From 93de2a6a4b91b72607136dd656edf03fb399d27f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Sep 2026 09:37:21 -0700 Subject: KVM: SEV: Do cache maintenance on the source VM during intra-host migration Manually perform cache maintenance on the source VM during intra-host migration to ensure no stale data is left in CPU caches after the VM is destroyed. Because the source VM is "converted" to a non-SEV VM, KVM's memory reclaim flows won't trigger cache maintenance, e.g. when all guest memory is reclaimed in response to detaching from the mmu_notifier. Note, relying on the destination VM to do cache maintenance isn't an option as KVM doesn't require identical guest memory configurations, i.e. the source VM may have access to memory that the destination VM does not. Enforcing equivalent memory configurations is infeasible, as it would require a *deep* comparison of memslots, e.g. to verify that not only are the memslot identical, but what the memslots point at is also identical. Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration") Cc: stable@vger.kernel.org Reported-by: Stefan Teodorescu Signed-off-by: Sean Christopherson Message-ID: <20260923163721.1584779-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- samples/seccomp/.gitignore | 5 + samples/seccomp/Makefile | 6 + samples/seccomp/bpf-direct.c | 191 ++++++++++++++++++++++ samples/seccomp/bpf-fancy.c | 105 ++++++++++++ samples/seccomp/bpf-helper.c | 96 +++++++++++ samples/seccomp/bpf-helper.h | 263 ++++++++++++++++++++++++++++++ samples/seccomp/dropper.c | 77 +++++++++ samples/seccomp/user-trap.c | 379 +++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 1122 insertions(+) create mode 100644 samples/seccomp/.gitignore create mode 100644 samples/seccomp/Makefile create mode 100644 samples/seccomp/bpf-direct.c create mode 100644 samples/seccomp/bpf-fancy.c create mode 100644 samples/seccomp/bpf-helper.c create mode 100644 samples/seccomp/bpf-helper.h create mode 100644 samples/seccomp/dropper.c create mode 100644 samples/seccomp/user-trap.c (limited to 'samples/seccomp') diff --git a/samples/seccomp/.gitignore b/samples/seccomp/.gitignore new file mode 100644 index 000000000..a6df0da77 --- /dev/null +++ b/samples/seccomp/.gitignore @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +/bpf-direct +/bpf-fancy +/dropper +/user-trap diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile new file mode 100644 index 000000000..c85ae0ed8 --- /dev/null +++ b/samples/seccomp/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +userprogs-always-y += bpf-fancy dropper bpf-direct user-trap + +bpf-fancy-objs := bpf-fancy.o bpf-helper.o + +userccflags += -I usr/include diff --git a/samples/seccomp/bpf-direct.c b/samples/seccomp/bpf-direct.c new file mode 100644 index 000000000..c09e4a17a --- /dev/null +++ b/samples/seccomp/bpf-direct.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Seccomp filter example for x86 (32-bit and 64-bit) with BPF macros + * + * Copyright (c) 2012 The Chromium OS Authors + * Author: Will Drewry + * + * The code may be used by anyone for any purpose, + * and can serve as a starting point for developing + * applications using prctl(PR_SET_SECCOMP, 2, ...). + */ +#if defined(__i386__) || defined(__x86_64__) +#define SUPPORTED_ARCH 1 +#endif + +#if defined(SUPPORTED_ARCH) +#define __USE_GNU 1 +#define _GNU_SOURCE 1 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n])) +#define syscall_nr (offsetof(struct seccomp_data, nr)) + +#if defined(__i386__) +#define REG_RESULT REG_EAX +#define REG_SYSCALL REG_EAX +#define REG_ARG0 REG_EBX +#define REG_ARG1 REG_ECX +#define REG_ARG2 REG_EDX +#define REG_ARG3 REG_ESI +#define REG_ARG4 REG_EDI +#define REG_ARG5 REG_EBP +#elif defined(__x86_64__) +#define REG_RESULT REG_RAX +#define REG_SYSCALL REG_RAX +#define REG_ARG0 REG_RDI +#define REG_ARG1 REG_RSI +#define REG_ARG2 REG_RDX +#define REG_ARG3 REG_R10 +#define REG_ARG4 REG_R8 +#define REG_ARG5 REG_R9 +#endif + +#ifndef PR_SET_NO_NEW_PRIVS +#define PR_SET_NO_NEW_PRIVS 38 +#endif + +#ifndef SYS_SECCOMP +#define SYS_SECCOMP 1 +#endif + +static void emulator(int nr, siginfo_t *info, void *void_context) +{ + ucontext_t *ctx = (ucontext_t *)(void_context); + int syscall; + char *buf; + ssize_t bytes; + size_t len; + if (info->si_code != SYS_SECCOMP) + return; + if (!ctx) + return; + syscall = ctx->uc_mcontext.gregs[REG_SYSCALL]; + buf = (char *) ctx->uc_mcontext.gregs[REG_ARG1]; + len = (size_t) ctx->uc_mcontext.gregs[REG_ARG2]; + + if (syscall != __NR_write) + return; + if (ctx->uc_mcontext.gregs[REG_ARG0] != STDERR_FILENO) + return; + /* Redirect stderr messages to stdout. Doesn't handle EINTR, etc */ + ctx->uc_mcontext.gregs[REG_RESULT] = -1; + if (write(STDOUT_FILENO, "[ERR] ", 6) > 0) { + bytes = write(STDOUT_FILENO, buf, len); + ctx->uc_mcontext.gregs[REG_RESULT] = bytes; + } + return; +} + +static int install_emulator(void) +{ + struct sigaction act; + sigset_t mask; + memset(&act, 0, sizeof(act)); + sigemptyset(&mask); + sigaddset(&mask, SIGSYS); + + act.sa_sigaction = &emulator; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGSYS, &act, NULL) < 0) { + perror("sigaction"); + return -1; + } + if (sigprocmask(SIG_UNBLOCK, &mask, NULL)) { + perror("sigprocmask"); + return -1; + } + return 0; +} + +static int install_filter(void) +{ + struct sock_filter filter[] = { + /* Grab the system call number */ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_nr), + /* Jump table for the allowed syscalls */ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_rt_sigreturn, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), +#ifdef __NR_sigreturn + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_sigreturn, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), +#endif + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit_group, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_read, 1, 0), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_write, 3, 2), + + /* Check that read is only using stdin. */ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDIN_FILENO, 4, 0), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL), + + /* Check that write is only using stdout */ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDOUT_FILENO, 1, 0), + /* Trap attempts to write to stderr */ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDERR_FILENO, 1, 2), + + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_TRAP), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL), + }; + struct sock_fprog prog = { + .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])), + .filter = filter, + }; + + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("prctl(NO_NEW_PRIVS)"); + return 1; + } + + + if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) { + perror("prctl"); + return 1; + } + return 0; +} + +#define payload(_c) (_c), sizeof((_c)) +int main(int argc, char **argv) +{ + char buf[4096]; + ssize_t bytes = 0; + if (install_emulator()) + return 1; + if (install_filter()) + return 1; + syscall(__NR_write, STDOUT_FILENO, + payload("OHAI! WHAT IS YOUR NAME? ")); + bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf)); + syscall(__NR_write, STDOUT_FILENO, payload("HELLO, ")); + syscall(__NR_write, STDOUT_FILENO, buf, bytes); + syscall(__NR_write, STDERR_FILENO, + payload("Error message going to STDERR\n")); + return 0; +} +#else /* SUPPORTED_ARCH */ +/* + * This sample is x86-only. Since kernel samples are compiled with the + * host toolchain, a non-x86 host will result in using only the main() + * below. + */ +int main(void) +{ + return 1; +} +#endif /* SUPPORTED_ARCH */ diff --git a/samples/seccomp/bpf-fancy.c b/samples/seccomp/bpf-fancy.c new file mode 100644 index 000000000..1ccb43502 --- /dev/null +++ b/samples/seccomp/bpf-fancy.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Seccomp BPF example using a macro-based generator. + * + * Copyright (c) 2012 The Chromium OS Authors + * Author: Will Drewry + * + * The code may be used by anyone for any purpose, + * and can serve as a starting point for developing + * applications using prctl(PR_ATTACH_SECCOMP_FILTER). + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "bpf-helper.h" + +#ifndef PR_SET_NO_NEW_PRIVS +#define PR_SET_NO_NEW_PRIVS 38 +#endif + +int main(int argc, char **argv) +{ + struct bpf_labels l = { + .count = 0, + }; + static const char msg1[] = "Please type something: "; + static const char msg2[] = "You typed: "; + char buf[256]; + struct sock_filter filter[] = { + /* TODO: LOAD_SYSCALL_NR(arch) and enforce an arch */ + LOAD_SYSCALL_NR, + SYSCALL(__NR_exit, ALLOW), + SYSCALL(__NR_exit_group, ALLOW), + SYSCALL(__NR_write, JUMP(&l, write_fd)), + SYSCALL(__NR_read, JUMP(&l, read)), + DENY, /* Don't passthrough into a label */ + + LABEL(&l, read), + ARG(0), + JNE(STDIN_FILENO, DENY), + ARG(1), + JNE((unsigned long)buf, DENY), + ARG(2), + JGE(sizeof(buf), DENY), + ALLOW, + + LABEL(&l, write_fd), + ARG(0), + JEQ(STDOUT_FILENO, JUMP(&l, write_buf)), + JEQ(STDERR_FILENO, JUMP(&l, write_buf)), + DENY, + + LABEL(&l, write_buf), + ARG(1), + JEQ((unsigned long)msg1, JUMP(&l, msg1_len)), + JEQ((unsigned long)msg2, JUMP(&l, msg2_len)), + JEQ((unsigned long)buf, JUMP(&l, buf_len)), + DENY, + + LABEL(&l, msg1_len), + ARG(2), + JLT(sizeof(msg1), ALLOW), + DENY, + + LABEL(&l, msg2_len), + ARG(2), + JLT(sizeof(msg2), ALLOW), + DENY, + + LABEL(&l, buf_len), + ARG(2), + JLT(sizeof(buf), ALLOW), + DENY, + }; + struct sock_fprog prog = { + .filter = filter, + .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])), + }; + ssize_t bytes; + bpf_resolve_jumps(&l, filter, sizeof(filter)/sizeof(*filter)); + + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("prctl(NO_NEW_PRIVS)"); + return 1; + } + + if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) { + perror("prctl(SECCOMP)"); + return 1; + } + syscall(__NR_write, STDOUT_FILENO, msg1, strlen(msg1)); + bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf)-1); + bytes = (bytes > 0 ? bytes : 0); + syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2)); + syscall(__NR_write, STDERR_FILENO, buf, bytes); + /* Now get killed */ + syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2)+2); + return 0; +} diff --git a/samples/seccomp/bpf-helper.c b/samples/seccomp/bpf-helper.c new file mode 100644 index 000000000..ae260d77a --- /dev/null +++ b/samples/seccomp/bpf-helper.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Seccomp BPF helper functions + * + * Copyright (c) 2012 The Chromium OS Authors + * Author: Will Drewry + * + * The code may be used by anyone for any purpose, + * and can serve as a starting point for developing + * applications using prctl(PR_ATTACH_SECCOMP_FILTER). + */ + +#include +#include +#include + +#include "bpf-helper.h" + +int bpf_resolve_jumps(struct bpf_labels *labels, + struct sock_filter *filter, size_t count) +{ + size_t i; + + if (count < 1 || count > BPF_MAXINSNS) + return -1; + /* + * Walk it once, backwards, to build the label table and do fixups. + * Since backward jumps are disallowed by BPF, this is easy. + */ + for (i = 0; i < count; ++i) { + size_t offset = count - i - 1; + struct sock_filter *instr = &filter[offset]; + if (instr->code != (BPF_JMP+BPF_JA)) + continue; + switch ((instr->jt<<8)|instr->jf) { + case (JUMP_JT<<8)|JUMP_JF: + if (labels->labels[instr->k].location == 0xffffffff) { + fprintf(stderr, "Unresolved label: '%s'\n", + labels->labels[instr->k].label); + return 1; + } + instr->k = labels->labels[instr->k].location - + (offset + 1); + instr->jt = 0; + instr->jf = 0; + continue; + case (LABEL_JT<<8)|LABEL_JF: + if (labels->labels[instr->k].location != 0xffffffff) { + fprintf(stderr, "Duplicate label use: '%s'\n", + labels->labels[instr->k].label); + return 1; + } + labels->labels[instr->k].location = offset; + instr->k = 0; /* fall through */ + instr->jt = 0; + instr->jf = 0; + continue; + } + } + return 0; +} + +/* Simple lookup table for labels. */ +__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label) +{ + struct __bpf_label *begin = labels->labels, *end; + int id; + + if (labels->count == BPF_LABELS_MAX) { + fprintf(stderr, "Too many labels\n"); + exit(1); + } + if (labels->count == 0) { + begin->label = label; + begin->location = 0xffffffff; + labels->count++; + return 0; + } + end = begin + labels->count; + for (id = 0; begin < end; ++begin, ++id) { + if (!strcmp(label, begin->label)) + return id; + } + begin->label = label; + begin->location = 0xffffffff; + labels->count++; + return id; +} + +void seccomp_bpf_print(struct sock_filter *filter, size_t count) +{ + struct sock_filter *end = filter + count; + for ( ; filter < end; ++filter) + printf("{ code=%u,jt=%u,jf=%u,k=%u },\n", + filter->code, filter->jt, filter->jf, filter->k); +} diff --git a/samples/seccomp/bpf-helper.h b/samples/seccomp/bpf-helper.h new file mode 100644 index 000000000..417e48a4c --- /dev/null +++ b/samples/seccomp/bpf-helper.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Example wrapper around BPF macros. + * + * Copyright (c) 2012 The Chromium OS Authors + * Author: Will Drewry + * + * The code may be used by anyone for any purpose, + * and can serve as a starting point for developing + * applications using prctl(PR_SET_SECCOMP, 2, ...). + * + * No guarantees are provided with respect to the correctness + * or functionality of this code. + */ +#ifndef __BPF_HELPER_H__ +#define __BPF_HELPER_H__ + +#include /* for __BITS_PER_LONG */ +#include +#include +#include /* for seccomp_data */ +#include +#include +#include + +#define BPF_LABELS_MAX 256 +struct bpf_labels { + int count; + struct __bpf_label { + const char *label; + __u32 location; + } labels[BPF_LABELS_MAX]; +}; + +int bpf_resolve_jumps(struct bpf_labels *labels, + struct sock_filter *filter, size_t count); +__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label); +void seccomp_bpf_print(struct sock_filter *filter, size_t count); + +#define JUMP_JT 0xff +#define JUMP_JF 0xff +#define LABEL_JT 0xfe +#define LABEL_JF 0xfe + +#define ALLOW \ + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW) +#define DENY \ + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL) +#define JUMP(labels, label) \ + BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \ + JUMP_JT, JUMP_JF) +#define LABEL(labels, label) \ + BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \ + LABEL_JT, LABEL_JF) +#define SYSCALL(nr, jt) \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (nr), 0, 1), \ + jt + +/* Lame, but just an example */ +#define FIND_LABEL(labels, label) seccomp_bpf_label((labels), #label) + +#define EXPAND(...) __VA_ARGS__ + +/* Ensure that we load the logically correct offset. */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32) +#else +#error "Unknown endianness" +#endif + +/* Map all width-sensitive operations */ +#if __BITS_PER_LONG == 32 + +#define JEQ(x, jt) JEQ32(x, EXPAND(jt)) +#define JNE(x, jt) JNE32(x, EXPAND(jt)) +#define JGT(x, jt) JGT32(x, EXPAND(jt)) +#define JLT(x, jt) JLT32(x, EXPAND(jt)) +#define JGE(x, jt) JGE32(x, EXPAND(jt)) +#define JLE(x, jt) JLE32(x, EXPAND(jt)) +#define JA(x, jt) JA32(x, EXPAND(jt)) +#define ARG(i) ARG_32(i) + +#elif __BITS_PER_LONG == 64 + +/* Ensure that we load the logically correct offset. */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define ENDIAN(_lo, _hi) _lo, _hi +#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define ENDIAN(_lo, _hi) _hi, _lo +#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) +#endif + +union arg64 { + struct { + __u32 ENDIAN(lo32, hi32); + }; + __u64 u64; +}; + +#define JEQ(x, jt) \ + JEQ64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define JGT(x, jt) \ + JGT64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define JGE(x, jt) \ + JGE64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define JNE(x, jt) \ + JNE64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define JLT(x, jt) \ + JLT64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define JLE(x, jt) \ + JLE64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) + +#define JA(x, jt) \ + JA64(((union arg64){.u64 = (x)}).lo32, \ + ((union arg64){.u64 = (x)}).hi32, \ + EXPAND(jt)) +#define ARG(i) ARG_64(i) + +#else +#error __BITS_PER_LONG value unusable. +#endif + +/* Loads the arg into A */ +#define ARG_32(idx) \ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)) + +/* Loads lo into M[0] and hi into M[1] and A */ +#define ARG_64(idx) \ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)), \ + BPF_STMT(BPF_ST, 0), /* lo -> M[0] */ \ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, HI_ARG(idx)), \ + BPF_STMT(BPF_ST, 1) /* hi -> M[1] */ + +#define JEQ32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 0, 1), \ + jt + +#define JNE32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 1, 0), \ + jt + +#define JA32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \ + jt + +#define JGE32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \ + jt + +#define JGT32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \ + jt + +#define JLE32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \ + jt + +#define JLT32(value, jt) \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \ + jt + +/* + * All the JXX64 checks assume lo is saved in M[0] and hi is saved in both + * A and M[1]. This invariant is kept by restoring A if necessary. + */ +#define JEQ64(lo, hi, jt) \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \ + /* if (lo != arg.lo) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JNE64(lo, hi, jt) \ + /* if (hi != arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo != arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JA64(lo, hi, jt) \ + /* if (hi & arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo & arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JGE64(lo, hi, jt) \ + /* if (hi > arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo >= arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JGT64(lo, hi, jt) \ + /* if (hi > arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo > arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JLE64(lo, hi, jt) \ + /* if (hi < arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo <= arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define JLT64(lo, hi, jt) \ + /* if (hi < arg.hi) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \ + /* if (hi != arg.hi) goto NOMATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \ + BPF_STMT(BPF_LD+BPF_MEM, 0), \ + /* if (lo < arg.lo) goto MATCH; */ \ + BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 2, 0), \ + BPF_STMT(BPF_LD+BPF_MEM, 1), \ + jt, \ + BPF_STMT(BPF_LD+BPF_MEM, 1) + +#define LOAD_SYSCALL_NR \ + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \ + offsetof(struct seccomp_data, nr)) + +#endif /* __BPF_HELPER_H__ */ diff --git a/samples/seccomp/dropper.c b/samples/seccomp/dropper.c new file mode 100644 index 000000000..4bca4b70f --- /dev/null +++ b/samples/seccomp/dropper.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Naive system call dropper built on seccomp_filter. + * + * Copyright (c) 2012 The Chromium OS Authors + * Author: Will Drewry + * + * The code may be used by anyone for any purpose, + * and can serve as a starting point for developing + * applications using prctl(PR_SET_SECCOMP, 2, ...). + * + * When run, returns the specified errno for the specified + * system call number against the given architecture. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int install_filter(int arch, int nr, int error) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, + (offsetof(struct seccomp_data, arch))), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, arch, 0, 3), + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, + (offsetof(struct seccomp_data, nr))), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1), + BPF_STMT(BPF_RET+BPF_K, + SECCOMP_RET_ERRNO|(error & SECCOMP_RET_DATA)), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])), + .filter = filter, + }; + if (error == -1) { + struct sock_filter kill = BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL); + filter[4] = kill; + } + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("prctl(NO_NEW_PRIVS)"); + return 1; + } + if (prctl(PR_SET_SECCOMP, 2, &prog)) { + perror("prctl(PR_SET_SECCOMP)"); + return 1; + } + return 0; +} + +int main(int argc, char **argv) +{ + if (argc < 5) { + fprintf(stderr, "Usage:\n" + "dropper []\n" + "Hint: AUDIT_ARCH_I386: 0x%X\n" + " AUDIT_ARCH_X86_64: 0x%X\n" + " errno == -1 means SECCOMP_RET_KILL\n" + "\n", AUDIT_ARCH_I386, AUDIT_ARCH_X86_64); + return 1; + } + if (install_filter(strtol(argv[1], NULL, 0), strtol(argv[2], NULL, 0), + strtol(argv[3], NULL, 0))) + return 1; + execv(argv[4], &argv[4]); + printf("Failed to execv\n"); + return 255; +} diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c new file mode 100644 index 000000000..a23fec357 --- /dev/null +++ b/samples/seccomp/user-trap.c @@ -0,0 +1,379 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + +static int seccomp(unsigned int op, unsigned int flags, void *args) +{ + errno = 0; + return syscall(__NR_seccomp, op, flags, args); +} + +static int send_fd(int sock, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int *fd_ptr; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + fd_ptr = (int *)CMSG_DATA(cmsg); + *fd_ptr = fd; + msg.msg_controllen = cmsg->cmsg_len; + + if (sendmsg(sock, &msg, 0) < 0) { + perror("sendmsg"); + return -1; + } + + return 0; +} + +static int recv_fd(int sock) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int *fd_ptr; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + + if (recvmsg(sock, &msg, 0) < 0) { + perror("recvmsg"); + return -1; + } + + cmsg = CMSG_FIRSTHDR(&msg); + fd_ptr = (int *)CMSG_DATA(cmsg); + + return *fd_ptr; +} + +static int user_trap_syscall(int nr, unsigned int flags) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); +} + +static int handle_req(struct seccomp_notif *req, + struct seccomp_notif_resp *resp, int listener) +{ + char path[PATH_MAX], source[PATH_MAX], target[PATH_MAX]; + int ret = -1, mem; + + resp->id = req->id; + resp->error = -EPERM; + resp->val = 0; + + if (req->data.nr != __NR_mount) { + fprintf(stderr, "huh? trapped something besides mount? %d\n", req->data.nr); + return -1; + } + + /* Only allow bind mounts. */ + if (!(req->data.args[3] & MS_BIND)) + return 0; + + /* + * Ok, let's read the task's memory to see where they wanted their + * mount to go. + */ + snprintf(path, sizeof(path), "/proc/%d/mem", req->pid); + mem = open(path, O_RDONLY); + if (mem < 0) { + perror("open mem"); + return -1; + } + + /* + * Now we avoid a TOCTOU: we referred to a pid by its pid, but since + * the pid that made the syscall may have died, we need to confirm that + * the pid is still valid after we open its /proc/pid/mem file. We can + * ask the listener fd this as follows. + * + * Note that this check should occur *after* any task-specific + * resources are opened, to make sure that the task has not died and + * we're not wrongly reading someone else's state in order to make + * decisions. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req->id) < 0) { + fprintf(stderr, "task died before we could map its memory\n"); + goto out; + } + + /* + * Phew, we've got the right /proc/pid/mem. Now we can read it. Note + * that to avoid another TOCTOU, we should read all of the pointer args + * before we decide to allow the syscall. + */ + if (lseek(mem, req->data.args[0], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, source, sizeof(source)); + if (ret < 0) { + perror("read"); + goto out; + } + + if (lseek(mem, req->data.args[1], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, target, sizeof(target)); + if (ret < 0) { + perror("read"); + goto out; + } + + /* + * Our policy is to only allow bind mounts inside /tmp. This isn't very + * interesting, because we could do unprivlieged bind mounts with user + * namespaces already, but you get the idea. + */ + if (!strncmp(source, "/tmp/", 5) && !strncmp(target, "/tmp/", 5)) { + if (mount(source, target, NULL, req->data.args[3], NULL) < 0) { + ret = -1; + perror("actual mount"); + goto out; + } + resp->error = 0; + } + + /* Even if we didn't allow it because of policy, generating the + * response was be a success, because we want to tell the worker EPERM. + */ + ret = 0; + +out: + close(mem); + return ret; +} + +int main(void) +{ + int sk_pair[2], ret = 1, status, listener; + pid_t worker = 0 , tracer = 0; + + if (socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair) < 0) { + perror("socketpair"); + return 1; + } + + worker = fork(); + if (worker < 0) { + perror("fork"); + goto close_pair; + } + + if (worker == 0) { + listener = user_trap_syscall(__NR_mount, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) { + perror("seccomp"); + exit(1); + } + + /* + * Drop privileges. We definitely can't mount as uid 1000. + */ + if (setuid(1000) < 0) { + perror("setuid"); + exit(1); + } + + /* + * Send the listener to the parent; also serves as + * synchronization. + */ + if (send_fd(sk_pair[1], listener) < 0) + exit(1); + close(listener); + + if (mkdir("/tmp/foo", 0755) < 0) { + perror("mkdir"); + exit(1); + } + + /* + * Try a bad mount just for grins. + */ + if (mount("/dev/sda", "/tmp/foo", NULL, 0, NULL) != -1) { + fprintf(stderr, "huh? mounted /dev/sda?\n"); + exit(1); + } + + if (errno != EPERM) { + perror("bad error from mount"); + exit(1); + } + + /* + * Ok, we expect this one to succeed. + */ + if (mount("/tmp/foo", "/tmp/foo", NULL, MS_BIND, NULL) < 0) { + perror("mount"); + exit(1); + } + + exit(0); + } + + /* + * Get the listener from the child. + */ + listener = recv_fd(sk_pair[0]); + if (listener < 0) + goto out_kill; + + /* + * Fork a task to handle the requests. This isn't strictly necessary, + * but it makes the particular writing of this sample easier, since we + * can just wait ofr the tracee to exit and kill the tracer. + */ + tracer = fork(); + if (tracer < 0) { + perror("fork"); + goto out_kill; + } + + if (tracer == 0) { + struct seccomp_notif *req; + struct seccomp_notif_resp *resp; + struct seccomp_notif_sizes sizes; + + if (seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes) < 0) { + perror("seccomp(GET_NOTIF_SIZES)"); + goto out_close; + } + + req = malloc(sizes.seccomp_notif); + if (!req) + goto out_close; + + resp = malloc(sizes.seccomp_notif_resp); + if (!resp) + goto out_req; + memset(resp, 0, sizes.seccomp_notif_resp); + + while (1) { + memset(req, 0, sizes.seccomp_notif); + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) { + perror("ioctl recv"); + goto out_resp; + } + + if (handle_req(req, resp, listener) < 0) + goto out_resp; + + /* + * ENOENT here means that the task may have gotten a + * signal and restarted the syscall. It's up to the + * handler to decide what to do in this case, but for + * the sample code, we just ignore it. Probably + * something better should happen, like undoing the + * mount, or keeping track of the args to make sure we + * don't do it again. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, resp) < 0 && + errno != ENOENT) { + perror("ioctl send"); + goto out_resp; + } + } +out_resp: + free(resp); +out_req: + free(req); +out_close: + close(listener); + exit(1); + } + + close(listener); + + if (waitpid(worker, &status, 0) != worker) { + perror("waitpid"); + goto out_kill; + } + + if (umount2("/tmp/foo", MNT_DETACH) < 0 && errno != EINVAL) { + perror("umount2"); + goto out_kill; + } + + if (remove("/tmp/foo") < 0 && errno != ENOENT) { + perror("remove"); + exit(1); + } + + if (!WIFEXITED(status) || WEXITSTATUS(status)) { + fprintf(stderr, "worker exited nonzero\n"); + goto out_kill; + } + + ret = 0; + +out_kill: + if (tracer > 0) + kill(tracer, SIGKILL); + if (worker > 0) + kill(worker, SIGKILL); + +close_pair: + close(sk_pair[0]); + close(sk_pair[1]); + return ret; +} -- cgit v1.3.1