- Linux-kselftest-mirror - lists.linaro.org

FAILED: patch "[PATCH] x86_64: Allow breakpoints to emulate call instructions" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4b33dadf37666c0860b88f9e52a16d07bf6d0b03 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra <peterz(a)infradead.org> Date: Wed, 1 May 2019 15:11:17 +0200 Subject: [PATCH] x86_64: Allow breakpoints to emulate call instructions In order to allow breakpoints to emulate call instructions, they need to push the return address onto the stack. The x86_64 int3 handler adds a small gap to allow the stack to grow some. Use this gap to add the return address to be able to emulate a call instruction at the breakpoint location. These helper functions are added: int3_emulate_jmp(): changes the location of the regs->ip to return there. (The next two are only for x86_64) int3_emulate_push(): to push the address onto the gap in the stack int3_emulate_call(): push the return address and change regs->ip Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Nicolai Stange <nstange(a)suse.de> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: the arch/x86 maintainers <x86(a)kernel.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Miroslav Benes <mbenes(a)suse.cz> Cc: Petr Mladek <pmladek(a)suse.com> Cc: Joe Lawrence <joe.lawrence(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: Nick Desaulniers <ndesaulniers(a)google.com> Cc: Nayna Jain <nayna(a)linux.ibm.com> Cc: Masahiro Yamada <yamada.masahiro(a)socionext.com> Cc: Joerg Roedel <jroedel(a)suse.de> Cc: "open list:KERNEL SELFTEST FRAMEWORK" <linux-kselftest(a)vger.kernel.org> Cc: stable(a)vger.kernel.org Fixes: b700e7f03df5 ("livepatch: kernel: add support for live patching") Tested-by: Nicolai Stange <nstange(a)suse.de> Reviewed-by: Nicolai Stange <nstange(a)suse.de> Reviewed-by: Masami Hiramatsu <mhiramat(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> [ Modified to only work for x86_64 and added comment to int3_emulate_push() ] Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index e85ff65c43c3..05861cc08787 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -39,4 +39,32 @@ extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); extern int after_bootmem; +static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + +#define INT3_INSN_SIZE 1 +#define CALL_INSN_SIZE 5 + +#ifdef CONFIG_X86_64 +static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) +{ + /* + * The int3 handler in entry_64.S adds a gap between the + * stack where the break point happened, and the saving of + * pt_regs. We can extend the original stack because of + * this gap. See the idtentry macro's create_gap option. + */ + regs->sp -= sizeof(unsigned long); + *(unsigned long *)regs->sp = val; +} + +static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func) +{ + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); + int3_emulate_jmp(regs, func); +} +#endif + #endif /* _ASM_X86_TEXT_PATCHING_H */

6 years, 5 months

1
0
0 0

[PATCH v2] KVM: selftests: Compile code with warnings enabled

by Thomas Huth

So far the KVM selftests are compiled without any compiler warnings enabled. That's quite bad, since we miss a lot of possible bugs this way. Let's enable at least "-Wall" and some other useful warning flags now, and fix at least the trivial problems in the code (like unused variables). Signed-off-by: Thomas Huth <thuth(a)redhat.com> --- v2: - Rebased to kvm/queue - Fix warnings in state_test.c and evmcs_test.c, too tools/testing/selftests/kvm/Makefile | 4 +++- tools/testing/selftests/kvm/dirty_log_test.c | 6 +++++- tools/testing/selftests/kvm/lib/kvm_util.c | 3 --- tools/testing/selftests/kvm/lib/x86_64/processor.c | 4 +--- tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c | 1 + tools/testing/selftests/kvm/x86_64/evmcs_test.c | 7 +------ tools/testing/selftests/kvm/x86_64/platform_info_test.c | 1 - tools/testing/selftests/kvm/x86_64/smm_test.c | 3 +-- tools/testing/selftests/kvm/x86_64/state_test.c | 7 +------ .../selftests/kvm/x86_64/vmx_close_while_nested_test.c | 5 +---- tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c | 5 ++--- 11 files changed, 16 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 79c524395ebe..d113eaf2d570 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,7 +34,9 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. +CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ + -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ + -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index a29d1119ccb3..ff20950aee05 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -131,6 +131,7 @@ static void *vcpu_worker(void *data) while (!READ_ONCE(host_quit)) { /* Let the guest dirty the random pages */ ret = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) { pages_count += TEST_PAGES_PER_LOOP; generate_random_array(guest_array, TEST_PAGES_PER_LOOP); @@ -423,8 +424,11 @@ int main(int argc, char *argv[]) unsigned long interval = TEST_HOST_LOOP_INTERVAL; bool mode_selected = false; uint64_t phys_offset = 0; - unsigned int mode, host_ipa_limit; + unsigned int mode; int opt, i; +#ifdef __aarch64__ + unsigned int host_ipa_limit; +#endif #ifdef USE_CLEAR_DIRTY_LOG if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) { diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index e9113857f44e..cf62de377310 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -135,7 +135,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm, unsigned long type) { struct kvm_vm *vm; - int kvm_fd; vm = calloc(1, sizeof(*vm)); TEST_ASSERT(vm != NULL, "Insufficient Memory"); @@ -556,7 +555,6 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, uint32_t flags) { int ret; - unsigned long pmem_size = 0; struct userspace_mem_region *region; size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size; @@ -1334,7 +1332,6 @@ void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index dc7fae9fa424..21f3040d90cb 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -229,8 +229,6 @@ void sregs_dump(FILE *stream, struct kvm_sregs *sregs, void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot) { - int rc; - TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -549,7 +547,6 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) struct pageDirectoryPointerEntry *pdpe; struct pageDirectoryEntry *pde; struct pageTableEntry *pte; - void *hva; TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -582,6 +579,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) unmapped_gva: TEST_ASSERT(false, "No mapping for vm virtual address, " "gva: 0x%lx", gva); + exit(EXIT_FAILURE); } static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot, diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 7c2c4d4055a8..63cc9c3f5ab6 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -87,6 +87,7 @@ int main(int argc, char *argv[]) while (1) { rc = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", run->exit_reason, diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 36669684eca5..b38260e29775 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -19,8 +19,6 @@ #define VCPU_ID 5 -static bool have_nested_state; - void l2_guest_code(void) { GUEST_SYNC(6); @@ -73,7 +71,6 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - struct vmx_pages *vmx_pages = NULL; vm_vaddr_t vmx_pages_gva = 0; struct kvm_regs regs1, regs2; @@ -88,8 +85,6 @@ int main(int argc, char *argv[]) .args[0] = (unsigned long)&evmcs_ver }; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); @@ -113,7 +108,7 @@ int main(int argc, char *argv[]) vcpu_regs_get(vm, VCPU_ID, &regs1); - vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (stage = 1;; stage++) { diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index eb3e7a838cb4..40050e44ec0a 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -81,7 +81,6 @@ static void test_msr_platform_info_disabled(struct kvm_vm *vm) int main(int argc, char *argv[]) { struct kvm_vm *vm; - struct kvm_run *state; int rv; uint64_t msr_platform_info; diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index fb8086964d83..4daf520bada1 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -87,7 +87,6 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - struct vmx_pages *vmx_pages = NULL; vm_vaddr_t vmx_pages_gva = 0; struct kvm_regs regs; @@ -115,7 +114,7 @@ int main(int argc, char *argv[]) vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); } else { printf("will skip SMM test with VMX enabled\n"); diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index e0a3c0204b7c..2a4121f4de01 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -22,8 +22,6 @@ #define VCPU_ID 5 -static bool have_nested_state; - void l2_guest_code(void) { GUEST_SYNC(6); @@ -122,7 +120,6 @@ void guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - struct vmx_pages *vmx_pages = NULL; vm_vaddr_t vmx_pages_gva = 0; struct kvm_regs regs1, regs2; @@ -132,8 +129,6 @@ int main(int argc, char *argv[]) struct ucall uc; int stage; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); @@ -142,7 +137,7 @@ int main(int argc, char *argv[]) vcpu_regs_get(vm, VCPU_ID, &regs1); if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); } else { printf("will skip nested state checks\n"); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 6edec6fd790b..97182b47b10c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -39,8 +39,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - uint32_t control; - uintptr_t save_cr3; GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_ASSERT(load_vmcs(vmx_pages)); @@ -55,7 +53,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { - struct vmx_pages *vmx_pages; vm_vaddr_t vmx_pages_gva; struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); @@ -68,7 +65,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ - vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (;;) { diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 18fa64db0d7a..6d37a3173956 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -121,7 +121,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } -void report(int64_t val) +static void report(int64_t val) { printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n", val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE); @@ -129,7 +129,6 @@ void report(int64_t val) int main(int argc, char *argv[]) { - struct vmx_pages *vmx_pages; vm_vaddr_t vmx_pages_gva; struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); @@ -142,7 +141,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ - vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (;;) { -- 2.21.0

6 years, 5 months

5
7
0 0

[PATCH v2 00/17] kunit: introduce KUnit, the Linux kernel unit testing framework

by Brendan Higgins

## TLDR I rebased the last patchset on 5.1-rc7 in hopes that we can get this in 5.2. Shuah, I think you, Greg KH, and myself talked off thread, and we agreed we would merge through your tree when the time came? Am I remembering correctly? ## Background This patch set proposes KUnit, a lightweight unit testing and mocking framework for the Linux kernel. Unlike Autotest and kselftest, KUnit is a true unit testing framework; it does not require installing the kernel on a test machine or in a VM and does not require tests to be written in userspace running on a host kernel. Additionally, KUnit is fast: From invocation to completion KUnit can run several dozen tests in under a second. Currently, the entire KUnit test suite for KUnit runs in under a second from the initial invocation (build time excluded). KUnit is heavily inspired by JUnit, Python's unittest.mock, and Googletest/Googlemock for C++. KUnit provides facilities for defining unit test cases, grouping related test cases into test suites, providing common infrastructure for running tests, mocking, spying, and much more. ## What's so special about unit testing? A unit test is supposed to test a single unit of code in isolation, hence the name. There should be no dependencies outside the control of the test; this means no external dependencies, which makes tests orders of magnitudes faster. Likewise, since there are no external dependencies, there are no hoops to jump through to run the tests. Additionally, this makes unit tests deterministic: a failing unit test always indicates a problem. Finally, because unit tests necessarily have finer granularity, they are able to test all code paths easily solving the classic problem of difficulty in exercising error handling code. ## Is KUnit trying to replace other testing frameworks for the kernel? No. Most existing tests for the Linux kernel are end-to-end tests, which have their place. A well tested system has lots of unit tests, a reasonable number of integration tests, and some end-to-end tests. KUnit is just trying to address the unit test space which is currently not being addressed. ## More information on KUnit There is a bunch of documentation near the end of this patch set that describes how to use KUnit and best practices for writing unit tests. For convenience I am hosting the compiled docs here: https://google.github.io/kunit-docs/third_party/kernel/docs/ Additionally for convenience, I have applied these patches to a branch: https://kunit.googlesource.com/linux/+/kunit/rfc/v5.1-rc7/v1 The repo may be cloned with: git clone https://kunit.googlesource.com/linux This patchset is on the kunit/rfc/v5.1-rc7/v1 branch. ## Changes Since Last Version None. I just rebased the last patchset on v5.1-rc7. -- 2.21.0.593.g511ec345e18-goog

6 years, 5 months

12
130
0 0

[PATCH AUTOSEL 4.19 009/244] selftests/bpf: set RLIMIT_MEMLOCK properly for test_libbpf_open.c

by Sasha Levin

From: Yonghong Song <yhs(a)fb.com> [ Upstream commit 6cea33701eb024bc6c920ab83940ee22afd29139 ] Test test_libbpf.sh failed on my development server with failure -bash-4.4$ sudo ./test_libbpf.sh [0] libbpf: Error in bpf_object__probe_name():Operation not permitted(1). Couldn't load basic 'r0 = 0' BPF program. test_libbpf: failed at file test_l4lb.o selftests: test_libbpf [FAILED] -bash-4.4$ The reason is because my machine has 64KB locked memory by default which is not enough for this program to get locked memory. Similar to other bpf selftests, let us increase RLIMIT_MEMLOCK to infinity, which fixed the issue. Signed-off-by: Yonghong Song <yhs(a)fb.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/test_libbpf_open.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c index 8fcd1c076add0..cbd55f5f8d598 100644 --- a/tools/testing/selftests/bpf/test_libbpf_open.c +++ b/tools/testing/selftests/bpf/test_libbpf_open.c @@ -11,6 +11,8 @@ static const char *__doc__ = #include <bpf/libbpf.h> #include <getopt.h> +#include "bpf_rlimit.h" + static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, {"debug", no_argument, NULL, 'D' }, -- 2.20.1

6 years, 5 months

1
0
0 0

[PATCH AUTOSEL 5.0 011/317] selftests/bpf: set RLIMIT_MEMLOCK properly for test_libbpf_open.c

by Sasha Levin

From: Yonghong Song <yhs(a)fb.com> [ Upstream commit 6cea33701eb024bc6c920ab83940ee22afd29139 ] Test test_libbpf.sh failed on my development server with failure -bash-4.4$ sudo ./test_libbpf.sh [0] libbpf: Error in bpf_object__probe_name():Operation not permitted(1). Couldn't load basic 'r0 = 0' BPF program. test_libbpf: failed at file test_l4lb.o selftests: test_libbpf [FAILED] -bash-4.4$ The reason is because my machine has 64KB locked memory by default which is not enough for this program to get locked memory. Similar to other bpf selftests, let us increase RLIMIT_MEMLOCK to infinity, which fixed the issue. Signed-off-by: Yonghong Song <yhs(a)fb.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/test_libbpf_open.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c index 8fcd1c076add0..cbd55f5f8d598 100644 --- a/tools/testing/selftests/bpf/test_libbpf_open.c +++ b/tools/testing/selftests/bpf/test_libbpf_open.c @@ -11,6 +11,8 @@ static const char *__doc__ = #include <bpf/libbpf.h> #include <getopt.h> +#include "bpf_rlimit.h" + static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, {"debug", no_argument, NULL, 'D' }, -- 2.20.1

6 years, 5 months

1
0
0 0

[PATCH AUTOSEL 5.1 015/375] selftests/bpf: set RLIMIT_MEMLOCK properly for test_libbpf_open.c

by Sasha Levin

From: Yonghong Song <yhs(a)fb.com> [ Upstream commit 6cea33701eb024bc6c920ab83940ee22afd29139 ] Test test_libbpf.sh failed on my development server with failure -bash-4.4$ sudo ./test_libbpf.sh [0] libbpf: Error in bpf_object__probe_name():Operation not permitted(1). Couldn't load basic 'r0 = 0' BPF program. test_libbpf: failed at file test_l4lb.o selftests: test_libbpf [FAILED] -bash-4.4$ The reason is because my machine has 64KB locked memory by default which is not enough for this program to get locked memory. Similar to other bpf selftests, let us increase RLIMIT_MEMLOCK to infinity, which fixed the issue. Signed-off-by: Yonghong Song <yhs(a)fb.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/test_libbpf_open.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c index 65cbd30704b5a..9e9db202d218a 100644 --- a/tools/testing/selftests/bpf/test_libbpf_open.c +++ b/tools/testing/selftests/bpf/test_libbpf_open.c @@ -11,6 +11,8 @@ static const char *__doc__ = #include <bpf/libbpf.h> #include <getopt.h> +#include "bpf_rlimit.h" + static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, {"debug", no_argument, NULL, 'D' }, -- 2.20.1

6 years, 5 months

1
0
0 0

[PATCH v3 0/3] Fix vDSO clock_getres()

by Vincenzo Frascino

clock_getres in the vDSO library has to preserve the same behaviour of posix_get_hrtimer_res(). In particular, posix_get_hrtimer_res() does: sec = 0; ns = hrtimer_resolution; and hrtimer_resolution depends on the enablement of the high resolution timers that can happen either at compile or at run time. A possible fix is to change the vdso implementation of clock_getres, keeping a copy of hrtimer_resolution in vdso data and using that directly [1]. This patchset implements the proposed fix for arm64, powerpc, s390, nds32 and adds a test to verify that the syscall and the vdso library implementation of clock_getres return the same values. Even if these patches are unified by the same topic, there is no dependency between them, hence they can be merged singularly by each arch maintainer. Note: arm64 and nds32 respective fixes have been merged in 5.2-rc1, hence they have been removed from this series. [1] https://marc.info/?l=linux-arm-kernel&m=155110381930196&w=2 Changes: -------- v3: - Rebased on 5.2-rc1. - Addressed review comments. v2: - Rebased on 5.1-rc5. - Addressed review comments. Cc: Christophe Leroy <christophe.leroy(a)c-s.fr> Cc: Benjamin Herrenschmidt <benh(a)kernel.crashing.org> Cc: Paul Mackerras <paulus(a)samba.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky(a)de.ibm.com> Cc: Heiko Carstens <heiko.carstens(a)de.ibm.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Vincenzo Frascino (3): powerpc: Fix vDSO clock_getres() s390: Fix vDSO clock_getres() kselftest: Extend vDSO selftest to clock_getres arch/powerpc/include/asm/vdso_datapage.h | 2 + arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/time.c | 1 + arch/powerpc/kernel/vdso32/gettimeofday.S | 7 +- arch/powerpc/kernel/vdso64/gettimeofday.S | 7 +- arch/s390/include/asm/vdso.h | 1 + arch/s390/kernel/asm-offsets.c | 2 +- arch/s390/kernel/time.c | 1 + arch/s390/kernel/vdso32/clock_getres.S | 12 +- arch/s390/kernel/vdso64/clock_getres.S | 10 +- tools/testing/selftests/vDSO/Makefile | 2 + .../selftests/vDSO/vdso_clock_getres.c | 137 ++++++++++++++++++ 12 files changed, 168 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/vDSO/vdso_clock_getres.c -- 2.21.0

6 years, 5 months

2
6
0 0

[PATCH v2] selftests: netfilter: missing error check when setting up veth interface

by Jeffrin Jose T

A test for the basic NAT functionality uses ip command which needs veth device.There is a condition where the kernel support for veth is not compiled into the kernel and the test script breaks.This patch contains code for reasonable error display and correct code exit. Signed-off-by: Jeffrin Jose T <jeffrin(a)rajagiritech.edu.in> --- tools/testing/selftests/netfilter/nft_nat.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..f25f72a75cf3 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -23,7 +23,11 @@ ip netns add ns0 ip netns add ns1 ip netns add ns2 -ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip +fi ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 ip -net ns0 link set lo up -- 2.20.1

6 years, 5 months

3
2
0 0

[PATCH v2 0/5] Fix vDSO clock_getres()

by Vincenzo Frascino

clock_getres in the vDSO library has to preserve the same behaviour of posix_get_hrtimer_res(). In particular, posix_get_hrtimer_res() does: sec = 0; ns = hrtimer_resolution; and hrtimer_resolution depends on the enablement of the high resolution timers that can happen either at compile or at run time. A possible fix is to change the vdso implementation of clock_getres, keeping a copy of hrtimer_resolution in vdso data and using that directly [1]. This patchset implements the proposed fix for arm64, powerpc, s390, nds32 and adds a test to verify that the syscall and the vdso library implementation of clock_getres return the same values. Even if these patches are unified by the same topic, there is no dependency between them, hence they can be merged singularly by each arch maintainer. [1] https://marc.info/?l=linux-arm-kernel&m=155110381930196&w=2 Changes: -------- v2: - Rebased on 5.1-rc5. - Addressed review comments. Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Benjamin Herrenschmidt <benh(a)kernel.crashing.org> Cc: Paul Mackerras <paulus(a)samba.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Martin Schwidefsky <schwidefsky(a)de.ibm.com> Cc: Heiko Carstens <heiko.carstens(a)de.ibm.com> Cc: Greentime Hu <green.hu(a)gmail.com> Cc: Vincent Chen <deanbo422(a)gmail.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Vincenzo Frascino (5): arm64: Fix vDSO clock_getres() powerpc: Fix vDSO clock_getres() s390: Fix vDSO clock_getres() nds32: Fix vDSO clock_getres() kselftest: Extend vDSO selftest to clock_getres arch/arm64/include/asm/vdso_datapage.h | 1 + arch/arm64/kernel/asm-offsets.c | 2 +- arch/arm64/kernel/vdso.c | 2 + arch/arm64/kernel/vdso/gettimeofday.S | 22 ++-- arch/nds32/include/asm/vdso_datapage.h | 1 + arch/nds32/kernel/vdso.c | 1 + arch/nds32/kernel/vdso/gettimeofday.c | 4 +- arch/powerpc/include/asm/vdso_datapage.h | 2 + arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/time.c | 1 + arch/powerpc/kernel/vdso32/gettimeofday.S | 7 +- arch/powerpc/kernel/vdso64/gettimeofday.S | 7 +- arch/s390/include/asm/vdso.h | 1 + arch/s390/kernel/asm-offsets.c | 2 +- arch/s390/kernel/time.c | 1 + arch/s390/kernel/vdso32/clock_getres.S | 12 +- arch/s390/kernel/vdso64/clock_getres.S | 10 +- tools/testing/selftests/vDSO/Makefile | 2 + .../selftests/vDSO/vdso_clock_getres.c | 108 ++++++++++++++++++ 19 files changed, 159 insertions(+), 29 deletions(-) create mode 100644 tools/testing/selftests/vDSO/vdso_clock_getres.c -- 2.21.0

6 years, 5 months

5
13
0 0

[PATCH 1/2] open: add close_range()

by Christian Brauner

This adds the close_range() syscall. It allows to efficiently close a range of file descriptors up to all file descriptors of a calling task. The syscall came up in a recent discussion around the new mount API and making new file descriptor types cloexec by default. During this discussion, Al suggested the close_range() syscall (cf. [1]). Note, a syscall in this manner has been requested by various people over time. First, it helps to close all file descriptors of an exec()ing task. This can be done safely via (quoting Al's example from [1] verbatim): /* that exec is sensitive */ unshare(CLONE_FILES); /* we don't want anything past stderr here */ close_range(3, ~0U); execve(....); The code snippet above is one way of working around the problem that file descriptors are not cloexec by default. This is aggravated by the fact that we can't just switch them over without massively regressing userspace. For a whole class of programs having an in-kernel method of closing all file descriptors is very helpful (e.g. demons, service managers, programming language standard libraries, container managers etc.). (Please note, unshare(CLONE_FILES) should only be needed if the calling task is multi-threaded and shares the file descriptor table with another thread in which case two threads could race with one thread allocating file descriptors and the other one closing them via close_range(). For the general case close_range() before the execve() is sufficient.) Second, it allows userspace to avoid implementing closing all file descriptors by parsing through /proc/<pid>/fd/* and calling close() on each file descriptor. From looking at various large(ish) userspace code bases this or similar patterns are very common in: - service managers (cf. [4]) - libcs (cf. [6]) - container runtimes (cf. [5]) - programming language runtimes/standard libraries - Python (cf. [2]) - Rust (cf. [7], [8]) As Dmitry pointed out there's even a long-standing glibc bug about missing kernel support for this task (cf. [3]). In addition, the syscall will also work for tasks that do not have procfs mounted and on kernels that do not have procfs support compiled in. In such situations the only way to make sure that all file descriptors are closed is to call close() on each file descriptor up to UINT_MAX or RLIMIT_NOFILE, OPEN_MAX trickery (cf. comment [8] on Rust). The performance is striking. For good measure, comparing the following simple close_all_fds() userspace implementation that is essentially just glibc's version in [6]: static int close_all_fds(void) { DIR *dir; struct dirent *direntp; dir = opendir("/proc/self/fd"); if (!dir) return -1; while ((direntp = readdir(dir))) { int fd; if (strcmp(direntp->d_name, ".") == 0) continue; if (strcmp(direntp->d_name, "..") == 0) continue; fd = atoi(direntp->d_name); if (fd == 0 || fd == 1 || fd == 2) continue; close(fd); } closedir(dir); /* cannot fail */ return 0; } to close_range() yields: 1. closing 4 open files: - close_all_fds(): ~280 us - close_range(): ~24 us 2. closing 1000 open files: - close_all_fds(): ~5000 us - close_range(): ~800 us close_range() is designed to allow for some flexibility. Specifically, it does not simply always close all open file descriptors of a task. Instead, callers can specify an upper bound. This is e.g. useful for scenarios where specific file descriptors are created with well-known numbers that are supposed to be excluded from getting closed. For extra paranoia close_range() comes with a flags argument. This can e.g. be used to implement extension. Once can imagine userspace wanting to stop at the first error instead of ignoring errors under certain circumstances. There might be other valid ideas in the future. In any case, a flag argument doesn't hurt and keeps us on the safe side. >From an implementation side this is kept rather dumb. It saw some input from David and Jann but all nonsense is obviously my own! - Errors to close file descriptors are currently ignored. (Could be changed by setting a flag in the future if needed.) - __close_range() is a rather simplistic wrapper around __close_fd(). My reasoning behind this is based on the nature of how __close_fd() needs to release an fd. But maybe I misunderstood specifics: We take the files_lock and rcu-dereference the fdtable of the calling task, we find the entry in the fdtable, get the file and need to release files_lock before calling filp_close(). In the meantime the fdtable might have been altered so we can't just retake the spinlock and keep the old rcu-reference of the fdtable around. Instead we need to grab a fresh reference to the fdtable. If my reasoning is correct then there's really no point in fancyfying __close_range(): We just need to rcu-dereference the fdtable of the calling task once to cap the max_fd value correctly and then go on calling __close_fd() in a loop. /* References */ [1]: https://lore.kernel.org/lkml/20190516165021.GD17978@ZenIV.linux.org.uk/ [2]: https://github.com/python/cpython/blob/9e4f2f3a6b8ee995c365e86d976937c141d8… [3]: https://sourceware.org/bugzilla/show_bug.cgi?id=10353#c7 [4]: https://github.com/systemd/systemd/blob/5238e9575906297608ff802a27e2ff9effa… [5]: https://github.com/lxc/lxc/blob/ddf4b77e11a4d08f09b7b9cd13e593f8c047edc5/sr… [6]: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/gr… Note that this is an internal implementation that is not exported. Currently, libc seems to not provide an exported version of this because of missing kernel support to do this. [7]: https://github.com/rust-lang/rust/issues/12148 [8]: https://github.com/rust-lang/rust/blob/5f47c0613ed4eb46fca3633c1297364c09e5… Rust's solution is slightly different but is equally unperformant. Rust calls getdtablesize() which is a glibc library function that simply returns the current RLIMIT_NOFILE or OPEN_MAX values. Rust then goes on to call close() on each fd. That's obviously overkill for most tasks. Rarely, tasks - especially non-demons - hit RLIMIT_NOFILE or OPEN_MAX. Let's be nice and assume an unprivileged user with RLIMIT_NOFILE set to 1024. Even in this case, there's a very high chance that in the common case Rust is calling the close() syscall 1021 times pointlessly if the task just has 0, 1, and 2 open. Suggested-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Christian Brauner <christian(a)brauner.io> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Jann Horn <jannh(a)google.com> Cc: David Howells <dhowells(a)redhat.com> Cc: Dmitry V. Levin <ldv(a)altlinux.org> Cc: Oleg Nesterov <oleg(a)redhat.com> Cc: Florian Weimer <fweimer(a)redhat.com> Cc: linux-api(a)vger.kernel.org --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + fs/file.c | 30 +++++++++++++++++++++ fs/open.c | 20 ++++++++++++++ include/linux/fdtable.h | 2 ++ include/linux/syscalls.h | 2 ++ include/uapi/asm-generic/unistd.h | 4 ++- 22 files changed, 75 insertions(+), 1 deletion(-) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 9e7704e44f6d..b55d93af8096 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -473,3 +473,4 @@ 541 common fsconfig sys_fsconfig 542 common fsmount sys_fsmount 543 common fspick sys_fspick +545 common close_range sys_close_range diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index aaf479a9e92d..0125c97c75dd 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -447,3 +447,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index c39e90600bb3..9a3270d29b42 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -886,6 +886,8 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_close_range 435 +__SYSCALL(__NR_close_range, sys_close_range) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index e01df3f2f80d..1a90b464e96f 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -354,3 +354,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7e3d0734b2f3..2dee2050f9ef 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -433,3 +433,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 26339e417695..923ef69e5a76 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0e2dd68ade57..967ed9de51cd 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -372,3 +372,4 @@ 431 n32 fsconfig sys_fsconfig 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick +435 n32 close_range sys_close_range diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 5eebfa0d155c..71de731102b1 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -348,3 +348,4 @@ 431 n64 fsconfig sys_fsconfig 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick +435 n64 close_range sys_close_range diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3cc1374e02d0..5a325ab29f88 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -421,3 +421,4 @@ 431 o32 fsconfig sys_fsconfig 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick +435 o32 close_range sys_close_range diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index c9e377d59232..dcc0a0879139 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -430,3 +430,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 103655d84b4b..ba2c1f078cbd 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -515,3 +515,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index e822b2964a83..d7c9043d2902 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig sys_fsconfig 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick +435 common close_range sys_close_range sys_close_range diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 016a727d4357..9b5e6bf0ce32 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -436,3 +436,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e047480b1605..8c674a1e0072 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -479,3 +479,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..7f7a89a96707 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -438,3 +438,4 @@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick +435 i386 close_range sys_close_range __ia32_sys_close_range diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..0f7d47ae921c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,7 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +435 common close_range __x64_sys_close_range # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 5fa0ee1c8e00..b489532265d0 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -404,3 +404,4 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +435 common close_range sys_close_range diff --git a/fs/file.c b/fs/file.c index 3da91a112bab..3680977a685a 100644 --- a/fs/file.c +++ b/fs/file.c @@ -641,6 +641,36 @@ int __close_fd(struct files_struct *files, unsigned fd) } EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ +/** + * __close_range() - Close all file descriptors in a given range. + * + * @fd: starting file descriptor to close + * @max_fd: last file descriptor to close + * + * This closes a range of file descriptors. All file descriptors + * from @fd up to and including @max_fd are closed. + */ +int __close_range(struct files_struct *files, unsigned fd, unsigned max_fd) +{ + unsigned int cur_max; + + if (fd > max_fd) + return -EINVAL; + + rcu_read_lock(); + cur_max = files_fdtable(files)->max_fds; + rcu_read_unlock(); + + /* cap to last valid index into fdtable */ + if (max_fd >= cur_max) + max_fd = cur_max - 1; + + while (fd <= max_fd) + __close_fd(files, fd++); + + return 0; +} + /* * variant of __close_fd that gets a ref on the file for later fput */ diff --git a/fs/open.c b/fs/open.c index 9c7d724a6f67..c7baaee7aa47 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1174,6 +1174,26 @@ SYSCALL_DEFINE1(close, unsigned int, fd) return retval; } +/** + * close_range() - Close all file descriptors in a given range. + * + * @fd: starting file descriptor to close + * @max_fd: last file descriptor to close + * @flags: reserved for future extensions + * + * This closes a range of file descriptors. All file descriptors + * from @fd up to and including @max_fd are closed. + * Currently, errors to close a given file descriptor are ignored. + */ +SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, + unsigned int, flags) +{ + if (flags) + return -EINVAL; + + return __close_range(current->files, fd, max_fd); +} + /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index f07c55ea0c22..fcd07181a365 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -121,6 +121,8 @@ extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); +extern int __close_range(struct files_struct *files, unsigned int fd, + unsigned int max_fd); extern int __close_fd_get_file(unsigned int fd, struct file **res); extern struct kmem_cache *files_cachep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e2870fe1be5b..c0189e223255 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -441,6 +441,8 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long sys_close(unsigned int fd); +asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd, + unsigned int flags); asmlinkage long sys_vhangup(void); /* fs/pipe.c */ diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a87904daf103..3f36c8745d24 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -844,9 +844,11 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_close_range 435 +__SYSCALL(__NR_close_range, sys_close_range) #undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 436 /* * 32 bit systems traditionally used different -- 2.21.0

6 years, 5 months

6
14
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror