From 932ecebb0405b9a41cd18946e6cff8a17d434e23 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Thu, 12 Apr 2012 16:47:54 -0500 Subject: seccomp: kill the seccomp_t typedef Replaces the seccomp_t typedef with struct seccomp to match modern kernel style. Signed-off-by: Will Drewry Reviewed-by: James Morris Acked-by: Serge Hallyn Acked-by: Eric Paris v18: rebase ... v14: rebase/nochanges v13: rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc v12: rebase on to linux-next v8-v11: no changes v7: struct seccomp_struct -> struct seccomp v6: original inclusion in this series. Signed-off-by: James Morris --- include/linux/seccomp.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux/seccomp.h') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index cc7a4e9cc7ad..d61f27fcaa97 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -7,7 +7,9 @@ #include #include -typedef struct { int mode; } seccomp_t; +struct seccomp { + int mode; +}; extern void __secure_computing(int); static inline void secure_computing(int this_syscall) @@ -19,7 +21,7 @@ static inline void secure_computing(int this_syscall) extern long prctl_get_seccomp(void); extern long prctl_set_seccomp(unsigned long); -static inline int seccomp_mode(seccomp_t *s) +static inline int seccomp_mode(struct seccomp *s) { return s->mode; } @@ -28,7 +30,7 @@ static inline int seccomp_mode(seccomp_t *s) #include -typedef struct { } seccomp_t; +struct seccomp { }; #define secure_computing(x) do { } while (0) @@ -42,7 +44,7 @@ static inline long prctl_set_seccomp(unsigned long arg2) return -EINVAL; } -static inline int seccomp_mode(seccomp_t *s) +static inline int seccomp_mode(struct seccomp *s) { return 0; } -- cgit v1.2.2 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 --- include/linux/seccomp.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 72 insertions(+), 4 deletions(-) (limited to 'include/linux/seccomp.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 */ -- cgit v1.2.2 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 --- include/linux/seccomp.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux/seccomp.h') 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); -- cgit v1.2.2 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 --- include/linux/seccomp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/seccomp.h') 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 */ -- cgit v1.2.2 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 --- include/linux/seccomp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/seccomp.h') 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. */ -- cgit v1.2.2 From b1fa650c7e6e81ca788fef52b1659295eb82ffdd Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 17 Apr 2012 12:08:48 +1000 Subject: seccomp: use a static inline for a function stub Fixes this error message when CONFIG_SECCOMP is not set: arch/powerpc/kernel/ptrace.c: In function 'do_syscall_trace_enter': arch/powerpc/kernel/ptrace.c:1713:2: error: statement with no effect [-Werror=unused-value] Signed-off-by: Stephen Rothwell Signed-off-by: James Morris --- include/linux/seccomp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/seccomp.h') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 5818e869651b..60f2b350ead7 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -90,7 +90,7 @@ static inline int seccomp_mode(struct seccomp *s) struct seccomp { }; struct seccomp_filter { }; -#define secure_computing(x) 0 +static inline int secure_computing(int this_syscall) { return 0; } static inline long prctl_get_seccomp(void) { -- cgit v1.2.2 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 --- include/linux/seccomp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/seccomp.h') 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 v1.2.2