mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	James Clark <james.clark@linaro.org>,
	Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH v10 02/16] perf annotate: Handle absolute addressing in data type profiling
Date: Sat, 21 Nov 2026 00:20:38 -0300	[thread overview]
Message-ID: <20261121032052.1392234-3-acme@kernel.org> (raw)
In-Reply-To: <20261121032052.1392234-1-acme@kernel.org>

From: Arnaldo Carvalho de Melo <acme@redhat.com>

x86 accesses globals with absolute addresses, and not only in 32-bit
builds: the 64-bit kernel's __default_send_IPI_dest_field uses a disp32
the CPU sign extends, an absolute SIB with no base and no index.  From an
allmodconfig clang build, arch/x86/kernel/ipi.o:

  890:	8b 04 25 00 c3 5f ff	mov    0xffffffffff5fc300,%eax
  8b1:	89 3c 25 10 c3 5f ff	mov    %edi,0xffffffffff5fc310

llvm-objdump prints the same displacements as -0xa03d00 and -0xa03cf0.
The operand parser only recognized offset(reg), so the resolver skipped
the access as not a memory reference.

Parse a bare hex number as an absolute memory operand, including the
negative disp32 llvm-objdump prints, and use the address in the resolver.
Jump, call and loop targets are left out; the displacement is sign
extended for 64-bit objects and zero extended for 32-bit ones; values
that do not fit, zero and relocatable addends are skipped.

An absolute global load records the type in the destination register, so
the state is TSR_KIND_TYPE; a POINTER state records the address itself.
Guard the comparisons that made a -1 frame base equal the -1 "no
register" of an absolute operand.  Operands left with no register, like a
user space "%gs:imm", are no longer looked up as variables, which can
change the data type stats of those samples.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-arch/annotate-x86.c | 44 ++++++++++++++++----
 tools/perf/util/annotate.c                   | 27 +++++++++++-
 tools/perf/util/annotate.h                   |  7 ++++
 3 files changed, 70 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/annotate-arch/annotate-x86.c b/tools/perf/util/annotate-arch/annotate-x86.c
index e38a4e7a54d5585c..19663b780d19e2c4 100644
--- a/tools/perf/util/annotate-arch/annotate-x86.c
+++ b/tools/perf/util/annotate-arch/annotate-x86.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include <stdlib.h>
+#include <limits.h>
 #include <linux/compiler.h>
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
@@ -230,6 +231,11 @@ static bool vtable_get_rettype(Dwarf_Die *class_die, int offset,
 	return die_get_real_type(&func_die, type_die) != NULL;
 }
 
+static bool is_stack_or_fb_reg(struct type_state *state, int fbreg, int reg)
+{
+	return (fbreg != -1 && reg == fbreg) || reg == state->stack_reg;
+}
+
 static void update_insn_state_x86(struct type_state *state,
 				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
 				  struct disasm_line *dl)
@@ -437,7 +443,7 @@ static void update_insn_state_x86(struct type_state *state,
 		invalidate_reg_state(tsr);
 
 		/* Case 1: Based on stack pointer or frame pointer */
-		if (sreg == fbreg || sreg == state->stack_reg) {
+		if (is_stack_or_fb_reg(state, fbreg, sreg)) {
 			struct type_state_stack *stack;
 			int offset = src->offset - fboff;
 
@@ -626,7 +632,7 @@ static void update_insn_state_x86(struct type_state *state,
 
 retry:
 		/* Check stack variables with offset */
-		if (sreg == fbreg || sreg == state->stack_reg) {
+		if (is_stack_or_fb_reg(state, fbreg, sreg)) {
 			struct type_state_stack *stack;
 			int offset = src->offset - fboff;
 
@@ -717,13 +723,17 @@ static void update_insn_state_x86(struct type_state *state,
 			pr_debug_type_name(&tsr->type, tsr->kind);
 		}
 		/* Or check if it's a global variable */
-		else if (sreg == DWARF_REG_PC) {
+		else if (sreg == DWARF_REG_PC ||
+			 annotated_op_loc__is_abs(src, map__dso(dloc->ms->map))) {
 			struct map_symbol *ms = dloc->ms;
 			u64 ip = ms->sym->start + dl->al.offset;
 			u64 addr;
 			int offset;
 
-			addr = annotate_calc_pcrel(ms, ip, src->offset, dl);
+			if (sreg == DWARF_REG_PC)
+				addr = annotate_calc_pcrel(ms, ip, src->offset, dl);
+			else
+				addr = annotated_op_loc__abs_addr(src, map__dso(ms->map));
 
 			if (!get_global_var_type(cu_die, dloc, ip, addr, &offset,
 						 &type_die) ||
@@ -737,7 +747,7 @@ static void update_insn_state_x86(struct type_state *state,
 			tsr->offset = 0;
 			tsr->ok = true;
 
-			pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d",
+			pr_debug_dtp("mov [%x] global addr=%#"PRIx64" -> reg%d",
 				     insn_offset, addr, dst->reg1);
 			pr_debug_type_name(&type_die, tsr->kind);
 		}
@@ -827,7 +837,7 @@ static void update_insn_state_x86(struct type_state *state,
 	/* Case 3. register to memory transfers */
 	if (!src->mem_ref && dst->mem_ref) {
 		/* Check stack variables with offset */
-		if (dst->reg1 == fbreg || dst->reg1 == state->stack_reg) {
+		if (is_stack_or_fb_reg(state, fbreg, dst->reg1)) {
 			struct type_state_stack *stack;
 			int offset = dst->offset - fboff;
 
@@ -931,7 +941,7 @@ static int extract_reg_offset(const struct arch *arch, const char *str,
 }
 
 static void extract_op_location_x86(const struct arch *arch,
-				    struct disasm_line *dl __maybe_unused,
+				    struct disasm_line *dl,
 				    const char *op_str, int op_idx __maybe_unused,
 				    struct annotated_op_loc *op_loc)
 {
@@ -960,6 +970,26 @@ static void extract_op_location_x86(const struct arch *arch,
 			op_loc->offset = strtol(s + 1, &p, 0);
 			if (p && p != s + 1)
 				op_loc->imm = true;
+		} else if ((*s == '-' || strstarts(s, "0x")) &&
+			   !ins__is_call(&dl->ins) && !ins__is_jump(&dl->ins) &&
+			   strncmp(dl->ins.name, "loop", 4)) {
+			bool neg = *s == '-';
+			u64 offset = strtoull(s + neg, NULL, 0);
+			bool exact;
+
+			if (neg)
+				offset = -offset;
+			/*
+			 * The offset is an int: a disp32 fits it as a u32 or,
+			 * sign extended, as an int, which is how the LLVM
+			 * disassembler prints one that does not fit an int.
+			 */
+			exact = (s64)(int)offset == (s64)offset;
+			if (offset != 0 && (offset <= UINT_MAX || exact)) {
+				/* An absolute address: 32-bit code, or a 64-bit disp32 */
+				op_loc->mem_ref = true;
+				op_loc->offset = offset;
+			}
 		}
 	}
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 66d3453e7ffd0d5d..61ee6a3b2fa91d57 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2755,6 +2755,21 @@ int arch__dwarf_regnum(const struct arch *arch, const char *str)
 	return reg < 0 ? -1 : reg;
 }
 
+/* A relocatable object's operand is an unrelocated addend, not an address */
+bool annotated_op_loc__is_abs(const struct annotated_op_loc *op_loc,
+			      const struct dso *dso)
+{
+	return !dso__rel(dso) && op_loc->mem_ref && op_loc->reg1 == -1 && op_loc->reg2 == -1 &&
+	       op_loc->segment == INSN_SEG_NONE && op_loc->offset != 0;
+}
+
+/* The disp32 of a 64-bit object is sign extended, a 32-bit one is not */
+u64 annotated_op_loc__abs_addr(const struct annotated_op_loc *op_loc,
+			       const struct dso *dso)
+{
+	return dso__is_64_bit(dso) ? (u64)(s64)op_loc->offset : (u32)op_loc->offset;
+}
+
 /**
  * annotate_get_insn_location - Get location of instruction
  * @arch: the architecture info
@@ -2772,7 +2787,7 @@ int arch__dwarf_regnum(const struct arch *arch, const char *str)
  *   mov  (%rax), %rcx   # src_reg1 = rax, src_mem = 1, src_offset = 0
  *                       # dst_reg1 = rcx, dst_mem = 0
  *
- *   mov  0x18, %r8      # src_reg1 = -1, src_mem = 0
+ *   mov  0x18, %r8      # src_reg1 = -1, src_mem = 1, src_offset = 0x18
  *                       # dst_reg1 = r8, dst_mem = 0
  *
  *   mov  %rsi, 8(%rbx,%rcx,4)  # src_reg1 = rsi, src_mem = 0, src_multi_regs = 0
@@ -3046,6 +3061,13 @@ __hist_entry__get_data_type(struct hist_entry *he, const struct arch *arch,
 			dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip,
 							    op_loc->offset, dl);
 		}
+		/* An absolute address: 32-bit code, or a 64-bit disp32 */
+		else if (annotated_op_loc__is_abs(op_loc, map__dso(ms->map))) {
+			struct dso *dso = map__dso(ms->map);
+
+			dloc.var_addr = annotated_op_loc__abs_addr(op_loc, dso);
+			op_loc->reg1 = DWARF_REG_PC;
+		}
 
 		/* This CPU access in kernel - pretend PC-relative addressing */
 		if (dso__kernel(map__dso(ms->map)) && arch__is_x86(arch) &&
@@ -3054,6 +3076,9 @@ __hist_entry__get_data_type(struct hist_entry *he, const struct arch *arch,
 			op_loc->reg1 = DWARF_REG_PC;
 		}
 
+		if (op_loc->reg1 == -1)
+			continue;
+
 		mem_type = find_data_type(&dloc);
 
 		if (mem_type == NULL && is_stack_canary(arch, op_loc)) {
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index bc2237609d6e16e8..dc4fc8b1b320c1fb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -18,6 +18,7 @@
 #include "branch.h"
 #include "evsel.h"
 
+struct dso;
 struct hist_browser_timer;
 struct hist_entry;
 struct map;
@@ -637,6 +638,12 @@ struct annotated_insn_loc {
 	     i < INSN_OP_MAX;						\
 	     i++, op_loc++)
 
+/* Bare number operand: an absolute address, as 32-bit code and the kernel use */
+bool annotated_op_loc__is_abs(const struct annotated_op_loc *op_loc,
+			      const struct dso *dso);
+u64 annotated_op_loc__abs_addr(const struct annotated_op_loc *op_loc,
+			       const struct dso *dso);
+
 /* Get detailed location info in the instruction */
 int annotate_get_insn_location(const struct arch *arch, struct disasm_line *dl,
 			       struct annotated_insn_loc *loc);
-- 
2.56.0


  parent reply	other threads:[~2026-11-21  3:21 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-21  3:20 [PATCH v10 00/16] perf coverage: A harness for perf, and the fixes it found Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 01/16] perf build: Link the GTK UI with EXTRA_CFLAGS Arnaldo Carvalho de Melo
2026-11-21  3:20 ` Arnaldo Carvalho de Melo [this message]
2026-11-21  3:20 ` [PATCH v10 03/16] perf annotate: Print the stats after the annotations Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 04/16] perf build: Record the features checked outside FEATURE_TESTS Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 05/16] perf annotate-x86: Parse movabs like a mov Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 06/16] perf annotate-data: Count flexible array accesses for the whole struct Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 07/16] perf tests: Exercise the x86 operand parser Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 08/16] perf tests: Exercise DW_OP_addrx global variables Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 09/16] perf tests: Exercise the flexible array member path Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 10/16] perf tests: Exercise data type resolution from a register Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 11/16] perf tests: Exercise the annotate stats output Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 12/16] perf tests: Fix the Intel PT virtual LBR check Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 13/16] perf test: Drop samples without an IP in the dlfilter test Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 14/16] perf test: Skip the LBR inline unwinding check when unsupported Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 15/16] perf scripts: Add a coverage harness for perf Arnaldo Carvalho de Melo
2026-11-21  3:20 ` [PATCH v10 16/16] perf scripts: Add a coverage table Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261121032052.1392234-3-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=irogers@google.com \
    --cc=james.clark@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=williams@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®