diff options
Diffstat (limited to 'include/uapi/linux')
47 files changed, 1188 insertions, 173 deletions
diff --git a/include/uapi/linux/amd-pmf.h b/include/uapi/linux/amd-pmf.h index 24cf9926dc59..151f264cd7d6 100644 --- a/include/uapi/linux/amd-pmf.h +++ b/include/uapi/linux/amd-pmf.h @@ -199,6 +199,9 @@ struct amd_pmf_info { /* BIOS parameters */ __u32 bios_input[AMD_PMF_BIOS_PARAMS_MAX]; __u32 bios_output[AMD_PMF_BIOS_PARAMS_MAX]; + + /* align to 64 bit boundary */ + __u32 __pad; }; #endif /* _UAPI_LINUX_AMD_PMF_H */ diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 701cad36de43..96e5b0184a1b 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -296,6 +296,7 @@ enum transaction_flags { TF_ACCEPT_FDS = 0x10, /* allow replies with file descriptors */ TF_CLEAR_BUF = 0x20, /* clear buffer on txn complete */ TF_UPDATE_TXN = 0x40, /* update the outdated pending async txn */ + TF_DEFER_COMPLETE = 0x80, /* defer transaction complete to userspace */ }; struct binder_transaction_data { diff --git a/include/uapi/linux/atm.h b/include/uapi/linux/atm.h index 95ebdcf4fe88..7a3789f39f52 100644 --- a/include/uapi/linux/atm.h +++ b/include/uapi/linux/atm.h @@ -39,7 +39,7 @@ #define ATM_MAX_VCI 65535 /* maximum VCI */ -/* "protcol" values for the socket system call */ +/* "protocol" values for the socket system call */ #define ATM_NO_AAL 0 /* AAL not specified */ #define ATM_AAL0 13 /* "raw" ATM cells */ #define ATM_AAL1 1 /* AAL1 (CBR) */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index e8f5ce677df7..abae0524746e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -122,6 +122,7 @@ #define AUDIT_OPENAT2 1337 /* Record showing openat2 how args */ #define AUDIT_DM_CTRL 1338 /* Device Mapper target control */ #define AUDIT_DM_EVENT 1339 /* Device Mapper events */ +#define AUDIT_FSOPEN 1340 /* Record showing fsopen fs_name arg */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 732b35cc08d1..8d7228834305 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -56,6 +56,19 @@ enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, + /* + * Follows a call of a bpf subprog. Taken when the subprog left with + * BPF_EXIT that has src_reg == BPF_UNWIND_EXIT. + */ + BPF_UNWIND_GOTO = 1, +}; + +enum bpf_pseudo_exit { + /* + * When bpf_exit->src_reg == BPF_UNWIND_EXIT, it's the same as bpf_exit, + * except that BPF_UNWIND_GOTO after the call is taken. + */ + BPF_UNWIND_EXIT = 1, }; /* Register numbers */ @@ -936,6 +949,33 @@ union bpf_iter_link_info { * 0 on success or -1 if an error occurred (in which case, * *errno* is set appropriately). * + * BPF_PROG_STREAM_OPEN + * Description + * Open a file descriptor for one of the BPF streams associated + * with the program identified by *prog_fd*. The stream is selected + * by *stream_id*. + * + * The returned file descriptor supports **read**\ (2) and + * **poll**\ (2). Reads block while the stream is empty unless + * **BPF_F_STREAM_NONBLOCK** is specified in *flags*. A non-blocking + * read of an empty stream fails with **EAGAIN**. + * + * **poll**\ (2) reports **POLLIN** when data is available and + * **POLLHUP** once the program has been freed, that is, after every + * reference to it, including links and other file descriptors, has + * been dropped. Hangup may lag the final release because program + * teardown is deferred. Buffered data remains readable after + * **POLLHUP** and a read returns zero after all such data has been + * consumed. + * + * The file descriptor is read-only and has the close-on-exec flag + * set. It is not seekable and **lseek**\ (2) fails with **ESPIPE**. + * *flags* may only contain **BPF_F_STREAM_NONBLOCK**. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -993,6 +1033,7 @@ enum bpf_cmd { BPF_TOKEN_CREATE, BPF_PROG_STREAM_READ_BY_FD, BPF_PROG_ASSOC_STRUCT_OPS, + BPF_PROG_STREAM_OPEN, __MAX_BPF_CMD, BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ }; @@ -1524,6 +1565,11 @@ enum { BPF_STREAM_STDERR = 2, }; +/* flags for BPF_PROG_STREAM_OPEN command */ +enum { + BPF_F_STREAM_NONBLOCK = (1U << 0), +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -1756,7 +1802,7 @@ union bpf_attr { __u32 prog_cnt; __u32 count; }; - __u32 :32; + __u32 type_id; /* output: per-program attach_flags. * not allowed to be set during effective query. */ @@ -1950,6 +1996,12 @@ union bpf_attr { __u32 flags; } prog_assoc_struct_ops; + struct { + __u32 prog_fd; + __u32 stream_id; + __u32 flags; + } prog_stream_open; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -4867,15 +4919,18 @@ union bpf_attr { * The non-negative copied *buf* length equal to or less than * *size* on success, or a negative error in case of failure. * - * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * long bpf_load_hdr_opt(void *ctx, void *searchby_res, u32 len, u64 flags) * Description * Load header option. Support reading a particular TCP header - * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). + * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). For the + * **bpf_tcp_ops** struct_ops, this helper can be called from the + * **parse_hdr**\ () and **write_hdr_opt**\ () operators. * - * If *flags* is 0, it will search the option from the - * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** - * has details on what skb_data contains under different - * *skops*\ **->op**. + * If *flags* is 0, it will search the option from the packet + * associated with the current operation. For + * **BPF_PROG_TYPE_SOCK_OPS**, the comment in + * **struct bpf_sock_ops** has details on what skb_data + * contains under different *op*. * * The first byte of the *searchby_res* specifies the * kind that it wants to search. @@ -4908,6 +4963,8 @@ union bpf_attr { * * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the * saved_syn packet or the just-received syn packet. + * Not supported by the **bpf_tcp_ops** struct_ops, which + * rejects all flags. * * Return * > 0 when found, the header option is copied to *searchby_res*. @@ -4928,9 +4985,9 @@ union bpf_attr { * packet. * * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. + * operation. * - * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * long bpf_store_hdr_opt(void *ctx, const void *from, u32 len, u64 flags) * Description * Store header option. The data will be copied * from buffer *from* with length *len* to the TCP header. @@ -4946,7 +5003,9 @@ union bpf_attr { * by searching the same option in the outgoing skb. * * This helper can only be called during - * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**, or from the + * **write_hdr_opt**\ () operator of the **bpf_tcp_ops** + * struct_ops. * * Return * 0 on success, or negative error in case of failure: @@ -4961,9 +5020,9 @@ union bpf_attr { * **-EFAULT** on failure to parse the existing header options. * * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. + * operation. * - * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * long bpf_reserve_hdr_opt(void *ctx, u32 len, u64 flags) * Description * Reserve *len* bytes for the bpf header option. The * space will be used by **bpf_store_hdr_opt**\ () later in @@ -4973,7 +5032,9 @@ union bpf_attr { * the total number of bytes will be reserved. * * This helper can only be called during - * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. + * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**, or from the + * **hdr_opt_len**\ () operator of the **bpf_tcp_ops** + * struct_ops. * * Return * 0 on success, or negative error in case of failure: @@ -4983,7 +5044,7 @@ union bpf_attr { * **-ENOSPC** if there is not enough space in the header. * * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. + * operation. * * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) * Description @@ -6890,6 +6951,8 @@ struct bpf_link_info { } xdp; struct { __u32 map_id; + __u32 :32; + __u64 cgroup_id; } struct_ops; struct { __u32 pf; @@ -7284,6 +7347,31 @@ enum { */ }; +/* + * Most callbacks of struct bpf_tcp_ops are placed in the slow + * path (e.g., one-shot connection setup or unlikely events like + * timers) and are invoked simply by defining non-NULL callbacks. + * + * Callbacks in the fast path, however, would incur noticeable + * overhead even when set to NULL, so they are disabled by default + * and must be explicitly enabled per socket via bpf_tcp_ops_set_flags(). + * + * The flags are per-socket and shared by all effective bpf_tcp_ops + * programs. + */ +enum { + /* .rtt() */ + BPF_TCP_OPS_FLAG_RTT = (1 << 0), + /* .parse_hdr() */ + BPF_TCP_OPS_FLAG_PARSE_HDR_OPT_ALL = (1 << 1), + BPF_TCP_OPS_FLAG_PARSE_HDR_OPT_UNKNOWN = (1 << 2), + /* .hdr_opt_len() and .write_hdr_opt() */ + BPF_TCP_OPS_FLAG_WRITE_HDR_OPT = (1 << 3), + /* .enqueue_rcvq() and .dequeue_rcvq() */ + BPF_TCP_OPS_FLAG_RCVQ = (1 << 4), + BPF_TCP_OPS_FLAG_ALL = (1 << 5) - 1, +}; + /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect * changes between the TCP and BPF versions. Ideally this should never happen. * If it does, we need to add code to convert them before calling @@ -7600,6 +7688,10 @@ struct bpf_task_work { __u64 __opaque; } __attribute__((aligned(8))); +struct bpf_rcu_head { + __u64 __opaque[6]; +} __attribute__((aligned(8))); + struct bpf_wq { __u64 __opaque[2]; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 618167cab4e6..11d65871d163 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -54,8 +54,8 @@ struct btf_type { * decl_tag and type_tag */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. - * "size" tells the size of the type it is describing. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC, ENUM64 + * and LOC_PARAM. "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. @@ -92,7 +92,9 @@ enum { BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ - + BTF_KIND_LOC_PARAM = 20, /* Location parameter information */ + BTF_KIND_LOC_PROTO = 21, /* Location prototype for site */ + BTF_KIND_LOCSEC = 22, /* Location section */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, }; @@ -212,4 +214,79 @@ struct btf_enum64 { __u32 val_hi32; }; +/* + * BTF_KIND_LOC_PARAM is followed by a single "struct btf_loc_param" + * that contains flags specifying the contents of the vlen-specified + * number of 4-byte values that follow. + */ +struct btf_loc_param { + __u32 flags; + __u32 values[]; +}; + +/* + * The combination of size, vlen and flags gives us the means to interpret + * the following vlen-specified set of 4-byte values: + * + * - a BTF_LOC_PARAM_CONST is a constant value; combination + * of size, vlen and _SIGNED flag determines it. If the value requires + * 64 bits it is stored in {lo,hi} order. + * - a BTF_LOC_PARAM_ADDR|BTF_LOC_PARAM_CONST is an address that should be + * normalized with respect to kernel/module base address. + * - a BTF_LOC_PARAM_REG with vlen 1 is a simple register number; + * with vlen 2 it is a multi-register parameter. Register numbers are + * numbers derived from DW_OP_reg values, i.e. 0 is DW_OP_reg0; since + * DW_OP_fbreg has its own special DW_OP_value and DW_OP_regx can refer + * to an arbitrary register number, we reserve BTF_LOC_PARAM_FBREG for + * the frame base register to avoid collisions. + * - a _REG | OFFSET describes an address without dereferencing it. + * - a _REG | DEREF with vlen 1 dereferences the value in the register + * number specified. + * - a REG | DEREF | OFFSET with vlen > 1 specifies the register number + * in the first 4-byte value and the offset in the remainder. + * In the case of REG and OFFSET combinations, the OFFSET has the width + * of the value words while the type size describes the represented parameter, + * so for example a REG | DEREF | OFFSET with size 8 and vlen 2 would be + * an 8-byte register dereference with signed 4-byte offset, since the vlen 2 + * values consist of a register value and the signed value. + */ +enum btf_loc_param_flags { + BTF_LOC_PARAM_SIGNED = 0x1, + BTF_LOC_PARAM_CONST = 0x2, + BTF_LOC_PARAM_ADDR = 0x4, + BTF_LOC_PARAM_REG = 0x8, + BTF_LOC_PARAM_DEREF = 0x10, + BTF_LOC_PARAM_OFFSET = 0x20, +}; + +enum { + BTF_LOC_PARAM_FBREG = 0xffffffff +}; + +/* + * BTF_KIND_LOC_PROTO specifies location prototypes; i.e. how locations relate + * to parameters; a struct btf_type of BTF_KIND_LOC_PROTO is followed by a + * vlen-specified number of __u32 BTF type ids which specify the associated + * BTF_KIND_LOC_PARAM for each function parameter associated with the + * location. The type should either be 0 (no location info) or point at + * a BTF_KIND_LOC_PARAM. + */ + +/* + * BTF_KIND_LOCSEC consists of vlen-specified number of "struct btf_loc" + * containing location site-specific information for a specific ELF section; + * for example locations in ".text" are in a LOCSEC named "inline.text". + * + * - function (func) + * - location prototype type id (loc_proto) + * - address offset (offset) relative to the runtime base address of the + * ELF section associated with the LOCSEC + */ + +struct btf_loc { + __u32 func; + __u32 loc_proto; + __u32 offset; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index cc3b9f7dccaf..47ee52859b45 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -230,7 +230,7 @@ * * Stored as an inline ref rather to avoid wasting space on a separate item on * top of the existing extent item. However, unlike the other inline refs, - * there is one one owner ref per extent rather than one per extent. + * there is one owner ref per extent rather than one per extent. * * Because of this, it goes at the front of the list of inline refs, and thus * must have a lower type value than any other inline ref type (to satisfy the @@ -243,7 +243,7 @@ #define BTRFS_EXTENT_DATA_REF_KEY 178 /* - * Obsolete key. Defintion removed in 6.6, value may be reused in the future. + * Obsolete key. Definition removed in 6.6, value may be reused in the future. * * #define BTRFS_EXTENT_REF_V0_KEY 180 */ @@ -1255,13 +1255,16 @@ static inline __u16 btrfs_qgroup_level(__u64 qgroupid) } /* - * is subvolume quota turned on? - */ -#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0) -/* - * RESCAN is set during the initialization phase + * The following BTRFS_QGROUP_STATUS_BIT_* are for * btrfs_qgroup_status_item::flags. + * + * Is subvolume quota turned on? */ -#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1) +#define BTRFS_QGROUP_STATUS_BIT_ON (0) +#define BTRFS_QGROUP_STATUS_FLAG_ON (1UL << BTRFS_QGROUP_STATUS_BIT_ON) + +/* RESCAN is set during the initialization phase */ +#define BTRFS_QGROUP_STATUS_BIT_RESCAN (1) +#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1UL << BTRFS_QGROUP_STATUS_BIT_RESCAN) /* * Some qgroup entries are known to be out of date, * either because the configuration has changed in a way that @@ -1269,14 +1272,16 @@ static inline __u16 btrfs_qgroup_level(__u64 qgroupid) * with a non-qgroup-aware version. * Turning qouta off and on again makes it inconsistent, too. */ -#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) +#define BTRFS_QGROUP_STATUS_BIT_INCONSISTENT (2) +#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1UL << BTRFS_QGROUP_STATUS_BIT_INCONSISTENT) /* * Whether or not this filesystem is using simple quotas. Not exactly the * incompat bit, because we support using simple quotas, disabling it, then * going back to full qgroup quotas. */ -#define BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE (1ULL << 3) +#define BTRFS_QGROUP_STATUS_BIT_SIMPLE_MODE (3) +#define BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE (1UL << BTRFS_QGROUP_STATUS_BIT_SIMPLE_MODE) #define BTRFS_QGROUP_STATUS_FLAGS_MASK (BTRFS_QGROUP_STATUS_FLAG_ON | \ BTRFS_QGROUP_STATUS_FLAG_RESCAN | \ diff --git a/include/uapi/linux/close_range.h b/include/uapi/linux/close_range.h index 2d804281554c..7da9ed95258a 100644 --- a/include/uapi/linux/close_range.h +++ b/include/uapi/linux/close_range.h @@ -2,11 +2,34 @@ #ifndef _UAPI_LINUX_CLOSE_RANGE_H #define _UAPI_LINUX_CLOSE_RANGE_H -/* Unshare the file descriptor table before closing file descriptors. */ -#define CLOSE_RANGE_UNSHARE (1U << 1) +/* + * A macro of one of these names defined before this header is parsed, by + * a libc or by a program's own fallback, would replace the enumerator. + */ +#undef CLOSE_RANGE_UNSHARE +#undef CLOSE_RANGE_CLOEXEC +#undef CLOSE_RANGE_EXCEPT +#undef CLOSE_RANGE_CLOEXEC_ONLY -/* Set the FD_CLOEXEC bit instead of closing the file descriptor. */ -#define CLOSE_RANGE_CLOEXEC (1U << 2) +enum close_range_flags { + /* Unshare the file descriptor table before closing file descriptors. */ + CLOSE_RANGE_UNSHARE = (1U << 1), + + /* Set the FD_CLOEXEC bit instead of closing the file descriptor. */ + CLOSE_RANGE_CLOEXEC = (1U << 2), + + /* Act on every file descriptor outside of the given range instead. */ + CLOSE_RANGE_EXCEPT = (1U << 3), + + /* Only close file descriptors that have the FD_CLOEXEC bit set. */ + CLOSE_RANGE_CLOEXEC_ONLY = (1U << 4), +}; + +/* Keep #ifdef working and let glibc skip its own definitions. */ +#define CLOSE_RANGE_UNSHARE CLOSE_RANGE_UNSHARE +#define CLOSE_RANGE_CLOEXEC CLOSE_RANGE_CLOEXEC +#define CLOSE_RANGE_EXCEPT CLOSE_RANGE_EXCEPT +#define CLOSE_RANGE_CLOEXEC_ONLY CLOSE_RANGE_CLOEXEC_ONLY #endif /* _UAPI_LINUX_CLOSE_RANGE_H */ diff --git a/include/uapi/linux/coredump.h b/include/uapi/linux/coredump.h index dc3789b78af0..6d0c53b534ea 100644 --- a/include/uapi/linux/coredump.h +++ b/include/uapi/linux/coredump.h @@ -11,12 +11,53 @@ * @COREDUMP_USERSPACE: userspace writes coredump * @COREDUMP_REJECT: don't generate coredump * @COREDUMP_WAIT: wait for coredump server + * @COREDUMP_RECORDS: send the coredump as a sequence of records instead of + * as a plain byte stream, see struct coredump_record_header; + * requires COREDUMP_KERNEL + * @COREDUMP_SPARSE: describe the holes in the coredump as zero records + * instead of transferring them; requires COREDUMP_RECORDS + * @COREDUMP_MEMORY_TYPES: dump the memory types in + * coredump_ack->memory_types instead of the ones + * the task selected; requires COREDUMP_KERNEL */ enum { COREDUMP_KERNEL = (1ULL << 0), COREDUMP_USERSPACE = (1ULL << 1), COREDUMP_REJECT = (1ULL << 2), COREDUMP_WAIT = (1ULL << 3), + COREDUMP_RECORDS = (1ULL << 4), + COREDUMP_SPARSE = (1ULL << 5), + COREDUMP_MEMORY_TYPES = (1ULL << 6), +}; + +/** + * coredump memory types + * @COREDUMP_MEMORY_ANON_PRIVATE: anonymous private memory + * @COREDUMP_MEMORY_ANON_SHARED: anonymous shared memory + * @COREDUMP_MEMORY_FILE_PRIVATE: file-backed private memory + * @COREDUMP_MEMORY_FILE_SHARED: file-backed shared memory + * @COREDUMP_MEMORY_ELF_HEADERS: the first page of a file-backed private + * mapping that starts an ELF file + * @COREDUMP_MEMORY_HUGETLB_PRIVATE: hugetlb private memory + * @COREDUMP_MEMORY_HUGETLB_SHARED: hugetlb shared memory + * @COREDUMP_MEMORY_DAX_PRIVATE: DAX private memory + * @COREDUMP_MEMORY_DAX_SHARED: DAX shared memory + * + * A bitmask of memory types a coredump may request to be included. New + * memory type bits must ensure that they do not steal memory from an + * existing one so a coredump server will continue to get the same + * coredumps even if a new bit is introduced. + */ +enum { + COREDUMP_MEMORY_ANON_PRIVATE = (1ULL << 0), + COREDUMP_MEMORY_ANON_SHARED = (1ULL << 1), + COREDUMP_MEMORY_FILE_PRIVATE = (1ULL << 2), + COREDUMP_MEMORY_FILE_SHARED = (1ULL << 3), + COREDUMP_MEMORY_ELF_HEADERS = (1ULL << 4), + COREDUMP_MEMORY_HUGETLB_PRIVATE = (1ULL << 5), + COREDUMP_MEMORY_HUGETLB_SHARED = (1ULL << 6), + COREDUMP_MEMORY_DAX_PRIVATE = (1ULL << 7), + COREDUMP_MEMORY_DAX_SHARED = (1ULL << 8), }; /** @@ -24,17 +65,19 @@ enum { * @size: size of struct coredump_req * @size_ack: known size of struct coredump_ack on this kernel * @mask: supported features + * @memory_types: the memory types the task selected + * @memory_types_mask: the memory types this kernel knows * * When a coredump happens the kernel will connect to the coredump * socket and send a coredump request to the coredump server. The @size * member is set to the size of struct coredump_req and provides a hint * to userspace how much data can be read. Userspace may use MSG_PEEK to * peek the size of struct coredump_req and then choose to consume it in - * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0 + * one go. Userspace may also simply read a COREDUMP_REQ_SIZE_VER0 * request. If the size the kernel sends is larger userspace simply * discards any remaining data. * - * The coredump_req->mask member is set to the currently know features. + * The coredump_req->mask member is set to the currently known features. * Userspace may only set coredump_ack->mask to the bits raised by the * kernel in coredump_req->mask. * @@ -42,15 +85,27 @@ enum { * struct coredump_ack the kernel knows. Userspace may only send up to * coredump_req->size_ack bytes to the kernel and must set * coredump_ack->size accordingly. + * + * @memory_types is set to the default memory types that are included in + * the coredump. This can be overridden by raising bits in + * coredump_ack->memory_types. + * + * @memory_types_mask contains a bitmask of all memory types the kernel + * knows about. A coredump server may only raise bits in + * coredump_ack->memory_types that are raised in + * coredump_req->memory_types_mask. */ struct coredump_req { __u32 size; __u32 size_ack; __u64 mask; + __u64 memory_types; + __u64 memory_types_mask; }; enum { COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */ + COREDUMP_REQ_SIZE_VER1 = 32U, /* memory_types and memory_types_mask added */ }; /** @@ -58,6 +113,8 @@ enum { * @size: size of the struct * @spare: unused * @mask: features kernel is supposed to use + * @memory_types: memory types to dump, only with COREDUMP_MEMORY_TYPES + * in @mask * * The @size member must be set to the size of struct coredump_ack. It * may never exceed what the kernel returned in coredump_req->size_ack @@ -67,15 +124,30 @@ enum { * The @mask member must be set to the features the coredump server * wants the kernel to use. Only bits the kernel returned in * coredump_req->mask may be set. + * + * If COREDUMP_MEMORY_TYPES is raised in @mask the kernel dumps the + * memory types set in the @memory_types mask. Zero is valid and dumps + * no memory apart from the mappings that are always dumped. + * + * Note that memory a task excluded via MADV_DONTDUMP |