Files
binutils-gdb/gdb/linux-nat.h
Your Name 21c90ca166 gdb/aarch64: restore in-order watchpoint matching
At Red Hat we have an out of tree AArch64 watchpoint test which broke
after this commit:

  commit cf16ab724a
  Date:   Tue Mar 12 17:08:18 2024 +0100

      [gdb/tdep] Fix gdb.base/watch-bitfields.exp on aarch64

The problem with AArch64 hardware watchpoints is that they (as I
understand it) are restricted to a minimum of 8 bytes.  This means
that, if the thing you are watching is less than 8-bytes, then there
is always scope for invalid watchpoint triggers caused by activity in
the part of the 8-bytes that are not being watched.

Or, as is the case in this RH test, multiple watchpoint are created
within an 8-byte region, and GDB can miss-identify which watchpoint
actually triggered.

Prior to the above commit the RH test was passing.  However, the test
was relying on, in the case of ambiguity, GDB selecting the first
created watchpoint.  That behaviour changed with the above commit.
Now GDB favours reporting non write breakpoints, and will only report
a write breakpoint if no non-write breakpoint exists in the same
region.

I originally posted a patch to try and tweak the existing logic to
restore enough of the original behaviour that the RH test would pass,
this can be found here (2 iterations):

  https://inbox.sourceware.org/gdb-patches/65e746b6394f04faa027e778f733eda95d20f368.1753115072.git.aburgess@redhat.com
  https://inbox.sourceware.org/gdb-patches/638cbe9b738c0c529f6370f90ba4a395711f63ae.1753971315.git.aburgess@redhat.com

Neither of these really resolved the problem, they fixed some cases,
but broke others.

Ultimately, the problem on AArch64 is that for a single watchpoint
trap, there could be multiple watchpoints that are potentially
responsible.  The existing API defined by the target_ops methods
stopped_by_watchpoint() and stopped_data_address() only allow for two
possible options:

  1. If stopped_by_watchpoint() is true then stopped_data_address()
     can return true and a single address which identifies all
     watchpoints at that single address, or

  2. If stopped_by_watchpoint() is true then stopped_data_address()
     can return false, in which case GDB will check all write
     watchpoints to see if any have changed, if they have, then GDB
     tells the user that that was the triggering watchpoint.

If we are in a situation where we have to choose between multiple
write and read watchpoints then the current API doesn't allow the
architecture specific code to tell GDB core about this case.

In this commit I propose that we change the target_ops API,
specifically, the method:

  bool target_ops::stopped_data_address (CORE_ADDR *);

will change to:

  std::vector<CORE_ADDR> target_ops::stopped_data_addresses ();

The architecture specific code can now return a set of watchpoint
addresses, allowing GDB to identify a set of watchpoints that might
have triggered.  GDB core can then select the most likely watchpoint,
and present that to the user.

As with the old API, target_ops::stopped_data_addresses should only be
called when target_ops::stopped_by_watchpoint is true, in which case
it's return values can be interpreted like this:

  a. An empty vector; this replaces the old case where false was
     returned.  GDB should check all the write watchpoints and select
     the one that changed as the responsible watchpoint.

  b. A single entry vector; all targets except AArch64 currently
     return at most a single entry vector.  The single address
     indicates the watchpoint(s) that triggered.

  c. A multi-entry vector; currently AArch64 only.  These addresses
     indicate the set of watchpoints that might have triggered.  GDB
     will check the write watchpoints to see which (if any) changed,
     and if no write watchpoints changed, GDB will present the first
     access watchpoint.

In the future, we might want to improve the handling of (c) so that
GDB tells the user that multiple access watchpoints might have
triggered, and then list all of them.  This might clear up some
confusion.  But I think that can be done in the future (I don't have
an immediate plan to work on this).  I think this change is already a
good improvement.

The changes for this are pretty extensive, but here's a basic summary:

  * Within gdb/ changing the API name from stopped_data_address to
    stopped_data_addresses throughout.  Comments are updated too where
    needed.

  * For targets other than AArch64, the existing code is retained with
    as few changes as possible, we only allow for a single address to
    be returned, the address is now wrapped in a vector.  Where we
    used to return false, we now return the empty vector.

  * For AArch64, the return a vector logic is pushed through to
    gdb/nat/aarch64-hw-point.{c,h}, and aarch64_stopped_data_address
    changes to aarch64_stopped_data_addresses, and is updated to
    return a vector of addresses.

  * In infrun.c there's some updates to some debug output.

  * In breakpoint.c the interesting changes are in
    watchpoints_triggered.  The existing code has three cases to
    handle:

    (i) target_stopped_by_watchpoint returns false.  This case is
        unchanged.

    (ii) target_stopped_data_address returns false.  This case is now
         calling target_stopped_data_addresses, and checks for the
	 empty vector, but otherwise is unchanged.

    (iii) target_stopped_data_address returns true, and a single
          address.  This code calls target_stopped_data_addresses, and
	  now handles the possibility of a vector containing multiple
	  entries.  We need to first loop over every watchpoint
	  setting its triggered status to 'no', then we check every
	  address in the vector setting matching watchpoint's
	  triggered status to 'yes'.  But the actual logic for if a
	  watchpoint matches an address or not is unchanged.

    The important thing to notice here is that in case (iii), before
    this patch, GDB could already set _multiple_ watchpoints to
    triggered.  For example, setting a read and write watchpoint on
    the same address would result in multiple watchpoints being marked
    as triggered.  This patch just extends this so that multiple
    watchpoints, at multiple addresses, can now be marked as
    triggered.

  * In remote.c there is an interesting change.  We need to allow
    gdbserver to pass the multiple addresses back to GDB.  To achieve
    this, I now allow multiple 'watch', 'rwatch', and 'awatch' tokens
    in a 'T' stop reply packet.  This change is largely backward
    compatible.  For old versions of GDB, GDB will just use the last
    such token as the watchpoint stop address.  For new GDBs, all of
    the addresses are collected and returned from the
    target_ops::stopped_data_addresses call.  If a new GDB connects to
    an old gdbserver then it'll only get a single watchpoint address
    in the 'T' packet, but that's no worse than we are now, and will
    not cause a GDB crash, GDB will just end up checking a restricted
    set of watchpoints (which is where we are right now).

  * In gdbserver/ the changes are pretty similar.  The API is renamed
    from ::stopped_data_address to ::stopped_data_addresses, and
    ::low_stopped_data_address to ::low_stopped_data_addresses.

  * For all targets except AArch64, the existing code is retained, we
    just wrap the single address into a vector.

  * For AArch64, we call aarch64_stopped_data_addresses, which returns
    the required vector.

For testing, I've built GDB on GNU/Linux for i386, x86-64, PPC64le,
ARM, and AArch64.  That still leaves a lot of targets possibly
impacted by this change as untested.  Which is a risk.  I certainly
wouldn't want to push this patch until after GDB 17 branches so we
have time to find and fix any regressions that are introduced.

Bug: https://sourceware.org/bugzilla/show_bug.cgi?id=33240
Bug: https://sourceware.org/bugzilla/show_bug.cgi?id=33252
2025-08-07 14:43:49 +01:00

349 lines
11 KiB
C++

/* Native debugging support for GNU/Linux (LWP layer).
Copyright (C) 2000-2025 Free Software Foundation, Inc.
This file is part of GDB.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#ifndef GDB_LINUX_NAT_H
#define GDB_LINUX_NAT_H
#include "nat/linux-nat.h"
#include "inf-ptrace.h"
#include "target.h"
#include <signal.h>
/* A prototype generic GNU/Linux target. A concrete instance should
override it with local methods. */
class linux_nat_target : public inf_ptrace_target
{
public:
linux_nat_target ();
~linux_nat_target () override = 0;
thread_control_capabilities get_thread_control_capabilities () override
{ return tc_schedlock; }
void create_inferior (const char *, const std::string &,
char **, int) override;
void attach (const char *, int) override;
void detach (inferior *, int) override;
void resume (ptid_t, int, enum gdb_signal) override;
ptid_t wait (ptid_t, struct target_waitstatus *, target_wait_flags) override;
void pass_signals (gdb::array_view<const unsigned char>) override;
enum target_xfer_status xfer_partial (enum target_object object,
const char *annex,
gdb_byte *readbuf,
const gdb_byte *writebuf,
ULONGEST offset, ULONGEST len,
ULONGEST *xfered_len) override;
void kill () override;
void mourn_inferior () override;
bool thread_alive (ptid_t ptid) override;
void update_thread_list () override;
std::string pid_to_str (ptid_t) override;
const char *thread_name (struct thread_info *) override;
bool stopped_by_watchpoint () override;
std::vector<CORE_ADDR> stopped_data_addresses () override;
bool stopped_by_sw_breakpoint () override;
bool supports_stopped_by_sw_breakpoint () override;
bool stopped_by_hw_breakpoint () override;
bool supports_stopped_by_hw_breakpoint () override;
void thread_events (bool) override;
bool supports_set_thread_options (gdb_thread_options options) override;
bool can_async_p () override;
bool supports_non_stop () override;
bool always_non_stop_p () override;
void async (bool) override;
void stop (ptid_t) override;
bool supports_multi_process () override;
bool supports_disable_randomization () override;
int core_of_thread (ptid_t ptid) override;
bool filesystem_is_local () override;
int fileio_open (struct inferior *inf, const char *filename,
int flags, int mode, int warn_if_slow,
fileio_error *target_errno) override;
std::optional<std::string>
fileio_readlink (struct inferior *inf,
const char *filename,
fileio_error *target_errno) override;
int fileio_lstat (struct inferior *inf, const char *filename,
struct stat *sb, fileio_error *target_errno) override;
int fileio_unlink (struct inferior *inf,
const char *filename,
fileio_error *target_errno) override;
int insert_fork_catchpoint (int) override;
int remove_fork_catchpoint (int) override;
int insert_vfork_catchpoint (int) override;
int remove_vfork_catchpoint (int) override;
int insert_exec_catchpoint (int) override;
int remove_exec_catchpoint (int) override;
int set_syscall_catchpoint (int pid, bool needed, int any_count,
gdb::array_view<const int> syscall_counts) override;
const char *pid_to_exec_file (int pid) override;
void post_attach (int) override;
void follow_fork (inferior *, ptid_t, target_waitkind, bool, bool) override;
void follow_clone (ptid_t) override;
std::vector<static_tracepoint_marker>
static_tracepoint_markers_by_strid (const char *id) override;
/* Methods that are meant to overridden by the concrete
arch-specific target instance. */
virtual void low_resume (ptid_t ptid, int step, enum gdb_signal sig)
{ inf_ptrace_target::resume (ptid, step, sig); }
virtual bool low_stopped_by_watchpoint ()
{ return false; }
virtual bool low_stopped_data_address (CORE_ADDR *addr_p)
{ return false; }
/* The method to call, if any, when a new thread is attached. */
virtual void low_new_thread (struct lwp_info *)
{}
/* The method to call, if any, when a thread is destroyed. */
virtual void low_delete_thread (struct arch_lwp_info *lp)
{
gdb_assert (lp == NULL);
}
/* The method to call, if any, when a new fork is attached. */
virtual void low_new_fork (struct lwp_info *parent, pid_t child_pid)
{}
/* The method to call, if any, when a new clone event is detected. */
virtual void low_new_clone (struct lwp_info *parent, pid_t child_lwp)
{}
/* The method to call, if any, when we have a new (from run/attach,
not fork) process to debug. The process is ptrace-stopped when
this is called. */
virtual void low_init_process (pid_t pid)
{}
/* The method to call, if any, when a process is no longer
attached. */
virtual void low_forget_process (pid_t pid)
{}
/* Hook to call prior to resuming a thread. */
virtual void low_prepare_to_resume (struct lwp_info *)
{}
/* Convert a ptrace/host siginfo object, into/from the siginfo in
the layout of the inferiors' architecture. Returns true if any
conversion was done; false otherwise, in which case the caller
does a straight memcpy. If DIRECTION is 1, then copy from INF to
PTRACE. If DIRECTION is 0, copy from PTRACE to INF. */
virtual bool low_siginfo_fixup (siginfo_t *ptrace, gdb_byte *inf,
int direction)
{ return false; }
/* SIGTRAP-like breakpoint status events recognizer. The default
recognizes SIGTRAP only. */
virtual bool low_status_is_event (int status);
protected:
void post_startup_inferior (ptid_t) override;
};
/* The final/concrete instance. */
extern linux_nat_target *linux_target;
struct arch_lwp_info;
/* Structure describing an LWP. */
struct lwp_info : intrusive_list_node<lwp_info>
{
lwp_info (ptid_t ptid)
: ptid (ptid)
{}
~lwp_info ();
DISABLE_COPY_AND_ASSIGN (lwp_info);
/* The process id of the LWP. This is a combination of the LWP id
and overall process id. */
ptid_t ptid = null_ptid;
/* If this flag is set, we need to set the event request flags the
next time we see this LWP stop. */
int must_set_ptrace_flags = 0;
/* Non-zero if we sent this LWP a SIGSTOP (but the LWP didn't report
it back yet). */
int signalled = 0;
/* Non-zero if this LWP is stopped. */
int stopped = 0;
/* Non-zero if this LWP will be/has been resumed. Note that an LWP
can be marked both as stopped and resumed at the same time. This
happens if we try to resume an LWP that has a wait status
pending. We shouldn't let the LWP run until that wait status has
been processed, but we should not report that wait status if GDB
didn't try to let the LWP run. */
int resumed = 0;
/* The last resume GDB requested on this thread. */
resume_kind last_resume_kind = resume_continue;
/* If non-zero, a pending wait status. A pending process exit is
recorded in WAITSTATUS, because W_EXITCODE(0,0) happens to be
0. */
int status = 0;
/* When 'stopped' is set, this is where the lwp last stopped, with
decr_pc_after_break already accounted for. If the LWP is
running and stepping, this is the address at which the lwp was
resumed (that is, it's the previous stop PC). If the LWP is
running and not stepping, this is 0. */
CORE_ADDR stop_pc = 0;
/* Non-zero if we were stepping this LWP. */
int step = 0;
/* The reason the LWP last stopped, if we need to track it
(breakpoint, watchpoint, etc.). */
target_stop_reason stop_reason = TARGET_STOPPED_BY_NO_REASON;
/* On architectures where it is possible to know the data address of
a triggered watchpoint, STOPPED_DATA_ADDRESS_P is non-zero, and
STOPPED_DATA_ADDRESS contains such data address. Otherwise,
STOPPED_DATA_ADDRESS_P is false, and STOPPED_DATA_ADDRESS is
undefined. Only valid if STOPPED_BY_WATCHPOINT is true. */
int stopped_data_address_p = 0;
CORE_ADDR stopped_data_address = 0;
/* Non-zero if we expect a duplicated SIGINT. */
int ignore_sigint = 0;
/* If WAITSTATUS->KIND != TARGET_WAITKIND_IGNORE, the waitstatus for
this LWP's last event. This usually corresponds to STATUS above,
however because W_EXITCODE(0,0) happens to be 0, a process exit
will be recorded here, while 'status == 0' is ambiguous. */
struct target_waitstatus waitstatus;
/* Signal whether we are in a SYSCALL_ENTRY or SYSCALL_RETURN event.
Valid values are TARGET_WAITKIND_SYSCALL_ENTRY,
TARGET_WAITKIND_SYSCALL_RETURN, or TARGET_WAITKIND_SYSCALL_IGNORE, when
not stopped at a syscall. */
target_waitkind syscall_state = TARGET_WAITKIND_IGNORE;
/* The processor core this LWP was last seen on. */
int core = -1;
/* Arch-specific additions. */
struct arch_lwp_info *arch_private = nullptr;
};
/* lwp_info iterator and range types. */
using lwp_info_iterator
= reference_to_pointer_iterator<intrusive_list<lwp_info>::iterator>;
using lwp_info_range = iterator_range<lwp_info_iterator>;
using lwp_info_safe_range = basic_safe_range<lwp_info_range>;
/* Get an iterable range over all lwps. */
lwp_info_range all_lwps ();
/* Same as the above, but safe against deletion while iterating. */
lwp_info_safe_range all_lwps_safe ();
/* Called from the LWP layer to inform the thread_db layer that PARENT
spawned CHILD. Both LWPs are currently stopped. This function
does whatever is required to have the child LWP under the
thread_db's control --- e.g., enabling event reporting. Returns
true on success, false if the process isn't using libpthread. */
extern int thread_db_notice_clone (ptid_t parent, ptid_t child);
/* Return the number of signals used by the threads library. */
extern unsigned int lin_thread_get_thread_signal_num (void);
/* Return the i-th signal used by the threads library. */
extern int lin_thread_get_thread_signal (unsigned int i);
/* Find process PID's pending signal set from /proc/pid/status. */
void linux_proc_pending_signals (int pid, sigset_t *pending,
sigset_t *blocked, sigset_t *ignored);
/* For linux_stop_lwp see nat/linux-nat.h. */
/* Stop all LWPs, synchronously. (Any events that trigger while LWPs
are being stopped are left pending.) */
extern void linux_stop_and_wait_all_lwps (void);
/* Set resumed LWPs running again, as they were before being stopped
with linux_stop_and_wait_all_lwps. (LWPS with pending events are
left stopped.) */
extern void linux_unstop_all_lwps (void);
/* Update linux-nat internal state when changing from one fork
to another. */
void linux_nat_switch_fork (ptid_t new_ptid);
/* Store the saved siginfo associated with PTID in *SIGINFO.
Return true if it was retrieved successfully, false otherwise (*SIGINFO is
uninitialized in such case). */
bool linux_nat_get_siginfo (ptid_t ptid, siginfo_t *siginfo);
#endif /* GDB_LINUX_NAT_H */