[PATCH v3 1/2] gdb: Make tagged pointer support configurable.

["Schimpe, Christina" <christina.schimpe@intel.com>]

From: Christina Schimpe <christina.schimpe@intel.com>

The gdbarch function gdbarch_remove_non_address_bits adjusts addresses to
enable debugging of programs with tagged pointers on Linux, for instance for
ARM's feature top byte ignore (TBI).
Once the function is implemented for an architecture, it adjusts addresses for
memory access, breakpoints and watchpoints.

Linear address masking (LAM) is Intel's (R) implementation of tagged
pointer support.  It requires certain adaptions to GDB's tagged pointer
support due to the following:
- LAM supports address tagging for data accesses only.  Thus, specifying
  breakpoints on tagged addresses is not a valid use case.
- In contrast to the implementation for ARM's TBI, the Linux kernel supports
  tagged pointers for memory access.

This patch makes GDB's tagged pointer support configurable such that it is
possible to enable the address adjustment for a specific feature only (e.g
memory access, breakpoints or watchpoints).  This way, one can make sure
that addresses are only adjusted when necessary.  In case of LAM, this
avoids unnecessary parsing of the /proc/<pid>/status file to get the
untag mask.
---
 gdb/aarch64-linux-nat.c   |  2 +-
 gdb/aarch64-linux-tdep.c  | 13 ++++----
 gdb/aarch64-tdep.c        | 17 ++++++----
 gdb/aarch64-tdep.h        |  6 ++++
 gdb/breakpoint.c          |  5 +--
 gdb/gdbarch-gen.h         | 49 ++++++++++++++++++++++-------
 gdb/gdbarch.c             | 66 ++++++++++++++++++++++++++++++++-------
 gdb/gdbarch_components.py | 53 ++++++++++++++++++++++++++-----
 gdb/target.c              |  3 +-
 9 files changed, 168 insertions(+), 46 deletions(-)

diff --git a/gdb/aarch64-linux-nat.c b/gdb/aarch64-linux-nat.c
index 4b2a0ba9f7b..ec07a897094 100644
--- a/gdb/aarch64-linux-nat.c
+++ b/gdb/aarch64-linux-nat.c
@@ -961,7 +961,7 @@ aarch64_linux_nat_target::stopped_data_address (CORE_ADDR *addr_p)
      kernel can potentially be tagged addresses.  */
   struct gdbarch *gdbarch = thread_architecture (inferior_ptid);
   const CORE_ADDR addr_trap
-    = gdbarch_remove_non_address_bits (gdbarch, (CORE_ADDR) siginfo.si_addr);
+    = aarch64_remove_non_address_bits (gdbarch, (CORE_ADDR) siginfo.si_addr);
 
   /* Check if the address matches any watched address.  */
   state = aarch64_get_debug_reg_state (inferior_ptid.pid ());
diff --git a/gdb/aarch64-linux-tdep.c b/gdb/aarch64-linux-tdep.c
index a1296a8f0c7..bf5ce72aa5f 100644
--- a/gdb/aarch64-linux-tdep.c
+++ b/gdb/aarch64-linux-tdep.c
@@ -2456,7 +2456,7 @@ static bool
 aarch64_linux_tagged_address_p (struct gdbarch *gdbarch, CORE_ADDR address)
 {
   /* Remove the top byte for the memory range check.  */
-  address = gdbarch_remove_non_address_bits (gdbarch, address);
+  address = aarch64_remove_non_address_bits (gdbarch, address);
 
   /* Check if the page that contains ADDRESS is mapped with PROT_MTE.  */
   if (!linux_address_in_memtag_page (address))
@@ -2478,7 +2478,7 @@ aarch64_linux_memtag_matches_p (struct gdbarch *gdbarch,
 
   /* Fetch the allocation tag for ADDRESS.  */
   std::optional<CORE_ADDR> atag
-    = aarch64_mte_get_atag (gdbarch_remove_non_address_bits (gdbarch, addr));
+    = aarch64_mte_get_atag (aarch64_remove_non_address_bits (gdbarch, addr));
 
   if (!atag.has_value ())
     return true;
@@ -2517,7 +2517,7 @@ aarch64_linux_set_memtags (struct gdbarch *gdbarch, struct value *address,
   else
     {
       /* Remove the top byte.  */
-      addr = gdbarch_remove_non_address_bits (gdbarch, addr);
+      addr = aarch64_remove_non_address_bits (gdbarch, addr);
 
       /* With G being the number of tag granules and N the number of tags
 	 passed in, we can have the following cases:
@@ -2566,7 +2566,7 @@ aarch64_linux_get_memtag (struct gdbarch *gdbarch, struct value *address,
   else
     {
       /* Remove the top byte.  */
-      addr = gdbarch_remove_non_address_bits (gdbarch, addr);
+      addr = aarch64_remove_non_address_bits (gdbarch, addr);
       std::optional<CORE_ADDR> atag = aarch64_mte_get_atag (addr);
 
       if (!atag.has_value ())
@@ -2640,8 +2640,9 @@ aarch64_linux_report_signal_info (struct gdbarch *gdbarch,
       uiout->text ("\n");
 
       std::optional<CORE_ADDR> atag
-	= aarch64_mte_get_atag (gdbarch_remove_non_address_bits (gdbarch,
-								 fault_addr));
+	= aarch64_mte_get_atag (
+	    aarch64_remove_non_address_bits (gdbarch, fault_addr));
+
       gdb_byte ltag = aarch64_mte_get_ltag (fault_addr);
 
       if (!atag.has_value ())
diff --git a/gdb/aarch64-tdep.c b/gdb/aarch64-tdep.c
index e4bca6c6632..ba1dc3d5844 100644
--- a/gdb/aarch64-tdep.c
+++ b/gdb/aarch64-tdep.c
@@ -4088,10 +4088,9 @@ aarch64_stack_frame_destroyed_p (struct gdbarch *gdbarch, CORE_ADDR pc)
   return streq (inst.opcode->name, "ret");
 }
 
-/* AArch64 implementation of the remove_non_address_bits gdbarch hook.  Remove
-   non address bits from a pointer value.  */
+/* See aarch64-tdep.h.  */
 
-static CORE_ADDR
+CORE_ADDR
 aarch64_remove_non_address_bits (struct gdbarch *gdbarch, CORE_ADDR pointer)
 {
   /* By default, we assume TBI and discard the top 8 bits plus the VA range
@@ -4585,9 +4584,15 @@ aarch64_gdbarch_init (struct gdbarch_info info, struct gdbarch_list *arches)
     tdep->ra_sign_state_regnum = ra_sign_state_offset + num_regs;
 
   /* Architecture hook to remove bits of a pointer that are not part of the
-     address, like memory tags (MTE) and pointer authentication signatures.  */
-  set_gdbarch_remove_non_address_bits (gdbarch,
-				       aarch64_remove_non_address_bits);
+     address, like memory tags (MTE) and pointer authentication signatures.
+     Configure address adjustment for watch-, breakpoints and memory
+     transfer.  */
+  set_gdbarch_remove_non_address_bits_watchpoint
+    (gdbarch, aarch64_remove_non_address_bits);
+  set_gdbarch_remove_non_address_bits_breakpoint
+    (gdbarch, aarch64_remove_non_address_bits);
+  set_gdbarch_remove_non_address_bits_memory
+    (gdbarch, aarch64_remove_non_address_bits);
 
   /* SME pseudo-registers.  */
   if (tdep->has_sme ())
diff --git a/gdb/aarch64-tdep.h b/gdb/aarch64-tdep.h
index 0e6024bfcbc..a9c8815f8be 100644
--- a/gdb/aarch64-tdep.h
+++ b/gdb/aarch64-tdep.h
@@ -203,4 +203,10 @@ void aarch64_displaced_step_fixup (struct gdbarch *gdbarch,
 
 bool aarch64_displaced_step_hw_singlestep (struct gdbarch *gdbarch);
 
+/* AArch64 implementation of the remove_non_address_bits gdbarch hooks.
+   Remove non address bits from a pointer value.  */
+
+CORE_ADDR aarch64_remove_non_address_bits (struct gdbarch *gdbarch,
+					   CORE_ADDR pointer);
+
 #endif /* aarch64-tdep.h */
diff --git a/gdb/breakpoint.c b/gdb/breakpoint.c
index a973518ac5f..8c2d9d247ec 100644
--- a/gdb/breakpoint.c
+++ b/gdb/breakpoint.c
@@ -2238,7 +2238,8 @@ update_watchpoint (struct watchpoint *b, bool reparse)
 		  loc->gdbarch = v->type ()->arch ();
 		  loc->pspace = wp_pspace;
 		  loc->address
-		    = gdbarch_remove_non_address_bits (loc->gdbarch, addr);
+		    = gdbarch_remove_non_address_bits_watchpoint (loc->gdbarch,
+								  addr);
 		  b->add_location (*loc);
 
 		  if (bitsize != 0)
@@ -7477,7 +7478,7 @@ adjust_breakpoint_address (struct gdbarch *gdbarch,
 	}
 
       adjusted_bpaddr
-	= gdbarch_remove_non_address_bits (gdbarch, adjusted_bpaddr);
+	= gdbarch_remove_non_address_bits_breakpoint (gdbarch, adjusted_bpaddr);
 
       /* An adjusted breakpoint address can significantly alter
 	 a user's expectations.  Print a warning if an adjustment
diff --git a/gdb/gdbarch-gen.h b/gdb/gdbarch-gen.h
index b982fd7cd09..9fda85f860f 100644
--- a/gdb/gdbarch-gen.h
+++ b/gdb/gdbarch-gen.h
@@ -684,19 +684,46 @@ extern CORE_ADDR gdbarch_addr_bits_remove (struct gdbarch *gdbarch, CORE_ADDR ad
 extern void set_gdbarch_addr_bits_remove (struct gdbarch *gdbarch, gdbarch_addr_bits_remove_ftype *addr_bits_remove);
 
 /* On some architectures, not all bits of a pointer are significant.
-   On AArch64, for example, the top bits of a pointer may carry a "tag", which
-   can be ignored by the kernel and the hardware.  The "tag" can be regarded as
-   additional data associated with the pointer, but it is not part of the address.
+   On AArch64 and amd64, for example, the top bits of a pointer may carry a
+   "tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+   regarded as additional data associated with the pointer, but it is not part
+   of the address.
 
    Given a pointer for the architecture, this hook removes all the
-   non-significant bits and sign-extends things as needed.  It gets used to remove
-   non-address bits from data pointers (for example, removing the AArch64 MTE tag
-   bits from a pointer) and from code pointers (removing the AArch64 PAC signature
-   from a pointer containing the return address). */
-
-typedef CORE_ADDR (gdbarch_remove_non_address_bits_ftype) (struct gdbarch *gdbarch, CORE_ADDR pointer);
-extern CORE_ADDR gdbarch_remove_non_address_bits (struct gdbarch *gdbarch, CORE_ADDR pointer);
-extern void set_gdbarch_remove_non_address_bits (struct gdbarch *gdbarch, gdbarch_remove_non_address_bits_ftype *remove_non_address_bits);
+   non-significant bits and sign-extends things as needed.  It gets used to
+   remove non-address bits from pointers used for watchpoints. */
+
+typedef CORE_ADDR (gdbarch_remove_non_address_bits_watchpoint_ftype) (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern CORE_ADDR gdbarch_remove_non_address_bits_watchpoint (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern void set_gdbarch_remove_non_address_bits_watchpoint (struct gdbarch *gdbarch, gdbarch_remove_non_address_bits_watchpoint_ftype *remove_non_address_bits_watchpoint);
+
+/* On some architectures, not all bits of a pointer are significant.
+   On AArch64 and amd64, for example, the top bits of a pointer may carry a
+   "tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+   regarded as additional data associated with the pointer, but it is not part
+   of the address.
+
+   Given a pointer for the architecture, this hook removes all the
+   non-significant bits and sign-extends things as needed.  It gets used to
+   remove non-address bits from pointers used for breakpoints. */
+
+typedef CORE_ADDR (gdbarch_remove_non_address_bits_breakpoint_ftype) (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern CORE_ADDR gdbarch_remove_non_address_bits_breakpoint (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern void set_gdbarch_remove_non_address_bits_breakpoint (struct gdbarch *gdbarch, gdbarch_remove_non_address_bits_breakpoint_ftype *remove_non_address_bits_breakpoint);
+
+/* On some architectures, not all bits of a pointer are significant.
+   On AArch64 and amd64, for example, the top bits of a pointer may carry a
+   "tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+   regarded as additional data associated with the pointer, but it is not part
+   of the address.
+
+   Given a pointer for the architecture, this hook removes all the
+   non-significant bits and sign-extends things as needed.  It gets used to
+   remove non-address bits from any pointer used to access memory. */
+
+typedef CORE_ADDR (gdbarch_remove_non_address_bits_memory_ftype) (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern CORE_ADDR gdbarch_remove_non_address_bits_memory (struct gdbarch *gdbarch, CORE_ADDR pointer);
+extern void set_gdbarch_remove_non_address_bits_memory (struct gdbarch *gdbarch, gdbarch_remove_non_address_bits_memory_ftype *remove_non_address_bits_memory);
 
 /* Return a string representation of the memory tag TAG. */
 
diff --git a/gdb/gdbarch.c b/gdb/gdbarch.c
index 58e9ebbdc59..99a54a38d61 100644
--- a/gdb/gdbarch.c
+++ b/gdb/gdbarch.c
@@ -143,7 +143,9 @@ struct gdbarch
   int frame_red_zone_size = 0;
   gdbarch_convert_from_func_ptr_addr_ftype *convert_from_func_ptr_addr = convert_from_func_ptr_addr_identity;
   gdbarch_addr_bits_remove_ftype *addr_bits_remove = core_addr_identity;
-  gdbarch_remove_non_address_bits_ftype *remove_non_address_bits = default_remove_non_address_bits;
+  gdbarch_remove_non_address_bits_watchpoint_ftype *remove_non_address_bits_watchpoint = default_remove_non_address_bits;
+  gdbarch_remove_non_address_bits_breakpoint_ftype *remove_non_address_bits_breakpoint = default_remove_non_address_bits;
+  gdbarch_remove_non_address_bits_memory_ftype *remove_non_address_bits_memory = default_remove_non_address_bits;
   gdbarch_memtag_to_string_ftype *memtag_to_string = default_memtag_to_string;
   gdbarch_tagged_address_p_ftype *tagged_address_p = default_tagged_address_p;
   gdbarch_memtag_matches_p_ftype *memtag_matches_p = default_memtag_matches_p;
@@ -407,7 +409,9 @@ verify_gdbarch (struct gdbarch *gdbarch)
   /* Skip verify of frame_red_zone_size, invalid_p == 0 */
   /* Skip verify of convert_from_func_ptr_addr, invalid_p == 0 */
   /* Skip verify of addr_bits_remove, invalid_p == 0 */
-  /* Skip verify of remove_non_address_bits, invalid_p == 0 */
+  /* Skip verify of remove_non_address_bits_watchpoint, invalid_p == 0 */
+  /* Skip verify of remove_non_address_bits_breakpoint, invalid_p == 0 */
+  /* Skip verify of remove_non_address_bits_memory, invalid_p == 0 */
   /* Skip verify of memtag_to_string, invalid_p == 0 */
   /* Skip verify of tagged_address_p, invalid_p == 0 */
   /* Skip verify of memtag_matches_p, invalid_p == 0 */
@@ -910,8 +914,14 @@ gdbarch_dump (struct gdbarch *gdbarch, struct ui_file *file)
 	      "gdbarch_dump: addr_bits_remove = <%s>\n",
 	      host_address_to_string (gdbarch->addr_bits_remove));
   gdb_printf (file,
-	      "gdbarch_dump: remove_non_address_bits = <%s>\n",
-	      host_address_to_string (gdbarch->remove_non_address_bits));
+	      "gdbarch_dump: remove_non_address_bits_watchpoint = <%s>\n",
+	      host_address_to_string (gdbarch->remove_non_address_bits_watchpoint));
+  gdb_printf (file,
+	      "gdbarch_dump: remove_non_address_bits_breakpoint = <%s>\n",
+	      host_address_to_string (gdbarch->remove_non_address_bits_breakpoint));
+  gdb_printf (file,
+	      "gdbarch_dump: remove_non_address_bits_memory = <%s>\n",
+	      host_address_to_string (gdbarch->remove_non_address_bits_memory));
   gdb_printf (file,
 	      "gdbarch_dump: memtag_to_string = <%s>\n",
 	      host_address_to_string (gdbarch->memtag_to_string));
@@ -3198,20 +3208,54 @@ set_gdbarch_addr_bits_remove (struct gdbarch *gdbarch,
 }
 
 CORE_ADDR
-gdbarch_remove_non_address_bits (struct gdbarch *gdbarch, CORE_ADDR pointer)
+gdbarch_remove_non_address_bits_watchpoint (struct gdbarch *gdbarch, CORE_ADDR pointer)
+{
+  gdb_assert (gdbarch != NULL);
+  gdb_assert (gdbarch->remove_non_address_bits_watchpoint != NULL);
+  if (gdbarch_debug >= 2)
+    gdb_printf (gdb_stdlog, "gdbarch_remove_non_address_bits_watchpoint called\n");
+  return gdbarch->remove_non_address_bits_watchpoint (gdbarch, pointer);
+}
+
+void
+set_gdbarch_remove_non_address_bits_watchpoint (struct gdbarch *gdbarch,
+						gdbarch_remove_non_address_bits_watchpoint_ftype remove_non_address_bits_watchpoint)
+{
+  gdbarch->remove_non_address_bits_watchpoint = remove_non_address_bits_watchpoint;
+}
+
+CORE_ADDR
+gdbarch_remove_non_address_bits_breakpoint (struct gdbarch *gdbarch, CORE_ADDR pointer)
+{
+  gdb_assert (gdbarch != NULL);
+  gdb_assert (gdbarch->remove_non_address_bits_breakpoint != NULL);
+  if (gdbarch_debug >= 2)
+    gdb_printf (gdb_stdlog, "gdbarch_remove_non_address_bits_breakpoint called\n");
+  return gdbarch->remove_non_address_bits_breakpoint (gdbarch, pointer);
+}
+
+void
+set_gdbarch_remove_non_address_bits_breakpoint (struct gdbarch *gdbarch,
+						gdbarch_remove_non_address_bits_breakpoint_ftype remove_non_address_bits_breakpoint)
+{
+  gdbarch->remove_non_address_bits_breakpoint = remove_non_address_bits_breakpoint;
+}
+
+CORE_ADDR
+gdbarch_remove_non_address_bits_memory (struct gdbarch *gdbarch, CORE_ADDR pointer)
 {
   gdb_assert (gdbarch != NULL);
-  gdb_assert (gdbarch->remove_non_address_bits != NULL);
+  gdb_assert (gdbarch->remove_non_address_bits_memory != NULL);
   if (gdbarch_debug >= 2)
-    gdb_printf (gdb_stdlog, "gdbarch_remove_non_address_bits called\n");
-  return gdbarch->remove_non_address_bits (gdbarch, pointer);
+    gdb_printf (gdb_stdlog, "gdbarch_remove_non_address_bits_memory called\n");
+  return gdbarch->remove_non_address_bits_memory (gdbarch, pointer);
 }
 
 void
-set_gdbarch_remove_non_address_bits (struct gdbarch *gdbarch,
-				     gdbarch_remove_non_address_bits_ftype remove_non_address_bits)
+set_gdbarch_remove_non_address_bits_memory (struct gdbarch *gdbarch,
+					    gdbarch_remove_non_address_bits_memory_ftype remove_non_address_bits_memory)
 {
-  gdbarch->remove_non_address_bits = remove_non_address_bits;
+  gdbarch->remove_non_address_bits_memory = remove_non_address_bits_memory;
 }
 
 std::string
diff --git a/gdb/gdbarch_components.py b/gdb/gdbarch_components.py
index 4006380076d..cc7c6d8677b 100644
--- a/gdb/gdbarch_components.py
+++ b/gdb/gdbarch_components.py
@@ -1232,18 +1232,55 @@ possible it should be in TARGET_READ_PC instead).
 Method(
     comment="""
 On some architectures, not all bits of a pointer are significant.
-On AArch64, for example, the top bits of a pointer may carry a "tag", which
-can be ignored by the kernel and the hardware.  The "tag" can be regarded as
-additional data associated with the pointer, but it is not part of the address.
+On AArch64 and amd64, for example, the top bits of a pointer may carry a
+"tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+regarded as additional data associated with the pointer, but it is not part
+of the address.
 
 Given a pointer for the architecture, this hook removes all the
-non-significant bits and sign-extends things as needed.  It gets used to remove
-non-address bits from data pointers (for example, removing the AArch64 MTE tag
-bits from a pointer) and from code pointers (removing the AArch64 PAC signature
-from a pointer containing the return address).
+non-significant bits and sign-extends things as needed.  It gets used to
+remove non-address bits from pointers used for watchpoints.
 """,
     type="CORE_ADDR",
-    name="remove_non_address_bits",
+    name="remove_non_address_bits_watchpoint",
+    params=[("CORE_ADDR", "pointer")],
+    predefault="default_remove_non_address_bits",
+    invalid=False,
+)
+
+Method(
+    comment="""
+On some architectures, not all bits of a pointer are significant.
+On AArch64 and amd64, for example, the top bits of a pointer may carry a
+"tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+regarded as additional data associated with the pointer, but it is not part
+of the address.
+
+Given a pointer for the architecture, this hook removes all the
+non-significant bits and sign-extends things as needed.  It gets used to
+remove non-address bits from pointers used for breakpoints.
+""",
+    type="CORE_ADDR",
+    name="remove_non_address_bits_breakpoint",
+    params=[("CORE_ADDR", "pointer")],
+    predefault="default_remove_non_address_bits",
+    invalid=False,
+)
+
+Method(
+    comment="""
+On some architectures, not all bits of a pointer are significant.
+On AArch64 and amd64, for example, the top bits of a pointer may carry a
+"tag", which can be ignored by the kernel and the hardware.  The "tag" can be
+regarded as additional data associated with the pointer, but it is not part
+of the address.
+
+Given a pointer for the architecture, this hook removes all the
+non-significant bits and sign-extends things as needed.  It gets used to
+remove non-address bits from any pointer used to access memory.
+""",
+    type="CORE_ADDR",
+    name="remove_non_address_bits_memory",
     params=[("CORE_ADDR", "pointer")],
     predefault="default_remove_non_address_bits",
     invalid=False,
diff --git a/gdb/target.c b/gdb/target.c
index 1b5aa11ed6f..b622de81e11 100644
--- a/gdb/target.c
+++ b/gdb/target.c
@@ -1608,7 +1608,8 @@ memory_xfer_partial (struct target_ops *ops, enum target_object object,
   if (len == 0)
     return TARGET_XFER_EOF;
 
-  memaddr = gdbarch_remove_non_address_bits (current_inferior ()->arch (),
+  memaddr
+   = gdbarch_remove_non_address_bits_memory (current_inferior ()->arch (),
 					     memaddr);
 
   /* Fill in READBUF with breakpoint shadows, or WRITEBUF with
-- 
2.34.1

Intel Deutschland GmbH
Registered Address: Am Campeon 10, 85579 Neubiberg, Germany
Tel: +49 89 99 8853-0, www.intel.de
Managing Directors: Sean Fennelly, Jeffrey Schneiderman, Tiffany Doon Silva
Chairperson of the Supervisory Board: Nicole Lau
Registered Office: Munich
Commercial Register: Amtsgericht Muenchen HRB 186928