From b7456536cf9466b402b540c5588d79a4177c723a Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:47:56 -0500 Subject: arch/x86: add syscall_get_arch to syscall.h Add syscall_get_arch() to export the current AUDIT_ARCH_* based on system call entry path. Signed-off-by: Will Drewry Acked-by: Serge Hallyn Reviewed-by: H. Peter Anvin Acked-by: Eric Paris Reviewed-by: Kees Cook v18: - update comment about x32 tasks - rebase to v3.4-rc2 v17: rebase and reviewed-by v14: rebase/nochanges v13: rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc Signed-off-by: James Morris --- arch/x86/include/asm/syscall.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 386b78686c4d..1ace47b62592 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -13,9 +13,11 @@ #ifndef _ASM_X86_SYSCALL_H #define _ASM_X86_SYSCALL_H +#include #include #include #include /* For NR_syscalls */ +#include /* for TS_COMPAT */ #include extern const unsigned long sys_call_table[]; @@ -88,6 +90,12 @@ static inline void syscall_set_arguments(struct task_struct *task, memcpy(®s->bx + i, args, n * sizeof(args[0])); } +static inline int syscall_get_arch(struct task_struct *task, + struct pt_regs *regs) +{ + return AUDIT_ARCH_I386; +} + #else /* CONFIG_X86_64 */ static inline void syscall_get_arguments(struct task_struct *task, @@ -212,6 +220,25 @@ static inline void syscall_set_arguments(struct task_struct *task, } } +static inline int syscall_get_arch(struct task_struct *task, + struct pt_regs *regs) +{ +#ifdef CONFIG_IA32_EMULATION + /* + * TS_COMPAT is set for 32-bit syscall entry and then + * remains set until we return to user mode. + * + * TIF_IA32 tasks should always have TS_COMPAT set at + * system call time. + * + * x32 tasks should be considered AUDIT_ARCH_X86_64. + */ + if (task_thread_info(task)->status & TS_COMPAT) + return AUDIT_ARCH_I386; +#endif + /* Both x32 and x86_64 are considered "64-bit". */ + return AUDIT_ARCH_X86_64; +} #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALL_H */ -- cgit v1.2.3 From e2cfabdfd075648216f99c2c03821cf3f47c1727 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:47:57 -0500 Subject: seccomp: add system call filtering using BPF [This patch depends on luto@mit.edu's no_new_privs patch: https://lkml.org/lkml/2012/1/30/264 The whole series including Andrew's patches can be found here: https://github.com/redpig/linux/tree/seccomp Complete diff here: https://github.com/redpig/linux/compare/1dc65fed...seccomp ] This patch adds support for seccomp mode 2. Mode 2 introduces the ability for unprivileged processes to install system call filtering policy expressed in terms of a Berkeley Packet Filter (BPF) program. This program will be evaluated in the kernel for each system call the task makes and computes a result based on data in the format of struct seccomp_data. A filter program may be installed by calling: struct sock_fprog fprog = { ... }; ... prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &fprog); The return value of the filter program determines if the system call is allowed to proceed or denied. If the first filter program installed allows prctl(2) calls, then the above call may be made repeatedly by a task to further reduce its access to the kernel. All attached programs must be evaluated before a system call will be allowed to proceed. Filter programs will be inherited across fork/clone and execve. However, if the task attaching the filter is unprivileged (!CAP_SYS_ADMIN) the no_new_privs bit will be set on the task. This ensures that unprivileged tasks cannot attach filters that affect privileged tasks (e.g., setuid binary). There are a number of benefits to this approach. A few of which are as follows: - BPF has been exposed to userland for a long time - BPF optimization (and JIT'ing) are well understood - Userland already knows its ABI: system call numbers and desired arguments - No time-of-check-time-of-use vulnerable data accesses are possible. - system call arguments are loaded on access only to minimize copying required for system call policy decisions. Mode 2 support is restricted to architectures that enable HAVE_ARCH_SECCOMP_FILTER. In this patch, the primary dependency is on syscall_get_arguments(). The full desired scope of this feature will add a few minor additional requirements expressed later in this series. Based on discussion, SECCOMP_RET_ERRNO and SECCOMP_RET_TRACE seem to be the desired additional functionality. No architectures are enabled in this patch. Signed-off-by: Will Drewry Acked-by: Serge Hallyn Reviewed-by: Indan Zupancic Acked-by: Eric Paris Reviewed-by: Kees Cook v18: - rebase to v3.4-rc2 - s/chk/check/ (akpm@linux-foundation.org,jmorris@namei.org) - allocate with GFP_KERNEL|__GFP_NOWARN (indan@nul.nu) - add a comment for get_u32 regarding endianness (akpm@) - fix other typos, style mistakes (akpm@) - added acked-by v17: - properly guard seccomp filter needed headers (leann@ubuntu.com) - tighten return mask to 0x7fff0000 v16: - no change v15: - add a 4 instr penalty when counting a path to account for seccomp_filter size (indan@nul.nu) - drop the max insns to 256KB (indan@nul.nu) - return ENOMEM if the max insns limit has been hit (indan@nul.nu) - move IP checks after args (indan@nul.nu) - drop !user_filter check (indan@nul.nu) - only allow explicit bpf codes (indan@nul.nu) - exit_code -> exit_sig v14: - put/get_seccomp_filter takes struct task_struct (indan@nul.nu,keescook@chromium.org) - adds seccomp_chk_filter and drops general bpf_run/chk_filter user - add seccomp_bpf_load for use by net/core/filter.c - lower max per-process/per-hierarchy: 1MB - moved nnp/capability check prior to allocation (all of the above: indan@nul.nu) v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: - added a maximum instruction count per path (indan@nul.nu,oleg@redhat.com) - removed copy_seccomp (keescook@chromium.org,indan@nul.nu) - reworded the prctl_set_seccomp comment (indan@nul.nu) v11: - reorder struct seccomp_data to allow future args expansion (hpa@zytor.com) - style clean up, @compat dropped, compat_sock_fprog32 (indan@nul.nu) - do_exit(SIGSYS) (keescook@chromium.org, luto@mit.edu) - pare down Kconfig doc reference. - extra comment clean up v10: - seccomp_data has changed again to be more aesthetically pleasing (hpa@zytor.com) - calling convention is noted in a new u32 field using syscall_get_arch. This allows for cross-calling convention tasks to use seccomp filters. (hpa@zytor.com) - lots of clean up (thanks, Indan!) v9: - n/a v8: - use bpf_chk_filter, bpf_run_filter. update load_fns - Lots of fixes courtesy of indan@nul.nu: -- fix up load behavior, compat fixups, and merge alloc code, -- renamed pc and dropped __packed, use bool compat. -- Added a hidden CONFIG_SECCOMP_FILTER to synthesize non-arch dependencies v7: (massive overhaul thanks to Indan, others) - added CONFIG_HAVE_ARCH_SECCOMP_FILTER - merged into seccomp.c - minimal seccomp_filter.h - no config option (part of seccomp) - no new prctl - doesn't break seccomp on systems without asm/syscall.h (works but arg access always fails) - dropped seccomp_init_task, extra free functions, ... - dropped the no-asm/syscall.h code paths - merges with network sk_run_filter and sk_chk_filter v6: - fix memory leak on attach compat check failure - require no_new_privs || CAP_SYS_ADMIN prior to filter installation. (luto@mit.edu) - s/seccomp_struct_/seccomp_/ for macros/functions (amwang@redhat.com) - cleaned up Kconfig (amwang@redhat.com) - on block, note if the call was compat (so the # means something) v5: - uses syscall_get_arguments (indan@nul.nu,oleg@redhat.com, mcgrathr@chromium.org) - uses union-based arg storage with hi/lo struct to handle endianness. Compromises between the two alternate proposals to minimize extra arg shuffling and account for endianness assuming userspace uses offsetof(). (mcgrathr@chromium.org, indan@nul.nu) - update Kconfig description - add include/seccomp_filter.h and add its installation - (naive) on-demand syscall argument loading - drop seccomp_t (eparis@redhat.com) v4: - adjusted prctl to make room for PR_[SG]ET_NO_NEW_PRIVS - now uses current->no_new_privs (luto@mit.edu,torvalds@linux-foundation.com) - assign names to seccomp modes (rdunlap@xenotime.net) - fix style issues (rdunlap@xenotime.net) - reworded Kconfig entry (rdunlap@xenotime.net) v3: - macros to inline (oleg@redhat.com) - init_task behavior fixed (oleg@redhat.com) - drop creator entry and extra NULL check (oleg@redhat.com) - alloc returns -EINVAL on bad sizing (serge.hallyn@canonical.com) - adds tentative use of "always_unprivileged" as per torvalds@linux-foundation.org and luto@mit.edu v2: - (patch 2 only) Signed-off-by: James Morris --- arch/Kconfig | 17 +++ include/linux/Kbuild | 1 + include/linux/seccomp.h | 76 +++++++++- kernel/fork.c | 3 + kernel/seccomp.c | 396 +++++++++++++++++++++++++++++++++++++++++++++--- kernel/sys.c | 2 +- 6 files changed, 472 insertions(+), 23 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 684eb5af439d..91c2c730fc1a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -216,4 +216,21 @@ config HAVE_CMPXCHG_DOUBLE config ARCH_WANT_OLD_COMPAT_IPC bool +config HAVE_ARCH_SECCOMP_FILTER + bool + help + This symbol should be selected by an architecure if it provides + asm/syscall.h, specifically syscall_get_arguments() and + syscall_get_arch(). + +config SECCOMP_FILTER + def_bool y + depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET + help + Enable tasks to build secure computing environments defined + in terms of Berkeley Packet Filter programs which implement + task-defined system call filtering polices. + + See Documentation/prctl/seccomp_filter.txt for details. + source "kernel/gcov/Kconfig" diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 3c9b616c834a..5c93d6c5d591 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -332,6 +332,7 @@ header-y += scc.h header-y += sched.h header-y += screen_info.h header-y += sdla.h +header-y += seccomp.h header-y += securebits.h header-y += selinux_netlink.h header-y += sem.h diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index d61f27fcaa97..86bb68fc7683 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -1,14 +1,67 @@ #ifndef _LINUX_SECCOMP_H #define _LINUX_SECCOMP_H +#include +#include + + +/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, ) */ +#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */ +#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */ +#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ + +/* + * All BPF programs must return a 32-bit value. + * The bottom 16-bits are reserved for future use. + * The upper 16-bits are ordered from least permissive values to most. + * + * The ordering ensures that a min_t() over composed return values always + * selects the least permissive choice. + */ +#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ + +/* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION 0x7fff0000U +#define SECCOMP_RET_DATA 0x0000ffffU + +/** + * struct seccomp_data - the format the BPF program executes over. + * @nr: the system call number + * @arch: indicates system call convention as an AUDIT_ARCH_* value + * as defined in . + * @instruction_pointer: at the time of the system call. + * @args: up to 6 system call arguments always stored as 64-bit values + * regardless of the architecture. + */ +struct seccomp_data { + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; +}; +#ifdef __KERNEL__ #ifdef CONFIG_SECCOMP #include #include +struct seccomp_filter; +/** + * struct seccomp - the state of a seccomp'ed process + * + * @mode: indicates one of the valid values above for controlled + * system calls available to a process. + * @filter: The metadata and ruleset for determining what system calls + * are allowed for a task. + * + * @filter must only be accessed from the context of current as there + * is no locking. + */ struct seccomp { int mode; + struct seccomp_filter *filter; }; extern void __secure_computing(int); @@ -19,7 +72,7 @@ static inline void secure_computing(int this_syscall) } extern long prctl_get_seccomp(void); -extern long prctl_set_seccomp(unsigned long); +extern long prctl_set_seccomp(unsigned long, char __user *); static inline int seccomp_mode(struct seccomp *s) { @@ -31,15 +84,16 @@ static inline int seccomp_mode(struct seccomp *s) #include struct seccomp { }; +struct seccomp_filter { }; -#define secure_computing(x) do { } while (0) +#define secure_computing(x) 0 static inline long prctl_get_seccomp(void) { return -EINVAL; } -static inline long prctl_set_seccomp(unsigned long arg2) +static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3) { return -EINVAL; } @@ -48,7 +102,21 @@ static inline int seccomp_mode(struct seccomp *s) { return 0; } - #endif /* CONFIG_SECCOMP */ +#ifdef CONFIG_SECCOMP_FILTER +extern void put_seccomp_filter(struct task_struct *tsk); +extern void get_seccomp_filter(struct task_struct *tsk); +extern u32 seccomp_bpf_load(int off); +#else /* CONFIG_SECCOMP_FILTER */ +static inline void put_seccomp_filter(struct task_struct *tsk) +{ + return; +} +static inline void get_seccomp_filter(struct task_struct *tsk) +{ + return; +} +#endif /* CONFIG_SECCOMP_FILTER */ +#endif /* __KERNEL__ */ #endif /* _LINUX_SECCOMP_H */ diff --git a/kernel/fork.c b/kernel/fork.c index b9372a0bff18..f7cf6fb107ec 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -170,6 +171,7 @@ void free_task(struct task_struct *tsk) free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); + put_seccomp_filter(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -1162,6 +1164,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto fork_out; ftrace_graph_init_task(p); + get_seccomp_filter(p); rt_mutex_init_task(p); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e8d76c5895ea..0aeec1960f91 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -3,16 +3,343 @@ * * Copyright 2004-2005 Andrea Arcangeli * - * This defines a simple but solid secure-computing mode. + * Copyright (C) 2012 Google, Inc. + * Will Drewry + * + * This defines a simple but solid secure-computing facility. + * + * Mode 1 uses a fixed list of allowed system calls. + * Mode 2 allows user-defined system call filters in the form + * of Berkeley Packet Filters/Linux Socket Filters. */ +#include #include -#include -#include #include +#include +#include /* #define SECCOMP_DEBUG 1 */ -#define NR_SECCOMP_MODES 1 + +#ifdef CONFIG_SECCOMP_FILTER +#include +#include +#include +#include +#include +#include + +/** + * struct seccomp_filter - container for seccomp BPF programs + * + * @usage: reference count to manage the object lifetime. + * get/put helpers should be used when accessing an instance + * outside of a lifetime-guarded section. In general, this + * is only needed for handling filters shared across tasks. + * @prev: points to a previously installed, or inherited, filter + * @len: the number of instructions in the program + * @insns: the BPF program instructions to evaluate + * + * seccomp_filter objects are organized in a tree linked via the @prev + * pointer. For any task, it appears to be a singly-linked list starting + * with current->seccomp.filter, the most recently attached or inherited filter. + * However, multiple filters may share a @prev node, by way of fork(), which + * results in a unidirectional tree existing in memory. This is similar to + * how namespaces work. + * + * seccomp_filter objects should never be modified after being attached + * to a task_struct (other than @usage). + */ +struct seccomp_filter { + atomic_t usage; + struct seccomp_filter *prev; + unsigned short len; /* Instruction count */ + struct sock_filter insns[]; +}; + +/* Limit any path through the tree to 256KB worth of instructions. */ +#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) + +static void seccomp_filter_log_failure(int syscall) +{ + int compat = 0; +#ifdef CONFIG_COMPAT + compat = is_compat_task(); +#endif + pr_info("%s[%d]: %ssystem call %d blocked at 0x%lx\n", + current->comm, task_pid_nr(current), + (compat ? "compat " : ""), + syscall, KSTK_EIP(current)); +} + +/** + * get_u32 - returns a u32 offset into data + * @data: a unsigned 64 bit value + * @index: 0 or 1 to return the first or second 32-bits + * + * This inline exists to hide the length of unsigned long. If a 32-bit + * unsigned long is passed in, it will be extended and the top 32-bits will be + * 0. If it is a 64-bit unsigned long, then whatever data is resident will be + * properly returned. + * + * Endianness is explicitly ignored and left for BPF program authors to manage + * as per the specific architecture. + */ +static inline u32 get_u32(u64 data, int index) +{ + return ((u32 *)&data)[index]; +} + +/* Helper for bpf_load below. */ +#define BPF_DATA(_name) offsetof(struct seccomp_data, _name) +/** + * bpf_load: checks and returns a pointer to the requested offset + * @off: offset into struct seccomp_data to load from + * + * Returns the requested 32-bits of data. + * seccomp_check_filter() should assure that @off is 32-bit aligned + * and not out of bounds. Failure to do so is a BUG. + */ +u32 seccomp_bpf_load(int off) +{ + struct pt_regs *regs = task_pt_regs(current); + if (off == BPF_DATA(nr)) + return syscall_get_nr(current, regs); + if (off == BPF_DATA(arch)) + return syscall_get_arch(current, regs); + if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) { + unsigned long value; + int arg = (off - BPF_DATA(args[0])) / sizeof(u64); + int index = !!(off % sizeof(u64)); + syscall_get_arguments(current, regs, arg, 1, &value); + return get_u32(value, index); + } + if (off == BPF_DATA(instruction_pointer)) + return get_u32(KSTK_EIP(current), 0); + if (off == BPF_DATA(instruction_pointer) + sizeof(u32)) + return get_u32(KSTK_EIP(current), 1); + /* seccomp_check_filter should make this impossible. */ + BUG(); +} + +/** + * seccomp_check_filter - verify seccomp filter code + * @filter: filter to verify + * @flen: length of filter + * + * Takes a previously checked filter (by sk_chk_filter) and + * redirects all filter code that loads struct sk_buff data + * and related data through seccomp_bpf_load. It also + * enforces length and alignment checking of those loads. + * + * Returns 0 if the rule set is legal or -EINVAL if not. + */ +static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) +{ + int pc; + for (pc = 0; pc < flen; pc++) { + struct sock_filter *ftest = &filter[pc]; + u16 code = ftest->code; + u32 k = ftest->k; + + switch (code) { + case BPF_S_LD_W_ABS: + ftest->code = BPF_S_ANC_SECCOMP_LD_W; + /* 32-bit aligned and not out of bounds. */ + if (k >= sizeof(struct seccomp_data) || k & 3) + return -EINVAL; + continue; + case BPF_S_LD_W_LEN: + ftest->code = BPF_S_LD_IMM; + ftest->k = sizeof(struct seccomp_data); + continue; + case BPF_S_LDX_W_LEN: + ftest->code = BPF_S_LDX_IMM; + ftest->k = sizeof(struct seccomp_data); + continue; + /* Explicitly include allowed calls. */ + case BPF_S_RET_K: + case BPF_S_RET_A: + case BPF_S_ALU_ADD_K: + case BPF_S_ALU_ADD_X: + case BPF_S_ALU_SUB_K: + case BPF_S_ALU_SUB_X: + case BPF_S_ALU_MUL_K: + case BPF_S_ALU_MUL_X: + case BPF_S_ALU_DIV_X: + case BPF_S_ALU_AND_K: + case BPF_S_ALU_AND_X: + case BPF_S_ALU_OR_K: + case BPF_S_ALU_OR_X: + case BPF_S_ALU_LSH_K: + case BPF_S_ALU_LSH_X: + case BPF_S_ALU_RSH_K: + case BPF_S_ALU_RSH_X: + case BPF_S_ALU_NEG: + case BPF_S_LD_IMM: + case BPF_S_LDX_IMM: + case BPF_S_MISC_TAX: + case BPF_S_MISC_TXA: + case BPF_S_ALU_DIV_K: + case BPF_S_LD_MEM: + case BPF_S_LDX_MEM: + case BPF_S_ST: + case BPF_S_STX: + case BPF_S_JMP_JA: + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JSET_K: + case BPF_S_JMP_JSET_X: + continue; + default: + return -EINVAL; + } + } + return 0; +} + +/** + * seccomp_run_filters - evaluates all seccomp filters against @syscall + * @syscall: number of the current system call + * + * Returns valid seccomp BPF response codes. + */ +static u32 seccomp_run_filters(int syscall) +{ + struct seccomp_filter *f; + u32 ret = SECCOMP_RET_KILL; + /* + * All filters in the list are evaluated and the lowest BPF return + * value always takes priority. + */ + for (f = current->seccomp.filter; f; f = f->prev) { + ret = sk_run_filter(NULL, f->insns); + if (ret != SECCOMP_RET_ALLOW) + break; + } + return ret; +} + +/** + * seccomp_attach_filter: Attaches a seccomp filter to current. + * @fprog: BPF program to install + * + * Returns 0 on success or an errno on failure. + */ +static long seccomp_attach_filter(struct sock_fprog *fprog) +{ + struct seccomp_filter *filter; + unsigned long fp_size = fprog->len * sizeof(struct sock_filter); + unsigned long total_insns = fprog->len; + long ret; + + if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) + return -EINVAL; + + for (filter = current->seccomp.filter; filter; filter = filter->prev) + total_insns += filter->len + 4; /* include a 4 instr penalty */ + if (total_insns > MAX_INSNS_PER_PATH) + return -ENOMEM; + + /* + * Installing a seccomp filter requires that the task have + * CAP_SYS_ADMIN in its namespace or be running with no_new_privs. + * This avoids scenarios where unprivileged tasks can affect the + * behavior of privileged children. + */ + if (!current->no_new_privs && + security_capable_noaudit(current_cred(), current_user_ns(), + CAP_SYS_ADMIN) != 0) + return -EACCES; + + /* Allocate a new seccomp_filter */ + filter = kzalloc(sizeof(struct seccomp_filter) + fp_size, + GFP_KERNEL|__GFP_NOWARN); + if (!filter) + return -ENOMEM; + atomic_set(&filter->usage, 1); + filter->len = fprog->len; + + /* Copy the instructions from fprog. */ + ret = -EFAULT; + if (copy_from_user(filter->insns, fprog->filter, fp_size)) + goto fail; + + /* Check and rewrite the fprog via the skb checker */ + ret = sk_chk_filter(filter->insns, filter->len); + if (ret) + goto fail; + + /* Check and rewrite the fprog for seccomp use */ + ret = seccomp_check_filter(filter->insns, filter->len); + if (ret) + goto fail; + + /* + * If there is an existing filter, make it the prev and don't drop its + * task reference. + */ + filter->prev = current->seccomp.filter; + current->seccomp.filter = filter; + return 0; +fail: + kfree(filter); + return ret; +} + +/** + * seccomp_attach_user_filter - attaches a user-supplied sock_fprog + * @user_filter: pointer to the user data containing a sock_fprog. + * + * Returns 0 on success and non-zero otherwise. + */ +long seccomp_attach_user_filter(char __user *user_filter) +{ + struct sock_fprog fprog; + long ret = -EFAULT; + +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sock_fprog fprog32; + if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) + goto out; + fprog.len = fprog32.len; + fprog.filter = compat_ptr(fprog32.filter); + } else /* falls through to the if below. */ +#endif + if (copy_from_user(&fprog, user_filter, sizeof(fprog))) + goto out; + ret = seccomp_attach_filter(&fprog); +out: + return ret; +} + +/* get_seccomp_filter - increments the reference count of the filter on @tsk */ +void get_seccomp_filter(struct task_struct *tsk) +{ + struct seccomp_filter *orig = tsk->seccomp.filter; + if (!orig) + return; + /* Reference count is bounded by the number of total processes. */ + atomic_inc(&orig->usage); +} + +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + struct seccomp_filter *orig = tsk->seccomp.filter; + /* Clean up single-reference branches iteratively. */ + while (orig && atomic_dec_and_test(&orig->usage)) { + struct seccomp_filter *freeme = orig; + orig = orig->prev; + kfree(freeme); + } +} +#endif /* CONFIG_SECCOMP_FILTER */ /* * Secure computing mode 1 allows only read/write/exit/sigreturn. @@ -34,10 +361,11 @@ static int mode1_syscalls_32[] = { void __secure_computing(int this_syscall) { int mode = current->seccomp.mode; - int * syscall; + int exit_sig = 0; + int *syscall; switch (mode) { - case 1: + case SECCOMP_MODE_STRICT: syscall = mode1_syscalls; #ifdef CONFIG_COMPAT if (is_compat_task()) @@ -47,7 +375,16 @@ void __secure_computing(int this_syscall) if (*syscall == this_syscall) return; } while (*++syscall); + exit_sig = SIGKILL; break; +#ifdef CONFIG_SECCOMP_FILTER + case SECCOMP_MODE_FILTER: + if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW) + return; + seccomp_filter_log_failure(this_syscall); + exit_sig = SIGSYS; + break; +#endif default: BUG(); } @@ -56,7 +393,7 @@ void __secure_computing(int this_syscall) dump_stack(); #endif audit_seccomp(this_syscall); - do_exit(SIGKILL); + do_exit(exit_sig); } long prctl_get_seccomp(void) @@ -64,25 +401,48 @@ long prctl_get_seccomp(void) return current->seccomp.mode; } -long prctl_set_seccomp(unsigned long seccomp_mode) +/** + * prctl_set_seccomp: configures current->seccomp.mode + * @seccomp_mode: requested mode to use + * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER + * + * This function may be called repeatedly with a @seccomp_mode of + * SECCOMP_MODE_FILTER to install additional filters. Every filter + * successfully installed will be evaluated (in reverse order) for each system + * call the task makes. + * + * Once current->seccomp.mode is non-zero, it may not be changed. + * + * Returns 0 on success or -EINVAL on failure. + */ +long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter) { - long ret; + long ret = -EINVAL; - /* can set it only once to be even more secure */ - ret = -EPERM; - if (unlikely(current->seccomp.mode)) + if (current->seccomp.mode && + current->seccomp.mode != seccomp_mode) goto out; - ret = -EINVAL; - if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) { - current->seccomp.mode = seccomp_mode; - set_thread_flag(TIF_SECCOMP); + switch (seccomp_mode) { + case SECCOMP_MODE_STRICT: + ret = 0; #ifdef TIF_NOTSC disable_TSC(); #endif - ret = 0; + break; +#ifdef CONFIG_SECCOMP_FILTER + case SECCOMP_MODE_FILTER: + ret = seccomp_attach_user_filter(filter); + if (ret) + goto out; + break; +#endif + default: + goto out; } - out: + current->seccomp.mode = seccomp_mode; + set_thread_flag(TIF_SECCOMP); +out: return ret; } diff --git a/kernel/sys.c b/kernel/sys.c index b82568b7d201..ba0ae8eea6fb 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1908,7 +1908,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: - error = prctl_set_seccomp(arg2); + error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); -- cgit v1.2.3 From acf3b2c71ed20c53dc69826683417703c2a88059 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:47:59 -0500 Subject: seccomp: add SECCOMP_RET_ERRNO This change adds the SECCOMP_RET_ERRNO as a valid return value from a seccomp filter. Additionally, it makes the first use of the lower 16-bits for storing a filter-supplied errno. 16-bits is more than enough for the errno-base.h calls. Returning errors instead of immediately terminating processes that violate seccomp policy allow for broader use of this functionality for kernel attack surface reduction. For example, a linux container could maintain a whitelist of pre-existing system calls but drop all new ones with errnos. This would keep a logically static attack surface while providing errnos that may allow for graceful failure without the downside of do_exit() on a bad call. This change also changes the signature of __secure_computing. It appears the only direct caller is the arm entry code and it clobbers any possible return value (register) immediately. Signed-off-by: Will Drewry Acked-by: Serge Hallyn Reviewed-by: Kees Cook Acked-by: Eric Paris v18: - fix up comments and rebase - fix bad var name which was fixed in later revs - remove _int() and just change the __secure_computing signature v16-v17: ... v15: - use audit_seccomp and add a skip label. (eparis@redhat.com) - clean up and pad out return codes (indan@nul.nu) v14: - no change/rebase v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: - move to WARN_ON if filter is NULL (oleg@redhat.com, luto@mit.edu, keescook@chromium.org) - return immediately for filter==NULL (keescook@chromium.org) - change evaluation to only compare the ACTION so that layered errnos don't result in the lowest one being returned. (keeschook@chromium.org) v11: - check for NULL filter (keescook@chromium.org) v10: - change loaders to fn v9: - n/a v8: - update Kconfig to note new need for syscall_set_return_value. - reordered such that TRAP behavior follows on later. - made the for loop a little less indent-y v7: - introduced Signed-off-by: James Morris --- arch/Kconfig | 6 ++++-- include/linux/seccomp.h | 10 ++++++---- kernel/seccomp.c | 42 ++++++++++++++++++++++++++++++++---------- 3 files changed, 42 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 91c2c730fc1a..beaab68c13b7 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -220,8 +220,10 @@ config HAVE_ARCH_SECCOMP_FILTER bool help This symbol should be selected by an architecure if it provides - asm/syscall.h, specifically syscall_get_arguments() and - syscall_get_arch(). + asm/syscall.h, specifically syscall_get_arguments(), + syscall_get_arch(), and syscall_set_return_value(). Additionally, + its system call entry path must respect a return value of -1 from + __secure_computing() and/or secure_computing(). config SECCOMP_FILTER def_bool y diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 86bb68fc7683..b4ce2c816e06 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -12,13 +12,14 @@ /* * All BPF programs must return a 32-bit value. - * The bottom 16-bits are reserved for future use. + * The bottom 16-bits are for optional return data. * The upper 16-bits are ordered from least permissive values to most. * * The ordering ensures that a min_t() over composed return values always * selects the least permissive choice. */ #define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ @@ -64,11 +65,12 @@ struct seccomp { struct seccomp_filter *filter; }; -extern void __secure_computing(int); -static inline void secure_computing(int this_syscall) +extern int __secure_computing(int); +static inline int secure_computing(int this_syscall) { if (unlikely(test_thread_flag(TIF_SECCOMP))) - __secure_computing(this_syscall); + return __secure_computing(this_syscall); + return 0; } extern long prctl_get_seccomp(void); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 0f7c709a523e..5f78fb6d2212 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -199,15 +199,20 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) static u32 seccomp_run_filters(int syscall) { struct seccomp_filter *f; - u32 ret = SECCOMP_RET_KILL; + u32 ret = SECCOMP_RET_ALLOW; + + /* Ensure unexpected behavior doesn't result in failing open. */ + if (WARN_ON(current->seccomp.filter == NULL)) + return SECCOMP_RET_KILL; + /* * All filters in the list are evaluated and the lowest BPF return - * value always takes priority. + * value always takes priority (ignoring the DATA). */ for (f = current->seccomp.filter; f; f = f->prev) { - ret = sk_run_filter(NULL, f->insns); - if (ret != SECCOMP_RET_ALLOW) - break; + u32 cur_ret = sk_run_filter(NULL, f->insns); + if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) + ret = cur_ret; } return ret; } @@ -346,11 +351,13 @@ static int mode1_syscalls_32[] = { }; #endif -void __secure_computing(int this_syscall) +int __secure_computing(int this_syscall) { int mode = current->seccomp.mode; int exit_sig = 0; int *syscall; + u32 ret = SECCOMP_RET_KILL; + int data; switch (mode) { case SECCOMP_MODE_STRICT: @@ -361,14 +368,26 @@ void __secure_computing(int this_syscall) #endif do { if (*syscall == this_syscall) - return; + return 0; } while (*++syscall); exit_sig = SIGKILL; break; #ifdef CONFIG_SECCOMP_FILTER case SECCOMP_MODE_FILTER: - if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW) - return; + ret = seccomp_run_filters(this_syscall); + data = ret & SECCOMP_RET_DATA; + switch (ret & SECCOMP_RET_ACTION) { + case SECCOMP_RET_ERRNO: + /* Set the low-order 16-bits as a errno. */ + syscall_set_return_value(current, task_pt_regs(current), + -data, 0); + goto skip; + case SECCOMP_RET_ALLOW: + return 0; + case SECCOMP_RET_KILL: + default: + break; + } exit_sig = SIGSYS; break; #endif @@ -379,8 +398,11 @@ void __secure_computing(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - audit_seccomp(this_syscall, exit_code, SECCOMP_RET_KILL); + audit_seccomp(this_syscall, exit_sig, ret); do_exit(exit_sig); +skip: + audit_seccomp(this_syscall, exit_sig, ret); + return -1; } long prctl_get_seccomp(void) -- cgit v1.2.3 From a0727e8ce513fe6890416da960181ceb10fbfae6 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:48:00 -0500 Subject: signal, x86: add SIGSYS info and make it synchronous. This change enables SIGSYS, defines _sigfields._sigsys, and adds x86 (compat) arch support. _sigsys defines fields which allow a signal handler to receive the triggering system call number, the relevant AUDIT_ARCH_* value for that number, and the address of the callsite. SIGSYS is added to the SYNCHRONOUS_MASK because it is desirable for it to have setup_frame() called for it. The goal is to ensure that ucontext_t reflects the machine state from the time-of-syscall and not from another signal handler. The first consumer of SIGSYS would be seccomp filter. In particular, a filter program could specify a new return value, SECCOMP_RET_TRAP, which would result in the system call being denied and the calling thread signaled. This also means that implementing arch-specific support can be dependent upon HAVE_ARCH_SECCOMP_FILTER. Suggested-by: H. Peter Anvin Signed-off-by: Will Drewry Acked-by: Serge Hallyn Reviewed-by: H. Peter Anvin Acked-by: Eric Paris v18: - added acked by, rebase v17: - rebase and reviewed-by addition v14: - rebase/nochanges v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: - reworded changelog (oleg@redhat.com) v11: - fix dropped words in the change description - added fallback copy_siginfo support. - added __ARCH_SIGSYS define to allow stepped arch support. v10: - first version based on suggestion Signed-off-by: James Morris --- arch/x86/ia32/ia32_signal.c | 4 ++++ arch/x86/include/asm/ia32.h | 6 ++++++ include/asm-generic/siginfo.h | 22 ++++++++++++++++++++++ kernel/signal.c | 9 ++++++++- 4 files changed, 40 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index a69245ba27e3..0b3f2354f6aa 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -67,6 +67,10 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) switch (from->si_code >> 16) { case __SI_FAULT >> 16: break; + case __SI_SYS >> 16: + put_user_ex(from->si_syscall, &to->si_syscall); + put_user_ex(from->si_arch, &to->si_arch); + break; case __SI_CHLD >> 16: if (ia32) { put_user_ex(from->si_utime, &to->si_utime); diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index ee52760549f0..b04cbdb138cd 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -144,6 +144,12 @@ typedef struct compat_siginfo { int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; + + struct { + unsigned int _call_addr; /* calling insn */ + int _syscall; /* triggering system call number */ + unsigned int _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; } _sifields; } compat_siginfo_t; diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h index 0dd4e87f6fba..31306f55eb02 100644 --- a/include/asm-generic/siginfo.h +++ b/include/asm-generic/siginfo.h @@ -90,9 +90,18 @@ typedef struct siginfo { __ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; + + /* SIGSYS */ + struct { + void __user *_call_addr; /* calling insn */ + int _syscall; /* triggering system call number */ + unsigned int _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; } _sifields; } siginfo_t; +/* If the arch shares siginfo, then it has SIGSYS. */ +#define __ARCH_SIGSYS #endif /* @@ -116,6 +125,11 @@ typedef struct siginfo { #define si_addr_lsb _sifields._sigfault._addr_lsb #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd +#ifdef __ARCH_SIGSYS +#define si_call_addr _sifields._sigsys._call_addr +#define si_syscall _sifields._sigsys._syscall +#define si_arch _sifields._sigsys._arch +#endif #ifdef __KERNEL__ #define __SI_MASK 0xffff0000u @@ -126,6 +140,7 @@ typedef struct siginfo { #define __SI_CHLD (4 << 16) #define __SI_RT (5 << 16) #define __SI_MESGQ (6 << 16) +#define __SI_SYS (7 << 16) #define __SI_CODE(T,N) ((T) | ((N) & 0xffff)) #else #define __SI_KILL 0 @@ -135,6 +150,7 @@ typedef struct siginfo { #define __SI_CHLD 0 #define __SI_RT 0 #define __SI_MESGQ 0 +#define __SI_SYS 0 #define __SI_CODE(T,N) (N) #endif @@ -231,6 +247,12 @@ typedef struct siginfo { #define POLL_HUP (__SI_POLL|6) /* device disconnected */ #define NSIGPOLL 6 +/* + * SIGSYS si_codes + */ +#define SYS_SECCOMP (__SI_SYS|1) /* seccomp triggered */ +#define NSIGSYS 1 + /* * sigevent definitions * diff --git a/kernel/signal.c b/kernel/signal.c index 17afcaf582d0..1a006b5d9d9d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -160,7 +160,7 @@ void recalc_sigpending(void) #define SYNCHRONOUS_MASK \ (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ - sigmask(SIGTRAP) | sigmask(SIGFPE)) + sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS)) int next_signal(struct sigpending *pending, sigset_t *mask) { @@ -2706,6 +2706,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) err |= __put_user(from->si_uid, &to->si_uid); err |= __put_user(from->si_ptr, &to->si_ptr); break; +#ifdef __ARCH_SIGSYS + case __SI_SYS: + err |= __put_user(from->si_call_addr, &to->si_call_addr); + err |= __put_user(from->si_syscall, &to->si_syscall); + err |= __put_user(from->si_arch, &to->si_arch); + break; +#endif default: /* this is just in case for now ... */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); -- cgit v1.2.3 From bb6ea4301a1109afdacaee576fedbfcd7152fc86 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:48:01 -0500 Subject: seccomp: Add SECCOMP_RET_TRAP Adds a new return value to seccomp filters that triggers a SIGSYS to be delivered with the new SYS_SECCOMP si_code. This allows in-process system call emulation, including just specifying an errno or cleanly dumping core, rather than just dying. Suggested-by: Markus Gutschke Suggested-by: Julien Tinnes Signed-off-by: Will Drewry Acked-by: Eric Paris v18: - acked-by, rebase - don't mention secure_computing_int() anymore v15: - use audit_seccomp/skip - pad out error spacing; clean up switch (indan@nul.nu) v14: - n/a v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: - rebase on to linux-next v11: - clarify the comment (indan@nul.nu) - s/sigtrap/sigsys v10: - use SIGSYS, syscall_get_arch, updates arch/Kconfig note suggested-by (though original suggestion had other behaviors) v9: - changes to SIGILL v8: - clean up based on changes to dependent patches v7: - introduction Signed-off-by: James Morris --- arch/Kconfig | 14 +++++++++----- include/asm-generic/siginfo.h | 2 +- include/linux/seccomp.h | 1 + kernel/seccomp.c | 26 ++++++++++++++++++++++++++ 4 files changed, 37 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index beaab68c13b7..66aef13f6038 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -219,11 +219,15 @@ config ARCH_WANT_OLD_COMPAT_IPC config HAVE_ARCH_SECCOMP_FILTER bool help - This symbol should be selected by an architecure if it provides - asm/syscall.h, specifically syscall_get_arguments(), - syscall_get_arch(), and syscall_set_return_value(). Additionally, - its system call entry path must respect a return value of -1 from - __secure_computing() and/or secure_computing(). + This symbol should be selected by an architecure if it provides: + asm/syscall.h: + - syscall_get_arch() + - syscall_get_arguments() + - syscall_rollback() + - syscall_set_return_value() + SIGSYS siginfo_t support must be implemented. + __secure_computing()/secure_computing()'s return value must be + checked, with -1 resulting in the syscall being skipped. config SECCOMP_FILTER def_bool y diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h index 31306f55eb02..af5d0350f84c 100644 --- a/include/asm-generic/siginfo.h +++ b/include/asm-generic/siginfo.h @@ -93,7 +93,7 @@ typedef struct siginfo { /* SIGSYS */ struct { - void __user *_call_addr; /* calling insn */ + void __user *_call_addr; /* calling user insn */ int _syscall; /* triggering system call number */ unsigned int _arch; /* AUDIT_ARCH_* of syscall */ } _sigsys; diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index b4ce2c816e06..317ccb78cf40 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -19,6 +19,7 @@ * selects the least permissive choice. */ #define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 5f78fb6d2212..9c3830692a08 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -332,6 +332,26 @@ void put_seccomp_filter(struct task_struct *tsk) kfree(freeme); } } + +/** + * seccomp_send_sigsys - signals the task to allow in-process syscall emulation + * @syscall: syscall number to send to userland + * @reason: filter-supplied reason code to send to userland (via si_errno) + * + * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. + */ +static void seccomp_send_sigsys(int syscall, int reason) +{ + struct siginfo info; + memset(&info, 0, sizeof(info)); + info.si_signo = SIGSYS; + info.si_code = SYS_SECCOMP; + info.si_call_addr = (void __user *)KSTK_EIP(current); + info.si_errno = reason; + info.si_arch = syscall_get_arch(current, task_pt_regs(current)); + info.si_syscall = syscall; + force_sig_info(SIGSYS, &info, current); +} #endif /* CONFIG_SECCOMP_FILTER */ /* @@ -382,6 +402,12 @@ int __secure_computing(int this_syscall) syscall_set_return_value(current, task_pt_regs(current), -data, 0); goto skip; + case SECCOMP_RET_TRAP: + /* Show the handler the original registers. */ + syscall_rollback(current, task_pt_regs(current)); + /* Let the filter pass back 16 bits of data. */ + seccomp_send_sigsys(this_syscall, data); + goto skip; case SECCOMP_RET_ALLOW: return 0; case SECCOMP_RET_KILL: -- cgit v1.2.3 From fb0fadf9b213f55ca9368f3edafe51101d5d2deb Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:48:02 -0500 Subject: ptrace,seccomp: Add PTRACE_SECCOMP support This change adds support for a new ptrace option, PTRACE_O_TRACESECCOMP, and a new return value for seccomp BPF programs, SECCOMP_RET_TRACE. When a tracer specifies the PTRACE_O_TRACESECCOMP ptrace option, the tracer will be notified, via PTRACE_EVENT_SECCOMP, for any syscall that results in a BPF program returning SECCOMP_RET_TRACE. The 16-bit SECCOMP_RET_DATA mask of the BPF program return value will be passed as the ptrace_message and may be retrieved using PTRACE_GETEVENTMSG. If the subordinate process is not using seccomp filter, then no system call notifications will occur even if the option is specified. If there is no tracer with PTRACE_O_TRACESECCOMP when SECCOMP_RET_TRACE is returned, the system call will not be executed and an -ENOSYS errno will be returned to userspace. This change adds a dependency on the system call slow path. Any future efforts to use the system call fast path for seccomp filter will need to address this restriction. Signed-off-by: Will Drewry Acked-by: Eric Paris v18: - rebase - comment fatal_signal check - acked-by - drop secure_computing_int comment v17: - ... v16: - update PT_TRACE_MASK to 0xbf4 so that STOP isn't clear on SETOPTIONS call (indan@nul.nu) [note PT_TRACE_MASK disappears in linux-next] v15: - add audit support for non-zero return codes - clean up style (indan@nul.nu) v14: - rebase/nochanges v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc (Brings back a change to ptrace.c and the masks.) v12: - rebase to linux-next - use ptrace_event and update arch/Kconfig to mention slow-path dependency - drop all tracehook changes and inclusion (oleg@redhat.com) v11: - invert the logic to just make it a PTRACE_SYSCALL accelerator (indan@nul.nu) v10: - moved to PTRACE_O_SECCOMP / PT_TRACE_SECCOMP v9: - n/a v8: - guarded PTRACE_SECCOMP use with an ifdef v7: - introduced Signed-off-by: James Morris --- arch/Kconfig | 10 +++++----- include/linux/ptrace.h | 5 ++++- include/linux/seccomp.h | 1 + kernel/seccomp.c | 16 ++++++++++++++++ 4 files changed, 26 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 66aef13f6038..c024b3ed6675 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -219,15 +219,15 @@ config ARCH_WANT_OLD_COMPAT_IPC config HAVE_ARCH_SECCOMP_FILTER bool help - This symbol should be selected by an architecure if it provides: - asm/syscall.h: + An arch should select this symbol if it provides all of these things: - syscall_get_arch() - syscall_get_arguments() - syscall_rollback() - syscall_set_return_value() - SIGSYS siginfo_t support must be implemented. - __secure_computing()/secure_computing()'s return value must be - checked, with -1 resulting in the syscall being skipped. + - SIGSYS siginfo_t support + - secure_computing is called from a ptrace_event()-safe context + - secure_computing return value is checked and a return value of -1 + results in the system call being skipped immediately. config SECCOMP_FILTER def_bool y diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 5c719627c2aa..597e4fdb97fe 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -58,6 +58,7 @@ #define PTRACE_EVENT_EXEC 4 #define PTRACE_EVENT_VFORK_DONE 5 #define PTRACE_EVENT_EXIT 6 +#define PTRACE_EVENT_SECCOMP 7 /* Extended result codes which enabled by means other than options. */ #define PTRACE_EVENT_STOP 128 @@ -69,8 +70,9 @@ #define PTRACE_O_TRACEEXEC (1 << PTRACE_EVENT_EXEC) #define PTRACE_O_TRACEVFORKDONE (1 << PTRACE_EVENT_VFORK_DONE) #define PTRACE_O_TRACEEXIT (1 << PTRACE_EVENT_EXIT) +#define PTRACE_O_TRACESECCOMP (1 << PTRACE_EVENT_SECCOMP) -#define PTRACE_O_MASK 0x0000007f +#define PTRACE_O_MASK 0x000000ff #include @@ -98,6 +100,7 @@ #define PT_TRACE_EXEC PT_EVENT_FLAG(PTRACE_EVENT_EXEC) #define PT_TRACE_VFORK_DONE PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE) #define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT) +#define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) /* single stepping state bits (used on ARM and PA-RISC) */ #define PT_SINGLESTEP_BIT 31 diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 317ccb78cf40..5818e869651b 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -21,6 +21,7 @@ #define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ #define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 9c3830692a08..d9db6ec46bc9 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -24,6 +24,7 @@ #ifdef CONFIG_SECCOMP_FILTER #include #include +#include #include #include #include @@ -408,6 +409,21 @@ int __secure_computing(int this_syscall) /* Let the filter pass back 16 bits of data. */ seccomp_send_sigsys(this_syscall, data); goto skip; + case SECCOMP_RET_TRACE: + /* Skip these calls if there is no tracer. */ + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) + goto skip; + /* Allow the BPF to provide the event message */ + ptrace_event(PTRACE_EVENT_SECCOMP, data); + /* + * The delivery of a fatal signal during event + * notification may silently skip tracer notification. + * Terminating the task now avoids executing a system + * call that may not be intended. + */ + if (fatal_signal_pending(current)) + break; + return 0; case SECCOMP_RET_ALLOW: return 0; case SECCOMP_RET_KILL: -- cgit v1.2.3 From c6cfbeb4029610c8c330c312dcf4d514cc067554 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:48:03 -0500 Subject: x86: Enable HAVE_ARCH_SECCOMP_FILTER Enable support for seccomp filter on x86: - syscall_get_arch() - syscall_get_arguments() - syscall_rollback() - syscall_set_return_value() - SIGSYS siginfo_t support - secure_computing is called from a ptrace_event()-safe context - secure_computing return value is checked (see below). SECCOMP_RET_TRACE and SECCOMP_RET_TRAP may result in seccomp needing to skip a system call without killing the process. This is done by returning a non-zero (-1) value from secure_computing. This change makes x86 respect that return value. To ensure that minimal kernel code is exposed, a non-zero return value results in an immediate return to user space (with an invalid syscall number). Signed-off-by: Will Drewry Reviewed-by: H. Peter Anvin Acked-by: Eric Paris Reviewed-by: Kees Cook v18: rebase and tweaked change description, acked-by v17: added reviewed by and rebased v..: all rebases since original introduction. Signed-off-by: James Morris --- arch/x86/Kconfig | 1 + arch/x86/kernel/ptrace.c | 7 ++++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d14cc6b79ad..3a41c4424a0a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -82,6 +82,7 @@ config X86 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC + select HAVE_ARCH_SECCOMP_FILTER config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 685845cf16e0..13b1990c7c58 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1480,7 +1480,11 @@ long syscall_trace_enter(struct pt_regs *regs) regs->flags |= X86_EFLAGS_TF; /* do the secure computing check first */ - secure_computing(regs->orig_ax); + if (secure_computing(regs->orig_ax)) { + /* seccomp failures shouldn't expose any additional code. */ + ret = -1L; + goto out; + } if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) ret = -1L; @@ -1505,6 +1509,7 @@ long syscall_trace_enter(struct pt_regs *regs) regs->dx, regs->r10); #endif +out: return ret ?: regs->orig_ax; } -- cgit v1.2.3 From e4da89d02f369450996cfd04f64b1cce4d8afaea Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Tue, 17 Apr 2012 14:48:57 -0500 Subject: seccomp: ignore secure_computing return values This change is inspired by https://lkml.org/lkml/2012/4/16/14 which fixes the build warnings for arches that don't support CONFIG_HAVE_ARCH_SECCOMP_FILTER. In particular, there is no requirement for the return value of secure_computing() to be checked unless the architecture supports seccomp filter. Instead of silencing the warnings with (void) a new static inline is added to encode the expected behavior in a compiler and human friendly way. v2: - cleans things up with a static inline - removes sfr's signed-off-by since it is a different approach v1: - matches sfr's original change Reported-by: Stephen Rothwell Signed-off-by: Will Drewry Acked-by: Kees Cook Signed-off-by: James Morris --- arch/microblaze/kernel/ptrace.c | 2 +- arch/mips/kernel/ptrace.c | 2 +- arch/powerpc/kernel/ptrace.c | 2 +- arch/s390/kernel/ptrace.c | 2 +- arch/sh/kernel/ptrace_32.c | 2 +- arch/sh/kernel/ptrace_64.c | 2 +- arch/sparc/kernel/ptrace_64.c | 2 +- include/linux/seccomp.h | 7 +++++++ 8 files changed, 14 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c index 6eb2aa927d89..ab1b9db661f3 100644 --- a/arch/microblaze/kernel/ptrace.c +++ b/arch/microblaze/kernel/ptrace.c @@ -136,7 +136,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - secure_computing(regs->r12); + secure_computing_strict(regs->r12); if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 7c24c2973c6d..4812c6d916e4 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -535,7 +535,7 @@ static inline int audit_arch(void) asmlinkage void syscall_trace_enter(struct pt_regs *regs) { /* do the secure computing check first */ - secure_computing(regs->regs[2]); + secure_computing_strict(regs->regs[2]); if (!(current->ptrace & PT_PTRACED)) goto out; diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 8d8e028893be..dd5e214cdf21 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1710,7 +1710,7 @@ long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - secure_computing(regs->gpr[0]); + secure_computing_strict(regs->gpr[0]); if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 02f300fbf070..4993e689b2c2 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -719,7 +719,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) long ret = 0; /* Do the secure computing check first. */ - secure_computing(regs->gprs[2]); + secure_computing_strict(regs->gprs[2]); /* * The sysc_tracesys code in entry.S stored the system diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 9698671444e6..81f999a672f6 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -503,7 +503,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - secure_computing(regs->regs[0]); + secure_computing_strict(regs->regs[0]); if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c index bc81e07dc098..af90339dadcd 100644 --- a/arch/sh/kernel/ptrace_64.c +++ b/arch/sh/kernel/ptrace_64.c @@ -522,7 +522,7 @@ asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs) { long long ret = 0; - secure_computing(regs->regs[9]); + secure_computing_strict(regs->regs[9]); if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index 6f97c0767995..484dabac7045 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -1062,7 +1062,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) int ret = 0; /* do the secure computing check first */ - secure_computing(regs->u_regs[UREG_G1]); + secure_computing_strict(regs->u_regs[UREG_G1]); if (test_thread_flag(TIF_SYSCALL_TRACE)) ret = tracehook_report_syscall_entry(regs); diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 60f2b350ead7..84f6320da50f 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -75,6 +75,12 @@ static inline int secure_computing(int this_syscall) return 0; } +/* A wrapper for architectures supporting only SECCOMP_MODE_STRICT. */ +static inline void secure_computing_strict(int this_syscall) +{ + BUG_ON(secure_computing(this_syscall) != 0); +} + extern long prctl_get_seccomp(void); extern long prctl_set_seccomp(unsigned long, char __user *); @@ -91,6 +97,7 @@ struct seccomp { }; struct seccomp_filter { }; static inline int secure_computing(int this_syscall) { return 0; } +static inline void secure_computing_strict(int this_syscall) { return; } static inline long prctl_get_seccomp(void) { -- cgit v1.2.3 From 45de6767dc51358a188f75dc4ad9dfddb7fb9480 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 May 2012 10:56:56 +0100 Subject: KEYS: Use the compat keyctl() syscall wrapper on Sparc64 for Sparc32 compat Use the 32-bit compat keyctl() syscall wrapper on Sparc64 for Sparc32 binary compatibility. Without this, keyctl(KEYCTL_INSTANTIATE_IOV) is liable to malfunction as it uses an iovec array read from userspace - though the kernel should survive this as it checks pointers and sizes anyway. I think all the other keyctl() function should just work, provided (a) the top 32-bits of each 64-bit argument register are cleared prior to invoking the syscall routine, and the 32-bit address space is right at the 0-end of the 64-bit address space. Most of the arguments are 32-bit anyway, and so for those clearing is not required. Signed-off-by: David Howells cc: sparclinux@vger.kernel.org cc: stable@vger.kernel.org --- arch/sparc/Kconfig | 3 +++ arch/sparc/kernel/systbls_64.S | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6c0683d3fcba..76c7ccfb1ebe 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -584,6 +584,9 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y +config KEYS_COMPAT + def_bool y if COMPAT && KEYS + endmenu source "net/Kconfig" diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index db86b1a0e9a9..3a58e0d66f51 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -74,7 +74,7 @@ sys_call_table32: .word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy /*270*/ .word sys32_io_submit, sys_io_cancel, compat_sys_io_getevents, sys32_mq_open, sys_mq_unlink .word compat_sys_mq_timedsend, compat_sys_mq_timedreceive, compat_sys_mq_notify, compat_sys_mq_getsetattr, compat_sys_waitid -/*280*/ .word sys32_tee, sys_add_key, sys_request_key, sys_keyctl, compat_sys_openat +/*280*/ .word sys32_tee, sys_add_key, sys_request_key, compat_sys_keyctl, compat_sys_openat .word sys_mkdirat, sys_mknodat, sys_fchownat, compat_sys_futimesat, compat_sys_fstatat64 /*290*/ .word sys_unlinkat, sys_renameat, sys_linkat, sys_symlinkat, sys_readlinkat .word sys_fchmodat, sys_faccessat, compat_sys_pselect6, compat_sys_ppoll, sys_unshare -- cgit v1.2.3