From: Linus Torvalds Date: Sun, 19 Oct 2014 23:25:56 +0000 (-0700) Subject: Merge git://git.infradead.org/users/eparis/audit X-Git-Url: http://drtracing.org/?a=commitdiff_plain;h=ab074ade9c33b3585da86d62e87bcb3e897a3f54;p=deliverable%2Flinux.git Merge git://git.infradead.org/users/eparis/audit Pull audit updates from Eric Paris: "So this change across a whole bunch of arches really solves one basic problem. We want to audit when seccomp is killing a process. seccomp hooks in before the audit syscall entry code. audit_syscall_entry took as an argument the arch of the given syscall. Since the arch is part of what makes a syscall number meaningful it's an important part of the record, but it isn't available when seccomp shoots the syscall... For most arch's we have a better way to get the arch (syscall_get_arch) So the solution was two fold: Implement syscall_get_arch() everywhere there is audit which didn't have it. Use syscall_get_arch() in the seccomp audit code. Having syscall_get_arch() everywhere meant it was a useless flag on the stack and we could get rid of it for the typical syscall entry. The other changes inside the audit system aren't grand, fixed some records that had invalid spaces. Better locking around the task comm field. Removing some dead functions and structs. Make some things static. Really minor stuff" * git://git.infradead.org/users/eparis/audit: (31 commits) audit: rename audit_log_remove_rule to disambiguate for trees audit: cull redundancy in audit_rule_change audit: WARN if audit_rule_change called illegally audit: put rule existence check in canonical order next: openrisc: Fix build audit: get comm using lock to avoid race in string printing audit: remove open_arg() function that is never used audit: correct AUDIT_GET_FEATURE return message type audit: set nlmsg_len for multicast messages. audit: use union for audit_field values since they are mutually exclusive audit: invalid op= values for rules audit: use atomic_t to simplify audit_serial() kernel/audit.c: use ARRAY_SIZE instead of sizeof/sizeof[0] audit: reduce scope of audit_log_fcaps audit: reduce scope of audit_net_id audit: arm64: Remove the audit arch argument to audit_syscall_entry arm64: audit: Add audit hook in syscall_trace_enter/exit() audit: x86: drop arch from __audit_syscall_entry() interface sparc: implement is_32bit_task sparc: properly conditionalize use of TIF_32BIT ... --- ab074ade9c33b3585da86d62e87bcb3e897a3f54 diff --cc arch/mips/include/asm/syscall.h index cdf68b33bd65,93b3b86c293c..bb7963753730 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@@ -129,14 -129,12 +129,14 @@@ extern const unsigned long sysn32_call_ static inline int syscall_get_arch(void) { - int arch = EM_MIPS; + int arch = AUDIT_ARCH_MIPS; #ifdef CONFIG_64BIT - if (!test_thread_flag(TIF_32BIT_REGS)) + if (!test_thread_flag(TIF_32BIT_REGS)) { arch |= __AUDIT_ARCH_64BIT; - if (test_thread_flag(TIF_32BIT_ADDR)) - arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32; + /* N32 sets only TIF_32BIT_ADDR */ + if (test_thread_flag(TIF_32BIT_ADDR)) + arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32; + } #endif #if defined(__LITTLE_ENDIAN) arch |= __AUDIT_ARCH_LE; diff --cc arch/x86/ia32/ia32entry.S index 711de084ab57,f5bdd2881815..8ffba18395c8 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@@ -194,16 -184,14 +194,16 @@@ sysexit_from_sys_call TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common - movl %esi,%r9d /* 6th arg: 4th syscall arg */ - movl %edx,%r8d /* 5th arg: 3rd syscall arg */ - /* (already in %ecx) 4th arg: 2nd syscall arg */ - movl %ebx,%edx /* 3rd arg: 1st syscall arg */ - movl %eax,%esi /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ + movl %esi,%r8d /* 5th arg: 4th syscall arg */ + movl %ecx,%r9d /*swap with edx*/ + movl %edx,%ecx /* 4th arg: 3rd syscall arg */ + movl %r9d,%edx /* 3rd arg: 2nd syscall arg */ + movl %ebx,%esi /* 2nd arg: 1st syscall arg */ + movl %eax,%edi /* 1st arg: syscall number */ call __audit_syscall_entry movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ cmpq $(IA32_NR_syscalls-1),%rax diff --cc arch/x86/kernel/ptrace.c index 29576c244699,eb1c87f0b03b..749b0e423419 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@@ -1441,126 -1441,24 +1441,126 @@@ void send_sigtrap(struct task_struct *t force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { - audit_syscall_entry(arch, regs->orig_ax, regs->di, ++ audit_syscall_entry(regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else #endif + { - audit_syscall_entry(arch, regs->orig_ax, regs->bx, ++ audit_syscall_entry(regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} /* - * We must return the syscall number to actually look up in the table. - * This can be -1L to skip running any syscall at all. + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp */ -long syscall_trace_enter(struct pt_regs *regs) +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + unsigned long ret = 0; + u32 work; + + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; + + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + user_exit(); + work &= ~TIF_NOHZ; + } + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) { long ret = 0; + u32 work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; - user_exit(); + BUG_ON(regs != task_pt_regs(current)); /* * If we stepped into a sysenter/syscall insn, it trapped in