From e20194725bb25bb94c238fd9056108ea50a760c0 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Mon, 17 Jun 2024 19:24:20 -0700 Subject: selftests/mm: fix vm_util.c build failures: add snapshot of fs.h On Ubuntu 23.04, on a clean git tree, the selftests/mm build fails due 10 or 20 missing items, all of which are found in fs.h, which is created via "make headers". However, as per [1], the idea is to stop requiring "make headers", and instead, take a snapshot of the files and check them in. Here are a few of the build errors: vm_util.c:34:21: error: variable has incomplete type 'struct pm_scan_arg' struct pm_scan_arg arg; ... vm_util.c:45:28: error: use of undeclared identifier 'PAGE_IS_WPALLOWED' ... vm_util.c:55:21: error: variable has incomplete type 'struct page_region' ... vm_util.c:105:20: error: use of undeclared identifier 'PAGE_IS_SOFT_DIRTY' To fix this, add fs.h, taken from a snapshot of ./usr/include/linux/fs.h after running "make headers". [1] commit e076eaca5906 ("selftests: break the dependency upon local header files") Link: https://lkml.kernel.org/r/20240618022422.804305-5-jhubbard@nvidia.com Signed-off-by: John Hubbard Acked-by: David Hildenbrand Cc: Andrei Vagin Cc: Axel Rasmussen Cc: Christian Brauner Cc: Jeff Xu Cc: Kees Cook Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Muhammad Usama Anjum Cc: Peter Xu Cc: Rich Felker Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/include/uapi/linux/fs.h | 392 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 392 insertions(+) create mode 100644 tools/include/uapi/linux/fs.h (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h new file mode 100644 index 000000000000..cc3fea99fd43 --- /dev/null +++ b/tools/include/uapi/linux/fs.h @@ -0,0 +1,392 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_FS_H +#define _LINUX_FS_H + +/* + * This file has definitions for some important file table structures + * and constants and structures used by various generic file system + * ioctl's. Please do not make any changes in this file before + * sending patches for review to linux-fsdevel@vger.kernel.org and + * linux-api@vger.kernel.org. + */ + +#include +#include +#include +#include + +/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#include + +/* + * It's silly to have NR_OPEN bigger than NR_FILE, but you can change + * the file limit at runtime and only root can increase the per-process + * nr_file rlimit, so it's safe to set up a ridiculously high absolute + * upper limit on files-per-process. + * + * Some programs (notably those using select()) may have to be + * recompiled to take full advantage of the new limits.. + */ + +/* Fixed constants first: */ +#undef NR_OPEN +#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ +#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ + +#define BLOCK_SIZE_BITS 10 +#define BLOCK_SIZE (1< Date: Mon, 17 Jun 2024 19:24:21 -0700 Subject: selftests/mm: kvm, mdwe fixes to avoid requiring "make headers" On Ubuntu 23.04, the kvm and mdwe selftests/mm build fails due to missing a few items that are found in prctl.h. Here is an excerpt of the build failures: ksm_tests.c:252:13: error: use of undeclared identifier 'PR_SET_MEMORY_MERGE' ... mdwe_test.c:26:18: error: use of undeclared identifier 'PR_SET_MDWE' mdwe_test.c:38:18: error: use of undeclared identifier 'PR_GET_MDWE' Fix these errors by adding a new tools/include/uapi/linux/prctl.h . This file was created by running "make headers", and then copying a snapshot over from ./usr/include/linux/prctl.h, as per the approach we settled on in [1]. [1] commit e076eaca5906 ("selftests: break the dependency upon local header files") Link: https://lkml.kernel.org/r/20240618022422.804305-6-jhubbard@nvidia.com Signed-off-by: John Hubbard Acked-by: David Hildenbrand Cc: Andrei Vagin Cc: Axel Rasmussen Cc: Christian Brauner Cc: Jeff Xu Cc: Kees Cook Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Muhammad Usama Anjum Cc: Peter Xu Cc: Rich Felker Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/include/uapi/linux/prctl.h | 331 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 331 insertions(+) create mode 100644 tools/include/uapi/linux/prctl.h (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h new file mode 100644 index 000000000000..35791791a879 --- /dev/null +++ b/tools/include/uapi/linux/prctl.h @@ -0,0 +1,331 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_PRCTL_H +#define _LINUX_PRCTL_H + +#include + +/* Values to pass as first argument to prctl() */ + +#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */ +#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */ + +/* Get/set current->mm->dumpable */ +#define PR_GET_DUMPABLE 3 +#define PR_SET_DUMPABLE 4 + +/* Get/set unaligned access control bits (if meaningful) */ +#define PR_GET_UNALIGN 5 +#define PR_SET_UNALIGN 6 +# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */ +# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */ + +/* Get/set whether or not to drop capabilities on setuid() away from + * uid 0 (as per security/commoncap.c) */ +#define PR_GET_KEEPCAPS 7 +#define PR_SET_KEEPCAPS 8 + +/* Get/set floating-point emulation control bits (if meaningful) */ +#define PR_GET_FPEMU 9 +#define PR_SET_FPEMU 10 +# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */ +# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */ + +/* Get/set floating-point exception mode (if meaningful) */ +#define PR_GET_FPEXC 11 +#define PR_SET_FPEXC 12 +# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */ +# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */ +# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */ +# define PR_FP_EXC_UND 0x040000 /* floating point underflow */ +# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */ +# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */ +# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */ +# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */ +# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */ +# define PR_FP_EXC_PRECISE 3 /* precise exception mode */ + +/* Get/set whether we use statistical process timing or accurate timestamp + * based process timing */ +#define PR_GET_TIMING 13 +#define PR_SET_TIMING 14 +# define PR_TIMING_STATISTICAL 0 /* Normal, traditional, + statistical process timing */ +# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based + process timing */ + +#define PR_SET_NAME 15 /* Set process name */ +#define PR_GET_NAME 16 /* Get process name */ + +/* Get/set process endian */ +#define PR_GET_ENDIAN 19 +#define PR_SET_ENDIAN 20 +# define PR_ENDIAN_BIG 0 +# define PR_ENDIAN_LITTLE 1 /* True little endian mode */ +# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */ + +/* Get/set process seccomp mode */ +#define PR_GET_SECCOMP 21 +#define PR_SET_SECCOMP 22 + +/* Get/set the capability bounding set (as per security/commoncap.c) */ +#define PR_CAPBSET_READ 23 +#define PR_CAPBSET_DROP 24 + +/* Get/set the process' ability to use the timestamp counter instruction */ +#define PR_GET_TSC 25 +#define PR_SET_TSC 26 +# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */ +# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */ + +/* Get/set securebits (as per security/commoncap.c) */ +#define PR_GET_SECUREBITS 27 +#define PR_SET_SECUREBITS 28 + +/* + * Get/set the timerslack as used by poll/select/nanosleep + * A value of 0 means "use default" + */ +#define PR_SET_TIMERSLACK 29 +#define PR_GET_TIMERSLACK 30 + +#define PR_TASK_PERF_EVENTS_DISABLE 31 +#define PR_TASK_PERF_EVENTS_ENABLE 32 + +/* + * Set early/late kill mode for hwpoison memory corruption. + * This influences when the process gets killed on a memory corruption. + */ +#define PR_MCE_KILL 33 +# define PR_MCE_KILL_CLEAR 0 +# define PR_MCE_KILL_SET 1 + +# define PR_MCE_KILL_LATE 0 +# define PR_MCE_KILL_EARLY 1 +# define PR_MCE_KILL_DEFAULT 2 + +#define PR_MCE_KILL_GET 34 + +/* + * Tune up process memory map specifics. + */ +#define PR_SET_MM 35 +# define PR_SET_MM_START_CODE 1 +# define PR_SET_MM_END_CODE 2 +# define PR_SET_MM_START_DATA 3 +# define PR_SET_MM_END_DATA 4 +# define PR_SET_MM_START_STACK 5 +# define PR_SET_MM_START_BRK 6 +# define PR_SET_MM_BRK 7 +# define PR_SET_MM_ARG_START 8 +# define PR_SET_MM_ARG_END 9 +# define PR_SET_MM_ENV_START 10 +# define PR_SET_MM_ENV_END 11 +# define PR_SET_MM_AUXV 12 +# define PR_SET_MM_EXE_FILE 13 +# define PR_SET_MM_MAP 14 +# define PR_SET_MM_MAP_SIZE 15 + +/* + * This structure provides new memory descriptor + * map which mostly modifies /proc/pid/stat[m] + * output for a task. This mostly done in a + * sake of checkpoint/restore functionality. + */ +struct prctl_mm_map { + __u64 start_code; /* code section bounds */ + __u64 end_code; + __u64 start_data; /* data section bounds */ + __u64 end_data; + __u64 start_brk; /* heap for brk() syscall */ + __u64 brk; + __u64 start_stack; /* stack starts at */ + __u64 arg_start; /* command line arguments bounds */ + __u64 arg_end; + __u64 env_start; /* environment variables bounds */ + __u64 env_end; + __u64 *auxv; /* auxiliary vector */ + __u32 auxv_size; /* vector size */ + __u32 exe_fd; /* /proc/$pid/exe link file */ +}; + +/* + * Set specific pid that is allowed to ptrace the current task. + * A value of 0 mean "no process". + */ +#define PR_SET_PTRACER 0x59616d61 +# define PR_SET_PTRACER_ANY ((unsigned long)-1) + +#define PR_SET_CHILD_SUBREAPER 36 +#define PR_GET_CHILD_SUBREAPER 37 + +/* + * If no_new_privs is set, then operations that grant new privileges (i.e. + * execve) will either fail or not grant them. This affects suid/sgid, + * file capabilities, and LSMs. + * + * Operations that merely manipulate or drop existing privileges (setresuid, + * capset, etc.) will still work. Drop those privileges if you want them gone. + * + * Changing LSM security domain is considered a new privilege. So, for example, + * asking selinux for a specific new context (e.g. with runcon) will result + * in execve returning -EPERM. + * + * See Documentation/userspace-api/no_new_privs.rst for more details. + */ +#define PR_SET_NO_NEW_PRIVS 38 +#define PR_GET_NO_NEW_PRIVS 39 + +#define PR_GET_TID_ADDRESS 40 + +#define PR_SET_THP_DISABLE 41 +#define PR_GET_THP_DISABLE 42 + +/* + * No longer implemented, but left here to ensure the numbers stay reserved: + */ +#define PR_MPX_ENABLE_MANAGEMENT 43 +#define PR_MPX_DISABLE_MANAGEMENT 44 + +#define PR_SET_FP_MODE 45 +#define PR_GET_FP_MODE 46 +# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */ +# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */ + +/* Control the ambient capability set */ +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 + +/* arm64 Scalable Vector Extension controls */ +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ +#define PR_SVE_SET_VL 50 /* set task vector length */ +# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SVE_GET_VL 51 /* get task vector length */ +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ +# define PR_SVE_VL_LEN_MASK 0xffff +# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 +# define PR_SPEC_L1D_FLUSH 2 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) + +/* Reset arm64 pointer authentication keys */ +#define PR_PAC_RESET_KEYS 54 +# define PR_PAC_APIAKEY (1UL << 0) +# define PR_PAC_APIBKEY (1UL << 1) +# define PR_PAC_APDAKEY (1UL << 2) +# define PR_PAC_APDBKEY (1UL << 3) +# define PR_PAC_APGAKEY (1UL << 4) + +/* Tagged user address controls for arm64 */ +#define PR_SET_TAGGED_ADDR_CTRL 55 +#define PR_GET_TAGGED_ADDR_CTRL 56 +# define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* MTE tag check fault modes */ +# define PR_MTE_TCF_NONE 0UL +# define PR_MTE_TCF_SYNC (1UL << 1) +# define PR_MTE_TCF_ASYNC (1UL << 2) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) +/* MTE tag inclusion mask */ +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) +/* Unused; kept only for source compatibility */ +# define PR_MTE_TCF_SHIFT 1 + +/* Control reclaim behavior when allocating memory */ +#define PR_SET_IO_FLUSHER 57 +#define PR_GET_IO_FLUSHER 58 + +/* Dispatch syscalls to a userspace handler */ +#define PR_SET_SYSCALL_USER_DISPATCH 59 +# define PR_SYS_DISPATCH_OFF 0 +# define PR_SYS_DISPATCH_ON 1 +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 + +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + +/* Request the scheduler to share a core */ +#define PR_SCHED_CORE 62 +# define PR_SCHED_CORE_GET 0 +# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */ +# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ +# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ +# define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 + +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) + +#define PR_GET_MDWE 66 + +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + +#define PR_GET_AUXV 0x41555856 + +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 + +#define PR_RISCV_V_SET_CONTROL 69 +#define PR_RISCV_V_GET_CONTROL 70 +# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0 +# define PR_RISCV_V_VSTATE_CTRL_OFF 1 +# define PR_RISCV_V_VSTATE_CTRL_ON 2 +# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4) +# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3 +# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc +# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f + +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + +#endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From 77179b6f30811bf0bd2f62fcdf235997123e70dc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 27 Jun 2024 10:08:57 -0700 Subject: tools: sync uapi/linux/fs.h header into tools subdir We need this UAPI header in tools/include subdirectory for using it from BPF selftests. Link: https://lkml.kernel.org/r/20240627170900.1672542-6-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Liam R. Howlett Cc: Alexey Dobriyan Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Mike Rapoport (IBM) Cc: Suren Baghdasaryan Cc: Andi Kleen Cc: Arnd Bergmann Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- tools/include/uapi/linux/fs.h | 180 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 170 insertions(+), 10 deletions(-) (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index cc3fea99fd43..8a27bc5c7a7f 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_FS_H -#define _LINUX_FS_H +#ifndef _UAPI_LINUX_FS_H +#define _UAPI_LINUX_FS_H /* * This file has definitions for some important file table structures @@ -13,10 +13,14 @@ #include #include #include +#ifndef __KERNEL__ #include +#endif /* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#if !defined(__KERNEL__) #include +#endif /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -308,29 +312,31 @@ struct fsxattr { typedef int __bitwise __kernel_rwf_t; /* high priority request, poll if possible */ -#define RWF_HIPRI ((__kernel_rwf_t)0x00000001) +#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001) /* per-IO O_DSYNC */ -#define RWF_DSYNC ((__kernel_rwf_t)0x00000002) +#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002) /* per-IO O_SYNC */ -#define RWF_SYNC ((__kernel_rwf_t)0x00000004) +#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004) /* per-IO, return -EAGAIN if operation would block */ -#define RWF_NOWAIT ((__kernel_rwf_t)0x00000008) +#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008) /* per-IO O_APPEND */ -#define RWF_APPEND ((__kernel_rwf_t)0x00000010) +#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) /* per-IO negation of O_APPEND */ -#define RWF_NOAPPEND ((__kernel_rwf_t)0x00000020) +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND) +#define PROCFS_IOCTL_MAGIC 'f' + /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -389,4 +395,158 @@ struct pm_scan_arg { __u64 return_mask; }; -#endif /* _LINUX_FS_H */ +/* /proc//maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc//maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + +#endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3