alpha: add HAVE_PERF_REGS and HAVE_PERF_USER_STACK_DUMP support

Let perf sample registers and dump the user stack, which is what the
perf tool needs for --call-graph dwarf.

The register indices follow the hardware numbering, so r0-r30 map
directly to DWARF register numbers, with pc after them. r9-r15
are callee-saved and live in switch_stack rather than pt_regs, so they
cannot be sampled. Without r15 an unwinder cannot recover the CFA of a
first frame that uses $15 as its frame pointer.

sp is not in pt_regs either: for user frames it comes from
user_stack_pointer(), and for kernel frames (PERF_SAMPLE_REGS_INTR) it
is the end of the trap frame, as in stacktrace.c.

Software events such as context switches and tracepoints hand perf a
per-CPU pt_regs filled in by perf_fetch_caller_regs() instead of a
trap frame. It is not on the stack and has no room for sp, so report
sp as 0 there rather than the address of the per-CPU buffer.

Assisted-by: Claude:claude-opus-5-5
Acked-by: Ian Rogers <irogers@google.com>
Tested-by: Magnus Lindholm <linmag7@gmail.com>
Reviewed-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Matt Turner <mattst88@gmail.com>
Link: https://lore.kernel.org/r/20261018-alpha-perf-regs-v3-v3-4-52be85332c57@gmail.com
Signed-off-by: Magnus Lindholm <linmag7@gmail.com>

Documentation/features/perf/perf-regs/arch-support.txt

@@ -6,7 +6,7 @@
     -----------------------
     |         arch |status|
     -----------------------
-    |       alpha: | TODO |
+    |       alpha: |  ok  |
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |

Documentation/features/perf/perf-stackdump/arch-support.txt

@@ -6,7 +6,7 @@
     -----------------------
     |         arch |status|
     -----------------------
-    |       alpha: | TODO |
+    |       alpha: |  ok  |
     |         arc: | TODO |
     |         arm: |  ok  |
     |       arm64: |  ok  |

arch/alpha/Kconfig

@@ -41,6 +41,8 @@ config ALPHA
 	select HAVE_PAGE_SIZE_8KB
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select GENERIC_IRQ_PROBE

arch/alpha/include/uapi/asm/perf_regs.h

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_ALPHA_PERF_REGS_H
+#define _ASM_ALPHA_PERF_REGS_H
+
+/*
+ * Indices 0-30 match the hardware (and DWARF) register numbers.
+ * r9-r15 are not saved in pt_regs and cannot be sampled.
+ */
+enum perf_event_alpha_regs {
+	PERF_REG_ALPHA_R0,
+	PERF_REG_ALPHA_R1,
+	PERF_REG_ALPHA_R2,
+	PERF_REG_ALPHA_R3,
+	PERF_REG_ALPHA_R4,
+	PERF_REG_ALPHA_R5,
+	PERF_REG_ALPHA_R6,
+	PERF_REG_ALPHA_R7,
+	PERF_REG_ALPHA_R8,
+	PERF_REG_ALPHA_R9,
+	PERF_REG_ALPHA_R10,
+	PERF_REG_ALPHA_R11,
+	PERF_REG_ALPHA_R12,
+	PERF_REG_ALPHA_R13,
+	PERF_REG_ALPHA_R14,
+	PERF_REG_ALPHA_R15,
+	PERF_REG_ALPHA_R16,
+	PERF_REG_ALPHA_R17,
+	PERF_REG_ALPHA_R18,
+	PERF_REG_ALPHA_R19,
+	PERF_REG_ALPHA_R20,
+	PERF_REG_ALPHA_R21,
+	PERF_REG_ALPHA_R22,
+	PERF_REG_ALPHA_R23,
+	PERF_REG_ALPHA_R24,
+	PERF_REG_ALPHA_R25,
+	PERF_REG_ALPHA_R26,
+	PERF_REG_ALPHA_R27,
+	PERF_REG_ALPHA_R28,
+	PERF_REG_ALPHA_GP,
+	PERF_REG_ALPHA_SP,
+	PERF_REG_ALPHA_PC,
+	PERF_REG_ALPHA_MAX,
+};
+
+#endif /* _ASM_ALPHA_PERF_REGS_H */

arch/alpha/kernel/Makefile

@@ -18,6 +18,7 @@ obj-$(CONFIG_PCI)	+= pci.o pci_iommu.o pci-sysfs.o
 obj-$(CONFIG_SRM_ENV)	+= srm_env.o
 obj-$(CONFIG_MODULES)	+= module.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o
 obj-$(CONFIG_RTC_DRV_ALPHA) += rtc.o
 obj-$(CONFIG_AUDIT)	+= audit.o
 

arch/alpha/kernel/perf_regs.c

@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bits.h>
+#include <linux/perf_event.h>
+#include <linux/sched/task_stack.h>
+#include <asm/perf_regs.h>
+
+#define REG(idx, field) \
+	[PERF_REG_ALPHA_##idx] = offsetof(struct pt_regs, field)
+
+#define REG_RESERVED	(~GENMASK_ULL(PERF_REG_ALPHA_MAX - 1, 0) | \
+			 GENMASK_ULL(PERF_REG_ALPHA_R15, PERF_REG_ALPHA_R9))
+
+static const unsigned int pt_regs_offset[PERF_REG_ALPHA_MAX] = {
+	REG(R0, r0),	REG(R1, r1),	REG(R2, r2),	REG(R3, r3),
+	REG(R4, r4),	REG(R5, r5),	REG(R6, r6),	REG(R7, r7),
+	REG(R8, r8),	REG(R16, r16),	REG(R17, r17),	REG(R18, r18),
+	REG(R19, r19),	REG(R20, r20),	REG(R21, r21),	REG(R22, r22),
+	REG(R23, r23),	REG(R24, r24),	REG(R25, r25),	REG(R26, r26),
+	REG(R27, r27),	REG(R28, r28),	REG(GP, gp),	REG(PC, pc),
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (idx == PERF_REG_ALPHA_SP) {
+		if (user_mode(regs))
+			return user_stack_pointer(regs);
+		/*
+		 * Software events built by perf_fetch_caller_regs() use a
+		 * per-CPU pt_regs rather than a trap frame, and pt_regs has
+		 * nowhere to record sp, so report none.
+		 */
+		if (!object_is_on_stack(regs))
+			return 0;
+		/* Same kernel sp approximation as stacktrace.c. */
+		return (unsigned long)(regs + 1);
+	}
+
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ALPHA_MAX ||
+			 BIT_ULL(idx) & REG_RESERVED))
+		return 0;
+
+	return *(unsigned long *)((void *)regs + pt_regs_offset[idx]);
+}
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	return PERF_SAMPLE_REGS_ABI_64;
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}