linux-sg2042/include/linux/ptrace.h

362 lines
13 KiB
C
Raw Normal View History

#ifndef _LINUX_PTRACE_H
#define _LINUX_PTRACE_H
#include <linux/compiler.h> /* For unlikely. */
#include <linux/sched.h> /* For struct task_struct. */
#include <linux/err.h> /* for IS_ERR_VALUE */
#include <linux/bug.h> /* For BUG_ON. */
#include <uapi/linux/ptrace.h>
/*
* Ptrace flags
*
* The owner ship rules for task->ptrace which holds the ptrace
* flags is simple. When a task is running it owns it's task->ptrace
* flags. When the a task is stopped the ptracer owns task->ptrace.
*/
ptrace: implement PTRACE_SEIZE PTRACE_ATTACH implicitly issues SIGSTOP on attach which has side effects on tracee signal and job control states. This patch implements a new ptrace request PTRACE_SEIZE which attaches a tracee without trapping it or affecting its signal and job control states. The usage is the same with PTRACE_ATTACH but it takes PTRACE_SEIZE_* flags in @data. Currently, the only defined flag is PTRACE_SEIZE_DEVEL which is a temporary flag to enable PTRACE_SEIZE. PTRACE_SEIZE will change ptrace behaviors outside of attach itself. The changes will be implemented gradually and the DEVEL flag is to prevent programs which expect full SEIZE behavior from using it before all the behavior modifications are complete while allowing unit testing. The flag will be removed once SEIZE behaviors are completely implemented. * PTRACE_SEIZE, unlike ATTACH, doesn't force tracee to trap. After attaching tracee continues to run unless a trap condition occurs. * PTRACE_SEIZE doesn't affect signal or group stop state. * If PTRACE_SEIZE'd, group stop uses PTRACE_EVENT_STOP trap which uses exit_code of (signr | PTRACE_EVENT_STOP << 8) where signr is one of the stopping signals if group stop is in effect or SIGTRAP otherwise, and returns usual trap siginfo on PTRACE_GETSIGINFO instead of NULL. Seizing sets PT_SEIZED in ->ptrace of the tracee. This flag will be used to determine whether new SEIZE behaviors should be enabled. Test program follows. #define PTRACE_SEIZE 0x4206 #define PTRACE_SEIZE_DEVEL 0x80000000 static const struct timespec ts100ms = { .tv_nsec = 100000000 }; static const struct timespec ts1s = { .tv_sec = 1 }; static const struct timespec ts3s = { .tv_sec = 3 }; int main(int argc, char **argv) { pid_t tracee; tracee = fork(); if (tracee == 0) { nanosleep(&ts100ms, NULL); while (1) { printf("tracee: alive\n"); nanosleep(&ts1s, NULL); } } if (argc > 1) kill(tracee, SIGSTOP); nanosleep(&ts100ms, NULL); ptrace(PTRACE_SEIZE, tracee, NULL, (void *)(unsigned long)PTRACE_SEIZE_DEVEL); if (argc > 1) { waitid(P_PID, tracee, NULL, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, NULL); } nanosleep(&ts3s, NULL); printf("tracer: exiting\n"); return 0; } When the above program is called w/o argument, tracee is seized while running and remains running. When tracer exits, tracee continues to run and print out messages. # ./test-seize-simple tracee: alive tracee: alive tracee: alive tracer: exiting tracee: alive tracee: alive When called with an argument, tracee is seized from stopped state and continued, and returns to stopped state when tracer exits. # ./test-seize tracee: alive tracee: alive tracee: alive tracer: exiting # ps -el|grep test-seize 1 T 0 4720 1 0 80 0 - 941 signal ttyS0 00:00:00 test-seize -v2: SEIZE doesn't schedule TRAP_STOP and leaves tracee running as Jan suggested. -v3: PTRACE_EVENT_STOP traps now report group stop state by signr. If group stop is in effect the stop signal number is returned as part of exit_code; otherwise, SIGTRAP. This was suggested by Denys and Oleg. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Denys Vlasenko <vda.linux@googlemail.com> Cc: Oleg Nesterov <oleg@redhat.com>
2011-06-14 17:20:15 +08:00
#define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */
#define PT_PTRACED 0x00000001
#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */
#define PT_PTRACE_CAP 0x00000004 /* ptracer can follow suid-exec */
#define PT_OPT_FLAG_SHIFT 3
/* PT_TRACE_* event enable flags */
#define PT_EVENT_FLAG(event) (1 << (PT_OPT_FLAG_SHIFT + (event)))
#define PT_TRACESYSGOOD PT_EVENT_FLAG(0)
#define PT_TRACE_FORK PT_EVENT_FLAG(PTRACE_EVENT_FORK)
#define PT_TRACE_VFORK PT_EVENT_FLAG(PTRACE_EVENT_VFORK)
#define PT_TRACE_CLONE PT_EVENT_FLAG(PTRACE_EVENT_CLONE)
#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)
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 <wad@chromium.org> Acked-by: Eric Paris <eparis@redhat.com> 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 <james.l.morris@oracle.com>
2012-04-13 05:48:02 +08:00
#define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
#define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
/* single stepping state bits (used on ARM and PA-RISC) */
#define PT_SINGLESTEP_BIT 31
#define PT_SINGLESTEP (1<<PT_SINGLESTEP_BIT)
#define PT_BLOCKSTEP_BIT 30
#define PT_BLOCKSTEP (1<<PT_BLOCKSTEP_BIT)
extern long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data);
extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
extern void ptrace_disable(struct task_struct *);
extern int ptrace_request(struct task_struct *child, long request,
unsigned long addr, unsigned long data);
extern void ptrace_notify(int exit_code);
extern void __ptrace_link(struct task_struct *child,
struct task_struct *new_parent);
extern void __ptrace_unlink(struct task_struct *child);
extern void exit_ptrace(struct task_struct *tracer);
#define PTRACE_MODE_READ 0x01
#define PTRACE_MODE_ATTACH 0x02
#define PTRACE_MODE_NOAUDIT 0x04
Security: split proc ptrace checking into read vs. attach Enable security modules to distinguish reading of process state via proc from full ptrace access by renaming ptrace_may_attach to ptrace_may_access and adding a mode argument indicating whether only read access or full attach access is requested. This allows security modules to permit access to reading process state without granting full ptrace access. The base DAC/capability checking remains unchanged. Read access to /proc/pid/mem continues to apply a full ptrace attach check since check_mem_permission() already requires the current task to already be ptracing the target. The other ptrace checks within proc for elements like environ, maps, and fds are changed to pass the read mode instead of attach. In the SELinux case, we model such reading of process state as a reading of a proc file labeled with the target process' label. This enables SELinux policy to permit such reading of process state without permitting control or manipulation of the target process, as there are a number of cases where programs probe for such information via proc but do not need to be able to control the target (e.g. procps, lsof, PolicyKit, ConsoleKit). At present we have to choose between allowing full ptrace in policy (more permissive than required/desired) or breaking functionality (or in some cases just silencing the denials via dontaudit rules but this can hide genuine attacks). This version of the patch incorporates comments from Casey Schaufler (change/replace existing ptrace_may_attach interface, pass access mode), and Chris Wright (provide greater consistency in the checking). Note that like their predecessors __ptrace_may_attach and ptrace_may_attach, the __ptrace_may_access and ptrace_may_access interfaces use different return value conventions from each other (0 or -errno vs. 1 or 0). I retained this difference to avoid any changes to the caller logic but made the difference clearer by changing the latter interface to return a bool rather than an int and by adding a comment about it to ptrace.h for any future callers. Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 20:32:49 +08:00
/* Returns true on success, false on denial. */
extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
static inline int ptrace_reparented(struct task_struct *child)
{
ptrace: ptrace_reparented() should check same_thread_group() ptrace_reparented() naively does parent != real_parent, this means it returns true even if the tracer _is_ the real parent. This is per process thing, not per-thread. The only reason ->real_parent can point to the non-leader thread is that we have __WNOTHREAD. Change it to check !same_thread_group(parent, real_parent). It has two callers, and in both cases the current check does not look right. exit_notify: we should respect ->exit_signal if the exiting leader is traced by any thread from the parent thread group. It is the child of the whole group, and we are going to send the signal to the whole group. wait_task_zombie: without __WNOTHREAD do_wait() should do the same for any thread, only sys_ptrace() is "bound" to the single thread. However do_wait(WEXITED) succeeds but does not release a traced natural child unless the caller is the tracer. Test-case: void *tfunc(void *arg) { assert(ptrace(PTRACE_ATTACH, (long)arg, 0,0) == 0); pause(); return NULL; } int main(void) { pthread_t thr; pid_t pid, stat, ret; pid = fork(); if (!pid) { pause(); assert(0); } assert(pthread_create(&thr, NULL, tfunc, (void*)(long)pid) == 0); assert(waitpid(-1, &stat, 0) == pid); assert(WIFSTOPPED(stat)); kill(pid, SIGKILL); assert(waitpid(-1, &stat, 0) == pid); assert(WIFSIGNALED(stat) && WTERMSIG(stat) == SIGKILL); ret = waitpid(pid, &stat, 0); if (ret < 0) return 0; printf("WTF? %d is dead, but: wait=%d stat=%x\n", pid, ret, stat); return 1; } Note that the main thread simply does pid = fork(); kill(pid, SIGKILL); and then without the patch wait4(WEXITED) succeeds twice and reports WTERMSIG(stat) == SIGKILL. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Tejun Heo <tj@kernel.org>
2011-06-24 23:34:06 +08:00
return !same_thread_group(child->real_parent, child->parent);
}
static inline void ptrace_unlink(struct task_struct *child)
{
if (unlikely(child->ptrace))
__ptrace_unlink(child);
}
int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
unsigned long data);
int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
unsigned long data);
/**
* ptrace_parent - return the task that is tracing the given task
* @task: task to consider
*
* Returns %NULL if no one is tracing @task, or the &struct task_struct
* pointer to its tracer.
*
* Must called under rcu_read_lock(). The pointer returned might be kept
* live only by RCU. During exec, this may be called with task_lock() held
* on @task, still held from when check_unsafe_exec() was called.
*/
static inline struct task_struct *ptrace_parent(struct task_struct *task)
{
if (unlikely(task->ptrace))
return rcu_dereference(task->parent);
return NULL;
}
/**
* ptrace_event_enabled - test whether a ptrace event is enabled
* @task: ptracee of interest
* @event: %PTRACE_EVENT_* to test
*
* Test whether @event is enabled for ptracee @task.
*
* Returns %true if @event is enabled, %false otherwise.
*/
static inline bool ptrace_event_enabled(struct task_struct *task, int event)
{
return task->ptrace & PT_EVENT_FLAG(event);
}
tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in <linux/tracehook.h>. There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file <linux/tracehook.h>. This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Reviewed-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:43 +08:00
/**
* ptrace_event - possibly stop for a ptrace event notification
* @event: %PTRACE_EVENT_* value to report
tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in <linux/tracehook.h>. There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file <linux/tracehook.h>. This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Reviewed-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:43 +08:00
* @message: value for %PTRACE_GETEVENTMSG to return
*
* Check whether @event is enabled and, if so, report @event and @message
* to the ptrace parent.
tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in <linux/tracehook.h>. There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file <linux/tracehook.h>. This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Reviewed-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:43 +08:00
*
* Called without locks.
*/
static inline void ptrace_event(int event, unsigned long message)
tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in <linux/tracehook.h>. There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file <linux/tracehook.h>. This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Reviewed-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:43 +08:00
{
if (unlikely(ptrace_event_enabled(current, event))) {
current->ptrace_message = message;
ptrace_notify((event << 8) | SIGTRAP);
} else if (event == PTRACE_EVENT_EXEC) {
/* legacy EXEC report via SIGTRAP */
if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED)
send_sig(SIGTRAP, current, 0);
}
tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in <linux/tracehook.h>. There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file <linux/tracehook.h>. This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Reviewed-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:43 +08:00
}
/**
* ptrace_init_task - initialize ptrace state for a new child
* @child: new child task
* @ptrace: true if child should be ptrace'd by parent's tracer
*
* This is called immediately after adding @child to its parent's children
* list. @ptrace is false in the normal case, and true to ptrace @child.
*
* Called with current's siglock and write_lock_irq(&tasklist_lock) held.
*/
static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
{
INIT_LIST_HEAD(&child->ptrace_entry);
INIT_LIST_HEAD(&child->ptraced);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
atomic_set(&child->ptrace_bp_refcnt, 1);
#endif
child->jobctl = 0;
child->ptrace = 0;
child->parent = child->real_parent;
if (unlikely(ptrace) && current->ptrace) {
child->ptrace = current->ptrace;
__ptrace_link(child, current->parent);
ptrace: dont send SIGSTOP on auto-attach if PT_SEIZED The fake SIGSTOP during attach has numerous problems. PTRACE_SEIZE is already fine, but we have basically the same problems is SIGSTOP is sent on auto-attach, the tracer can't know if this signal signal should be cancelled or not. Change ptrace_event() to set JOBCTL_TRAP_STOP if the new child is PT_SEIZED, this triggers the PTRACE_EVENT_STOP report. Thereafter a PT_SEIZED task can never report the bogus SIGSTOP. Test-case: #define PTRACE_SEIZE 0x4206 #define PTRACE_SEIZE_DEVEL 0x80000000 #define PTRACE_EVENT_STOP 7 #define WEVENT(s) ((s & 0xFF0000) >> 16) int main(void) { int child, grand_child, status; long message; child = fork(); if (!child) { kill(getpid(), SIGSTOP); fork(); assert(0); return 0x23; } assert(ptrace(PTRACE_SEIZE, child, 0,PTRACE_SEIZE_DEVEL) == 0); assert(wait(&status) == child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACEFORK) == 0); assert(ptrace(PTRACE_CONT, child, 0,0) == 0); assert(waitpid(child, &status, 0) == child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP); assert(WEVENT(status) == PTRACE_EVENT_FORK); assert(ptrace(PTRACE_GETEVENTMSG, child, 0, &message) == 0); grand_child = message; assert(waitpid(grand_child, &status, 0) == grand_child); assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP); assert(WEVENT(status) == PTRACE_EVENT_STOP); kill(child, SIGKILL); kill(grand_child, SIGKILL); return 0; } Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Tejun Heo <tj@kernel.org>
2011-07-09 01:14:17 +08:00
if (child->ptrace & PT_SEIZED)
task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
else
sigaddset(&child->pending.signal, SIGSTOP);
set_tsk_thread_flag(child, TIF_SIGPENDING);
}
}
/**
* ptrace_release_task - final ptrace-related cleanup of a zombie being reaped
* @task: task in %EXIT_DEAD state
*
* Called with write_lock(&tasklist_lock) held.
*/
static inline void ptrace_release_task(struct task_struct *task)
{
BUG_ON(!list_empty(&task->ptraced));
ptrace_unlink(task);
BUG_ON(!list_empty(&task->ptrace_entry));
}
#ifndef force_successful_syscall_return
/*
* System call handlers that, upon successful completion, need to return a
* negative value should call force_successful_syscall_return() right before
* returning. On architectures where the syscall convention provides for a
* separate error flag (e.g., alpha, ia64, ppc{,64}, sparc{,64}, possibly
* others), this macro can be used to ensure that the error flag will not get
* set. On architectures which do not support a separate error flag, the macro
* is a no-op and the spurious error condition needs to be filtered out by some
* other means (e.g., in user-level, by passing an extra argument to the
* syscall handler, or something along those lines).
*/
#define force_successful_syscall_return() do { } while (0)
#endif
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-04 03:23:06 +08:00
#ifndef is_syscall_success
/*
* On most systems we can tell if a syscall is a success based on if the retval
* is an error value. On some systems like ia64 and powerpc they have different
* indicators of success/failure and must define their own.
*/
#define is_syscall_success(regs) (!IS_ERR_VALUE((unsigned long)(regs_return_value(regs))))
#endif
/*
* <asm/ptrace.h> should define the following things inside #ifdef __KERNEL__.
*
* These do-nothing inlines are used when the arch does not
* implement single-step. The kerneldoc comments are here
* to document the interface for all arch definitions.
*/
#ifndef arch_has_single_step
/**
* arch_has_single_step - does this CPU support user-mode single-step?
*
* If this is defined, then there must be function declarations or
* inlines for user_enable_single_step() and user_disable_single_step().
* arch_has_single_step() should evaluate to nonzero iff the machine
* supports instruction single-step for user mode.
* It can be a constant or it can test a CPU feature bit.
*/
#define arch_has_single_step() (0)
/**
* user_enable_single_step - single-step in user-mode task
* @task: either current or a task stopped in %TASK_TRACED
*
* This can only be called when arch_has_single_step() has returned nonzero.
* Set @task so that when it returns to user mode, it will trap after the
* next single instruction executes. If arch_has_block_step() is defined,
* this must clear the effects of user_enable_block_step() too.
*/
static inline void user_enable_single_step(struct task_struct *task)
{
BUG(); /* This can never be called. */
}
/**
* user_disable_single_step - cancel user-mode single-step
* @task: either current or a task stopped in %TASK_TRACED
*
* Clear @task of the effects of user_enable_single_step() and
* user_enable_block_step(). This can be called whether or not either
* of those was ever called on @task, and even if arch_has_single_step()
* returned zero.
*/
static inline void user_disable_single_step(struct task_struct *task)
{
}
ptrace: move user_enable_single_step & co prototypes to linux/ptrace.h While in theory user_enable_single_step/user_disable_single_step/ user_enable_blockstep could also be provided as an inline or macro there's no good reason to do so, and having the prototype in one places keeps code size and confusion down. Roland said: The original thought there was that user_enable_single_step() et al might well be only an instruction or three on a sane machine (as if we have any of those!), and since there is only one call site inlining would be beneficial. But I agree that there is no strong reason to care about inlining it. As to the arch changes, there is only one thought I'd add to the record. It was always my thinking that for an arch where PTRACE_SINGLESTEP does text-modifying breakpoint insertion, user_enable_single_step() should not be provided. That is, arch_has_single_step()=>true means that there is an arch facility with "pure" semantics that does not have any unexpected side effects. Inserting a breakpoint might do very unexpected strange things in multi-threaded situations. Aside from that, it is a peculiar side effect that user_{enable,disable}_single_step() should cause COW de-sharing of text pages and so forth. For PTRACE_SINGLESTEP, all these peculiarities are the status quo ante for that arch, so having arch_ptrace() itself do those is one thing. But for building other things in the future, it is nicer to have a uniform "pure" semantics that arch-independent code can expect. OTOH, all such arch issues are really up to the arch maintainer. As of today, there is nothing but ptrace using user_enable_single_step() et al so it's a distinction without a practical difference. If/when there are other facilities that use user_enable_single_step() and might care, the affected arch's can revisit the question when someone cares about the quality of the arch support for said new facility. Signed-off-by: Christoph Hellwig <hch@lst.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-11 07:22:46 +08:00
#else
extern void user_enable_single_step(struct task_struct *);
extern void user_disable_single_step(struct task_struct *);
#endif /* arch_has_single_step */
#ifndef arch_has_block_step
/**
* arch_has_block_step - does this CPU support user-mode block-step?
*
* If this is defined, then there must be a function declaration or inline
* for user_enable_block_step(), and arch_has_single_step() must be defined
* too. arch_has_block_step() should evaluate to nonzero iff the machine
* supports step-until-branch for user mode. It can be a constant or it
* can test a CPU feature bit.
*/
#define arch_has_block_step() (0)
/**
* user_enable_block_step - step until branch in user-mode task
* @task: either current or a task stopped in %TASK_TRACED
*
* This can only be called when arch_has_block_step() has returned nonzero,
* and will never be called when single-instruction stepping is being used.
* Set @task so that when it returns to user mode, it will trap after the
* next branch or trap taken.
*/
static inline void user_enable_block_step(struct task_struct *task)
{
BUG(); /* This can never be called. */
}
ptrace: move user_enable_single_step & co prototypes to linux/ptrace.h While in theory user_enable_single_step/user_disable_single_step/ user_enable_blockstep could also be provided as an inline or macro there's no good reason to do so, and having the prototype in one places keeps code size and confusion down. Roland said: The original thought there was that user_enable_single_step() et al might well be only an instruction or three on a sane machine (as if we have any of those!), and since there is only one call site inlining would be beneficial. But I agree that there is no strong reason to care about inlining it. As to the arch changes, there is only one thought I'd add to the record. It was always my thinking that for an arch where PTRACE_SINGLESTEP does text-modifying breakpoint insertion, user_enable_single_step() should not be provided. That is, arch_has_single_step()=>true means that there is an arch facility with "pure" semantics that does not have any unexpected side effects. Inserting a breakpoint might do very unexpected strange things in multi-threaded situations. Aside from that, it is a peculiar side effect that user_{enable,disable}_single_step() should cause COW de-sharing of text pages and so forth. For PTRACE_SINGLESTEP, all these peculiarities are the status quo ante for that arch, so having arch_ptrace() itself do those is one thing. But for building other things in the future, it is nicer to have a uniform "pure" semantics that arch-independent code can expect. OTOH, all such arch issues are really up to the arch maintainer. As of today, there is nothing but ptrace using user_enable_single_step() et al so it's a distinction without a practical difference. If/when there are other facilities that use user_enable_single_step() and might care, the affected arch's can revisit the question when someone cares about the quality of the arch support for said new facility. Signed-off-by: Christoph Hellwig <hch@lst.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-11 07:22:46 +08:00
#else
extern void user_enable_block_step(struct task_struct *);
#endif /* arch_has_block_step */
#ifdef ARCH_HAS_USER_SINGLE_STEP_INFO
extern void user_single_step_siginfo(struct task_struct *tsk,
struct pt_regs *regs, siginfo_t *info);
#else
static inline void user_single_step_siginfo(struct task_struct *tsk,
struct pt_regs *regs, siginfo_t *info)
{
memset(info, 0, sizeof(*info));
info->si_signo = SIGTRAP;
}
#endif
#ifndef arch_ptrace_stop_needed
/**
* arch_ptrace_stop_needed - Decide whether arch_ptrace_stop() should be called
* @code: current->exit_code value ptrace will stop with
* @info: siginfo_t pointer (or %NULL) for signal ptrace will stop with
*
* This is called with the siglock held, to decide whether or not it's
* necessary to release the siglock and call arch_ptrace_stop() with the
* same @code and @info arguments. It can be defined to a constant if
* arch_ptrace_stop() is never required, or always is. On machines where
* this makes sense, it should be defined to a quick test to optimize out
* calling arch_ptrace_stop() when it would be superfluous. For example,
* if the thread has not been back to user mode since the last stop, the
* thread state might indicate that nothing needs to be done.
*/
#define arch_ptrace_stop_needed(code, info) (0)
#endif
#ifndef arch_ptrace_stop
/**
* arch_ptrace_stop - Do machine-specific work before stopping for ptrace
* @code: current->exit_code value ptrace will stop with
* @info: siginfo_t pointer (or %NULL) for signal ptrace will stop with
*
* This is called with no locks held when arch_ptrace_stop_needed() has
* just returned nonzero. It is allowed to block, e.g. for user memory
* access. The arch can have machine-specific work to be done before
* ptrace stops. On ia64, register backing store gets written back to user
* memory here. Since this can be costly (requires dropping the siglock),
* we only do it when the arch requires it for this particular stop, as
* indicated by arch_ptrace_stop_needed().
*/
#define arch_ptrace_stop(code, info) do { } while (0)
#endif
#ifndef current_pt_regs
#define current_pt_regs() task_pt_regs(current)
#endif
#ifndef ptrace_signal_deliver
#define ptrace_signal_deliver() ((void)0)
#endif
/*
* unlike current_pt_regs(), this one is equal to task_pt_regs(current)
* on *all* architectures; the only reason to have a per-arch definition
* is optimisation.
*/
#ifndef signal_pt_regs
#define signal_pt_regs() task_pt_regs(current)
#endif
#ifndef current_user_stack_pointer
#define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
#endif
extern int task_current_syscall(struct task_struct *target, long *callno,
unsigned long args[6], unsigned int maxargs,
unsigned long *sp, unsigned long *pc);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
extern int ptrace_get_breakpoints(struct task_struct *tsk);
extern void ptrace_put_breakpoints(struct task_struct *tsk);
#else
static inline void ptrace_put_breakpoints(struct task_struct *tsk) { }
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
#endif