March 2021 - Linux-kselftest-mirror

[PATCH] dma-mapping: benchmark: use the correct HiSilicon copyright

by Hao Fang

s/Hisilicon/HiSilicon/g. It should use capital S, according to https://www.hisilicon.com/en/terms-of-use. Signed-off-by: Hao Fang <fanghao11(a)huawei.com> --- kernel/dma/map_benchmark.c | 2 +- tools/testing/selftests/dma/dma_map_benchmark.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index e0e64f8..00d6549 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020 Hisilicon Limited. + * Copyright (C) 2020 HiSilicon Limited. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index fb23ce9..b492bed 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020 Hisilicon Limited. + * Copyright (C) 2020 HiSilicon Limited. */ #include <fcntl.h> -- 2.8.1

3 years

3
2
0 0

[PATCH] dma-mapping: benchmark: Add support for multi-pages map/unmap

by chenxiang

From: Xiang Chen <chenxiang66(a)hisilicon.com> Currently it only support one page map/unmap once a time for dma-map benchmark, but there are some other scenaries which need to support for multi-page map/unmap: for those multi-pages interfaces such as dma_alloc_coherent() and dma_map_sg(), the time spent on multi-pages map/unmap is not the time of a single page * npages (not linear) as it may use block description instead of page description when it is satified with the size such as 2M/1G, and also it can send a single TLB invalidation command to invalidate multi-pages instead of multi-times when RIL is enabled (which will short the time of unmap). So it is necessary to add support for multi-pages map/unmap. Add a parameter "-g" to support multi-pages map/unmap. Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> --- kernel/dma/map_benchmark.c | 21 ++++++++++++++------- tools/testing/selftests/dma/dma_map_benchmark.c | 20 ++++++++++++++++---- 2 files changed, 30 insertions(+), 11 deletions(-) diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index e0e64f8..a5c1b01 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -38,7 +38,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; struct map_benchmark_data { @@ -58,9 +59,11 @@ static int map_benchmark_thread(void *data) void *buf; dma_addr_t dma_addr; struct map_benchmark_data *map = data; + int npages = map->bparam.granule; + u64 size = npages * PAGE_SIZE; int ret = 0; - buf = (void *)__get_free_page(GFP_KERNEL); + buf = alloc_pages_exact(size, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data) * 66 means evertything goes well! 66 is lucky. */ if (map->dir != DMA_FROM_DEVICE) - memset(buf, 0x66, PAGE_SIZE); + memset(buf, 0x66, size); map_stime = ktime_get(); - dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir); + dma_addr = dma_map_single(map->dev, buf, size, map->dir); if (unlikely(dma_mapping_error(map->dev, dma_addr))) { pr_err("dma_map_single failed on %s\n", dev_name(map->dev)); @@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data) ndelay(map->bparam.dma_trans_ns); unmap_stime = ktime_get(); - dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir); + dma_unmap_single(map->dev, dma_addr, size, map->dir); unmap_etime = ktime_get(); unmap_delta = ktime_sub(unmap_etime, unmap_stime); @@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data) } out: - free_page((unsigned long)buf); + free_pages_exact(buf, size); return ret; } @@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, struct map_benchmark_data *map = file->private_data; void __user *argp = (void __user *)arg; u64 old_dma_mask; - int ret; if (copy_from_user(&map->bparam, argp, sizeof(map->bparam))) @@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, return -EINVAL; } + if (map->bparam.granule < 1 || map->bparam.granule > 1024) { + pr_err("invalid granule size\n"); + return -EINVAL; + } + switch (map->bparam.dma_dir) { case DMA_MAP_BIDIRECTIONAL: map->dir = DMA_BIDIRECTIONAL; diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index fb23ce9..6f2caa6 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -40,7 +40,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; int main(int argc, char **argv) @@ -51,11 +52,13 @@ int main(int argc, char **argv) int threads = 1, seconds = 20, node = -1; /* default dma mask 32bit, bidirectional DMA */ int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL; + /* default granule 1 PAGESIZE */ + int granule = 1; int cmd = DMA_MAP_BENCHMARK; char *p; - while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) { + while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) { switch (opt) { case 't': threads = atoi(optarg); @@ -75,6 +78,9 @@ int main(int argc, char **argv) case 'x': xdelay = atoi(optarg); break; + case 'g': + granule = atoi(optarg); + break; default: return -1; } @@ -110,6 +116,11 @@ int main(int argc, char **argv) exit(1); } + if (granule < 1 || granule > 1024) { + fprintf(stderr, "invalid granule size\n"); + exit(1); + } + fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR); if (fd == -1) { perror("open"); @@ -123,14 +134,15 @@ int main(int argc, char **argv) map.dma_bits = bits; map.dma_dir = dir; map.dma_trans_ns = xdelay; + map.granule = granule; if (ioctl(fd, cmd, &map)) { perror("ioctl"); exit(1); } - printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n", - threads, seconds, node, dir[directions]); + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n", + threads, seconds, node, dir[directions], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); printf("average unmap latency(us):%.1f standard deviation:%.1f\n", -- 2.8.1

3 years

3
2
0 0

[PATCH v31 00/12] Landlock LSM

by Mickaël Salaün

Hi, This updated patch series fixes minor issues in the filesystem handling, renames a function, improves documentation, and synchronizes syscall numbers with -next. The SLOC count is 1327 for security/landlock/ and 2590 for tools/testing/selftest/landlock/ . Test coverage for security/landlock/ is 93.6% of lines. The code not covered only deals with internal kernel errors (e.g. memory allocation) and race conditions. This series is being fuzzed by syzkaller (covering internal kernel errors) that now supports Landlock: https://github.com/google/syzkaller/pull/2380 The compiled documentation is available here: https://landlock.io/linux-doc/landlock-v31/userspace-api/landlock.html This series can be applied on top of v5.12-rc3 . This can be tested with CONFIG_SECURITY_LANDLOCK, CONFIG_SAMPLE_LANDLOCK and by prepending "landlock," to CONFIG_LSM. This patch series can be found in a Git repository here: https://github.com/landlock-lsm/linux/commits/landlock-v31 This patch series seems ready for upstream and I would really appreciate final reviews. Landlock LSM ------------ The goal of Landlock is to enable to restrict ambient rights (e.g. global filesystem access) for a set of processes. Because Landlock is a stackable LSM [1], it makes possible to create safe security sandboxes as new security layers in addition to the existing system-wide access-controls. This kind of sandbox is expected to help mitigate the security impact of bugs or unexpected/malicious behaviors in user-space applications. Landlock empowers any process, including unprivileged ones, to securely restrict themselves. Landlock is inspired by seccomp-bpf but instead of filtering syscalls and their raw arguments, a Landlock rule can restrict the use of kernel objects like file hierarchies, according to the kernel semantic. Landlock also takes inspiration from other OS sandbox mechanisms: XNU Sandbox, FreeBSD Capsicum or OpenBSD Pledge/Unveil. In this current form, Landlock misses some access-control features. This enables to minimize this patch series and ease review. This series still addresses multiple use cases, especially with the combined use of seccomp-bpf: applications with built-in sandboxing, init systems, security sandbox tools and security-oriented APIs [2]. [1] https://lore.kernel.org/lkml/50db058a-7dde-441b-a7f9-f6837fe8b69f@schaufler… [2] https://lore.kernel.org/lkml/f646e1c7-33cf-333f-070c-0a40ad0468cd@digikod.n… Previous versions: v30: https://lore.kernel.org/lkml/20210316204252.427806-1-mic@digikod.net/ v29: https://lore.kernel.org/lkml/20210225190614.2181147-1-mic@digikod.net/ v28: https://lore.kernel.org/lkml/20210202162710.657398-1-mic@digikod.net/ v27: https://lore.kernel.org/lkml/20210121205119.793296-1-mic@digikod.net/ v26: https://lore.kernel.org/lkml/20201209192839.1396820-1-mic@digikod.net/ v25: https://lore.kernel.org/lkml/20201201192322.213239-1-mic@digikod.net/ v24: https://lore.kernel.org/lkml/20201112205141.775752-1-mic@digikod.net/ v23: https://lore.kernel.org/lkml/20201103182109.1014179-1-mic@digikod.net/ v22: https://lore.kernel.org/lkml/20201027200358.557003-1-mic@digikod.net/ v21: https://lore.kernel.org/lkml/20201008153103.1155388-1-mic@digikod.net/ v20: https://lore.kernel.org/lkml/20200802215903.91936-1-mic@digikod.net/ v19: https://lore.kernel.org/lkml/20200707180955.53024-1-mic@digikod.net/ v18: https://lore.kernel.org/lkml/20200526205322.23465-1-mic@digikod.net/ v17: https://lore.kernel.org/lkml/20200511192156.1618284-1-mic@digikod.net/ v16: https://lore.kernel.org/lkml/20200416103955.145757-1-mic@digikod.net/ v15: https://lore.kernel.org/lkml/20200326202731.693608-1-mic@digikod.net/ v14: https://lore.kernel.org/lkml/20200224160215.4136-1-mic@digikod.net/ v13: https://lore.kernel.org/lkml/20191104172146.30797-1-mic@digikod.net/ v12: https://lore.kernel.org/lkml/20191031164445.29426-1-mic@digikod.net/ v11: https://lore.kernel.org/lkml/20191029171505.6650-1-mic@digikod.net/ v10: https://lore.kernel.org/lkml/20190721213116.23476-1-mic@digikod.net/ v9: https://lore.kernel.org/lkml/20190625215239.11136-1-mic@digikod.net/ v8: https://lore.kernel.org/lkml/20180227004121.3633-1-mic@digikod.net/ v7: https://lore.kernel.org/lkml/20170821000933.13024-1-mic@digikod.net/ v6: https://lore.kernel.org/lkml/20170328234650.19695-1-mic@digikod.net/ v5: https://lore.kernel.org/lkml/20170222012632.4196-1-mic@digikod.net/ v4: https://lore.kernel.org/lkml/20161026065654.19166-1-mic@digikod.net/ v3: https://lore.kernel.org/lkml/20160914072415.26021-1-mic@digikod.net/ v2: https://lore.kernel.org/lkml/1472121165-29071-1-git-send-email-mic@digikod.… v1: https://lore.kernel.org/kernel-hardening/1458784008-16277-1-git-send-email-… Casey Schaufler (1): LSM: Infrastructure management of the superblock Mickaël Salaün (11): landlock: Add object management landlock: Add ruleset and domain management landlock: Set up the security framework and manage credentials landlock: Add ptrace restrictions fs,security: Add sb_delete hook landlock: Support filesystem access-control landlock: Add syscall implementations arch: Wire up Landlock syscalls selftests/landlock: Add user space tests samples/landlock: Add a sandbox manager example landlock: Add user and kernel documentation Documentation/security/index.rst | 1 + Documentation/security/landlock.rst | 85 + Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/landlock.rst | 311 ++ MAINTAINERS | 15 + arch/Kconfig | 7 + arch/alpha/kernel/syscalls/syscall.tbl | 3 + arch/arm/tools/syscall.tbl | 3 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 6 + arch/ia64/kernel/syscalls/syscall.tbl | 3 + arch/m68k/kernel/syscalls/syscall.tbl | 3 + arch/microblaze/kernel/syscalls/syscall.tbl | 3 + arch/mips/kernel/syscalls/syscall_n32.tbl | 3 + arch/mips/kernel/syscalls/syscall_n64.tbl | 3 + arch/mips/kernel/syscalls/syscall_o32.tbl | 3 + arch/parisc/kernel/syscalls/syscall.tbl | 3 + arch/powerpc/kernel/syscalls/syscall.tbl | 3 + arch/s390/kernel/syscalls/syscall.tbl | 3 + arch/sh/kernel/syscalls/syscall.tbl | 3 + arch/sparc/kernel/syscalls/syscall.tbl | 3 + arch/um/Kconfig | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 3 + arch/x86/entry/syscalls/syscall_64.tbl | 3 + arch/xtensa/kernel/syscalls/syscall.tbl | 3 + fs/super.c | 1 + include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 4 + include/linux/security.h | 4 + include/linux/syscalls.h | 7 + include/uapi/asm-generic/unistd.h | 8 +- include/uapi/linux/landlock.h | 128 + kernel/sys_ni.c | 5 + samples/Kconfig | 7 + samples/Makefile | 1 + samples/landlock/.gitignore | 1 + samples/landlock/Makefile | 13 + samples/landlock/sandboxer.c | 238 ++ security/Kconfig | 11 +- security/Makefile | 2 + security/landlock/Kconfig | 21 + security/landlock/Makefile | 4 + security/landlock/common.h | 20 + security/landlock/cred.c | 46 + security/landlock/cred.h | 58 + security/landlock/fs.c | 693 ++++ security/landlock/fs.h | 70 + security/landlock/limits.h | 21 + security/landlock/object.c | 67 + security/landlock/object.h | 91 + security/landlock/ptrace.c | 120 + security/landlock/ptrace.h | 14 + security/landlock/ruleset.c | 473 +++ security/landlock/ruleset.h | 165 + security/landlock/setup.c | 40 + security/landlock/setup.h | 18 + security/landlock/syscalls.c | 445 +++ security/security.c | 51 +- security/selinux/hooks.c | 58 +- security/selinux/include/objsec.h | 6 + security/selinux/ss/services.c | 3 +- security/smack/smack.h | 6 + security/smack/smack_lsm.c | 35 +- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/landlock/.gitignore | 2 + tools/testing/selftests/landlock/Makefile | 24 + tools/testing/selftests/landlock/base_test.c | 219 ++ tools/testing/selftests/landlock/common.h | 183 ++ tools/testing/selftests/landlock/config | 7 + tools/testing/selftests/landlock/fs_test.c | 2792 +++++++++++++++++ .../testing/selftests/landlock/ptrace_test.c | 337 ++ tools/testing/selftests/landlock/true.c | 5 + 72 files changed, 6926 insertions(+), 77 deletions(-) create mode 100644 Documentation/security/landlock.rst create mode 100644 Documentation/userspace-api/landlock.rst create mode 100644 include/uapi/linux/landlock.h create mode 100644 samples/landlock/.gitignore create mode 100644 samples/landlock/Makefile create mode 100644 samples/landlock/sandboxer.c create mode 100644 security/landlock/Kconfig create mode 100644 security/landlock/Makefile create mode 100644 security/landlock/common.h create mode 100644 security/landlock/cred.c create mode 100644 security/landlock/cred.h create mode 100644 security/landlock/fs.c create mode 100644 security/landlock/fs.h create mode 100644 security/landlock/limits.h create mode 100644 security/landlock/object.c create mode 100644 security/landlock/object.h create mode 100644 security/landlock/ptrace.c create mode 100644 security/landlock/ptrace.h create mode 100644 security/landlock/ruleset.c create mode 100644 security/landlock/ruleset.h create mode 100644 security/landlock/setup.c create mode 100644 security/landlock/setup.h create mode 100644 security/landlock/syscalls.c create mode 100644 tools/testing/selftests/landlock/.gitignore create mode 100644 tools/testing/selftests/landlock/Makefile create mode 100644 tools/testing/selftests/landlock/base_test.c create mode 100644 tools/testing/selftests/landlock/common.h create mode 100644 tools/testing/selftests/landlock/config create mode 100644 tools/testing/selftests/landlock/fs_test.c create mode 100644 tools/testing/selftests/landlock/ptrace_test.c create mode 100644 tools/testing/selftests/landlock/true.c base-commit: 1e28eed17697bcf343c6743f0028cc3b5dd88bf0 -- 2.30.2

3 years

3
17
0 0

[PATCH 0/4] kvm: cpuid: fix cpuid nent field

by Emanuele Giuseppe Esposito

This series aims to clarify the behavior of KVM_GET_EMULATED_CPUID and KVM_GET_SUPPORTED ioctls, and fix a corner case where the nent field of the struct kvm_cpuid2 is matching the amount of entries that kvm returns. Patch 1 proposes the nent field fix to cpuid.c, patch 2 updates the ioctl documentation accordingly and patches 3 and 4 provide a selftest to check KVM_GET_EMULATED_CPUID accordingly. Emanuele Giuseppe Esposito (4): kvm: cpuid: adjust the returned nent field of kvm_cpuid2 for KVM_GET_SUPPORTED_CPUID and KVM_GET_EMULATED_CPUID Documentation: kvm: update KVM_GET_EMULATED_CPUID ioctl description selftests: add kvm_get_emulated_cpuid selftests: kvm: add get_emulated_cpuid test Documentation/virt/kvm/api.rst | 10 +- arch/x86/kvm/cpuid.c | 6 + tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 1 + .../selftests/kvm/lib/x86_64/processor.c | 33 ++++ .../selftests/kvm/x86_64/get_emulated_cpuid.c | 183 ++++++++++++++++++ 7 files changed, 229 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/get_emulated_cpuid.c -- 2.30.2

3 years

3
11
0 0

[PATCH 0/4] kvm: cpuid: fix cpuid nent field

by Emanuele Giuseppe Esposito

This series aims to clarify the behavior of KVM_GET_EMULATED_CPUID and KVM_GET_SUPPORTED ioctls, and fix a corner case where the nent field of the struct kvm_cpuid2 is matching the amount of entries that kvm returns. Patch 1 proposes the nent field fix to cpuid.c, patch 2 updates the ioctl documentation accordingly and patches 3 and 4 provide a selftest to check KVM_GET_EMULATED_CPUID accordingly. Signed-off-by: Emanuele Giuseppe Esposito <eesposit(a)redhat.com> --- v2: - better fix in cpuid.c, perform the nent check after the switch statement - fix bug in get_emulated_cpuid.c selftest, each entry needs to have at least the padding zeroed otherwise it fails. Emanuele Giuseppe Esposito (4): kvm: cpuid: adjust the returned nent field of kvm_cpuid2 for KVM_GET_SUPPORTED_CPUID and KVM_GET_EMULATED_CPUID Documentation: kvm: update KVM_GET_EMULATED_CPUID ioctl description selftests: add kvm_get_emulated_cpuid selftests: kvm: add get_emulated_cpuid test Documentation/virt/kvm/api.rst | 10 +- arch/x86/kvm/cpuid.c | 35 ++-- tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 1 + .../selftests/kvm/lib/x86_64/processor.c | 33 +++ .../selftests/kvm/x86_64/get_emulated_cpuid.c | 198 ++++++++++++++++++ 7 files changed, 256 insertions(+), 23 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/get_emulated_cpuid.c -- 2.30.2

3 years

2
6
0 0

[PATCH V5 00/10] PKS: Add Protection Key Supervisor support

by ira.weiny＠intel.com

From: Ira Weiny <ira.weiny(a)intel.com> Introduce a new page protection mechanism for supervisor pages, Protection Key Supervisor (PKS). Generally PKS enables protections on 'domains' of supervisor pages to limit supervisor mode access to pages beyond the normal paging protections. PKS works in a similar fashion to user space pkeys, PKU. As with PKU, supervisor pkeys are checked in addition to normal paging protections and Access or Writes can be disabled via a MSR update without TLB flushes when permissions change. Also like PKU, a page mapping is assigned to a domain by setting pkey bits in the page table entry for that mapping. Access is controlled through a PKRS register which is updated via WRMSR/RDMSR. XSAVE is not supported for the PKRS MSR. Therefore the implementation saves/restores the MSR across context switches and during exceptions. Nested exceptions are supported by each exception getting a new PKS state. For consistent behavior with current paging protections, pkey 0 is reserved and configured to allow full access via the pkey mechanism, thus preserving the default paging protections on mappings with the default pkey value of 0. Other keys, (1-15) are allocated by an allocator which prepares us for key contention from day one. Kernel users should be prepared for the allocator to fail either because of key exhaustion or due to PKS not being supported on the CPU instance. The following are key attributes of PKS. 1) Fast switching of permissions 1a) Prevents access without page table manipulations 1b) No TLB flushes required 2) Works on a per thread basis PKS is available with 4 and 5 level paging. Like PKRU it consumes 4 bits from the PTE to store the pkey within the entry. All code to support PKS is configured via ARCH_ENABLE_SUPERVISOR_PKEYS which is designed to only be turned on when a user is configured on in the kernel. Those users must depend on ARCH_HAS_SUPERVISOR_PKEYS to properly work with other architectures which do not yet support PKS. Originally this series was submitted as part of a large patch set which converted the kmap call sites.[1] Many follow on discussions revealed a few problems. The first of which was that some callers leak a kmap mapping across threads rather than containing it to a critical section. Attempts were made to see if these 'global kmaps' could be supported.[2] However, supporting global kmaps had many problems. Work is being done in parallel on converting as many kmap calls to the new kmap_local_page().[3] Changes from V4 [5] From kernel test robot <lkp(a)intel.com> Fix i386 build: pks_init_task not found Move MSR_IA32_PKRS and INIT_PKRS_VALUE into patch 5 where they are first 'used'. (Technically nothing is 'used' until the final test patch. But review wise this is much cleaner.) From Sean Christoperson Add documentation details on what happens if the pkey is violated Change cpu_feature_enabled to be in WARN_ON check Clean up commit message of patch 6 Fix some checkpatch errors [1] https://lore.kernel.org/lkml/20201009195033.3208459-1-ira.weiny@intel.com/ [2] https://lore.kernel.org/lkml/87mtycqcjf.fsf@nanos.tec.linutronix.de/ [3] https://lore.kernel.org/lkml/20210128061503.1496847-1-ira.weiny@intel.com/ https://lore.kernel.org/lkml/20210210062221.3023586-1-ira.weiny@intel.com/ https://lore.kernel.org/lkml/20210205170030.856723-1-ira.weiny@intel.com/ https://lore.kernel.org/lkml/20210217024826.3466046-1-ira.weiny@intel.com/ [4] https://lore.kernel.org/lkml/20201106232908.364581-1-ira.weiny@intel.com/ [5] https://lore.kernel.org/lkml/20210322053020.2287058-1-ira.weiny@intel.com/ Fenghua Yu (1): x86/pks: Add PKS kernel API Ira Weiny (9): x86/pkeys: Create pkeys_common.h x86/fpu: Refactor arch_set_user_pkey_access() for PKS support x86/pks: Add additional PKEY helper macros x86/pks: Add PKS defines and Kconfig options x86/pks: Add PKS setup code x86/fault: Adjust WARN_ON for PKey fault x86/pks: Preserve the PKRS MSR on context switch x86/entry: Preserve PKRS MSR across exceptions x86/pks: Add PKS test code Documentation/core-api/protection-keys.rst | 112 +++- arch/x86/Kconfig | 1 + arch/x86/entry/calling.h | 26 + arch/x86/entry/common.c | 58 ++ arch/x86/entry/entry_64.S | 22 +- arch/x86/entry/entry_64_compat.S | 6 +- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/disabled-features.h | 8 +- arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/pgtable.h | 10 +- arch/x86/include/asm/pgtable_types.h | 12 + arch/x86/include/asm/pkeys.h | 4 + arch/x86/include/asm/pkeys_common.h | 34 + arch/x86/include/asm/pks.h | 54 ++ arch/x86/include/asm/processor-flags.h | 2 + arch/x86/include/asm/processor.h | 47 +- arch/x86/include/uapi/asm/processor-flags.h | 2 + arch/x86/kernel/cpu/common.c | 2 + arch/x86/kernel/fpu/xstate.c | 22 +- arch/x86/kernel/head_64.S | 7 +- arch/x86/kernel/process.c | 3 + arch/x86/kernel/process_64.c | 2 + arch/x86/mm/fault.c | 31 +- arch/x86/mm/pkeys.c | 218 +++++- include/linux/pgtable.h | 4 + include/linux/pkeys.h | 34 + kernel/entry/common.c | 14 +- lib/Kconfig.debug | 11 + lib/Makefile | 3 + lib/pks/Makefile | 3 + lib/pks/pks_test.c | 693 ++++++++++++++++++++ mm/Kconfig | 5 + tools/testing/selftests/x86/Makefile | 3 +- tools/testing/selftests/x86/test_pks.c | 150 +++++ 34 files changed, 1528 insertions(+), 77 deletions(-) create mode 100644 arch/x86/include/asm/pkeys_common.h create mode 100644 arch/x86/include/asm/pks.h create mode 100644 lib/pks/Makefile create mode 100644 lib/pks/pks_test.c create mode 100644 tools/testing/selftests/x86/test_pks.c -- 2.28.0.rc0.12.gb6a658bd00c9

3 years

3
12
0 0

[PATCH v8 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

by Zi Yan

From: Zi Yan <ziy(a)nvidia.com> We did not have a direct user interface of splitting the compound page backing a THP and there is no need unless we want to expose the THP implementation details to users. Make <debugfs>/split_huge_pages accept a new command to do that. By writing "<pid>,<vaddr_start>,<vaddr_end>" to <debugfs>/split_huge_pages, THPs within the given virtual address range from the process with the given pid are split. It is used to test split_huge_page function. In addition, a selftest program is added to tools/testing/selftests/vm to utilize the interface by splitting PMD THPs and PTE-mapped THPs. This does not change the old behavior, i.e., writing 1 to the interface to split all THPs in the system. Changelog: >From v7: 1. Used the right way of looping through page cache pages. (the error was pointed out by Matthew Wilcox) >From v6: 1. pr_info -> pr_debug. 2. Added cond_resched() in all split loops. (suggested by David Rientjes) >From v5: 1. Skipped special VMAs and other fixes. (suggested by Yang Shi) >From v4: 1. Fixed the error code return issue, spotted by kernel test robot <lkp(a)intel.com>. >From v3: 1. Factored out split huge pages in the given pid code to a separate function. 2. Added the missing put_page for not split pages. 3. pr_debug -> pr_info, make reading results simpler. >From v2: 1. Reused existing <debugfs>/split_huge_pages interface. (suggested by Yang Shi) >From v1: 1. Removed unnecessary calling to vma_migratable, spotted by kernel test robot <lkp(a)intel.com>. 2. Dropped the use of find_mm_struct and code it directly, since there is no need for the permission check in that function and the function is only available when migration is on. 3. Added some comments in the selftest program to clarify how PTE-mapped THPs are formed. Signed-off-by: Zi Yan <ziy(a)nvidia.com> Reviewed-by: Yang Shi <shy828301(a)gmail.com> --- mm/huge_memory.c | 155 ++++++++- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + .../selftests/vm/split_huge_page_test.c | 318 ++++++++++++++++++ 4 files changed, 467 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8eba529a0f17..1bcab247aea8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> @@ -2927,16 +2928,14 @@ static struct shrinker deferred_split_shrinker = { }; #ifdef CONFIG_DEBUG_FS -static int split_huge_pages_set(void *data, u64 val) +static void split_huge_pages_all(void) { struct zone *zone; struct page *page; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; - if (val != 1) - return -EINVAL; - + pr_debug("Split all THPs\n"); for_each_populated_zone(zone) { max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { @@ -2960,15 +2959,155 @@ static int split_huge_pages_set(void *data, u64 val) unlock_page(page); next: put_page(page); + cond_resched(); } } - pr_info("%lu of %lu THP split\n", split, total); + pr_debug("%lu of %lu THP split\n", split, total); +} - return 0; +static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) +{ + return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || + is_vm_hugetlb_page(vma); +} + +static int split_huge_pages_pid(int pid, unsigned long vaddr_start, + unsigned long vaddr_end) +{ + int ret = 0; + struct task_struct *task; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + unsigned long addr; + + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; + + /* Find the task_struct from pid */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + ret = -ESRCH; + goto out; + } + get_task_struct(task); + rcu_read_unlock(); + + /* Find the mm_struct */ + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + ret = -EINVAL; + goto out; + } + + pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", + pid, vaddr_start, vaddr_end); + + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned int follflags; + struct page *page; + + if (!vma || addr < vma->vm_start) + break; + + /* skip special VMA and hugetlb VMA */ + if (vma_not_suitable_for_thp_split(vma)) { + addr = vma->vm_end; + continue; + } + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + if (IS_ERR(page)) + continue; + if (!page) + continue; + + if (!is_transparent_hugepage(page)) + goto next; + + total++; + if (!can_split_huge_page(compound_head(page), NULL)) + goto next; + + if (!trylock_page(page)) + goto next; + + if (!split_huge_page(page)) + split++; + + unlock_page(page); +next: + put_page(page); + cond_resched(); + } + mmap_read_unlock(mm); + mmput(mm); + + pr_debug("%lu of %lu THP split\n", split, total); + +out: + return ret; } -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, - "%llu\n"); + +#define MAX_INPUT_BUF_SZ 255 + +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppops) +{ + static DEFINE_MUTEX(split_debug_mutex); + ssize_t ret; + char input_buf[MAX_INPUT_BUF_SZ]; /* hold pid, start_vaddr, end_vaddr */ + int pid; + unsigned long vaddr_start, vaddr_end; + + ret = mutex_lock_interruptible(&split_debug_mutex); + if (ret) + return ret; + + ret = -EFAULT; + + memset(input_buf, 0, MAX_INPUT_BUF_SZ); + if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) + goto out; + + input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + if (ret == 1 && pid == 1) { + split_huge_pages_all(); + ret = strlen(input_buf); + goto out; + } else if (ret != 3) { + ret = -EINVAL; + goto out; + } + + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end); + if (!ret) + ret = strlen(input_buf); +out: + mutex_unlock(&split_debug_mutex); + return ret; + +} + +static const struct file_operations split_huge_pages_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_write, + .llseek = no_llseek, +}; static int __init split_huge_pages_debugfs(void) { diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index c8deddc81e7a..da92ded5a27c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -23,3 +23,4 @@ write_to_hugetlbfs hmm-tests memfd_secret local_config.* +split_huge_page_test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 38e25b90f8bf..266580ea938c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -43,6 +43,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += split_huge_page_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c new file mode 100644 index 000000000000..2c0c18e60c57 --- /dev/null +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual + * address range in a process via <debugfs>/split_huge_pages interface. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <inttypes.h> +#include <string.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <malloc.h> +#include <stdbool.h> + +uint64_t pagesize; +unsigned int pageshift; +uint64_t pmd_pagesize; + +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" +#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" +#define SMAP_PATH "/proc/self/smaps" +#define INPUT_MAX 80 + +#define PFN_MASK ((1UL<<55)-1) +#define KPF_THP (1UL<<22) + +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +{ + uint64_t paddr; + uint64_t page_flags; + + if (pagemap_file) { + pread(pagemap_file, &paddr, sizeof(paddr), + ((long)vaddr >> pageshift) * sizeof(paddr)); + + if (kpageflags_file) { + pread(kpageflags_file, &page_flags, sizeof(page_flags), + (paddr & PFN_MASK) * sizeof(page_flags)); + + return !!(page_flags & KPF_THP); + } + } + return 0; +} + + +static uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_PATH, O_RDONLY); + if (fd == -1) { + perror("Open hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + perror("Read hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +static int write_file(const char *path, const char *buf, size_t buflen) +{ + int fd; + ssize_t numwritten; + + fd = open(path, O_WRONLY); + if (fd == -1) + return 0; + + numwritten = write(fd, buf, buflen - 1); + close(fd); + if (numwritten < 1) + return 0; + + return (unsigned int) numwritten; +} + +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end) +{ + char input[INPUT_MAX]; + int ret; + + ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start, + vaddr_end); + if (ret >= INPUT_MAX) { + printf("%s: Debugfs input is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { + perror(SPLIT_DEBUGFS); + exit(EXIT_FAILURE); + } +} + +#define MAX_LINE_LENGTH 500 + +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) +{ + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +static uint64_t check_huge(void *addr) +{ + uint64_t thp = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) { + printf("%s: Pattern is too long\n", __func__); + exit(EXIT_FAILURE); + } + + + fp = fopen(SMAP_PATH, "r"); + if (!fp) { + printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); + exit(EXIT_FAILURE); + } + if (!check_for_pattern(fp, addr_pattern, buffer)) + goto err_out; + + /* + * Fetch the AnonHugePages: in the same block and check the number of + * hugepages. + */ + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) + goto err_out; + + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { + printf("Reading smap error\n"); + exit(EXIT_FAILURE); + } + +err_out: + fclose(fp); + return thp; +} + +void split_pmd_thp(void) +{ + char *one_page; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + + one_page = memalign(pmd_pagesize, len); + + if (!one_page) { + printf("Fail to allocate memory\n"); + exit(EXIT_FAILURE); + } + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocated\n"); + exit(EXIT_FAILURE); + } + + /* split all THPs */ + write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len); + + for (i = 0; i < len; i++) + if (one_page[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + + + thp_size = check_huge(one_page); + if (thp_size) { + printf("Still %ld kB AnonHugePages not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split huge pages successful\n"); + free(one_page); +} + +void split_pte_mapped_thp(void) +{ + char *one_page, *pte_mapped, *pte_mapped2; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + const char *pagemap_template = "/proc/%d/pagemap"; + const char *kpageflags_proc = "/proc/kpageflags"; + char pagemap_proc[255]; + int pagemap_fd; + int kpageflags_fd; + + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { + perror("get pagemap proc error"); + exit(EXIT_FAILURE); + } + pagemap_fd = open(pagemap_proc, O_RDONLY); + + if (pagemap_fd == -1) { + perror("read pagemap:"); + exit(EXIT_FAILURE); + } + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + + if (kpageflags_fd == -1) { + perror("read kpageflags:"); + exit(EXIT_FAILURE); + } + + one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocated\n"); + exit(EXIT_FAILURE); + } + + /* remap the first pagesize of first THP */ + pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); + + /* remap the Nth pagesize of Nth THP */ + for (i = 1; i < 4; i++) { + pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, + pagesize, pagesize, + MREMAP_MAYMOVE|MREMAP_FIXED, + pte_mapped + pagesize * i); + if (pte_mapped2 == (char *)-1) { + perror("mremap failed"); + exit(EXIT_FAILURE); + } + } + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + + if (thp_size != 4) { + printf("Some THPs are missing during mremap\n"); + exit(EXIT_FAILURE); + } + + /* split all remapped THPs */ + write_debugfs(getpid(), (uint64_t)pte_mapped, + (uint64_t)pte_mapped + pagesize * 4); + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) { + if (pte_mapped[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + } + + if (thp_size) { + printf("Still %ld THPs not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split PTE-mapped huge pages successful\n"); + munmap(one_page, len); + close(pagemap_fd); + close(kpageflags_fd); +} + +int main(int argc, char **argv) +{ + if (geteuid() != 0) { + printf("Please run the benchmark as root\n"); + exit(EXIT_FAILURE); + } + + pagesize = getpagesize(); + pageshift = ffs(pagesize) - 1; + pmd_pagesize = read_pmd_pagesize(); + + split_pmd_thp(); + split_pte_mapped_thp(); + + return 0; +} -- 2.30.2

3 years

1
1
0 0

[PATCH] memfd_secret: use unsigned int rather than long as syscall flags type

by Mike Rapoport

From: Mike Rapoport <rppt(a)linux.ibm.com> Yuri Norov says: If parameter size is the same for native and compat ABIs, we may wire a syscall made by compat client to native handler. This is true for unsigned int, but not true for unsigned long or pointer. That's why I suggest using unsigned int and so avoid creating compat entry point. Use unsigned int as the type of the flags parameter in memfd_secret() system call. Signed-off-by: Mike Rapoport <rppt(a)linux.ibm.com> --- @Andrew, The patch is vs v5.12-rc5-mmots-2021-03-30-23, I'd appreciate if it would be added as a fixup to the memfd_secret series. include/linux/syscalls.h | 2 +- mm/secretmem.c | 2 +- tools/testing/selftests/vm/memfd_secret.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 49c93c906893..1a1b5d724497 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1050,7 +1050,7 @@ asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr _ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type, const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); -asmlinkage long sys_memfd_secret(unsigned long flags); +asmlinkage long sys_memfd_secret(unsigned int flags); /* * Architecture-specific system calls diff --git a/mm/secretmem.c b/mm/secretmem.c index f2ae3f32a193..3b1ba3991964 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -199,7 +199,7 @@ static struct file *secretmem_file_create(unsigned long flags) return file; } -SYSCALL_DEFINE1(memfd_secret, unsigned long, flags) +SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) { struct file *file; int fd, err; diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c index c878c2b841fc..2462f52e9c96 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -38,7 +38,7 @@ static unsigned long page_size; static unsigned long mlock_limit_cur; static unsigned long mlock_limit_max; -static int memfd_secret(unsigned long flags) +static int memfd_secret(unsigned int flags) { return syscall(__NR_memfd_secret, flags); } -- 2.28.0

3 years

3
2
0 0

[PATCH] selftests/bpf: add LDFLAGS when building test_verifier

by Jisheng Zhang

From: Jisheng Zhang <jszhang(a)kernel.org> This is useful for cross compile process to point linker to the correct libelf, libcap, libz path. Signed-off-by: Jisheng Zhang <jszhang(a)kernel.org> --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 044bfdcf5b74..dac1c5094e28 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -447,7 +447,7 @@ verifier/tests.h: verifier/*.c ) > verifier/tests.h) $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) $(call msg,BINARY,,$@) - $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) -- 2.31.0

3 years

3
2
0 0

[PATCH v7 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

by Zi Yan

From: Zi Yan <ziy(a)nvidia.com> We did not have a direct user interface of splitting the compound page backing a THP and there is no need unless we want to expose the THP implementation details to users. Make <debugfs>/split_huge_pages accept a new command to do that. By writing "<pid>,<vaddr_start>,<vaddr_end>" to <debugfs>/split_huge_pages, THPs within the given virtual address range from the process with the given pid are split. It is used to test split_huge_page function. In addition, a selftest program is added to tools/testing/selftests/vm to utilize the interface by splitting PMD THPs and PTE-mapped THPs. This does not change the old behavior, i.e., writing 1 to the interface to split all THPs in the system. Changelog: >From v6: 1. pr_info -> pr_debug. 2. Added cond_resched() in all split loops. (suggested by David Rientjes) >From v5: 1. Skipped special VMAs and other fixes. (suggested by Yang Shi) >From v4: 1. Fixed the error code return issue, spotted by kernel test robot <lkp(a)intel.com>. >From v3: 1. Factored out split huge pages in the given pid code to a separate function. 2. Added the missing put_page for not split pages. 3. pr_debug -> pr_info, make reading results simpler. >From v2: 1. Reused existing <debugfs>/split_huge_pages interface. (suggested by Yang Shi) >From v1: 1. Removed unnecessary calling to vma_migratable, spotted by kernel test robot <lkp(a)intel.com>. 2. Dropped the use of find_mm_struct and code it directly, since there is no need for the permission check in that function and the function is only available when migration is on. 3. Added some comments in the selftest program to clarify how PTE-mapped THPs are formed. Signed-off-by: Zi Yan <ziy(a)nvidia.com> Reviewed-by: Yang Shi <shy828301(a)gmail.com> --- mm/huge_memory.c | 155 ++++++++- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + .../selftests/vm/split_huge_page_test.c | 318 ++++++++++++++++++ 4 files changed, 467 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8eba529a0f17..1bcab247aea8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> @@ -2927,16 +2928,14 @@ static struct shrinker deferred_split_shrinker = { }; #ifdef CONFIG_DEBUG_FS -static int split_huge_pages_set(void *data, u64 val) +static void split_huge_pages_all(void) { struct zone *zone; struct page *page; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; - if (val != 1) - return -EINVAL; - + pr_debug("Split all THPs\n"); for_each_populated_zone(zone) { max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { @@ -2960,15 +2959,155 @@ static int split_huge_pages_set(void *data, u64 val) unlock_page(page); next: put_page(page); + cond_resched(); } } - pr_info("%lu of %lu THP split\n", split, total); + pr_debug("%lu of %lu THP split\n", split, total); +} - return 0; +static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) +{ + return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || + is_vm_hugetlb_page(vma); +} + +static int split_huge_pages_pid(int pid, unsigned long vaddr_start, + unsigned long vaddr_end) +{ + int ret = 0; + struct task_struct *task; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + unsigned long addr; + + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; + + /* Find the task_struct from pid */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + ret = -ESRCH; + goto out; + } + get_task_struct(task); + rcu_read_unlock(); + + /* Find the mm_struct */ + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + ret = -EINVAL; + goto out; + } + + pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", + pid, vaddr_start, vaddr_end); + + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned int follflags; + struct page *page; + + if (!vma || addr < vma->vm_start) + break; + + /* skip special VMA and hugetlb VMA */ + if (vma_not_suitable_for_thp_split(vma)) { + addr = vma->vm_end; + continue; + } + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + if (IS_ERR(page)) + continue; + if (!page) + continue; + + if (!is_transparent_hugepage(page)) + goto next; + + total++; + if (!can_split_huge_page(compound_head(page), NULL)) + goto next; + + if (!trylock_page(page)) + goto next; + + if (!split_huge_page(page)) + split++; + + unlock_page(page); +next: + put_page(page); + cond_resched(); + } + mmap_read_unlock(mm); + mmput(mm); + + pr_debug("%lu of %lu THP split\n", split, total); + +out: + return ret; } -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, - "%llu\n"); + +#define MAX_INPUT_BUF_SZ 255 + +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppops) +{ + static DEFINE_MUTEX(split_debug_mutex); + ssize_t ret; + char input_buf[MAX_INPUT_BUF_SZ]; /* hold pid, start_vaddr, end_vaddr */ + int pid; + unsigned long vaddr_start, vaddr_end; + + ret = mutex_lock_interruptible(&split_debug_mutex); + if (ret) + return ret; + + ret = -EFAULT; + + memset(input_buf, 0, MAX_INPUT_BUF_SZ); + if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) + goto out; + + input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + if (ret == 1 && pid == 1) { + split_huge_pages_all(); + ret = strlen(input_buf); + goto out; + } else if (ret != 3) { + ret = -EINVAL; + goto out; + } + + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end); + if (!ret) + ret = strlen(input_buf); +out: + mutex_unlock(&split_debug_mutex); + return ret; + +} + +static const struct file_operations split_huge_pages_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_write, + .llseek = no_llseek, +}; static int __init split_huge_pages_debugfs(void) { diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index c8deddc81e7a..da92ded5a27c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -23,3 +23,4 @@ write_to_hugetlbfs hmm-tests memfd_secret local_config.* +split_huge_page_test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 38e25b90f8bf..266580ea938c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -43,6 +43,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += split_huge_page_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c new file mode 100644 index 000000000000..2c0c18e60c57 --- /dev/null +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual + * address range in a process via <debugfs>/split_huge_pages interface. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <inttypes.h> +#include <string.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <malloc.h> +#include <stdbool.h> + +uint64_t pagesize; +unsigned int pageshift; +uint64_t pmd_pagesize; + +#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" +#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" +#define SMAP_PATH "/proc/self/smaps" +#define INPUT_MAX 80 + +#define PFN_MASK ((1UL<<55)-1) +#define KPF_THP (1UL<<22) + +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +{ + uint64_t paddr; + uint64_t page_flags; + + if (pagemap_file) { + pread(pagemap_file, &paddr, sizeof(paddr), + ((long)vaddr >> pageshift) * sizeof(paddr)); + + if (kpageflags_file) { + pread(kpageflags_file, &page_flags, sizeof(page_flags), + (paddr & PFN_MASK) * sizeof(page_flags)); + + return !!(page_flags & KPF_THP); + } + } + return 0; +} + + +static uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_PATH, O_RDONLY); + if (fd == -1) { + perror("Open hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + perror("Read hpage_pmd_size failed"); + exit(EXIT_FAILURE); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +static int write_file(const char *path, const char *buf, size_t buflen) +{ + int fd; + ssize_t numwritten; + + fd = open(path, O_WRONLY); + if (fd == -1) + return 0; + + numwritten = write(fd, buf, buflen - 1); + close(fd); + if (numwritten < 1) + return 0; + + return (unsigned int) numwritten; +} + +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end) +{ + char input[INPUT_MAX]; + int ret; + + ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start, + vaddr_end); + if (ret >= INPUT_MAX) { + printf("%s: Debugfs input is too long\n", __func__); + exit(EXIT_FAILURE); + } + + if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) { + perror(SPLIT_DEBUGFS); + exit(EXIT_FAILURE); + } +} + +#define MAX_LINE_LENGTH 500 + +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) +{ + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +static uint64_t check_huge(void *addr) +{ + uint64_t thp = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) { + printf("%s: Pattern is too long\n", __func__); + exit(EXIT_FAILURE); + } + + + fp = fopen(SMAP_PATH, "r"); + if (!fp) { + printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); + exit(EXIT_FAILURE); + } + if (!check_for_pattern(fp, addr_pattern, buffer)) + goto err_out; + + /* + * Fetch the AnonHugePages: in the same block and check the number of + * hugepages. + */ + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) + goto err_out; + + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { + printf("Reading smap error\n"); + exit(EXIT_FAILURE); + } + +err_out: + fclose(fp); + return thp; +} + +void split_pmd_thp(void) +{ + char *one_page; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + + one_page = memalign(pmd_pagesize, len); + + if (!one_page) { + printf("Fail to allocate memory\n"); + exit(EXIT_FAILURE); + } + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocated\n"); + exit(EXIT_FAILURE); + } + + /* split all THPs */ + write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len); + + for (i = 0; i < len; i++) + if (one_page[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + + + thp_size = check_huge(one_page); + if (thp_size) { + printf("Still %ld kB AnonHugePages not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split huge pages successful\n"); + free(one_page); +} + +void split_pte_mapped_thp(void) +{ + char *one_page, *pte_mapped, *pte_mapped2; + size_t len = 4 * pmd_pagesize; + uint64_t thp_size; + size_t i; + const char *pagemap_template = "/proc/%d/pagemap"; + const char *kpageflags_proc = "/proc/kpageflags"; + char pagemap_proc[255]; + int pagemap_fd; + int kpageflags_fd; + + if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) { + perror("get pagemap proc error"); + exit(EXIT_FAILURE); + } + pagemap_fd = open(pagemap_proc, O_RDONLY); + + if (pagemap_fd == -1) { + perror("read pagemap:"); + exit(EXIT_FAILURE); + } + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + + if (kpageflags_fd == -1) { + perror("read kpageflags:"); + exit(EXIT_FAILURE); + } + + one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + + madvise(one_page, len, MADV_HUGEPAGE); + + for (i = 0; i < len; i++) + one_page[i] = (char)i; + + thp_size = check_huge(one_page); + if (!thp_size) { + printf("No THP is allocated\n"); + exit(EXIT_FAILURE); + } + + /* remap the first pagesize of first THP */ + pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE); + + /* remap the Nth pagesize of Nth THP */ + for (i = 1; i < 4; i++) { + pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i, + pagesize, pagesize, + MREMAP_MAYMOVE|MREMAP_FIXED, + pte_mapped + pagesize * i); + if (pte_mapped2 == (char *)-1) { + perror("mremap failed"); + exit(EXIT_FAILURE); + } + } + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + + if (thp_size != 4) { + printf("Some THPs are missing during mremap\n"); + exit(EXIT_FAILURE); + } + + /* split all remapped THPs */ + write_debugfs(getpid(), (uint64_t)pte_mapped, + (uint64_t)pte_mapped + pagesize * 4); + + /* smap does not show THPs after mremap, use kpageflags instead */ + thp_size = 0; + for (i = 0; i < pagesize * 4; i++) { + if (pte_mapped[i] != (char)i) { + printf("%ld byte corrupted\n", i); + exit(EXIT_FAILURE); + } + if (i % pagesize == 0 && + is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + thp_size++; + } + + if (thp_size) { + printf("Still %ld THPs not split\n", thp_size); + exit(EXIT_FAILURE); + } + + printf("Split PTE-mapped huge pages successful\n"); + munmap(one_page, len); + close(pagemap_fd); + close(kpageflags_fd); +} + +int main(int argc, char **argv) +{ + if (geteuid() != 0) { + printf("Please run the benchmark as root\n"); + exit(EXIT_FAILURE); + } + + pagesize = getpagesize(); + pageshift = ffs(pagesize) - 1; + pmd_pagesize = read_pmd_pagesize(); + + split_pmd_thp(); + split_pte_mapped_thp(); + + return 0; +} -- 2.30.2

3 years

3
3
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror March 2021