8 0x8UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X16 0x10UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_LAST FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X16 + u8 negotiated_link_speed; + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_UNKNOWN 0x0UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G1 0x1UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G2 0x2UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G3 0x3UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G4 0x4UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G5 0x5UL + #define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_LAST FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G5 + u8 unused_7[2]; + u8 pcie_compliance; + u8 unused_8; + __le16 l2_db_multi_page_size_kb; + u8 unused_9[5]; u8 valid; }; @@ -2322,6 +2379,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF 0x200UL #define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG 0x400UL #define FUNC_CFG_REQ_ENABLES2_PHYSICAL_SLOT_NUMBER 0x800UL + #define FUNC_CFG_REQ_ENABLES2_PCIE_COMPLIANCE 0x1000UL u8 port_kdnet_mode; #define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL #define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED 0x1UL @@ -2353,7 +2411,8 @@ struct hwrm_func_cfg_input { __le16 xid_partition_cfg; #define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK 0x1UL #define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK 0x2UL - __le16 unused_2; + u8 pcie_compliance; + u8 unused_2; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -2370,11 +2429,41 @@ struct hwrm_func_cfg_output { struct hwrm_func_cfg_cmd_err { u8 code; #define FUNC_CFG_CMD_ERR_CODE_UNKNOWN 0x0UL - #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_RANGE 0x1UL - #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_MORE_THAN_MAX 0x2UL - #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_UNSUPPORTED 0x3UL - #define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT 0x4UL - #define FUNC_CFG_CMD_ERR_CODE_LAST FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT + #define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_OUT_OF_RANGE 0x1UL + #define FUNC_CFG_CMD_ERR_CODE_NPAR_PARTITION_DOWN_FAILED 0x2UL + #define FUNC_CFG_CMD_ERR_CODE_TPID_SET_DFLT_VLAN_NOT_SET 0x3UL + #define FUNC_CFG_CMD_ERR_CODE_RES_ARRAY_ALLOC_FAILED 0x4UL + #define FUNC_CFG_CMD_ERR_CODE_TX_RING_ASSET_TEST_FAILED 0x5UL + #define FUNC_CFG_CMD_ERR_CODE_TX_RING_RES_UPDATE_FAILED 0x6UL + #define FUNC_CFG_CMD_ERR_CODE_APPLY_MAX_BW_FAILED 0x7UL + #define FUNC_CFG_CMD_ERR_CODE_ENABLE_EVB_FAILED 0x8UL + #define FUNC_CFG_CMD_ERR_CODE_RSS_CTXT_ASSET_TEST_FAILED 0x9UL + #define FUNC_CFG_CMD_ERR_CODE_RSS_CTXT_RES_UPDATE_FAILED 0xaUL + #define FUNC_CFG_CMD_ERR_CODE_CMPL_RING_ASSET_TEST_FAILED 0xbUL + #define FUNC_CFG_CMD_ERR_CODE_CMPL_RING_RES_UPDATE_FAILED 0xcUL + #define FUNC_CFG_CMD_ERR_CODE_NQ_ASSET_TEST_FAILED 0xdUL + #define FUNC_CFG_CMD_ERR_CODE_NQ_RES_UPDATE_FAILED 0xeUL + #define FUNC_CFG_CMD_ERR_CODE_RX_RING_ASSET_TEST_FAILED 0xfUL + #define FUNC_CFG_CMD_ERR_CODE_RX_RING_RES_UPDATE_FAILED 0x10UL + #define FUNC_CFG_CMD_ERR_CODE_VNIC_ASSET_TEST_FAILED 0x11UL + #define FUNC_CFG_CMD_ERR_CODE_VNIC_RES_UPDATE_FAILED 0x12UL + #define FUNC_CFG_CMD_ERR_CODE_FAILED_TO_START_STATS_THREAD 0x13UL + #define FUNC_CFG_CMD_ERR_CODE_RDMA_SRIOV_DISABLED 0x14UL + #define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_DISABLED 0x15UL + #define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_ASSET_TEST_FAILED 0x16UL + #define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_RES_UPDATE_FAILED 0x17UL + #define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_DISABLED 0x18UL + #define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_ASSET_TEST_FAILED 0x19UL + #define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_RES_UPDATE_FAILED 0x1aUL + #define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_DISABLED 0x1bUL + #define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_ASSET_TEST_FAILED 0x1cUL + #define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_RES_UPDATE_FAILED 0x1dUL + #define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_DISABLED 0x1eUL + #define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_ASSET_TEST_FAILED 0x1fUL + #define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_RES_UPDATE_FAILED 0x20UL + #define FUNC_CFG_CMD_ERR_CODE_INVALID_KDNET_MODE 0x21UL + #define FUNC_CFG_CMD_ERR_CODE_SCHQ_CFG_FAIL 0x22UL + #define FUNC_CFG_CMD_ERR_CODE_LAST FUNC_CFG_CMD_ERR_CODE_SCHQ_CFG_FAIL u8 unused_0[7]; }; @@ -3780,6 +3869,7 @@ struct hwrm_func_backing_store_cfg_v2_input { #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE 0x28UL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ERR_QPC_TRACE 0x2bUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID __le16 instance; @@ -3865,6 +3955,7 @@ struct hwrm_func_backing_store_qcfg_v2_input { #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE 0x28UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ERR_QPC_TRACE 0x2bUL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID __le16 instance; @@ -3904,6 +3995,7 @@ struct hwrm_func_backing_store_qcfg_v2_output { #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE 0x27UL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE 0x28UL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ERR_QPC_TRACE 0x2aUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID __le16 instance; @@ -4027,6 +4119,7 @@ struct hwrm_func_backing_store_qcaps_v2_input { #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE 0x28UL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ERR_QPC_TRACE 0x2bUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID u8 rsvd[6]; @@ -4070,6 +4163,7 @@ struct hwrm_func_backing_store_qcaps_v2_output { #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE 0x28UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ERR_QPC_TRACE 0x2bUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID __le16 entry_size; @@ -4216,6 +4310,10 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE 0x100000UL #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE 0x200000UL #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE 0x400000UL + #define PORT_PHY_CFG_REQ_FLAGS_LINK_TRAINING_ENABLE 0x800000UL + #define PORT_PHY_CFG_REQ_FLAGS_LINK_TRAINING_DISABLE 0x1000000UL + #define PORT_PHY_CFG_REQ_FLAGS_PRECODING_ENABLE 0x2000000UL + #define PORT_PHY_CFG_REQ_FLAGS_PRECODING_DISABLE 0x4000000UL __le32 enables; #define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE 0x1UL #define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX 0x2UL @@ -4703,6 +4801,8 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT 0x1UL #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN 0x2UL #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED 0x4UL + #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_LINK_TRAINING 0x8UL + #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_PRECODING 0x10UL char phy_vendor_name[16]; char phy_vendor_partnumber[16]; __le16 support_pam4_speeds; @@ -4725,6 +4825,10 @@ struct hwrm_port_phy_qcfg_output { u8 link_down_reason; #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF 0x1UL #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_OTP_SPEED_VIOLATION 0x2UL + #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_CABLE_REMOVED 0x4UL + #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_MODULE_FAULT 0x8UL + #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_BMC_REQUEST 0x10UL + #define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_TX_LASER_DISABLED 0x20UL __le16 support_speeds2; #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB 0x1UL #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB 0x2UL @@ -5882,9 +5986,10 @@ struct hwrm_port_led_qcaps_output { #define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_SUPPORTED 0x8UL #define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_ALT_SUPPORTED 0x10UL __le16 led0_color_caps; - #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD 0x1UL - #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED 0x2UL - #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD 0x1UL + #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED 0x2UL + #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GRNAMB_SUPPORTED 0x8UL u8 led1_id; u8 led1_type; #define PORT_LED_QCAPS_RESP_LED1_TYPE_SPEED 0x0UL @@ -5900,9 +6005,10 @@ struct hwrm_port_led_qcaps_output { #define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_SUPPORTED 0x8UL #define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_ALT_SUPPORTED 0x10UL __le16 led1_color_caps; - #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD 0x1UL - #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED 0x2UL - #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD 0x1UL + #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED 0x2UL + #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GRNAMB_SUPPORTED 0x8UL u8 led2_id; u8 led2_type; #define PORT_LED_QCAPS_RESP_LED2_TYPE_SPEED 0x0UL @@ -5918,9 +6024,10 @@ struct hwrm_port_led_qcaps_output { #define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_SUPPORTED 0x8UL #define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_ALT_SUPPORTED 0x10UL __le16 led2_color_caps; - #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD 0x1UL - #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED 0x2UL - #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD 0x1UL + #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED 0x2UL + #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GRNAMB_SUPPORTED 0x8UL u8 led3_id; u8 led3_type; #define PORT_LED_QCAPS_RESP_LED3_TYPE_SPEED 0x0UL @@ -5936,9 +6043,10 @@ struct hwrm_port_led_qcaps_output { #define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_SUPPORTED 0x8UL #define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_ALT_SUPPORTED 0x10UL __le16 led3_color_caps; - #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD 0x1UL - #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED 0x2UL - #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD 0x1UL + #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED 0x2UL + #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED 0x4UL + #define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GRNAMB_SUPPORTED 0x8UL u8 unused_4[3]; u8 valid; }; @@ -6643,6 +6751,67 @@ struct hwrm_queue_dscp2pri_cfg_output { u8 valid; }; +/* hwrm_queue_pfcwd_timeout_qcaps_input (size:128b/16B) */ +struct hwrm_queue_pfcwd_timeout_qcaps_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* hwrm_queue_pfcwd_timeout_qcaps_output (size:128b/16B) */ +struct hwrm_queue_pfcwd_timeout_qcaps_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 max_pfcwd_timeout; + u8 unused_0[5]; + u8 valid; +}; + +/* hwrm_queue_pfcwd_timeout_cfg_input (size:192b/24B) */ +struct hwrm_queue_pfcwd_timeout_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 pfcwd_timeout_value; + u8 unused_0[6]; +}; + +/* hwrm_queue_pfcwd_timeout_cfg_output (size:128b/16B) */ +struct hwrm_queue_pfcwd_timeout_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_queue_pfcwd_timeout_qcfg_input (size:128b/16B) */ +struct hwrm_queue_pfcwd_timeout_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* hwrm_queue_pfcwd_timeout_qcfg_output (size:128b/16B) */ +struct hwrm_queue_pfcwd_timeout_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 pfcwd_timeout_value; + u8 unused_0[5]; + u8 valid; +}; + /* hwrm_vnic_alloc_input (size:192b/24B) */ struct hwrm_vnic_alloc_input { __le16 req_type; @@ -7036,9 +7205,22 @@ struct hwrm_vnic_rss_cfg_output { /* hwrm_vnic_rss_cfg_cmd_err (size:64b/8B) */ struct hwrm_vnic_rss_cfg_cmd_err { u8 code; - #define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN 0x0UL - #define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY 0x1UL - #define VNIC_RSS_CFG_CMD_ERR_CODE_LAST VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY + #define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN 0x0UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY 0x1UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_UNABLE_TO_GET_RSS_CFG 0x2UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_TYPE_UNSUPPORTED 0x3UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_TYPE_ERR 0x4UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_MODE_FAIL 0x5UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_RING_GRP_TABLE_ALLOC_ERR 0x6UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_KEY_ALLOC_ERR 0x7UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_DMA_FAILED 0x8UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_RX_RING_ALLOC_ERR 0x9UL + #define VNIC_RSS_CFG_CMD_ERR_CODE_CMPL_RING_ALLOC_ERR 0xaUL + #define VNIC_RSS_CFG_CMD_ERR_CODE_HW_SET_RSS_FAILED 0xbUL + #define VNIC_RSS_CFG_CMD_ERR_CODE_CTX_INVALID 0xcUL + #define VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_INVALID 0xdUL + #define VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_RING_TABLE_PAIR_INVALID 0xeUL + #define VNIC_RSS_CFG_CMD_ERR_CODE_LAST VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_RING_TABLE_PAIR_INVALID u8 unused_0[7]; }; @@ -7177,7 +7359,7 @@ struct hwrm_vnic_rss_cos_lb_ctx_free_output { u8 valid; }; -/* hwrm_ring_alloc_input (size:704b/88B) */ +/* hwrm_ring_alloc_input (size:768b/96B) */ struct hwrm_ring_alloc_input { __le16 req_type; __le16 cmpl_ring; @@ -7195,6 +7377,7 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE 0x400UL #define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID 0x800UL #define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID 0x1000UL + #define RING_ALLOC_REQ_ENABLES_DPI_VALID 0x2000UL u8 ring_type; #define RING_ALLOC_REQ_RING_TYPE_L2_CMPL 0x0UL #define RING_ALLOC_REQ_RING_TYPE_TX 0x1UL @@ -7287,6 +7470,8 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE u8 unused_4; __le64 cq_handle; + __le16 dpi; + __le16 unused_5[3]; }; /* hwrm_ring_alloc_output (size:128b/16B) */ @@ -7776,7 +7961,10 @@ struct hwrm_cfa_l2_set_rx_mask_cmd_err { u8 code; #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN 0x0UL #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL - #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR + #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_MAX_VLAN_TAGS 0x2UL + #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_VNIC_ID 0x3UL + #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_ACTION 0x4UL + #define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_ACTION u8 unused_0[7]; }; @@ -8109,9 +8297,38 @@ struct hwrm_cfa_ntuple_filter_alloc_output { /* hwrm_cfa_ntuple_filter_alloc_cmd_err (size:64b/8B) */ struct hwrm_cfa_ntuple_filter_alloc_cmd_err { u8 code; - #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN 0x0UL - #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL - #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN 0x0UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ZERO_MAC 0x65UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_BC_MC_MAC 0x66UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_VNIC 0x67UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_PF_FID 0x68UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_L2_CTXT_ID 0x69UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_NULL_L2_CTXT_CFG 0x6aUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_NULL_L2_DATA_FLD 0x6bUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_CFA_LAYOUT 0x6cUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_CTXT_ALLOC_FAIL 0x6dUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ROCE_FLOW_ERR 0x6eUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_OWNER_FID 0x6fUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ZERO_REF_CNT 0x70UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_FLOW_TYPE 0x71UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_IVLAN 0x72UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_MAX_VLAN_ID 0x73UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_TNL_REQ 0x74UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_ADDR 0x75UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_IVLAN 0x76UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L3_ADDR 0x77UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L3_ADDR_TYPE 0x78UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_T_L3_ADDR_TYPE 0x79UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_DST_VNIC_ID 0x7aUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VNI 0x7bUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_DST_ID 0x7cUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_FAIL_ROCE_L2_FLOW 0x7dUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_NPAR_VLAN 0x7eUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ATSP_ADD 0x7fUL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_DFLT_VLAN_FAIL 0x80UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_L3_TYPE 0x81UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VAL_FAIL_TNL_FLOW 0x82UL + #define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VAL_FAIL_TNL_FLOW u8 unused_0[7]; }; @@ -9181,7 +9398,7 @@ struct pcie_ctx_hw_stats { __le64 pcie_recovery_histogram; }; -/* pcie_ctx_hw_stats_v2 (size:4096b/512B) */ +/* pcie_ctx_hw_stats_v2 (size:4544b/568B) */ struct pcie_ctx_hw_stats_v2 { __le64 pcie_pl_signal_integrity; __le64 pcie_dl_signal_integrity; @@ -9212,6 +9429,9 @@ struct pcie_ctx_hw_stats_v2 { __le64 pcie_other_packet_count; __le64 pcie_blocked_packet_count; __le64 pcie_cmpl_packet_count; + __le32 pcie_rd_latency_histogram[12]; + __le32 pcie_rd_latency_all_normal_count; + __le32 unused_2; }; /* hwrm_stat_generic_qstats_input (size:256b/32B) */ @@ -9406,7 +9626,8 @@ struct hwrm_struct_hdr { #define STRUCT_HDR_STRUCT_ID_MSIX_PER_VF 0xc8UL #define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_COUNT 0x12cUL #define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND 0x12dUL - #define STRUCT_HDR_STRUCT_ID_LAST STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND + #define STRUCT_HDR_STRUCT_ID_DBG_TOKEN_CLAIMS 0x190UL + #define STRUCT_HDR_STRUCT_ID_LAST STRUCT_HDR_STRUCT_ID_DBG_TOKEN_CLAIMS __le16 len; u8 version; #define STRUCT_HDR_VERSION_0 0x0UL @@ -9459,11 +9680,13 @@ struct hwrm_fw_set_structured_data_output { /* hwrm_fw_set_structured_data_cmd_err (size:64b/8B) */ struct hwrm_fw_set_structured_data_cmd_err { u8 code; - #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL - #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL - #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT 0x2UL - #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID 0x3UL - #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT 0x2UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID 0x3UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_ALREADY_ADDED 0x4UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_INST_IN_PROG 0x5UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_INST_IN_PROG u8 unused_0[7]; }; @@ -9487,7 +9710,9 @@ struct hwrm_fw_get_structured_data_input { #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER 0x201UL #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL 0x202UL #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL 0x300UL - #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL + #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_SUPPORTED 0x320UL + #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_ACTIVE 0x321UL + #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_ACTIVE u8 count; u8 unused_0; }; @@ -10172,7 +10397,8 @@ struct hwrm_dbg_log_buffer_flush_input { #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE 0x9UL #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE 0xaUL #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE 0xbUL - #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE + #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE 0xcUL + #define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE u8 unused_1[2]; __le32 flags; #define DBG_LOG_BUFFER_FLUSH_REQ_FLAGS_FLUSH_ALL_BUFFERS 0x1UL @@ -10295,10 +10521,15 @@ struct hwrm_nvm_write_output { /* hwrm_nvm_write_cmd_err (size:64b/8B) */ struct hwrm_nvm_write_cmd_err { u8 code; - #define NVM_WRITE_CMD_ERR_CODE_UNKNOWN 0x0UL - #define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL - #define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL - #define NVM_WRITE_CMD_ERR_CODE_LAST NVM_WRITE_CMD_ERR_CODE_NO_SPACE + #define NVM_WRITE_CMD_ERR_CODE_UNKNOWN 0x0UL + #define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL + #define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL + #define NVM_WRITE_CMD_ERR_CODE_WRITE_FAILED 0x3UL + #define NVM_WRITE_CMD_ERR_CODE_REQD_ERASE_FAILED 0x4UL + #define NVM_WRITE_CMD_ERR_CODE_VERIFY_FAILED 0x5UL + #define NVM_WRITE_CMD_ERR_CODE_INVALID_HEADER 0x6UL + #define NVM_WRITE_CMD_ERR_CODE_UPDATE_DIGEST_FAILED 0x7UL + #define NVM_WRITE_CMD_ERR_CODE_LAST NVM_WRITE_CMD_ERR_CODE_UPDATE_DIGEST_FAILED u8 unused_0[7]; }; @@ -10438,7 +10669,11 @@ struct hwrm_nvm_get_dev_info_output { __le16 srt2_fw_minor; __le16 srt2_fw_build; __le16 srt2_fw_patch; - u8 unused_0[7]; + u8 security_soc_fw_major; + u8 security_soc_fw_minor; + u8 security_soc_fw_build; + u8 security_soc_fw_patch; + u8 unused_0[3]; u8 valid; }; @@ -10568,7 +10803,9 @@ struct hwrm_nvm_install_update_cmd_err { #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE 0x2UL #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK 0x3UL #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT 0x4UL - #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_DEFRAG_FAILED 0x5UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN_DIR_ERR 0x6UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN_DIR_ERR u8 unused_0[7]; }; @@ -10591,7 +10828,8 @@ struct hwrm_nvm_get_variable_input { __le16 index_2; __le16 index_3; u8 flags; - #define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT 0x1UL + #define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT 0x1UL + #define NVM_GET_VARIABLE_REQ_FLAGS_VALIDATE_OPT_VALUE 0x2UL u8 unused_0; }; @@ -10606,18 +10844,25 @@ struct hwrm_nvm_get_variable_output { #define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0 0x0UL #define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL #define NVM_GET_VARIABLE_RESP_OPTION_NUM_LAST NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF - u8 unused_0[3]; + u8 flags; + #define NVM_GET_VARIABLE_RESP_FLAGS_VALIDATE_OPT_VALUE 0x1UL + u8 unused_0[2]; u8 valid; }; /* hwrm_nvm_get_variable_cmd_err (size:64b/8B) */ struct hwrm_nvm_get_variable_cmd_err { u8 code; - #define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL - #define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL - #define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL - #define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL - #define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT + #define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_INDEX_INVALID 0x4UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_ACCESS_DENIED 0x5UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_CB_FAILED 0x6UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_INVALID_DATA_LEN 0x7UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_NO_MEM 0x8UL + #define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST NVM_GET_VARIABLE_CMD_ERR_CODE_NO_MEM u8 unused_0[7]; }; @@ -10667,10 +10912,17 @@ struct hwrm_nvm_set_variable_output { /* hwrm_nvm_set_variable_cmd_err (size:64b/8B) */ struct hwrm_nvm_set_variable_cmd_err { u8 code; - #define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL - #define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL - #define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL - #define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR + #define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN 0x0UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR 0x2UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_ACTION_NOT_SUPPORTED 0x4UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_INDEX_INVALID 0x5UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_ACCESS_DENIED 0x6UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_CB_FAILED 0x7UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_INVALID_DATA_LEN 0x8UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_NO_MEM 0x9UL + #define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST NVM_SET_VARIABLE_CMD_ERR_CODE_NO_MEM u8 unused_0[7]; }; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cc700925b802..a98c83346134 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -7,6 +7,7 @@ #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> +#include <crypto/sha2.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> @@ -109,6 +110,7 @@ struct bpf_map_ops { long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); + int (*map_get_hash)(struct bpf_map *map, u32 hash_buf_size, void *hash_buf); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -206,6 +208,7 @@ enum btf_field_type { BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), BPF_RES_SPIN_LOCK = (1 << 12), + BPF_TASK_WORK = (1 << 13), }; enum bpf_cgroup_storage_type { @@ -259,6 +262,7 @@ struct btf_record { int timer_off; int wq_off; int refcount_off; + int task_work_off; struct btf_field fields[]; }; @@ -285,9 +289,11 @@ struct bpf_map_owner { bool xdp_has_frags; u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE]; const struct btf_type *attach_func_proto; + enum bpf_attach_type expected_attach_type; }; struct bpf_map { + u8 sha[SHA256_DIGEST_SIZE]; const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY @@ -328,6 +334,7 @@ struct bpf_map { atomic64_t sleepable_refcnt; s64 __percpu *elem_count; u64 cookie; /* write-once */ + char *excl_prog_sha; }; static inline const char *btf_field_type_name(enum btf_field_type type) @@ -358,6 +365,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; + case BPF_TASK_WORK: + return "bpf_task_work"; default: WARN_ON_ONCE(1); return "unknown"; @@ -396,6 +405,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); + case BPF_TASK_WORK: + return sizeof(struct bpf_task_work); default: WARN_ON_ONCE(1); return 0; @@ -428,6 +439,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); + case BPF_TASK_WORK: + return __alignof__(struct bpf_task_work); default: WARN_ON_ONCE(1); return 0; @@ -459,6 +472,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: + case BPF_TASK_WORK: break; default: WARN_ON_ONCE(1); @@ -595,6 +609,7 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); void bpf_wq_cancel_and_free(void *timer); +void bpf_task_work_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -767,12 +782,15 @@ enum bpf_type_flag { */ MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to skb_metadata_end()-skb_metadata_len() */ + DYNPTR_TYPE_SKB_META = BIT(19 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ - | DYNPTR_TYPE_XDP) + | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -1110,7 +1128,7 @@ struct bpf_prog_offload { */ #define MAX_BPF_FUNC_REG_ARGS 5 -/* The argument is a structure. */ +/* The argument is a structure or a union. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) /* The argument is signed. */ @@ -1358,6 +1376,8 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, + /* Points to skb_metadata_end()-skb_metadata_len() */ + BPF_DYNPTR_TYPE_SKB_META, }; int bpf_dynptr_check_size(u32 size); @@ -1619,6 +1639,7 @@ struct bpf_prog_aux { bool priv_stack_requested; bool changes_pkt_data; bool might_sleep; + bool kprobe_write_ctx; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; @@ -1628,6 +1649,7 @@ struct bpf_prog_aux { /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; + struct bpf_prog_aux *main_prog_aux; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; @@ -1711,7 +1733,10 @@ struct bpf_prog { enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ - u8 tag[BPF_TAG_SIZE]; + union { + u8 digest[SHA256_DIGEST_SIZE]; + u8 tag[BPF_TAG_SIZE]; + }; struct bpf_prog_stats __percpu *stats; int __percpu *active; unsigned int (*bpf_func)(const void *ctx, @@ -1985,6 +2010,7 @@ static inline void bpf_module_put(const void *data, struct module *owner) module_put(owner); } int bpf_struct_ops_link_create(union bpf_attr *attr); +u32 bpf_struct_ops_id(const void *kdata); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ @@ -2411,6 +2437,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); +void bpf_obj_free_task_work(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); @@ -2697,7 +2724,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); -int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); +int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); @@ -2874,6 +2901,7 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); +void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) @@ -3161,6 +3189,11 @@ static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) { } + +static inline void bpf_prog_report_arena_violation(bool write, unsigned long addr, + unsigned long fault_ip) +{ +} #endif /* CONFIG_BPF_SYSCALL */ static __always_inline int @@ -3403,6 +3436,38 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ +#if defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) + +struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags); +struct bpf_key *bpf_lookup_system_key(u64 id); +void bpf_key_put(struct bpf_key *bkey); +int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, + struct bpf_dynptr *sig_p, + struct bpf_key *trusted_keyring); + +#else +static inline struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) +{ + return NULL; +} + +static inline struct bpf_key *bpf_lookup_system_key(u64 id) +{ + return NULL; +} + +static inline void bpf_key_put(struct bpf_key *bkey) +{ +} + +static inline int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, + struct bpf_dynptr *sig_p, + struct bpf_key *trusted_keyring) +{ + return -EOPNOTSUPP; +} +#endif /* defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) */ + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 94defa405c85..4c497e839526 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -26,28 +26,6 @@ /* Patch buffer size */ #define INSN_BUF_SIZE 32 -/* Liveness marks, used for registers and spilled-regs (in stack slots). - * Read marks propagate upwards until they find a write mark; they record that - * "one of this state's descendants read this reg" (and therefore the reg is - * relevant for states_equal() checks). - * Write marks collect downwards and do not propagate; they record that "the - * straight-line code that reached this state (from its parent) wrote this reg" - * (and therefore that reads propagated from this state or its descendants - * should not propagate to its parent). - * A state with a write mark can receive read marks; it just won't propagate - * them to its parent, since the write mark is a property, not of the state, - * but of the link between it and its parent. See mark_reg_read() and - * mark_stack_slot_read() in kernel/bpf/verifier.c. - */ -enum bpf_reg_liveness { - REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ - REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */ - REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */ - REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64, - REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */ - REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ -}; - #define ITER_PREFIX "bpf_iter_" enum bpf_iter_state { @@ -212,8 +190,6 @@ struct bpf_reg_state { * allowed and has the same effect as bpf_sk_release(sk). */ u32 ref_obj_id; - /* parentage chain for liveness checking */ - struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' @@ -226,7 +202,6 @@ struct bpf_reg_state { * patching which only happens after main verification finished. */ s32 subreg_def; - enum bpf_reg_liveness live; /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ bool precise; }; @@ -445,6 +420,7 @@ struct bpf_verifier_state { bool speculative; bool in_sleepable; + bool cleaned; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -665,6 +641,7 @@ struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ + u32 postorder_start; /* The idx to the env->cfg.insn_postorder */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; /* offsets in range [stack_depth .. fastcall_stack_off) @@ -744,6 +721,8 @@ struct bpf_scc_info { struct bpf_scc_visit visits[]; }; +struct bpf_liveness; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -794,7 +773,10 @@ struct bpf_verifier_env { struct { int *insn_state; int *insn_stack; - /* vector of instruction indexes sorted in post-order */ + /* + * vector of instruction indexes sorted in post-order, grouped by subprogram, + * see bpf_subprog_info->postorder_start. + */ int *insn_postorder; int cur_stack; /* current position in the insn_postorder vector */ @@ -842,6 +824,7 @@ struct bpf_verifier_env { struct bpf_insn insn_buf[INSN_BUF_SIZE]; struct bpf_insn epilogue_buf[INSN_BUF_SIZE]; struct bpf_scc_callchain callchain_buf; + struct bpf_liveness *liveness; /* array of pointers to bpf_scc_info indexed by SCC id */ struct bpf_scc_info **scc_info; u32 scc_cnt; @@ -875,13 +858,15 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, #define verifier_bug_if(cond, env, fmt, args...) \ ({ \ bool __cond = (cond); \ - if (unlikely(__cond)) { \ - BPF_WARN_ONCE(1, "verifier bug: " fmt "(" #cond ")\n", ##args); \ - bpf_log(&env->log, "verifier bug: " fmt "(" #cond ")\n", ##args); \ - } \ + if (unlikely(__cond)) \ + verifier_bug(env, fmt " (" #cond ")", ##args); \ (__cond); \ }) -#define verifier_bug(env, fmt, args...) verifier_bug_if(1, env, fmt, ##args) +#define verifier_bug(env, fmt, args...) \ + ({ \ + BPF_WARN_ONCE(1, "verifier bug: " fmt "\n", ##args); \ + bpf_log(&env->log, "verifier bug: " fmt "\n", ##args); \ + }) static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { @@ -962,6 +947,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) case BPF_PROG_TYPE_STRUCT_OPS: return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_SYSCALL: return false; default: return true; @@ -1062,4 +1048,21 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifie void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno); +struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off); +int bpf_jmp_offset(struct bpf_insn *insn); +int bpf_insn_successors(struct bpf_prog *prog, u32 idx, u32 succ[2]); +void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask); +bool bpf_calls_callback(struct bpf_verifier_env *env, int insn_idx); + +int bpf_stack_liveness_init(struct bpf_verifier_env *env); +void bpf_stack_liveness_free(struct bpf_verifier_env *env); +int bpf_update_live_stack(struct bpf_verifier_env *env); +int bpf_mark_stack_read(struct bpf_verifier_env *env, u32 frameno, u32 insn_idx, u64 mask); +void bpf_mark_stack_write(struct bpf_verifier_env *env, u32 frameno, u64 mask); +int bpf_reset_stack_write_marks(struct bpf_verifier_env *env, u32 insn_idx); +int bpf_commit_stack_write_marks(struct bpf_verifier_env *env); +int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st); +bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 spi); +void bpf_reset_live_stack_callchain(struct bpf_verifier_env *env); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 1af241525a17..f6e0795db484 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -67,7 +67,7 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { - void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); + void *p = kvmalloc_node_align_noprof(len, 1, GFP_USER | __GFP_NOWARN, NUMA_NO_NODE); if (!p) return ERR_PTR(-ENOMEM); diff --git a/include/linux/btf.h b/include/linux/btf.h index 9eda6b113f9b..f06976ffb63f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -86,7 +86,7 @@ * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ -#define __bpf_kfunc __used __retain noinline +#define __bpf_kfunc __used __retain __noclone noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 0a80e1f9aa20..3fc0efa0825b 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -22,11 +22,8 @@ struct page; * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * - * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: - * - * nth_page(@bv_page, n) == @bv_page + n - * - * This holds because page_is_mergeable() checks the above property. + * All pages within a bio_vec starting from @bv_page are contiguous and + * can simply be iterated (see bvec_advance()). */ struct bio_vec { struct page *bv_page; diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 5dfdbb63b1d5..d30816dd93c7 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -16,6 +16,10 @@ #define CAN_CTRLMODE_FD_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) +#define CAN_CTRLMODE_TDC_AUTO_MASK \ + (CAN_CTRLMODE_TDC_AUTO) +#define CAN_CTRLMODE_TDC_MANUAL_MASK \ + (CAN_CTRLMODE_TDC_MANUAL) /* * struct can_tdc - CAN FD Transmission Delay Compensation parameters @@ -114,13 +118,24 @@ struct can_tdc_const { u32 tdcf_max; }; +struct data_bittiming_params { + const struct can_bittiming_const *data_bittiming_const; + struct can_bittiming data_bittiming; + const struct can_tdc_const *tdc_const; + struct can_tdc tdc; + const u32 *data_bitrate_const; + unsigned int data_bitrate_const_cnt; + int (*do_set_data_bittiming)(struct net_device *dev); + int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); +}; + #ifdef CONFIG_CAN_CALC_BITTIMING int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, struct netlink_ext_ack *extack); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, const struct can_bittiming *dbt, - u32 *ctrlmode, u32 ctrlmode_supported); + u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, @@ -133,7 +148,7 @@ can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, static inline void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, const struct can_bittiming *dbt, - u32 *ctrlmode, u32 ctrlmode_supported) + u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported) { } #endif /* CONFIG_CAN_CALC_BITTIMING */ @@ -150,6 +165,35 @@ int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, struct netlink_ext_ack *extack); /* + * can_get_relative_tdco() - TDCO relative to the sample point + * + * struct can_tdc::tdco represents the absolute offset from TDCV. Some + * controllers use instead an offset relative to the Sample Point (SP) + * such that: + * + * SSP = TDCV + absolute TDCO + * = TDCV + SP + relative TDCO + * + * -+----------- one bit ----------+-- TX pin + * |<--- Sample Point --->| + * + * --+----------- one bit ----------+-- RX pin + * |<-------- TDCV -------->| + * |<------------------------>| absolute TDCO + * |<--- Sample Point --->| + * | |<->| relative TDCO + * |<------------- Secondary Sample Point ------------>| + */ +static inline s32 can_get_relative_tdco(const struct data_bittiming_params *dbt_params) +{ + const struct can_bittiming *dbt = &dbt_params->data_bittiming; + s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg + + dbt->phase_seg1) * dbt->brp; + + return (s32)dbt_params->tdc.tdco - sample_point_in_tc; +} + +/* * can_bit_time() - Duration of one bit * * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 9a92cbe5b2cb..a2229a61ccde 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -38,17 +38,6 @@ enum can_termination_gpio { CAN_TERMINATION_GPIO_MAX, }; -struct data_bittiming_params { - const struct can_bittiming_const *data_bittiming_const; - struct can_bittiming data_bittiming; - const struct can_tdc_const *tdc_const; - struct can_tdc tdc; - const u32 *data_bitrate_const; - unsigned int data_bitrate_const_cnt; - int (*do_set_data_bittiming)(struct net_device *dev); - int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); -}; - /* * CAN common private data */ @@ -96,56 +85,6 @@ static inline bool can_fd_tdc_is_enabled(const struct can_priv *priv) return !!(priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK); } -/* - * can_get_relative_tdco() - TDCO relative to the sample point - * - * struct can_tdc::tdco represents the absolute offset from TDCV. Some - * controllers use instead an offset relative to the Sample Point (SP) - * such that: - * - * SSP = TDCV + absolute TDCO - * = TDCV + SP + relative TDCO - * - * -+----------- one bit ----------+-- TX pin - * |<--- Sample Point --->| - * - * --+----------- one bit ----------+-- RX pin - * |<-------- TDCV -------->| - * |<------------------------>| absolute TDCO - * |<--- Sample Point --->| - * | |<->| relative TDCO - * |<------------- Secondary Sample Point ------------>| - */ -static inline s32 can_get_relative_tdco(const struct can_priv *priv) -{ - const struct can_bittiming *dbt = &priv->fd.data_bittiming; - s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg + - dbt->phase_seg1) * dbt->brp; - - return (s32)priv->fd.tdc.tdco - sample_point_in_tc; -} - -/* helper to define static CAN controller features at device creation time */ -static inline int __must_check can_set_static_ctrlmode(struct net_device *dev, - u32 static_mode) -{ - struct can_priv *priv = netdev_priv(dev); - - /* alloc_candev() succeeded => netdev_priv() is valid at this point */ - if (priv->ctrlmode_supported & static_mode) { - netdev_warn(dev, - "Controller features can not be supported and static at the same time\n"); - return -EINVAL; - } - priv->ctrlmode = static_mode; - - /* override MTU which was set by default in can_setup()? */ - if (static_mode & CAN_CTRLMODE_FD) - dev->mtu = CANFD_MTU; - - return 0; -} - static inline u32 can_get_static_ctrlmode(struct can_priv *priv) { return priv->ctrlmode & ~priv->ctrlmode_supported; @@ -187,7 +126,10 @@ struct can_priv *safe_candev_priv(struct net_device *dev); int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); +void can_set_default_mtu(struct net_device *dev); int can_change_mtu(struct net_device *dev, int new_mtu); +int __must_check can_set_static_ctrlmode(struct net_device *dev, + u32 static_mode); int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd); int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, struct kernel_ethtool_ts_info *info); @@ -199,6 +141,8 @@ int can_restart_now(struct net_device *dev); void can_bus_off(struct net_device *dev); const char *can_get_state_str(const enum can_state state); +const char *can_get_ctrlmode_str(u32 ctrlmode); + void can_state_get_by_berr_counter(const struct net_device *dev, const struct can_berr_counter *bec, enum can_state *tx_state, diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h index f38772fd0c07..d3788a3d0942 100644 --- a/include/linux/can/dev/peak_canfd.h +++ b/include/linux/can/dev/peak_canfd.h @@ -2,8 +2,8 @@ /* * CAN driver for PEAK System micro-CAN based adapters * - * Copyright (C) 2003-2011 PEAK System-Technik GmbH - * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com> + * Copyright (C) 2003-2025 PEAK System-Technik GmbH + * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> */ #ifndef PUCAN_H #define PUCAN_H diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 0bf7d33a1048..7fcec025c5e0 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -96,6 +96,14 @@ enum cc_attr { * enabled to run SEV-SNP guests. */ CC_ATTR_HOST_SEV_SNP, + + /** + * @CC_ATTR_SNP_SECURE_AVIC: Secure AVIC mode is active. + * + * The host kernel is running with the necessary features enabled + * to run SEV-SNP guests with full Secure AVIC capabilities. + */ + CC_ATTR_SNP_SECURE_AVIC, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdx/bitfield.h b/include/linux/cdx/bitfield.h new file mode 100644 index 000000000000..567f8ec47582 --- /dev/null +++ b/include/linux/cdx/bitfield.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2013 Solarflare Communications Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef CDX_BITFIELD_H +#define CDX_BITFIELD_H + +#include <linux/bitfield.h> + +/* Lowest bit numbers and widths */ +#define CDX_DWORD_LBN 0 +#define CDX_DWORD_WIDTH 32 + +/* Specified attribute (e.g. LBN) of the specified field */ +#define CDX_VAL(field, attribute) field ## _ ## attribute +/* Low bit number of the specified field */ +#define CDX_LOW_BIT(field) CDX_VAL(field, LBN) +/* Bit width of the specified field */ +#define CDX_WIDTH(field) CDX_VAL(field, WIDTH) +/* High bit number of the specified field */ +#define CDX_HIGH_BIT(field) (CDX_LOW_BIT(field) + CDX_WIDTH(field) - 1) + +/* A doubleword (i.e. 4 byte) datatype - little-endian in HW */ +struct cdx_dword { + __le32 cdx_u32; +}; + +/* Value expanders for printk */ +#define CDX_DWORD_VAL(dword) \ + ((unsigned int)le32_to_cpu((dword).cdx_u32)) + +/* + * Extract bit field portion [low,high) from the 32-bit little-endian + * element which contains bits [min,max) + */ +#define CDX_DWORD_FIELD(dword, field) \ + (FIELD_GET(GENMASK(CDX_HIGH_BIT(field), CDX_LOW_BIT(field)), \ + le32_to_cpu((dword).cdx_u32))) + +/* + * Creates the portion of the named bit field that lies within the + * range [min,max). + */ +#define CDX_INSERT_FIELD(field, value) \ + (FIELD_PREP(GENMASK(CDX_HIGH_BIT(field), \ + CDX_LOW_BIT(field)), value)) + +/* + * Creates the portion of the named bit fields that lie within the + * range [min,max). + */ +#define CDX_INSERT_FIELDS(field1, value1, \ + field2, value2, \ + field3, value3, \ + field4, value4, \ + field5, value5, \ + field6, value6, \ + field7, value7) \ + (CDX_INSERT_FIELD(field1, (value1)) | \ + CDX_INSERT_FIELD(field2, (value2)) | \ + CDX_INSERT_FIELD(field3, (value3)) | \ + CDX_INSERT_FIELD(field4, (value4)) | \ + CDX_INSERT_FIELD(field5, (value5)) | \ + CDX_INSERT_FIELD(field6, (value6)) | \ + CDX_INSERT_FIELD(field7, (value7))) + +#define CDX_POPULATE_DWORD(dword, ...) \ + (dword).cdx_u32 = cpu_to_le32(CDX_INSERT_FIELDS(__VA_ARGS__)) + +/* Populate a dword field with various numbers of arguments */ +#define CDX_POPULATE_DWORD_7 CDX_POPULATE_DWORD +#define CDX_POPULATE_DWORD_6(dword, ...) \ + CDX_POPULATE_DWORD_7(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_5(dword, ...) \ + CDX_POPULATE_DWORD_6(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_4(dword, ...) \ + CDX_POPULATE_DWORD_5(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_3(dword, ...) \ + CDX_POPULATE_DWORD_4(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_2(dword, ...) \ + CDX_POPULATE_DWORD_3(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_1(dword, ...) \ + CDX_POPULATE_DWORD_2(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_SET_DWORD(dword) \ + CDX_POPULATE_DWORD_1(dword, CDX_DWORD, 0xffffffff) + +#endif /* CDX_BITFIELD_H */ diff --git a/include/linux/cdx/edac_cdx_pcol.h b/include/linux/cdx/edac_cdx_pcol.h new file mode 100644 index 000000000000..749db33bb482 --- /dev/null +++ b/include/linux/cdx/edac_cdx_pcol.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Driver for AMD network controllers and boards + * + * Copyright (C) 2021, Xilinx, Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef MC_CDX_PCOL_H +#define MC_CDX_PCOL_H +#include <linux/cdx/mcdi.h> + +#define MC_CMD_EDAC_GET_DDR_CONFIG_OUT_WORD_LENGTH_LEN 4 +/* Number of registers for the DDR controller */ +#define MC_CMD_GET_DDR_CONFIG_OFST 4 +#define MC_CMD_GET_DDR_CONFIG_LEN 4 + +/***********************************/ +/* MC_CMD_EDAC_GET_DDR_CONFIG + * Provides detailed configuration for the DDR controller of the given index. + */ +#define MC_CMD_EDAC_GET_DDR_CONFIG 0x3 + +/* MC_CMD_EDAC_GET_DDR_CONFIG_IN msgrequest */ +#define MC_CMD_EDAC_GET_DDR_CONFIG_IN_CONTROLLER_INDEX_OFST 0 +#define MC_CMD_EDAC_GET_DDR_CONFIG_IN_CONTROLLER_INDEX_LEN 4 + +#endif /* MC_CDX_PCOL_H */ diff --git a/include/linux/cdx/mcdi.h b/include/linux/cdx/mcdi.h new file mode 100644 index 000000000000..74075305cba4 --- /dev/null +++ b/include/linux/cdx/mcdi.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2008-2013 Solarflare Communications Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef CDX_MCDI_H +#define CDX_MCDI_H + +#include <linux/mutex.h> +#include <linux/kref.h> +#include <linux/rpmsg.h> + +#include "linux/cdx/bitfield.h" + +/** + * enum cdx_mcdi_mode - MCDI transaction mode + * @MCDI_MODE_EVENTS: wait for an mcdi response callback. + * @MCDI_MODE_FAIL: we think MCDI is dead, so fail-fast all calls + */ +enum cdx_mcdi_mode { + MCDI_MODE_EVENTS, + MCDI_MODE_FAIL, +}; + +#define MCDI_RPC_TIMEOUT (10 * HZ) +#define MCDI_RPC_LONG_TIMEOU (60 * HZ) +#define MCDI_RPC_POST_RST_TIME (10 * HZ) + +/** + * enum cdx_mcdi_cmd_state - State for an individual MCDI command + * @MCDI_STATE_QUEUED: Command not started and is waiting to run. + * @MCDI_STATE_RETRY: Command was submitted and MC rejected with no resources, + * as MC have too many outstanding commands. Command will be retried once + * another command returns. + * @MCDI_STATE_RUNNING: Command was accepted and is running. + * @MCDI_STATE_RUNNING_CANCELLED: Command is running but the issuer cancelled + * the command. + * @MCDI_STATE_FINISHED: Processing of this command has completed. + */ + +enum cdx_mcdi_cmd_state { + MCDI_STATE_QUEUED, + MCDI_STATE_RETRY, + MCDI_STATE_RUNNING, + MCDI_STATE_RUNNING_CANCELLED, + MCDI_STATE_FINISHED, +}; + +/** + * struct cdx_mcdi - CDX MCDI Firmware interface, to interact + * with CDX controller. + * @mcdi: MCDI interface + * @mcdi_ops: MCDI operations + * @r5_rproc : R5 Remoteproc device handle + * @rpdev: RPMsg device + * @ept: RPMsg endpoint + * @work: Post probe work + */ +struct cdx_mcdi { + /* MCDI interface */ + struct cdx_mcdi_data *mcdi; + const struct cdx_mcdi_ops *mcdi_ops; + + struct rproc *r5_rproc; + struct rpmsg_device *rpdev; + struct rpmsg_endpoint *ept; + struct work_struct work; +}; + +struct cdx_mcdi_ops { + void (*mcdi_request)(struct cdx_mcdi *cdx, + const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len); + unsigned int (*mcdi_rpc_timeout)(struct cdx_mcdi *cdx, unsigned int cmd); +}; + +typedef void cdx_mcdi_async_completer(struct cdx_mcdi *cdx, + unsigned long cookie, int rc, + struct cdx_dword *outbuf, + size_t outlen_actual); + +/** + * struct cdx_mcdi_cmd - An outstanding MCDI command + * @ref: Reference count. There will be one reference if the command is + * in the mcdi_iface cmd_list, another if it's on a cleanup list, + * and a third if it's queued in the work queue. + * @list: The data for this entry in mcdi->cmd_list + * @cleanup_list: The data for this entry in a cleanup list + * @work: The work item for this command, queued in mcdi->workqueue + * @mcdi: The mcdi_iface for this command + * @state: The state of this command + * @inlen: inbuf length + * @inbuf: Input buffer + * @quiet: Whether to silence errors + * @reboot_seen: Whether a reboot has been seen during this command, + * to prevent duplicates + * @seq: Sequence number + * @started: Jiffies this command was started at + * @cookie: Context for completion function + * @completer: Completion function + * @handle: Command handle + * @cmd: Command number + * @rc: Return code + * @outlen: Length of output buffer + * @outbuf: Output buffer + */ +struct cdx_mcdi_cmd { + struct kref ref; + struct list_head list; + struct list_head cleanup_list; + struct work_struct work; + struct cdx_mcdi_iface *mcdi; + enum cdx_mcdi_cmd_state state; + size_t inlen; + const struct cdx_dword *inbuf; + bool quiet; + bool reboot_seen; + u8 seq; + unsigned long started; + unsigned long cookie; + cdx_mcdi_async_completer *completer; + unsigned int handle; + unsigned int cmd; + int rc; + size_t outlen; + struct cdx_dword *outbuf; + /* followed by inbuf data if necessary */ +}; + +/** + * struct cdx_mcdi_iface - MCDI protocol context + * @cdx: The associated NIC + * @iface_lock: Serialise access to this structure + * @outstanding_cleanups: Count of cleanups + * @cmd_list: List of outstanding and running commands + * @workqueue: Workqueue used for delayed processing + * @cmd_complete_wq: Waitqueue for command completion + * @db_held_by: Command the MC doorbell is in use by + * @seq_held_by: Command each sequence number is in use by + * @prev_handle: The last used command handle + * @mode: Poll for mcdi completion, or wait for an mcdi_event + * @prev_seq: The last used sequence number + * @new_epoch: Indicates start of day or start of MC reboot recovery + */ +struct cdx_mcdi_iface { + struct cdx_mcdi *cdx; + /* Serialise access */ + struct mutex iface_lock; + unsigned int outstanding_cleanups; + struct list_head cmd_list; + struct workqueue_struct *workqueue; + wait_queue_head_t cmd_complete_wq; + struct cdx_mcdi_cmd *db_held_by; + struct cdx_mcdi_cmd *seq_held_by[16]; + unsigned int prev_handle; + enum cdx_mcdi_mode mode; + u8 prev_seq; + bool new_epoch; +}; + +/** + * struct cdx_mcdi_data - extra state for NICs that implement MCDI + * @iface: Interface/protocol state + * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH. + */ +struct cdx_mcdi_data { + struct cdx_mcdi_iface iface; + u32 fn_flags; +}; + +void cdx_mcdi_finish(struct cdx_mcdi *cdx); +int cdx_mcdi_init(struct cdx_mcdi *cdx); +void cdx_mcdi_process_cmd(struct cdx_mcdi *cdx, struct cdx_dword *outbuf, int len); +int cdx_mcdi_rpc(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + struct cdx_dword *outbuf, size_t outlen, size_t *outlen_actual); + +/* + * We expect that 16- and 32-bit fields in MCDI requests and responses + * are appropriately aligned, but 64-bit fields are only + * 32-bit-aligned. + */ +#define MCDI_DECLARE_BUF(_name, _len) struct cdx_dword _name[DIV_ROUND_UP(_len, 4)] = {{0}} +#define _MCDI_PTR(_buf, _offset) \ + ((u8 *)(_buf) + (_offset)) +#define MCDI_PTR(_buf, _field) \ + _MCDI_PTR(_buf, MC_CMD_ ## _field ## _OFST) +#define _MCDI_CHECK_ALIGN(_ofst, _align) \ + ((void)BUILD_BUG_ON_ZERO((_ofst) & ((_align) - 1)), \ + (_ofst)) +#define _MCDI_DWORD(_buf, _field) \ + ((_buf) + (_MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _OFST, 4) >> 2)) + +#define MCDI_SET_DWORD(_buf, _field, _value) \ + CDX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), CDX_DWORD, _value) +#define MCDI_DWORD(_buf, _field) \ + CDX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), CDX_DWORD) +#endif /* CDX_MCDI_H */ diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 52a98886a455..1fd22ea6eba4 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -11,7 +11,7 @@ #include <linux/module.h> #include <asm/cfi.h> -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI extern bool cfi_warn; enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, @@ -52,7 +52,7 @@ static inline u32 cfi_get_func_hash(void *func) extern u32 cfi_bpf_hash; extern u32 cfi_bpf_subprog_hash; -#else /* CONFIG_CFI_CLANG */ +#else /* CONFIG_CFI */ static inline int cfi_get_offset(void) { return 0; } static inline u32 cfi_get_func_hash(void *func) { return 0; } @@ -60,7 +60,7 @@ static inline u32 cfi_get_func_hash(void *func) { return 0; } #define cfi_bpf_hash 0U #define cfi_bpf_subprog_hash 0U -#endif /* CONFIG_CFI_CLANG */ +#endif /* CONFIG_CFI */ #ifdef CONFIG_ARCH_USES_CFI_TRAPS bool is_cfi_trap(unsigned long addr); diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h index 685f7181780f..a86af9bc8bdc 100644 --- a/include/linux/cfi_types.h +++ b/include/linux/cfi_types.h @@ -8,7 +8,7 @@ #ifdef __ASSEMBLY__ #include <linux/linkage.h> -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI /* * Use the __kcfi_typeid_<function> type identifier symbol to * annotate indirectly called assembly functions. The compiler emits @@ -29,12 +29,12 @@ #define SYM_TYPED_START(name, linkage, align...) \ SYM_TYPED_ENTRY(name, linkage, align) -#else /* CONFIG_CFI_CLANG */ +#else /* CONFIG_CFI */ #define SYM_TYPED_START(name, linkage, align...) \ SYM_START(name, linkage, align) -#endif /* CONFIG_CFI_CLANG */ +#endif /* CONFIG_CFI */ #ifndef SYM_TYPED_FUNC_START #define SYM_TYPED_FUNC_START(name) \ @@ -43,7 +43,7 @@ #else /* __ASSEMBLY__ */ -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI #define DEFINE_CFI_TYPE(name, func) \ /* \ * Force a reference to the function so the compiler generates \ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 6b93a64115fe..93318fce31f3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -91,6 +91,12 @@ enum { * cgroup_threadgroup_rwsem. This makes hot path operations such as * forks and exits into the slow path and more expensive. * + * Alleviate the contention between fork, exec, exit operations and + * writing to cgroup.procs by taking a per threadgroup rwsem instead of + * the global cgroup_threadgroup_rwsem. Fork and other operations + * from threads in different thread groups no longer contend with + * writing to cgroup.procs. + * * The static usage pattern of creating a cgroup, enabling controllers, * and then seeding it with CLONE_INTO_CGROUP doesn't require write * locking cgroup_threadgroup_rwsem and thus doesn't benefit from @@ -140,6 +146,17 @@ enum { __CFTYPE_ADDED = (1 << 18), }; +enum cgroup_attach_lock_mode { + /* Default */ + CGRP_ATTACH_LOCK_GLOBAL, + + /* When pid=0 && threadgroup=false, see comments in cgroup_procs_write_start */ + CGRP_ATTACH_LOCK_NONE, + + /* When favordynmods is on, see comments above CGRP_ROOT_FAVOR_DYNMODS */ + CGRP_ATTACH_LOCK_PER_THREADGROUP, +}; + /* * cgroup_file is the handle for a file instance created in a cgroup which * is used, for example, to generate file changed notifications. This can @@ -433,6 +450,23 @@ struct cgroup_freezer_state { * frozen, SIGSTOPped, and PTRACEd. */ int nr_frozen_tasks; + + /* Freeze time data consistency protection */ + seqcount_t freeze_seq; + + /* + * Most recent time the cgroup was requested to freeze. + * Accesses guarded by freeze_seq counter. Writes serialized + * by css_set_lock. + */ + u64 freeze_start_nsec; + + /* + * Total duration the cgroup has spent freezing. + * Accesses guarded by freeze_seq counter. Writes serialized + * by css_set_lock. + */ + u64 frozen_nsec; }; struct cgroup { @@ -746,7 +780,6 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); - void (*post_attach)(void); int (*can_fork)(struct task_struct *task, struct css_set *cset); void (*cancel_fork)(struct task_struct *task, struct css_set *cset); @@ -822,6 +855,7 @@ struct cgroup_subsys { }; extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; +extern bool cgroup_enable_per_threadgroup_rwsem; struct cgroup_of_peak { unsigned long value; @@ -833,11 +867,14 @@ struct cgroup_of_peak { * @tsk: target task * * Allows cgroup operations to synchronize against threadgroup changes - * using a percpu_rw_semaphore. + * using a global percpu_rw_semaphore and a per threadgroup rw_semaphore when + * favordynmods is on. See the comment above CGRP_ROOT_FAVOR_DYNMODS definition. */ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { percpu_down_read(&cgroup_threadgroup_rwsem); + if (cgroup_enable_per_threadgroup_rwsem) + down_read(&tsk->signal->cgroup_threadgroup_rwsem); } /** @@ -848,6 +885,8 @@ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) */ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) { + if (cgroup_enable_per_threadgroup_rwsem) + up_read(&tsk->signal->cgroup_threadgroup_rwsem); percpu_up_read(&cgroup_threadgroup_rwsem); } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b18fb5fcb38e..6ed477338b16 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -27,6 +27,7 @@ #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> +#include <linux/cgroup_namespace.h> struct kernel_clone_args; @@ -354,6 +355,11 @@ static inline bool css_is_dying(struct cgroup_subsys_state *css) return css->flags & CSS_DYING; } +static inline bool css_is_online(struct cgroup_subsys_state *css) +{ + return css->flags & CSS_ONLINE; +} + static inline bool css_is_self(struct cgroup_subsys_state *css) { if (css == &css->cgroup->self) { @@ -650,6 +656,7 @@ static inline void cgroup_kthread_ready(void) } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); +struct cgroup *__cgroup_get_from_id(u64 id); struct cgroup *cgroup_get_from_id(u64 id); #else /* !CONFIG_CGROUPS */ @@ -783,52 +790,6 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ -struct cgroup_namespace { - struct ns_common ns; - struct user_namespace *user_ns; - struct ucounts *ucounts; - struct css_set *root_cset; -}; - -extern struct cgroup_namespace init_cgroup_ns; - -#ifdef CONFIG_CGROUPS - -void free_cgroup_ns(struct cgroup_namespace *ns); - -struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, - struct user_namespace *user_ns, - struct cgroup_namespace *old_ns); - -int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, - struct cgroup_namespace *ns); - -static inline void get_cgroup_ns(struct cgroup_namespace *ns) -{ - refcount_inc(&ns->ns.count); -} - -static inline void put_cgroup_ns(struct cgroup_namespace *ns) -{ - if (refcount_dec_and_test(&ns->ns.count)) - free_cgroup_ns(ns); -} - -#else /* !CONFIG_CGROUPS */ - -static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } -static inline struct cgroup_namespace * -copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, - struct cgroup_namespace *old_ns) -{ - return old_ns; -} - -static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } -static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } - -#endif /* !CONFIG_CGROUPS */ - #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); diff --git a/include/linux/cgroup_namespace.h b/include/linux/cgroup_namespace.h new file mode 100644 index 000000000000..78a8418558a4 --- /dev/null +++ b/include/linux/cgroup_namespace.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CGROUP_NAMESPACE_H +#define _LINUX_CGROUP_NAMESPACE_H + +#include <linux/ns_common.h> + +struct cgroup_namespace { + struct ns_common ns; + struct user_namespace *user_ns; + struct ucounts *ucounts; + struct css_set *root_cset; +}; + +extern struct cgroup_namespace init_cgroup_ns; + +#ifdef CONFIG_CGROUPS + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +void free_cgroup_ns(struct cgroup_namespace *ns); + +struct cgroup_namespace *copy_cgroup_ns(u64 flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns); + +int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) +{ + ns_ref_inc(ns); +} + +static inline void put_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns_ref_put(ns)) + free_cgroup_ns(ns); +} + +#else /* !CONFIG_CGROUPS */ + +static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } +static inline struct cgroup_namespace * +copy_cgroup_ns(u64 flags, struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + return old_ns; +} + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } +static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } + +#endif /* !CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_NAMESPACE_H */ diff --git a/include/linux/codetag.h b/include/linux/codetag.h index 457ed8fd3214..8ea2a5f7c98a 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -16,13 +16,16 @@ struct module; #define CODETAG_SECTION_START_PREFIX "__start_" #define CODETAG_SECTION_STOP_PREFIX "__stop_" +/* codetag flags */ +#define CODETAG_FLAG_INACCURATE (1 << 0) + /* * An instance of this structure is created in a special ELF section at every * code location being tagged. At runtime, the special section is treated as * an array of these. */ struct codetag { - unsigned int flags; /* used in later patches */ + unsigned int flags; unsigned int lineno; const char *modname; const char *function; diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa4ffe037bc7..8720a0705900 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -18,23 +18,42 @@ #define KASAN_ABI_VERSION 5 /* + * Clang 22 added preprocessor macros to match GCC, in hopes of eventually + * dropping __has_feature support for sanitizers: + * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c + * Create these macros for older versions of clang so that it is easy to clean + * up once the minimum supported version of LLVM for building the kernel always + * creates these macros. + * * Note: Checking __has_feature(*_sanitizer) is only true if the feature is * enabled. Therefore it is not required to additionally check defined(CONFIG_*) * to avoid adding redundant attributes in other configurations. */ +#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__) +#define __SANITIZE_ADDRESS__ +#endif +#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__) +#define __SANITIZE_HWADDRESS__ +#endif +#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__) +#define __SANITIZE_THREAD__ +#endif -#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) -/* Emulate GCC's __SANITIZE_ADDRESS__ flag */ +/* + * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel. + */ +#ifdef __SANITIZE_HWADDRESS__ #define __SANITIZE_ADDRESS__ +#endif + +#ifdef __SANITIZE_ADDRESS__ #define __no_sanitize_address \ __attribute__((no_sanitize("address", "hwaddress"))) #else #define __no_sanitize_address #endif -#if __has_feature(thread_sanitizer) -/* emulate gcc's __SANITIZE_THREAD__ flag */ -#define __SANITIZE_THREAD__ +#ifdef __SANITIZE_THREAD__ #define __no_sanitize_thread \ __attribute__((no_sanitize("thread"))) #else diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 64ff73c533e5..5b45ea7dff3e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -248,7 +248,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ -#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_CFI) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) /* * Force a reference to the external symbol so the compiler generates * __kcfi_typid. diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 16755431fc11..2f3e80bf9f35 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -330,6 +330,29 @@ struct ftrace_likely_data { #endif /* + * The assume attribute is used to indicate that a certain condition is + * assumed to be true. If this condition is violated at runtime, the behavior + * is undefined. Compilers may or may not use this indication to generate + * optimized code. + * + * Note that the clang documentation states that optimizers may react + * differently to this attribute, and this may even have a negative + * performance impact. Therefore this attribute should be used with care. + * + * Optional: only supported since gcc >= 13 + * Optional: only supported since clang >= 19 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#index-assume-statement-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#id13 + * + */ +#ifdef CONFIG_CC_HAS_ASSUME +# define __assume(expr) __attribute__((__assume__(expr))) +#else +# define __assume(expr) +#endif + +/* * Optional: only supported since gcc >= 15 * Optional: only supported since clang >= 18 * diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b91b993f58ee..487b3bf2e1ea 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 95f3807c8c55..40966512ea18 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -780,11 +780,10 @@ struct cpufreq_frequency_table { else -int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); +int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy); + +int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy); -int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy, - struct cpufreq_frequency_table *table); int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy); int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, diff --git a/include/linux/cred.h b/include/linux/cred.h index a102a10f833f..89ae50ad2ace 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -148,7 +148,7 @@ struct cred { extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); -extern int copy_creds(struct task_struct *, unsigned long); +extern int copy_creds(struct task_struct *, u64); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); diff --git a/include/linux/damon.h b/include/linux/damon.h index f13664c62ddd..cae8c613c5fc 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -110,7 +110,7 @@ struct damon_target { * * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. - * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. + * @DAMOS_PAGEOUT: Reclaim the region. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. @@ -121,10 +121,10 @@ struct damon_target { * @NR_DAMOS_ACTIONS: Total number of DAMOS actions * * The support of each action is up to running &struct damon_operations. - * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR supports all actions except - * &enum DAMOS_LRU_PRIO and &enum DAMOS_LRU_DEPRIO. &enum DAMON_OPS_PADDR - * supports only &enum DAMOS_PAGEOUT, &enum DAMOS_LRU_PRIO, &enum - * DAMOS_LRU_DEPRIO, and &DAMOS_STAT. + * Refer to 'Operation Action' section of Documentation/mm/damon/design.rst for + * status of the supports. + * + * Note that DAMOS_PAGEOUT doesn't trigger demotions. */ enum damos_action { DAMOS_WILLNEED, @@ -636,6 +636,7 @@ struct damon_operations { * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. + * @dealloc_on_cancel: De-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. @@ -645,6 +646,7 @@ struct damon_call_control { void *data; bool repeat; int return_code; + bool dealloc_on_cancel; /* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; @@ -746,7 +748,8 @@ struct damon_attrs { * Accesses to other fields must be protected by themselves. * * @ops: Set of monitoring operations for given use cases. - * + * @addr_unit: Scale factor for core to ops address conversion. + * @min_sz_region: Minimum region size. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. */ @@ -788,6 +791,8 @@ struct damon_ctx { struct mutex kdamond_lock; struct damon_operations ops; + unsigned long addr_unit; + unsigned long min_sz_region; struct list_head adaptive_targets; struct list_head schemes; @@ -876,7 +881,7 @@ static inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, - unsigned int nr_ranges); + unsigned int nr_ranges, unsigned long min_sz_region); void damon_update_region_access_rate(struct damon_region *r, bool accessed, struct damon_attrs *attrs); @@ -933,6 +938,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs } +bool damon_initialized(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); bool damon_is_running(struct damon_ctx *ctx); diff --git a/include/linux/device.h b/include/linux/device.h index 0470d19da7f2..b031ff71a5bd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -851,6 +851,9 @@ static inline bool device_pm_not_required(struct device *dev) static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; +#ifdef CONFIG_PM + dev->power.no_callbacks = true; +#endif } static inline void dev_pm_syscore_device(struct device *dev, bool val) diff --git a/include/linux/device/devres.h b/include/linux/device/devres.h index ae696d10faff..8c5f57e0d613 100644 --- a/include/linux/device/devres.h +++ b/include/linux/device/devres.h @@ -80,6 +80,8 @@ 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); +const void * +devm_kmemdup_const(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) { diff --git a/include/linux/dibs.h b/include/linux/dibs.h new file mode 100644 index 000000000000..c75607f8a5cf --- /dev/null +++ b/include/linux/dibs.h @@ -0,0 +1,464 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Direct Internal Buffer Sharing + * + * Definitions for the DIBS module + * + * Copyright IBM Corp. 2025 + */ +#ifndef _DIBS_H +#define _DIBS_H + +#include <linux/device.h> +#include <linux/uuid.h> + +/* DIBS - Direct Internal Buffer Sharing - concept + * ----------------------------------------------- + * In the case of multiple system sharing the same hardware, dibs fabrics can + * provide dibs devices to these systems. The systems use dibs devices of the + * same fabric to communicate via dmbs (Direct Memory Buffers). Each dmb has + * exactly one owning local dibs device and one remote using dibs device, that + * is authorized to write into this dmb. This access control is provided by the + * dibs fabric. + * + * Because the access to the dmb is based on access to physical memory, it is + * lossless and synchronous. The remote devices can directly access any offset + * of the dmb. + * + * Dibs fabrics, dibs devices and dmbs are identified by tokens and ids. + * Dibs fabric id is unique within the same hardware (with the exception of the + * dibs loopback fabric), dmb token is unique within the same fabric, dibs + * device gids are guaranteed to be unique within the same fabric and + * statistically likely to be globally unique. The exchange of these tokens and + * ids between the systems is not part of the dibs concept. + * + * The dibs layer provides an abstraction between dibs device drivers and dibs + * clients. + */ + +/* DMB - Direct Memory Buffer + * -------------------------- + * A dibs client provides a dmb as input buffer for a local receiving + * dibs device for exactly one (remote) sending dibs device. Only this + * sending device can send data into this dmb using move_data(). Sender + * and receiver can be the same device. A dmb belongs to exactly one client. + */ +struct dibs_dmb { + /* tok - Token for this dmb + * Used by remote and local devices and clients to address this dmb. + * Provided by dibs fabric. Unique per dibs fabric. + */ + u64 dmb_tok; + /* rgid - GID of designated remote sending device */ + uuid_t rgid; + /* cpu_addr - buffer address */ + void *cpu_addr; + /* len - buffer length */ + u32 dmb_len; + /* idx - Index of this DMB on this receiving device */ + u32 idx; + /* VLAN support (deprecated) + * In order to write into a vlan-tagged dmb, the remote device needs + * to belong to the this vlan + */ + u32 vlan_valid; + u32 vlan_id; + /* optional, used by device driver */ + dma_addr_t dma_addr; +}; + +/* DIBS events + * ----------- + * Dibs devices can optionally notify dibs clients about events that happened + * in the fabric or at the remote device or remote dmb. + */ +enum dibs_event_type { + /* Buffer event, e.g. a remote dmb was unregistered */ + DIBS_BUF_EVENT, + /* Device event, e.g. a remote dibs device was disabled */ + DIBS_DEV_EVENT, + /* Software event, a dibs client can send an event signal to a + * remote dibs device. + */ + DIBS_SW_EVENT, + DIBS_OTHER_TYPE }; + +enum dibs_event_subtype { + DIBS_BUF_UNREGISTERED, + DIBS_DEV_DISABLED, + DIBS_DEV_ERR_STATE, + DIBS_OTHER_SUBTYPE +}; + +struct dibs_event { + u32 type; + u32 subtype; + /* uuid_null if invalid */ + uuid_t gid; + /* zero if invalid */ + u64 buffer_tok; + u64 time; + /* additional data or zero */ + u64 data; +}; + +struct dibs_dev; + +/* DIBS client + * ----------- + */ +#define MAX_DIBS_CLIENTS 8 +#define NO_DIBS_CLIENT 0xff +/* All dibs clients have access to all dibs devices. + * A dibs client provides the following functions to be called by dibs layer or + * dibs device drivers: + */ +struct dibs_client_ops { + /** + * add_dev() - add a dibs device + * @dev: device that was added + * + * Will be called during dibs_register_client() for all existing + * dibs devices and whenever a new dibs device is registered. + * dev is usable until dibs_client.remove() is called. + * *dev is protected by device refcounting. + */ + void (*add_dev)(struct dibs_dev *dev); + /** + * del_dev() - remove a dibs device + * @dev: device to be removed + * + * Will be called whenever a dibs device is removed. + * Will be called during dibs_unregister_client() for all existing + * dibs devices and whenever a dibs device is unregistered. + * The device has already stopped initiative for this client: + * No new handlers will be started. + * The device is no longer usable by this client after this call. + */ + void (*del_dev)(struct dibs_dev *dev); + /** + * handle_irq() - Handle signaling for a DMB + * @dev: device that owns the dmb + * @idx: Index of the dmb that got signalled + * @dmbemask: signaling mask of the dmb + * + * Handle signaling for a dmb that was registered by this client + * for this device. + * The dibs device can coalesce multiple signaling triggers into a + * single call of handle_irq(). dmbemask can be used to indicate + * different kinds of triggers. + * + * Context: Called in IRQ context by dibs device driver + */ + void (*handle_irq)(struct dibs_dev *dev, unsigned int idx, + u16 dmbemask); + /** + * handle_event() - Handle control information sent by device + * @dev: device reporting the event + * @event: ism event structure + * + * * Context: Called in IRQ context by dibs device driver + */ + void (*handle_event)(struct dibs_dev *dev, + const struct dibs_event *event); +}; + +struct dibs_client { + /* client name for logging and debugging purposes */ + const char *name; + const struct dibs_client_ops *ops; + /* client index - provided and used by dibs layer */ + u8 id; +}; + +/* Functions to be called by dibs clients: + */ +/** + * dibs_register_client() - register a client with dibs layer + * @client: this client + * + * Will call client->ops->add_dev() for all existing dibs devices. + * Return: zero on success. + */ +int dibs_register_client(struct dibs_client *client); +/** + * dibs_unregister_client() - unregister a client with dibs layer + * @client: this client + * + * Will call client->ops->del_dev() for all existing dibs devices. + * Return: zero on success. + */ +int dibs_unregister_client(struct dibs_client *client); + +/* dibs clients can call dibs device ops. */ + +/* DIBS devices + * ------------ + */ + +/* Defined fabric id / CHID for all loopback devices: + * All dibs loopback devices report this fabric id. In this case devices with + * the same fabric id can NOT communicate via dibs. Only loopback devices with + * the same dibs device gid can communicate (=same device with itself). + */ +#define DIBS_LOOPBACK_FABRIC 0xFFFF + +/* A dibs device provides the following functions to be called by dibs clients. + * They are mandatory, unless marked 'optional'. + */ +struct dibs_dev_ops { + /** + * get_fabric_id() + * @dev: local dibs device + * + * Only devices on the same dibs fabric can communicate. Fabric_id is + * unique inside the same HW system. Use fabric_id for fast negative + * checks, but only query_remote_gid() can give a reliable positive + * answer: + * Different fabric_id: dibs is not possible + * Same fabric_id: dibs may be possible or not + * (e.g. different HW systems) + * EXCEPTION: DIBS_LOOPBACK_FABRIC denotes an ism_loopback device + * that can only communicate with itself. Use dibs_dev.gid + * or query_remote_gid()to determine whether sender and + * receiver use the same ism_loopback device. + * Return: 2 byte dibs fabric id + */ + u16 (*get_fabric_id)(struct dibs_dev *dev); + /** + * query_remote_gid() + * @dev: local dibs device + * @rgid: gid of remote dibs device + * @vid_valid: if zero, vid will be ignored; + * deprecated, ignored if device does not support vlan + * @vid: VLAN id; deprecated, ignored if device does not support vlan + * + * Query whether a remote dibs device is reachable via this local device + * and this vlan id. + * Return: 0 if remote gid is reachable. + */ + int (*query_remote_gid)(struct dibs_dev *dev, const uuid_t *rgid, + u32 vid_valid, u32 vid); + /** + * max_dmbs() + * Return: Max number of DMBs that can be registered for this kind of + * dibs_dev + */ + int (*max_dmbs)(void); + /** + * register_dmb() - allocate and register a dmb + * @dev: dibs device + * @dmb: dmb struct to be registered + * @client: dibs client + * @vid: VLAN id; deprecated, ignored if device does not support vlan + * + * The following fields of dmb must provide valid input: + * @rgid: gid of remote user device + * @dmb_len: buffer length + * @idx: Optionally:requested idx (if non-zero) + * @vlan_valid: if zero, vlan_id will be ignored; + * deprecated, ignored if device does not support vlan + * @vlan_id: deprecated, ignored if device does not support vlan + * Upon return in addition the following fields will be valid: + * @dmb_tok: for usage by remote and local devices and clients + * @cpu_addr: allocated buffer + * @idx: dmb index, unique per dibs device + * @dma_addr: to be used by device driver,if applicable + * + * Allocate a dmb buffer and register it with this device and for this + * client. + * Return: zero on success + */ + int (*register_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb, + struct dibs_client *client); + /** + * unregister_dmb() - unregister and free a dmb + * @dev: dibs device + * @dmb: dmb struct to be unregistered + * The following fields of dmb must provide valid input: + * @dmb_tok + * @cpu_addr + * @idx + * + * Free dmb.cpu_addr and unregister the dmb from this device. + * Return: zero on success + */ + int (*unregister_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb); + /** + * move_data() - write into a remote dmb + * @dev: Local sending dibs device + * @dmb_tok: Token of the remote dmb + * @idx: signaling index in dmbemask + * @sf: signaling flag; + * if true, idx will be turned on at target dmbemask mask + * and target device will be signaled. + * @offset: offset within target dmb + * @data: pointer to data to be sent + * @size: length of data to be sent, can be zero. + * + * Use dev to write data of size at offset into a remote dmb + * identified by dmb_tok. Data is moved synchronously, *data can + * be freed when this function returns. + * + * If signaling flag (sf) is true, bit number idx bit will be turned + * on in the dmbemask mask when handle_irq() is called at the remote + * dibs client that owns the target dmb. The target device may chose + * to coalesce the signaling triggers of multiple move_data() calls + * to the same target dmb into a single handle_irq() call. + * Return: zero on success + */ + int (*move_data)(struct dibs_dev *dev, u64 dmb_tok, unsigned int idx, + bool sf, unsigned int offset, void *data, + unsigned int size); + /** + * add_vlan_id() - add dibs device to vlan (optional, deprecated) + * @dev: dibs device + * @vlan_id: vlan id + * + * In order to write into a vlan-tagged dmb, the remote device needs + * to belong to the this vlan. A device can belong to more than 1 vlan. + * Any device can access an untagged dmb. + * Deprecated, only supported for backwards compatibility. + * Return: zero on success + */ + int (*add_vlan_id)(struct dibs_dev *dev, u64 vlan_id); + /** + * del_vlan_id() - remove dibs device from vlan (optional, deprecated) + * @dev: dibs device + * @vlan_id: vlan id + * Return: zero on success + */ + int (*del_vlan_id)(struct dibs_dev *dev, u64 vlan_id); + /** + * signal_event() - trigger an event at a remote dibs device (optional) + * @dev: local dibs device + * @rgid: gid of remote dibs device + * trigger_irq: zero: notification may be coalesced with other events + * non-zero: notify immediately + * @subtype: 4 byte event code, meaning is defined by dibs client + * @data: 8 bytes of additional information, + * meaning is defined by dibs client + * + * dibs devices can offer support for sending a control event of type + * EVENT_SWR to a remote dibs device. + * NOTE: handle_event() will be called for all registered dibs clients + * at the remote device. + * Return: zero on success + */ + int (*signal_event)(struct dibs_dev *dev, const uuid_t *rgid, + u32 trigger_irq, u32 event_code, u64 info); + /** + * support_mmapped_rdmb() - can this device provide memory mapped + * remote dmbs? (optional) + * @dev: dibs device + * + * A dibs device can provide a kernel address + length, that represent + * a remote target dmb (like MMIO). Alternatively to calling + * move_data(), a dibs client can write into such a ghost-send-buffer + * (= to this kernel address) and the data will automatically + * immediately appear in the target dmb, even without calling + * move_data(). + * + * Either all 3 function pointers for support_dmb_nocopy(), + * attach_dmb() and detach_dmb() are defined, or all of them must + * be NULL. + * + * Return: non-zero, if memory mapped remote dmbs are supported. + */ + int (*support_mmapped_rdmb)(struct dibs_dev *dev); + /** + * attach_dmb() - attach local memory to a remote dmb + * @dev: Local sending ism device + * @dmb: all other parameters are passed in the form of a + * dmb struct + * TODO: (THIS IS CONFUSING, should be changed) + * dmb_tok: (in) Token of the remote dmb, we want to attach to + * cpu_addr: (out) MMIO address + * dma_addr: (out) MMIO address (if applicable, invalid otherwise) + * dmb_len: (out) length of local MMIO region, + * equal to length of remote DMB. + * sba_idx: (out) index of remote dmb (NOT HELPFUL, should be removed) + * + * Provides a memory address to the sender that can be used to + * directly write into the remote dmb. + * Memory is available until detach_dmb is called + * + * Return: Zero upon success, Error code otherwise + */ + int (*attach_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb); + /** + * detach_dmb() - Detach the ghost buffer from a remote dmb + * @dev: ism device + * @token: dmb token of the remote dmb + * + * No need to free cpu_addr. + * + * Return: Zero upon success, Error code otherwise + */ + int (*detach_dmb)(struct dibs_dev *dev, u64 token); +}; + +struct dibs_dev { + struct list_head list; + struct device dev; + /* To be filled by device driver, before calling dibs_dev_add(): */ + const struct dibs_dev_ops *ops; + uuid_t gid; + /* priv pointer for device driver */ + void *drv_priv; + + /* priv pointer per client; for client usage only */ + void *priv[MAX_DIBS_CLIENTS]; + + /* get this lock before accessing any of the fields below */ + spinlock_t lock; + /* array of client ids indexed by dmb idx; + * can be used as indices into priv and subs arrays + */ + u8 *dmb_clientid_arr; + /* Sparse array of all ISM clients */ + struct dibs_client *subs[MAX_DIBS_CLIENTS]; +}; + +static inline void dibs_set_priv(struct dibs_dev *dev, + struct dibs_client *client, void *priv) +{ + dev->priv[client->id] = priv; +} + +static inline void *dibs_get_priv(struct dibs_dev *dev, + struct dibs_client *client) +{ + return dev->priv[client->id]; +} + +/* ------- End of client-only functions ----------- */ + +/* Functions to be called by dibs device drivers: + */ +/** + * dibs_dev_alloc() - allocate and reference device structure + * + * The following fields will be valid upon successful return: dev + * NOTE: Use put_device(dibs_get_dev(@dibs)) to give up your reference instead + * of freeing @dibs @dev directly once you have successfully called this + * function. + * Return: Pointer to dibs device structure + */ +struct dibs_dev *dibs_dev_alloc(void); +/** + * dibs_dev_add() - register with dibs layer and all clients + * @dibs: dibs device + * + * The following fields must be valid upon entry: dev, ops, drv_priv + * All fields will be valid upon successful return. + * Return: zero on success + */ +int dibs_dev_add(struct dibs_dev *dibs); +/** + * dibs_dev_del() - unregister from dibs layer and all clients + * @dibs: dibs device + */ +void dibs_dev_del(struct dibs_dev *dibs); + +#endif /* _DIBS_H */ diff --git a/include/linux/dlm.h b/include/linux/dlm.h index bacda9898f2b..7e7b45b0d097 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -88,12 +88,43 @@ int dlm_new_lockspace(const char *name, const char *cluster, int *ops_result, dlm_lockspace_t **lockspace); /* + * dlm_release_lockspace() release_option values: + * + * DLM_RELEASE_NO_LOCKS returns -EBUSY if any locks (lkb's) + * exist in the local lockspace. + * + * DLM_RELEASE_UNUSED previous value that is no longer used. + * + * DLM_RELEASE_NORMAL releases the lockspace regardless of any + * locks managed in the local lockspace. + * + * DLM_RELEASE_NO_EVENT release the lockspace regardless of any + * locks managed in the local lockspace, and does not submit + * a leave event to the cluster manager, so other nodes will + * not be notified that the node should be removed from the + * list of lockspace members. + * + * DLM_RELEASE_RECOVER like DLM_RELEASE_NORMAL, but the remaining + * nodes will handle the removal of the node as if the node + * had failed, e.g. the recover_slot() callback would be used. + */ +#define DLM_RELEASE_NO_LOCKS 0 +#define DLM_RELEASE_UNUSED 1 +#define DLM_RELEASE_NORMAL 2 +#define DLM_RELEASE_NO_EVENT 3 +#define DLM_RELEASE_RECOVER 4 +#define __DLM_RELEASE_MAX DLM_RELEASE_RECOVER + +/* * dlm_release_lockspace * * Stop a lockspace. + * + * release_option: see DLM_RELEASE values above. */ -int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); +int dlm_release_lockspace(dlm_lockspace_t *lockspace, + unsigned int release_option); /* * dlm_lock diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index f48e5fb88bd5..332b80c42b6f 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page, { __free_pages(page, get_order(size)); } +static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ +} #endif /* CONFIG_DMA_CMA*/ #ifdef CONFIG_DMA_DECLARE_COHERENT diff --git a/include/linux/dpll.h b/include/linux/dpll.h index fa1e76920d0e..25be745bf41f 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -38,6 +38,12 @@ struct dpll_device_ops { void *dpll_priv, enum dpll_feature_state *state, struct netlink_ext_ack *extack); + int (*phase_offset_avg_factor_set)(const struct dpll_device *dpll, + void *dpll_priv, u32 factor, + struct netlink_ext_ack *extack); + int (*phase_offset_avg_factor_get)(const struct dpll_device *dpll, + void *dpll_priv, u32 *factor, + struct netlink_ext_ack *extack); }; struct dpll_pin_ops { diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7fa1eb3cc823..61d50571ad88 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev, int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts); +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + 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 *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table *table); @@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ + return -EINVAL; +} static inline void em_dev_unregister_perf_domain(struct device *dev) { } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de5bd76a400c..c2d8b4ec62eb 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -492,7 +492,29 @@ struct ethtool_pause_stats { }; #define ETHTOOL_MAX_LANES 8 +/** + * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for + * the end-of-list marker, total 17 items + */ +#define ETHTOOL_FEC_HIST_MAX 17 +/** + * struct ethtool_fec_hist_range - error bits range for FEC histogram + * statistics + * @low: low bound of the bin (inclusive) + * @high: high bound of the bin (inclusive) + */ +struct ethtool_fec_hist_range { + u16 low; + u16 high; +}; +struct ethtool_fec_hist { + struct ethtool_fec_hist_value { + u64 sum; + u64 per_lane[ETHTOOL_MAX_LANES]; + } values[ETHTOOL_FEC_HIST_MAX]; + const struct ethtool_fec_hist_range *ranges; +}; /** * struct ethtool_fec_stats - statistics for IEEE 802.3 FEC * @corrected_blocks: number of received blocks corrected by FEC @@ -856,8 +878,8 @@ struct kernel_ethtool_ts_info { enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_source phc_source; int phc_phyindex; - enum hwtstamp_tx_types tx_types; - enum hwtstamp_rx_filters rx_filters; + u32 tx_types; + u32 rx_filters; }; /** @@ -968,6 +990,7 @@ struct kernel_ethtool_ts_info { * @reset: Reset (part of) the device, as specified by a bitmask of * flags from &enum ethtool_reset_flags. Returns a negative * error code or zero. + * @get_rx_ring_count: Return the number of RX rings * @get_rxfh_key_size: Get the size of the RX flow hash key. * Returns zero if not supported for this specific device. * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table. @@ -1162,6 +1185,7 @@ struct ethtool_ops { int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); + u32 (*get_rx_ring_count)(struct net_device *dev); u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *); @@ -1212,7 +1236,8 @@ struct ethtool_ops { int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); void (*get_fec_stats)(struct net_device *dev, - struct ethtool_fec_stats *fec_stats); + struct ethtool_fec_stats *fec_stats, + struct ethtool_fec_hist *hist); int (*get_fecparam)(struct net_device *, struct ethtool_fecparam *); int (*set_fecparam)(struct net_device *, diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index cfb0dd1ea49c..3aac58a520c7 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -123,6 +123,12 @@ enum fid_type { FILEID_BCACHEFS_WITH_PARENT = 0xb2, /* + * + * 64 bit namespace identifier, 32 bit namespace type, 32 bit inode number. + */ + FILEID_NSFS = 0xf1, + + /* * 64 bit unique kernfs id */ FILEID_KERNFS = 0xfe, diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h index 2382dec6d6ab..81f0e698acbf 100644 --- a/include/linux/fbcon.h +++ b/include/linux/fbcon.h @@ -1,6 +1,13 @@ #ifndef _LINUX_FBCON_H #define _LINUX_FBCON_H +#include <linux/compiler_types.h> + +struct fb_blit_caps; +struct fb_info; +struct fb_var_screeninfo; +struct fb_videomode; + #ifdef CONFIG_FRAMEBUFFER_CONSOLE void __init fb_console_init(void); void __exit fb_console_exit(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 1e7fd3ee759e..f5c859b8131a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -78,6 +78,9 @@ struct ctl_table_header; /* unused opcode to mark special atomic instruction */ #define BPF_PROBE_ATOMIC 0xe0 +/* unused opcode to mark special ldsx instruction. Same as BPF_NOSPEC */ +#define BPF_PROBE_MEM32SX 0xc0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -997,12 +1000,6 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) return prog->len * sizeof(struct bpf_insn); } -static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) -{ - return round_up(bpf_prog_insn_size(prog) + - sizeof(__be64) + 1, SHA1_BLOCK_SIZE); -} - static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), @@ -1296,7 +1293,7 @@ void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { - pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, + pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) @@ -1784,6 +1781,7 @@ int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); +void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) @@ -1818,6 +1816,11 @@ static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, voi unsigned long len, bool flush) { } + +static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index d38c6e538e5c..6d208769d456 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -88,23 +88,30 @@ struct fw_card { int node_id; int generation; - int current_tlabel; - u64 tlabel_mask; - struct list_head transaction_list; u64 reset_jiffies; - u32 split_timeout_hi; - u32 split_timeout_lo; - unsigned int split_timeout_cycles; - unsigned int split_timeout_jiffies; + struct { + int current_tlabel; + u64 tlabel_mask; + struct list_head list; + spinlock_t lock; + } transactions; + + struct { + u32 hi; + u32 lo; + unsigned int cycles; + unsigned int jiffies; + spinlock_t lock; + } split_timeout; unsigned long long guid; unsigned max_receive; int link_speed; int config_rom_generation; - spinlock_t lock; /* Take this lock when handling the lists in - * this struct. */ + spinlock_t lock; + struct fw_node *local_node; struct fw_node *root_node; struct fw_node *irm_node; @@ -115,8 +122,6 @@ struct fw_card { int index; struct list_head link; - struct list_head phy_receiver_list; - struct delayed_work br_work; /* bus reset job */ bool br_short; @@ -131,7 +136,11 @@ struct fw_card { bool broadcast_channel_allocated; u32 broadcast_channel; - __be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; + + struct { + __be32 buffer[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; + spinlock_t lock; + } topology_map; __be32 maint_utility_register; diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h index d4212bc42b2c..a33b45027356 100644 --- a/include/linux/firmware/imx/sm.h +++ b/include/linux/firmware/imx/sm.h @@ -26,13 +26,43 @@ #define SCMI_IMX94_CTRL_SAI3_MCLK 5U /*!< WAKE SAI3 MCLK */ #define SCMI_IMX94_CTRL_SAI4_MCLK 6U /*!< WAKE SAI4 MCLK */ +#if IS_ENABLED(CONFIG_IMX_SCMI_MISC_DRV) int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val); int scmi_imx_misc_ctrl_set(u32 id, u32 val); +#else +static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) +{ + return -EOPNOTSUPP; +} +static inline int scmi_imx_misc_ctrl_set(u32 id, u32 val) +{ + return -EOPNOTSUPP; +} +#endif + +#if IS_ENABLED(CONFIG_IMX_SCMI_CPU_DRV) int scmi_imx_cpu_start(u32 cpuid, bool start); int scmi_imx_cpu_started(u32 cpuid, bool *started); int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, bool boot, bool resume); +#else +static inline int scmi_imx_cpu_start(u32 cpuid, bool start) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_cpu_started(u32 cpuid, bool *started) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, + bool boot, bool resume) +{ + return -EOPNOTSUPP; +} +#endif enum scmi_imx_lmm_op { SCMI_IMX_LMM_BOOT, @@ -44,7 +74,24 @@ enum scmi_imx_lmm_op { #define SCMI_IMX_LMM_OP_FORCEFUL 0 #define SCMI_IMX_LMM_OP_GRACEFUL BIT(0) +#if IS_ENABLED(CONFIG_IMX_SCMI_LMM_DRV) int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags); int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info); int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector); +#else +static inline int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector) +{ + return -EOPNOTSUPP; +} +#endif #endif diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index 0f667bf1d4d9..a55ca771286b 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -175,4 +175,10 @@ static inline int qcom_scm_qseecom_app_send(u32 app_id, #endif /* CONFIG_QCOM_QSEECOM */ +int qcom_scm_qtee_invoke_smc(phys_addr_t inbuf, size_t inbuf_size, + phys_addr_t outbuf, size_t outbuf_size, + u64 *result, u64 *response_type); +int qcom_scm_qtee_callback_response(phys_addr_t buf, size_t buf_size, + u64 *result, u64 *response_type); + #endif diff --git a/include/linux/firmware/qcom/qcom_tzmem.h b/include/linux/firmware/qcom/qcom_tzmem.h index b83b63a0c049..48ac0e5454c7 100644 --- a/include/linux/firmware/qcom/qcom_tzmem.h +++ b/include/linux/firmware/qcom/qcom_tzmem.h @@ -53,4 +53,19 @@ DEFINE_FREE(qcom_tzmem, void *, if (_T) qcom_tzmem_free(_T)) phys_addr_t qcom_tzmem_to_phys(void *ptr); +#if IS_ENABLED(CONFIG_QCOM_TZMEM_MODE_SHMBRIDGE) +int qcom_tzmem_shm_bridge_create(phys_addr_t paddr, size_t size, u64 *handle); +void qcom_tzmem_shm_bridge_delete(u64 handle); +#else +static inline int qcom_tzmem_shm_bridge_create(phys_addr_t paddr, + size_t size, u64 *handle) +{ + return 0; +} + +static inline void qcom_tzmem_shm_bridge_delete(u64 handle) +{ +} +#endif + #endif /* __QCOM_TZMEM */ diff --git a/include/linux/freezer.h b/include/linux/freezer.h index b303472255be..32884c9721e5 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -47,6 +47,7 @@ extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); +extern void thaw_process(struct task_struct *p); static inline bool try_to_freeze(void) { @@ -80,6 +81,7 @@ static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} static inline void thaw_kernel_threads(void) {} +static inline void thaw_process(struct task_struct *p) {} static inline bool try_to_freeze(void) { return false; } diff --git a/include/linux/fs.h b/include/linux/fs.h index d7ab4f96d705..75fb216b0f7a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -72,9 +72,7 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct fscrypt_inode_info; struct fscrypt_operations; -struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; @@ -149,7 +147,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) @@ -356,6 +355,7 @@ struct readahead_control; #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE +#define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -537,7 +537,7 @@ struct address_space { /* * Returns true if any of the pages in the mapping are marked with the tag. */ -static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } @@ -585,7 +585,7 @@ static inline void i_mmap_assert_write_locked(struct address_space *mapping) /* * Might pages of this file be mapped into userspace? */ -static inline int mapping_mapped(struct address_space *mapping) +static inline int mapping_mapped(const struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } @@ -599,7 +599,7 @@ static inline int mapping_mapped(struct address_space *mapping) * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ -static inline int mapping_writably_mapped(struct address_space *mapping) +static inline int mapping_writably_mapped(const struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } @@ -667,6 +667,124 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_CACHED_LINK 0x0040 /* + * Inode state bits. Protected by inode->i_lock + * + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. + * + * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, + * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at + * various stages of removing an inode. + * + * Two bits are used for locking and completion notification, I_NEW and I_SYNC. + * + * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * these changes separately from I_DIRTY_SYNC so that we + * don't have to write inode on fdatasync() when only + * e.g. the timestamps have changed. + * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update + * I_NEW Serves as both a mutex and completion notification. + * New inodes set I_NEW. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_NEW to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_NEW, without I_NEW actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. + * I_WILL_FREE Must be set when calling write_inode_now() if i_count + * is zero. I_FREEING must be set when I_WILL_FREE is + * cleared. + * I_FREEING Set when inode is about to be freed but still has dirty + * pages or buffers attached or the inode itself is still + * dirty. + * I_CLEAR Added by clear_inode(). In this state the inode is + * clean and can be destroyed. Inode keeps I_FREEING. + * + * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are + * prohibited for many purposes. iget() must wait for + * the inode to be completely released, then create it + * anew. Other functions will just ignore such inodes, + * if appropriate. I_NEW is used for waiting. + * + * I_SYNC Writeback of inode is running. The bit is set during + * data writeback, and cleared with a wakeup on the bit + * address once it is done. The bit is also used to pin + * the inode in memory for flusher thread. + * + * I_REFERENCED Marks the inode as recently references on the LRU list. + * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab the i_pages lock. See + * inode_switch_wbs_work_fn() for details. + * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * + * I_CREATING New object's inode in the middle of setting up. + * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * + * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. + */ + +enum inode_state_bits { + __I_NEW = 0U, + __I_SYNC = 1U, + __I_LRU_ISOLATING = 2U + /* reserved wait address bit 3 */ +}; + +enum inode_state_flags_t { + I_NEW = (1U << __I_NEW), + I_SYNC = (1U << __I_SYNC), + I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), + /* reserved flag bit 3 */ + I_DIRTY_SYNC = (1U << 4), + I_DIRTY_DATASYNC = (1U << 5), + I_DIRTY_PAGES = (1U << 6), + I_WILL_FREE = (1U << 7), + I_FREEING = (1U << 8), + I_CLEAR = (1U << 9), + I_REFERENCED = (1U << 10), + I_LINKABLE = (1U << 11), + I_DIRTY_TIME = (1U << 12), + I_WB_SWITCH = (1U << 13), + I_OVL_INUSE = (1U << 14), + I_CREATING = (1U << 15), + I_DONTCACHE = (1U << 16), + I_SYNC_QUEUED = (1U << 17), + I_PINNING_NETFS_WB = (1U << 18) +}; + +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) +#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) + +/* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' @@ -724,7 +842,7 @@ struct inode { #endif /* Misc */ - u32 i_state; + enum inode_state_flags_t i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; @@ -780,14 +898,6 @@ struct inode { struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#ifdef CONFIG_FS_ENCRYPTION - struct fscrypt_inode_info *i_crypt_info; -#endif - -#ifdef CONFIG_FS_VERITY - struct fsverity_info *i_verity_info; -#endif - void *i_private; /* fs or device private pointer */ } __randomize_layout; @@ -2008,20 +2118,18 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, /** * struct renamedata - contains all information required for renaming - * @old_mnt_idmap: idmap of the old mount the inode was found from + * @mnt_idmap: idmap of the mount in which the rename is happening. * @old_parent: parent of source * @old_dentry: source - * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct mnt_idmap *old_mnt_idmap; + struct mnt_idmap *mnt_idmap; struct dentry *old_parent; struct dentry *old_dentry; - struct mnt_idmap *new_mnt_idmap; struct dentry *new_parent; struct dentry *new_dentry; struct inode **delegated_inode; @@ -2052,8 +2160,6 @@ 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); -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, unsigned long arg); @@ -2279,6 +2385,8 @@ static inline bool can_mmap_file(struct file *file) return true; } +int __compat_vma_mmap_prepare(const struct file_operations *f_op, + struct file *file, struct vm_area_struct *vma); int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma); static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) @@ -2492,117 +2600,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, }; } -/* - * Inode state bits. Protected by inode->i_lock - * - * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, - * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. - * - * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, - * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at - * various stages of removing an inode. - * - * Two bits are used for locking and completion notification, I_NEW and I_SYNC. - * - * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync() (unless I_DIRTY_DATASYNC is also set). - * Timestamp updates are the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of - * these changes separately from I_DIRTY_SYNC so that we - * don't have to write inode on fdatasync() when only - * e.g. the timestamps have changed. - * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_DIRTY_TIME The inode itself has dirty timestamps, and the - * lazytime mount option is enabled. We keep track of this - * separately from I_DIRTY_SYNC in order to implement - * lazytime. This gets cleared if I_DIRTY_INODE - * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But - * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already - * in place because writeback might already be in progress - * and we don't want to lose the time update - * I_NEW Serves as both a mutex and completion notification. - * New inodes set I_NEW. If two processes both create - * the same inode, one of them will release its inode and - * wait for I_NEW to be released before returning. - * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can - * also cause waiting on I_NEW, without I_NEW actually - * being set. find_inode() uses this to prevent returning - * nearly-dead inodes. - * I_WILL_FREE Must be set when calling write_inode_now() if i_count - * is zero. I_FREEING must be set when I_WILL_FREE is - * cleared. - * I_FREEING Set when inode is about to be freed but still has dirty - * pages or buffers attached or the inode itself is still - * dirty. - * I_CLEAR Added by clear_inode(). In this state the inode is - * clean and can be destroyed. Inode keeps I_FREEING. - * - * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are - * prohibited for many purposes. iget() must wait for - * the inode to be completely released, then create it - * anew. Other functions will just ignore such inodes, - * if appropriate. I_NEW is used for waiting. - * - * I_SYNC Writeback of inode is running. The bit is set during - * data writeback, and cleared with a wakeup on the bit - * address once it is done. The bit is also used to pin - * the inode in memory for flusher thread. - * - * I_REFERENCED Marks the inode as recently references on the LRU list. - * - * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to - * synchronize competing switching instances and to tell - * wb stat updates to grab the i_pages lock. See - * inode_switch_wbs_work_fn() for details. - * - * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper - * and work dirs among overlayfs mounts. - * - * I_CREATING New object's inode in the middle of setting up. - * - * I_DONTCACHE Evict inode as soon as it is not used anymore. - * - * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. - * Used to detect that mark_inode_dirty() should not move - * inode between dirty lists. - * - * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. - * - * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding - * i_count. - * - * Q: What is the difference between I_WILL_FREE and I_FREEING? - * - * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait - * upon. There's one free address left. - */ -#define __I_NEW 0 -#define I_NEW (1 << __I_NEW) -#define __I_SYNC 1 -#define I_SYNC (1 << __I_SYNC) -#define __I_LRU_ISOLATING 2 -#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) - -#define I_DIRTY_SYNC (1 << 3) -#define I_DIRTY_DATASYNC (1 << 4) -#define I_DIRTY_PAGES (1 << 5) -#define I_WILL_FREE (1 << 6) -#define I_FREEING (1 << 7) -#define I_CLEAR (1 << 8) -#define I_REFERENCED (1 << 9) -#define I_LINKABLE (1 << 10) -#define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 12) -#define I_OVL_INUSE (1 << 13) -#define I_CREATING (1 << 14) -#define I_DONTCACHE (1 << 15) -#define I_SYNC_QUEUED (1 << 16) -#define I_PINNING_NETFS_WB (1 << 17) - -#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) -#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) - extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { @@ -2614,6 +2611,11 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline int icount_read(const struct inode *inode) +{ + return atomic_read(&inode->i_count); +} + /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. @@ -2713,12 +2715,6 @@ static inline bool is_mgtime(const struct inode *inode) return inode->i_opflags & IOP_MGTIME; } -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_nodev(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); @@ -3281,7 +3277,7 @@ static inline bool is_dot_dotdot(const char *name, size_t len) /** * name_contains_dotdot - check if a file name contains ".." path components - * + * @name: File path string to check * Search for ".." surrounded by either '/' or start/end of string. */ static inline bool name_contains_dotdot(const char *name) @@ -3313,8 +3309,8 @@ extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); -extern int generic_delete_inode(struct inode *inode); -static inline int generic_drop_inode(struct inode *inode) +extern int inode_just_drop(struct inode *inode); +static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } @@ -3393,7 +3389,6 @@ static inline struct inode *new_inode_pseudo(struct super_block *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 *); -extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); @@ -4023,4 +4018,18 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); +static inline bool extensible_ioctl_valid(unsigned int cmd_a, + unsigned int cmd_b, size_t min_size) +{ + if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) + return false; + if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) + return false; + if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) + return false; + if (_IOC_SIZE(cmd_a) < min_size) + return false; + return true; +} + #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 7773eb870039..671f031be173 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -186,10 +186,12 @@ struct fc_log { extern __attribute__((format(printf, 4, 5))) void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); -#define __logfc(fc, l, fmt, ...) logfc((fc)->log.log, NULL, \ - l, fmt, ## __VA_ARGS__) -#define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \ - l, fmt, ## __VA_ARGS__) +#define __logfc(fc, l, fmt, ...) \ + logfc((fc)->log.log, NULL, (l), (fmt), ## __VA_ARGS__) +#define __plogp(p, prefix, l, fmt, ...) \ + logfc((p)->log, (prefix), (l), (fmt), ## __VA_ARGS__) +#define __plog(p, l, fmt, ...) __plogp(p, (p)->prefix, l, fmt, ## __VA_ARGS__) + /** * infof - Store supplementary informational message * @fc: The context in which to log the informational message @@ -201,6 +203,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) #define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) +#define infofcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message @@ -213,6 +217,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) #define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__) #define warnfc(fc, fmt, ...) __plog((&(fc)->log), 'w', fmt, ## __VA_ARGS__) +#define warnfcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message @@ -225,6 +231,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) #define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__) #define errorfc(fc, fmt, ...) __plog((&(fc)->log), 'e', fmt, ## __VA_ARGS__) +#define errorfcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message @@ -237,5 +245,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) #define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL) #define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL) +#define invalfcp(fc, prefix, fmt, ...) \ + (errorfcp(fc, prefix, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 10dd161690a2..516aba5b858b 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -61,6 +61,12 @@ struct fscrypt_name { /* Crypto operations for filesystems */ struct fscrypt_operations { + /* + * The offset of the pointer to struct fscrypt_inode_info in the + * filesystem-specific part of the inode, relative to the beginning of + * the common part of the inode (the 'struct inode'). + */ + ptrdiff_t inode_info_offs; /* * If set, then fs/crypto/ will allocate a global bounce page pool the @@ -195,16 +201,44 @@ struct fscrypt_operations { int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags); +/* + * Returns the address of the fscrypt info pointer within the + * filesystem-specific part of the inode. (To save memory on filesystems that + * don't support fscrypt, a field in 'struct inode' itself is no longer used.) + */ +static inline struct fscrypt_inode_info ** +fscrypt_inode_info_addr(const struct inode *inode) +{ + VFS_WARN_ON_ONCE(inode->i_sb->s_cop->inode_info_offs == 0); + return (void *)inode + inode->i_sb->s_cop->inode_info_offs; +} + +/* + * Load the inode's fscrypt info pointer, using a raw dereference. Since this + * uses a raw dereference with no memory barrier, it is appropriate to use only + * when the caller knows the inode's key setup already happened, resulting in + * non-NULL fscrypt info. E.g., the file contents en/decryption functions use + * this, since fscrypt_file_open() set up the key. + */ +static inline struct fscrypt_inode_info * +fscrypt_get_inode_info_raw(const struct inode *inode) +{ + struct fscrypt_inode_info *ci = *fscrypt_inode_info_addr(inode); + + VFS_WARN_ON_ONCE(ci == NULL); + return ci; +} + static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { /* * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info(). - * I.e., another task may publish ->i_crypt_info concurrently, executing - * a RELEASE barrier. We need to use smp_load_acquire() here to safely + * I.e., another task may publish the fscrypt info concurrently, + * executing a RELEASE barrier. Use smp_load_acquire() here to safely * ACQUIRE the memory the other task published. */ - return smp_load_acquire(&inode->i_crypt_info); + return smp_load_acquire(fscrypt_inode_info_addr(inode)); } /** diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b301bf7199d3..3601e25779ba 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -145,7 +145,6 @@ struct ptp_qoriq { struct ptp_clock *clock; struct ptp_clock_info caps; struct resource *rsrc; - struct dentry *debugfs_root; struct device *dev; bool extts_fifo_support; bool fiper3_support; @@ -195,14 +194,5 @@ int ptp_qoriq_settime(struct ptp_clock_info *ptp, int ptp_qoriq_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on); int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event); -#ifdef CONFIG_DEBUG_FS -void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq); -void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq); -#else -static inline void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq) -{ } -static inline void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq) -{ } -#endif #endif diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 1eb7eae580be..5bc7280425a7 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -26,8 +26,16 @@ /* Arbitrary limit to bound the kmalloc() size. Can be changed. */ #define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 +struct fsverity_info; + /* Verity operations for filesystems */ struct fsverity_operations { + /** + * The offset of the pointer to struct fsverity_info in the + * filesystem-specific part of the inode, relative to the beginning of + * the common part of the inode (the 'struct inode'). + */ + ptrdiff_t inode_info_offs; /** * Begin enabling verity on the given file. @@ -124,15 +132,37 @@ struct fsverity_operations { #ifdef CONFIG_FS_VERITY +/* + * Returns the address of the verity info pointer within the filesystem-specific + * part of the inode. (To save memory on filesystems that don't support + * fsverity, a field in 'struct inode' itself is no longer used.) + */ +static inline struct fsverity_info ** +fsverity_info_addr(const struct inode *inode) +{ + VFS_WARN_ON_ONCE(inode->i_sb->s_vop->inode_info_offs == 0); + return (void *)inode + inode->i_sb->s_vop->inode_info_offs; +} + static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) { /* - * Pairs with the cmpxchg_release() in fsverity_set_info(). - * I.e., another task may publish ->i_verity_info concurrently, - * executing a RELEASE barrier. We need to use smp_load_acquire() here - * to safely ACQUIRE the memory the other task published. + * Since this function can be called on inodes belonging to filesystems + * that don't support fsverity at all, and fsverity_info_addr() doesn't + * work on such filesystems, we have to start with an IS_VERITY() check. + * Checking IS_VERITY() here is also useful to minimize the overhead of + * fsverity_active() on non-verity files. + */ + if (!IS_VERITY(inode)) + return NULL; + + /* + * Pairs with the cmpxchg_release() in fsverity_set_info(). I.e., + * another task may publish the inode's verity info concurrently, + * executing a RELEASE barrier. Use smp_load_acquire() here to safely + * ACQUIRE the memory the other task published. */ - return smp_load_acquire(&inode->i_verity_info); + return smp_load_acquire(fsverity_info_addr(inode)); } /* enable.c */ @@ -156,12 +186,19 @@ void __fsverity_cleanup_inode(struct inode *inode); * fsverity_cleanup_inode() - free the inode's verity info, if present * @inode: an inode being evicted * - * Filesystems must call this on inode eviction to free ->i_verity_info. + * Filesystems must call this on inode eviction to free the inode's verity info. */ static inline void fsverity_cleanup_inode(struct inode *inode) { - if (inode->i_verity_info) + /* + * Only IS_VERITY() inodes can have verity info, so start by checking + * for IS_VERITY() (which is faster than retrieving the pointer to the + * verity info). This minimizes overhead for non-verity inodes. + */ + if (IS_VERITY(inode)) __fsverity_cleanup_inode(inode); + else + VFS_WARN_ON_ONCE(*fsverity_info_addr(inode) != NULL); } /* read_metadata.c */ @@ -267,12 +304,12 @@ static inline bool fsverity_verify_page(struct page *page) * fsverity_active() - do reads from the inode need to go through fs-verity? * @inode: inode to check * - * This checks whether ->i_verity_info has been set. + * This checks whether the inode's verity info has been set. * * Filesystems call this from ->readahead() to check whether the pages need to * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with - * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before the verity info.) * * Return: true if reads need to go through fs-verity, otherwise false */ @@ -287,7 +324,7 @@ static inline bool fsverity_active(const struct inode *inode) * @filp: the struct file being set up * * When opening a verity file, deny the open if it is for writing. Otherwise, - * set up the inode's ->i_verity_info if not already done. + * set up the inode's verity info if not already done. * * When combined with fscrypt, this must be called after fscrypt_file_open(). * Otherwise, we won't have the key set up to decrypt the verity metadata. diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 5ebf26fcdcfa..0ceb4e09306c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -354,7 +354,7 @@ static inline struct page *alloc_page_vma_noprof(gfp_t gfp, } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) -struct page *alloc_pages_nolock_noprof(int nid, unsigned int order); +struct page *alloc_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); #define alloc_pages_nolock(...) alloc_hooks(alloc_pages_nolock_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 667f8fd58a79..fabe2baf7b50 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -388,28 +388,6 @@ struct gpio_irq_chip { * implies that if the chip supports IRQs, these IRQs need to be threaded * as the chip access may sleep when e.g. reading out the IRQ status * registers. - * @read_reg: reader function for generic GPIO - * @write_reg: writer function for generic GPIO - * @be_bits: if the generic GPIO has big endian bit order (bit 31 is representing - * line 0, bit 30 is line 1 ... bit 0 is line 31) this is set to true by the - * generic GPIO core. It is for internal housekeeping only. - * @reg_dat: data (in) register for generic GPIO - * @reg_set: output set register (out=high) for generic GPIO - * @reg_clr: output clear register (out=low) for generic GPIO - * @reg_dir_out: direction out setting register for generic GPIO - * @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 - * shadowed and real data registers writes together. - * @bgpio_data: shadowed data register for generic GPIO to clear/set bits - * safely. - * @bgpio_dir: shadowed direction register for generic GPIO to clear/set - * direction safely. A "1" in this word means the line is set as - * output. * * A gpio_chip can help platforms abstract various sources of GPIOs so * they can all be accessed through a common programming interface. @@ -475,23 +453,6 @@ struct gpio_chip { const char *const *names; bool can_sleep; -#if IS_ENABLED(CONFIG_GPIO_GENERIC) - unsigned long (*read_reg)(void __iomem *reg); - void (*write_reg)(void __iomem *reg, unsigned long data); - bool be_bits; - void __iomem *reg_dat; - void __iomem *reg_set; - void __iomem *reg_clr; - 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; - unsigned long bgpio_dir; -#endif /* CONFIG_GPIO_GENERIC */ - #ifdef CONFIG_GPIOLIB_IRQCHIP /* * With CONFIG_GPIOLIB_IRQCHIP we get an irqchip inside the gpiolib @@ -723,21 +684,6 @@ int gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc, #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ -int bgpio_init(struct gpio_chip *gc, struct device *dev, - unsigned long sz, void __iomem *dat, void __iomem *set, - void __iomem *clr, void __iomem *dirout, void __iomem *dirin, - unsigned long flags); - -#define BGPIOF_BIG_ENDIAN BIT(0) -#define BGPIOF_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ -#define BGPIOF_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ -#define BGPIOF_BIG_ENDIAN_BYTE_ORDER BIT(3) -#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 */ -#define BGPIOF_NO_INPUT BIT(8) /* only output */ - #ifdef CONFIG_GPIOLIB_IRQCHIP int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain); @@ -772,23 +718,68 @@ struct gpio_pin_range { #ifdef CONFIG_PINCTRL -int gpiochip_add_pin_range(struct gpio_chip *gc, const char *pinctl_name, - unsigned int gpio_offset, unsigned int pin_offset, - unsigned int npins); +int gpiochip_add_pin_range_with_pins(struct gpio_chip *gc, + const char *pinctl_name, + unsigned int gpio_offset, + unsigned int pin_offset, + unsigned int const *pins, + unsigned int npins); int gpiochip_add_pingroup_range(struct gpio_chip *gc, struct pinctrl_dev *pctldev, unsigned int gpio_offset, const char *pin_group); void gpiochip_remove_pin_ranges(struct gpio_chip *gc); +static inline int +gpiochip_add_pin_range(struct gpio_chip *gc, + const char *pinctl_name, + unsigned int gpio_offset, + unsigned int pin_offset, + unsigned int npins) +{ + return gpiochip_add_pin_range_with_pins(gc, pinctl_name, gpio_offset, + pin_offset, NULL, npins); +} + +static inline int +gpiochip_add_sparse_pin_range(struct gpio_chip *gc, + const char *pinctl_name, + unsigned int gpio_offset, + unsigned int const *pins, + unsigned int npins) +{ + return gpiochip_add_pin_range_with_pins(gc, pinctl_name, gpio_offset, 0, + pins, npins); +} #else /* ! CONFIG_PINCTRL */ static inline int +gpiochip_add_pin_range_with_pins(struct gpio_chip *gc, + const char *pinctl_name, + unsigned int gpio_offset, + unsigned int pin_offset, + unsigned int npins) +{ + return 0; +} + +static inline int gpiochip_add_pin_range(struct gpio_chip *gc, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, unsigned int npins) { return 0; } + +static inline int +gpiochip_add_sparse_pin_range(struct gpio_chip *gc, + const char *pinctl_name, + unsigned int gpio_offset, + unsigned int const *pins, + unsigned int npins) +{ + return 0; +} + static inline int gpiochip_add_pingroup_range(struct gpio_chip *gc, struct pinctrl_dev *pctldev, diff --git a/include/linux/gpio/forwarder.h b/include/linux/gpio/forwarder.h new file mode 100644 index 000000000000..ee5d8355f735 --- /dev/null +++ b/include/linux/gpio/forwarder.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GPIO_FORWARDER_H +#define __LINUX_GPIO_FORWARDER_H + +struct gpio_desc; +struct gpio_chip; +struct gpiochip_fwd; + +struct gpiochip_fwd *devm_gpiochip_fwd_alloc(struct device *dev, + unsigned int ngpios); +int gpiochip_fwd_desc_add(struct gpiochip_fwd *fwd, + struct gpio_desc *desc, unsigned int offset); +void gpiochip_fwd_desc_free(struct gpiochip_fwd *fwd, unsigned int offset); +int gpiochip_fwd_register(struct gpiochip_fwd *fwd, void *data); + +struct gpio_chip *gpiochip_fwd_get_gpiochip(struct gpiochip_fwd *fwd); + +void *gpiochip_fwd_get_data(struct gpiochip_fwd *fwd); + +int gpiochip_fwd_gpio_request(struct gpiochip_fwd *fwd, unsigned int offset); +int gpiochip_fwd_gpio_get_direction(struct gpiochip_fwd *fwd, + unsigned int offset); +int gpiochip_fwd_gpio_direction_input(struct gpiochip_fwd *fwd, + unsigned int offset); +int gpiochip_fwd_gpio_direction_output(struct gpiochip_fwd *fwd, + unsigned int offset, + int value); +int gpiochip_fwd_gpio_get(struct gpiochip_fwd *fwd, unsigned int offset); +int gpiochip_fwd_gpio_get_multiple(struct gpiochip_fwd *fwd, + unsigned long *mask, + unsigned long *bits); +int gpiochip_fwd_gpio_set(struct gpiochip_fwd *fwd, unsigned int offset, + int value); +int gpiochip_fwd_gpio_set_multiple(struct gpiochip_fwd *fwd, + unsigned long *mask, + unsigned long *bits); +int gpiochip_fwd_gpio_set_config(struct gpiochip_fwd *fwd, unsigned int offset, + unsigned long config); +int gpiochip_fwd_gpio_to_irq(struct gpiochip_fwd *fwd, unsigned int offset); + +#endif diff --git a/include/linux/gpio/generic.h b/include/linux/gpio/generic.h index f3a8db4598bb..ff566dc9c3cb 100644 --- a/include/linux/gpio/generic.h +++ b/include/linux/gpio/generic.h @@ -9,6 +9,16 @@ struct device; +#define GPIO_GENERIC_BIG_ENDIAN BIT(0) +#define GPIO_GENERIC_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ +#define GPIO_GENERIC_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ +#define GPIO_GENERIC_BIG_ENDIAN_BYTE_ORDER BIT(3) +#define GPIO_GENERIC_READ_OUTPUT_REG_SET BIT(4) /* reg_set stores output value */ +#define GPIO_GENERIC_NO_OUTPUT BIT(5) /* only input */ +#define GPIO_GENERIC_NO_SET_ON_INPUT BIT(6) +#define GPIO_GENERIC_PINCTRL_BACKEND BIT(7) /* Call pinctrl direction setters */ +#define GPIO_GENERIC_NO_INPUT BIT(8) /* only output */ + /** * struct gpio_generic_chip_config - Generic GPIO chip configuration data * @dev: Parent device of the new GPIO chip (compulsory). @@ -50,26 +60,55 @@ struct gpio_generic_chip_config { * struct gpio_generic_chip - Generic GPIO chip implementation. * @gc: The underlying struct gpio_chip object, implementing low-level GPIO * chip routines. + * @read_reg: reader function for generic GPIO + * @write_reg: writer function for generic GPIO + * @be_bits: if the generic GPIO has big endian bit order (bit 31 is + * representing line 0, bit 30 is line 1 ... bit 0 is line 31) this + * is set to true by the generic GPIO core. It is for internal + * housekeeping only. + * @reg_dat: data (in) register for generic GPIO + * @reg_set: output set register (out=high) for generic GPIO + * @reg_clr: output clear register (out=low) for generic GPIO + * @reg_dir_out: direction out setting register for generic GPIO + * @reg_dir_in: direction in setting register for generic GPIO + * @dir_unreadable: indicates that the direction register(s) cannot be read and + * we need to rely on out internal state tracking. + * @pinctrl: the generic GPIO uses a pin control backend. + * @bits: number of register bits used for a generic GPIO + * i.e. <register width> * 8 + * @lock: used to lock chip->sdata. Also, this is needed to keep + * shadowed and real data registers writes together. + * @sdata: shadowed data register for generic GPIO to clear/set bits safely. + * @sdir: shadowed direction register for generic GPIO to clear/set direction + * safely. A "1" in this word means the line is set as output. */ struct gpio_generic_chip { struct gpio_chip gc; + unsigned long (*read_reg)(void __iomem *reg); + void (*write_reg)(void __iomem *reg, unsigned long data); + bool be_bits; + void __iomem *reg_dat; + void __iomem *reg_set; + void __iomem *reg_clr; + void __iomem *reg_dir_out; + void __iomem *reg_dir_in; + bool dir_unreadable; + bool pinctrl; + int bits; + raw_spinlock_t lock; + unsigned long sdata; + unsigned long sdir; }; -/** - * gpio_generic_chip_init() - Initialize a generic GPIO chip. - * @chip: Generic GPIO chip to set up. - * @cfg: Generic GPIO chip configuration. - * - * Returns 0 on success, negative error number on failure. - */ -static inline int -gpio_generic_chip_init(struct gpio_generic_chip *chip, - const struct gpio_generic_chip_config *cfg) +static inline struct gpio_generic_chip * +to_gpio_generic_chip(struct gpio_chip *gc) { - return bgpio_init(&chip->gc, cfg->dev, cfg->sz, cfg->dat, cfg->set, - cfg->clr, cfg->dirout, cfg->dirin, cfg->flags); + return container_of(gc, struct gpio_generic_chip, gc); } +int gpio_generic_chip_init(struct gpio_generic_chip *chip, + const struct gpio_generic_chip_config *cfg); + /** * gpio_generic_chip_set() - Set the GPIO line value of the generic GPIO chip. * @chip: Generic GPIO chip to use. @@ -94,17 +133,48 @@ gpio_generic_chip_set(struct gpio_generic_chip *chip, unsigned int offset, return chip->gc.set(&chip->gc, offset, value); } +/** + * gpio_generic_read_reg() - Read a register using the underlying callback. + * @chip: Generic GPIO chip to use. + * @reg: Register to read. + * + * Returns: value read from register. + */ +static inline unsigned long +gpio_generic_read_reg(struct gpio_generic_chip *chip, void __iomem *reg) +{ + if (WARN_ON(!chip->read_reg)) + return 0; + + return chip->read_reg(reg); +} + +/** + * gpio_generic_write_reg() - Write a register using the underlying callback. + * @chip: Generic GPIO chip to use. + * @reg: Register to write to. + * @val: New value to write. + */ +static inline void gpio_generic_write_reg(struct gpio_generic_chip *chip, + void __iomem *reg, unsigned long val) +{ + if (WARN_ON(!chip->write_reg)) + return; + + chip->write_reg(reg, val); +} + #define gpio_generic_chip_lock(gen_gc) \ - raw_spin_lock(&(gen_gc)->gc.bgpio_lock) + raw_spin_lock(&(gen_gc)->lock) #define gpio_generic_chip_unlock(gen_gc) \ - raw_spin_unlock(&(gen_gc)->gc.bgpio_lock) + raw_spin_unlock(&(gen_gc)->lock) #define gpio_generic_chip_lock_irqsave(gen_gc, flags) \ - raw_spin_lock_irqsave(&(gen_gc)->gc.bgpio_lock, flags) + raw_spin_lock_irqsave(&(gen_gc)->lock, flags) #define gpio_generic_chip_unlock_irqrestore(gen_gc, flags) \ - raw_spin_unlock_irqrestore(&(gen_gc)->gc.bgpio_lock, flags) + raw_spin_unlock_irqrestore(&(gen_gc)->lock, flags) DEFINE_LOCK_GUARD_1(gpio_generic_lock, struct gpio_generic_chip, diff --git a/include/linux/gpio/gpio-nomadik.h b/include/linux/gpio/gpio-nomadik.h index b5a84864650d..592a774a53cd 100644 --- a/include/linux/gpio/gpio-nomadik.h +++ b/include/linux/gpio/gpio-nomadik.h @@ -261,16 +261,14 @@ struct platform_device; * true. */ void nmk_gpio_dbg_show_one(struct seq_file *s, struct pinctrl_dev *pctldev, - struct gpio_chip *chip, unsigned int offset, - unsigned int gpio); + struct gpio_chip *chip, unsigned int offset); #else static inline void nmk_gpio_dbg_show_one(struct seq_file *s, struct pinctrl_dev *pctldev, struct gpio_chip *chip, - unsigned int offset, - unsigned int gpio) + unsigned int offset) { } diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index c722c67668c6..622a2939ebe0 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -6,6 +6,7 @@ struct device; struct fwnode_handle; struct gpio_regmap; +struct gpio_chip; struct irq_domain; struct regmap; @@ -40,6 +41,13 @@ struct regmap; * @drvdata: (Optional) Pointer to driver specific data which is * not used by gpio-remap but is provided "as is" to the * driver callback(s). + * @init_valid_mask: (Optional) Routine to initialize @valid_mask, to be used + * if not all GPIOs are valid. + * @regmap_irq_chip: (Optional) Pointer on an regmap_irq_chip structure. If + * set, a regmap-irq device will be created and the IRQ + * domain will be set accordingly. + * @regmap_irq_line (Optional) The IRQ the device uses to signal interrupts. + * @regmap_irq_flags (Optional) The IRQF_ flags to use for the interrupt. * * The ->reg_mask_xlate translates a given base address and GPIO offset to * register and mask pair. The base address is one of the given register @@ -78,10 +86,20 @@ struct gpio_regmap_config { int ngpio_per_reg; struct irq_domain *irq_domain; +#ifdef CONFIG_REGMAP_IRQ + struct regmap_irq_chip *regmap_irq_chip; + int regmap_irq_line; + unsigned long regmap_irq_flags; +#endif + int (*reg_mask_xlate)(struct gpio_regmap *gpio, unsigned int base, unsigned int offset, unsigned int *reg, unsigned int *mask); + int (*init_valid_mask)(struct gpio_chip *gc, + unsigned long *valid_mask, + unsigned int ngpios); + void *drvdata; }; diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h index 7ed3fdd55dda..45f181bcf890 100644 --- a/include/linux/habanalabs/cpucp_if.h +++ b/include/linux/habanalabs/cpucp_if.h @@ -1425,9 +1425,13 @@ struct cpucp_monitor_dump { * from "pkt_subidx" field in struct cpucp_packet. * * HL_PASSTHROUGHT_VERSIONS - Fetch all firmware versions. + * HL_GET_ERR_COUNTERS_CMD - Command to get error counters + * HL_GET_P_STATE - get performance state */ enum hl_passthrough_type { HL_PASSTHROUGH_VERSIONS, + HL_GET_ERR_COUNTERS_CMD, + HL_GET_P_STATE, }; #endif /* CPUCP_IF_H */ diff --git a/include/linux/hfs_common.h b/include/linux/hfs_common.h new file mode 100644 index 000000000000..8838ca2f3d08 --- /dev/null +++ b/include/linux/hfs_common.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HFS/HFS+ common definitions, inline functions, + * and shared functionality. + */ + +#ifndef _HFS_COMMON_H_ +#define _HFS_COMMON_H_ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#define hfs_dbg(fmt, ...) \ + pr_debug("pid %d:%s:%d %s(): " fmt, \ + current->pid, __FILE__, __LINE__, __func__, ##__VA_ARGS__) \ + +#endif /* _HFS_COMMON_H_ */ diff --git a/include/linux/hid.h b/include/linux/hid.h index 2cc4f1e4ea96..c32425b5d011 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -364,6 +364,7 @@ struct hid_item { * | @HID_QUIRK_HAVE_SPECIAL_DRIVER: * | @HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE: * | @HID_QUIRK_IGNORE_SPECIAL_DRIVER + * | @HID_QUIRK_POWER_ON_AFTER_BACKLIGHT * | @HID_QUIRK_FULLSPEED_INTERVAL: * | @HID_QUIRK_NO_INIT_REPORTS: * | @HID_QUIRK_NO_IGNORE: @@ -391,6 +392,7 @@ struct hid_item { #define HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE BIT(20) #define HID_QUIRK_NOINVERT BIT(21) #define HID_QUIRK_IGNORE_SPECIAL_DRIVER BIT(22) +#define HID_QUIRK_POWER_ON_AFTER_BACKLIGHT BIT(23) #define HID_QUIRK_FULLSPEED_INTERVAL BIT(28) #define HID_QUIRK_NO_INIT_REPORTS BIT(29) #define HID_QUIRK_NO_IGNORE BIT(30) diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 36053c3d6d64..0574c21ca45d 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -7,7 +7,7 @@ */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); -void *__kmap_local_page_prot(struct page *page, pgprot_t prot); +void *__kmap_local_page_prot(const struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); @@ -33,7 +33,7 @@ static inline void kmap_flush_tlb(unsigned long addr) { } #endif void *kmap_high(struct page *page); -void kunmap_high(struct page *page); +void kunmap_high(const struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); @@ -50,7 +50,7 @@ static inline void *kmap(struct page *page) return addr; } -static inline void kunmap(struct page *page) +static inline void kunmap(const struct page *page) { might_sleep(); if (!PageHighMem(page)) @@ -68,12 +68,12 @@ static inline void kmap_flush_unused(void) __kmap_flush_unused(); } -static inline void *kmap_local_page(struct page *page) +static inline void *kmap_local_page(const struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } -static inline void *kmap_local_page_try_from_panic(struct page *page) +static inline void *kmap_local_page_try_from_panic(const struct page *page) { if (!PageHighMem(page)) return page_address(page); @@ -81,13 +81,13 @@ static inline void *kmap_local_page_try_from_panic(struct page *page) return NULL; } -static inline void *kmap_local_folio(struct folio *folio, size_t offset) +static inline void *kmap_local_folio(const struct folio *folio, size_t offset) { - struct page *page = folio_page(folio, offset / PAGE_SIZE); + const struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } -static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) +static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } @@ -102,7 +102,7 @@ static inline void __kunmap_local(const void *vaddr) kunmap_local_indexed(vaddr); } -static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) +static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); @@ -113,7 +113,7 @@ static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) return __kmap_local_page_prot(page, prot); } -static inline void *kmap_atomic(struct page *page) +static inline void *kmap_atomic(const struct page *page) { return kmap_atomic_prot(page, kmap_prot); } @@ -173,32 +173,32 @@ static inline void *kmap(struct page *page) return page_address(page); } -static inline void kunmap_high(struct page *page) { } +static inline void kunmap_high(const struct page *page) { } static inline void kmap_flush_unused(void) { } -static inline void kunmap(struct page *page) +static inline void kunmap(const struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } -static inline void *kmap_local_page(struct page *page) +static inline void *kmap_local_page(const struct page *page) { return page_address(page); } -static inline void *kmap_local_page_try_from_panic(struct page *page) +static inline void *kmap_local_page_try_from_panic(const struct page *page) { return page_address(page); } -static inline void *kmap_local_folio(struct folio *folio, size_t offset) +static inline void *kmap_local_folio(const struct folio *folio, size_t offset) { return folio_address(folio) + offset; } -static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) +static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot) { return kmap_local_page(page); } @@ -215,7 +215,7 @@ static inline void __kunmap_local(const void *addr) #endif } -static inline void *kmap_atomic(struct page *page) +static inline void *kmap_atomic(const struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); @@ -225,7 +225,7 @@ static inline void *kmap_atomic(struct page *page) return page_address(page); } -static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) +static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot) { return kmap_atomic(page); } diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 6234f316468c..105cc4c00cc3 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -43,7 +43,7 @@ static inline void *kmap(struct page *page); * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ -static inline void kunmap(struct page *page); +static inline void kunmap(const struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address @@ -93,7 +93,7 @@ static inline void kmap_flush_unused(void); * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ -static inline void *kmap_local_page(struct page *page); +static inline void *kmap_local_page(const struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage @@ -129,7 +129,7 @@ static inline void *kmap_local_page(struct page *page); * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ -static inline void *kmap_local_folio(struct folio *folio, size_t offset); +static inline void *kmap_local_folio(const struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! @@ -176,7 +176,7 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ -static inline void *kmap_atomic(struct page *page); +static inline void *kmap_atomic(const struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1ef867bb8c44..2cf1bf65b225 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -154,14 +154,11 @@ static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) return ktime_to_ns(timer->node.expires); } -static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) -{ - return ktime_sub(timer->node.expires, timer->base->get_time()); -} +ktime_t hrtimer_cb_get_time(const struct hrtimer *timer); -static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) +static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { - return timer->base->get_time(); + return ktime_sub(timer->node.expires, hrtimer_cb_get_time(timer)); } static inline int hrtimer_is_hres_active(struct hrtimer *timer) @@ -200,8 +197,7 @@ __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { - return __hrtimer_expires_remaining_adjusted(timer, - timer->base->get_time()); + return __hrtimer_expires_remaining_adjusted(timer, hrtimer_cb_get_time(timer)); } #ifdef CONFIG_TIMERFD @@ -363,7 +359,7 @@ hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { - return hrtimer_forward(timer, timer->base->get_time(), interval); + return hrtimer_forward(timer, hrtimer_cb_get_time(timer), interval); } /* Precise sleep: */ diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h index 84a5045f80f3..aa49ffa130e5 100644 --- a/include/linux/hrtimer_defs.h +++ b/include/linux/hrtimer_defs.h @@ -41,7 +41,6 @@ * @seq: seqcount around __run_hrtimer * @running: pointer to the currently running hrtimer * @active: red black tree root node for the active timers - * @get_time: function to retrieve the current time of the clock * @offset: offset of this clock to the monotonic base */ struct hrtimer_clock_base { @@ -51,7 +50,6 @@ struct hrtimer_clock_base { seqcount_raw_spinlock_t seq; struct hrtimer *running; struct timerqueue_head active; - ktime_t (*get_time)(void); ktime_t offset; } __hrtimer_clock_base_align; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7748489fde1b..f327d62fc985 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -94,12 +94,15 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define THP_ORDERS_ALL \ (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT) -#define TVA_SMAPS (1 << 0) /* Will be used for procfs */ -#define TVA_IN_PF (1 << 1) /* Page fault handler */ -#define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */ +enum tva_type { + TVA_SMAPS, /* Exposing "THPeligible:" in smaps. */ + TVA_PAGEFAULT, /* Serving a page fault. */ + TVA_KHUGEPAGED, /* Khugepaged collapse. */ + TVA_FORCED_COLLAPSE, /* Forced collapse (e.g. MADV_COLLAPSE). */ +}; -#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ - (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) +#define thp_vma_allowable_order(vma, vm_flags, type, order) \ + (!!thp_vma_allowable_orders(vma, vm_flags, type, BIT(order))) #define split_folio(f) split_folio_to_list(f, NULL) @@ -264,14 +267,14 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, - unsigned long tva_flags, + enum tva_type type, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags - * @tva_flags: Which TVA flags to honour + * @type: TVA type * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed @@ -285,11 +288,14 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, - unsigned long tva_flags, + enum tva_type type, unsigned long orders) { - /* Optimization to check if required orders are enabled early. */ - if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { + /* + * Optimization to check if required orders are enabled early. Only + * forced collapse ignores sysfs configs. + */ + if (type != TVA_FORCED_COLLAPSE && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) @@ -303,7 +309,7 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return 0; } - return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); + return __thp_vma_allowable_orders(vma, vm_flags, type, orders); } struct thpsize { @@ -318,16 +324,32 @@ struct thpsize { (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +/* + * Check whether THPs are explicitly disabled for this VMA, for example, + * through madvise or prctl. + */ static inline bool vma_thp_disabled(struct vm_area_struct *vma, - vm_flags_t vm_flags) -{ + vm_flags_t vm_flags, bool forced_collapse) +{ + /* Are THPs disabled for this VMA? */ + if (vm_flags & VM_NOHUGEPAGE) + return true; + /* Are THPs disabled for all VMAs in the whole process? */ + if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, vma->vm_mm)) + return true; /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. + * Are THPs disabled only for VMAs where we didn't get an explicit + * advise to use them? */ - return (vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); + if (vm_flags & VM_HUGEPAGE) + return false; + /* + * Forcing a collapse (e.g., madv_collapse), is a clear advice to + * use THPs. + */ + if (forced_collapse) + return false; + return mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, vma->vm_mm); } static inline bool thp_disabled_by_hw(void) @@ -479,6 +501,8 @@ extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_folio(const struct folio *folio) { + VM_WARN_ON_ONCE(!folio); + return READ_ONCE(huge_zero_folio) == folio; } @@ -495,6 +519,17 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); +static inline struct folio *get_persistent_huge_zero_folio(void) +{ + if (!IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) + return NULL; + + if (unlikely(!huge_zero_folio)) + return NULL; + + return huge_zero_folio; +} + static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); @@ -526,7 +561,7 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, - unsigned long tva_flags, + enum tva_type type, unsigned long orders) { return 0; @@ -553,22 +588,26 @@ static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { - return 0; + VM_WARN_ON_ONCE_PAGE(1, page); + return -EINVAL; } static inline int split_huge_page(struct page *page) { - return 0; + VM_WARN_ON_ONCE_PAGE(1, page); + return -EINVAL; } static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { - return 0; + VM_WARN_ON_ONCE_FOLIO(1, folio); + return -EINVAL; } static inline int try_folio_split(struct folio *folio, struct page *page, struct list_head *list) { - return 0; + VM_WARN_ON_ONCE_FOLIO(1, folio); + return -EINVAL; } static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} @@ -685,6 +724,11 @@ static inline int change_huge_pud(struct mmu_gather *tlb, { return 0; } + +static inline struct folio *get_persistent_huge_zero_folio(void) +{ + return NULL; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, @@ -698,4 +742,26 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) return split_folio_to_list_to_order(folio, NULL, new_order); } +/** + * largest_zero_folio - Get the largest zero size folio available + * + * This function shall be used when mm_get_huge_zero_folio() cannot be + * used as there is no appropriate mm lifetime to tie the huge zero folio + * from the caller. + * + * Deduce the size of the folio with folio_size instead of assuming the + * folio size. + * + * Return: pointer to PMD sized zero folio if CONFIG_PERSISTENT_HUGE_ZERO_FOLIO + * is enabled or a single page sized zero folio + */ +static inline struct folio *largest_zero_folio(void) +{ + struct folio *folio = get_persistent_huge_zero_folio(); + + if (folio) + return folio; + + return page_folio(ZERO_PAGE(0)); +} #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 526d27e88b3b..8e63e46b8e1f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -788,9 +788,14 @@ static inline unsigned huge_page_shift(struct hstate *h) return h->order + PAGE_SHIFT; } +static inline bool order_is_gigantic(unsigned int order) +{ + return order > MAX_PAGE_ORDER; +} + static inline bool hstate_is_gigantic(struct hstate *h) { - return huge_page_order(h) > MAX_PAGE_ORDER; + return order_is_gigantic(huge_page_order(h)); } static inline unsigned int pages_per_huge_page(const struct hstate *h) diff --git a/include/linux/hw_bitfield.h b/include/linux/hw_bitfield.h new file mode 100644 index 000000000000..df202e167ce4 --- /dev/null +++ b/include/linux/hw_bitfield.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2025, Collabora Ltd. + */ + +#ifndef _LINUX_HW_BITFIELD_H +#define _LINUX_HW_BITFIELD_H + +#include <linux/bitfield.h> +#include <linux/build_bug.h> +#include <linux/limits.h> + +/** + * FIELD_PREP_WM16() - prepare a bitfield element with a mask in the upper half + * @_mask: shifted mask defining the field's length and position + * @_val: value to put in the field + * + * FIELD_PREP_WM16() masks and shifts up the value, as well as bitwise ORs the + * result with the mask shifted up by 16. + * + * This is useful for a common design of hardware registers where the upper + * 16-bit half of a 32-bit register is used as a write-enable mask. In such a + * register, a bit in the lower half is only updated if the corresponding bit + * in the upper half is high. + */ +#define FIELD_PREP_WM16(_mask, _val) \ + ({ \ + typeof(_val) __val = _val; \ + typeof(_mask) __mask = _mask; \ + __BF_FIELD_CHECK(__mask, ((u16)0U), __val, \ + "HWORD_UPDATE: "); \ + (((typeof(__mask))(__val) << __bf_shf(__mask)) & (__mask)) | \ + ((__mask) << 16); \ + }) + +/** + * FIELD_PREP_WM16_CONST() - prepare a constant bitfield element with a mask in + * the upper half + * @_mask: shifted mask defining the field's length and position + * @_val: value to put in the field + * + * FIELD_PREP_WM16_CONST() masks and shifts up the value, as well as bitwise ORs + * the result with the mask shifted up by 16. + * + * This is useful for a common design of hardware registers where the upper + * 16-bit half of a 32-bit register is used as a write-enable mask. In such a + * register, a bit in the lower half is only updated if the corresponding bit + * in the upper half is high. + * + * Unlike FIELD_PREP_WM16(), this is a constant expression and can therefore + * be used in initializers. Error checking is less comfortable for this + * version. + */ +#define FIELD_PREP_WM16_CONST(_mask, _val) \ + ( \ + FIELD_PREP_CONST(_mask, _val) | \ + (BUILD_BUG_ON_ZERO(const_true((u64)(_mask) > U16_MAX)) + \ + ((_mask) << 16)) \ + ) + + +#endif /* _LINUX_HW_BITFIELD_H */ diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 3a63dff62d03..301a83afbd66 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -24,6 +24,7 @@ enum hwmon_sensor_types { hwmon_curr, hwmon_power, hwmon_energy, + hwmon_energy64, hwmon_humidity, hwmon_fan, hwmon_pwm, @@ -491,6 +492,9 @@ int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, char *hwmon_sanitize_name(const char *name); char *devm_hwmon_sanitize_name(struct device *dev, const char *name); +void hwmon_lock(struct device *dev); +void hwmon_unlock(struct device *dev); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 20fd41b51d5c..11a19241e360 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -499,7 +499,7 @@ static inline struct i2c_client *i2c_verify_client(struct device *dev) * Modules for add-on boards must use other calls. */ #ifdef CONFIG_I2C_BOARDINFO -int +int __init i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n); #else diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 043f5c7ff398..c52a82dd79a6 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -558,6 +558,26 @@ struct i3c_master_controller { #define i3c_bus_for_each_i3cdev(bus, dev) \ list_for_each_entry(dev, &(bus)->devs.i3c, common.node) +/** + * struct i3c_dma - DMA transfer and mapping descriptor + * @dev: device object of a device doing DMA + * @buf: destination/source buffer for DMA + * @len: length of transfer + * @map_len: length of DMA mapping + * @addr: mapped DMA address for a Host Controller Driver + * @dir: DMA direction + * @bounce_buf: an allocated bounce buffer if transfer needs it or NULL + */ +struct i3c_dma { + struct device *dev; + void *buf; + size_t len; + size_t map_len; + dma_addr_t addr; + enum dma_data_direction dir; + void *bounce_buf; +}; + int i3c_master_do_i2c_xfers(struct i3c_master_controller *master, const struct i2c_msg *xfers, int nxfers); @@ -575,6 +595,12 @@ int i3c_master_get_free_addr(struct i3c_master_controller *master, int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, u8 addr); int i3c_master_do_daa(struct i3c_master_controller *master); +struct i3c_dma *i3c_master_dma_map_single(struct device *dev, void *ptr, + size_t len, bool force_bounce, + enum dma_data_direction dir); +void i3c_master_dma_unmap_single(struct i3c_dma *dma_xfer); +DEFINE_FREE(i3c_master_dma_unmap_single, void *, + if (_T) i3c_master_dma_unmap_single(_T)) int i3c_master_set_info(struct i3c_master_controller *master, const struct i3c_device_info *info); diff --git a/include/linux/idr.h b/include/linux/idr.h index 2267902d29a7..789e23e67444 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -334,14 +334,6 @@ static inline void ida_init(struct ida *ida) xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } -/* - * ida_simple_get() and ida_simple_remove() are deprecated. Use - * ida_alloc() and ida_free() instead respectively. - */ -#define ida_simple_get(ida, start, end, gfp) \ - ida_alloc_range(ida, start, (end) - 1, gfp) -#define ida_simple_remove(ida, id) ida_free(ida, id) - static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e5a2096e022e..ddff9102f633 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -220,6 +220,12 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_MAX_AID_S1G 8191 #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 + +/* S1G encoding types */ +#define IEEE80211_S1G_TIM_ENC_MODE_BLOCK 0 +#define IEEE80211_S1G_TIM_ENC_MODE_SINGLE 1 +#define IEEE80211_S1G_TIM_ENC_MODE_OLB 2 + /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section 6.2.1.1.2. @@ -1176,6 +1182,18 @@ enum ieee80211_s1g_chanwidth { IEEE80211_S1G_CHANWIDTH_16MHZ = 15, }; +/** + * enum ieee80211_s1g_pri_chanwidth - S1G primary channel widths + * described in IEEE80211-2024 Table 10-39. + * + * @IEEE80211_S1G_PRI_CHANWIDTH_2MHZ: 2MHz primary channel + * @IEEE80211_S1G_PRI_CHANWIDTH_1MHZ: 1MHz primary channel + */ +enum ieee80211_s1g_pri_chanwidth { + IEEE80211_S1G_PRI_CHANWIDTH_2MHZ = 0, + IEEE80211_S1G_PRI_CHANWIDTH_1MHZ = 1, +}; + #define WLAN_SA_QUERY_TR_ID_LEN 2 #define WLAN_MEMBERSHIP_LEN 8 #define WLAN_USER_POSITION_LEN 16 @@ -3164,8 +3182,12 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) -#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) +#define S1G_OPER_CH_WIDTH_PRIMARY BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) +#define S1G_OPER_CH_PRIMARY_LOCATION BIT(5) + +#define S1G_2M_PRIMARY_LOCATION_LOWER 0 +#define S1G_2M_PRIMARY_LOCATION_UPPER 1 /* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ #define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 @@ -4757,15 +4779,8 @@ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) return 1024 * tu; } -/** - * ieee80211_check_tim - check if AID bit is set in TIM - * @tim: the TIM IE - * @tim_len: length of the TIM IE - * @aid: the AID to look for - * Return: whether or not traffic is indicated in the TIM for the given AID - */ -static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, - u8 tim_len, u16 aid) +static inline bool __ieee80211_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid) { u8 mask; u8 index, indexn1, indexn2; @@ -4788,6 +4803,254 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, return !!(tim->virtual_map[index] & mask); } +struct s1g_tim_aid { + u16 aid; + u8 target_blk; /* Target block index */ + u8 target_subblk; /* Target subblock index */ + u8 target_subblk_bit; /* Target subblock bit */ +}; + +struct s1g_tim_enc_block { + u8 enc_mode; + bool inverse; + const u8 *ptr; + u8 len; + + /* + * For an OLB encoded block that spans multiple blocks, this + * is the offset into the span described by that encoded block. + */ + u8 olb_blk_offset; +}; + +/* + * Helper routines to quickly extract the length of an encoded block. Validation + * is also performed to ensure the length extracted lies within the TIM. + */ + +static inline int ieee80211_s1g_len_bitmap(const u8 *ptr, const u8 *end) +{ + u8 blkmap; + u8 n_subblks; + + if (ptr >= end) + return -EINVAL; + + blkmap = *ptr; + n_subblks = hweight8(blkmap); + + if (ptr + 1 + n_subblks > end) + return -EINVAL; + + return 1 + n_subblks; +} + +static inline int ieee80211_s1g_len_single(const u8 *ptr, const u8 *end) +{ + return (ptr + 1 > end) ? -EINVAL : 1; +} + +static inline int ieee80211_s1g_len_olb(const u8 *ptr, const u8 *end) +{ + if (ptr >= end) + return -EINVAL; + + return (ptr + 1 + *ptr > end) ? -EINVAL : 1 + *ptr; +} + +/* + * Enumerate all encoded blocks until we find the encoded block that describes + * our target AID. OLB is a special case as a single encoded block can describe + * multiple blocks as a single encoded block. + */ +static inline int ieee80211_s1g_find_target_block(struct s1g_tim_enc_block *enc, + const struct s1g_tim_aid *aid, + const u8 *ptr, const u8 *end) +{ + /* need at least block-control octet */ + while (ptr + 1 <= end) { + u8 ctrl = *ptr++; + u8 mode = ctrl & 0x03; + bool contains, inverse = ctrl & BIT(2); + u8 span, blk_off = ctrl >> 3; + int len; + + switch (mode) { + case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: + len = ieee80211_s1g_len_bitmap(ptr, end); + contains = blk_off == aid->target_blk; + break; + case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: + len = ieee80211_s1g_len_single(ptr, end); + contains = blk_off == aid->target_blk; + break; + case IEEE80211_S1G_TIM_ENC_MODE_OLB: + len = ieee80211_s1g_len_olb(ptr, end); + /* + * An OLB encoded block can describe more then one + * block, meaning an encoded OLB block can span more + * then a single block. + */ + if (len > 0) { + /* Minus one for the length octet */ + span = DIV_ROUND_UP(len - 1, 8); + /* + * Check if our target block lies within the + * block span described by this encoded block. + */ + contains = (aid->target_blk >= blk_off) && + (aid->target_blk < blk_off + span); + } + break; + default: + return -EOPNOTSUPP; + } + + if (len < 0) + return len; + + if (contains) { + enc->enc_mode = mode; + enc->inverse = inverse; + enc->ptr = ptr; + enc->len = (u8)len; + enc->olb_blk_offset = blk_off; + return 0; + } + + ptr += len; + } + + return -ENOENT; +} + +static inline bool ieee80211_s1g_parse_bitmap(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + const u8 *ptr = enc->ptr; + u8 blkmap = *ptr++; + + /* + * If our block bitmap does not contain a set bit that corresponds + * to our AID, it could mean a variety of things depending on if + * the encoding mode is inverted or not. + * + * 1. If inverted, it means the entire subblock is present and hence + * our AID has been set. + * 2. If not inverted, it means our subblock is not present and hence + * it is all zero meaning our AID is not set. + */ + if (!(blkmap & BIT(aid->target_subblk))) + return enc->inverse; + + /* + * Increment ptr by the number of set subblocks that appear before our + * target subblock. If our target subblock is 0, do nothing as ptr + * already points to our target subblock. + */ + if (aid->target_subblk) + ptr += hweight8(blkmap & GENMASK(aid->target_subblk - 1, 0)); + + return !!(*ptr & BIT(aid->target_subblk_bit)) ^ enc->inverse; +} + +static inline bool ieee80211_s1g_parse_single(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + /* + * Single AID mode describes, as the name suggests, a single AID + * within the block described by the encoded block. The octet + * contains the 6 LSBs of the AID described in the block. The other + * 2 bits are reserved. When inversed, every single AID described + * by the current block have buffered traffic except for the AID + * described in the single AID octet. + */ + return ((*enc->ptr & 0x3f) == (aid->aid & 0x3f)) ^ enc->inverse; +} + +static inline bool ieee80211_s1g_parse_olb(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + const u8 *ptr = enc->ptr; + u8 blk_len = *ptr++; + /* + * Given an OLB encoded block that describes multiple blocks, + * calculate the offset into the span. Then calculate the + * subblock location normally. + */ + u16 span_offset = aid->target_blk - enc->olb_blk_offset; + u16 subblk_idx = span_offset * 8 + aid->target_subblk; + + if (subblk_idx >= blk_len) + return enc->inverse; + + return !!(ptr[subblk_idx] & BIT(aid->target_subblk_bit)) ^ enc->inverse; +} + +/* + * An S1G PVB has 3 non optional encoding types, each that can be inverted. + * An S1G PVB is constructed with zero or more encoded block subfields. Each + * encoded block represents a single "block" of AIDs (64), and each encoded + * block can contain one of the 3 encoding types alongside a single bit for + * whether the bits should be inverted. + * + * As the standard makes no guarantee about the ordering of encoded blocks, + * we must parse every encoded block in the worst case scenario given an + * AID that lies within the last block. + */ +static inline bool ieee80211_s1g_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid) +{ + int err; + struct s1g_tim_aid target_aid; + struct s1g_tim_enc_block enc_blk; + + if (tim_len < 3) + return false; + + target_aid.aid = aid; + target_aid.target_blk = (aid >> 6) & 0x1f; + target_aid.target_subblk = (aid >> 3) & 0x7; + target_aid.target_subblk_bit = aid & 0x7; + + /* + * Find our AIDs target encoded block and fill &enc_blk with the + * encoded blocks information. If no entry is found or an error + * occurs return false. + */ + err = ieee80211_s1g_find_target_block(&enc_blk, &target_aid, + tim->virtual_map, + (const u8 *)tim + tim_len + 2); + if (err) + return false; + + switch (enc_blk.enc_mode) { + case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: + return ieee80211_s1g_parse_bitmap(&enc_blk, &target_aid); + case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: + return ieee80211_s1g_parse_single(&enc_blk, &target_aid); + case IEEE80211_S1G_TIM_ENC_MODE_OLB: + return ieee80211_s1g_parse_olb(&enc_blk, &target_aid); + default: + return false; + } +} + +/** + * ieee80211_check_tim - check if AID bit is set in TIM + * @tim: the TIM IE + * @tim_len: length of the TIM IE + * @aid: the AID to look for + * @s1g: whether the TIM is from an S1G PPDU + * Return: whether or not traffic is indicated in the TIM for the given AID + */ +static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid, bool s1g) +{ + return s1g ? ieee80211_s1g_check_tim(tim, tim_len, aid) : + __ieee80211_check_tim(tim, tim_len, aid); +} + /** * ieee80211_get_tdls_action - get TDLS action code * @skb: the skb containing the frame, length will not be checked @@ -5818,4 +6081,21 @@ static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) _data + ieee80211_mle_common_size(_data),\ _len - ieee80211_mle_common_size(_data)) +/* NAN operation mode, as defined in Wi-Fi Aware (TM) specification Table 81 */ +#define NAN_OP_MODE_PHY_MODE_VHT 0x01 +#define NAN_OP_MODE_PHY_MODE_HE 0x10 +#define NAN_OP_MODE_PHY_MODE_MASK 0x11 +#define NAN_OP_MODE_80P80MHZ 0x02 +#define NAN_OP_MODE_160MHZ 0x04 +#define NAN_OP_MODE_PNDL_SUPPRTED 0x08 + +/* NAN Device capabilities, as defined in Wi-Fi Aware (TM) specification + * Table 79 + */ +#define NAN_DEV_CAPA_DFS_OWNER 0x01 +#define NAN_DEV_CAPA_EXT_KEY_ID_SUPPORTED 0x02 +#define NAN_DEV_CAPA_SIM_NDP_RX_SUPPORTED 0x04 +#define NAN_DEV_CAPA_NDPE_SUPPORTED 0x08 +#define NAN_DEV_CAPA_S3_SUPPORTED 0x10 + #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index ff3beda1312c..db45d6f1c4f4 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -43,7 +43,7 @@ struct pppox_sock { /* struct sock must be the first member of pppox_sock */ struct sock sk; struct ppp_channel chan; - struct pppox_sock *next; /* for hash table */ + struct pppox_sock __rcu *next; /* for hash table */ union { struct pppoe_opt pppoe; struct pptp_opt pptp; diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index a9033696b0aa..704fd415c2b4 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -24,9 +24,6 @@ struct inet_diag_handler { bool net_admin, struct sk_buff *skb); - size_t (*idiag_get_aux_size)(struct sock *sk, - bool net_admin); - int (*destroy)(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req); @@ -41,6 +38,11 @@ struct inet_diag_dump_data { #define inet_diag_nla_bpf_stgs req_nlas[INET_DIAG_REQ_SK_BPF_STORAGES] struct bpf_sk_storage_diag *bpf_stg_diag; + bool mark_needed; /* INET_DIAG_BC_MARK_COND present. */ +#ifdef CONFIG_SOCK_CGROUP_DATA + bool cgroup_needed; /* INET_DIAG_BC_CGROUP_COND present. */ +#endif + bool userlocks_needed; /* INET_DIAG_BC_AUTO present. */ }; struct inet_connection_sock; @@ -48,18 +50,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, u16 nlmsg_flags, bool net_admin); -void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r); -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *req); - -struct sock *inet_diag_find_one_icsk(struct net *net, - struct inet_hashinfo *hashinfo, - const struct inet_diag_req_v2 *req); -int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); +int inet_diag_bc_sk(const struct inet_diag_dump_data *cb_data, struct sock *sk); void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index cfa6d0c0c322..7509025b4071 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -11,11 +11,14 @@ /* io_uring_cmd is being issued again */ #define IORING_URING_CMD_REISSUE (1U << 31) +typedef void (*io_uring_cmd_tw_t)(struct io_uring_cmd *cmd, + unsigned issue_flags); + struct io_uring_cmd { struct file *file; const struct io_uring_sqe *sqe; /* callback to defer completions to task context */ - void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); + io_uring_cmd_tw_t task_work_cb; u32 cmd_op; u32 flags; u8 pdu[32]; /* available inline for free use */ @@ -53,11 +56,11 @@ int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd, * Note: the caller should never hard code @issue_flags and is only allowed * to pass the mask provided by the core io_uring code. */ -void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, u64 res2, - unsigned issue_flags); +void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret, u64 res2, + unsigned issue_flags, bool is_cqe32); void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned), + io_uring_cmd_tw_t task_work_cb, unsigned flags); /* @@ -70,6 +73,21 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, /* Execute the request from a blocking context */ void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd); +/* + * Select a buffer from the provided buffer group for multishot uring_cmd. + * Returns the selected buffer address and size. + */ +struct io_br_sel io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd, + unsigned buf_group, size_t *len, + unsigned int issue_flags); + +/* + * Complete a multishot uring_cmd event. This will post a CQE to the completion + * queue and update the provided buffer. + */ +bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd, + struct io_br_sel *sel, unsigned int issue_flags); + #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, @@ -86,13 +104,12 @@ static inline int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd, { return -EOPNOTSUPP; } -static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, - u64 ret2, unsigned issue_flags) +static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret, + u64 ret2, unsigned issue_flags, bool is_cqe32) { } static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned), - unsigned flags) + io_uring_cmd_tw_t task_work_cb, unsigned flags) { } static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, @@ -102,28 +119,28 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, static inline void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd) { } -#endif - -/* - * Polled completions must ensure they are coming from a poll queue, and - * hence are completed inside the usual poll handling loops. - */ -static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd, - ssize_t ret, ssize_t res2) +static inline struct io_br_sel +io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd, unsigned buf_group, + size_t *len, unsigned int issue_flags) +{ + return (struct io_br_sel) { .val = -EOPNOTSUPP }; +} +static inline bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd, + struct io_br_sel *sel, unsigned int issue_flags) { - lockdep_assert(in_task()); - io_uring_cmd_done(ioucmd, ret, res2, 0); + return true; } +#endif /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) + io_uring_cmd_tw_t task_work_cb) { __io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE); } static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) + io_uring_cmd_tw_t task_work_cb) { __io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0); } @@ -142,6 +159,18 @@ static inline void *io_uring_cmd_ctx_handle(struct io_uring_cmd *cmd) return cmd_to_io_kiocb(cmd)->ctx; } +static inline void io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret, + unsigned issue_flags) +{ + return __io_uring_cmd_done(ioucmd, ret, 0, issue_flags, false); +} + +static inline void io_uring_cmd_done32(struct io_uring_cmd *ioucmd, s32 ret, + u64 res2, unsigned issue_flags) +{ + return __io_uring_cmd_done(ioucmd, ret, res2, issue_flags, true); +} + int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, void (*release)(void *), unsigned int index, unsigned int issue_flags); diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 80a178f3d896..c2ea6280901d 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -86,6 +86,25 @@ struct io_mapped_region { }; /* + * Return value from io_buffer_list selection, to avoid stashing it in + * struct io_kiocb. For legacy/classic provided buffers, keeping a reference + * across execution contexts are fine. But for ring provided buffers, the + * list may go away as soon as ->uring_lock is dropped. As the io_kiocb + * persists, it's better to just keep the buffer local for those cases. + */ +struct io_br_sel { + struct io_buffer_list *buf_list; + /* + * Some selection parts return the user address, others return an error. + */ + union { + void __user *addr; + ssize_t val; + }; +}; + + +/* * Arbitrary limit, can be raised if need be */ #define IO_RINGFD_REG_MAX 16 @@ -420,9 +439,6 @@ struct io_ring_ctx { struct list_head defer_list; unsigned nr_drained; - struct io_alloc_cache msg_cache; - spinlock_t msg_lock; - #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ @@ -674,12 +690,6 @@ struct io_kiocb { /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ struct io_buffer *kbuf; - /* - * stores buffer ID for ring provided buffers, valid IFF - * REQ_F_BUFFER_RING is set. - */ - struct io_buffer_list *buf_list; - struct io_rsrc_node *buf_node; }; @@ -727,10 +737,4 @@ struct io_overflow_cqe { struct list_head list; struct io_uring_cqe cqe; }; - -static inline bool io_ctx_cqe32(struct io_ring_ctx *ctx) -{ - return ctx->flags & IORING_SETUP_CQE32; -} - #endif diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 14f7eaf1b443..079d8773790c 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -118,8 +118,8 @@ struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); -int __copy_io(unsigned long clone_flags, struct task_struct *tsk); -static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +int __copy_io(u64 clone_flags, struct task_struct *tsk); +static inline int copy_io(u64 clone_flags, struct task_struct *tsk) { if (!current->io_context) return 0; @@ -129,7 +129,7 @@ static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } -static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +static inline int copy_io(u64 clone_flags, struct task_struct *tsk) { return 0; } diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 91324c331a4b..bdd2e0652bc3 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -14,62 +14,64 @@ #include <linux/io.h> /** - * read_poll_timeout - Periodically poll an address until a condition is - * met or a timeout occurs - * @op: accessor function (takes @args as its arguments) - * @val: Variable to read the value into - * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please - * read usleep_range() function description for details and + * poll_timeout_us - Periodically poll and perform an operation until + * a condition is met or a timeout occurs + * + * @op: Operation + * @cond: Break condition + * @sleep_us: Maximum time to sleep between operations in us (0 tight-loops). + * Please read usleep_range() function description for details and * limitations. * @timeout_us: Timeout in us, 0 means never timeout - * @sleep_before_read: if it is true, sleep @sleep_us before read. - * @args: arguments for @op poll + * @sleep_before_op: if it is true, sleep @sleep_us before operation. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. * - * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. Must not + * Returns: 0 on success and -ETIMEDOUT upon a timeout. Must not * be called from atomic context if sleep_us or timeout_us are used. */ -#define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ - sleep_before_read, args...) \ +#define poll_timeout_us(op, cond, sleep_us, timeout_us, sleep_before_op) \ ({ \ u64 __timeout_us = (timeout_us); \ unsigned long __sleep_us = (sleep_us); \ ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ + int ___ret; \ might_sleep_if((__sleep_us) != 0); \ - if (sleep_before_read && __sleep_us) \ + if ((sleep_before_op) && __sleep_us) \ usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ for (;;) { \ - (val) = op(args); \ - if (cond) \ + bool __expired = __timeout_us && \ + ktime_compare(ktime_get(), __timeout) > 0; \ + /* guarantee 'op' and 'cond' are evaluated after timeout expired */ \ + barrier(); \ + op; \ + if (cond) { \ + ___ret = 0; \ break; \ - if (__timeout_us && \ - ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = op(args); \ + } \ + if (__expired) { \ + ___ret = -ETIMEDOUT; \ break; \ } \ if (__sleep_us) \ usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ cpu_relax(); \ } \ - (cond) ? 0 : -ETIMEDOUT; \ + ___ret; \ }) /** - * read_poll_timeout_atomic - Periodically poll an address until a condition is - * met or a timeout occurs - * @op: accessor function (takes @args as its arguments) - * @val: Variable to read the value into - * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Please - * read udelay() function description for details and + * poll_timeout_us_atomic - Periodically poll and perform an operation until + * a condition is met or a timeout occurs + * + * @op: Operation + * @cond: Break condition + * @delay_us: Time to udelay between operations in us (0 tight-loops). + * Please read udelay() function description for details and * limitations. * @timeout_us: Timeout in us, 0 means never timeout - * @delay_before_read: if it is true, delay @delay_us before read. - * @args: arguments for @op poll + * @delay_before_op: if it is true, delay @delay_us before operation. * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock @@ -78,27 +80,32 @@ * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. * - * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. + * Returns: 0 on success and -ETIMEDOUT upon a timeout. */ -#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ - delay_before_read, args...) \ +#define poll_timeout_us_atomic(op, cond, delay_us, timeout_us, \ + delay_before_op) \ ({ \ u64 __timeout_us = (timeout_us); \ s64 __left_ns = __timeout_us * NSEC_PER_USEC; \ unsigned long __delay_us = (delay_us); \ u64 __delay_ns = __delay_us * NSEC_PER_USEC; \ - if (delay_before_read && __delay_us) { \ + int ___ret; \ + if ((delay_before_op) && __delay_us) { \ udelay(__delay_us); \ if (__timeout_us) \ __left_ns -= __delay_ns; \ } \ for (;;) { \ - (val) = op(args); \ - if (cond) \ + bool __expired = __timeout_us && __left_ns < 0; \ + /* guarantee 'op' and 'cond' are evaluated after timeout expired */ \ + barrier(); \ + op; \ + if (cond) { \ + ___ret = 0; \ break; \ - if (__timeout_us && __left_ns < 0) { \ - (val) = op(args); \ + } \ + if (__expired) { \ + ___ret = -ETIMEDOUT; \ break; \ } \ if (__delay_us) { \ @@ -110,10 +117,61 @@ if (__timeout_us) \ __left_ns--; \ } \ - (cond) ? 0 : -ETIMEDOUT; \ + ___ret; \ }) /** + * read_poll_timeout - Periodically poll an address until a condition is + * met or a timeout occurs + * @op: accessor function (takes @args as its arguments) + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. + * @timeout_us: Timeout in us, 0 means never timeout + * @sleep_before_read: if it is true, sleep @sleep_us before read. + * @args: arguments for @op poll + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. + */ +#define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ + sleep_before_read, args...) \ + poll_timeout_us((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read) + +/** + * read_poll_timeout_atomic - Periodically poll an address until a condition is + * met or a timeout occurs + * @op: accessor function (takes @args as its arguments) + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. + * @timeout_us: Timeout in us, 0 means never timeout + * @delay_before_read: if it is true, delay @delay_us before read. + * @args: arguments for @op poll + * + * This macro does not rely on timekeeping. Hence it is safe to call even when + * timekeeping is suspended, at the expense of an underestimation of wall clock + * time, which is rather minimal with a non-zero delay_us. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. + */ +#define read_poll_timeout_atomic(op, val, cond, sleep_us, timeout_us, \ + sleep_before_read, args...) \ + poll_timeout_us_atomic((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read) + +/** * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs * @op: accessor function (takes @addr as its only argument) * @addr: Address to poll diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e8240cf2611a..12faca29bbb9 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -129,20 +129,25 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif #if defined(CONFIG_IPC_NS) -extern struct ipc_namespace *copy_ipcs(unsigned long flags, +static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) +{ + return container_of(ns, struct ipc_namespace, ns); +} + +extern struct ipc_namespace *copy_ipcs(u64 flags, struct user_namespace *user_ns, struct ipc_namespace *ns); static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) { if (ns) { - if (refcount_inc_not_zero(&ns->ns.count)) + if (ns_ref_get(ns)) return ns; } @@ -151,7 +156,7 @@ static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns extern void put_ipc_ns(struct ipc_namespace *ns); #else -static inline struct ipc_namespace *copy_ipcs(unsigned long flags, +static inline struct ipc_namespace *copy_ipcs(u64 flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (flags & CLONE_NEWIPC) diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 5d69820d8b02..892e2d656e1e 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -109,8 +109,9 @@ struct ipmi_smi_msg { enum ipmi_smi_msg_type type; - long msgid; - void *user_data; + long msgid; + /* Response to this message, will be NULL if not from a user request. */ + struct ipmi_recv_msg *recv_msg; int data_size; unsigned char data[IPMI_MAX_MSG_LENGTH]; @@ -168,9 +169,11 @@ struct ipmi_smi_handlers { * are held when this is run. Message are delivered one at * a time by the message handler, a new message will not be * delivered until the previous message is returned. + * + * This can return an error if the SMI is not in a state where it + * can send a message. */ - void (*sender)(void *send_info, - struct ipmi_smi_msg *msg); + int (*sender)(void *send_info, struct ipmi_smi_msg *msg); /* * Called by the upper layer to request that we try to get diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bc6ec2959173..43b7bb828738 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -214,18 +214,21 @@ struct inet6_cork { /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { + /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ struct in6_addr saddr; - struct in6_pktinfo sticky_pktinfo; - const struct in6_addr *daddr_cache; + __be32 flow_label; + u32 dst_cookie; + struct ipv6_txoptions __rcu *opt; + s16 hop_limit; + u8 pmtudisc; + u8 tclass; #ifdef CONFIG_IPV6_SUBTREES - const struct in6_addr *saddr_cache; + bool saddr_cache; #endif + bool daddr_cache; - __be32 flow_label; - __u32 frag_size; - - s16 hop_limit; u8 mcast_hops; + u32 frag_size; int ucast_oif; int mcast_oif; @@ -233,7 +236,7 @@ struct ipv6_pinfo { /* pktoption flags */ union { struct { - __u16 srcrt:1, + u16 srcrt:1, osrcrt:1, rxinfo:1, rxoinfo:1, @@ -250,29 +253,25 @@ struct ipv6_pinfo { recvfragsize:1; /* 1 bits hole */ } bits; - __u16 all; + u16 all; } rxopt; /* sockopt flags */ - __u8 srcprefs; /* 001: prefer temporary address + u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ - __u8 pmtudisc; - __u8 min_hopcount; - __u8 tclass; + u8 min_hopcount; __be32 rcv_flowinfo; + struct in6_pktinfo sticky_pktinfo; - __u32 dst_cookie; + struct sk_buff *pktoptions; + struct sk_buff *rxpmtu; + struct inet6_cork cork; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; - - struct ipv6_txoptions __rcu *opt; - struct sk_buff *pktoptions; - struct sk_buff *rxpmtu; - struct inet6_cork cork; }; /* We currently use available bits from inet_sk(sk)->inet_flags, @@ -295,7 +294,7 @@ struct raw6_sock { __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; - + struct numa_drop_counters drop_counters; struct ipv6_pinfo inet6; }; diff --git a/include/linux/irq.h b/include/linux/irq.h index 1d6b606a81ef..c67e76fbcc07 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -669,6 +669,8 @@ extern int irq_chip_set_parent_state(struct irq_data *data, extern int irq_chip_get_parent_state(struct irq_data *data, enum irqchip_irq_state which, bool *state); +extern void irq_chip_shutdown_parent(struct irq_data *data); +extern unsigned int irq_chip_startup_parent(struct irq_data *data); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); @@ -976,10 +978,6 @@ static inline void irq_free_desc(unsigned int irq) irq_free_descs(irq, 1); } -#ifdef CONFIG_GENERIC_IRQ_LEGACY -void irq_init_desc(unsigned int irq); -#endif - /** * struct irq_chip_regs - register offsets for struct irq_gci * @enable: Enable register offset to reg_base diff --git a/include/linux/ism.h b/include/linux/ism.h index 8358b4cd7ba6..b7feb4dcd5a8 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -11,17 +11,6 @@ #include <linux/workqueue.h> -struct ism_dmb { - u64 dmb_tok; - u64 rgid; - u32 dmb_len; - u32 sba_idx; - u32 vlan_valid; - u32 vlan_id; - void *cpu_addr; - dma_addr_t dma_addr; -}; - /* Unless we gain unexpected popularity, this limit should hold for a while */ #define MAX_CLIENTS 8 #define ISM_NR_DMBS 1920 @@ -30,19 +19,17 @@ struct ism_dev { spinlock_t lock; /* protects the ism device */ spinlock_t cmd_lock; /* serializes cmds */ struct list_head list; + struct dibs_dev *dibs; struct pci_dev *pdev; struct ism_sba *sba; dma_addr_t sba_dma_addr; DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS); - u8 *sba_client_arr; /* entries are indices into 'clients' array */ void *priv[MAX_CLIENTS]; struct ism_eq *ieq; dma_addr_t ieq_dma_addr; - struct device dev; - u64 local_gid; int ieq_idx; struct ism_client *subs[MAX_CLIENTS]; @@ -58,14 +45,7 @@ struct ism_event { struct ism_client { const char *name; - void (*add)(struct ism_dev *dev); - void (*remove)(struct ism_dev *dev); void (*handle_event)(struct ism_dev *dev, struct ism_event *event); - /* Parameter dmbemask contains a bit vector with updated DMBEs, if sent - * via ism_move_data(). Callback function must handle all active bits - * indicated by dmbemask. - */ - void (*handle_irq)(struct ism_dev *dev, unsigned int bit, u16 dmbemask); /* Private area - don't touch! */ u8 id; }; @@ -82,12 +62,6 @@ static inline void ism_set_priv(struct ism_dev *dev, struct ism_client *client, dev->priv[client->id] = priv; } -int ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb, - struct ism_client *client); -int ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb); -int ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, - unsigned int offset, void *data, unsigned int size); - const struct smcd_ops *ism_get_smcd_ops(void); #endif /* _ISM_H */ diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 91b20788273d..0d1927da8055 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -61,7 +61,7 @@ extern void register_refined_jiffies(long clock_tick_rate); -/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */ +/* TICK_USEC is the time between ticks in usec */ #define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) /* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h index 6f612d69ea0c..9eca967d8526 100644 --- a/include/linux/kasan-enabled.h +++ b/include/linux/kasan-enabled.h @@ -4,32 +4,46 @@ #include <linux/static_key.h> -#ifdef CONFIG_KASAN_HW_TAGS - +#if defined(CONFIG_ARCH_DEFER_KASAN) || defined(CONFIG_KASAN_HW_TAGS) +/* + * Global runtime flag for KASAN modes that need runtime control. + * Used by ARCH_DEFER_KASAN architectures and HW_TAGS mode. + */ DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); +/* + * Runtime control for shadow memory initialization or HW_TAGS mode. + * Uses static key for architectures that need deferred KASAN or HW_TAGS. + */ static __always_inline bool kasan_enabled(void) { return static_branch_likely(&kasan_flag_enabled); } -static inline bool kasan_hw_tags_enabled(void) +static inline void kasan_enable(void) { - return kasan_enabled(); + static_branch_enable(&kasan_flag_enabled); } - -#else /* CONFIG_KASAN_HW_TAGS */ - -static inline bool kasan_enabled(void) +#else +/* For architectures that can enable KASAN early, use compile-time check. */ +static __always_inline bool kasan_enabled(void) { return IS_ENABLED(CONFIG_KASAN); } +static inline void kasan_enable(void) {} +#endif /* CONFIG_ARCH_DEFER_KASAN || CONFIG_KASAN_HW_TAGS */ + +#ifdef CONFIG_KASAN_HW_TAGS +static inline bool kasan_hw_tags_enabled(void) +{ + return kasan_enabled(); +} +#else static inline bool kasan_hw_tags_enabled(void) { return false; } - #endif /* CONFIG_KASAN_HW_TAGS */ #endif /* LINUX_KASAN_ENABLED_H */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 890011071f2b..d12e1a5f5a9a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -200,7 +200,7 @@ static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s, } bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init, - bool still_accessible); + bool still_accessible, bool no_quarantine); /** * kasan_slab_free - Poison, initialize, and quarantine a slab object. * @object: Object to be freed. @@ -226,11 +226,13 @@ bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init, * @Return true if KASAN took ownership of the object; false otherwise. */ static __always_inline bool kasan_slab_free(struct kmem_cache *s, - void *object, bool init, - bool still_accessible) + void *object, bool init, + bool still_accessible, + bool no_quarantine) { if (kasan_enabled()) - return __kasan_slab_free(s, object, init, still_accessible); + return __kasan_slab_free(s, object, init, still_accessible, + no_quarantine); return false; } @@ -427,7 +429,8 @@ static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) } static inline bool kasan_slab_free(struct kmem_cache *s, void *object, - bool init, bool still_accessible) + bool init, bool still_accessible, + bool no_quarantine) { return false; } @@ -543,6 +546,12 @@ void kasan_report_async(void); #endif /* CONFIG_KASAN_HW_TAGS */ +#ifdef CONFIG_KASAN_GENERIC +void __init kasan_init_generic(void); +#else +static inline void kasan_init_generic(void) { } +#endif + #ifdef CONFIG_KASAN_SW_TAGS void __init kasan_init_sw_tags(void); #else @@ -562,7 +571,7 @@ static inline void kasan_init_hw_tags(void) { } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); -int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, @@ -574,7 +583,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } @@ -610,7 +619,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start, static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 989315dabb86..5b46924fdff5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -164,11 +164,23 @@ extern int root_mountflags; extern bool early_boot_irqs_disabled; -/* - * Values used for system_state. Ordering of the states must not be changed +/** + * enum system_states - Values used for system_state. + * + * @SYSTEM_BOOTING: %0, no init needed + * @SYSTEM_SCHEDULING: system is ready for scheduling; OK to use RCU + * @SYSTEM_FREEING_INITMEM: system is freeing all of initmem; almost running + * @SYSTEM_RUNNING: system is up and running + * @SYSTEM_HALT: system entered clean system halt state + * @SYSTEM_POWER_OFF: system entered shutdown/clean power off state + * @SYSTEM_RESTART: system entered emergency power off or normal restart + * @SYSTEM_SUSPEND: system entered suspend or hibernate state + * + * Note: + * Ordering of the states must not be changed * as code checks for <, <=, >, >= STATE. */ -extern enum system_states { +enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, SYSTEM_FREEING_INITMEM, @@ -177,7 +189,8 @@ extern enum system_states { SYSTEM_POWER_OFF, SYSTEM_RESTART, SYSTEM_SUSPEND, -} system_state; +}; +extern enum system_states system_state; /* * General tracing related utility functions - trace_printk(), diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 1b10a5d84b68..ff7e231b0485 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -395,6 +395,9 @@ struct kimage { /* Information for loading purgatory */ struct purgatory_info purgatory_info; + + /* Force carrying over the DTB from the current boot */ + bool force_dtb; #endif #ifdef CONFIG_CRASH_HOTPLUG @@ -460,7 +463,8 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec file flags */ #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ - KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG) + KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG | \ + KEXEC_FILE_NO_CMA | KEXEC_FILE_FORCE_DTB) /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h index 348844cffb13..559d13a3bc44 100644 --- a/include/linux/kexec_handover.h +++ b/include/linux/kexec_handover.h @@ -40,6 +40,7 @@ struct kho_serialization; #ifdef CONFIG_KEXEC_HANDOVER bool kho_is_enabled(void); +bool is_kho_boot(void); int kho_preserve_folio(struct folio *folio); int kho_preserve_phys(phys_addr_t phys, size_t size); @@ -60,6 +61,11 @@ static inline bool kho_is_enabled(void) return false; } +static inline bool is_kho_boot(void) +{ + return false; +} + static inline int kho_preserve_folio(struct folio *folio) { return -EOPNOTSUPP; diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index ff6120463745..eb1946a70cff 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -2,6 +2,8 @@ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H +#include <linux/mm.h> + extern unsigned int khugepaged_max_ptes_none __read_mostly; #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -20,13 +22,13 @@ extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags)) + if (mm_flags_test(MMF_VM_HUGEPAGE, oldmm)) __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) { - if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) + if (mm_flags_test(MMF_VM_HUGEPAGE, mm)) __khugepaged_exit(mm); } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index c17b955e7b0b..067538fc4d58 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -56,13 +56,19 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { /* Adding mm to ksm is best effort on fork. */ - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) + if (mm_flags_test(MMF_VM_MERGEABLE, oldmm)) { + long nr_ksm_zero_pages = atomic_long_read(&mm->ksm_zero_pages); + + mm->ksm_merging_pages = 0; + mm->ksm_rmap_items = 0; + atomic_long_add(nr_ksm_zero_pages, &ksm_zero_pages); __ksm_enter(mm); + } } static inline int ksm_execve(struct mm_struct *mm) { - if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + if (mm_flags_test(MMF_VM_MERGE_ANY, mm)) return __ksm_enter(mm); return 0; @@ -70,7 +76,7 @@ static inline int ksm_execve(struct mm_struct *mm) static inline void ksm_exit(struct mm_struct *mm) { - if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) + if (mm_flags_test(MMF_VM_MERGEABLE, mm)) __ksm_exit(mm); } diff --git a/include/linux/list.h b/include/linux/list.h index e7e28afd28f8..5bfda2f91fca 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -20,8 +20,16 @@ * using the generic single-entry routines. */ +/** + * LIST_HEAD_INIT - initialize a &struct list_head's links to point to itself + * @name: name of the list_head + */ #define LIST_HEAD_INIT(name) { &(name), &(name) } +/** + * LIST_HEAD - definition of a &struct list_head with initialization values + * @name: name of the list_head + */ #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) @@ -637,6 +645,20 @@ static inline void list_splice_tail_init(struct list_head *list, }) /** + * list_last_entry_or_null - get the last element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_last_entry_or_null(ptr, type, member) ({ \ + struct list_head *head__ = (ptr); \ + struct list_head *pos__ = READ_ONCE(head__->prev); \ + pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ +}) + +/** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index 2ba846419524..0d91d060e3e9 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -66,6 +66,8 @@ */ #define local_trylock(lock) __local_trylock(this_cpu_ptr(lock)) +#define local_lock_is_locked(lock) __local_lock_is_locked(lock) + /** * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable * interrupts if acquired diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index d80b5306a2c0..a4dc479157b5 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -17,7 +17,10 @@ typedef struct { /* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */ typedef struct { - local_lock_t llock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; + struct task_struct *owner; +#endif u8 acquired; } local_trylock_t; @@ -31,7 +34,7 @@ typedef struct { .owner = NULL, # define LOCAL_TRYLOCK_DEBUG_INIT(lockname) \ - .llock = { LOCAL_LOCK_DEBUG_INIT((lockname).llock) }, + LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { @@ -81,7 +84,7 @@ do { \ local_lock_debug_init(lock); \ } while (0) -#define __local_trylock_init(lock) __local_lock_init(lock.llock) +#define __local_trylock_init(lock) __local_lock_init((local_lock_t *)lock) #define __spinlock_nested_bh_init(lock) \ do { \ @@ -162,6 +165,9 @@ do { \ !!tl; \ }) +/* preemption or migration must be disabled before calling __local_lock_is_locked */ +#define __local_lock_is_locked(lock) READ_ONCE(this_cpu_ptr(lock)->acquired) + #define __local_lock_release(lock) \ do { \ local_trylock_t *tl; \ @@ -282,4 +288,8 @@ do { \ __local_trylock(lock); \ }) +/* migration must be disabled before calling __local_lock_is_locked */ +#define __local_lock_is_locked(__lock) \ + (rt_mutex_owner(&this_cpu_ptr(__lock)->lock) == current) + #endif /* CONFIG_PREEMPT_RT */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index fd11fffdd3c3..adbe234a6f6c 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -211,7 +211,7 @@ LSM_HOOK(int, 0, file_open, struct file *file) LSM_HOOK(int, 0, file_post_open, struct file *file, int mask) LSM_HOOK(int, 0, file_truncate, struct file *file) LSM_HOOK(int, 0, task_alloc, struct task_struct *task, - unsigned long clone_flags) + u64 clone_flags) LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 090d1d3e19fe..79ec5a2bdcca 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -116,6 +116,9 @@ struct lsm_blob_sizes { int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ int lbs_tun_dev; int lbs_bdev; + int lbs_bpf_map; + int lbs_bpf_prog; + int lbs_bpf_token; }; /* diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index bafe143b1f78..66f98a3da8d8 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -57,17 +57,17 @@ * MT_FLAGS_ALLOC_RANGE flag. * * Node types: - * 0x??1 = Root - * 0x?00 = 16 bit nodes - * 0x010 = 32 bit nodes - * 0x110 = 64 bit nodes + * 0b??1 = Root + * 0b?00 = 16 bit nodes + * 0b010 = 32 bit nodes + * 0b110 = 64 bit nodes * * Slot size and location in the parent pointer: * type : slot location - * 0x??1 : Root - * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 - * 0x010 : 32 bit values, type in 0-2, slot in 3-6 - * 0x110 : 64 bit values, type in 0-2, slot in 3-6 + * 0b??1 : Root + * 0b?00 : 16 bit values, type in 0-1, slot in 2-6 + * 0b010 : 32 bit values, type in 0-2, slot in 3-6 + * 0b110 : 64 bit values, type in 0-2, slot in 3-6 */ /* @@ -194,7 +194,6 @@ enum store_type { #define MAPLE_RESERVED_RANGE 4096 #ifdef CONFIG_LOCKDEP -typedef struct lockdep_map *lockdep_map_p; #define mt_lock_is_held(mt) \ (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) @@ -207,7 +206,6 @@ typedef struct lockdep_map *lockdep_map_p; #define mt_on_stack(mt) (mt).ma_external_lock = NULL #else -typedef struct { /* nothing */ } lockdep_map_p; #define mt_lock_is_held(mt) 1 #define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) @@ -230,8 +228,10 @@ typedef struct { /* nothing */ } lockdep_map_p; */ struct maple_tree { union { - spinlock_t ma_lock; - lockdep_map_p ma_external_lock; + spinlock_t ma_lock; +#ifdef CONFIG_LOCKDEP + struct lockdep_map *ma_external_lock; +#endif }; unsigned int ma_flags; void __rcu *ma_root; @@ -442,7 +442,9 @@ struct ma_state { struct maple_enode *node; /* The node containing this entry */ unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ - struct maple_alloc *alloc; /* Allocated nodes for this operation */ + struct slab_sheaf *sheaf; /* Allocated nodes for this operation */ + struct maple_node *alloc; /* A single allocated node for fast path writes */ + unsigned long node_request; /* The number of nodes to allocate for this operation */ enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; @@ -481,6 +483,9 @@ struct ma_wr_state { #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) +/* + * When changing MA_STATE, remember to also change rust/kernel/maple_tree.rs + */ #define MA_STATE(name, mt, first, end) \ struct ma_state name = { \ .tree = mt, \ @@ -490,7 +495,9 @@ struct ma_wr_state { .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ + .sheaf = NULL, \ .alloc = NULL, \ + .node_request = 0, \ .mas_flags = 0, \ .store_type = wr_invalid, \ } diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 725fd7727422..a82755e1fc40 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -113,6 +113,7 @@ int mei_cldev_register_notif_cb(struct mei_cl_device *cldev, mei_cldev_cb_t notif_cb); u8 mei_cldev_ver(const struct mei_cl_device *cldev); +size_t mei_cldev_mtu(const struct mei_cl_device *cldev); void *mei_cldev_get_drvdata(const struct mei_cl_device *cldev); void mei_cldev_set_drvdata(struct mei_cl_device *cldev, void *data); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b96746376e17..fcda8481de9a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -40,8 +40,9 @@ extern unsigned long long max_possible_pfn; * via a driver, and never indicated in the firmware-provided memory map as * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the * kernel resource tree. - * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are - * not initialized (only for reserved regions). + * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not + * fully initialized. Users of this flag are responsible to properly initialize + * struct pages of this region * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use, * either explictitly with memblock_reserve_kern() or via memblock * allocation APIs. All memblock allocations set this flag. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 785173aa0739..16fe0306e50e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -341,17 +341,25 @@ enum page_memcg_data_flags { __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; +#define __OBJEXTS_ALLOC_FAIL MEMCG_DATA_OBJEXTS #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ +#define __OBJEXTS_ALLOC_FAIL (1UL << 0) #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { - /* slabobj_ext vector failed to allocate */ - OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, + /* + * Use bit 0 with zero other bits to signal that slabobj_ext vector + * failed to allocate. The same bit 0 with valid upper bits means + * MEMCG_DATA_OBJEXTS. + */ + OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, + /* slabobj_ext vector allocated with kmalloc_nolock() */ + OBJEXTS_NOSPIN_ALLOC = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; @@ -900,7 +908,13 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(gfp_t gfp_mask); +void __mem_cgroup_handle_over_high(gfp_t gfp_mask); + +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) +{ + if (unlikely(current->memcg_nr_pages_over_high)) + __mem_cgroup_handle_over_high(gfp_mask); +} unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1053,6 +1067,8 @@ extern int mem_cgroup_init(void); #define MEM_CGROUP_ID_SHIFT 0 +#define root_mem_cgroup (NULL) + static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; @@ -1596,14 +1612,16 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages, - gfp_t gfp_mask); -void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) + void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); +void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk); +bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, + gfp_t gfp_mask); +void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages); #if BITS_PER_LONG < 64 static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) @@ -1640,32 +1658,37 @@ static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) } #endif -static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) -{ -#ifdef CONFIG_MEMCG_V1 - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return !!memcg->tcpmem_pressure; -#endif /* CONFIG_MEMCG_V1 */ - do { - if (time_before64(get_jiffies_64(), mem_cgroup_get_socket_pressure(memcg))) - return true; - } while ((memcg = parent_mem_cgroup(memcg))); - return false; -} - int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 -static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; -static inline void mem_cgroup_sk_free(struct sock *sk) { }; -static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) + +static inline void mem_cgroup_sk_alloc(struct sock *sk) +{ +} + +static inline void mem_cgroup_sk_free(struct sock *sk) +{ +} + +static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) +{ +} + +static inline bool mem_cgroup_sk_charge(const struct sock *sk, + unsigned int nr_pages, + gfp_t gfp_mask) { return false; } +static inline void mem_cgroup_sk_uncharge(const struct sock *sk, + unsigned int nr_pages) +{ +} + static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 7b151441341b..34941a4b9026 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -15,7 +15,7 @@ struct kmem_cache; typedef void * (mempool_alloc_t)(gfp_t gfp_mask, void *pool_data); typedef void (mempool_free_t)(void *element, void *pool_data); -typedef struct mempool_s { +typedef struct mempool { spinlock_t lock; int min_nr; /* nr of elements at *elements */ int curr_nr; /* Current nr of elements at *elements */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 4aa151914eab..e5951ba12a28 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -157,45 +157,52 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) return 1 << pgmap->vmemmap_shift; } -static inline bool is_device_private_page(const struct page *page) +static inline bool folio_is_device_private(const struct folio *folio) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && - is_zone_device_page(page) && - page_pgmap(page)->type == MEMORY_DEVICE_PRIVATE; + folio_is_zone_device(folio) && + folio->pgmap->type == MEMORY_DEVICE_PRIVATE; } -static inline bool folio_is_device_private(const struct folio *folio) +static inline bool is_device_private_page(const struct page *page) { - return is_device_private_page(&folio->page); + return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + folio_is_device_private(page_folio(page)); } -static inline bool is_pci_p2pdma_page(const struct page *page) +static inline bool folio_is_pci_p2pdma(const struct folio *folio) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && - is_zone_device_page(page) && - page_pgmap(page)->type == MEMORY_DEVICE_PCI_P2PDMA; + folio_is_zone_device(folio) && + folio->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } -static inline bool is_device_coherent_page(const struct page *page) +static inline bool is_pci_p2pdma_page(const struct page *page) { - return is_zone_device_page(page) && - page_pgmap(page)->type == MEMORY_DEVICE_COHERENT; + return IS_ENABLED(CONFIG_PCI_P2PDMA) && + folio_is_pci_p2pdma(page_folio(page)); } static inline bool folio_is_device_coherent(const struct folio *folio) { - return is_device_coherent_page(&folio->page); + return folio_is_zone_device(folio) && + folio->pgmap->type == MEMORY_DEVICE_COHERENT; } -static inline bool is_fsdax_page(const struct page *page) +static inline bool is_device_coherent_page(const struct page *page) { - return is_zone_device_page(page) && - page_pgmap(page)->type == MEMORY_DEVICE_FS_DAX; + return folio_is_device_coherent(page_folio(page)); } static inline bool folio_is_fsdax(const struct folio *folio) { - return is_fsdax_page(&folio->page); + return folio_is_zone_device(folio) && + folio->pgmap->type == MEMORY_DEVICE_FS_DAX; +} + +static inline bool is_fsdax_page(const struct page *page) +{ + return folio_is_fsdax(page_folio(page)); } #ifdef CONFIG_ZONE_DEVICE @@ -204,8 +211,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); -struct dev_pagemap *get_dev_pagemap(unsigned long pfn, - struct dev_pagemap *pgmap); +struct dev_pagemap *get_dev_pagemap(unsigned long pfn); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); @@ -227,8 +233,7 @@ static inline void devm_memunmap_pages(struct device *dev, { } -static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, - struct dev_pagemap *pgmap) +static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn) { return NULL; } diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 2d13bbea4f3a..f72e6d4b14a7 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -117,8 +117,10 @@ struct arizona_pdata { /** Check for line output with HPDET method */ bool hpdet_acc_id_line; +#ifdef CONFIG_GPIOLIB_LEGACY /** GPIO used for mic isolation with HPDET */ int hpdet_id_gpio; +#endif /** Channel to use for headphone detection */ unsigned int hpdet_channel; @@ -129,8 +131,10 @@ struct arizona_pdata { /** Extra debounce timeout used during initial mic detection (ms) */ unsigned int micd_detect_debounce; +#ifdef CONFIG_GPIOLIB_LEGACY /** GPIO for mic detection polarity */ int micd_pol_gpio; +#endif /** Mic detect ramp rate */ unsigned int micd_bias_start_time; @@ -184,8 +188,10 @@ struct arizona_pdata { /** Haptic actuator type */ unsigned int hap_act; +#ifdef CONFIG_GPIOLIB_LEGACY /** GPIO for primary IRQ (used for edge triggered emulation) */ int irq_gpio; +#endif /** General purpose switch control */ unsigned int gpsw; diff --git a/include/linux/mfd/bq257xx.h b/include/linux/mfd/bq257xx.h new file mode 100644 index 000000000000..1d6ddc7fb09f --- /dev/null +++ b/include/linux/mfd/bq257xx.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Register definitions for TI BQ257XX + * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/ + */ + +#define BQ25703_CHARGE_OPTION_0 0x00 +#define BQ25703_CHARGE_CURRENT 0x02 +#define BQ25703_MAX_CHARGE_VOLT 0x04 +#define BQ25703_OTG_VOLT 0x06 +#define BQ25703_OTG_CURRENT 0x08 +#define BQ25703_INPUT_VOLTAGE 0x0a +#define BQ25703_MIN_VSYS 0x0c +#define BQ25703_IIN_HOST 0x0e +#define BQ25703_CHARGER_STATUS 0x20 +#define BQ25703_PROCHOT_STATUS 0x22 +#define BQ25703_IIN_DPM 0x24 +#define BQ25703_ADCIBAT_CHG 0x28 +#define BQ25703_ADCIINCMPIN 0x2a +#define BQ25703_ADCVSYSVBAT 0x2c +#define BQ25703_MANUFACT_DEV_ID 0x2e +#define BQ25703_CHARGE_OPTION_1 0x30 +#define BQ25703_CHARGE_OPTION_2 0x32 +#define BQ25703_CHARGE_OPTION_3 0x34 +#define BQ25703_ADC_OPTION 0x3a + +#define BQ25703_EN_LWPWR BIT(15) +#define BQ25703_WDTMR_ADJ_MASK GENMASK(14, 13) +#define BQ25703_WDTMR_DISABLE 0 +#define BQ25703_WDTMR_5_SEC 1 +#define BQ25703_WDTMR_88_SEC 2 +#define BQ25703_WDTMR_175_SEC 3 + +#define BQ25703_ICHG_MASK GENMASK(12, 6) +#define BQ25703_ICHG_STEP_UA 64000 +#define BQ25703_ICHG_MIN_UA 64000 +#define BQ25703_ICHG_MAX_UA 8128000 + +#define BQ25703_MAX_CHARGE_VOLT_MASK GENMASK(15, 4) +#define BQ25703_VBATREG_STEP_UV 16000 +#define BQ25703_VBATREG_MIN_UV 1024000 +#define BQ25703_VBATREG_MAX_UV 19200000 + +#define BQ25703_OTG_VOLT_MASK GENMASK(13, 6) +#define BQ25703_OTG_VOLT_STEP_UV 64000 +#define BQ25703_OTG_VOLT_MIN_UV 4480000 +#define BQ25703_OTG_VOLT_MAX_UV 20800000 +#define BQ25703_OTG_VOLT_NUM_VOLT 256 + +#define BQ25703_OTG_CUR_MASK GENMASK(14, 8) +#define BQ25703_OTG_CUR_STEP_UA 50000 +#define BQ25703_OTG_CUR_MAX_UA 6350000 + +#define BQ25703_MINVSYS_MASK GENMASK(13, 8) +#define BQ25703_MINVSYS_STEP_UV 256000 +#define BQ25703_MINVSYS_MIN_UV 1024000 +#define BQ25703_MINVSYS_MAX_UV 16128000 + +#define BQ25703_STS_AC_STAT BIT(15) +#define BQ25703_STS_IN_FCHRG BIT(10) +#define BQ25703_STS_IN_PCHRG BIT(9) +#define BQ25703_STS_FAULT_ACOV BIT(7) +#define BQ25703_STS_FAULT_BATOC BIT(6) +#define BQ25703_STS_FAULT_ACOC BIT(5) + +#define BQ25703_IINDPM_MASK GENMASK(14, 8) +#define BQ25703_IINDPM_STEP_UA 50000 +#define BQ25703_IINDPM_MIN_UA 50000 +#define BQ25703_IINDPM_MAX_UA 6400000 +#define BQ25703_IINDPM_DEFAULT_UA 3300000 +#define BQ25703_IINDPM_OFFSET_UA 50000 + +#define BQ25703_ADCIBAT_DISCHG_MASK GENMASK(6, 0) +#define BQ25703_ADCIBAT_CHG_MASK GENMASK(14, 8) +#define BQ25703_ADCIBAT_CHG_STEP_UA 64000 +#define BQ25703_ADCIBAT_DIS_STEP_UA 256000 + +#define BQ25703_ADCIIN GENMASK(15, 8) +#define BQ25703_ADCIINCMPIN_STEP 50000 + +#define BQ25703_ADCVSYS_MASK GENMASK(15, 8) +#define BQ25703_ADCVBAT_MASK GENMASK(7, 0) +#define BQ25703_ADCVSYSVBAT_OFFSET_UV 2880000 +#define BQ25703_ADCVSYSVBAT_STEP 64000 + +#define BQ25703_ADC_CH_MASK GENMASK(7, 0) +#define BQ25703_ADC_CONV_EN BIT(15) +#define BQ25703_ADC_START BIT(14) +#define BQ25703_ADC_FULL_SCALE BIT(13) +#define BQ25703_ADC_CMPIN_EN BIT(7) +#define BQ25703_ADC_VBUS_EN BIT(6) +#define BQ25703_ADC_PSYS_EN BIT(5) +#define BQ25703_ADC_IIN_EN BIT(4) +#define BQ25703_ADC_IDCHG_EN BIT(3) +#define BQ25703_ADC_ICHG_EN BIT(2) +#define BQ25703_ADC_VSYS_EN BIT(1) +#define BQ25703_ADC_VBAT_EN BIT(0) + +#define BQ25703_EN_OTG_MASK BIT(12) + +struct bq257xx_device { + struct i2c_client *client; + struct regmap *regmap; +}; diff --git a/include/linux/mfd/loongson-se.h b/include/linux/mfd/loongson-se.h new file mode 100644 index 000000000000..07afa0c2524d --- /dev/null +++ b/include/linux/mfd/loongson-se.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (C) 2025 Loongson Technology Corporation Limited */ + +#ifndef __MFD_LOONGSON_SE_H__ +#define __MFD_LOONGSON_SE_H__ + +#define LOONGSON_ENGINE_CMD_TIMEOUT_US 10000 +#define SE_SEND_CMD_REG 0x0 +#define SE_SEND_CMD_REG_LEN 0x8 +/* Controller command ID */ +#define SE_CMD_START 0x0 +#define SE_CMD_SET_DMA 0x3 +#define SE_CMD_SET_ENGINE_CMDBUF 0x4 + +#define SE_S2LINT_STAT 0x88 +#define SE_S2LINT_EN 0x8c +#define SE_S2LINT_CL 0x94 +#define SE_L2SINT_STAT 0x98 +#define SE_L2SINT_SET 0xa0 + +#define SE_INT_ALL 0xffffffff +#define SE_INT_CONTROLLER BIT(0) + +#define SE_ENGINE_MAX 16 +#define SE_ENGINE_RNG 1 +#define SE_CMD_RNG 0x100 + +#define SE_ENGINE_TPM 5 +#define SE_CMD_TPM 0x500 + +#define SE_ENGINE_CMD_SIZE 32 + +struct loongson_se_engine { + struct loongson_se *se; + int id; + + /* Command buffer */ + void *command; + void *command_ret; + + void *data_buffer; + uint buffer_size; + /* Data buffer offset to DMA base */ + uint buffer_off; + + struct completion completion; + +}; + +struct loongson_se_engine *loongson_se_init_engine(struct device *dev, int id); +int loongson_se_send_engine_cmd(struct loongson_se_engine *engine); + +#endif diff --git a/include/linux/mfd/max7360.h b/include/linux/mfd/max7360.h new file mode 100644 index 000000000000..44cf2bf651a2 --- /dev/null +++ b/include/linux/mfd/max7360.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __LINUX_MFD_MAX7360_H +#define __LINUX_MFD_MAX7360_H + +#include <linux/bits.h> + +#define MAX7360_MAX_KEY_ROWS 8 +#define MAX7360_MAX_KEY_COLS 8 +#define MAX7360_MAX_KEY_NUM (MAX7360_MAX_KEY_ROWS * MAX7360_MAX_KEY_COLS) +#define MAX7360_ROW_SHIFT 3 + +#define MAX7360_MAX_GPIO 8 +#define MAX7360_MAX_GPO 6 +#define MAX7360_PORT_PWM_COUNT 8 +#define MAX7360_PORT_RTR_PIN (MAX7360_PORT_PWM_COUNT - 1) + +/* + * MAX7360 registers + */ +#define MAX7360_REG_KEYFIFO 0x00 +#define MAX7360_REG_CONFIG 0x01 +#define MAX7360_REG_DEBOUNCE 0x02 +#define MAX7360_REG_INTERRUPT 0x03 +#define MAX7360_REG_PORTS 0x04 +#define MAX7360_REG_KEYREP 0x05 +#define MAX7360_REG_SLEEP 0x06 + +/* + * MAX7360 GPIO registers + * + * All these registers are reset together when writing bit 3 of + * MAX7360_REG_GPIOCFG. + */ +#define MAX7360_REG_GPIOCFG 0x40 +#define MAX7360_REG_GPIOCTRL 0x41 +#define MAX7360_REG_GPIODEB 0x42 +#define MAX7360_REG_GPIOCURR 0x43 +#define MAX7360_REG_GPIOOUTM 0x44 +#define MAX7360_REG_PWMCOM 0x45 +#define MAX7360_REG_RTRCFG 0x46 +#define MAX7360_REG_I2C_TIMEOUT 0x48 +#define MAX7360_REG_GPIOIN 0x49 +#define MAX7360_REG_RTR_CNT 0x4A +#define MAX7360_REG_PWMBASE 0x50 +#define MAX7360_REG_PWMCFGBASE 0x58 + +#define MAX7360_REG_GPIO_LAST 0x5F + +#define MAX7360_REG_PWM(x) (MAX7360_REG_PWMBASE + (x)) +#define MAX7360_REG_PWMCFG(x) (MAX7360_REG_PWMCFGBASE + (x)) + +/* + * Configuration register bits + */ +#define MAX7360_FIFO_EMPTY 0x3F +#define MAX7360_FIFO_OVERFLOW 0x7F +#define MAX7360_FIFO_RELEASE BIT(6) +#define MAX7360_FIFO_COL GENMASK(5, 3) +#define MAX7360_FIFO_ROW GENMASK(2, 0) + +#define MAX7360_CFG_SLEEP BIT(7) +#define MAX7360_CFG_INTERRUPT BIT(5) +#define MAX7360_CFG_KEY_RELEASE BIT(3) +#define MAX7360_CFG_WAKEUP BIT(1) +#define MAX7360_CFG_TIMEOUT BIT(0) + +#define MAX7360_DEBOUNCE GENMASK(4, 0) +#define MAX7360_DEBOUNCE_MIN 9 +#define MAX7360_DEBOUNCE_MAX 40 +#define MAX7360_PORTS GENMASK(8, 5) + +#define MAX7360_INTERRUPT_TIME_MASK GENMASK(4, 0) +#define MAX7360_INTERRUPT_FIFO_MASK GENMASK(7, 5) + +#define MAX7360_PORT_CFG_INTERRUPT_MASK BIT(7) +#define MAX7360_PORT_CFG_INTERRUPT_EDGES BIT(6) +#define MAX7360_PORT_CFG_COMMON_PWM BIT(5) + +/* + * Autosleep register values + */ +#define MAX7360_AUTOSLEEP_8192MS 0x01 +#define MAX7360_AUTOSLEEP_4096MS 0x02 +#define MAX7360_AUTOSLEEP_2048MS 0x03 +#define MAX7360_AUTOSLEEP_1024MS 0x04 +#define MAX7360_AUTOSLEEP_512MS 0x05 +#define MAX7360_AUTOSLEEP_256MS 0x06 + +#define MAX7360_GPIO_CFG_RTR_EN BIT(7) +#define MAX7360_GPIO_CFG_GPIO_EN BIT(4) +#define MAX7360_GPIO_CFG_GPIO_RST BIT(3) + +#define MAX7360_ROT_DEBOUNCE GENMASK(3, 0) +#define MAX7360_ROT_DEBOUNCE_MIN 0 +#define MAX7360_ROT_DEBOUNCE_MAX 15 +#define MAX7360_ROT_INTCNT GENMASK(6, 4) +#define MAX7360_ROT_INTCNT_DLY BIT(7) + +#define MAX7360_INT_INTI 0 +#define MAX7360_INT_INTK 1 + +#define MAX7360_INT_GPIO 0 +#define MAX7360_INT_KEYPAD 1 +#define MAX7360_INT_ROTARY 2 + +#define MAX7360_NR_INTERNAL_IRQS 3 + +#endif diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index f372926d5894..dd46fe424a80 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -31,12 +31,6 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode, unsigned int channel, u8 ato, bool atox, unsigned int *sample); -/* Deprecated calls */ -static inline int mc13xxx_irq_ack(struct mc13xxx *mc13xxx, int irq) -{ - return 0; -} - static inline int mc13xxx_irq_request_nounmask(struct mc13xxx *mc13xxx, int irq, irq_handler_t handler, const char *name, void *dev) diff --git a/include/linux/mfd/nct6694.h b/include/linux/mfd/nct6694.h new file mode 100644 index 000000000000..6eb9be2cd4a0 --- /dev/null +++ b/include/linux/mfd/nct6694.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Nuvoton Technology Corp. + * + * Nuvoton NCT6694 USB transaction and data structure. + */ + +#ifndef __MFD_NCT6694_H +#define __MFD_NCT6694_H + +#define NCT6694_VENDOR_ID 0x0416 +#define NCT6694_PRODUCT_ID 0x200B +#define NCT6694_INT_IN_EP 0x81 +#define NCT6694_BULK_IN_EP 0x02 +#define NCT6694_BULK_OUT_EP 0x03 + +#define NCT6694_HCTRL_SET 0x40 +#define NCT6694_HCTRL_GET 0x80 + +#define NCT6694_URB_TIMEOUT 1000 + +enum nct6694_irq_id { + NCT6694_IRQ_GPIO0 = 0, + NCT6694_IRQ_GPIO1, + NCT6694_IRQ_GPIO2, + NCT6694_IRQ_GPIO3, + NCT6694_IRQ_GPIO4, + NCT6694_IRQ_GPIO5, + NCT6694_IRQ_GPIO6, + NCT6694_IRQ_GPIO7, + NCT6694_IRQ_GPIO8, + NCT6694_IRQ_GPIO9, + NCT6694_IRQ_GPIOA, + NCT6694_IRQ_GPIOB, + NCT6694_IRQ_GPIOC, + NCT6694_IRQ_GPIOD, + NCT6694_IRQ_GPIOE, + NCT6694_IRQ_GPIOF, + NCT6694_IRQ_CAN0, + NCT6694_IRQ_CAN1, + NCT6694_IRQ_RTC, + NCT6694_NR_IRQS, +}; + +enum nct6694_response_err_status { + NCT6694_NO_ERROR = 0, + NCT6694_FORMAT_ERROR, + NCT6694_RESERVED1, + NCT6694_RESERVED2, + NCT6694_NOT_SUPPORT_ERROR, + NCT6694_NO_RESPONSE_ERROR, + NCT6694_TIMEOUT_ERROR, + NCT6694_PENDING, +}; + +struct __packed nct6694_cmd_header { + u8 rsv1; + u8 mod; + union __packed { + __le16 offset; + struct __packed { + u8 cmd; + u8 sel; + }; + }; + u8 hctrl; + u8 rsv2; + __le16 len; +}; + +struct __packed nct6694_response_header { + u8 sequence_id; + u8 sts; + u8 reserved[4]; + __le16 len; +}; + +union __packed nct6694_usb_msg { + struct nct6694_cmd_header cmd_header; + struct nct6694_response_header response_header; +}; + +struct nct6694 { + struct device *dev; + struct ida gpio_ida; + struct ida i2c_ida; + struct ida canfd_ida; + struct ida wdt_ida; + struct irq_domain *domain; + struct mutex access_lock; + spinlock_t irq_lock; + struct urb *int_in_urb; + struct usb_device *udev; + union nct6694_usb_msg *usb_msg; + __le32 *int_buffer; + unsigned int irq_enable; +}; + +int nct6694_read_msg(struct nct6694 *nct6694, const struct nct6694_cmd_header *cmd_hd, void *buf); +int nct6694_write_msg(struct nct6694 *nct6694, const struct nct6694_cmd_header *cmd_hd, void *buf); + +#endif diff --git a/include/linux/mfd/qnap-mcu.h b/include/linux/mfd/qnap-mcu.h index 8d48c212fd44..42bf523f9a5b 100644 --- a/include/linux/mfd/qnap-mcu.h +++ b/include/linux/mfd/qnap-mcu.h @@ -7,6 +7,8 @@ #ifndef _LINUX_QNAP_MCU_H_ #define _LINUX_QNAP_MCU_H_ +#include <linux/types.h> + struct qnap_mcu; struct qnap_mcu_variant { diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index ce786c96404a..73a71ef69152 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -189,6 +189,69 @@ enum { /* Charger/Battey */ #define BD71828_REG_CHG_STATE 0x65 #define BD71828_REG_CHG_FULL 0xd2 +#define BD71828_REG_CHG_EN 0x6F +#define BD71828_REG_DCIN_STAT 0x68 +#define BD71828_MASK_DCIN_DET 0x01 +#define BD71828_REG_VDCIN_U 0x9c +#define BD71828_MASK_CHG_EN 0x01 +#define BD71828_CHG_MASK_DCIN_U 0x0f +#define BD71828_REG_BAT_STAT 0x67 +#define BD71828_REG_BAT_TEMP 0x6c +#define BD71828_MASK_BAT_TEMP 0x07 +#define BD71828_BAT_TEMP_OPEN 0x07 +#define BD71828_MASK_BAT_DET 0x20 +#define BD71828_MASK_BAT_DET_DONE 0x10 +#define BD71828_REG_CHG_STATE 0x65 +#define BD71828_REG_VBAT_U 0x8c +#define BD71828_MASK_VBAT_U 0x0f +#define BD71828_REG_VBAT_REX_AVG_U 0x92 + +#define BD71828_REG_OCV_PWRON_U 0x8A + +#define BD71828_REG_VBAT_MIN_AVG_U 0x8e +#define BD71828_REG_VBAT_MIN_AVG_L 0x8f + +#define BD71828_REG_CC_CNT3 0xb5 +#define BD71828_REG_CC_CNT2 0xb6 +#define BD71828_REG_CC_CNT1 0xb7 +#define BD71828_REG_CC_CNT0 0xb8 +#define BD71828_REG_CC_CURCD_AVG_U 0xb2 +#define BD71828_MASK_CC_CURCD_AVG_U 0x3f +#define BD71828_MASK_CC_CUR_DIR 0x80 +#define BD71828_REG_VM_BTMP_U 0xa1 +#define BD71828_REG_VM_BTMP_L 0xa2 +#define BD71828_MASK_VM_BTMP_U 0x0f +#define BD71828_REG_COULOMB_CTRL 0xc4 +#define BD71828_REG_COULOMB_CTRL2 0xd2 +#define BD71828_MASK_REX_CC_CLR 0x01 +#define BD71828_MASK_FULL_CC_CLR 0x10 +#define BD71828_REG_CC_CNT_FULL3 0xbd +#define BD71828_REG_CC_CNT_CHG3 0xc1 + +#define BD71828_REG_VBAT_INITIAL1_U 0x86 +#define BD71828_REG_VBAT_INITIAL1_L 0x87 + +#define BD71828_REG_VBAT_INITIAL2_U 0x88 +#define BD71828_REG_VBAT_INITIAL2_L 0x89 + +#define BD71828_REG_IBAT_U 0xb0 +#define BD71828_REG_IBAT_L 0xb1 + +#define BD71828_REG_IBAT_AVG_U 0xb2 +#define BD71828_REG_IBAT_AVG_L 0xb3 + +#define BD71828_REG_VSYS_AVG_U 0x96 +#define BD71828_REG_VSYS_AVG_L 0x97 +#define BD71828_REG_VSYS_MIN_AVG_U 0x98 +#define BD71828_REG_VSYS_MIN_AVG_L 0x99 +#define BD71828_REG_CHG_SET1 0x75 +#define BD71828_REG_ALM_VBAT_LIMIT_U 0xaa +#define BD71828_REG_BATCAP_MON_LIMIT_U 0xcc +#define BD71828_REG_CONF 0x64 + +#define BD71828_REG_DCIN_CLPS 0x71 + +#define BD71828_REG_MEAS_CLEAR 0xaf /* LEDs */ #define BD71828_REG_LED_CTRL 0x4A diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 9af01bdd86d2..ca691641788b 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -32,6 +32,7 @@ #define PHY_ID_LAN8814 0x00221660 #define PHY_ID_LAN8804 0x00221670 #define PHY_ID_LAN8841 0x00221650 +#define PHY_ID_LAN8842 0x002216C0 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 9009e27b5f44..1f0ac122c3bf 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -12,14 +12,6 @@ typedef void free_folio_t(struct folio *folio, unsigned long private); struct migration_target_control; -/* - * Return values from addresss_space_operations.migratepage(): - * - negative errno on page migration failure; - * - zero on page migration success; - */ -#define MIGRATEPAGE_SUCCESS 0 -#define MIGRATEPAGE_UNMAP 1 - /** * struct movable_operations - Driver page migration * @isolate_page: @@ -35,8 +27,7 @@ struct migration_target_control; * @src page. The driver should copy the contents of the * @src page to the @dst page and set up the fields of @dst page. * Both pages are locked. - * If page migration is successful, the driver should - * return MIGRATEPAGE_SUCCESS. + * If page migration is successful, the driver should return 0. * If the driver cannot migrate the page at the moment, it can return * -EAGAIN. The VM interprets this as a temporary migration failure and * will retry it later. Any other error value is a permanent migration diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 991526039ccb..7ef2c7c7d803 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -41,7 +41,6 @@ struct mlx5_core_cq { int cqe_sz; __be32 *set_ci_db; __be32 *arm_db; - struct mlx5_uars_page *uar; refcount_t refcount; struct completion free; unsigned vector; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9d2467f982ad..d7f46a8fbfa1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1248,6 +1248,7 @@ enum mlx5_cap_type { MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, MLX5_CAP_SHAMPO = 0x1d, + MLX5_CAP_PSP = 0x1e, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1487,6 +1488,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_SHAMPO(mdev, cap) \ MLX5_GET(shampo_cap, mdev->caps.hca[MLX5_CAP_SHAMPO]->cur, cap) +#define MLX5_CAP_PSP(mdev, cap)\ + MLX5_GET(psp_cap, (mdev)->caps.hca[MLX5_CAP_PSP]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, @@ -1521,6 +1525,7 @@ enum { MLX5_PHYSICAL_LAYER_RECOVERY_GROUP = 0x1a, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21, + MLX5_RS_FEC_HISTOGRAM_GROUP = 0x23, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c5fbfb85749..5405ca1038f9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -130,12 +130,14 @@ enum { MLX5_REG_PDDR = 0x5031, MLX5_REG_PMLP = 0x5002, MLX5_REG_PPLM = 0x5023, + MLX5_REG_PPHCR = 0x503E, MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MTCAP = 0x9009, MLX5_REG_MTMP = 0x900A, MLX5_REG_MCIA = 0x9014, + MLX5_REG_MNVDA = 0x9024, MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, MLX5_REG_MRTC = 0x902d, @@ -432,7 +434,6 @@ struct mlx5_sq_bfreg { struct mlx5_uars_page *up; bool wc; u32 index; - unsigned int offset; }; struct mlx5_core_health { @@ -611,7 +612,7 @@ struct mlx5_priv { struct mlx5_ft_pool *ft_pool; struct mlx5_bfreg_data bfregs; - struct mlx5_uars_page *uar; + struct mlx5_sq_bfreg bfreg; #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; struct mlx5_sf_dev_table *sf_dev_table; @@ -657,12 +658,14 @@ struct mlx5e_resources { u32 pdn; struct mlx5_td td; u32 mkey; - struct mlx5_sq_bfreg bfreg; + struct mlx5_sq_bfreg *bfregs; + unsigned int num_bfregs; #define MLX5_MAX_NUM_TC 8 u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; + netdevice_tracker tracker; struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; @@ -801,6 +804,8 @@ struct mlx5_db { int index; }; +#define MLX5_DEFAULT_NUM_DOORBELLS 8 + enum { MLX5_COMP_EQ_SIZE = 1024, }; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 86055d55836d..6ac76a0c3827 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -308,6 +308,8 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); struct mlx5_fc *mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size); void mlx5_fc_local_destroy(struct mlx5_fc *counter); +void mlx5_fc_local_get(struct mlx5_fc *counter); +void mlx5_fc_local_put(struct mlx5_fc *counter); u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 8360d9011d4f..07614cd95bed 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -189,6 +189,9 @@ enum { MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, MLX5_CMD_OP_RELEASE_XRQ_ERROR = 0x729, MLX5_CMD_OP_MODIFY_XRQ = 0x72a, + MLX5_CMD_OPCODE_QUERY_DELEGATED_VHCA = 0x732, + MLX5_CMD_OPCODE_CREATE_ESW_VPORT = 0x733, + MLX5_CMD_OPCODE_DESTROY_ESW_VPORT = 0x734, MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, @@ -311,6 +314,8 @@ enum { MLX5_CMD_OP_CREATE_UMEM = 0xa08, MLX5_CMD_OP_DESTROY_UMEM = 0xa0a, MLX5_CMD_OP_SYNC_STEERING = 0xb00, + MLX5_CMD_OP_PSP_GEN_SPI = 0xb10, + MLX5_CMD_OP_PSP_ROTATE_KEY = 0xb11, MLX5_CMD_OP_QUERY_VHCA_STATE = 0xb0d, MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, @@ -486,12 +491,14 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; - u8 reserved_at_60[0x2]; + u8 reformat_l2_to_l3_psp_tunnel[0x1]; + u8 reformat_l3_psp_tunnel_to_l2[0x1]; u8 reformat_insert[0x1]; u8 reformat_remove[0x1]; u8 macsec_encrypt[0x1]; u8 macsec_decrypt[0x1]; - u8 reserved_at_66[0x2]; + u8 psp_encrypt[0x1]; + u8 psp_decrypt[0x1]; u8 reformat_add_macsec[0x1]; u8 reformat_remove_macsec[0x1]; u8 reparse[0x1]; @@ -700,7 +707,7 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 reserved_at_1a0[0x8]; + u8 psp_syndrome[0x8]; u8 macsec_syndrome[0x8]; u8 ipsec_syndrome[0x8]; u8 ipsec_next_header[0x8]; @@ -1508,6 +1515,21 @@ struct mlx5_ifc_macsec_cap_bits { u8 reserved_at_40[0x7c0]; }; +struct mlx5_ifc_psp_cap_bits { + u8 reserved_at_0[0x1]; + u8 psp_crypto_offload[0x1]; + u8 reserved_at_2[0x1]; + u8 psp_crypto_esp_aes_gcm_256_encrypt[0x1]; + u8 psp_crypto_esp_aes_gcm_128_encrypt[0x1]; + u8 psp_crypto_esp_aes_gcm_256_decrypt[0x1]; + u8 psp_crypto_esp_aes_gcm_128_decrypt[0x1]; + u8 reserved_at_7[0x4]; + u8 log_max_num_of_psp_spi[0x5]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x7e0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -1873,7 +1895,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2a0[0x7]; u8 mkey_pcie_tph[0x1]; - u8 reserved_at_2a8[0x3]; + u8 reserved_at_2a8[0x1]; + u8 tis_tir_td_order[0x1]; + + u8 psp[0x1]; u8 shampo[0x1]; u8 reserved_at_2ac[0x4]; u8 max_wqe_sz_rq[0x10]; @@ -1934,7 +1959,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_rqt[0x5]; u8 reserved_at_390[0x3]; u8 log_max_rqt_size[0x5]; - u8 reserved_at_398[0x3]; + u8 reserved_at_398[0x1]; + u8 vnic_env_cnt_bar_uar_access[0x1]; + u8 vnic_env_cnt_odp_page_fault[0x1]; u8 log_max_tis_per_sq[0x5]; u8 ext_stride_num_range[0x1]; @@ -2207,7 +2234,23 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_440[0x8]; u8 max_num_eqs_24b[0x18]; - u8 reserved_at_460[0x3a0]; + + u8 reserved_at_460[0x144]; + u8 load_balance_id[0x4]; + u8 reserved_at_5a8[0x18]; + + u8 query_adjacent_functions_id[0x1]; + u8 ingress_egress_esw_vport_connect[0x1]; + u8 function_id_type_vhca_id[0x1]; + u8 reserved_at_5c3[0x1]; + u8 lag_per_mp_group[0x1]; + u8 reserved_at_5c5[0xb]; + u8 delegate_vhca_management_profiles[0x10]; + + u8 delegated_vhca_max[0x10]; + u8 delegate_vhca_max[0x10]; + + u8 reserved_at_600[0x200]; }; enum mlx5_ifc_flow_destination_type { @@ -3788,6 +3831,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; struct mlx5_ifc_ipsec_cap_bits ipsec_cap; + struct mlx5_ifc_psp_cap_bits psp_cap; u8 reserved_at_0[0x8000]; }; @@ -3817,6 +3861,7 @@ enum { enum { MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC = 0x0, MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC = 0x1, + MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP = 0x2, }; struct mlx5_ifc_vlan_bits { @@ -3981,7 +4026,13 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 handled_pkt_steering_fail[0x40]; - u8 reserved_at_360[0xc80]; + u8 bar_uar_access[0x20]; + + u8 odp_local_triggered_page_fault[0x20]; + + u8 odp_remote_triggered_page_fault[0x20]; + + u8 reserved_at_3c0[0xc20]; }; struct mlx5_ifc_traffic_counter_bits { @@ -4863,6 +4914,11 @@ union mlx5_ifc_field_select_802_1_r_roce_auto_bits { u8 reserved_at_0[0x20]; }; +struct mlx5_ifc_rs_histogram_cntrs_bits { + u8 hist[16][0x40]; + u8 reserved_at_400[0x2c0]; +}; + union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; @@ -4877,6 +4933,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { 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; + struct mlx5_ifc_rs_histogram_cntrs_bits rs_histogram_cntrs; u8 reserved_at_0[0x7c0]; }; @@ -5159,7 +5216,9 @@ struct mlx5_ifc_set_hca_cap_in_bits { u8 other_function[0x1]; u8 ec_vf_function[0x1]; - u8 reserved_at_42[0xe]; + u8 reserved_at_42[0x1]; + u8 function_id_type[0x1]; + u8 reserved_at_44[0xc]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -6357,7 +6416,9 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 other_function[0x1]; u8 ec_vf_function[0x1]; - u8 reserved_at_42[0xe]; + u8 reserved_at_42[0x1]; + u8 function_id_type[0x1]; + u8 reserved_at_44[0xc]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -6983,6 +7044,28 @@ struct mlx5_ifc_query_esw_vport_context_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_destroy_esw_vport_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x20]; +}; + +struct mlx5_ifc_destroy_esw_vport_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vport_num[0x10]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_modify_esw_vport_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7118,6 +7201,8 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP = 0xa, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6 = 0xc, + MLX5_REFORMAT_TYPE_ADD_PSP_TUNNEL = 0xd, + MLX5_REFORMAT_TYPE_DEL_PSP_TUNNEL = 0xe, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, @@ -7244,6 +7329,7 @@ enum { MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, MLX5_ACTION_IN_FIELD_OUT_EMD_47_32 = 0x6F, MLX5_ACTION_IN_FIELD_OUT_EMD_31_0 = 0x70, + MLX5_ACTION_IN_FIELD_PSP_SYNDROME = 0x71, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -7484,6 +7570,85 @@ struct mlx5_ifc_query_adapter_in_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_function_vhca_rid_info_reg_bits { + u8 host_number[0x8]; + u8 host_pci_device_function[0x8]; + u8 host_pci_bus[0x8]; + u8 reserved_at_18[0x3]; + u8 pci_bus_assigned[0x1]; + u8 function_type[0x4]; + + u8 parent_pci_device_function[0x8]; + u8 parent_pci_bus[0x8]; + u8 vhca_id[0x10]; + + u8 reserved_at_40[0x10]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_delegated_function_vhca_rid_info_bits { + struct mlx5_ifc_function_vhca_rid_info_reg_bits function_vhca_rid_info; + + u8 reserved_at_80[0x18]; + u8 manage_profile[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_query_delegated_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 functions_count[0x10]; + + u8 reserved_at_80[0x80]; + + struct mlx5_ifc_delegated_function_vhca_rid_info_bits + delegated_function_vhca_rid_info[]; +}; + +struct mlx5_ifc_query_delegated_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_create_esw_vport_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 vport_num[0x10]; +}; + +struct mlx5_ifc_create_esw_vport_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 managed_vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_qp_2rst_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7611,7 +7776,12 @@ struct mlx5_ifc_modify_vport_state_in_bits { u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_at_60[0x18]; + u8 reserved_at_60[0x10]; + u8 ingress_connect[0x1]; + u8 egress_connect[0x1]; + u8 ingress_connect_valid[0x1]; + u8 egress_connect_valid[0x1]; + u8 reserved_at_74[0x4]; u8 admin_state[0x4]; u8 reserved_at_7c[0x4]; }; @@ -11587,6 +11757,28 @@ struct mlx5_ifc_mtctr_reg_bits { u8 second_clock_timestamp[0x40]; }; +struct mlx5_ifc_bin_range_layout_bits { + u8 reserved_at_0[0xa]; + u8 high_val[0x6]; + u8 reserved_at_10[0xa]; + u8 low_val[0x6]; +}; + +struct mlx5_ifc_pphcr_reg_bits { + u8 active_hist_type[0x4]; + u8 reserved_at_4[0x4]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x8]; + u8 num_of_bins[0x8]; + u8 reserved_at_30[0x10]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_bin_range_layout_bits bin_range[16]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -11653,6 +11845,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mtmp_reg_bits mtmp_reg; struct mlx5_ifc_mtptm_reg_bits mtptm_reg; struct mlx5_ifc_mtctr_reg_bits mtctr_reg; + struct mlx5_ifc_pphcr_reg_bits pphcr_reg; u8 reserved_at_0[0x60e0]; }; @@ -12954,6 +13147,7 @@ enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_TLS = 0x1, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_IPSEC = 0x2, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_MACSEC = 0x4, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_PSP = 0x6, }; struct mlx5_ifc_tls_static_params_bits { @@ -13371,4 +13565,64 @@ enum mlx5e_pcie_cong_event_mod_field { MLX5_PCIE_CONG_EVENT_MOD_THRESH = BIT(2), }; +struct mlx5_ifc_psp_rotate_key_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_psp_rotate_key_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum mlx5_psp_gen_spi_in_key_size { + MLX5_PSP_GEN_SPI_IN_KEY_SIZE_128 = 0x0, + MLX5_PSP_GEN_SPI_IN_KEY_SIZE_256 = 0x1, +}; + +struct mlx5_ifc_key_spi_bits { + u8 spi[0x20]; + + u8 reserved_at_20[0x60]; + + u8 key[8][0x20]; +}; + +struct mlx5_ifc_psp_gen_spi_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 key_size[0x2]; + u8 reserved_at_62[0xe]; + u8 num_of_spi[0x10]; +}; + +struct mlx5_ifc_psp_gen_spi_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x10]; + u8 num_of_spi[0x10]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_key_spi_bits key_spi[]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index fc7eeff99a8a..d67aedc6ea68 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -237,13 +237,11 @@ enum { }; enum { - MLX5_ETH_WQE_SVLAN = 1 << 0, MLX5_ETH_WQE_TRAILER_HDR_OUTER_IP_ASSOC = 1 << 26, MLX5_ETH_WQE_TRAILER_HDR_OUTER_L4_ASSOC = 1 << 27, MLX5_ETH_WQE_TRAILER_HDR_INNER_IP_ASSOC = 3 << 26, MLX5_ETH_WQE_TRAILER_HDR_INNER_L4_ASSOC = 1 << 28, MLX5_ETH_WQE_INSERT_TRAILER = 1 << 30, - MLX5_ETH_WQE_INSERT_VLAN = 1 << 15, }; enum { @@ -253,9 +251,15 @@ enum { MLX5_ETH_WQE_SWP_OUTER_L4_UDP = 1 << 5, }; +/* Metadata bits 0-7 are used by timestamping */ +/* Base shift for metadata bits used by IPsec and MACsec */ +#define MLX5_ETH_WQE_FT_META_SHIFT 8 + enum { - MLX5_ETH_WQE_FT_META_IPSEC = BIT(0), - MLX5_ETH_WQE_FT_META_MACSEC = BIT(1), + MLX5_ETH_WQE_FT_META_IPSEC = BIT(0) << MLX5_ETH_WQE_FT_META_SHIFT, + MLX5_ETH_WQE_FT_META_MACSEC = BIT(1) << MLX5_ETH_WQE_FT_META_SHIFT, + MLX5_ETH_WQE_FT_META_MACSEC_FS_ID_MASK = + GENMASK(5, 2) << MLX5_ETH_WQE_FT_META_SHIFT, }; struct mlx5_wqe_eth_seg { @@ -275,10 +279,6 @@ struct mlx5_wqe_eth_seg { DECLARE_FLEX_ARRAY(u8, data); }; } inline_hdr; - struct { - __be16 type; - __be16 vlan_tci; - } insert; __be32 trailer; }; }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index c36cc6d82926..c87b9507cfa1 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -135,4 +135,6 @@ int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev); u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev); int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *out, u16 opmod); +int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id); + #endif /* __MLX5_VPORT_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ae97a0b8ec7..06978b4dbeb8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -34,6 +34,8 @@ #include <linux/slab.h> #include <linux/cacheinfo.h> #include <linux/rcuwait.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> struct mempolicy; struct anon_vma; @@ -69,6 +71,15 @@ static inline void totalram_pages_add(long count) extern void * high_memory; +/* + * Convert between pages and MB + * 20 is the shift for 1MB (2^20 = 1MB) + * PAGE_SHIFT is the shift for page size (e.g., 12 for 4KB pages) + * So (20 - PAGE_SHIFT) converts between pages and MB + */ +#define PAGES_TO_MB(pages) ((pages) >> (20 - PAGE_SHIFT)) +#define MB_TO_PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) + #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else @@ -198,11 +209,13 @@ extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; #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)) +bool page_range_contiguous(const struct page *page, unsigned long nr_pages); #else -#define nth_page(page,n) ((page) + (n)) -#define folio_page_idx(folio, p) ((p) - &(folio)->page) +static inline bool page_range_contiguous(const struct page *page, + unsigned long nr_pages) +{ + return true; +} #endif /* to align the pointer to the (next) page boundary */ @@ -214,6 +227,20 @@ extern unsigned long sysctl_admin_reserve_kbytes; /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) +/** + * folio_page_idx - Return the number of a page in a folio. + * @folio: The folio. + * @page: The folio page. + * + * This function expects that the page is actually part of the folio. + * The returned number is relative to the start of the folio. + */ +static inline unsigned long folio_page_idx(const struct folio *folio, + const struct page *page) +{ + return page - &folio->page; +} + static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); @@ -648,13 +675,21 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif +#ifdef CONFIG_FIND_NORMAL_PAGE /* - * Called by vm_normal_page() for special PTEs to find the - * page for @addr. This is useful if the default behavior - * (using pte_page()) would not find the correct page. + * Called by vm_normal_page() for special PTEs in @vma at @addr. This + * allows for returning a "normal" page from vm_normal_page() even + * though the PTE indicates that the "struct page" either does not exist + * or should not be touched: "special". + * + * Do not add new users: this really only works when a "normal" page + * was mapped, but then the PTE got changed to something weird (+ + * marked special) that would not make pte_pfn() identify the originally + * inserted page. */ - struct page *(*find_special_page)(struct vm_area_struct *vma, - unsigned long addr); + struct page *(*find_normal_page)(struct vm_area_struct *vma, + unsigned long addr); +#endif /* CONFIG_FIND_NORMAL_PAGE */ }; #ifdef CONFIG_NUMA_BALANCING @@ -684,7 +719,7 @@ static inline void release_fault_lock(struct vm_fault *vmf) mmap_read_unlock(vmf->vma->vm_mm); } -static inline void assert_fault_locked(struct vm_fault *vmf) +static inline void assert_fault_locked(const struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); @@ -697,12 +732,42 @@ static inline void release_fault_lock(struct vm_fault *vmf) mmap_read_unlock(vmf->vma->vm_mm); } -static inline void assert_fault_locked(struct vm_fault *vmf) +static inline void assert_fault_locked(const struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ +static inline bool mm_flags_test(int flag, const struct mm_struct *mm) +{ + return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +static inline bool mm_flags_test_and_set(int flag, struct mm_struct *mm) +{ + return test_and_set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +static inline bool mm_flags_test_and_clear(int flag, struct mm_struct *mm) +{ + return test_and_clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +static inline void mm_flags_set(int flag, struct mm_struct *mm) +{ + set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +static inline void mm_flags_clear(int flag, struct mm_struct *mm) +{ + clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + +static inline void mm_flags_clear_all(struct mm_struct *mm) +{ + bitmap_zero(ACCESS_PRIVATE(&mm->flags, __mm_flags), NUM_MM_FLAG_BITS); +} + extern const struct vm_operations_struct vma_dummy_vm_ops; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) @@ -810,7 +875,7 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) vma->vm_end >= vma->vm_mm->start_stack; } -static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) +static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -824,7 +889,7 @@ static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) return false; } -static inline bool vma_is_foreign(struct vm_area_struct *vma) +static inline bool vma_is_foreign(const struct vm_area_struct *vma) { if (!current->mm) return true; @@ -835,7 +900,7 @@ static inline bool vma_is_foreign(struct vm_area_struct *vma) return false; } -static inline bool vma_is_accessible(struct vm_area_struct *vma) +static inline bool vma_is_accessible(const struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } @@ -846,7 +911,7 @@ static inline bool is_shared_maywrite(vm_flags_t vm_flags) (VM_SHARED | VM_MAYWRITE); } -static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) +static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } @@ -930,14 +995,14 @@ static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ -bool vma_is_shmem(struct vm_area_struct *vma); -bool vma_is_anon_shmem(struct vm_area_struct *vma); +bool vma_is_shmem(const struct vm_area_struct *vma); +bool vma_is_anon_shmem(const struct vm_area_struct *vma); #else -static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } -static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } +static inline bool vma_is_shmem(const struct vm_area_struct *vma) { return false; } +static inline bool vma_is_anon_shmem(const struct vm_area_struct *vma) { return false; } #endif -int vma_is_stack_for_current(struct vm_area_struct *vma); +int vma_is_stack_for_current(const struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } @@ -953,12 +1018,12 @@ static inline unsigned int folio_large_order(const struct folio *folio) } #ifdef NR_PAGES_IN_LARGE_FOLIO -static inline long folio_large_nr_pages(const struct folio *folio) +static inline unsigned long folio_large_nr_pages(const struct folio *folio) { return folio->_nr_pages; } #else -static inline long folio_large_nr_pages(const struct folio *folio) +static inline unsigned long folio_large_nr_pages(const struct folio *folio) { return 1L << folio_large_order(folio); } @@ -971,11 +1036,11 @@ static inline long folio_large_nr_pages(const struct folio *folio) * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ -static inline unsigned int compound_order(struct page *page) +static inline unsigned int compound_order(const struct page *page) { - struct folio *folio = (struct folio *)page; + const struct folio *folio = (struct folio *)page; - if (!test_bit(PG_head, &folio->flags)) + if (!test_bit(PG_head, &folio->flags.f)) return 0; return folio_large_order(folio); } @@ -1191,7 +1256,7 @@ int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ -static inline unsigned long page_size(struct page *page) +static inline unsigned long page_size(const struct page *page) { return PAGE_SIZE << compound_order(page); } @@ -1505,21 +1570,26 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags) */ static inline int page_zone_id(struct page *page) { - return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; + return (page->flags.f >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS -int page_to_nid(const struct page *page); +int memdesc_nid(memdesc_flags_t mdf); #else -static inline int page_to_nid(const struct page *page) +static inline int memdesc_nid(memdesc_flags_t mdf) { - return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; + return (mdf.f >> NODES_PGSHIFT) & NODES_MASK; } #endif +static inline int page_to_nid(const struct page *page) +{ + return memdesc_nid(PF_POISONED_CHECK(page)->flags); +} + static inline int folio_nid(const struct folio *folio) { - return page_to_nid(&folio->page); + return memdesc_nid(folio->flags); } #ifdef CONFIG_NUMA_BALANCING @@ -1588,14 +1658,14 @@ static inline void page_cpupid_reset_last(struct page *page) #else static inline int folio_last_cpupid(struct folio *folio) { - return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; + return (folio->flags.f >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { - page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; + page->flags.f |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ @@ -1691,7 +1761,7 @@ static inline u8 page_kasan_tag(const struct page *page) u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { - tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag = (page->flags.f >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } @@ -1706,12 +1776,12 @@ static inline void page_kasan_tag_set(struct page *page, u8 tag) return; tag ^= 0xff; - old_flags = READ_ONCE(page->flags); + old_flags = READ_ONCE(page->flags.f); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } while (unlikely(!try_cmpxchg(&page->flags.f, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) @@ -1742,26 +1812,26 @@ static inline pg_data_t *page_pgdat(const struct page *page) return NODE_DATA(page_to_nid(page)); } -static inline struct zone *folio_zone(const struct folio *folio) +static inline pg_data_t *folio_pgdat(const struct folio *folio) { - return page_zone(&folio->page); + return NODE_DATA(folio_nid(folio)); } -static inline pg_data_t *folio_pgdat(const struct folio *folio) +static inline struct zone *folio_zone(const struct folio *folio) { - return page_pgdat(&folio->page); + return &folio_pgdat(folio)->node_zones[folio_zonenum(folio)]; } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { - page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); - page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; + page->flags.f &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); + page->flags.f |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } -static inline unsigned long page_to_section(const struct page *page) +static inline unsigned long memdesc_section(memdesc_flags_t mdf) { - return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; + return (mdf.f >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif @@ -1785,7 +1855,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) } #ifdef CONFIG_MMU -static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) +static inline pte_t mk_pte(const struct page *page, pgprot_t pgprot) { return pfn_pte(page_to_pfn(page), pgprot); } @@ -1800,7 +1870,7 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) * * Return: A page table entry suitable for mapping this folio. */ -static inline pte_t folio_mk_pte(struct folio *folio, pgprot_t pgprot) +static inline pte_t folio_mk_pte(const struct folio *folio, pgprot_t pgprot) { return pfn_pte(folio_pfn(folio), pgprot); } @@ -1816,7 +1886,7 @@ static inline pte_t folio_mk_pte(struct folio *folio, pgprot_t pgprot) * * Return: A page table entry suitable for mapping this folio. */ -static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot) +static inline pmd_t folio_mk_pmd(const struct folio *folio, pgprot_t pgprot) { return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot)); } @@ -1832,7 +1902,7 @@ static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot) * * Return: A page table entry suitable for mapping this folio. */ -static inline pud_t folio_mk_pud(struct folio *folio, pgprot_t pgprot) +static inline pud_t folio_mk_pud(const struct folio *folio, pgprot_t pgprot) { return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot)); } @@ -1900,7 +1970,7 @@ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); - if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) + if (!mm_flags_test(MMF_HAS_PINNED, vma->vm_mm)) return false; return folio_maybe_dma_pinned(folio); @@ -1966,14 +2036,14 @@ static inline bool folio_is_longterm_pinnable(struct folio *folio) static inline void set_page_zone(struct page *page, enum zone_type zone) { - page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); - page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; + page->flags.f &= ~(ZONES_MASK << ZONES_PGSHIFT); + page->flags.f |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { - page->flags &= ~(NODES_MASK << NODES_PGSHIFT); - page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; + page->flags.f &= ~(NODES_MASK << NODES_PGSHIFT); + page->flags.f |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, @@ -1992,30 +2062,46 @@ static inline void set_page_links(struct page *page, enum zone_type zone, * * Return: A positive power of two. */ -static inline long folio_nr_pages(const struct folio *folio) +static inline unsigned long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; return folio_large_nr_pages(folio); } -/* Only hugetlbfs can allocate folios larger than MAX_ORDER */ -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -#define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) +#if !defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) +/* + * We don't expect any folios that exceed buddy sizes (and consequently + * memory sections). + */ +#define MAX_FOLIO_ORDER MAX_PAGE_ORDER +#elif defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +/* + * Only pages within a single memory section are guaranteed to be + * contiguous. By limiting folios to a single memory section, all folio + * pages are guaranteed to be contiguous. + */ +#define MAX_FOLIO_ORDER PFN_SECTION_SHIFT #else -#define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES +/* + * There is no real limit on the folio size. We limit them to the maximum we + * currently expect (e.g., hugetlb, dax). + */ +#define MAX_FOLIO_ORDER PUD_ORDER #endif +#define MAX_FOLIO_NR_PAGES (1UL << MAX_FOLIO_ORDER) + /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ -static inline long compound_nr(struct page *page) +static inline unsigned long compound_nr(const struct page *page) { - struct folio *folio = (struct folio *)page; + const struct folio *folio = (struct folio *)page; - if (!test_bit(PG_head, &folio->flags)) + if (!test_bit(PG_head, &folio->flags.f)) return 1; return folio_large_nr_pages(folio); } @@ -2351,6 +2437,8 @@ struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); +struct page *vm_normal_page_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t pud); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); @@ -2529,7 +2617,7 @@ void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, - struct task_struct *task, bool bypass_rlim); + const struct task_struct *task, bool bypass_rlim); struct kvec; struct page *get_dump_page(unsigned long addr, int *locked); @@ -2654,7 +2742,7 @@ static inline void update_hiwater_rss(struct mm_struct *mm) unsigned long _rss = get_mm_rss(mm); if (data_race(mm->hiwater_rss) < _rss) - (mm)->hiwater_rss = _rss; + data_race(mm->hiwater_rss = _rss); } static inline void update_hiwater_vm(struct mm_struct *mm) @@ -2846,16 +2934,22 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } #endif /* CONFIG_MMU */ +enum pt_flags { + PT_reserved = PG_reserved, + /* High bits are used for zone/node/section */ +}; + static inline struct ptdesc *virt_to_ptdesc(const void *x) { return page_ptdesc(virt_to_page(x)); } -static inline void *ptdesc_to_virt(const struct ptdesc *pt) -{ - return page_to_virt(ptdesc_page(pt)); -} - +/** + * ptdesc_address - Virtual address of page table. + * @pt: Page table descriptor. + * + * Return: The first byte of the page table described by @pt. + */ static inline void *ptdesc_address(const struct ptdesc *pt) { return folio_address(ptdesc_folio(pt)); @@ -2863,7 +2957,7 @@ static inline void *ptdesc_address(const struct ptdesc *pt) static inline bool pagetable_is_reserved(struct ptdesc *pt) { - return folio_test_reserved(ptdesc_folio(pt)); + return test_bit(PT_reserved, &pt->pt_flags.f); } /** @@ -2973,21 +3067,26 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ +static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) +{ + return compound_nr(ptdesc_page(ptdesc)); +} + static inline void __pagetable_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __SetPageTable(ptdesc_page(ptdesc)); + mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); + __ClearPageTable(ptdesc_page(ptdesc)); + mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) @@ -3292,7 +3391,7 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ -extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); +extern int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, @@ -3432,7 +3531,7 @@ struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) return mtree_load(&mm->mm_mt, addr); } -static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +static inline unsigned long stack_guard_start_gap(const struct vm_area_struct *vma) { if (vma->vm_flags & VM_GROWSDOWN) return stack_guard_gap; @@ -3444,7 +3543,7 @@ static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) return 0; } -static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +static inline unsigned long vm_start_gap(const struct vm_area_struct *vma) { unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; @@ -3455,7 +3554,7 @@ static inline unsigned long vm_start_gap(struct vm_area_struct *vma) return vm_start; } -static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +static inline unsigned long vm_end_gap(const struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; @@ -3467,7 +3566,7 @@ static inline unsigned long vm_end_gap(struct vm_area_struct *vma) return vm_end; } -static inline unsigned long vma_pages(struct vm_area_struct *vma) +static inline unsigned long vma_pages(const struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } @@ -3484,7 +3583,7 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } -static inline bool range_in_vma(struct vm_area_struct *vma, +static inline bool range_in_vma(const struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); @@ -3600,7 +3699,7 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ -static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, +static inline bool gup_can_follow_protnone(const struct vm_area_struct *vma, unsigned int flags) { /* @@ -3730,7 +3829,7 @@ static inline bool debug_guardpage_enabled(void) return static_branch_unlikely(&_debug_guardpage_enabled); } -static inline bool page_is_guard(struct page *page) +static inline bool page_is_guard(const struct page *page) { if (!debug_guardpage_enabled()) return false; @@ -3761,7 +3860,7 @@ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } -static inline bool page_is_guard(struct page *page) { return false; } +static inline bool page_is_guard(const struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, @@ -3784,7 +3883,7 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) } #endif /* __HAVE_ARCH_GATE_AREA */ -extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); +bool process_shares_mm(const struct task_struct *p, const struct mm_struct *mm); void drop_slab(void); @@ -3843,7 +3942,7 @@ void vmemmap_free(unsigned long start, unsigned long end, #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP -static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ if (altmap) @@ -3857,7 +3956,7 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap, altmap->alloc -= nr_pfns; } #else -static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { return 0; } diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 89b518ff097e..d6c1011b38f2 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -25,7 +25,7 @@ * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ -static inline int folio_is_file_lru(struct folio *folio) +static inline int folio_is_file_lru(const struct folio *folio) { return !folio_test_swapbacked(folio); } @@ -84,7 +84,7 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio) * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ -static __always_inline enum lru_list folio_lru_list(struct folio *folio) +static __always_inline enum lru_list folio_lru_list(const struct folio *folio) { enum lru_list lru; @@ -141,9 +141,9 @@ static inline int lru_tier_from_refs(int refs, bool workingset) return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } -static inline int folio_lru_refs(struct folio *folio) +static inline int folio_lru_refs(const struct folio *folio) { - unsigned long flags = READ_ONCE(folio->flags); + unsigned long flags = READ_ONCE(folio->flags.f); if (!(flags & BIT(PG_referenced))) return 0; @@ -154,14 +154,14 @@ static inline int folio_lru_refs(struct folio *folio) return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } -static inline int folio_lru_gen(struct folio *folio) +static inline int folio_lru_gen(const struct folio *folio) { - unsigned long flags = READ_ONCE(folio->flags); + unsigned long flags = READ_ONCE(folio->flags.f); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } -static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +static inline bool lru_gen_is_active(const struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; @@ -217,12 +217,13 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } -static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, +static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec, + const struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); - struct lru_gen_folio *lrugen = &lruvec->lrugen; + const struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ @@ -268,7 +269,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + set_mask_bits(&folio->flags.f, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ @@ -293,7 +294,7 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; - flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); + flags = set_mask_bits(&folio->flags.f, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); @@ -302,11 +303,11 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return true; } -static inline void folio_migrate_refs(struct folio *new, struct folio *old) +static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { - unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; + unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK; - set_mask_bits(&new->flags, LRU_REFS_MASK, refs); + set_mask_bits(&new->flags.f, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ @@ -330,7 +331,7 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return false; } -static inline void folio_migrate_refs(struct folio *new, struct folio *old) +static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { } @@ -508,7 +509,7 @@ static inline void dec_tlb_flush_pending(struct mm_struct *mm) atomic_dec(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +static inline bool mm_tlb_flush_pending(const struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that @@ -521,7 +522,7 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +static inline bool mm_tlb_flush_nested(const struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL @@ -605,7 +606,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, return false; } -static inline bool vma_has_recency(struct vm_area_struct *vma) +static inline bool vma_has_recency(const struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 08bc2442db93..90e5790c318f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -20,6 +20,7 @@ #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <linux/types.h> +#include <linux/bitmap.h> #include <asm/mmu.h> @@ -33,6 +34,10 @@ struct address_space; struct futex_private_hash; struct mem_cgroup; +typedef struct { + unsigned long f; +} memdesc_flags_t; + /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -71,7 +76,7 @@ struct mem_cgroup; #endif struct page { - unsigned long flags; /* Atomic flags, some possibly + memdesc_flags_t flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. @@ -89,21 +94,10 @@ struct page { union { struct list_head lru; - /* Or, for the Unevictable "LRU list" slot */ - struct { - /* Always even, to negate PageTail */ - void *__filler; - /* Count page's or folio's mlocks */ - unsigned int mlock_count; - }; - /* Or, free page */ struct list_head buddy_list; struct list_head pcp_list; - struct { - struct llist_node pcp_llist; - unsigned int order; - }; + struct llist_node pcp_llist; }; struct address_space *mapping; union { @@ -114,7 +108,8 @@ struct page { * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if swapcache flag set. - * Indicates order in the buddy system if PageBuddy. + * Indicates order in the buddy system if PageBuddy + * or on pcp_llist. */ unsigned long private; }; @@ -382,11 +377,13 @@ struct folio { union { struct { /* public: */ - unsigned long flags; + memdesc_flags_t flags; union { struct list_head lru; /* private: avoid cluttering the output */ + /* For the Unevictable "LRU list" slot */ struct { + /* Avoid compound_head */ void *__filler; /* public: */ unsigned int mlock_count; @@ -525,7 +522,7 @@ FOLIO_MATCH(compound_head, _head_3); /** * struct ptdesc - Memory descriptor for page tables. - * @__page_flags: Same as page flags. Powerpc only. + * @pt_flags: enum pt_flags plus zone/node/section. * @pt_rcu_head: For freeing page table pages. * @pt_list: List of used page tables. Used for s390 gmap shadow pages * (which are not linked into the user page tables) and x86 @@ -547,7 +544,7 @@ FOLIO_MATCH(compound_head, _head_3); * understanding of the issues. */ struct ptdesc { - unsigned long __page_flags; + memdesc_flags_t pt_flags; union { struct rcu_head pt_rcu_head; @@ -585,7 +582,7 @@ struct ptdesc { #define TABLE_MATCH(pg, pt) \ static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt)) -TABLE_MATCH(flags, __page_flags); +TABLE_MATCH(flags, pt_flags); TABLE_MATCH(compound_head, pt_list); TABLE_MATCH(compound_head, _pt_pad_1); TABLE_MATCH(mapping, __page_mapping); @@ -627,10 +624,15 @@ static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) atomic_dec(&ptdesc->pt_share_count); } -static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +static inline int ptdesc_pmd_pts_count(const struct ptdesc *ptdesc) { return atomic_read(&ptdesc->pt_share_count); } + +static inline bool ptdesc_pmd_is_shared(struct ptdesc *ptdesc) +{ + return !!ptdesc_pmd_pts_count(ptdesc); +} #else static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) { @@ -655,7 +657,7 @@ static inline void set_page_private(struct page *page, unsigned long private) page->private = private; } -static inline void *folio_get_private(struct folio *folio) +static inline void *folio_get_private(const struct folio *folio) { return folio->private; } @@ -780,13 +782,14 @@ struct pfnmap_track_ctx { */ struct vm_area_desc { /* Immutable state. */ - struct mm_struct *mm; + const struct mm_struct *const mm; + struct file *const file; /* May vary from vm_file in stacked callers. */ unsigned long start; unsigned long end; /* Mutable fields. Populated with initial state. */ pgoff_t pgoff; - struct file *file; + struct file *vm_file; vm_flags_t vm_flags; pgprot_t page_prot; @@ -927,6 +930,15 @@ struct mm_cid { }; #endif +/* + * Opaque type representing current mm_struct flag state. Must be accessed via + * mm_flags_xxx() helper functions. + */ +#define NUM_MM_FLAG_BITS (64) +typedef struct { + DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS); +} __private mm_flags_t; + struct kioctx_table; struct iommu_mm_data; struct mm_struct { @@ -1026,10 +1038,10 @@ struct mm_struct { * counters */ /* - * With some kernel config, the current mmap_lock's offset - * inside 'mm_struct' is at 0x120, which is very optimal, as + * Typically the current mmap_lock's offset is 56 bytes from + * the last cacheline boundary, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different - * cachelines, and when mmap_lock is highly contended, both + * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * @@ -1102,6 +1114,11 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ +#ifdef CONFIG_ARCH_HAS_ELF_CORE_EFLAGS + /* the ABI-related flags from the ELF header. Used for core dump */ + unsigned long saved_e_flags; +#endif + struct percpu_counter rss_stat[NR_MM_COUNTERS]; struct linux_binfmt *binfmt; @@ -1109,7 +1126,7 @@ struct mm_struct { /* Architecture-specific MM context */ mm_context_t context; - unsigned long flags; /* Must use atomic bitops to access */ + mm_flags_t flags; /* Must use mm_flags_* hlpers to access */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; @@ -1219,6 +1236,40 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; +/* Set the first system word of mm flags, non-atomically. */ +static inline void __mm_flags_set_word(struct mm_struct *mm, unsigned long value) +{ + unsigned long *bitmap = ACCESS_PRIVATE(&mm->flags, __mm_flags); + + bitmap_copy(bitmap, &value, BITS_PER_LONG); +} + +/* Obtain a read-only view of the bitmap. */ +static inline const unsigned long *__mm_flags_get_bitmap(const struct mm_struct *mm) +{ + return (const unsigned long *)ACCESS_PRIVATE(&mm->flags, __mm_flags); +} + +/* Read the first system word of mm flags, non-atomically. */ +static inline unsigned long __mm_flags_get_word(const struct mm_struct *mm) +{ + const unsigned long *bitmap = __mm_flags_get_bitmap(mm); + + return bitmap_read(bitmap, 0, BITS_PER_LONG); +} + +/* + * Update the first system word of mm flags ONLY, applying the specified mask to + * it, then setting all flags specified by bits. + */ +static inline void __mm_flags_set_mask_bits_word(struct mm_struct *mm, + unsigned long mask, unsigned long bits) +{ + unsigned long *bitmap = ACCESS_PRIVATE(&mm->flags, __mm_flags); + + set_mask_bits(bitmap, mask, bits); +} + #define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; @@ -1719,7 +1770,7 @@ enum { * the modes are SUID_DUMP_* defined in linux/sched/coredump.h */ #define MMF_DUMPABLE_BITS 2 -#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) +#define MMF_DUMPABLE_MASK (BIT(MMF_DUMPABLE_BITS) - 1) /* coredump filter bits */ #define MMF_DUMP_ANON_PRIVATE 2 #define MMF_DUMP_ANON_SHARED 3 @@ -1734,13 +1785,13 @@ enum { #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS #define MMF_DUMP_FILTER_BITS 9 #define MMF_DUMP_FILTER_MASK \ - (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) + ((BIT(MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + (BIT(MMF_DUMP_ANON_PRIVATE) | BIT(MMF_DUMP_ANON_SHARED) | \ + BIT(MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) #ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS -# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +# define MMF_DUMP_MASK_DEFAULT_ELF BIT(MMF_DUMP_ELF_HEADERS) #else # define MMF_DUMP_MASK_DEFAULT_ELF 0 #endif @@ -1748,19 +1799,16 @@ enum { #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ #define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */ -/* - * This one-shot flag is dropped due to necessity of changing exe once again - * on NFS restore - */ -//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ +#define MMF_HUGE_ZERO_FOLIO 18 /* mm has ever used the global huge zero folio */ #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ -#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) +#define MMF_DISABLE_THP_EXCEPT_ADVISED 23 /* no THP except when advised (e.g., VM_HUGEPAGE) */ +#define MMF_DISABLE_THP_COMPLETELY 24 /* no THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (BIT(MMF_DISABLE_THP_COMPLETELY) | \ + BIT(MMF_DISABLE_THP_EXCEPT_ADVISED)) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* @@ -1773,27 +1821,33 @@ enum { #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_HAS_MDWE 28 -#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) - +#define MMF_HAS_MDWE_MASK BIT(MMF_HAS_MDWE) #define MMF_HAS_MDWE_NO_INHERIT 29 #define MMF_VM_MERGE_ANY 30 -#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) +#define MMF_VM_MERGE_ANY_MASK BIT(MMF_VM_MERGE_ANY) #define MMF_TOPDOWN 31 /* mm searches top down by default */ -#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) +#define MMF_TOPDOWN_MASK BIT(MMF_TOPDOWN) -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ +#define MMF_INIT_LEGACY_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) -static inline unsigned long mmf_init_flags(unsigned long flags) +/* Legacy flags must fit within 32 bits. */ +static_assert((u64)MMF_INIT_LEGACY_MASK <= (u64)UINT_MAX); + +/* + * Initialise legacy flags according to masks, propagating selected flags on + * fork. Further flag manipulation can be performed by the caller. + */ +static inline unsigned long mmf_init_legacy_flags(unsigned long flags) { if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) flags &= ~((1UL << MMF_HAS_MDWE) | (1UL << MMF_HAS_MDWE_NO_INHERIT)); - return flags & MMF_INIT_MASK; + return flags & MMF_INIT_LEGACY_MASK; } #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mman.h b/include/linux/mman.h index de9e8e6229a4..0ba8a7e8b90a 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -201,7 +201,7 @@ static inline bool arch_memory_deny_write_exec_supported(void) static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { /* If MDWE is disabled, we have nothing to deny. */ - if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + if (!mm_flags_test(MMF_HAS_MDWE, current->mm)) return false; /* If the new VMA is not executable, we have nothing to deny. */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 11a078de9150..2c9fffa58714 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -148,91 +148,6 @@ static inline void vma_refcount_put(struct vm_area_struct *vma) } /* - * Try to read-lock a vma. The function is allowed to occasionally yield false - * locked result to avoid performance overhead, in which case we fall back to - * using mmap_lock. The function should never yield false unlocked result. - * False locked result is possible if mm_lock_seq overflows or if vma gets - * reused and attached to a different mm before we lock it. - * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got - * detached. - * - * WARNING! The vma passed to this function cannot be used if the function - * fails to lock it because in certain cases RCU lock is dropped and then - * reacquired. Once RCU lock is dropped the vma can be concurently freed. - */ -static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, - struct vm_area_struct *vma) -{ - int oldcnt; - - /* - * Check before locking. A race might cause false locked result. - * We can use READ_ONCE() for the mm_lock_seq here, and don't need - * ACQUIRE semantics, because this is just a lockless check whose result - * we don't rely on for anything - the mm_lock_seq read against which we - * need ordering is below. - */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) - return NULL; - - /* - * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() - * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. - * Acquire fence is required here to avoid reordering against later - * vm_lock_seq check and checks inside lock_vma_under_rcu(). - */ - if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, - VMA_REF_LIMIT))) { - /* return EAGAIN if vma got detached from under us */ - return oldcnt ? NULL : ERR_PTR(-EAGAIN); - } - - rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); - - /* - * If vma got attached to another mm from under us, that mm is not - * stable and can be freed in the narrow window after vma->vm_refcnt - * is dropped and before rcuwait_wake_up(mm) is called. Grab it before - * releasing vma->vm_refcnt. - */ - if (unlikely(vma->vm_mm != mm)) { - /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ - struct mm_struct *other_mm = vma->vm_mm; - - /* - * __mmdrop() is a heavy operation and we don't need RCU - * protection here. Release RCU lock during these operations. - * We reinstate the RCU read lock as the caller expects it to - * be held when this function returns even on error. - */ - rcu_read_unlock(); - mmgrab(other_mm); - vma_refcount_put(vma); - mmdrop(other_mm); - rcu_read_lock(); - return NULL; - } - - /* - * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. - * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq - * modification invalidates all existing locks. - * - * We must use ACQUIRE semantics for the mm_lock_seq so that if we are - * racing with vma_end_write_all(), we only start reading from the VMA - * after it has been unlocked. - * This pairs with RELEASE semantics in vma_end_write_all(). - */ - if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { - vma_refcount_put(vma); - return NULL; - } - - return vma; -} - -/* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 68f09a955a90..e0e2c265e5d1 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -337,11 +337,15 @@ struct mmc_slot { struct regulator; struct mmc_pwrseq; +struct notifier_block; struct mmc_supply { struct regulator *vmmc; /* Card power supply */ struct regulator *vqmmc; /* Optional Vccq supply */ struct regulator *vqmmc2; /* Optional supply for phy */ + + struct notifier_block vmmc_nb; /* Notifier for vmmc */ + struct work_struct uv_work; /* Undervoltage work */ }; struct mmc_ctx { @@ -494,6 +498,13 @@ struct mmc_host { unsigned int can_dma_map_merge:1; /* merging can be used */ unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ + /* + * Indicates if an undervoltage event has already been handled. + * This prevents repeated regulator notifiers from triggering + * multiple REGULATOR_EVENT_UNDER_VOLTAGE events. + */ + unsigned int undervoltage:1; /* Undervoltage state */ + int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ @@ -565,6 +576,7 @@ struct mmc_host { int hsq_depth; u32 err_stats[MMC_ERR_MAX]; + u32 max_sd_hs_hz; unsigned long private[] ____cacheline_aligned; }; @@ -743,5 +755,6 @@ int mmc_send_status(struct mmc_card *card, u32 *status); int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); +int mmc_read_tuning(struct mmc_host *host, unsigned int blksz, unsigned int blocks); #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index fe3d6d98f8da..673cbdf43453 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -77,7 +77,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43439 0xa9af #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_43751 0xaae7 -#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 +#define SDIO_DEVICE_ID_BROADCOM_43752 0xaae8 #define SDIO_VENDOR_ID_CYPRESS 0x04b4 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xbd3d diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c5da9141983..7fb7331c5725 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -234,7 +234,21 @@ enum node_stat_item { #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ - PGPROMOTE_CANDIDATE, /* candidate pages to promote */ + /** + * Candidate pages for promotion based on hint fault latency. This + * counter is used to control the promotion rate and adjust the hot + * threshold. + */ + PGPROMOTE_CANDIDATE, + /** + * Not rate-limited (NRL) candidate pages for those can be promoted + * without considering hot threshold because of enough free pages in + * fast-tier node. These promotions bypass the regular hotness checks + * and do NOT influence the promotion rate-limiter or + * threshold-adjustment logic. + * This is for statistics/monitoring purposes. + */ + PGPROMOTE_CANDIDATE_NRL, #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, @@ -245,6 +259,7 @@ enum node_stat_item { NR_HUGETLB, #endif NR_BALLOON_PAGES, + NR_KERNEL_FILE_PAGES, NR_VM_NODE_STAT_ITEMS }; @@ -1089,7 +1104,7 @@ static inline unsigned long promo_wmark_pages(const struct zone *z) return wmark_pages(z, WMARK_PROMO); } -static inline unsigned long zone_managed_pages(struct zone *zone) +static inline unsigned long zone_managed_pages(const struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } @@ -1113,12 +1128,12 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } -static inline bool zone_is_initialized(struct zone *zone) +static inline bool zone_is_initialized(const struct zone *zone) { return zone->initialized; } -static inline bool zone_is_empty(struct zone *zone) +static inline bool zone_is_empty(const struct zone *zone) { return zone->spanned_pages == 0; } @@ -1169,26 +1184,31 @@ static inline bool zone_is_empty(struct zone *zone) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) +static inline enum zone_type memdesc_zonenum(memdesc_flags_t flags) +{ + ASSERT_EXCLUSIVE_BITS(flags.f, ZONES_MASK << ZONES_PGSHIFT); + return (flags.f >> ZONES_PGSHIFT) & ZONES_MASK; +} + static inline enum zone_type page_zonenum(const struct page *page) { - ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); - return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; + return memdesc_zonenum(page->flags); } static inline enum zone_type folio_zonenum(const struct folio *folio) { - return page_zonenum(&folio->page); + return memdesc_zonenum(folio->flags); } #ifdef CONFIG_ZONE_DEVICE -static inline bool is_zone_device_page(const struct page *page) +static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) { - return page_zonenum(page) == ZONE_DEVICE; + return memdesc_zonenum(mdf) == ZONE_DEVICE; } static inline struct dev_pagemap *page_pgmap(const struct page *page) { - VM_WARN_ON_ONCE_PAGE(!is_zone_device_page(page), page); + VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(page->flags), page); return page_folio(page)->pgmap; } @@ -1203,9 +1223,9 @@ static inline struct dev_pagemap *page_pgmap(const struct page *page) static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { - if (is_zone_device_page(a) != is_zone_device_page(b)) + if (memdesc_is_zone_device(a->flags) != memdesc_is_zone_device(b->flags)) return false; - if (!is_zone_device_page(a)) + if (!memdesc_is_zone_device(a->flags)) return true; return page_pgmap(a) == page_pgmap(b); } @@ -1213,7 +1233,7 @@ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else -static inline bool is_zone_device_page(const struct page *page) +static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) { return false; } @@ -1228,9 +1248,14 @@ static inline struct dev_pagemap *page_pgmap(const struct page *page) } #endif +static inline bool is_zone_device_page(const struct page *page) +{ + return memdesc_is_zone_device(page->flags); +} + static inline bool folio_is_zone_device(const struct folio *folio) { - return is_zone_device_page(&folio->page); + return memdesc_is_zone_device(folio->flags); } static inline bool is_zone_movable_page(const struct page *page) @@ -1248,7 +1273,7 @@ static inline bool folio_is_zone_movable(const struct folio *folio) * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ -static inline bool zone_intersects(struct zone *zone, +static inline bool zone_intersects(const struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) @@ -1415,7 +1440,7 @@ typedef struct pglist_data { int kswapd_order; enum zone_type kswapd_highest_zoneidx; - int kswapd_failures; /* Number of 'reclaimed == 0' runs */ + atomic_t kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; @@ -1556,12 +1581,12 @@ static inline int local_memory_node(int node_id) { return node_id; }; #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE -static inline bool zone_is_zone_device(struct zone *zone) +static inline bool zone_is_zone_device(const struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else -static inline bool zone_is_zone_device(struct zone *zone) +static inline bool zone_is_zone_device(const struct zone *zone) { return false; } @@ -1573,19 +1598,19 @@ static inline bool zone_is_zone_device(struct zone *zone) * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ -static inline bool managed_zone(struct zone *zone) +static inline bool managed_zone(const struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ -static inline bool populated_zone(struct zone *zone) +static inline bool populated_zone(const struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA -static inline int zone_to_nid(struct zone *zone) +static inline int zone_to_nid(const struct zone *zone) { return zone->node; } @@ -1595,7 +1620,7 @@ static inline void zone_set_nid(struct zone *zone, int nid) zone->node = nid; } #else -static inline int zone_to_nid(struct zone *zone) +static inline int zone_to_nid(const struct zone *zone) { return 0; } @@ -1622,7 +1647,7 @@ static inline int is_highmem_idx(enum zone_type idx) * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ -static inline int is_highmem(struct zone *zone) +static inline int is_highmem(const struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } @@ -1688,12 +1713,12 @@ static inline struct zone *zonelist_zone(struct zoneref *zoneref) return zoneref->zone; } -static inline int zonelist_zone_idx(struct zoneref *zoneref) +static inline int zonelist_zone_idx(const struct zoneref *zoneref) { return zoneref->zone_idx; } -static inline int zonelist_node_idx(struct zoneref *zoneref) +static inline int zonelist_node_idx(const struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } @@ -1996,7 +2021,7 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section) return (struct page *)map; } -static inline int present_section(struct mem_section *section) +static inline int present_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } @@ -2006,12 +2031,12 @@ static inline int present_section_nr(unsigned long nr) return present_section(__nr_to_section(nr)); } -static inline int valid_section(struct mem_section *section) +static inline int valid_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } -static inline int early_section(struct mem_section *section) +static inline int early_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } @@ -2021,27 +2046,27 @@ static inline int valid_section_nr(unsigned long nr) return valid_section(__nr_to_section(nr)); } -static inline int online_section(struct mem_section *section) +static inline int online_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE -static inline int online_device_section(struct mem_section *section) +static inline int online_device_section(const struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else -static inline int online_device_section(struct mem_section *section) +static inline int online_device_section(const struct mem_section *section) { return 0; } #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT -static inline int preinited_vmemmap_section(struct mem_section *section) +static inline int preinited_vmemmap_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT)); @@ -2051,7 +2076,7 @@ void sparse_vmemmap_init_nid_early(int nid); void sparse_vmemmap_init_nid_late(int nid); #else -static inline int preinited_vmemmap_section(struct mem_section *section) +static inline int preinited_vmemmap_section(const struct mem_section *section) { return 0; } diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 70b366b64816..0acd1089d149 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -11,7 +11,9 @@ struct fs_struct; struct user_namespace; struct ns_common; -extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, +extern struct mnt_namespace init_mnt_ns; + +extern struct mnt_namespace *copy_mnt_ns(u64, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); DEFINE_FREE(put_mnt_ns, struct mnt_namespace *, if (!IS_ERR_OR_NULL(_T)) put_mnt_ns(_T)) diff --git a/include/linux/module.h b/include/linux/module.h index 3319a5269d28..e135cc79acee 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -244,14 +244,22 @@ struct module_kobject *lookup_or_create_module_kobject(const char *name); /* What your module does. */ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) -#ifdef MODULE +/* + * Format: __mod_device_table__kmod_<modname>__<type>__<name> + * Parts of the string `__kmod_` and `__` are used as delimiters when parsing + * a symbol in file2alias.c + */ +#define __mod_device_table(type, name) \ + __PASTE(__mod_device_table__, \ + __PASTE(__KBUILD_MODNAME, \ + __PASTE(__, \ + __PASTE(type, \ + __PASTE(__, name))))) + /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ -static typeof(name) __mod_device_table__##type##__##name \ +static typeof(name) __mod_device_table(type, name) \ __attribute__ ((used, alias(__stringify(name)))) -#else /* !MODULE */ -#define MODULE_DEVICE_TABLE(type, name) -#endif /* Version of form [<epoch>:]<version>[-<extra-version>]. * Or for CVS/RCS ID version, everything but the number is stripped. diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 3a25122d83e2..6907aedc4f74 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -349,6 +349,19 @@ static inline void kernel_param_unlock(struct module *mod) __module_param_call("", name, ¶m_ops_##type, &var, perm, \ -1, KERNEL_PARAM_FL_UNSAFE) +/** + * __core_param_cb - similar like core_param, with a set/get ops instead of type. + * @name: the name of the cmdline and sysfs parameter (often the same as var) + * @var: the variable + * @ops: the set & get operations for this parameter. + * @perm: visibility in sysfs + * + * Ideally this should be called 'core_param_cb', but the name has been + * used for module core parameter, so add the '__' prefix + */ +#define __core_param_cb(name, ops, arg, perm) \ + __module_param_call("", name, ops, arg, perm, -1, 0) + #endif /* !MODULE */ /** diff --git a/include/linux/msi.h b/include/linux/msi.h index e5e86a8529fb..d415dd15a0a9 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -431,8 +431,6 @@ struct msi_domain_info; * function. * @domain_free_irqs: Optional function to override the default free * function. - * @msi_post_free: Optional function which is invoked after freeing - * all interrupts. * @msi_translate: Optional translate callback to support the odd wire to * MSI bridges, e.g. MBIGEN * @@ -473,8 +471,6 @@ struct msi_domain_ops { struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, struct device *dev); - void (*msi_post_free)(struct irq_domain *domain, - struct device *dev); int (*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec, irq_hw_number_t *hwirq, unsigned int *type); }; @@ -568,6 +564,8 @@ enum { MSI_FLAG_PARENT_PM_DEV = (1 << 8), /* Support for parent mask/unmask */ MSI_FLAG_PCI_MSI_MASK_PARENT = (1 << 9), + /* Support for parent startup/shutdown */ + MSI_FLAG_PCI_MSI_STARTUP_PARENT = (1 << 10), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), diff --git a/include/linux/namei.h b/include/linux/namei.h index 5d085428e471..a7800ef04e76 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,13 +57,17 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); - -extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); -extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); -extern void done_path_create(struct path *, struct dentry *); -extern struct dentry *kern_path_locked(const char *, struct path *); -extern struct dentry *kern_path_locked_negative(const char *, struct path *); -extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); +struct dentry *kern_path_parent(const char *name, struct path *parent); + +extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); +extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); +extern void end_creating_path(struct path *, struct dentry *); +extern struct dentry *start_removing_path(const char *, struct path *); +extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); +static inline void end_removing_path(struct path *path , struct dentry *dentry) +{ + end_creating_path(path, dentry); +} int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); @@ -80,6 +84,9 @@ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); +struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, + struct qstr *name, + struct dentry *base); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h index 012b5d499c1a..ab13bd777a28 100644 --- a/include/linux/net/intel/libie/adminq.h +++ b/include/linux/net/intel/libie/adminq.h @@ -9,6 +9,7 @@ #define LIBIE_CHECK_STRUCT_LEN(n, X) \ static_assert((n) == sizeof(struct X)) +#define LIBIE_AQ_MAX_BUF_LEN 4096 /** * struct libie_aqc_generic - Generic structure used in adminq communication @@ -192,8 +193,9 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps); #define LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE 0x0085 #define LIBIE_AQC_CAPS_NAC_TOPOLOGY 0x0087 #define LIBIE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 -#define LIBIE_AQC_BIT_ROCEV2_LAG 0x01 -#define LIBIE_AQC_BIT_SRIOV_LAG 0x02 +#define LIBIE_AQC_BIT_ROCEV2_LAG BIT(0) +#define LIBIE_AQC_BIT_SRIOV_LAG BIT(1) +#define LIBIE_AQC_BIT_SRIOV_AA_LAG BIT(2) #define LIBIE_AQC_CAPS_FLEX10 0x00F1 #define LIBIE_AQC_CAPS_CEM 0x00F2 @@ -221,6 +223,94 @@ struct libie_aqc_list_caps_elem { }; LIBIE_CHECK_STRUCT_LEN(32, libie_aqc_list_caps_elem); +/* Admin Queue command opcodes */ +enum libie_adminq_opc { + /* FW Logging Commands */ + libie_aqc_opc_fw_logs_config = 0xFF30, + libie_aqc_opc_fw_logs_register = 0xFF31, + libie_aqc_opc_fw_logs_query = 0xFF32, + libie_aqc_opc_fw_logs_event = 0xFF33, +}; + +enum libie_aqc_fw_logging_mod { + LIBIE_AQC_FW_LOG_ID_GENERAL = 0, + LIBIE_AQC_FW_LOG_ID_CTRL, + LIBIE_AQC_FW_LOG_ID_LINK, + LIBIE_AQC_FW_LOG_ID_LINK_TOPO, + LIBIE_AQC_FW_LOG_ID_DNL, + LIBIE_AQC_FW_LOG_ID_I2C, + LIBIE_AQC_FW_LOG_ID_SDP, + LIBIE_AQC_FW_LOG_ID_MDIO, + LIBIE_AQC_FW_LOG_ID_ADMINQ, + LIBIE_AQC_FW_LOG_ID_HDMA, + LIBIE_AQC_FW_LOG_ID_LLDP, + LIBIE_AQC_FW_LOG_ID_DCBX, + LIBIE_AQC_FW_LOG_ID_DCB, + LIBIE_AQC_FW_LOG_ID_XLR, + LIBIE_AQC_FW_LOG_ID_NVM, + LIBIE_AQC_FW_LOG_ID_AUTH, + LIBIE_AQC_FW_LOG_ID_VPD, + LIBIE_AQC_FW_LOG_ID_IOSF, + LIBIE_AQC_FW_LOG_ID_PARSER, + LIBIE_AQC_FW_LOG_ID_SW, + LIBIE_AQC_FW_LOG_ID_SCHEDULER, + LIBIE_AQC_FW_LOG_ID_TXQ, + LIBIE_AQC_FW_LOG_ID_RSVD, + LIBIE_AQC_FW_LOG_ID_POST, + LIBIE_AQC_FW_LOG_ID_WATCHDOG, + LIBIE_AQC_FW_LOG_ID_TASK_DISPATCH, + LIBIE_AQC_FW_LOG_ID_MNG, + LIBIE_AQC_FW_LOG_ID_SYNCE, + LIBIE_AQC_FW_LOG_ID_HEALTH, + LIBIE_AQC_FW_LOG_ID_TSDRV, + LIBIE_AQC_FW_LOG_ID_PFREG, + LIBIE_AQC_FW_LOG_ID_MDLVER, + LIBIE_AQC_FW_LOG_ID_MAX +}; + +/* Set FW Logging configuration (indirect 0xFF30) + * Register for FW Logging (indirect 0xFF31) + * Query FW Logging (indirect 0xFF32) + * FW Log Event (indirect 0xFF33) + */ +#define LIBIE_AQC_FW_LOG_CONF_UART_EN BIT(0) +#define LIBIE_AQC_FW_LOG_CONF_AQ_EN BIT(1) +#define LIBIE_AQC_FW_LOG_QUERY_REGISTERED BIT(2) +#define LIBIE_AQC_FW_LOG_CONF_SET_VALID BIT(3) +#define LIBIE_AQC_FW_LOG_AQ_REGISTER BIT(0) +#define LIBIE_AQC_FW_LOG_AQ_QUERY BIT(2) + +#define LIBIE_AQC_FW_LOG_MIN_RESOLUTION 1 +#define LIBIE_AQC_FW_LOG_MAX_RESOLUTION 128 + +struct libie_aqc_fw_log { + u8 cmd_flags; + + u8 rsp_flag; + __le16 fw_rt_msb; + union { + struct { + __le32 fw_rt_lsb; + } sync; + struct { + __le16 log_resolution; + __le16 mdl_cnt; + } cfg; + } ops; + __le32 addr_high; + __le32 addr_low; +}; + +/* Response Buffer for: + * Set Firmware Logging Configuration (0xFF30) + * Query FW Logging (0xFF32) + */ +struct libie_aqc_fw_log_cfg_resp { + __le16 module_identifier; + u8 log_level; + u8 rsvd0; +}; + /** * struct libie_aq_desc - Admin Queue (AQ) descriptor * @flags: LIBIE_AQ_FLAG_* flags @@ -252,6 +342,7 @@ struct libie_aq_desc { struct libie_aqc_driver_ver driver_ver; struct libie_aqc_req_res res_owner; struct libie_aqc_list_caps get_cap; + struct libie_aqc_fw_log fw_log; } params; }; LIBIE_CHECK_STRUCT_LEN(32, libie_aq_desc); diff --git a/include/linux/net/intel/libie/fwlog.h b/include/linux/net/intel/libie/fwlog.h new file mode 100644 index 000000000000..36b13fabca9e --- /dev/null +++ b/include/linux/net/intel/libie/fwlog.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2022, Intel Corporation. */ + +#ifndef _LIBIE_FWLOG_H_ +#define _LIBIE_FWLOG_H_ + +#include <linux/net/intel/libie/adminq.h> + +/* Only a single log level should be set and all log levels under the set value + * are enabled, e.g. if log level is set to LIBIE_FW_LOG_LEVEL_VERBOSE, then all + * other log levels are included (except LIBIE_FW_LOG_LEVEL_NONE) + */ +enum libie_fwlog_level { + LIBIE_FWLOG_LEVEL_NONE = 0, + LIBIE_FWLOG_LEVEL_ERROR = 1, + LIBIE_FWLOG_LEVEL_WARNING = 2, + LIBIE_FWLOG_LEVEL_NORMAL = 3, + LIBIE_FWLOG_LEVEL_VERBOSE = 4, + LIBIE_FWLOG_LEVEL_INVALID, /* all values >= this entry are invalid */ +}; + +struct libie_fwlog_module_entry { + /* module ID for the corresponding firmware logging event */ + u16 module_id; + /* verbosity level for the module_id */ + u8 log_level; +}; + +struct libie_fwlog_cfg { + /* list of modules for configuring log level */ + struct libie_fwlog_module_entry module_entries[LIBIE_AQC_FW_LOG_ID_MAX]; + /* options used to configure firmware logging */ + u16 options; +#define LIBIE_FWLOG_OPTION_ARQ_ENA BIT(0) +#define LIBIE_FWLOG_OPTION_UART_ENA BIT(1) + /* set before calling libie_fwlog_init() so the PF registers for + * firmware logging on initialization + */ +#define LIBIE_FWLOG_OPTION_REGISTER_ON_INIT BIT(2) + /* set in the libie_aq_fwlog_get() response if the PF is registered for + * FW logging events over ARQ + */ +#define LIBIE_FWLOG_OPTION_IS_REGISTERED BIT(3) + + /* minimum number of log events sent per Admin Receive Queue event */ + u16 log_resolution; +}; + +struct libie_fwlog_data { + u16 data_size; + u8 *data; +}; + +struct libie_fwlog_ring { + struct libie_fwlog_data *rings; + u16 index; + u16 size; + u16 head; + u16 tail; +}; + +#define LIBIE_FWLOG_RING_SIZE_INDEX_DFLT 3 +#define LIBIE_FWLOG_RING_SIZE_DFLT 256 +#define LIBIE_FWLOG_RING_SIZE_MAX 512 + +struct libie_fwlog { + struct libie_fwlog_cfg cfg; + bool supported; /* does hardware support FW logging? */ + struct libie_fwlog_ring ring; + struct dentry *debugfs; + /* keep track of all the dentrys for FW log modules */ + struct dentry **debugfs_modules; + struct_group_tagged(libie_fwlog_api, api, + struct pci_dev *pdev; + int (*send_cmd)(void *, struct libie_aq_desc *, void *, u16); + void *priv; + struct dentry *debugfs_root; + ); +}; + +int libie_fwlog_init(struct libie_fwlog *fwlog, struct libie_fwlog_api *api); +void libie_fwlog_deinit(struct libie_fwlog *fwlog); +void libie_fwlog_reregister(struct libie_fwlog *fwlog); +void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, u16 len); +#endif /* _LIBIE_FWLOG_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f3a3b761abfb..d1a687444b27 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1906,6 +1906,7 @@ enum netdev_reg_state { * device struct * @mpls_ptr: mpls_dev struct pointer * @mctp_ptr: MCTP specific data + * @psp_dev: PSP crypto device registered for this netdev * * @dev_addr: Hw address (before bcast, * because most packets are unicast) @@ -2310,6 +2311,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MCTP) struct mctp_dev __rcu *mctp_ptr; #endif +#if IS_ENABLED(CONFIG_INET_PSP) + struct psp_dev __rcu *psp_dev; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) @@ -3459,6 +3463,32 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } +struct numa_drop_counters { + atomic_t drops0 ____cacheline_aligned_in_smp; + atomic_t drops1 ____cacheline_aligned_in_smp; +}; + +static inline int numa_drop_read(const struct numa_drop_counters *ndc) +{ + return atomic_read(&ndc->drops0) + atomic_read(&ndc->drops1); +} + +static inline void numa_drop_add(struct numa_drop_counters *ndc, int val) +{ + int n = numa_node_id() % 2; + + if (n) + atomic_add(val, &ndc->drops1); + else + atomic_add(val, &ndc->drops0); +} + +static inline void numa_drop_reset(struct numa_drop_counters *ndc) +{ + atomic_set(&ndc->drops0, 0); + atomic_set(&ndc->drops1, 0); +} + /* * Incoming packets are placed on per-CPU queues */ @@ -3504,13 +3534,9 @@ struct softnet_data { struct sk_buff_head input_pkt_queue; struct napi_struct backlog; - atomic_t dropped ____cacheline_aligned_in_smp; + struct numa_drop_counters drop_counters; - /* Another possibly contended cache line */ - spinlock_t defer_lock ____cacheline_aligned_in_smp; - int defer_count; - int defer_ipi_scheduled; - struct sk_buff *defer_list; + int defer_ipi_scheduled ____cacheline_aligned_in_smp; call_single_data_t defer_csd; }; @@ -5290,13 +5316,18 @@ void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { - netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; + netdev_features_t feature; + + if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER)) + gso_type |= __SKB_GSO_TCP_FIXEDID; + + feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 98c96d649bf9..72ee7d210a74 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -21,7 +21,7 @@ #include <linux/rolling_buffer.h> enum netfs_sreq_ref_trace; -typedef struct mempool_s mempool_t; +typedef struct mempool mempool_t; struct folio_queue; /** diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index b5ea9882eda8..f22eec466040 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -55,7 +55,6 @@ struct netpoll_info { struct delayed_work tx_work; - struct netpoll *netpoll; struct rcu_head rcu; }; diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 7d22ea50b098..f5b68b8abb54 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -3,14 +3,151 @@ #define _LINUX_NS_COMMON_H #include <linux/refcount.h> +#include <linux/rbtree.h> +#include <uapi/linux/sched.h> struct proc_ns_operations; +struct cgroup_namespace; +struct ipc_namespace; +struct mnt_namespace; +struct net; +struct pid_namespace; +struct time_namespace; +struct user_namespace; +struct uts_namespace; + +extern struct cgroup_namespace init_cgroup_ns; +extern struct ipc_namespace init_ipc_ns; +extern struct mnt_namespace init_mnt_ns; +extern struct net init_net; +extern struct pid_namespace init_pid_ns; +extern struct time_namespace init_time_ns; +extern struct user_namespace init_user_ns; +extern struct uts_namespace init_uts_ns; + +extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations utsns_operations; +extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations cgroupns_operations; +extern const struct proc_ns_operations timens_operations; +extern const struct proc_ns_operations timens_for_children_operations; + struct ns_common { + u32 ns_type; struct dentry *stashed; const struct proc_ns_operations *ops; unsigned int inum; - refcount_t count; + refcount_t __ns_ref; /* do not use directly */ + union { + struct { + u64 ns_id; + struct rb_node ns_tree_node; + struct list_head ns_list_node; + }; + struct rcu_head ns_rcu; + }; }; +int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); +void __ns_common_free(struct ns_common *ns); + +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns)->ns, \ + const struct cgroup_namespace *: &(__ns)->ns, \ + struct ipc_namespace *: &(__ns)->ns, \ + const struct ipc_namespace *: &(__ns)->ns, \ + struct mnt_namespace *: &(__ns)->ns, \ + const struct mnt_namespace *: &(__ns)->ns, \ + struct net *: &(__ns)->ns, \ + const struct net *: &(__ns)->ns, \ + struct pid_namespace *: &(__ns)->ns, \ + const struct pid_namespace *: &(__ns)->ns, \ + struct time_namespace *: &(__ns)->ns, \ + const struct time_namespace *: &(__ns)->ns, \ + struct user_namespace *: &(__ns)->ns, \ + const struct user_namespace *: &(__ns)->ns, \ + struct uts_namespace *: &(__ns)->ns, \ + const struct uts_namespace *: &(__ns)->ns) + +#define ns_init_inum(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ + struct ipc_namespace *: IPC_NS_INIT_INO, \ + struct mnt_namespace *: MNT_NS_INIT_INO, \ + struct net *: NET_NS_INIT_INO, \ + struct pid_namespace *: PID_NS_INIT_INO, \ + struct time_namespace *: TIME_NS_INIT_INO, \ + struct user_namespace *: USER_NS_INIT_INO, \ + struct uts_namespace *: UTS_NS_INIT_INO) + +#define ns_init_ns(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &init_cgroup_ns, \ + struct ipc_namespace *: &init_ipc_ns, \ + struct mnt_namespace *: &init_mnt_ns, \ + struct net *: &init_net, \ + struct pid_namespace *: &init_pid_ns, \ + struct time_namespace *: &init_time_ns, \ + struct user_namespace *: &init_user_ns, \ + struct uts_namespace *: &init_uts_ns) + +#define to_ns_operations(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ + struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ + struct mnt_namespace *: &mntns_operations, \ + struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ + struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ + struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ + struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ + struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) + +#define ns_common_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CLONE_NEWCGROUP, \ + struct ipc_namespace *: CLONE_NEWIPC, \ + struct mnt_namespace *: CLONE_NEWNS, \ + struct net *: CLONE_NEWNET, \ + struct pid_namespace *: CLONE_NEWPID, \ + struct time_namespace *: CLONE_NEWTIME, \ + struct user_namespace *: CLONE_NEWUSER, \ + struct uts_namespace *: CLONE_NEWUTS) + +#define ns_common_init(__ns) \ + __ns_common_init(to_ns_common(__ns), \ + ns_common_type(__ns), \ + to_ns_operations(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0)) + +#define ns_common_init_inum(__ns, __inum) \ + __ns_common_init(to_ns_common(__ns), \ + ns_common_type(__ns), \ + to_ns_operations(__ns), \ + __inum) + +#define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) + +static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) +{ + return refcount_dec_and_test(&ns->__ns_ref); +} + +static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) +{ + return refcount_inc_not_zero(&ns->__ns_ref); +} + +#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) +#define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref) +#define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns))) +#define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns))) +#define ns_ref_put_and_lock(__ns, __lock) \ + refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock)) + #endif diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h new file mode 100644 index 000000000000..e5a5fa83d36b --- /dev/null +++ b/include/linux/nsfs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ + +#ifndef _LINUX_NSFS_H +#define _LINUX_NSFS_H + +#include <linux/ns_common.h> +#include <linux/cred.h> +#include <linux/pid_namespace.h> + +struct path; +struct task_struct; +struct proc_ns_operations; + +int ns_get_path(struct path *path, struct task_struct *task, + const struct proc_ns_operations *ns_ops); +typedef struct ns_common *ns_get_path_helper_t(void *); +int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, + void *private_data); + +bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); + +int ns_get_name(char *buf, size_t size, struct task_struct *task, + const struct proc_ns_operations *ns_ops); +void nsfs_init(void); + +#define __current_namespace_from_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: current->nsproxy->cgroup_ns, \ + struct ipc_namespace *: current->nsproxy->ipc_ns, \ + struct net *: current->nsproxy->net_ns, \ + struct pid_namespace *: task_active_pid_ns(current), \ + struct mnt_namespace *: current->nsproxy->mnt_ns, \ + struct time_namespace *: current->nsproxy->time_ns, \ + struct user_namespace *: current_user_ns(), \ + struct uts_namespace *: current->nsproxy->uts_ns) + +#define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns) + +#endif /* _LINUX_NSFS_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index dab6a1734a22..bd118a187dec 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -42,17 +42,6 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; -#define to_ns_common(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &(__ns->ns), \ - struct ipc_namespace *: &(__ns->ns), \ - struct net *: &(__ns->ns), \ - struct pid_namespace *: &(__ns->ns), \ - struct mnt_namespace *: &(__ns->ns), \ - struct time_namespace *: &(__ns->ns), \ - struct user_namespace *: &(__ns->ns), \ - struct uts_namespace *: &(__ns->ns)) - /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. @@ -103,7 +92,7 @@ static inline struct cred *nsset_cred(struct nsset *set) * */ -int copy_namespaces(unsigned long flags, struct task_struct *tsk); +int copy_namespaces(u64 flags, struct task_struct *tsk); void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); diff --git a/include/linux/nstree.h b/include/linux/nstree.h new file mode 100644 index 000000000000..8b8636690473 --- /dev/null +++ b/include/linux/nstree.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NSTREE_H +#define _LINUX_NSTREE_H + +#include <linux/ns_common.h> +#include <linux/nsproxy.h> +#include <linux/rbtree.h> +#include <linux/seqlock.h> +#include <linux/rculist.h> +#include <linux/cookie.h> + +extern struct ns_tree cgroup_ns_tree; +extern struct ns_tree ipc_ns_tree; +extern struct ns_tree mnt_ns_tree; +extern struct ns_tree net_ns_tree; +extern struct ns_tree pid_ns_tree; +extern struct ns_tree time_ns_tree; +extern struct ns_tree user_ns_tree; +extern struct ns_tree uts_ns_tree; + +#define to_ns_tree(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(cgroup_ns_tree), \ + struct ipc_namespace *: &(ipc_ns_tree), \ + struct net *: &(net_ns_tree), \ + struct pid_namespace *: &(pid_ns_tree), \ + struct mnt_namespace *: &(mnt_ns_tree), \ + struct time_namespace *: &(time_ns_tree), \ + struct user_namespace *: &(user_ns_tree), \ + struct uts_namespace *: &(uts_ns_tree)) + +u64 ns_tree_gen_id(struct ns_common *ns); +void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree); +void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree); +struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type); +struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns, + struct ns_tree *ns_tree, + bool previous); + +static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) +{ + ns_tree_gen_id(ns); + __ns_tree_add_raw(ns, ns_tree); +} + +/** + * ns_tree_add_raw - Add a namespace to a namespace + * @ns: Namespace to add + * + * This function adds a namespace to the appropriate namespace tree + * without assigning a id. + */ +#define ns_tree_add_raw(__ns) __ns_tree_add_raw(to_ns_common(__ns), to_ns_tree(__ns)) + +/** + * ns_tree_add - Add a namespace to a namespace tree + * @ns: Namespace to add + * + * This function assigns a new id to the namespace and adds it to the + * appropriate namespace tree and list. + */ +#define ns_tree_add(__ns) __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns)) + +/** + * ns_tree_remove - Remove a namespace from a namespace tree + * @ns: Namespace to remove + * + * This function removes a namespace from the appropriate namespace + * tree and list. + */ +#define ns_tree_remove(__ns) __ns_tree_remove(to_ns_common(__ns), to_ns_tree(__ns)) + +#define ns_tree_adjoined_rcu(__ns, __previous) \ + __ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous) + +#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node)) + +#endif /* _LINUX_NSTREE_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 615a560d9edb..f3b13da78aac 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -103,7 +103,7 @@ struct nvmem_cell_info { * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is - * generated with ida_simple_get() and provided id field is ignored. + * generated with ida_alloc() and provided id field is ignored. * * Note: Specifying name and setting id to -1 implies a unique device * whose name is provided as-is (kept unaltered). diff --git a/include/linux/of.h b/include/linux/of.h index a62154aeda1b..5e2c6ed9370a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -550,6 +550,13 @@ static inline struct device_node *of_get_next_child( return NULL; } +static inline struct device_node *of_get_next_child_with_prefix( + const struct device_node *node, struct device_node *prev, + const char *prefix) +{ + return NULL; +} + static inline struct device_node *of_get_next_available_child( const struct device_node *node, struct device_node *prev) { diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index a480063c9cb1..1db8543dfc8a 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -55,7 +55,6 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 bus_token); extern void of_msi_configure(struct device *dev, const struct device_node *np); extern u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in); -u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else static inline void of_irq_init(const struct of_device_id *matches) { @@ -105,11 +104,6 @@ static inline u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, { return id_in; } -static inline u32 of_msi_map_id(struct device *dev, - struct device_node *msi_np, u32 id_in) -{ - return id_in; -} #endif #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC) diff --git a/include/linux/once.h b/include/linux/once.h index 30346fcdc799..449a0e34ad5a 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -46,7 +46,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, #define DO_ONCE(func, ...) \ ({ \ bool ___ret = false; \ - static bool __section(".data..once") ___done = false; \ + static bool __section(".data..do_once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ @@ -64,7 +64,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, #define DO_ONCE_SLEEPABLE(func, ...) \ ({ \ bool ___ret = false; \ - static bool __section(".data..once") ___done = false; \ + static bool __section(".data..do_once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ ___ret = __do_once_sleepable_start(&___done); \ diff --git a/include/linux/oom.h b/include/linux/oom.h index 1e0fc6931ce9..7b02bc1d0a7e 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -91,7 +91,7 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) */ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) { - if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) + if (unlikely(mm_flags_test(MMF_UNSTABLE, mm))) return VM_FAULT_SIGBUS; return 0; } diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 154ed0dbb43f..725f95f7e416 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -239,6 +239,76 @@ static inline bool __must_check __must_check_overflow(bool overflow) __overflows_type(n, T)) /** + * range_overflows() - Check if a range is out of bounds + * @start: Start of the range. + * @size: Size of the range. + * @max: Exclusive upper boundary. + * + * A strict check to determine if the range [@start, @start + @size) is + * invalid with respect to the allowable range [0, @max). Any range + * starting at or beyond @max is considered an overflow, even if @size is 0. + * + * Returns: true if the range is out of bounds. + */ +#define range_overflows(start, size, max) ({ \ + typeof(start) start__ = (start); \ + typeof(size) size__ = (size); \ + typeof(max) max__ = (max); \ + (void)(&start__ == &size__); \ + (void)(&start__ == &max__); \ + start__ >= max__ || size__ > max__ - start__; \ +}) + +/** + * range_overflows_t() - Check if a range is out of bounds + * @type: Data type to use. + * @start: Start of the range. + * @size: Size of the range. + * @max: Exclusive upper boundary. + * + * Same as range_overflows() but forcing the parameters to @type. + * + * Returns: true if the range is out of bounds. + */ +#define range_overflows_t(type, start, size, max) \ + range_overflows((type)(start), (type)(size), (type)(max)) + +/** + * range_end_overflows() - Check if a range's endpoint is out of bounds + * @start: Start of the range. + * @size: Size of the range. + * @max: Exclusive upper boundary. + * + * Checks only if the endpoint of a range (@start + @size) exceeds @max. + * Unlike range_overflows(), a zero-sized range at the boundary (@start == @max) + * is not considered an overflow. Useful for iterator-style checks. + * + * Returns: true if the endpoint exceeds the boundary. + */ +#define range_end_overflows(start, size, max) ({ \ + typeof(start) start__ = (start); \ + typeof(size) size__ = (size); \ + typeof(max) max__ = (max); \ + (void)(&start__ == &size__); \ + (void)(&start__ == &max__); \ + start__ > max__ || size__ > max__ - start__; \ +}) + +/** + * range_end_overflows_t() - Check if a range's endpoint is out of bounds + * @type: Data type to use. + * @start: Start of the range. + * @size: Size of the range. + * @max: Exclusive upper boundary. + * + * Same as range_end_overflows() but forcing the parameters to @type. + * + * Returns: true if the endpoint exceeds the boundary. + */ +#define range_end_overflows_t(type, start, size, max) \ + range_end_overflows((type)(start), (type)(size), (type)(max)) + +/** * castable_to_type - like __same_type(), but also allows for casted literals * * @n: variable or constant value diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8d3fa3a91ce4..48e27768e7ba 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -217,7 +217,7 @@ static __always_inline const struct page *page_fixed_fake_head(const struct page * cold cacheline in some cases. */ if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && - test_bit(PG_head, &page->flags)) { + test_bit(PG_head, &page->flags.f)) { /* * We can safely access the field of the @page[1] with PG_head * because the @page is a compound page composed with at least @@ -316,7 +316,7 @@ static __always_inline unsigned long _compound_head(const struct page *page) * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ -#define folio_page(folio, n) nth_page(&(folio)->page, n) +#define folio_page(folio, n) (&(folio)->page + (n)) static __always_inline int PageTail(const struct page *page) { @@ -325,14 +325,14 @@ static __always_inline int PageTail(const struct page *page) static __always_inline int PageCompound(const struct page *page) { - return test_bit(PG_head, &page->flags) || + return test_bit(PG_head, &page->flags.f) || READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { - return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; + return READ_ONCE(page->flags.f) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM @@ -349,8 +349,8 @@ static const unsigned long *const_folio_flags(const struct folio *folio, const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); - VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); - return &page[n].flags; + VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); + return &page[n].flags.f; } static unsigned long *folio_flags(struct folio *folio, unsigned n) @@ -358,8 +358,8 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n) struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); - VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); - return &page[n].flags; + VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); + return &page[n].flags.f; } /* @@ -449,37 +449,37 @@ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ -{ return test_bit(PG_##lname, &policy(page, 0)->flags); } +{ return test_bit(PG_##lname, &policy(page, 0)->flags.f); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ -{ set_bit(PG_##lname, &policy(page, 1)->flags); } +{ set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ -{ clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ -{ __set_bit(PG_##lname, &policy(page, 1)->flags); } +{ __set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ -{ __clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ __clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ -{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ -{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ @@ -846,7 +846,7 @@ static __always_inline bool folio_test_head(const struct folio *folio) static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); - return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); + return test_bit(PG_head, &page->flags.f) && !page_is_fake_head(page); } __SETPAGEFLAG(Head, head, PF_ANY) @@ -1170,28 +1170,28 @@ static __always_inline int PageAnonExclusive(const struct page *page) */ if (PageHuge(page)) page = compound_head(page); - return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); + return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); - set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); + set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); - clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); + clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); - __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); + __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } #ifdef CONFIG_MMU @@ -1241,7 +1241,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ static inline int folio_has_private(const struct folio *folio) { - return !!(folio->flags & PAGE_FLAGS_PRIVATE); + return !!(folio->flags.f & PAGE_FLAGS_PRIVATE); } #undef PF_ANY diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 6a44be0f39f4..e046278a01fa 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -13,12 +13,11 @@ #include <linux/types.h> -#define PB_migratetype_bits 3 /* Bit indices that affect a whole block of pages */ enum pageblock_bits { - PB_migrate, - PB_migrate_end = PB_migrate + PB_migratetype_bits - 1, - /* 3 bits required for migrate types */ + PB_migrate_0, + PB_migrate_1, + PB_migrate_2, PB_compact_skip,/* If set the block is skipped by compaction */ #ifdef CONFIG_MEMORY_ISOLATION @@ -37,11 +36,10 @@ enum pageblock_bits { #define NR_PAGEBLOCK_BITS (roundup_pow_of_two(__NR_PAGEBLOCK_BITS)) -#define MIGRATETYPE_MASK ((1UL << (PB_migrate_end + 1)) - 1) +#define MIGRATETYPE_MASK (BIT(PB_migrate_0)|BIT(PB_migrate_1)|BIT(PB_migrate_2)) #ifdef CONFIG_MEMORY_ISOLATION -#define MIGRATETYPE_AND_ISO_MASK \ - (((1UL << (PB_migrate_end + 1)) - 1) | BIT(PB_migrate_isolate)) +#define MIGRATETYPE_AND_ISO_MASK (MIGRATETYPE_MASK | BIT(PB_migrate_isolate)) #else #define MIGRATETYPE_AND_ISO_MASK MIGRATETYPE_MASK #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 12a12dae727d..185644e288ea 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -140,7 +140,7 @@ static inline int inode_drain_writes(struct inode *inode) return filemap_write_and_wait(inode->i_mapping); } -static inline bool mapping_empty(struct address_space *mapping) +static inline bool mapping_empty(const struct address_space *mapping) { return xa_empty(&mapping->i_pages); } @@ -166,7 +166,7 @@ static inline bool mapping_empty(struct address_space *mapping) * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ -static inline bool mapping_shrinkable(struct address_space *mapping) +static inline bool mapping_shrinkable(const struct address_space *mapping) { void *head; @@ -211,6 +211,8 @@ enum mapping_flags { folio contents */ AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, + AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't + account usage to user cgroups */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -265,7 +267,7 @@ static inline void mapping_clear_unevictable(struct address_space *mapping) clear_bit(AS_UNEVICTABLE, &mapping->flags); } -static inline bool mapping_unevictable(struct address_space *mapping) +static inline bool mapping_unevictable(const struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } @@ -275,7 +277,7 @@ static inline void mapping_set_exiting(struct address_space *mapping) set_bit(AS_EXITING, &mapping->flags); } -static inline int mapping_exiting(struct address_space *mapping) +static inline int mapping_exiting(const struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } @@ -285,7 +287,7 @@ static inline void mapping_set_no_writeback_tags(struct address_space *mapping) set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } -static inline int mapping_use_writeback_tags(struct address_space *mapping) +static inline int mapping_use_writeback_tags(const struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } @@ -331,7 +333,7 @@ static inline void mapping_set_inaccessible(struct address_space *mapping) set_bit(AS_INACCESSIBLE, &mapping->flags); } -static inline bool mapping_inaccessible(struct address_space *mapping) +static inline bool mapping_inaccessible(const struct address_space *mapping) { return test_bit(AS_INACCESSIBLE, &mapping->flags); } @@ -341,18 +343,18 @@ static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_ set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline bool mapping_writeback_may_deadlock_on_reclaim(struct address_space *mapping) +static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping) { return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline gfp_t mapping_gfp_mask(struct address_space * mapping) +static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ -static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, +static inline gfp_t mapping_gfp_constraint(const struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; @@ -475,11 +477,17 @@ mapping_min_folio_order(const struct address_space *mapping) } static inline unsigned long -mapping_min_folio_nrpages(struct address_space *mapping) +mapping_min_folio_nrpages(const struct address_space *mapping) { return 1UL << mapping_min_folio_order(mapping); } +static inline unsigned long +mapping_min_folio_nrbytes(const struct address_space *mapping) +{ + return mapping_min_folio_nrpages(mapping) << PAGE_SHIFT; +} + /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. @@ -489,7 +497,7 @@ mapping_min_folio_nrpages(struct address_space *mapping) * new folio to the page cache and need to know what index to give it, * call this function. */ -static inline pgoff_t mapping_align_index(struct address_space *mapping, +static inline pgoff_t mapping_align_index(const struct address_space *mapping, pgoff_t index) { return round_down(index, mapping_min_folio_nrpages(mapping)); @@ -499,7 +507,7 @@ static inline pgoff_t mapping_align_index(struct address_space *mapping, * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. */ -static inline bool mapping_large_folio_support(struct address_space *mapping) +static inline bool mapping_large_folio_support(const struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON, @@ -514,7 +522,7 @@ static inline size_t mapping_max_folio_size(const struct address_space *mapping) return PAGE_SIZE << mapping_max_folio_order(mapping); } -static inline int filemap_nr_thps(struct address_space *mapping) +static inline int filemap_nr_thps(const struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); @@ -543,7 +551,7 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *folio_mapping(struct folio *); +struct address_space *folio_mapping(const struct folio *folio); /** * folio_flush_mapping - Find the file mapping this folio belongs to. @@ -928,7 +936,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, * * Return: The index of the folio which follows this folio in the file. */ -static inline pgoff_t folio_next_index(struct folio *folio) +static inline pgoff_t folio_next_index(const struct folio *folio) { return folio->index + folio_nr_pages(folio); } @@ -957,7 +965,7 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ -static inline bool folio_contains(struct folio *folio, pgoff_t index) +static inline bool folio_contains(const struct folio *folio, pgoff_t index) { VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); return index - folio->index < folio_nr_pages(folio); @@ -1034,13 +1042,13 @@ static inline loff_t page_offset(struct page *page) /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ -static inline pgoff_t folio_pgoff(struct folio *folio) +static inline pgoff_t folio_pgoff(const struct folio *folio) { return folio->index; } -static inline pgoff_t linear_page_index(struct vm_area_struct *vma, - unsigned long address) +static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, + const unsigned long address) { pgoff_t pgoff; pgoff = (address - vma->vm_start) >> PAGE_SHIFT; @@ -1460,7 +1468,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_pos(struct readahead_control *rac) +static inline loff_t readahead_pos(const struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } @@ -1469,7 +1477,7 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline size_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(const struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } @@ -1478,7 +1486,7 @@ static inline size_t readahead_length(struct readahead_control *rac) * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ -static inline pgoff_t readahead_index(struct readahead_control *rac) +static inline pgoff_t readahead_index(const struct readahead_control *rac) { return rac->_index; } @@ -1487,7 +1495,7 @@ static inline pgoff_t readahead_index(struct readahead_control *rac) * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ -static inline unsigned int readahead_count(struct readahead_control *rac) +static inline unsigned int readahead_count(const struct readahead_control *rac) { return rac->_nr_pages; } @@ -1496,12 +1504,12 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline size_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(const struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } -static inline unsigned long dir_pages(struct inode *inode) +static inline unsigned long dir_pages(const struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -1515,8 +1523,8 @@ static inline unsigned long dir_pages(struct inode *inode) * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ -static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, - struct inode *inode) +static inline ssize_t folio_mkwrite_check_truncate(const struct folio *folio, + const struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; @@ -1547,7 +1555,8 @@ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, * Return: The number of filesystem blocks covered by this folio. */ static inline -unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) +unsigned int i_blocks_per_folio(const struct inode *inode, + const struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 5d3a0cccc6bf..63be5a451627 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -51,12 +51,12 @@ static inline void folio_batch_reinit(struct folio_batch *fbatch) fbatch->i = 0; } -static inline unsigned int folio_batch_count(struct folio_batch *fbatch) +static inline unsigned int folio_batch_count(const struct folio_batch *fbatch) { return fbatch->nr; } -static inline unsigned int folio_batch_space(struct folio_batch *fbatch) +static inline unsigned int folio_batch_space(const struct folio_batch *fbatch) { return PAGEVEC_SIZE - fbatch->nr; } diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 682472c15495..88e18615dd72 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -134,6 +134,9 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, int walk_kernel_page_table_range(unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); +int walk_kernel_page_table_range_lockless(unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, void *private); int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); diff --git a/include/linux/panic.h b/include/linux/panic.h index 7be742628c25..6f972a66c13e 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -43,6 +43,12 @@ void abort(void); extern atomic_t panic_cpu; #define PANIC_CPU_INVALID -1 +bool panic_try_start(void); +void panic_reset(void); +bool panic_in_progress(void); +bool panic_on_this_cpu(void); +bool panic_on_other_cpu(void); + /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ec9d96025683..fd1d91017b99 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -859,7 +859,7 @@ struct perf_event { /* mmap bits */ struct mutex mmap_mutex; - atomic_t mmap_count; + refcount_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; @@ -1719,7 +1719,7 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * -get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, +get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h new file mode 100644 index 000000000000..9174fa59bbc5 --- /dev/null +++ b/include/linux/pgalloc.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGALLOC_H +#define _LINUX_PGALLOC_H + +#include <linux/pgtable.h> +#include <asm/pgalloc.h> + +/* + * {pgd,p4d}_populate_kernel() are defined as macros to allow + * compile-time optimization based on the configured page table levels. + * Without this, linking may fail because callers (e.g., KASAN) may rely + * on calls to these functions being optimized away when passing symbols + * that exist only for certain page table levels. + */ +#define pgd_populate_kernel(addr, pgd, p4d) \ + do { \ + pgd_populate(&init_mm, pgd, p4d); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ + } while (0) + +#define p4d_populate_kernel(addr, p4d, pud) \ + do { \ + p4d_populate(&init_mm, p4d, pud); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ + } while (0) + +#endif /* _LINUX_PGALLOC_H */ diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 8a7f4f802c57..38a82d65e58e 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -107,7 +107,8 @@ static inline bool get_page_tag_ref(struct page *page, union codetag_ref *ref, if (static_key_enabled(&mem_profiling_compressed)) { pgalloc_tag_idx idx; - idx = (page->flags >> alloc_tag_ref_offs) & alloc_tag_ref_mask; + idx = (page->flags.f >> alloc_tag_ref_offs) & + alloc_tag_ref_mask; idx_to_ref(idx, ref); handle->page = page; } else { @@ -149,11 +150,11 @@ static inline void update_page_tag_ref(union pgtag_ref_handle handle, union code idx = (unsigned long)ref_to_idx(ref); idx = (idx & alloc_tag_ref_mask) << alloc_tag_ref_offs; do { - old_flags = READ_ONCE(page->flags); + old_flags = READ_ONCE(page->flags.f); flags = old_flags; flags &= ~(alloc_tag_ref_mask << alloc_tag_ref_offs); flags |= idx; - } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } while (unlikely(!try_cmpxchg(&page->flags.f, &old_flags, flags))); } else { if (WARN_ON(!handle.ref || !ref)) return; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 4c035637eeb7..32e8457ad535 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -232,9 +232,9 @@ static inline int pmd_dirty(pmd_t pmd) * and the mode cannot be used in interrupt context. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define arch_enter_lazy_mmu_mode() do {} while (0) -#define arch_leave_lazy_mmu_mode() do {} while (0) -#define arch_flush_lazy_mmu_mode() do {} while (0) +static inline void arch_enter_lazy_mmu_mode(void) {} +static inline void arch_leave_lazy_mmu_mode(void) {} +static inline void arch_flush_lazy_mmu_mode(void) {} #endif #ifndef pte_batch_hint @@ -1467,6 +1467,22 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned } #endif +/* + * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values + * and let generic vmalloc, ioremap and page table update code know when + * arch_sync_kernel_mappings() needs to be called. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + #endif /* CONFIG_MMU */ /* @@ -1938,10 +1954,11 @@ static inline bool arch_has_pfn_modify_check(void) /* * Page Table Modification bits for pgtbl_mod_mask. * - * These are used by the p?d_alloc_track*() set of functions an in the generic - * vmalloc/ioremap code to track at which page-table levels entries have been - * modified. Based on that the code can better decide when vmalloc and ioremap - * mapping changes need to be synchronized to other page-tables in the system. + * These are used by the p?d_alloc_track*() and p*d_populate_kernel() + * functions in the generic vmalloc, ioremap and page table update code + * to track at which page-table levels entries have been modified. + * Based on that the code can better decide when page table changes need + * to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 @@ -1958,6 +1975,32 @@ static inline bool arch_has_pfn_modify_check(void) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; +enum pgtable_level { + PGTABLE_LEVEL_PTE = 0, + PGTABLE_LEVEL_PMD, + PGTABLE_LEVEL_PUD, + PGTABLE_LEVEL_P4D, + PGTABLE_LEVEL_PGD, +}; + +static inline const char *pgtable_level_to_str(enum pgtable_level level) +{ + switch (level) { + case PGTABLE_LEVEL_PTE: + return "pte"; + case PGTABLE_LEVEL_PMD: + return "pmd"; + case PGTABLE_LEVEL_PUD: + return "pud"; + case PGTABLE_LEVEL_P4D: + return "p4d"; + case PGTABLE_LEVEL_PGD: + return "pgd"; + default: + return "unknown"; + } +} + #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) diff --git a/include/linux/phy.h b/include/linux/phy.h index 4c2b8b6e7187..7a54a8b4d277 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -169,6 +169,16 @@ static inline bool phy_interface_empty(const unsigned long *intf) return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } +static inline void phy_interface_copy(unsigned long *d, const unsigned long *s) +{ + bitmap_copy(d, s, PHY_INTERFACE_MODE_MAX); +} + +static inline unsigned int phy_interface_weight(const unsigned long *intf) +{ + return bitmap_weight(intf, PHY_INTERFACE_MODE_MAX); +} + static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { @@ -1268,9 +1278,13 @@ struct phy_driver { #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -#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) +#define PHY_ID_MATCH_EXTACT_MASK GENMASK(31, 0) +#define PHY_ID_MATCH_MODEL_MASK GENMASK(31, 4) +#define PHY_ID_MATCH_VENDOR_MASK GENMASK(31, 10) + +#define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_EXTACT_MASK +#define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_MODEL_MASK +#define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_VENDOR_MASK /** * phy_id_compare - compare @id1 with @id2 taking account of @mask @@ -1287,6 +1301,32 @@ static inline bool phy_id_compare(u32 id1, u32 id2, u32 mask) } /** + * phy_id_compare_vendor - compare @id with @vendor mask + * @id: PHY ID + * @vendor_mask: PHY Vendor mask + * + * Return: true if the bits from @id match @vendor using the + * generic PHY Vendor mask. + */ +static inline bool phy_id_compare_vendor(u32 id, u32 vendor_mask) +{ + return phy_id_compare(id, vendor_mask, PHY_ID_MATCH_VENDOR_MASK); +} + +/** + * phy_id_compare_model - compare @id with @model mask + * @id: PHY ID + * @model_mask: PHY Model mask + * + * Return: true if the bits from @id match @model using the + * generic PHY Model mask. + */ +static inline bool phy_id_compare_model(u32 id, u32 model_mask) +{ + return phy_id_compare(id, model_mask, PHY_ID_MATCH_MODEL_MASK); +} + +/** * phydev_id_compare - compare @id with the PHY's Clause 22 ID * @phydev: the PHY device * @id: the PHY ID to be matched @@ -1990,9 +2030,7 @@ static inline int phy_read_status(struct phy_device *phydev) return genphy_read_status(phydev); } -void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); -int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); @@ -2094,16 +2132,6 @@ int __phy_hwtstamp_set(struct phy_device *phydev, extern const struct bus_type mdio_bus_type; extern const struct class mdio_bus_class; -struct mdio_board_info { - const char *bus_id; - char modalias[MDIO_NAME_SIZE]; - int mdio_addr; - const void *platform_data; -}; - -int mdiobus_register_board_info(const struct mdio_board_info *info, - unsigned int n); - /** * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 5399b9e41e35..d17ff750c708 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -17,7 +17,7 @@ struct net_device; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier); -int fixed_phy_add(int phy_id, const struct fixed_phy_status *status); +void fixed_phy_add(const struct fixed_phy_status *status); struct phy_device *fixed_phy_register(const struct fixed_phy_status *status, struct device_node *np); @@ -26,11 +26,7 @@ extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); #else -static inline int fixed_phy_add(int phy_id, - const struct fixed_phy_status *status) -{ - return -ENODEV; -} +static inline void fixed_phy_add(const struct fixed_phy_status *status) {} static inline struct phy_device * fixed_phy_register(const struct fixed_phy_status *status, struct device_node *np) @@ -41,16 +37,6 @@ fixed_phy_register(const struct fixed_phy_status *status, static inline void fixed_phy_unregister(struct phy_device *phydev) { } -static inline int fixed_phy_set_link_update(struct phy_device *phydev, - int (*link_update)(struct net_device *, - struct fixed_phy_status *)) -{ - return -ENODEV; -} -static inline int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier) -{ - return -EINVAL; -} #endif /* CONFIG_FIXED_PHY */ #endif /* __PHY_FIXED_H */ diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 30659b615fca..9af0411761d7 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -320,9 +320,8 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * If in 802.3z mode, the link speed is fixed, dependent on the * @state->interface. Duplex and pause modes are negotiated via * the in-band configuration word. Advertised pause modes are set - * according to the @state->an_enabled and @state->advertising - * flags. Beware of MACs which only support full duplex at gigabit - * and higher speeds. + * according to @state->advertising. Beware of MACs which only + * support full duplex at gigabit and higher speeds. * * If in Cisco SGMII mode, the link speed and duplex mode are passed * in the serial bitstream 16-bit configuration word, and the MAC @@ -331,7 +330,7 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * responsible for reading the configuration word and configuring * itself accordingly. * - * Valid state members: interface, an_enabled, pause, advertising. + * Valid state members: interface, pause, advertising. * * Implementations are expected to update the MAC to reflect the * requested settings - i.o.w., if nothing has changed between two diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c67a5811199..445517a72ad0 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -54,10 +54,15 @@ extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS +static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) +{ + return container_of(ns, struct pid_namespace, ns); +} + static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } @@ -78,12 +83,15 @@ static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) } #endif -extern struct pid_namespace *copy_pid_ns(unsigned long flags, +extern struct pid_namespace *copy_pid_ns(u64 flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); +extern bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor); + #else /* !CONFIG_PID_NS */ #include <linux/err.h> @@ -97,7 +105,7 @@ static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) return 0; } -static inline struct pid_namespace *copy_pid_ns(unsigned long flags, +static inline struct pid_namespace *copy_pid_ns(u64 flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) @@ -118,6 +126,12 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } + +static inline bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor) +{ + return false; +} #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 1bcf071b860e..d9245ecec71d 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -88,9 +88,13 @@ struct pinctrl_map; * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. * @PIN_CONFIG_MODE_PWM: this will configure the pin for PWM - * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a - * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/driver-api/pin-control.rst, + * @PIN_CONFIG_LEVEL: setting this will configure the pin as an output and + * drive a value on the line. Use argument 1 to indicate high level, + * argument 0 to indicate low level. Conversely the value of the line + * can be read using this parameter, if and only if that value can be + * represented as a binary 0 or 1 where 0 indicate a low voltage level + * and 1 indicate a high voltage level. + * (Please see Documentation/driver-api/pin-control.rst, * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode * without driving a value there. For most platforms this reduces to @@ -137,7 +141,7 @@ enum pin_config_param { PIN_CONFIG_INPUT_SCHMITT_UV, PIN_CONFIG_MODE_LOW_POWER, PIN_CONFIG_MODE_PWM, - PIN_CONFIG_OUTPUT, + PIN_CONFIG_LEVEL, PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, PIN_CONFIG_PERSIST_STATE, diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index d138e1815645..1a8084e29405 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -11,6 +11,7 @@ #ifndef __LINUX_PINCTRL_PINCTRL_H #define __LINUX_PINCTRL_PINCTRL_H +#include <linux/bits.h> #include <linux/types.h> struct device; @@ -206,16 +207,20 @@ extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group, const unsigned int **pins, unsigned int *num_pins); +#define PINFUNCTION_FLAG_GPIO BIT(0) + /** * struct pinfunction - Description about a function * @name: Name of the function * @groups: An array of groups for this function * @ngroups: Number of groups in @groups + * @flags: Additional pin function flags */ struct pinfunction { const char *name; const char * const *groups; size_t ngroups; + unsigned long flags; }; /* Convenience macro to define a single named pinfunction */ @@ -226,6 +231,15 @@ struct pinfunction { .ngroups = (_ngroups), \ } +/* Same as PINCTRL_PINFUNCTION() but for the GPIO category of functions */ +#define PINCTRL_GPIO_PINFUNCTION(_name, _groups, _ngroups) \ +(struct pinfunction) { \ + .name = (_name), \ + .groups = (_groups), \ + .ngroups = (_ngroups), \ + .flags = PINFUNCTION_FLAG_GPIO, \ + } + #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_PINCTRL) extern struct pinctrl_dev *of_pinctrl_get(struct device_node *np); #else diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h index d6f7b58d6ad0..6db6c3e1ccc2 100644 --- a/include/linux/pinctrl/pinmux.h +++ b/include/linux/pinctrl/pinmux.h @@ -66,6 +66,8 @@ struct pinmux_ops { unsigned int selector, const char * const **groups, unsigned int *num_groups); + bool (*function_is_gpio) (struct pinctrl_dev *pctldev, + unsigned int selector); int (*set_mux) (struct pinctrl_dev *pctldev, unsigned int func_selector, unsigned int group_selector); int (*gpio_request_enable) (struct pinctrl_dev *pctldev, diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index c19b404e3d8d..69294f79cc88 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -1825,6 +1825,16 @@ struct ec_response_pwm_get_duty { uint16_t duty; /* Duty cycle, EC_PWM_MAX_DUTY = 100% */ } __ec_align2; +#define EC_CMD_PWM_GET_FAN_DUTY 0x0027 + +struct ec_params_pwm_get_fan_duty { + uint8_t fan_idx; +} __ec_align1; + +struct ec_response_pwm_get_fan_duty { + uint32_t percent; /* Percentage of duty cycle, ranging from 0 ~ 100 */ +} __ec_align4; + /*****************************************************************************/ /* * Lightbar commands. This looks worse than it is. Since we only use one HOST @@ -3127,14 +3137,31 @@ struct ec_params_thermal_set_threshold_v1 { /****************************************************************************/ -/* Toggle automatic fan control */ +/* Set or get fan control mode */ #define EC_CMD_THERMAL_AUTO_FAN_CTRL 0x0052 +enum ec_auto_fan_ctrl_cmd { + EC_AUTO_FAN_CONTROL_CMD_SET = 0, + EC_AUTO_FAN_CONTROL_CMD_GET, +}; + /* Version 1 of input params */ struct ec_params_auto_fan_ctrl_v1 { uint8_t fan_idx; } __ec_align1; +/* Version 2 of input params */ +struct ec_params_auto_fan_ctrl_v2 { + uint8_t fan_idx; + uint8_t cmd; /* enum ec_auto_fan_ctrl_cmd */ + uint8_t set_auto; /* only used with EC_AUTO_FAN_CONTROL_CMD_SET - bool + */ +} __ec_align4; + +struct ec_response_auto_fan_control { + uint8_t is_auto; /* bool */ +} __ec_align1; + /* Get/Set TMP006 calibration data */ #define EC_CMD_TMP006_GET_CALIBRATION 0x0053 #define EC_CMD_TMP006_SET_CALIBRATION 0x0054 diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 3ec24f445c29..de14923720a5 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -33,12 +33,18 @@ /* * Max bus-specific overhead incurred by request/responses. - * I2C requires 1 additional byte for requests. - * I2C requires 2 additional bytes for responses. - * SPI requires up to 32 additional bytes for responses. + * + * Request: + * - I2C requires 1 byte (see struct ec_host_request_i2c). + * - ISHTP requires 4 bytes (see struct cros_ish_out_msg). + * + * Response: + * - I2C requires 2 bytes (see struct ec_host_response_i2c). + * - ISHTP requires 4 bytes (see struct cros_ish_in_msg). + * - SPI requires 32 bytes (see EC_MSG_PREAMBLE_COUNT). */ #define EC_PROTO_VERSION_UNKNOWN 0 -#define EC_MAX_REQUEST_OVERHEAD 1 +#define EC_MAX_REQUEST_OVERHEAD 4 #define EC_MAX_RESPONSE_OVERHEAD 32 /* @@ -122,6 +128,7 @@ struct cros_ec_command { * @dout_size: Size of dout buffer to allocate (zero to use static dout). * @wake_enabled: True if this device can wake the system from sleep. * @suspended: True if this device had been suspended. + * @registered: True if this device had been registered. * @cmd_xfer: Send command to EC and get response. * Returns the number of bytes received if the communication * succeeded, but that doesn't mean the EC was happy with the @@ -180,6 +187,7 @@ struct cros_ec_device { int dout_size; bool wake_enabled; bool suspended; + bool registered; int (*cmd_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); int (*pkt_xfer)(struct cros_ec_device *ec, @@ -272,6 +280,8 @@ int cros_ec_cmd_readmem(struct cros_ec_device *ec_dev, u8 offset, u8 size, void int cros_ec_get_cmd_versions(struct cros_ec_device *ec_dev, u16 cmd); +bool cros_ec_device_registered(struct cros_ec_device *ec_dev); + /** * cros_ec_get_time_ns() - Return time in ns. * diff --git a/include/linux/platform_data/dmtimer-omap.h b/include/linux/platform_data/dmtimer-omap.h index 95d852aef130..726d89143842 100644 --- a/include/linux/platform_data/dmtimer-omap.h +++ b/include/linux/platform_data/dmtimer-omap.h @@ -36,9 +36,13 @@ struct omap_dm_timer_ops { int (*set_pwm)(struct omap_dm_timer *timer, int def_on, int toggle, int trigger, int autoreload); int (*get_pwm_status)(struct omap_dm_timer *timer); + int (*set_cap)(struct omap_dm_timer *timer, + int autoreload, bool config_period); + int (*get_cap_status)(struct omap_dm_timer *timer); int (*set_prescaler)(struct omap_dm_timer *timer, int prescaler); unsigned int (*read_counter)(struct omap_dm_timer *timer); + unsigned int (*read_cap)(struct omap_dm_timer *timer, bool is_period); int (*write_counter)(struct omap_dm_timer *timer, unsigned int value); unsigned int (*read_status)(struct omap_dm_timer *timer); diff --git a/include/linux/platform_data/tmio.h b/include/linux/platform_data/tmio.h index b060124ba1ae..426291713b83 100644 --- a/include/linux/platform_data/tmio.h +++ b/include/linux/platform_data/tmio.h @@ -47,6 +47,9 @@ /* Some controllers have a CBSY bit */ #define TMIO_MMC_HAVE_CBSY BIT(11) +/* Some controllers have a 64-bit wide data port register */ +#define TMIO_MMC_64BIT_DATA_PORT BIT(12) + struct tmio_mmc_data { void *chan_priv_tx; void *chan_priv_rx; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index 78276a11c48d..1571e9157fa5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -27,6 +27,7 @@ #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 +#define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 #define INT3472_PDEV_MAX_NAME_LEN 23 #define INT3472_MAX_SENSOR_GPIOS 3 diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c84edf217819..f67a2cb7d781 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -115,6 +115,12 @@ struct dev_pm_domain_list { * genpd provider specific way, likely through a * parent device node. This flag makes genpd to * skip its internal support for this. + * + * GENPD_FLAG_NO_STAY_ON: For genpd OF providers a powered-on PM domain at + * initialization is prevented from being + * powered-off until the ->sync_state() callback is + * invoked. This flag informs genpd to allow a + * power-off without waiting for ->sync_state(). */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -126,6 +132,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) #define GENPD_FLAG_DEV_NAME_FW (1U << 8) #define GENPD_FLAG_NO_SYNC_STATE (1U << 9) +#define GENPD_FLAG_NO_STAY_ON (1U << 10) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index cf477beae4bb..789406d95e69 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -98,6 +98,25 @@ struct dev_pm_opp_data { unsigned long u_volt; }; +/** + * struct dev_pm_opp_key - Key used to identify OPP entries + * @freq: Frequency in Hz. Use 0 if frequency is not to be matched. + * @level: Performance level associated with the OPP entry. + * Use OPP_LEVEL_UNSET if level is not to be matched. + * @bw: Bandwidth associated with the OPP entry. + * Use 0 if bandwidth is not to be matched. + * + * This structure is used to uniquely identify an OPP entry based on + * frequency, performance level, and bandwidth. Each field can be + * selectively ignored during matching by setting it to its respective + * NOP value. + */ +struct dev_pm_opp_key { + unsigned long freq; + unsigned int level; + u32 bw; +}; + #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); @@ -131,6 +150,10 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available); +struct dev_pm_opp *dev_pm_opp_find_key_exact(struct device *dev, + struct dev_pm_opp_key *key, + bool available); + struct dev_pm_opp * dev_pm_opp_find_freq_exact_indexed(struct device *dev, unsigned long freq, u32 index, bool available); @@ -289,6 +312,13 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_key_exact(struct device *dev, + struct dev_pm_opp_key *key, + bool available) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct dev_pm_opp * dev_pm_opp_find_freq_exact_indexed(struct device *dev, unsigned long freq, u32 index, bool available) diff --git a/include/linux/poison.h b/include/linux/poison.h index 8ca2235f78d5..299e2dd7da6d 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -90,4 +90,7 @@ /********** lib/stackdepot.c **********/ #define STACK_DEPOT_POISON ((void *)(0xD390 + POISON_POINTER_DELTA)) +/********** io_uring/ **********/ +#define IO_URING_PTR_POISON ((void *)(0x1091UL + POISON_POINTER_DELTA)) + #endif diff --git a/include/linux/power/max77705_charger.h b/include/linux/power/max77705_charger.h index fdec9af9c541..6653abfdf747 100644 --- a/include/linux/power/max77705_charger.h +++ b/include/linux/power/max77705_charger.h @@ -9,35 +9,27 @@ #ifndef __MAX77705_CHARGER_H #define __MAX77705_CHARGER_H __FILE__ +#include <linux/regmap.h> + /* MAX77705_CHG_REG_CHG_INT */ -#define MAX77705_BYP_I BIT(0) -#define MAX77705_INP_LIMIT_I BIT(1) -#define MAX77705_BATP_I BIT(2) -#define MAX77705_BAT_I BIT(3) -#define MAX77705_CHG_I BIT(4) -#define MAX77705_WCIN_I BIT(5) -#define MAX77705_CHGIN_I BIT(6) -#define MAX77705_AICL_I BIT(7) - -/* MAX77705_CHG_REG_CHG_INT_MASK */ -#define MAX77705_BYP_IM BIT(0) -#define MAX77705_INP_LIMIT_IM BIT(1) -#define MAX77705_BATP_IM BIT(2) -#define MAX77705_BAT_IM BIT(3) -#define MAX77705_CHG_IM BIT(4) -#define MAX77705_WCIN_IM BIT(5) -#define MAX77705_CHGIN_IM BIT(6) -#define MAX77705_AICL_IM BIT(7) +#define MAX77705_BYP_I (0) +#define MAX77705_INP_LIMIT_I (1) +#define MAX77705_BATP_I (2) +#define MAX77705_BAT_I (3) +#define MAX77705_CHG_I (4) +#define MAX77705_WCIN_I (5) +#define MAX77705_CHGIN_I (6) +#define MAX77705_AICL_I (7) /* MAX77705_CHG_REG_CHG_INT_OK */ -#define MAX77705_BYP_OK BIT(0) -#define MAX77705_DISQBAT_OK BIT(1) -#define MAX77705_BATP_OK BIT(2) -#define MAX77705_BAT_OK BIT(3) -#define MAX77705_CHG_OK BIT(4) -#define MAX77705_WCIN_OK BIT(5) -#define MAX77705_CHGIN_OK BIT(6) -#define MAX77705_AICL_OK BIT(7) +#define MAX77705_BYP_OK BIT(MAX77705_BYP_I) +#define MAX77705_DISQBAT_OK BIT(MAX77705_INP_LIMIT_I) +#define MAX77705_BATP_OK BIT(MAX77705_BATP_I) +#define MAX77705_BAT_OK BIT(MAX77705_BAT_I) +#define MAX77705_CHG_OK BIT(MAX77705_CHG_I) +#define MAX77705_WCIN_OK BIT(MAX77705_WCIN_I) +#define MAX77705_CHGIN_OK BIT(MAX77705_CHGIN_I) +#define MAX77705_AICL_OK BIT(MAX77705_AICL_I) /* MAX77705_CHG_REG_DETAILS_00 */ #define MAX77705_BATP_DTLS BIT(0) @@ -63,7 +55,6 @@ #define MAX77705_BUCK_SHIFT 2 #define MAX77705_BOOST_SHIFT 3 #define MAX77705_WDTEN_SHIFT 4 -#define MAX77705_MODE_MASK GENMASK(3, 0) #define MAX77705_CHG_MASK BIT(MAX77705_CHG_SHIFT) #define MAX77705_UNO_MASK BIT(MAX77705_UNO_SHIFT) #define MAX77705_OTG_MASK BIT(MAX77705_OTG_SHIFT) @@ -74,34 +65,19 @@ #define MAX77705_OTG_CTRL (MAX77705_OTG_MASK | MAX77705_BOOST_MASK) /* MAX77705_CHG_REG_CNFG_01 */ -#define MAX77705_FCHGTIME_SHIFT 0 -#define MAX77705_FCHGTIME_MASK GENMASK(2, 0) -#define MAX77705_CHG_RSTRT_SHIFT 4 -#define MAX77705_CHG_RSTRT_MASK GENMASK(5, 4) #define MAX77705_FCHGTIME_DISABLE 0 #define MAX77705_CHG_RSTRT_DISABLE 0x3 -#define MAX77705_PQEN_SHIFT 7 -#define MAX77705_PQEN_MASK BIT(7) #define MAX77705_CHG_PQEN_DISABLE 0 #define MAX77705_CHG_PQEN_ENABLE 1 /* MAX77705_CHG_REG_CNFG_02 */ -#define MAX77705_OTG_ILIM_SHIFT 6 -#define MAX77705_OTG_ILIM_MASK GENMASK(7, 6) #define MAX77705_OTG_ILIM_500 0 #define MAX77705_OTG_ILIM_900 1 #define MAX77705_OTG_ILIM_1200 2 #define MAX77705_OTG_ILIM_1500 3 -#define MAX77705_CHG_CC GENMASK(5, 0) /* MAX77705_CHG_REG_CNFG_03 */ -#define MAX77705_TO_ITH_SHIFT 0 -#define MAX77705_TO_ITH_MASK GENMASK(2, 0) -#define MAX77705_TO_TIME_SHIFT 3 -#define MAX77705_TO_TIME_MASK GENMASK(5, 3) -#define MAX77705_SYS_TRACK_DIS_SHIFT 7 -#define MAX77705_SYS_TRACK_DIS_MASK BIT(7) #define MAX77705_TO_ITH_150MA 0 #define MAX77705_TO_TIME_30M 3 #define MAX77705_SYS_TRACK_ENABLE 0 @@ -110,15 +86,8 @@ /* MAX77705_CHG_REG_CNFG_04 */ #define MAX77705_CHG_MINVSYS_SHIFT 6 #define MAX77705_CHG_MINVSYS_MASK GENMASK(7, 6) -#define MAX77705_CHG_PRM_SHIFT 0 -#define MAX77705_CHG_PRM_MASK GENMASK(5, 0) - -#define MAX77705_CHG_CV_PRM_SHIFT 0 -#define MAX77705_CHG_CV_PRM_MASK GENMASK(5, 0) /* MAX77705_CHG_REG_CNFG_05 */ -#define MAX77705_REG_B2SOVRC_SHIFT 0 -#define MAX77705_REG_B2SOVRC_MASK GENMASK(3, 0) #define MAX77705_B2SOVRC_DISABLE 0 #define MAX77705_B2SOVRC_4_5A 6 #define MAX77705_B2SOVRC_4_8A 8 @@ -128,9 +97,8 @@ #define MAX77705_WDTCLR_SHIFT 0 #define MAX77705_WDTCLR_MASK GENMASK(1, 0) #define MAX77705_WDTCLR 1 -#define MAX77705_CHGPROT_MASK GENMASK(3, 2) -#define MAX77705_CHGPROT_UNLOCKED GENMASK(3, 2) -#define MAX77705_SLOWEST_LX_SLOPE GENMASK(6, 5) +#define MAX77705_CHGPROT_UNLOCKED 3 +#define MAX77705_SLOWEST_LX_SLOPE 3 /* MAX77705_CHG_REG_CNFG_07 */ #define MAX77705_CHG_FMBST 4 @@ -140,36 +108,14 @@ #define MAX77705_REG_FGSRC_MASK BIT(MAX77705_REG_FGSRC_SHIFT) /* MAX77705_CHG_REG_CNFG_08 */ -#define MAX77705_REG_FSW_SHIFT 0 -#define MAX77705_REG_FSW_MASK GENMASK(1, 0) #define MAX77705_CHG_FSW_3MHz 0 #define MAX77705_CHG_FSW_2MHz 1 #define MAX77705_CHG_FSW_1_5MHz 2 /* MAX77705_CHG_REG_CNFG_09 */ -#define MAX77705_CHG_CHGIN_LIM_MASK GENMASK(6, 0) -#define MAX77705_CHG_EN_MASK BIT(7) #define MAX77705_CHG_DISABLE 0 -#define MAX77705_CHARGER_CHG_CHARGING(_reg) \ - (((_reg) & MAX77705_CHG_EN_MASK) > 1) - - -/* MAX77705_CHG_REG_CNFG_10 */ -#define MAX77705_CHG_WCIN_LIM GENMASK(5, 0) - -/* MAX77705_CHG_REG_CNFG_11 */ -#define MAX77705_VBYPSET_SHIFT 0 -#define MAX77705_VBYPSET_MASK GENMASK(6, 0) /* MAX77705_CHG_REG_CNFG_12 */ -#define MAX77705_CHGINSEL_SHIFT 5 -#define MAX77705_CHGINSEL_MASK BIT(MAX77705_CHGINSEL_SHIFT) -#define MAX77705_WCINSEL_SHIFT 6 -#define MAX77705_WCINSEL_MASK BIT(MAX77705_WCINSEL_SHIFT) -#define MAX77705_VCHGIN_REG_MASK GENMASK(4, 3) -#define MAX77705_WCIN_REG_MASK GENMASK(2, 1) -#define MAX77705_REG_DISKIP_SHIFT 0 -#define MAX77705_REG_DISKIP_MASK BIT(MAX77705_REG_DISKIP_SHIFT) /* REG=4.5V, UVLO=4.7V */ #define MAX77705_VCHGIN_4_5 0 /* REG=4.5V, UVLO=4.7V */ @@ -183,9 +129,59 @@ #define MAX77705_CURRENT_CHGIN_MIN 100000 #define MAX77705_CURRENT_CHGIN_MAX 3200000 +enum max77705_field_idx { + MAX77705_CHGPROT, + MAX77705_CHG_EN, + MAX77705_CHG_CC_LIM, + MAX77705_CHG_CHGIN_LIM, + MAX77705_CHG_CV_PRM, + MAX77705_CHG_PQEN, + MAX77705_CHG_RSTRT, + MAX77705_CHG_WCIN, + MAX77705_FCHGTIME, + MAX77705_LX_SLOPE, + MAX77705_MODE, + MAX77705_OTG_ILIM, + MAX77705_REG_B2SOVRC, + MAX77705_REG_DISKIP, + MAX77705_REG_FSW, + MAX77705_SYS_TRACK, + MAX77705_TO, + MAX77705_TO_TIME, + MAX77705_VBYPSET, + MAX77705_VCHGIN, + MAX77705_WCIN, + MAX77705_N_REGMAP_FIELDS, +}; + +static const struct reg_field max77705_reg_field[MAX77705_N_REGMAP_FIELDS] = { + [MAX77705_MODE] = REG_FIELD(MAX77705_CHG_REG_CNFG_00, 0, 3), + [MAX77705_FCHGTIME] = REG_FIELD(MAX77705_CHG_REG_CNFG_01, 0, 2), + [MAX77705_CHG_RSTRT] = REG_FIELD(MAX77705_CHG_REG_CNFG_01, 4, 5), + [MAX77705_CHG_PQEN] = REG_FIELD(MAX77705_CHG_REG_CNFG_01, 7, 7), + [MAX77705_CHG_CC_LIM] = REG_FIELD(MAX77705_CHG_REG_CNFG_02, 0, 5), + [MAX77705_OTG_ILIM] = REG_FIELD(MAX77705_CHG_REG_CNFG_02, 6, 7), + [MAX77705_TO] = REG_FIELD(MAX77705_CHG_REG_CNFG_03, 0, 2), + [MAX77705_TO_TIME] = REG_FIELD(MAX77705_CHG_REG_CNFG_03, 3, 5), + [MAX77705_SYS_TRACK] = REG_FIELD(MAX77705_CHG_REG_CNFG_03, 7, 7), + [MAX77705_CHG_CV_PRM] = REG_FIELD(MAX77705_CHG_REG_CNFG_04, 0, 5), + [MAX77705_REG_B2SOVRC] = REG_FIELD(MAX77705_CHG_REG_CNFG_05, 0, 3), + [MAX77705_CHGPROT] = REG_FIELD(MAX77705_CHG_REG_CNFG_06, 2, 3), + [MAX77705_LX_SLOPE] = REG_FIELD(MAX77705_CHG_REG_CNFG_06, 5, 6), + [MAX77705_REG_FSW] = REG_FIELD(MAX77705_CHG_REG_CNFG_08, 0, 1), + [MAX77705_CHG_CHGIN_LIM] = REG_FIELD(MAX77705_CHG_REG_CNFG_09, 0, 6), + [MAX77705_CHG_EN] = REG_FIELD(MAX77705_CHG_REG_CNFG_09, 7, 7), + [MAX77705_CHG_WCIN] = REG_FIELD(MAX77705_CHG_REG_CNFG_10, 0, 5), + [MAX77705_VBYPSET] = REG_FIELD(MAX77705_CHG_REG_CNFG_11, 0, 6), + [MAX77705_REG_DISKIP] = REG_FIELD(MAX77705_CHG_REG_CNFG_12, 0, 0), + [MAX77705_WCIN] = REG_FIELD(MAX77705_CHG_REG_CNFG_12, 1, 2), + [MAX77705_VCHGIN] = REG_FIELD(MAX77705_CHG_REG_CNFG_12, 3, 4), +}; + struct max77705_charger_data { struct device *dev; struct regmap *regmap; + struct regmap_field *rfield[MAX77705_N_REGMAP_FIELDS]; struct power_supply_battery_info *bat_info; struct workqueue_struct *wqueue; struct work_struct chgin_work; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index f21f806bfb38..360ffdf272da 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -176,6 +176,8 @@ enum power_supply_property { POWER_SUPPLY_PROP_MANUFACTURE_YEAR, POWER_SUPPLY_PROP_MANUFACTURE_MONTH, POWER_SUPPLY_PROP_MANUFACTURE_DAY, + POWER_SUPPLY_PROP_INTERNAL_RESISTANCE, + POWER_SUPPLY_PROP_STATE_OF_HEALTH, /* Properties of type `const char *' */ POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 1fad1c8a4c76..102202185d7a 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -372,7 +372,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, /* * Migrate-Disable and why it is undesired. * - * When a preempted task becomes elegible to run under the ideal model (IOW it + * When a preempted task becomes eligible to run under the ideal model (IOW it * becomes one of the M highest priority tasks), it might still have to wait * for the preemptee's migrate_disable() section to complete. Thereby suffering * a reduction in bandwidth in the exact duration of the migrate_disable() @@ -387,7 +387,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, * - a lower priority tasks; which under preempt_disable() could've instantly * migrated away when another CPU becomes available, is now constrained * by the ability to push the higher priority task away, which might itself be - * in a migrate_disable() section, reducing it's available bandwidth. + * in a migrate_disable() section, reducing its available bandwidth. * * IOW it trades latency / moves the interference term, but it stays in the * system, and as long as it remains unbounded, the system is not fully @@ -399,7 +399,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a * number of primitives into becoming preemptible, they would also allow * migration. This turns out to break a bunch of per-cpu usage. To this end, - * all these primitives employ migirate_disable() to restore this implicit + * all these primitives employ migrate_disable() to restore this implicit * assumption. * * This is a 'temporary' work-around at best. The correct solution is getting @@ -407,7 +407,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, * per-cpu locking or short preempt-disable regions. * * The end goal must be to get rid of migrate_disable(), alternatively we need - * a schedulability theory that does not depend on abritrary migration. + * a schedulability theory that does not depend on arbitrary migration. * * * Notes on the implementation. @@ -424,8 +424,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, * work-conserving schedulers. * */ -extern void migrate_disable(void); -extern void migrate_enable(void); /** * preempt_disable_nested - Disable preemption inside a normally preempt disabled section @@ -471,7 +469,6 @@ static __always_inline void preempt_enable_nested(void) DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) -DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) #ifdef CONFIG_PREEMPT_DYNAMIC diff --git a/include/linux/printk.h b/include/linux/printk.h index 5d22b803f51e..45c663124c9b 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -330,8 +330,6 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress) #endif -bool this_cpu_in_panic(void); - #ifdef CONFIG_SMP extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 4b20375f3783..e81b8e596e4f 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -5,7 +5,7 @@ #ifndef _LINUX_PROC_NS_H #define _LINUX_PROC_NS_H -#include <linux/ns_common.h> +#include <linux/nsfs.h> #include <uapi/linux/nsfs.h> struct pid_namespace; @@ -17,7 +17,6 @@ struct inode; struct proc_ns_operations { const char *name; const char *real_ns_name; - int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsset *nsset, struct ns_common *ns); @@ -66,25 +65,6 @@ static inline void proc_free_inum(unsigned int inum) {} #endif /* CONFIG_PROC_FS */ -static inline int ns_alloc_inum(struct ns_common *ns) -{ - WRITE_ONCE(ns->stashed, NULL); - return proc_alloc_inum(&ns->inum); -} - -#define ns_free_inum(ns) proc_free_inum((ns)->inum) - #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) -extern int ns_get_path(struct path *path, struct task_struct *task, - const struct proc_ns_operations *ns_ops); -typedef struct ns_common *ns_get_path_helper_t(void *); -extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, - void *private_data); - -extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); - -extern int ns_get_name(char *buf, size_t size, struct task_struct *task, - const struct proc_ns_operations *ns_ops); -extern void nsfs_init(void); #endif /* _LINUX_PROC_NS_H */ diff --git a/include/linux/property.h b/include/linux/property.h index 82f0cb3abd1e..50b26589dd70 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -176,6 +176,16 @@ struct fwnode_handle *fwnode_get_next_available_child_node( for (child = fwnode_get_next_available_child_node(fwnode, NULL); child;\ child = fwnode_get_next_available_child_node(fwnode, child)) +#define fwnode_for_each_child_node_scoped(fwnode, child) \ + for (struct fwnode_handle *child __free(fwnode_handle) = \ + fwnode_get_next_child_node(fwnode, NULL); \ + child; child = fwnode_get_next_child_node(fwnode, child)) + +#define fwnode_for_each_available_child_node_scoped(fwnode, child) \ + for (struct fwnode_handle *child __free(fwnode_handle) = \ + fwnode_get_next_available_child_node(fwnode, NULL); \ + child; child = fwnode_get_next_available_child_node(fwnode, child)) + struct fwnode_handle *device_get_next_child_node(const struct device *dev, struct fwnode_handle *child); @@ -574,8 +584,8 @@ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name); -int software_node_register_node_group(const struct software_node **node_group); -void software_node_unregister_node_group(const struct software_node **node_group); +int software_node_register_node_group(const struct software_node * const *node_group); +void software_node_unregister_node_group(const struct software_node * const *node_group); int software_node_register(const struct software_node *node); void software_node_unregister(const struct software_node *node); diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index 1504fb012c05..540abf7de048 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -7,6 +7,8 @@ enum psp_platform_access_msg { PSP_CMD_NONE = 0x0, + PSP_SFS_GET_FW_VERSIONS, + PSP_SFS_UPDATE, PSP_CMD_HSTI_QUERY = 0x14, PSP_I2C_REQ_BUS_CMD = 0x64, PSP_DYNAMIC_BOOST_GET_NONCE, diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 3d089bd4d5e9..884364596dd3 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -67,6 +67,8 @@ struct ptp_system_timestamp { * @n_ext_ts: The number of external time stamp channels. * @n_per_out: The number of programmable periodic signals. * @n_pins: The number of programmable pins. + * @n_per_lp: The number of channels that support loopback the periodic + * output signal. * @pps: Indicates whether the clock supports a PPS callback. * * @supported_perout_flags: The set of flags the driver supports for the @@ -175,6 +177,11 @@ struct ptp_system_timestamp { * scheduling time (>=0) or negative value in case further * scheduling is not required. * + * @perout_loopback: Request driver to enable or disable the periodic output + * signal loopback. + * parameter index: index of the periodic output signal channel. + * parameter on: caller passes one to enable or zero to disable. + * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). * @@ -189,6 +196,7 @@ struct ptp_clock_info { int n_ext_ts; int n_per_out; int n_pins; + int n_per_lp; int pps; unsigned int supported_perout_flags; unsigned int supported_extts_flags; @@ -213,6 +221,8 @@ struct ptp_clock_info { int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); long (*do_aux_work)(struct ptp_clock_info *ptp); + int (*perout_loopback)(struct ptp_clock_info *ptp, unsigned int index, + int on); }; struct ptp_clock; @@ -361,6 +371,24 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); /** + * ptp_clock_index_by_of_node() - obtain the device index of + * a PTP clock based on the PTP device of_node + * + * @np: The device of_node pointer of the PTP device. + * Return: The PHC index on success or -1 on failure. + */ +int ptp_clock_index_by_of_node(struct device_node *np); + +/** + * ptp_clock_index_by_dev() - obtain the device index of + * a PTP clock based on the PTP device. + * + * @parent: The parent device (PTP device) pointer of the PTP clock. + * Return: The PHC index on success or -1 on failure. + */ +int ptp_clock_index_by_dev(struct device *parent); + +/** * ptp_find_pin() - obtain the pin index of a given auxiliary function * * The caller must hold ptp_clock::pincfg_mux. Drivers do not have @@ -425,6 +453,10 @@ static inline void ptp_clock_event(struct ptp_clock *ptp, { } static inline int ptp_clock_index(struct ptp_clock *ptp) { return -1; } +static inline int ptp_clock_index_by_of_node(struct device_node *np) +{ return -1; } +static inline int ptp_clock_index_by_dev(struct device *parent) +{ return -1; } static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 551329220e4f..534531807d95 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -243,6 +243,24 @@ static inline bool ptr_ring_empty_bh(struct ptr_ring *r) return ret; } +/* Zero entries from tail to specified head. + * NB: if consumer_head can be >= r->size need to fixup tail later. + */ +static inline void __ptr_ring_zero_tail(struct ptr_ring *r, int consumer_head) +{ + int head = consumer_head; + + /* Zero out entries in the reverse order: this way we touch the + * cache line that producer might currently be reading the last; + * producer won't make progress and touch other cache lines + * besides the first one until we write out all entries. + */ + while (likely(head > r->consumer_tail)) + r->queue[--head] = NULL; + + r->consumer_tail = consumer_head; +} + /* Must only be called after __ptr_ring_peek returned !NULL */ static inline void __ptr_ring_discard_one(struct ptr_ring *r) { @@ -261,8 +279,7 @@ static inline void __ptr_ring_discard_one(struct ptr_ring *r) /* Note: we must keep consumer_head valid at all times for __ptr_ring_empty * to work correctly. */ - int consumer_head = r->consumer_head; - int head = consumer_head++; + int consumer_head = r->consumer_head + 1; /* Once we have processed enough entries invalidate them in * the ring all at once so producer can reuse their space in the ring. @@ -270,16 +287,9 @@ static inline void __ptr_ring_discard_one(struct ptr_ring *r) * but helps keep the implementation simple. */ if (unlikely(consumer_head - r->consumer_tail >= r->batch || - consumer_head >= r->size)) { - /* Zero out entries in the reverse order: this way we touch the - * cache line that producer might currently be reading the last; - * producer won't make progress and touch other cache lines - * besides the first one until we write out all entries. - */ - while (likely(head >= r->consumer_tail)) - r->queue[head--] = NULL; - r->consumer_tail = consumer_head; - } + consumer_head >= r->size)) + __ptr_ring_zero_tail(r, consumer_head); + if (unlikely(consumer_head >= r->size)) { consumer_head = 0; r->consumer_tail = 0; @@ -513,7 +523,6 @@ static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n, void (*destroy)(void *)) { unsigned long flags; - int head; spin_lock_irqsave(&r->consumer_lock, flags); spin_lock(&r->producer_lock); @@ -525,17 +534,14 @@ static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n, * Clean out buffered entries (for simplicity). This way following code * can test entries for NULL and if not assume they are valid. */ - head = r->consumer_head - 1; - while (likely(head >= r->consumer_tail)) - r->queue[head--] = NULL; - r->consumer_tail = r->consumer_head; + __ptr_ring_zero_tail(r, r->consumer_head); /* * Go over entries in batch, start moving head back and copy entries. * Stop when we run into previously unconsumed entries. */ while (n) { - head = r->consumer_head - 1; + int head = r->consumer_head - 1; if (head < 0) head = r->size - 1; if (r->queue[head]) { diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 8cafc483db53..549ac4aaad59 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -5,6 +5,7 @@ #include <linux/cdev.h> #include <linux/device.h> #include <linux/err.h> +#include <linux/gpio/driver.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> @@ -321,6 +322,7 @@ struct pwm_ops { * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier * @atomic: can the driver's ->apply() be called in atomic context + * @gpio: &struct gpio_chip to operate this PWM chip's lines as GPO * @uses_pwmchip_alloc: signals if pwmchip_allow was used to allocate this chip * @operational: signals if the chip can be used (or is already deregistered) * @nonatomic_lock: mutex for nonatomic chips @@ -340,6 +342,7 @@ struct pwm_chip { bool atomic; /* only used internally by the PWM framework */ + struct gpio_chip gpio; bool uses_pwmchip_alloc; bool operational; union { diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 120536f4c6eb..f67f96711f0d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -24,7 +24,7 @@ #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> -#include <linux/preempt.h> +#include <linux/sched.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> @@ -962,6 +962,20 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) preempt_enable_notrace(); } +static __always_inline void rcu_read_lock_dont_migrate(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_disable(); + rcu_read_lock(); +} + +static inline void rcu_read_unlock_migrate(void) +{ + rcu_read_unlock(); + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_enable(); +} + /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. diff --git a/include/linux/regulator/s2dos05.h b/include/linux/regulator/s2dos05.h new file mode 100644 index 000000000000..2e89fcbce769 --- /dev/null +++ b/include/linux/regulator/s2dos05.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +// s2dos05.h +// +// Copyright (c) 2016 Samsung Electronics Co., Ltd +// http://www.samsung.com +// Copyright (C) 2024 Dzmitry Sankouski <dsankouski@gmail.com> + +#ifndef __LINUX_S2DOS05_H +#define __LINUX_S2DOS05_H + +// S2DOS05 registers +// Slave Addr : 0xC0 +enum S2DOS05_reg { + S2DOS05_REG_DEV_ID, + S2DOS05_REG_TOPSYS_STAT, + S2DOS05_REG_STAT, + S2DOS05_REG_EN, + S2DOS05_REG_LDO1_CFG, + S2DOS05_REG_LDO2_CFG, + S2DOS05_REG_LDO3_CFG, + S2DOS05_REG_LDO4_CFG, + S2DOS05_REG_BUCK_CFG, + S2DOS05_REG_BUCK_VOUT, + S2DOS05_REG_IRQ_MASK = 0x0D, + S2DOS05_REG_SSD_TSD = 0x0E, + S2DOS05_REG_OCL = 0x10, + S2DOS05_REG_IRQ = 0x11 +}; + +// S2DOS05 regulator ids +enum S2DOS05_regulators { + S2DOS05_LDO1, + S2DOS05_LDO2, + S2DOS05_LDO3, + S2DOS05_LDO4, + S2DOS05_BUCK1, + S2DOS05_REG_MAX, +}; + +#define S2DOS05_IRQ_PWRMT_MASK BIT(5) +#define S2DOS05_IRQ_TSD_MASK BIT(4) +#define S2DOS05_IRQ_SSD_MASK BIT(3) +#define S2DOS05_IRQ_SCP_MASK BIT(2) +#define S2DOS05_IRQ_UVLO_MASK BIT(1) +#define S2DOS05_IRQ_OCD_MASK BIT(0) + +#define S2DOS05_BUCK_MIN1 506250 +#define S2DOS05_LDO_MIN1 1500000 +#define S2DOS05_LDO_MIN2 2700000 +#define S2DOS05_BUCK_STEP1 6250 +#define S2DOS05_LDO_STEP1 25000 +#define S2DOS05_LDO_VSEL_MASK 0x7F +#define S2DOS05_LDO_FD_MASK 0x80 +#define S2DOS05_BUCK_VSEL_MASK 0xFF +#define S2DOS05_BUCK_FD_MASK 0x08 + +#define S2DOS05_ENABLE_MASK_L1 BIT(0) +#define S2DOS05_ENABLE_MASK_L2 BIT(1) +#define S2DOS05_ENABLE_MASK_L3 BIT(2) +#define S2DOS05_ENABLE_MASK_L4 BIT(3) +#define S2DOS05_ENABLE_MASK_B1 BIT(4) + +#define S2DOS05_RAMP_DELAY 12000 + +#define S2DOS05_ENABLE_TIME_LDO 50 +#define S2DOS05_ENABLE_TIME_BUCK 350 + +#define S2DOS05_LDO_N_VOLTAGES (S2DOS05_LDO_VSEL_MASK + 1) +#define S2DOS05_BUCK_N_VOLTAGES (S2DOS05_BUCK_VSEL_MASK + 1) + +#define S2DOS05_REGULATOR_MAX (S2DOS05_REG_MAX) + +#endif // __LINUX_S2DOS05_H diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 6fb4894b8cfd..a7d92718b653 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -157,27 +157,42 @@ struct rdt_ctrl_domain { }; /** + * struct mbm_cntr_cfg - Assignable counter configuration. + * @evtid: MBM event to which the counter is assigned. Only valid + * if @rdtgroup is not NULL. + * @rdtgrp: resctrl group assigned to the counter. NULL if the + * counter is free. + */ +struct mbm_cntr_cfg { + enum resctrl_event_id evtid; + struct rdtgroup *rdtgrp; +}; + +/** * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource * @hdr: common header for different domain types * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold - * @mbm_total: saved state for MBM total bandwidth - * @mbm_local: saved state for MBM local bandwidth + * @mbm_states: Per-event pointer to the MBM event's saved state. + * An MBM event's state is an array of struct mbm_state + * indexed by RMID on x86 or combined CLOSID, RMID on Arm. * @mbm_over: worker to periodically read MBM h/w counters * @cqm_limbo: worker to periodically read CQM h/w counters * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters + * @cntr_cfg: array of assignable counters' configuration (indexed + * by counter ID) */ struct rdt_mon_domain { struct rdt_domain_hdr hdr; unsigned int ci_id; unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; + struct mbm_state *mbm_states[QOS_NUM_L3_MBM_EVENTS]; struct delayed_work mbm_over; struct delayed_work cqm_limbo; int mbm_work_cpu; int cqm_work_cpu; + struct mbm_cntr_cfg *cntr_cfg; }; /** @@ -256,39 +271,52 @@ enum resctrl_schema_fmt { }; /** + * struct resctrl_mon - Monitoring related data of a resctrl resource. + * @num_rmid: Number of RMIDs available. + * @mbm_cfg_mask: Memory transactions that can be tracked when bandwidth + * monitoring events can be configured. + * @num_mbm_cntrs: Number of assignable counters. + * @mbm_cntr_assignable:Is system capable of supporting counter assignment? + * @mbm_assign_on_mkdir:True if counters should automatically be assigned to MBM + * events of monitor groups created via mkdir. + */ +struct resctrl_mon { + int num_rmid; + unsigned int mbm_cfg_mask; + int num_mbm_cntrs; + bool mbm_cntr_assignable; + bool mbm_assign_on_mkdir; +}; + +/** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine - * @num_rmid: Number of RMIDs available * @ctrl_scope: Scope of this resource for control functions * @mon_scope: Scope of this resource for monitor functions * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. + * @mon: Monitoring related data. * @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. * @schema_fmt: Which format string and parser is used for this schema. - * @evt_list: List of monitoring events - * @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 { int rid; bool alloc_capable; bool mon_capable; - int num_rmid; enum resctrl_scope ctrl_scope; enum resctrl_scope mon_scope; struct resctrl_cache cache; struct resctrl_membw membw; + struct resctrl_mon mon; struct list_head ctrl_domains; struct list_head mon_domains; char *name; enum resctrl_schema_fmt schema_fmt; - struct list_head evt_list; - unsigned int mbm_cfg_mask; bool cdp_capable; }; @@ -372,8 +400,29 @@ 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); +void resctrl_enable_mon_event(enum resctrl_event_id eventid); + +bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); + bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); +static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid) +{ + return (eventid >= QOS_L3_MBM_TOTAL_EVENT_ID && + eventid <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id eventid); + +/* Iterate over all memory bandwidth events */ +#define for_each_mbm_event_id(eventid) \ + for (eventid = QOS_L3_MBM_TOTAL_EVENT_ID; \ + eventid <= QOS_L3_MBM_LOCAL_EVENT_ID; eventid++) + +/* Iterate over memory bandwidth arrays in domain structures */ +#define for_each_mbm_idx(idx) \ + for (idx = 0; idx < QOS_NUM_L3_MBM_EVENTS; idx++) + /** * resctrl_arch_mon_event_config_write() - Write the config for an event. * @config_info: struct resctrl_mon_config_info describing the resource, domain @@ -416,6 +465,26 @@ static inline u32 resctrl_get_config_index(u32 closid, bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l); int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); +/** + * resctrl_arch_mbm_cntr_assign_enabled() - Check if MBM counter assignment + * mode is enabled. + * @r: Pointer to the resource structure. + * + * Return: + * true if the assignment mode is enabled, false otherwise. + */ +bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r); + +/** + * resctrl_arch_mbm_cntr_assign_set() - Configure the MBM counter assignment mode. + * @r: Pointer to the resource structure. + * @enable: Set to true to enable, false to disable the assignment mode. + * + * Return: + * 0 on success, < 0 on error. + */ +int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable); + /* * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. @@ -528,6 +597,63 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain * */ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r); +/** + * resctrl_arch_config_cntr() - Configure the counter with its new RMID + * and event details. + * @r: Resource structure. + * @d: The domain in which counter with ID @cntr_id should be configured. + * @evtid: Monitoring event type (e.g., QOS_L3_MBM_TOTAL_EVENT_ID + * or QOS_L3_MBM_LOCAL_EVENT_ID). + * @rmid: RMID. + * @closid: CLOSID. + * @cntr_id: Counter ID to configure. + * @assign: True to assign the counter or update an existing assignment, + * false to unassign the counter. + * + * This can be called from any CPU. + */ +void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, + enum resctrl_event_id evtid, u32 rmid, u32 closid, + u32 cntr_id, bool assign); + +/** + * resctrl_arch_cntr_read() - Read the event data corresponding to the counter ID + * assigned to the RMID, event pair for this resource + * and domain. + * @r: Resource that the counter should be read from. + * @d: Domain that the counter should be read from. + * @closid: CLOSID that matches the RMID. + * @rmid: The RMID to which @cntr_id is assigned. + * @cntr_id: The counter to read. + * @eventid: The MBM event to which @cntr_id is assigned. + * @val: Result of the counter read in bytes. + * + * Called on a CPU that belongs to domain @d when "mbm_event" mode is enabled. + * Called from a non-migrateable process context via smp_call_on_cpu() unless all + * CPUs are nohz_full, in which case it is called via IPI (smp_call_function_any()). + * + * Return: + * 0 on success, or -EIO, -EINVAL etc on error. + */ +int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid, int cntr_id, + enum resctrl_event_id eventid, u64 *val); + +/** + * resctrl_arch_reset_cntr() - Reset any private state associated with counter ID. + * @r: The domain's resource. + * @d: The counter ID's domain. + * @closid: CLOSID that matches the RMID. + * @rmid: The RMID to which @cntr_id is assigned. + * @cntr_id: The counter to reset. + * @eventid: The MBM event to which @cntr_id is assigned. + * + * This can be called from any CPU. + */ +void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid, int cntr_id, + enum resctrl_event_id eventid); + extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h index a25fb9c4070d..acfe07860b34 100644 --- a/include/linux/resctrl_types.h +++ b/include/linux/resctrl_types.h @@ -34,11 +34,18 @@ /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS GENMASK(6, 0) -/* - * Event IDs, the values match those used to program IA32_QM_EVTSEL before - * reading IA32_QM_CTR on RDT systems. - */ +/* Number of memory transactions that an MBM event can be configured with */ +#define NUM_MBM_TRANSACTIONS 7 + +/* Event IDs */ enum resctrl_event_id { + /* Must match value of first event below */ + QOS_FIRST_EVENT = 0x01, + + /* + * These values match those used to program IA32_QM_EVTSEL before + * reading IA32_QM_CTR on RDT systems. + */ QOS_L3_OCCUP_EVENT_ID = 0x01, QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, @@ -47,4 +54,7 @@ enum resctrl_event_id { QOS_NUM_EVENTS, }; +#define QOS_NUM_L3_MBM_EVENTS (QOS_L3_MBM_LOCAL_EVENT_ID - QOS_L3_MBM_TOTAL_EVENT_ID + 1) +#define MBM_STATE_IDX(evt) ((evt) - QOS_L3_MBM_TOTAL_EVENT_ID) + #endif /* __LINUX_RESCTRL_TYPES_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 6cd020eea37a..daa92a58585d 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -394,18 +394,8 @@ typedef int __bitwise rmap_t; /* The anonymous (sub)page is exclusive to a single process. */ #define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) -/* - * Internally, we're using an enum to specify the granularity. We make the - * compiler emit specialized code for each granularity. - */ -enum rmap_level { - RMAP_LEVEL_PTE = 0, - RMAP_LEVEL_PMD, - RMAP_LEVEL_PUD, -}; - -static inline void __folio_rmap_sanity_checks(const struct folio *folio, - const struct page *page, int nr_pages, enum rmap_level level) +static __always_inline void __folio_rmap_sanity_checks(const struct folio *folio, + const struct page *page, int nr_pages, enum pgtable_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); @@ -427,18 +417,18 @@ static inline void __folio_rmap_sanity_checks(const struct folio *folio, VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio); switch (level) { - case RMAP_LEVEL_PTE: + case PGTABLE_LEVEL_PTE: break; - case RMAP_LEVEL_PMD: + case PGTABLE_LEVEL_PMD: /* * We don't support folios larger than a single PMD yet. So - * when RMAP_LEVEL_PMD is set, we assume that we are creating + * when PGTABLE_LEVEL_PMD is set, we assume that we are creating * a single "entire" mapping of the folio. */ VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio); VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio); break; - case RMAP_LEVEL_PUD: + case PGTABLE_LEVEL_PUD: /* * Assume that we are creating a single "entire" mapping of the * folio. @@ -447,7 +437,7 @@ static inline void __folio_rmap_sanity_checks(const struct folio *folio, VM_WARN_ON_FOLIO(nr_pages != HPAGE_PUD_NR, folio); break; default: - VM_WARN_ON_ONCE(true); + BUILD_BUG(); } /* @@ -567,14 +557,14 @@ static inline void hugetlb_remove_rmap(struct folio *folio) static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *dst_vma, - enum rmap_level level) + enum pgtable_level level) { const int orig_nr_pages = nr_pages; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { - case RMAP_LEVEL_PTE: + case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { atomic_inc(&folio->_mapcount); break; @@ -587,11 +577,13 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio, } folio_add_large_mapcount(folio, orig_nr_pages, dst_vma); break; - case RMAP_LEVEL_PMD: - case RMAP_LEVEL_PUD: + case PGTABLE_LEVEL_PMD: + case PGTABLE_LEVEL_PUD: atomic_inc(&folio->_entire_mapcount); folio_inc_large_mapcount(folio, dst_vma); break; + default: + BUILD_BUG(); } } @@ -609,13 +601,13 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio, static inline void folio_dup_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *dst_vma) { - __folio_dup_file_rmap(folio, page, nr_pages, dst_vma, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, nr_pages, dst_vma, PGTABLE_LEVEL_PTE); } static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, struct page *page, struct vm_area_struct *dst_vma) { - __folio_dup_file_rmap(folio, page, 1, dst_vma, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, 1, dst_vma, PGTABLE_LEVEL_PTE); } /** @@ -632,7 +624,7 @@ static inline void folio_dup_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *dst_vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, dst_vma, RMAP_LEVEL_PTE); + __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, dst_vma, PGTABLE_LEVEL_PTE); #else WARN_ON_ONCE(true); #endif @@ -640,7 +632,7 @@ static inline void folio_dup_file_rmap_pmd(struct folio *folio, static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *dst_vma, - struct vm_area_struct *src_vma, enum rmap_level level) + struct vm_area_struct *src_vma, enum pgtable_level level) { const int orig_nr_pages = nr_pages; bool maybe_pinned; @@ -665,7 +657,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, * copying if the folio maybe pinned. */ switch (level) { - case RMAP_LEVEL_PTE: + case PGTABLE_LEVEL_PTE: if (unlikely(maybe_pinned)) { for (i = 0; i < nr_pages; i++) if (PageAnonExclusive(page + i)) @@ -687,8 +679,8 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, } while (page++, --nr_pages > 0); folio_add_large_mapcount(folio, orig_nr_pages, dst_vma); break; - case RMAP_LEVEL_PMD: - case RMAP_LEVEL_PUD: + case PGTABLE_LEVEL_PMD: + case PGTABLE_LEVEL_PUD: if (PageAnonExclusive(page)) { if (unlikely(maybe_pinned)) return -EBUSY; @@ -697,6 +689,8 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, atomic_inc(&folio->_entire_mapcount); folio_inc_large_mapcount(folio, dst_vma); break; + default: + BUILD_BUG(); } return 0; } @@ -730,7 +724,7 @@ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, nr_pages, dst_vma, - src_vma, RMAP_LEVEL_PTE); + src_vma, PGTABLE_LEVEL_PTE); } static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, @@ -738,7 +732,7 @@ static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, 1, dst_vma, src_vma, - RMAP_LEVEL_PTE); + PGTABLE_LEVEL_PTE); } /** @@ -770,7 +764,7 @@ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, dst_vma, - src_vma, RMAP_LEVEL_PMD); + src_vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; @@ -778,7 +772,7 @@ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, } static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, - struct page *page, int nr_pages, enum rmap_level level) + struct page *page, int nr_pages, enum pgtable_level level) { VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio); @@ -873,7 +867,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, static inline int folio_try_share_anon_rmap_pte(struct folio *folio, struct page *page) { - return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE); + return __folio_try_share_anon_rmap(folio, page, 1, PGTABLE_LEVEL_PTE); } /** @@ -904,7 +898,7 @@ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio, { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR, - RMAP_LEVEL_PMD); + PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; @@ -928,6 +922,11 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, /* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) +/* Result flags */ + +/* The page is mapped across page table boundary */ +#define PVMW_PGTABLE_CROSSED (1 << 16) + struct page_vma_mapped_walk { unsigned long pfn; unsigned long nr_pages; diff --git a/include/linux/rseq.h b/include/linux/rseq.h index bc8af3eb5598..69553e7c14c1 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -7,6 +7,12 @@ #include <linux/preempt.h> #include <linux/sched.h> +#ifdef CONFIG_MEMBARRIER +# define RSEQ_EVENT_GUARD irq +#else +# define RSEQ_EVENT_GUARD preempt +#endif + /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. @@ -41,9 +47,8 @@ static inline void rseq_handle_notify_resume(struct ksignal *ksig, static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - preempt_disable(); - __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); - preempt_enable(); + scoped_guard(RSEQ_EVENT_GUARD) + __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); rseq_handle_notify_resume(ksig, regs); } @@ -65,7 +70,7 @@ static inline void rseq_migrate(struct task_struct *t) * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; @@ -107,7 +112,7 @@ static inline void rseq_preempt(struct task_struct *t) static inline void rseq_migrate(struct task_struct *t) { } -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { } static inline void rseq_execve(struct task_struct *t) diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index fa9f1021541e..ede4c6bf6f22 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -44,6 +44,16 @@ static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock) return READ_ONCE(lock->owner) != NULL; } +#ifdef CONFIG_RT_MUTEXES +#define RT_MUTEX_HAS_WAITERS 1UL + +static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock) +{ + unsigned long owner = (unsigned long) READ_ONCE(lock->owner); + + return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS); +} +#endif extern void rt_mutex_base_init(struct rt_mutex_base *rtb); /** diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h index f267a06c6b1e..276b509c03e3 100644 --- a/include/linux/rtsx_usb.h +++ b/include/linux/rtsx_usb.h @@ -99,6 +99,17 @@ extern int rtsx_usb_card_exclusive_check(struct rtsx_ucr *ucr, int card); #define CD_MASK (SD_CD | MS_CD | XD_CD) #define SD_WP 0x08 +/* OCPCTL */ +#define MS_OCP_DETECT_EN 0x08 +#define MS_OCP_INT_EN 0x04 +#define MS_OCP_INT_CLR 0x02 +#define MS_OCP_CLEAR 0x01 + +/* OCPSTAT */ +#define MS_OCP_DETECT 0x80 +#define MS_OCP_NOW 0x02 +#define MS_OCP_EVER 0x01 + /* reader command field offset & parameters */ #define READ_REG_CMD 0 #define WRITE_REG_CMD 1 diff --git a/include/linux/rv.h b/include/linux/rv.h index 14410a42faef..9520aab34bcb 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -7,16 +7,14 @@ #ifndef _LINUX_RV_H #define _LINUX_RV_H -#include <linux/types.h> -#include <linux/list.h> - #define MAX_DA_NAME_LEN 32 #define MAX_DA_RETRY_RACING_EVENTS 3 #ifdef CONFIG_RV +#include <linux/array_size.h> #include <linux/bitops.h> +#include <linux/list.h> #include <linux/types.h> -#include <linux/array_size.h> /* * Deterministic automaton per-object variables. diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h index 309ca72f2dfb..adcc43042c90 100644 --- a/include/linux/rw_hint.h +++ b/include/linux/rw_hint.h @@ -14,6 +14,7 @@ enum rw_hint { WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, + WRITE_LIFE_HINT_NR, } __packed; /* Sparse ignores __packed annotations on enums, hence the #ifndef below. */ diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 6f8a4965f9b9..29f6ceb98d74 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -158,6 +158,7 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) static inline void sg_set_page(struct scatterlist *sg, struct page *page, unsigned int len, unsigned int offset) { + VM_WARN_ON_ONCE(!page_range_contiguous(page, ALIGN(len + offset, PAGE_SIZE) / PAGE_SIZE)); sg_assign_page(sg, page); sg->offset = offset; sg->length = len; @@ -600,7 +601,7 @@ void __sg_page_iter_start(struct sg_page_iter *piter, */ static inline struct page *sg_page_iter_page(struct sg_page_iter *piter) { - return nth_page(sg_page(piter->sg), piter->sg_pgoffset); + return sg_page(piter->sg) + piter->sg_pgoffset; } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index f8188b833350..cbb7340c5866 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -49,6 +49,9 @@ #include <linux/tracepoint-defs.h> #include <linux/unwind_deferred_types.h> #include <asm/kmap_size.h> +#ifndef COMPILE_OFFSETS +#include <generated/rq-offsets.h> +#endif /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -706,7 +709,6 @@ struct sched_dl_entity { unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; - unsigned int dl_server_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -733,7 +735,6 @@ struct sched_dl_entity { * runnable task. */ struct rq *rq; - dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES @@ -883,6 +884,11 @@ struct task_struct { #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; +#ifdef CONFIG_CFS_BANDWIDTH + struct callback_head sched_throttle_work; + struct list_head throttle_node; + bool throttled; +#endif #endif @@ -2312,4 +2318,114 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #define alloc_tag_restore(_tag, _old) do {} while (0) #endif +#ifndef MODULE +#ifndef COMPILE_OFFSETS + +extern void ___migrate_enable(void); + +struct rq; +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +/* + * The "struct rq" is not available here, so we can't access the + * "runqueues" with this_cpu_ptr(), as the compilation will fail in + * this_cpu_ptr() -> raw_cpu_ptr() -> __verify_pcpu_ptr(): + * typeof((ptr) + 0) + * + * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here. + */ +#ifdef CONFIG_SMP +#define this_rq_raw() arch_raw_cpu_ptr(&runqueues) +#else +#define this_rq_raw() PERCPU_PTR(&runqueues) +#endif +#define this_rq_pinned() (*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned)) + +static inline void __migrate_enable(void) +{ + struct task_struct *p = current; + +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Check both overflow from migrate_disable() and superfluous + * migrate_enable(). + */ + if (WARN_ON_ONCE((s16)p->migration_disabled <= 0)) + return; +#endif + + if (p->migration_disabled > 1) { + p->migration_disabled--; + return; + } + + /* + * Ensure stop_task runs either before or after this, and that + * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). + */ + guard(preempt)(); + if (unlikely(p->cpus_ptr != &p->cpus_mask)) + ___migrate_enable(); + /* + * Mustn't clear migration_disabled() until cpus_ptr points back at the + * regular cpus_mask, otherwise things that race (eg. + * select_fallback_rq) get confused. + */ + barrier(); + p->migration_disabled = 0; + this_rq_pinned()--; +} + +static inline void __migrate_disable(void) +{ + struct task_struct *p = current; + + if (p->migration_disabled) { +#ifdef CONFIG_DEBUG_PREEMPT + /* + *Warn about overflow half-way through the range. + */ + WARN_ON_ONCE((s16)p->migration_disabled < 0); +#endif + p->migration_disabled++; + return; + } + + guard(preempt)(); + this_rq_pinned()++; + p->migration_disabled = 1; +} +#else /* !COMPILE_OFFSETS */ +static inline void __migrate_disable(void) { } +static inline void __migrate_enable(void) { } +#endif /* !COMPILE_OFFSETS */ + +/* + * So that it is possible to not export the runqueues variable, define and + * export migrate_enable/migrate_disable in kernel/sched/core.c too, and use + * them for the modules. The macro "INSTANTIATE_EXPORTED_MIGRATE_DISABLE" will + * be defined in kernel/sched/core.c. + */ +#ifndef INSTANTIATE_EXPORTED_MIGRATE_DISABLE +static inline void migrate_disable(void) +{ + __migrate_disable(); +} + +static inline void migrate_enable(void) +{ + __migrate_enable(); +} +#else /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ +extern void migrate_disable(void); +extern void migrate_enable(void); +#endif /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ + +#else /* MODULE */ +extern void migrate_disable(void); +extern void migrate_enable(void); +#endif /* MODULE */ + +DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) + #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 6eb65ceed213..b7fafe999073 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,6 +8,20 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ +static inline unsigned long __mm_flags_get_dumpable(struct mm_struct *mm) +{ + /* + * By convention, dumpable bits are contained in first 32 bits of the + * bitmap, so we can simply access this first unsigned long directly. + */ + return __mm_flags_get_word(mm); +} + +static inline void __mm_flags_set_mask_dumpable(struct mm_struct *mm, int value) +{ + __mm_flags_set_mask_bits_word(mm, MMF_DUMPABLE_MASK, value); +} + extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things @@ -22,7 +36,9 @@ static inline int __get_dumpable(unsigned long mm_flags) static inline int get_dumpable(struct mm_struct *mm) { - return __get_dumpable(mm->flags); + unsigned long flags = __mm_flags_get_dumpable(mm); + + return __get_dumpable(flags); } #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 7047101dbf58..d82b7a9b0658 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -108,7 +108,11 @@ enum scx_kf_mask { SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ - /* ops.dequeue (in REST) may be nested inside DISPATCH */ + /* + * ops.dispatch() may release rq lock temporarily and thus ENQUEUE and + * SELECT_CPU may be nested inside. ops.dequeue (in REST) may also be + * nested inside DISPATCH. + */ SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2201da0afecc..0232d983b715 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -178,7 +178,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, - struct rlimit *rlim_stack); + const struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, @@ -211,7 +211,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, - struct rlimit *rlim_stack) {} + const struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 1ef1edbaaf79..7d6449982822 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -226,6 +226,10 @@ struct signal_struct { struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + struct rw_semaphore cgroup_threadgroup_rwsem; +#endif + /* * Thread is the potential origin of an oom condition; kill first on * oom diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ea41795a352b..525aa2a632b2 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,7 +63,7 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern int sched_fork(u64 clone_flags, struct task_struct *p); extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); @@ -210,9 +210,8 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * - * Nests both inside and outside of read_lock(&tasklist_lock). - * It must not be nested with write_lock_irq(&tasklist_lock), - * neither inside nor outside. + * Nests inside of read_lock(&tasklist_lock). It must not be nested with + * write_lock_irq(&tasklist_lock), neither inside nor outside. */ static inline void task_lock(struct task_struct *p) { diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 5263746b63e8..bbcfdf12aa6e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -30,33 +30,24 @@ struct sd_flag_debug { }; extern const struct sd_flag_debug sd_flag_debug[]; +struct sched_domain_topology_level; + #ifdef CONFIG_SCHED_SMT -static inline int cpu_smt_flags(void) -{ - return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC; -} +extern int cpu_smt_flags(void); +extern const struct cpumask *tl_smt_mask(struct sched_domain_topology_level *tl, int cpu); #endif #ifdef CONFIG_SCHED_CLUSTER -static inline int cpu_cluster_flags(void) -{ - return SD_CLUSTER | SD_SHARE_LLC; -} +extern int cpu_cluster_flags(void); +extern const struct cpumask *tl_cls_mask(struct sched_domain_topology_level *tl, int cpu); #endif #ifdef CONFIG_SCHED_MC -static inline int cpu_core_flags(void) -{ - return SD_SHARE_LLC; -} +extern int cpu_core_flags(void); +extern const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu); #endif -#ifdef CONFIG_NUMA -static inline int cpu_numa_flags(void) -{ - return SD_NUMA; -} -#endif +extern const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu); extern int arch_asym_cpu_priority(int cpu); @@ -172,7 +163,7 @@ bool cpus_equal_capacity(int this_cpu, int that_cpu); bool cpus_share_cache(int this_cpu, int that_cpu); bool cpus_share_resources(int this_cpu, int that_cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(struct sched_domain_topology_level *tl, int cpu); typedef int (*sched_domain_flags_f)(void); struct sd_data { diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 688466a0e816..aafaac1496b0 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -153,7 +153,7 @@ struct scmi_perf_domain_info { * for a given device * @fast_switch_rate_limit: gets the minimum time (us) required between * successive fast_switching requests - * @power_scale_mw_get: indicates if the power values provided are in milliWatts + * @power_scale_get: indicates if the power values provided are in milliWatts * or in some other (abstract) scale */ struct scmi_perf_proto_ops { diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 923d68e07679..1690706206e8 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -12,6 +12,7 @@ #define SCREEN_INFO_MAX_RESOURCES 3 struct pci_dev; +struct pixel_format; struct resource; static inline bool __screen_info_has_lfb(unsigned int type) @@ -136,6 +137,7 @@ static inline u32 __screen_info_vesapm_info_base(const struct screen_info *si) ssize_t screen_info_resources(const struct screen_info *si, struct resource *r, size_t num); u32 __screen_info_lfb_bits_per_pixel(const struct screen_info *si); +int screen_info_pixel_format(const struct screen_info *si, struct pixel_format *f); #if defined(CONFIG_PCI) void screen_info_apply_fixups(void); diff --git a/include/linux/security.h b/include/linux/security.h index 521bcb5b9717..bd33f194c94a 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -489,7 +489,7 @@ int security_file_receive(struct file *file); int security_file_open(struct file *file); int security_file_post_open(struct file *file, int mask); int security_file_truncate(struct file *file); -int security_task_alloc(struct task_struct *task, unsigned long clone_flags); +int security_task_alloc(struct task_struct *task, u64 clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); void security_cred_free(struct cred *cred); @@ -567,7 +567,8 @@ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, int security_setprocattr(int lsmid, const char *name, void *value, size_t size); int security_ismaclabel(const char *name); int security_secid_to_secctx(u32 secid, struct lsm_context *cp); -int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp); +int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp, + int lsmid); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); void security_release_secctx(struct lsm_context *cp); void security_inode_invalidate_secctx(struct inode *inode); @@ -1215,7 +1216,7 @@ static inline int security_file_truncate(struct file *file) } static inline int security_task_alloc(struct task_struct *task, - unsigned long clone_flags) + u64 clone_flags) { return 0; } @@ -1551,7 +1552,8 @@ static inline int security_secid_to_secctx(u32 secid, struct lsm_context *cp) } static inline int security_lsmprop_to_secctx(struct lsm_prop *prop, - struct lsm_context *cp) + struct lsm_context *cp, + int lsmid) { return -EOPNOTSUPP; } diff --git a/include/linux/sem.h b/include/linux/sem.h index c4deefe42aeb..275269ce2ec8 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -9,12 +9,12 @@ struct task_struct; #ifdef CONFIG_SYSVIPC -extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk); +extern int copy_semundo(u64 clone_flags, struct task_struct *tsk); extern void exit_sem(struct task_struct *tsk); #else -static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) +static inline int copy_semundo(u64 clone_flags, struct task_struct *tsk) { return 0; } diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 60c65cea74f6..5c71945a5e4d 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -522,6 +522,28 @@ struct ethtool_modinfo; struct sfp_bus; /** + * struct sfp_module_caps - sfp module capabilities + * @interfaces: bitmap of interfaces that the module may support + * @link_modes: bitmap of ethtool link modes that the module may support + */ +struct sfp_module_caps { + DECLARE_PHY_INTERFACE_MASK(interfaces); + __ETHTOOL_DECLARE_LINK_MODE_MASK(link_modes); + /** + * @may_have_phy: indicate whether the module may have an ethernet PHY + * There is no way to be sure that a module has a PHY as the EEPROM + * doesn't contain this information. When set, this does not mean that + * the module definitely has a PHY. + */ + bool may_have_phy; + /** + * @port: one of ethtool %PORT_* definitions, parsed from the module + * EEPROM, or %PORT_OTHER if the port type is not known. + */ + u8 port; +}; + +/** * struct sfp_upstream_ops - upstream operations structure * @attach: called when the sfp socket driver is bound to the upstream * (mandatory). @@ -554,11 +576,7 @@ struct sfp_upstream_ops { }; #if IS_ENABLED(CONFIG_SFP) -int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support); -bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); -void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support, unsigned long *interfaces); +const struct sfp_module_caps *sfp_get_module_caps(struct sfp_bus *bus); phy_interface_t sfp_select_interface(struct sfp_bus *bus, const unsigned long *link_modes); @@ -578,24 +596,10 @@ int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, void sfp_bus_del_upstream(struct sfp_bus *bus); const char *sfp_get_name(struct sfp_bus *bus); #else -static inline int sfp_parse_port(struct sfp_bus *bus, - const struct sfp_eeprom_id *id, - unsigned long *support) -{ - return PORT_OTHER; -} - -static inline bool sfp_may_have_phy(struct sfp_bus *bus, - const struct sfp_eeprom_id *id) -{ - return false; -} - -static inline void sfp_parse_support(struct sfp_bus *bus, - const struct sfp_eeprom_id *id, - unsigned long *support, - unsigned long *interfaces) +static inline const struct sfp_module_caps * +sfp_get_module_caps(struct sfp_bus *bus) { + return NULL; } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 6d0f9c599ff7..0e47465ef0fd 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -99,9 +99,9 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM -bool shmem_mapping(struct address_space *mapping); +bool shmem_mapping(const struct address_space *mapping); #else -static inline bool shmem_mapping(struct address_space *mapping) +static inline bool shmem_mapping(const struct address_space *mapping) { return false; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 14b923ddb6df..fb3fec9affaa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -674,7 +674,7 @@ enum { /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 3, + __SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, @@ -707,6 +707,12 @@ enum { SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, + + /* These indirectly map onto the same netdev feature. + * If NETIF_F_TSO_MANGLEID is set it may mangle both inner and outer IDs. + */ + SKB_GSO_TCP_FIXEDID = 1 << 30, + SKB_GSO_TCP_FIXEDID_INNER = 1 << 31, }; #if BITS_PER_LONG > 32 @@ -1159,6 +1165,45 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } +static inline void skb_dst_check_unset(struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE((skb->_skb_refdst & SKB_DST_PTRMASK) && + !(skb->_skb_refdst & SKB_DST_NOREF)); +} + +/** + * skb_dstref_steal() - return current dst_entry value and clear it + * @skb: buffer + * + * Resets skb dst_entry without adjusting its reference count. Useful in + * cases where dst_entry needs to be temporarily reset and restored. + * Note that the returned value cannot be used directly because it + * might contain SKB_DST_NOREF bit. + * + * When in doubt, prefer skb_dst_drop() over skb_dstref_steal() to correctly + * handle dst_entry reference counting. + * + * Returns: original skb dst_entry. + */ +static inline unsigned long skb_dstref_steal(struct sk_buff *skb) +{ + unsigned long refdst = skb->_skb_refdst; + + skb->_skb_refdst = 0; + return refdst; +} + +/** + * skb_dstref_restore() - restore skb dst_entry removed via skb_dstref_steal() + * @skb: buffer + * @refdst: dst entry from a call to skb_dstref_steal() + */ +static inline void skb_dstref_restore(struct sk_buff *skb, unsigned long refdst) +{ + skb_dst_check_unset(skb); + skb->_skb_refdst = refdst; +} + /** * skb_dst_set - sets skb dst * @skb: buffer @@ -1169,6 +1214,7 @@ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { + skb_dst_check_unset(skb); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } @@ -1185,6 +1231,7 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { + skb_dst_check_unset(skb); WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; @@ -4172,6 +4219,8 @@ int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); +int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, + struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); @@ -4859,6 +4908,9 @@ enum skb_ext_id { #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif +#if IS_ENABLED(CONFIG_INET_PSP) + SKB_EXT_PSP, +#endif SKB_EXT_NUM, /* must be last */ }; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 0b9095a281b8..49847888c287 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -315,7 +315,7 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, static inline void sock_drop(struct sock *sk, struct sk_buff *skb) { - sk_drops_add(sk, skb); + sk_drops_skbadd(sk, skb); kfree_skb(skb); } diff --git a/include/linux/slab.h b/include/linux/slab.h index d5a8ab98035c..cf443f064a66 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -335,6 +335,37 @@ struct kmem_cache_args { * %NULL means no constructor. */ void (*ctor)(void *); + /** + * @sheaf_capacity: Enable sheaves of given capacity for the cache. + * + * With a non-zero value, allocations from the cache go through caching + * arrays called sheaves. Each cpu has a main sheaf that's always + * present, and a spare sheaf that may be not present. When both become + * empty, there's an attempt to replace an empty sheaf with a full sheaf + * from the per-node barn. + * + * When no full sheaf is available, and gfp flags allow blocking, a + * sheaf is allocated and filled from slab(s) using bulk allocation. + * Otherwise the allocation falls back to the normal operation + * allocating a single object from a slab. + * + * Analogically when freeing and both percpu sheaves are full, the barn + * may replace it with an empty sheaf, unless it's over capacity. In + * that case a sheaf is bulk freed to slab pages. + * + * The sheaves do not enforce NUMA placement of objects, so allocations + * via kmem_cache_alloc_node() with a node specified other than + * NUMA_NO_NODE will bypass them. + * + * Bulk allocation and free operations also try to use the cpu sheaves + * and barn, but fallback to using slab pages directly. + * + * When slub_debug is enabled for the cache, the sheaf_capacity argument + * is ignored. + * + * %0 means no sheaves will be created. + */ + unsigned int sheaf_capacity; }; struct kmem_cache *__kmem_cache_create_args(const char *name, @@ -465,11 +496,16 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc_noprof(const void *objp, size_t new_size, - gfp_t flags) __realloc_size(2); -#define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) +void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size, + unsigned long align, + gfp_t flags, int nid) __realloc_size(2); +#define krealloc_noprof(_o, _s, _f) krealloc_node_align_noprof(_o, _s, 1, _f, NUMA_NO_NODE) +#define krealloc_node_align(...) alloc_hooks(krealloc_node_align_noprof(__VA_ARGS__)) +#define krealloc_node(_o, _s, _f, _n) krealloc_node_align(_o, _s, 1, _f, _n) +#define krealloc(...) krealloc_node(__VA_ARGS__, NUMA_NO_NODE) void kfree(const void *objp); +void kfree_nolock(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -798,6 +834,22 @@ void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) +struct slab_sheaf * +kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size); + +int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp, + struct slab_sheaf **sheafp, unsigned int size); + +void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp, + struct slab_sheaf *sheaf); + +void *kmem_cache_alloc_from_sheaf_noprof(struct kmem_cache *cachep, gfp_t gfp, + struct slab_sheaf *sheaf) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_from_sheaf(...) \ + alloc_hooks(kmem_cache_alloc_from_sheaf_noprof(__VA_ARGS__)) + +unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf); + /* * These macros allow declaring a kmem_buckets * parameter alongside size, which * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call @@ -910,6 +962,9 @@ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t f } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) +void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); +#define kmalloc_nolock(...) alloc_hooks(kmalloc_nolock_noprof(__VA_ARGS__)) + #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) @@ -1041,18 +1096,20 @@ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) -void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1); -#define kvmalloc_node_noprof(size, flags, node) \ - __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node) -#define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) - -#define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) -#define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) +void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align, + gfp_t flags, int node) __alloc_size(1); +#define kvmalloc_node_align_noprof(_size, _align, _flags, _node) \ + __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node) +#define kvmalloc_node_align(...) \ + alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__)) +#define kvmalloc_node(_s, _f, _n) kvmalloc_node_align(_s, 1, _f, _n) +#define kvmalloc(...) kvmalloc_node(__VA_ARGS__, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) + #define kmem_buckets_valloc(_b, _size, _flags) \ - alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) + alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), 1, _flags, NUMA_NO_NODE)) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) @@ -1062,7 +1119,7 @@ kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc_node_noprof(bytes, flags, node); + return kvmalloc_node_align_noprof(bytes, 1, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) @@ -1073,9 +1130,12 @@ kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) -void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) - __realloc_size(2); -#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) +void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, + gfp_t flags, int nid) __realloc_size(2); +#define kvrealloc_node_align(...) \ + alloc_hooks(kvrealloc_node_align_noprof(__VA_ARGS__)) +#define kvrealloc_node(_p, _s, _f, _n) kvrealloc_node_align(_p, _s, 1, _f, _n) +#define kvrealloc(...) kvrealloc_node(__VA_ARGS__, NUMA_NO_NODE) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h new file mode 100644 index 000000000000..6f66eb339b3f --- /dev/null +++ b/include/linux/soc/airoha/airoha_offload.h @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 AIROHA Inc + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + */ +#ifndef AIROHA_OFFLOAD_H +#define AIROHA_OFFLOAD_H + +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +enum { + PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED = 0x0f, +}; + +struct airoha_ppe_dev { + struct { + int (*setup_tc_block_cb)(struct airoha_ppe_dev *dev, + void *type_data); + void (*check_skb)(struct airoha_ppe_dev *dev, + struct sk_buff *skb, u16 hash, + bool rx_wlan); + } ops; + + void *priv; +}; + +#if (IS_BUILTIN(CONFIG_NET_AIROHA) || IS_MODULE(CONFIG_NET_AIROHA)) +struct airoha_ppe_dev *airoha_ppe_get_dev(struct device *dev); +void airoha_ppe_put_dev(struct airoha_ppe_dev *dev); + +static inline int airoha_ppe_dev_setup_tc_block_cb(struct airoha_ppe_dev *dev, + void *type_data) +{ + return dev->ops.setup_tc_block_cb(dev, type_data); +} + +static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, + struct sk_buff *skb, + u16 hash, bool rx_wlan) +{ + dev->ops.check_skb(dev, skb, hash, rx_wlan); +} +#else +static inline struct airoha_ppe_dev *airoha_ppe_get_dev(struct device *dev) +{ + return NULL; +} + +static inline void airoha_ppe_put_dev(struct airoha_ppe_dev *dev) +{ +} + +static inline int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, + void *type_data) +{ + return -EOPNOTSUPP; +} + +static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, + struct sk_buff *skb, u16 hash, + bool rx_wlan) +{ +} +#endif + +#define NPU_NUM_CORES 8 +#define NPU_NUM_IRQ 6 +#define NPU_RX0_DESC_NUM 512 +#define NPU_RX1_DESC_NUM 512 + +/* CTRL */ +#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) +#define NPU_RX_DMA_DESC_DONE_MASK BIT(0) +/* INFO */ +#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 28) +#define NPU_RX_DMA_PKT_ID_MASK GENMASK(28, 26) +#define NPU_RX_DMA_SRC_PORT_MASK GENMASK(25, 21) +#define NPU_RX_DMA_CRSN_MASK GENMASK(20, 16) +#define NPU_RX_DMA_FOE_ID_MASK GENMASK(15, 0) +/* DATA */ +#define NPU_RX_DMA_SID_MASK GENMASK(31, 16) +#define NPU_RX_DMA_FRAG_TYPE_MASK GENMASK(15, 14) +#define NPU_RX_DMA_PRIORITY_MASK GENMASK(13, 10) +#define NPU_RX_DMA_RADIO_ID_MASK GENMASK(9, 6) +#define NPU_RX_DMA_VAP_ID_MASK GENMASK(5, 2) +#define NPU_RX_DMA_FRAME_TYPE_MASK GENMASK(1, 0) + +struct airoha_npu_rx_dma_desc { + u32 ctrl; + u32 info; + u32 data; + u32 addr; + u64 rsv; +} __packed; + +/* CTRL */ +#define NPU_TX_DMA_DESC_SCHED_MASK BIT(31) +#define NPU_TX_DMA_DESC_LEN_MASK GENMASK(30, 18) +#define NPU_TX_DMA_DESC_VEND_LEN_MASK GENMASK(17, 1) +#define NPU_TX_DMA_DESC_DONE_MASK BIT(0) + +#define NPU_TXWI_LEN 192 + +struct airoha_npu_tx_dma_desc { + u32 ctrl; + u32 addr; + u64 rsv; + u8 txwi[NPU_TXWI_LEN]; +} __packed; + +enum airoha_npu_wlan_set_cmd { + WLAN_FUNC_SET_WAIT_PCIE_ADDR, + WLAN_FUNC_SET_WAIT_DESC, + WLAN_FUNC_SET_WAIT_NPU_INIT_DONE, + WLAN_FUNC_SET_WAIT_TRAN_TO_CPU, + WLAN_FUNC_SET_WAIT_BA_WIN_SIZE, + WLAN_FUNC_SET_WAIT_DRIVER_MODEL, + WLAN_FUNC_SET_WAIT_DEL_STA, + WLAN_FUNC_SET_WAIT_DRAM_BA_NODE_ADDR, + WLAN_FUNC_SET_WAIT_PKT_BUF_ADDR, + WLAN_FUNC_SET_WAIT_IS_TEST_NOBA, + WLAN_FUNC_SET_WAIT_FLUSHONE_TIMEOUT, + WLAN_FUNC_SET_WAIT_FLUSHALL_TIMEOUT, + WLAN_FUNC_SET_WAIT_IS_FORCE_TO_CPU, + WLAN_FUNC_SET_WAIT_PCIE_STATE, + WLAN_FUNC_SET_WAIT_PCIE_PORT_TYPE, + WLAN_FUNC_SET_WAIT_ERROR_RETRY_TIMES, + WLAN_FUNC_SET_WAIT_BAR_INFO, + WLAN_FUNC_SET_WAIT_FAST_FLAG, + WLAN_FUNC_SET_WAIT_NPU_BAND0_ONCPU, + WLAN_FUNC_SET_WAIT_TX_RING_PCIE_ADDR, + WLAN_FUNC_SET_WAIT_TX_DESC_HW_BASE, + WLAN_FUNC_SET_WAIT_TX_BUF_SPACE_HW_BASE, + WLAN_FUNC_SET_WAIT_RX_RING_FOR_TXDONE_HW_BASE, + WLAN_FUNC_SET_WAIT_TX_PKT_BUF_ADDR, + WLAN_FUNC_SET_WAIT_INODE_TXRX_REG_ADDR, + WLAN_FUNC_SET_WAIT_INODE_DEBUG_FLAG, + WLAN_FUNC_SET_WAIT_INODE_HW_CFG_INFO, + WLAN_FUNC_SET_WAIT_INODE_STOP_ACTION, + WLAN_FUNC_SET_WAIT_INODE_PCIE_SWAP, + WLAN_FUNC_SET_WAIT_RATELIMIT_CTRL, + WLAN_FUNC_SET_WAIT_HWNAT_INIT, + WLAN_FUNC_SET_WAIT_ARHT_CHIP_INFO, + WLAN_FUNC_SET_WAIT_TX_BUF_CHECK_ADDR, + WLAN_FUNC_SET_WAIT_TOKEN_ID_SIZE, +}; + +enum airoha_npu_wlan_get_cmd { + WLAN_FUNC_GET_WAIT_NPU_INFO, + WLAN_FUNC_GET_WAIT_LAST_RATE, + WLAN_FUNC_GET_WAIT_COUNTER, + WLAN_FUNC_GET_WAIT_DBG_COUNTER, + WLAN_FUNC_GET_WAIT_RXDESC_BASE, + WLAN_FUNC_GET_WAIT_WCID_DBG_COUNTER, + WLAN_FUNC_GET_WAIT_DMA_ADDR, + WLAN_FUNC_GET_WAIT_RING_SIZE, + WLAN_FUNC_GET_WAIT_NPU_SUPPORT_MAP, + WLAN_FUNC_GET_WAIT_MDC_LOCK_ADDRESS, + WLAN_FUNC_GET_WAIT_NPU_VERSION, +}; + +struct airoha_npu { +#if (IS_BUILTIN(CONFIG_NET_AIROHA_NPU) || IS_MODULE(CONFIG_NET_AIROHA_NPU)) + struct device *dev; + struct regmap *regmap; + + struct airoha_npu_core { + struct airoha_npu *npu; + /* protect concurrent npu memory accesses */ + spinlock_t lock; + struct work_struct wdt_work; + } cores[NPU_NUM_CORES]; + + int irqs[NPU_NUM_IRQ]; + + struct airoha_foe_stats __iomem *stats; + + struct { + int (*ppe_init)(struct airoha_npu *npu); + int (*ppe_deinit)(struct airoha_npu *npu); + int (*ppe_init_stats)(struct airoha_npu *npu, + dma_addr_t addr, u32 num_stats_entries); + int (*ppe_flush_sram_entries)(struct airoha_npu *npu, + dma_addr_t foe_addr, + int sram_num_entries); + int (*ppe_foe_commit_entry)(struct airoha_npu *npu, + dma_addr_t foe_addr, + u32 entry_size, u32 hash, + bool ppe2); + int (*wlan_init_reserved_memory)(struct airoha_npu *npu); + int (*wlan_send_msg)(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_set_cmd func_id, + void *data, int data_len, gfp_t gfp); + int (*wlan_get_msg)(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd func_id, + void *data, int data_len, gfp_t gfp); + u32 (*wlan_get_queue_addr)(struct airoha_npu *npu, int qid, + bool xmit); + void (*wlan_set_irq_status)(struct airoha_npu *npu, u32 val); + u32 (*wlan_get_irq_status)(struct airoha_npu *npu, int q); + void (*wlan_enable_irq)(struct airoha_npu *npu, int q); + void (*wlan_disable_irq)(struct airoha_npu *npu, int q); + } ops; +#endif +}; + +#if (IS_BUILTIN(CONFIG_NET_AIROHA_NPU) || IS_MODULE(CONFIG_NET_AIROHA_NPU)) +struct airoha_npu *airoha_npu_get(struct device *dev); +void airoha_npu_put(struct airoha_npu *npu); + +static inline int airoha_npu_wlan_init_reserved_memory(struct airoha_npu *npu) +{ + return npu->ops.wlan_init_reserved_memory(npu); +} + +static inline int airoha_npu_wlan_send_msg(struct airoha_npu *npu, + int ifindex, + enum airoha_npu_wlan_set_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return npu->ops.wlan_send_msg(npu, ifindex, cmd, data, data_len, gfp); +} + +static inline int airoha_npu_wlan_get_msg(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return npu->ops.wlan_get_msg(npu, ifindex, cmd, data, data_len, gfp); +} + +static inline u32 airoha_npu_wlan_get_queue_addr(struct airoha_npu *npu, + int qid, bool xmit) +{ + return npu->ops.wlan_get_queue_addr(npu, qid, xmit); +} + +static inline void airoha_npu_wlan_set_irq_status(struct airoha_npu *npu, + u32 val) +{ + npu->ops.wlan_set_irq_status(npu, val); +} + +static inline u32 airoha_npu_wlan_get_irq_status(struct airoha_npu *npu, int q) +{ + return npu->ops.wlan_get_irq_status(npu, q); +} + +static inline void airoha_npu_wlan_enable_irq(struct airoha_npu *npu, int q) +{ + npu->ops.wlan_enable_irq(npu, q); +} + +static inline void airoha_npu_wlan_disable_irq(struct airoha_npu *npu, int q) +{ + npu->ops.wlan_disable_irq(npu, q); +} +#else +static inline struct airoha_npu *airoha_npu_get(struct device *dev) +{ + return NULL; +} + +static inline void airoha_npu_put(struct airoha_npu *npu) +{ +} + +static inline int airoha_npu_wlan_init_reserved_memory(struct airoha_npu *npu) +{ + return -EOPNOTSUPP; +} + +static inline int airoha_npu_wlan_send_msg(struct airoha_npu *npu, + int ifindex, + enum airoha_npu_wlan_set_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return -EOPNOTSUPP; +} + +static inline int airoha_npu_wlan_get_msg(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return -EOPNOTSUPP; +} + +static inline u32 airoha_npu_wlan_get_queue_addr(struct airoha_npu *npu, + int qid, bool xmit) +{ + return 0; +} + +static inline void airoha_npu_wlan_set_irq_status(struct airoha_npu *npu, + u32 val) +{ +} + +static inline u32 airoha_npu_wlan_get_irq_status(struct airoha_npu *npu, + int q) +{ + return 0; +} + +static inline void airoha_npu_wlan_enable_irq(struct airoha_npu *npu, int q) +{ +} + +static inline void airoha_npu_wlan_disable_irq(struct airoha_npu *npu, int q) +{ +} +#endif + +#endif /* AIROHA_OFFLOAD_H */ diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index d8949a4ed0dc..c4ff6bab176d 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -147,7 +147,7 @@ struct mtk_wed_device { u32 wpdma_tx; u32 wpdma_txfree; u32 wpdma_rx_glo; - u32 wpdma_rx; + u32 wpdma_rx[MTK_WED_RX_QUEUES]; u32 wpdma_rx_rro[MTK_WED_RX_QUEUES]; u32 wpdma_rx_pg; diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 2996a3c28ef3..0a984e2579fe 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef _LINUX_QCOM_GENI_SE @@ -36,6 +37,7 @@ enum geni_se_protocol_type { GENI_SE_I2C, GENI_SE_I3C, GENI_SE_SPI_SLAVE, + GENI_SE_INVALID_PROTO = 255, }; struct geni_wrapper; @@ -531,5 +533,7 @@ void geni_icc_set_tag(struct geni_se *se, u32 tag); int geni_icc_enable(struct geni_se *se); int geni_icc_disable(struct geni_se *se); + +int geni_load_se_firmware(struct geni_se *se, enum geni_se_protocol_type protocol); #endif #endif diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index 9e8e60421192..8ea8230579a2 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -24,7 +24,7 @@ int qcom_mdt_load(struct device *dev, const struct firmware *fw, phys_addr_t *reloc_base); int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, - const char *fw_name, int pas_id, void *mem_region, + const char *fw_name, void *mem_region, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len, @@ -54,9 +54,8 @@ static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, static inline int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, - const char *fw_name, int pas_id, - void *mem_region, phys_addr_t mem_phys, - size_t mem_size, + const char *fw_name, void *mem_region, + phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base) { return -ENODEV; diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 0832776262ac..e6a3476bcef1 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -19,6 +19,7 @@ struct dentry; struct fwnode_handle; +struct device_node; struct sdw_bus; struct sdw_slave; @@ -1086,6 +1087,10 @@ int sdw_stream_add_slave(struct sdw_slave *slave, int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +struct device *of_sdw_find_device_by_node(struct device_node *np); + +int sdw_slave_get_current_bank(struct sdw_slave *sdev); + int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base); /* messaging and data APIs */ @@ -1119,6 +1124,18 @@ static inline int sdw_stream_remove_slave(struct sdw_slave *slave, return -EINVAL; } +static inline struct device *of_sdw_find_device_by_node(struct device_node *np) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return NULL; +} + +static inline int sdw_slave_get_current_bank(struct sdw_slave *sdev) +{ + WARN_ONCE(1, "SoundWire API is disabled"); + return -EINVAL; +} + /* messaging and data APIs */ static inline int sdw_read(struct sdw_slave *slave, u32 addr) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e9ea43234d9a..cb2c2df31089 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -21,7 +21,7 @@ #include <uapi/linux/spi/spi.h> /* Max no. of CS supported per spi device */ -#define SPI_CS_CNT_MAX 24 +#define SPI_DEVICE_CS_CNT_MAX 4 struct dma_chan; struct software_node; @@ -170,6 +170,7 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * two delays will be added up. * @chip_select: Array of physical chipselect, spi->chipselect[i] gives * the corresponding physical CS for logical CS i. + * @num_chipselect: Number of physical chipselects used. * @cs_index_mask: Bit mask of the active chipselect(s) in the chipselect array * @cs_gpiod: Array of GPIO descriptors of the corresponding chipselect lines * (optional, NULL when not using a GPIO line) @@ -228,7 +229,8 @@ struct spi_device { struct spi_delay cs_hold; struct spi_delay cs_inactive; - u8 chip_select[SPI_CS_CNT_MAX]; + u8 chip_select[SPI_DEVICE_CS_CNT_MAX]; + u8 num_chipselect; /* * Bit mask of the chipselect(s) that the driver need to use from @@ -236,9 +238,9 @@ struct spi_device { * multiple chip selects & memories are connected in parallel * then more than one bit need to be set in cs_index_mask. */ - u32 cs_index_mask : SPI_CS_CNT_MAX; + u32 cs_index_mask : SPI_DEVICE_CS_CNT_MAX; - struct gpio_desc *cs_gpiod[SPI_CS_CNT_MAX]; /* Chip select gpio desc */ + struct gpio_desc *cs_gpiod[SPI_DEVICE_CS_CNT_MAX]; /* Chip select gpio desc */ /* * Likely need more hooks for more protocol options affecting how @@ -315,7 +317,7 @@ static inline bool spi_is_csgpiod(struct spi_device *spi) { u8 idx; - for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { + for (idx = 0; idx < spi->num_chipselect; idx++) { if (spi_get_csgpiod(spi, idx)) return true; } @@ -719,8 +721,8 @@ struct spi_controller { bool auto_runtime_pm; bool fallback; bool last_cs_mode_high; - s8 last_cs[SPI_CS_CNT_MAX]; - u32 last_cs_index_mask : SPI_CS_CNT_MAX; + s8 last_cs[SPI_DEVICE_CS_CNT_MAX]; + u32 last_cs_index_mask : SPI_DEVICE_CS_CNT_MAX; struct completion xfer_completion; size_t max_dma_len; diff --git a/include/linux/stddef.h b/include/linux/stddef.h index dab49e2ec8c0..80b6bfb944f0 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -94,7 +94,8 @@ enum { __DECLARE_FLEX_ARRAY(TYPE, NAME) /** - * TRAILING_OVERLAP() - Overlap a flexible-array member with trailing members. + * __TRAILING_OVERLAP() - Overlap a flexible-array member with trailing + * members. * * Creates a union between a flexible-array member (FAM) in a struct and a set * of additional members that would otherwise follow it. @@ -102,15 +103,30 @@ enum { * @TYPE: Flexible structure type name, including "struct" keyword. * @NAME: Name for a variable to define. * @FAM: The flexible-array member within @TYPE + * @ATTRS: Any struct attributes (usually empty) * @MEMBERS: Trailing overlapping members. */ -#define TRAILING_OVERLAP(TYPE, NAME, FAM, MEMBERS) \ +#define __TRAILING_OVERLAP(TYPE, NAME, FAM, ATTRS, MEMBERS) \ union { \ TYPE NAME; \ struct { \ - unsigned char __offset_to_##FAM[offsetof(TYPE, FAM)]; \ + unsigned char __offset_to_FAM[offsetof(TYPE, FAM)]; \ MEMBERS \ - }; \ + } ATTRS; \ } +/** + * TRAILING_OVERLAP() - Overlap a flexible-array member with trailing members. + * + * Creates a union between a flexible-array member (FAM) in a struct and a set + * of additional members that would otherwise follow it. + * + * @TYPE: Flexible structure type name, including "struct" keyword. + * @NAME: Name for a variable to define. + * @FAM: The flexible-array member within @TYPE + * @MEMBERS: Trailing overlapping members. + */ +#define TRAILING_OVERLAP(TYPE, NAME, FAM, MEMBERS) \ + __TRAILING_OVERLAP(TYPE, NAME, FAM, /* no attrs */, MEMBERS) + #endif diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 26ddf95d23f9..fa1318bac06c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -190,18 +190,27 @@ struct plat_stmmacenet_data { int bus_id; int phy_addr; /* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media - * ^ ^ - * mac_interface phy_interface + * ^ + * phy_interface * - * mac_interface is the MAC-side interface, which may be the same - * as phy_interface if there is no intervening PCS. If there is a - * PCS, then mac_interface describes the interface mode between the - * MAC and PCS, and phy_interface describes the interface mode - * between the PCS and PHY. - */ - phy_interface_t mac_interface; - /* phy_interface is the PHY-side interface - the interface used by - * an attached PHY. + * The Synopsys dwmac core only covers the MAC and an optional + * integrated PCS. Where the integrated PCS is used with a SerDes, + * e.g. for 1000base-X or Cisco SGMII, the connection between the + * PCS and SerDes will be TBI. + * + * Where the Synopsys dwmac core has been instantiated with multiple + * interface modes, these are selected via core-external configuration + * which is sampled when the dwmac core is reset. How this is done is + * platform glue specific, but this defines the interface used from + * the Synopsys dwmac core to the rest of the SoC. + * + * Where PCS other than the optional integrated Synopsys dwmac PCS + * is used, this counts as "the rest of the SoC" in the above + * paragraph. + * + * phy_interface is the PHY-side interface - the interface used by + * an attached PHY or SFP etc. This is equivalent to the interface + * that phylink uses. */ phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; @@ -238,7 +247,7 @@ struct plat_stmmacenet_data { 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 (*fix_soc_reset)(struct stmmac_priv *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); int (*mac_finish)(struct net_device *ndev, @@ -248,6 +257,8 @@ struct plat_stmmacenet_data { 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); + int (*suspend)(struct device *dev, void *priv); + int (*resume)(struct device *dev, void *priv); struct mac_device_info *(*setup)(void *priv); int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index f3ba4f52ff26..ee84087d4b26 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -17,6 +17,12 @@ #include <linux/types.h> +static inline const char *str_assert_deassert(bool v) +{ + return v ? "assert" : "deassert"; +} +#define str_deassert_assert(v) str_assert_deassert(!(v)) + static inline const char *str_enable_disable(bool v) { return v ? "enable" : "disable"; @@ -41,6 +47,12 @@ static inline const char *str_high_low(bool v) } #define str_low_high(v) str_high_low(!(v)) +static inline const char *str_input_output(bool v) +{ + return v ? "input" : "output"; +} +#define str_output_input(v) str_input_output(!(v)) + static inline const char *str_on_off(bool v) { return v ? "on" : "off"; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 317ae31e89b3..b02876f1ae38 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -418,6 +418,12 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { } #endif /* CONFIG_HIBERNATION */ +#if defined(CONFIG_HIBERNATION) && defined(CONFIG_SUSPEND) +bool pm_hibernation_mode_is_suspend(void); +#else +static inline bool pm_hibernation_mode_is_suspend(void) { return false; } +#endif + int arch_resume_nosmt(void); #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..e818fbade1e2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -236,40 +236,6 @@ enum { #define SWAP_CONT_MAX 0x7f /* Max count */ /* - * We use this to track usage of a cluster. A cluster is a block of swap disk - * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All - * free clusters are organized into a list. We fetch an entry from the list to - * get a free cluster. - * - * The flags field determines if a cluster is free. This is - * protected by cluster lock. - */ -struct swap_cluster_info { - spinlock_t lock; /* - * Protect swap_cluster_info fields - * other than list, and swap_info_struct->swap_map - * elements corresponding to the swap cluster. - */ - u16 count; - u8 flags; - u8 order; - struct list_head list; -}; - -/* All on-list cluster must have a non-zero flag. */ -enum swap_cluster_flags { - CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ - CLUSTER_FLAG_FREE, - CLUSTER_FLAG_NONFULL, - CLUSTER_FLAG_FRAG, - /* Clusters with flags above are allocatable */ - CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, - CLUSTER_FLAG_FULL, - CLUSTER_FLAG_DISCARD, - CLUSTER_FLAG_MAX, -}; - -/* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as @@ -310,7 +276,6 @@ struct swap_info_struct { /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ - atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ atomic_long_t inuse_pages; /* number of those currently in use */ struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */ @@ -321,11 +286,8 @@ struct swap_info_struct { struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like - * swap_map, lowest_bit, highest_bit, - * inuse_pages, cluster_next, - * cluster_nr, lowest_alloc, - * highest_alloc, free/discard cluster - * list. other fields are only changed + * swap_map, inuse_pages and all cluster + * lists. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If @@ -385,6 +347,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) @@ -507,10 +479,7 @@ extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); -struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; -extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); -extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); @@ -520,11 +489,6 @@ static inline void put_swap_device(struct swap_info_struct *si) } #else /* CONFIG_SWAP */ -static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) -{ - return NULL; -} - static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 77f45e5d4413..66c06fcdfe19 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1005,6 +1005,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); asmlinkage long sys_uretprobe(void); +asmlinkage long sys_uprobe(void); + /* pciconfig: alpha, arm, arm64, ia64, sparc */ asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, unsigned long off, unsigned long len, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index f418aae4f113..9a25a2911652 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -106,10 +106,7 @@ struct attribute_group { const struct bin_attribute *, int); struct attribute **attrs; - union { - const struct bin_attribute *const *bin_attrs; - const struct bin_attribute *const *bin_attrs_new; - }; + const struct bin_attribute *const *bin_attrs; }; #define SYSFS_PREALLOC 010000 @@ -293,7 +290,7 @@ __ATTRIBUTE_GROUPS(_name) #define BIN_ATTRIBUTE_GROUPS(_name) \ static const struct attribute_group _name##_group = { \ - .bin_attrs_new = _name##_attrs, \ + .bin_attrs = _name##_attrs, \ }; \ __ATTRIBUTE_GROUPS(_name) @@ -308,12 +305,8 @@ struct bin_attribute { struct address_space *(*f_mapping)(void); ssize_t (*read)(struct file *, struct kobject *, const struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*read_new)(struct file *, struct kobject *, const struct bin_attribute *, - char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, const struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write_new)(struct file *, struct kobject *, - const struct bin_attribute *, char *, loff_t, size_t); loff_t (*llseek)(struct file *, struct kobject *, const struct bin_attribute *, loff_t, int); int (*mmap)(struct file *, struct kobject *, const struct bin_attribute *attr, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 57e478bfaef2..20b8c6e21fef 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -122,8 +122,9 @@ struct tcp_options_received { smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ - u8 saw_unknown:1, /* Received unknown option */ - unused:7; + u8 accecn:6, /* AccECN index in header, 0=no options */ + saw_unknown:1, /* Received unknown option */ + unused:1; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -168,6 +169,11 @@ struct tcp_request_sock { * after data-in-SYN. */ u8 syn_tos; + bool accecn_ok; + u8 syn_ect_snt: 2, + syn_ect_rcv: 2, + accecn_fail_mode:4; + u8 saw_accecn_opt :2; #ifdef CONFIG_TCP_AO u8 ao_keyid; u8 ao_rcv_next; @@ -209,6 +215,9 @@ struct tcp_sock { u16 gso_segs; /* Max number of segs per GSO packet */ /* from STCP, retrans queue hinting */ struct sk_buff *retransmit_skb_hint; +#if defined(CONFIG_TLS_DEVICE) + void (*tcp_clean_acked)(struct sock *sk, u32 acked_seq); +#endif __cacheline_group_end(tcp_sock_read_tx); /* TXRX read-mostly hotpath cache lines */ @@ -226,13 +235,13 @@ struct tcp_sock { repair : 1, tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ + is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ + recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_txrx); /* RX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_rx); u32 copied_seq; /* Head of yet unread data */ - u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 snd_wl1; /* Sequence for window update */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 rttvar_us; /* smoothed mdev_max */ @@ -240,14 +249,10 @@ struct tcp_sock { u16 advmss; /* Advertised MSS */ u16 urg_data; /* Saved octet of OOB data and control flags */ u32 lost; /* Total data packets lost incl. rexmits */ + u32 snd_ssthresh; /* Slow start size threshold */ 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); /* TX read-write hotpath cache lines */ @@ -270,6 +275,7 @@ struct tcp_sock { u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 accecn_opt_tstamp; /* Last AccECN option sent timestamp */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set @@ -285,6 +291,14 @@ struct tcp_sock { * Header prediction flags * 0x5?10 << 16 + snd_wnd in net byte order */ + u8 nonagle : 4,/* Disable Nagle algorithm? */ + rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ + u8 received_ce_pending:4, /* Not yet transmit cnt of received_ce */ + unused2:4; + u8 accecn_minlen:2,/* Minimum length of AccECN option sent */ + est_ecnfield:2,/* ECN field for AccECN delivered estimates */ + accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */ + prev_ecnfield:2; /* ECN bits from the previous segment */ __be32 pred_flags; u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ u64 tcp_mstamp; /* most recent packet received/sent */ @@ -297,14 +311,18 @@ struct tcp_sock { u32 snd_up; /* Urgent pointer */ u32 delivered; /* Total data packets delivered incl. rexmits */ u32 delivered_ce; /* Like the above but only ECE marked packets */ + u32 received_ce; /* Like the above but for rcvd CE marked pkts */ + u32 received_ecn_bytes[3]; /* received byte counters for three ECN + * types: INET_ECN_ECT_1, INET_ECN_ECT_0, + * and INET_ECN_CE + */ u32 app_limited; /* limited until "delivered" reaches this val */ u32 rcv_wnd; /* Current receiver window */ + u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ /* * Options received (usually on last packet, some only on SYN packets). */ struct tcp_options_received rx_opt; - u8 nonagle : 4,/* Disable Nagle algorithm? */ - rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ __cacheline_group_end(tcp_sock_write_txrx); /* RX read-write hotpath cache lines */ @@ -326,6 +344,7 @@ struct tcp_sock { u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_rtt_last_tsecr; + u32 delivered_ecn_bytes[3]; u64 first_tx_mstamp; /* start of window send phase */ u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked @@ -372,7 +391,8 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - unused:5; + syn_ect_snt:2, /* AccECN ECT memory, only */ + syn_ect_rcv:2; /* ... needed during 3WHS + first seqno */ u8 thin_lto : 1,/* Use linear timeouts for thin streams */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ @@ -388,6 +408,8 @@ struct tcp_sock { syn_fastopen_child:1; /* created TFO passive child socket */ u8 keepalive_probes; /* num of allowed keep alive probes */ + u8 accecn_fail_mode:4, /* AccECN failure handling */ + saw_accecn_opt:2; /* An AccECN option was seen */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ /* RTT measurement */ @@ -426,6 +448,9 @@ struct tcp_sock { * the first SYN. */ u32 undo_marker; /* snd_una upon a new recovery episode. */ int undo_retrans; /* number of undoable retransmissions. */ + u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG + * while socket was owned by user. + */ u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans * Total data bytes retransmitted */ @@ -472,9 +497,6 @@ struct tcp_sock { u32 probe_seq_end; } mtu_probe; u32 plb_rehash; /* PLB-triggered rehash attempts */ - u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG - * while socket was owned by user. - */ #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h index a38494d6b5f4..1f3e5dad6d0d 100644 --- a/include/linux/tee_core.h +++ b/include/linux/tee_core.h @@ -8,9 +8,11 @@ #include <linux/cdev.h> #include <linux/device.h> +#include <linux/dma-buf.h> #include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/scatterlist.h> #include <linux/tee.h> #include <linux/tee_drv.h> #include <linux/types.h> @@ -26,10 +28,19 @@ #define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ #define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ +#define TEE_SHM_DMA_BUF BIT(4) /* Memory with dma-buf handle */ +#define TEE_SHM_DMA_MEM BIT(5) /* Memory allocated with */ + /* dma_alloc_pages() */ #define TEE_DEVICE_FLAG_REGISTERED 0x1 #define TEE_MAX_DEV_NAME_LEN 32 +enum tee_dma_heap_id { + TEE_DMA_HEAP_SECURE_VIDEO_PLAY = 1, + TEE_DMA_HEAP_TRUSTED_UI, + TEE_DMA_HEAP_SECURE_VIDEO_RECORD, +}; + /** * struct tee_device - TEE Device representation * @name: name of device @@ -65,22 +76,30 @@ struct tee_device { /** * struct tee_driver_ops - driver operations vtable * @get_version: returns version of driver - * @open: called when the device file is opened - * @release: release this open file + * @open: called for a context when the device file is opened + * @close_context: called when the device file is closed + * @release: called to release the context * @open_session: open a new session * @close_session: close a session * @system_session: declare session as a system session * @invoke_func: invoke a trusted function + * @object_invoke_func: invoke a TEE object * @cancel_req: request cancel of an ongoing invoke or open * @supp_recv: called for supplicant to get a command * @supp_send: called for supplicant to send a response * @shm_register: register shared memory buffer in TEE * @shm_unregister: unregister shared memory buffer in TEE + * + * The context given to @open might last longer than the device file if it is + * tied to other resources in the TEE driver. @close_context is called when the + * client closes the device file, even if there are existing references to the + * context. The TEE driver can use @close_context to start cleaning up. */ struct tee_driver_ops { void (*get_version)(struct tee_device *teedev, struct tee_ioctl_version_data *vers); int (*open)(struct tee_context *ctx); + void (*close_context)(struct tee_context *ctx); void (*release)(struct tee_context *ctx); int (*open_session)(struct tee_context *ctx, struct tee_ioctl_open_session_arg *arg, @@ -90,6 +109,9 @@ struct tee_driver_ops { int (*invoke_func)(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg, struct tee_param *param); + int (*object_invoke_func)(struct tee_context *ctx, + struct tee_ioctl_object_invoke_arg *arg, + struct tee_param *param); int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, struct tee_param *param); @@ -117,6 +139,36 @@ struct tee_desc { }; /** + * struct tee_protmem_pool - protected memory pool + * @ops: operations + * + * This is an abstract interface where this struct is expected to be + * embedded in another struct specific to the implementation. + */ +struct tee_protmem_pool { + const struct tee_protmem_pool_ops *ops; +}; + +/** + * struct tee_protmem_pool_ops - protected memory pool operations + * @alloc: called when allocating protected memory + * @free: called when freeing protected memory + * @update_shm: called when registering a dma-buf to update the @shm + * with physical address of the buffer or to return the + * @parent_shm of the memory pool + * @destroy_pool: called when destroying the pool + */ +struct tee_protmem_pool_ops { + int (*alloc)(struct tee_protmem_pool *pool, struct sg_table *sgt, + size_t size, size_t *offs); + void (*free)(struct tee_protmem_pool *pool, struct sg_table *sgt); + int (*update_shm)(struct tee_protmem_pool *pool, struct sg_table *sgt, + size_t offs, struct tee_shm *shm, + struct tee_shm **parent_shm); + void (*destroy_pool)(struct tee_protmem_pool *pool); +}; + +/** * tee_device_alloc() - Allocate a new struct tee_device instance * @teedesc: Descriptor for this driver * @dev: Parent device for this device @@ -154,6 +206,29 @@ int tee_device_register(struct tee_device *teedev); */ void tee_device_unregister(struct tee_device *teedev); +int tee_device_register_dma_heap(struct tee_device *teedev, + enum tee_dma_heap_id id, + struct tee_protmem_pool *pool); +void tee_device_put_all_dma_heaps(struct tee_device *teedev); + +/** + * tee_device_get() - Increment the user count for a tee_device + * @teedev: Pointer to the tee_device + * + * If tee_device_unregister() has been called and the final user of @teedev + * has already released the device, this function will fail to prevent new users + * from accessing the device during the unregistration process. + * + * Returns: true if @teedev remains valid, otherwise false + */ +bool tee_device_get(struct tee_device *teedev); + +/** + * tee_device_put() - Decrease the user count for a tee_device + * @teedev: pointer to the tee_device + */ +void tee_device_put(struct tee_device *teedev); + /** * tee_device_set_dev_groups() - Set device attribute groups * @teedev: Device to register @@ -230,6 +305,16 @@ static inline void tee_shm_pool_free(struct tee_shm_pool *pool) } /** + * tee_protmem_static_pool_alloc() - Create a protected memory manager + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + * + * @returns pointer to a 'struct tee_protmem_pool' or an ERR_PTR on failure. + */ +struct tee_protmem_pool *tee_protmem_static_pool_alloc(phys_addr_t paddr, + size_t size); + +/** * tee_get_drvdata() - Return driver_data pointer * @returns the driver_data pointer supplied to tee_register(). */ @@ -244,6 +329,9 @@ void *tee_get_drvdata(struct tee_device *teedev); */ struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); +struct tee_shm *tee_shm_alloc_dma_mem(struct tee_context *ctx, + size_t page_count); + int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, @@ -315,4 +403,25 @@ struct tee_context *teedev_open(struct tee_device *teedev); */ void teedev_close_context(struct tee_context *ctx); +/** + * teedev_ctx_get() - Increment the reference count of a context + * @ctx: Pointer to the context + * + * This function increases the refcount of the context, which is tied to + * resources shared by the same tee_device. During the unregistration process, + * the context may remain valid even after tee_device_unregister() has returned. + * + * Users should ensure that the context's refcount is properly decreased before + * calling tee_device_put(), typically within the context's release() function. + * Alternatively, users can call tee_device_get() and teedev_ctx_get() together + * and release them simultaneously (see shm_alloc_helper()). + */ +void teedev_ctx_get(struct tee_context *ctx); + +/** + * teedev_ctx_put() - Decrease reference count on a context + * @ctx: pointer to the context + */ +void teedev_ctx_put(struct tee_context *ctx); + #endif /*__TEE_CORE_H*/ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a54c203000ed..88a6f9697c89 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -82,6 +82,16 @@ struct tee_param_memref { struct tee_shm *shm; }; +struct tee_param_ubuf { + void __user *uaddr; + size_t size; +}; + +struct tee_param_objref { + u64 id; + u64 flags; +}; + struct tee_param_value { u64 a; u64 b; @@ -92,6 +102,8 @@ struct tee_param { u64 attr; union { struct tee_param_memref memref; + struct tee_param_objref objref; + struct tee_param_ubuf ubuf; struct tee_param_value value; } u; }; @@ -117,6 +129,16 @@ struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** + * tee_shm_register_fd() - Register shared memory from file descriptor + * + * @ctx: Context that allocates the shared memory + * @fd: Shared memory file descriptor reference + * + * @returns a pointer to 'struct tee_shm' on success, and ERR_PTR on failure + */ +struct tee_shm *tee_shm_register_fd(struct tee_context *ctx, int fd); + +/** * tee_shm_free() - Free shared memory * @shm: Handle to shared memory to free */ diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index bb2c52f4fc94..c514d0e5a45c 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -33,17 +33,22 @@ struct time_namespace { extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS +static inline struct time_namespace *to_time_ns(struct ns_common *ns) +{ + return container_of(ns, struct time_namespace, ns); +} +void __init time_ns_init(void); extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } -struct time_namespace *copy_time_ns(unsigned long flags, +struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); @@ -52,7 +57,7 @@ struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { - if (refcount_dec_and_test(&ns->ns.count)) + if (ns_ref_put(ns)) free_time_ns(ns); } @@ -108,6 +113,10 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #else +static inline void __init time_ns_init(void) +{ +} + static inline int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { @@ -129,7 +138,7 @@ static inline void put_time_ns(struct time_namespace *ns) } static inline -struct time_namespace *copy_time_ns(unsigned long flags, +struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index c27aac67cb3f..b8ae89ea28ab 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -76,6 +76,7 @@ struct tk_read_base { * @cs_was_changed_seq: The sequence number of clocksource change events * @clock_valid: Indicator for valid clock * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset + * @monotonic_to_aux: CLOCK_MONOTONIC to CLOCK_AUX offset * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP * interval. @@ -117,6 +118,9 @@ struct tk_read_base { * @offs_aux is used by the auxiliary timekeepers which do not utilize any * of the regular timekeeper offset fields. * + * @monotonic_to_aux is a timespec64 representation of @offs_aux to + * accelerate the VDSO update for CLOCK_AUX. + * * The cacheline ordering of the structure is optimized for in kernel usage of * the ktime_get() and ktime_get_ts64() family of time accessors. Struct * timekeeper is prepended in the core timekeeping code with a sequence count, @@ -159,7 +163,10 @@ struct timekeeper { u8 cs_was_changed_seq; u8 clock_valid; - struct timespec64 monotonic_to_boot; + union { + struct timespec64 monotonic_to_boot; + struct timespec64 monotonic_to_aux; + }; u64 cycle_interval; u64 xtime_interval; diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 57ed3035cc30..c52b862dad45 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -51,9 +51,15 @@ struct tnum tnum_xor(struct tnum a, struct tnum b); /* Multiply two tnums, return @a * @b */ struct tnum tnum_mul(struct tnum a, struct tnum b); +/* Return true if the known bits of both tnums have the same value */ +bool tnum_overlap(struct tnum a, struct tnum b); + /* Return a tnum representing numbers satisfying both @a and @b */ struct tnum tnum_intersect(struct tnum a, struct tnum b); +/* Returns a tnum representing numbers satisfying either @a or @b */ +struct tnum tnum_union(struct tnum t1, struct tnum t2); + /* Return @a with all but the lowest @size bytes cleared */ struct tnum tnum_cast(struct tnum a, u8 size); diff --git a/include/linux/topology.h b/include/linux/topology.h index 33b7fda97d39..6575af39fd10 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -260,7 +260,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu) #endif -static inline const struct cpumask *cpu_cpu_mask(int cpu) +static inline const struct cpumask *cpu_node_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } diff --git a/include/linux/udp.h b/include/linux/udp.h index 4e1a672af4c5..58795688a186 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -44,6 +44,12 @@ enum { UDP_FLAGS_UDPLITE_RECV_CC, /* set via udplite setsockopt */ }; +/* per NUMA structure for lockless producer usage. */ +struct udp_prod_queue { + struct llist_head ll_root ____cacheline_aligned_in_smp; + atomic_t rmem_alloc; +}; + struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; @@ -90,6 +96,8 @@ struct udp_sock { struct sk_buff *skb, int nhoff); + struct udp_prod_queue *udp_prod_queue; + /* udp_recvmsg try to use this before splicing sk_receive_queue */ struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; @@ -108,6 +116,7 @@ struct udp_sock { * the last UDP socket cacheline. */ struct hlist_node tunnel_list; + struct numa_drop_counters drop_counters; }; #define udp_test_bit(nr, sk) \ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 516217c39094..ee3d36eda45d 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -17,6 +17,7 @@ #include <linux/wait.h> #include <linux/timer.h> #include <linux/seqlock.h> +#include <linux/mutex.h> struct uprobe; struct vm_area_struct; @@ -185,8 +186,14 @@ struct xol_area; struct uprobes_state { struct xol_area *xol_area; +#ifdef CONFIG_X86_64 + struct hlist_head head_tramps; +#endif }; +typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, + uprobe_opcode_t *insn, int nbytes, void *data); + extern void __init uprobes_init(void); extern int set_swbp(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr); extern int set_orig_insn(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr); @@ -194,7 +201,11 @@ extern bool is_swbp_insn(uprobe_opcode_t *insn); extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); -extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t); +extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t, + bool is_register); +extern int uprobe_write(struct arch_uprobe *auprobe, struct vm_area_struct *vma, const unsigned long opcode_vaddr, + uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify, bool is_register, bool do_update_ref_ctr, + void *data); extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc); @@ -205,7 +216,7 @@ extern void uprobe_start_dup_mmap(void); extern void uprobe_end_dup_mmap(void); extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm); extern void uprobe_free_utask(struct task_struct *t); -extern void uprobe_copy_process(struct task_struct *t, unsigned long flags); +extern void uprobe_copy_process(struct task_struct *t, u64 flags); extern int uprobe_post_sstep_notifier(struct pt_regs *regs); extern int uprobe_pre_sstep_notifier(struct pt_regs *regs); extern void uprobe_notify_resume(struct pt_regs *regs); @@ -224,8 +235,13 @@ extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs); extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len); extern void uprobe_handle_trampoline(struct pt_regs *regs); -extern void *arch_uprobe_trampoline(unsigned long *psize); +extern void *arch_uretprobe_trampoline(unsigned long *psize); extern unsigned long uprobe_get_trampoline_vaddr(void); +extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len); +extern void arch_uprobe_clear_state(struct mm_struct *mm); +extern void arch_uprobe_init_state(struct mm_struct *mm); +extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr); +extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr); #else /* !CONFIG_UPROBES */ struct uprobes_state { }; @@ -281,7 +297,7 @@ static inline bool uprobe_deny_signal(void) static inline void uprobe_free_utask(struct task_struct *t) { } -static inline void uprobe_copy_process(struct task_struct *t, unsigned long flags) +static inline void uprobe_copy_process(struct task_struct *t, u64 flags) { } static inline void uprobe_clear_state(struct mm_struct *mm) diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h index ee19e9f915b8..22e0dab0809e 100644 --- a/include/linux/usb/uvc.h +++ b/include/linux/usb/uvc.h @@ -29,10 +29,32 @@ #define UVC_GUID_EXT_GPIO_CONTROLLER \ {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x03} +#define UVC_GUID_CHROMEOS_XU \ + {0x24, 0xe9, 0xd7, 0x74, 0xc9, 0x49, 0x45, 0x4a, \ + 0x98, 0xa3, 0xc8, 0x07, 0x7e, 0x05, 0x1c, 0xa3} #define UVC_GUID_MSXU_1_5 \ {0xdc, 0x95, 0x3f, 0x0f, 0x32, 0x26, 0x4e, 0x4c, \ 0x92, 0xc9, 0xa0, 0x47, 0x82, 0xf4, 0x3b, 0xc8} +/* https://learn.microsoft.com/en-us/windows-hardware/drivers/stream/uvc-extensions-1-5#222-extension-unit-controls */ +#define UVC_MSXU_CONTROL_FOCUS 0x01 +#define UVC_MSXU_CONTROL_EXPOSURE 0x02 +#define UVC_MSXU_CONTROL_EVCOMPENSATION 0x03 +#define UVC_MSXU_CONTROL_WHITEBALANCE 0x04 +#define UVC_MSXU_CONTROL_FACE_AUTHENTICATION 0x06 +#define UVC_MSXU_CONTROL_CAMERA_EXTRINSICS 0x07 +#define UVC_MSXU_CONTROL_CAMERA_INTRINSICS 0x08 +#define UVC_MSXU_CONTROL_METADATA 0x09 +#define UVC_MSXU_CONTROL_IR_TORCH 0x0a +#define UVC_MSXU_CONTROL_DIGITALWINDOW 0x0b +#define UVC_MSXU_CONTROL_DIGITALWINDOW_CONFIG 0x0c +#define UVC_MSXU_CONTROL_VIDEO_HDR 0x0d +#define UVC_MSXU_CONTROL_FRAMERATE_THROTTLE 0x0e +#define UVC_MSXU_CONTROL_FIELDOFVIEW2_CONFIG 0x0f +#define UVC_MSXU_CONTROL_FIELDOFVIEW2 0x10 + +#define UVC_CROSXU_CONTROL_IQ_PROFILE 0x04 + #define UVC_GUID_FORMAT_MJPEG \ { 'M', 'J', 'P', 'G', 0x00, 0x00, 0x10, 0x00, \ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 8afa8c3a0973..57d1ff006090 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -33,7 +33,7 @@ extern void user_event_mm_dup(struct task_struct *t, extern void user_event_mm_remove(struct task_struct *t); static inline void user_events_fork(struct task_struct *t, - unsigned long clone_flags) + u64 clone_flags) { struct user_event_mm *old_mm; @@ -68,7 +68,7 @@ static inline void user_events_exit(struct task_struct *t) } #else static inline void user_events_fork(struct task_struct *t, - unsigned long clone_flags) + u64 clone_flags) { } diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index a0bb6d012137..9a9aebbf96b9 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -168,10 +168,15 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns, #ifdef CONFIG_USER_NS +static inline struct user_namespace *to_user_ns(struct ns_common *ns) +{ + return container_of(ns, struct user_namespace, ns); +} + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } @@ -181,7 +186,7 @@ extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { - if (ns && refcount_dec_and_test(&ns->ns.count)) + if (ns && ns_ref_put(ns)) __put_user_ns(ns); } diff --git a/include/linux/uts_namespace.h b/include/linux/uts_namespace.h new file mode 100644 index 000000000000..60f37fec0f4b --- /dev/null +++ b/include/linux/uts_namespace.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UTS_NAMESPACE_H +#define _LINUX_UTS_NAMESPACE_H + +#include <linux/ns_common.h> +#include <uapi/linux/utsname.h> + +struct user_namespace; +extern struct user_namespace init_user_ns; + +struct uts_namespace { + struct new_utsname name; + struct user_namespace *user_ns; + struct ucounts *ucounts; + struct ns_common ns; +} __randomize_layout; + +extern struct uts_namespace init_uts_ns; + +#ifdef CONFIG_UTS_NS +static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) +{ + return container_of(ns, struct uts_namespace, ns); +} + +static inline void get_uts_ns(struct uts_namespace *ns) +{ + ns_ref_inc(ns); +} + +extern struct uts_namespace *copy_utsname(u64 flags, + struct user_namespace *user_ns, struct uts_namespace *old_ns); +extern void free_uts_ns(struct uts_namespace *ns); + +static inline void put_uts_ns(struct uts_namespace *ns) +{ + if (ns_ref_put(ns)) + free_uts_ns(ns); +} + +void uts_ns_init(void); +#else +static inline void get_uts_ns(struct uts_namespace *ns) +{ +} + +static inline void put_uts_ns(struct uts_namespace *ns) +{ +} + +static inline struct uts_namespace *copy_utsname(u64 flags, + struct user_namespace *user_ns, struct uts_namespace *old_ns) +{ + if (flags & CLONE_NEWUTS) + return ERR_PTR(-EINVAL); + + return old_ns; +} + +static inline void uts_ns_init(void) +{ +} +#endif + +#endif /* _LINUX_UTS_NAMESPACE_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index bf7613ba412b..547bd4439706 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -7,7 +7,7 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> -#include <uapi/linux/utsname.h> +#include <linux/uts_namespace.h> enum uts_proc { UTS_PROC_ARCH, @@ -18,57 +18,6 @@ enum uts_proc { UTS_PROC_DOMAINNAME, }; -struct user_namespace; -extern struct user_namespace init_user_ns; - -struct uts_namespace { - struct new_utsname name; - struct user_namespace *user_ns; - struct ucounts *ucounts; - struct ns_common ns; -} __randomize_layout; -extern struct uts_namespace init_uts_ns; - -#ifdef CONFIG_UTS_NS -static inline void get_uts_ns(struct uts_namespace *ns) -{ - refcount_inc(&ns->ns.count); -} - -extern struct uts_namespace *copy_utsname(unsigned long flags, - struct user_namespace *user_ns, struct uts_namespace *old_ns); -extern void free_uts_ns(struct uts_namespace *ns); - -static inline void put_uts_ns(struct uts_namespace *ns) -{ - if (refcount_dec_and_test(&ns->ns.count)) - free_uts_ns(ns); -} - -void uts_ns_init(void); -#else -static inline void get_uts_ns(struct uts_namespace *ns) -{ -} - -static inline void put_uts_ns(struct uts_namespace *ns) -{ -} - -static inline struct uts_namespace *copy_utsname(unsigned long flags, - struct user_namespace *user_ns, struct uts_namespace *old_ns) -{ - if (flags & CLONE_NEWUTS) - return ERR_PTR(-EINVAL); - - return old_ns; -} - -static inline void uts_ns_init(void) -{ -} -#endif - #ifdef CONFIG_PROC_SYSCTL extern void uts_proc_notify(enum uts_proc proc); #else diff --git a/include/linux/verification.h b/include/linux/verification.h index 4f3022d081c3..dec7f2beabfd 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -36,6 +36,7 @@ enum key_being_used_for { VERIFYING_KEY_SIGNATURE, VERIFYING_KEY_SELF_SIGNATURE, VERIFYING_UNSPECIFIED_SIGNATURE, + VERIFYING_BPF_SIGNATURE, NR__KEY_BEING_USED_FOR }; #ifdef CONFIG_SYSTEM_DATA_VERIFICATION diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 219037f4c08d..9609cf365e8e 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -50,7 +50,7 @@ * * Author: Bill Dirks <bill@thedirks.org> * Justin Schoeman - * Hans Verkuil <hverkuil@xs4all.nl> + * Hans Verkuil <hverkuil@kernel.org> * et al. */ #ifndef __LINUX_VIDEODEV2_H diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 918cf25cd3c6..7427b79d6f3d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -193,14 +193,15 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, } static inline void virtio_get_features(struct virtio_device *vdev, - u64 *features) + u64 *features_out) { if (vdev->config->get_extended_features) { - vdev->config->get_extended_features(vdev, features); + vdev->config->get_extended_features(vdev, features_out); return; } - virtio_features_from_u64(features, vdev->config->get_features(vdev)); + virtio_features_from_u64(features_out, + vdev->config->get_features(vdev)); } /** @@ -326,13 +327,11 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) static inline bool virtio_get_shm_region(struct virtio_device *vdev, - struct virtio_shm_region *region, u8 id) + struct virtio_shm_region *region_out, u8 id) { - if (!region->len) - return false; if (!vdev->config->get_shm_region) return false; - return vdev->config->get_shm_region(vdev, region, id); + return vdev->config->get_shm_region(vdev, region_out, id); } static inline bool virtio_is_little_endian(struct virtio_device *vdev) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 9e15a088ba38..92f80b4d69a6 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -2,6 +2,8 @@ #ifndef VM_EVENT_ITEM_H_INCLUDED #define VM_EVENT_ITEM_H_INCLUDED +#include <linux/thread_info.h> + #ifdef CONFIG_ZONE_DMA #define DMA_ZONE(xx) xx##_DMA, #else diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index fdc9aeb74a44..eb54b7b3202f 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -197,9 +197,15 @@ extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1 extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) -void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags) - __realloc_size(2); -#define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) +void *__must_check vrealloc_node_align_noprof(const void *p, size_t size, + unsigned long align, gfp_t flags, int nid) __realloc_size(2); +#define vrealloc_node_noprof(_p, _s, _f, _nid) \ + vrealloc_node_align_noprof(_p, _s, 1, _f, _nid) +#define vrealloc_noprof(_p, _s, _f) \ + vrealloc_node_align_noprof(_p, _s, 1, _f, NUMA_NO_NODE) +#define vrealloc_node_align(...) alloc_hooks(vrealloc_node_align_noprof(__VA_ARGS__)) +#define vrealloc_node(...) alloc_hooks(vrealloc_node_noprof(__VA_ARGS__)) +#define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); @@ -220,22 +226,6 @@ int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); /* - * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values - * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() - * needs to be called. - */ -#ifndef ARCH_PAGE_TABLE_SYNC_MASK -#define ARCH_PAGE_TABLE_SYNC_MASK 0 -#endif - -/* - * There is no default implementation for arch_sync_kernel_mappings(). It is - * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK - * is 0. - */ -void arch_sync_kernel_mappings(unsigned long start, unsigned long end); - -/* * Lowlevel-APIs (not for driver use!) */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 45d5dd470ff6..dabc351cc127 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -410,7 +410,7 @@ enum wq_flags { __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ /* BH wq only allows the following flags */ - __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI, + __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI | WQ_PERCPU, }; enum wq_consts { @@ -434,10 +434,10 @@ enum wq_consts { * short queue flush time. Don't queue works which can run for too * long. * - * system_highpri_wq is similar to system_wq but for work items which + * system_highpri_wq is similar to system_percpu_wq but for work items which * require WQ_HIGHPRI. * - * system_long_wq is similar to system_wq but may host long running + * system_long_wq is similar to system_percpu_wq but may host long running * works. Queue flushing might take relatively long. * * system_dfl_wq is unbound workqueue. Workers are not bound to @@ -445,13 +445,13 @@ enum wq_consts { * executed immediately as long as max_active limit is not reached and * resources are available. * - * system_freezable_wq is equivalent to system_wq except that it's + * system_freezable_wq is equivalent to system_percpu_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. - * system_power_efficient_wq is identical to system_wq if + * system_power_efficient_wq is identical to system_percpu_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. * * system_bh[_highpri]_wq are convenience interface to softirq. BH work items @@ -502,7 +502,7 @@ void workqueue_softirq_dead(unsigned int cpu); * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means * that the sum of per-node max_active's may be larger than @max_active. * - * For detailed information on %WQ_* flags, please refer to + * For detailed information on %WQ_\* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: @@ -570,7 +570,7 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ - alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) + alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) @@ -708,7 +708,7 @@ static inline bool mod_delayed_work(struct workqueue_struct *wq, */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { - return queue_work_on(cpu, system_wq, work); + return queue_work_on(cpu, system_percpu_wq, work); } /** @@ -727,7 +727,7 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work) */ static inline bool schedule_work(struct work_struct *work) { - return queue_work(system_wq, work); + return queue_work(system_percpu_wq, work); } /** @@ -770,21 +770,21 @@ extern void __warn_flushing_systemwide_wq(void) #define flush_scheduled_work() \ ({ \ __warn_flushing_systemwide_wq(); \ - __flush_workqueue(system_wq); \ + __flush_workqueue(system_percpu_wq); \ }) #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ \ - if ((__builtin_constant_p(_wq == system_wq) && \ - _wq == system_wq) || \ + if ((__builtin_constant_p(_wq == system_percpu_wq) && \ + _wq == system_percpu_wq) || \ (__builtin_constant_p(_wq == system_highpri_wq) && \ _wq == system_highpri_wq) || \ (__builtin_constant_p(_wq == system_long_wq) && \ _wq == system_long_wq) || \ - (__builtin_constant_p(_wq == system_unbound_wq) && \ - _wq == system_unbound_wq) || \ + (__builtin_constant_p(_wq == system_dfl_wq) && \ + _wq == system_dfl_wq) || \ (__builtin_constant_p(_wq == system_freezable_wq) && \ _wq == system_freezable_wq) || \ (__builtin_constant_p(_wq == system_power_efficient_wq) && \ @@ -807,7 +807,7 @@ extern void __warn_flushing_systemwide_wq(void) static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { - return queue_delayed_work_on(cpu, system_wq, dwork, delay); + return queue_delayed_work_on(cpu, system_percpu_wq, dwork, delay); } /** @@ -821,7 +821,7 @@ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { - return queue_delayed_work(system_wq, dwork, delay); + return queue_delayed_work(system_percpu_wq, dwork, delay); } #ifndef CONFIG_SMP diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a2848d731a46..22dd4adc5667 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -265,6 +265,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } +void inode_switch_wbs_work_fn(struct work_struct *work); + #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) @@ -360,12 +362,6 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb); struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error); -typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, - void *data); - -int write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc, writepage_t writepage, - void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, diff --git a/include/linux/zpool.h b/include/linux/zpool.h deleted file mode 100644 index 369ef068fad8..000000000000 --- a/include/linux/zpool.h +++ /dev/null @@ -1,86 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * zpool memory storage api - * - * Copyright (C) 2014 Dan Streetman - * - * This is a common frontend for the zswap compressed memory storage - * implementations. - */ - -#ifndef _ZPOOL_H_ -#define _ZPOOL_H_ - -struct zpool; - -bool zpool_has_pool(char *type); - -struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp); - -const char *zpool_get_type(struct zpool *pool); - -void zpool_destroy_pool(struct zpool *pool); - -int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, - unsigned long *handle, const int nid); - -void zpool_free(struct zpool *pool, unsigned long handle); - -void *zpool_obj_read_begin(struct zpool *zpool, unsigned long handle, - void *local_copy); - -void zpool_obj_read_end(struct zpool *zpool, unsigned long handle, - void *handle_mem); - -void zpool_obj_write(struct zpool *zpool, unsigned long handle, - void *handle_mem, size_t mem_len); - -u64 zpool_get_total_pages(struct zpool *pool); - - -/** - * struct zpool_driver - driver implementation for zpool - * @type: name of the driver. - * @list: entry in the list of zpool drivers. - * @create: create a new pool. - * @destroy: destroy a pool. - * @malloc: allocate mem from a pool. - * @free: free mem from a pool. - * @sleep_mapped: whether zpool driver can sleep during map. - * @map: map a handle. - * @unmap: unmap a handle. - * @total_size: get total size of a pool. - * - * This is created by a zpool implementation and registered - * with zpool. - */ -struct zpool_driver { - char *type; - struct module *owner; - atomic_t refcount; - struct list_head list; - - void *(*create)(const char *name, gfp_t gfp); - void (*destroy)(void *pool); - - int (*malloc)(void *pool, size_t size, gfp_t gfp, - unsigned long *handle, const int nid); - void (*free)(void *pool, unsigned long handle); - - void *(*obj_read_begin)(void *pool, unsigned long handle, - void *local_copy); - void (*obj_read_end)(void *pool, unsigned long handle, - void *handle_mem); - void (*obj_write)(void *pool, unsigned long handle, - void *handle_mem, size_t mem_len); - - u64 (*total_pages)(void *pool); -}; - -void zpool_register_driver(struct zpool_driver *driver); - -int zpool_unregister_driver(struct zpool_driver *driver); - -bool zpool_can_sleep_mapped(struct zpool *pool); - -#endif |