Merge branch 'for-next/kselftest' into for-next/core

* for-next/kselftest: (32 commits)
  : arm64 kselftest updates.
  kselftest/arm64: Explicitly build no BTI tests with BTI disabled
  kselftest/arm64: bti: force static linking
  selftests/arm64: Use switch statements in mte_common_util.c
  selftests/arm64: Remove casts to/from void in check_tags_inclusion
  selftests/arm64: Check failures to set tags in check_tags_inclusion
  selftests/arm64: Allow zero tags in mte_switch_mode()
  selftests/arm64: Log errors in verify_mte_pointer_validity()
  kselftest/arm64: Fix ABI header directory location
  selftests/arm64: Fix O= builds for the floating point tests
  selftests/arm64: Clean the fp helper libraries
  selftests/arm64: Define top_srcdir for the fp tests
  selftests/arm64: Use TEST_GEN_PROGS_EXTENDED in the FP Makefile
  kselftest/arm64: fix array_size.cocci warning
  selftests/arm64: Add a testcase for handling of ZA on clone()
  kselftest/arm64: Add SME support to syscall ABI test
  kselftest/arm64: Add coverage for the ZA ptrace interface
  kselftest/arm64: Add streaming SVE to SVE ptrace tests
  kselftest/arm64: signal: Add SME signal handling tests
  kselftest/arm64: Add stress test for SME ZA context switching
  kselftest/arm64: signal: Handle ZA signal context in core code
  ...

Author: ctmarinas

tools/testing/selftests/arm64/Makefile

@@ -17,16 +17,7 @@ top_srcdir = $(realpath ../../../../)
 # Additional include paths needed by kselftest.h and local headers
 CFLAGS += -I$(top_srcdir)/tools/testing/selftests/
 
-# Guessing where the Kernel headers could have been installed
-# depending on ENV config
-ifeq ($(KBUILD_OUTPUT),)
-khdr_dir = $(top_srcdir)/usr/include
-else
-# the KSFT preferred location when KBUILD_OUTPUT is set
-khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include
-endif
-
-CFLAGS += -I$(khdr_dir)
+CFLAGS += $(KHDR_INCLUDES)
 
 export CFLAGS
 export top_srcdir

tools/testing/selftests/arm64/abi/.gitignore

@@ -1 +1,2 @@
 syscall-abi
+tpidr2

tools/testing/selftests/arm64/abi/Makefile

@@ -1,8 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2021 ARM Limited
 
-TEST_GEN_PROGS := syscall-abi
+TEST_GEN_PROGS := syscall-abi tpidr2
 
 include ../../lib.mk
 
 $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
+
+# Build with nolibc since TPIDR2 is intended to be actively managed by
+# libc and we're trying to test the functionality that it depends on here.
+$(OUTPUT)/tpidr2: tpidr2.c
+	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+		-static -include ../../../../include/nolibc/nolibc.h \
+		-ffreestanding -Wall $^ -o $@ -lgcc

tools/testing/selftests/arm64/abi/syscall-abi-asm.S

@@ -9,15 +9,42 @@
 // invoked is configured in x8 of the input GPR data.
 //
 // x0:	SVE VL, 0 for FP only
+// x1:	SME VL
 //
 //	GPRs:	gpr_in, gpr_out
 //	FPRs:	fpr_in, fpr_out
 //	Zn:	z_in, z_out
 //	Pn:	p_in, p_out
 //	FFR:	ffr_in, ffr_out
+//	ZA:	za_in, za_out
+//	SVCR:	svcr_in, svcr_out
+
+#include "syscall-abi.h"
 
 .arch_extension sve
 
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
 .globl do_syscall
 do_syscall:
 	// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@@ -30,6 +57,24 @@ do_syscall:
 	stp	x25, x26, [sp, #80]
 	stp	x27, x28, [sp, #96]
 
+	// Set SVCR if we're doing SME
+	cbz	x1, 1f
+	adrp	x2, svcr_in
+	ldr	x2, [x2, :lo12:svcr_in]
+	msr	S3_3_C4_C2_2, x2
+1:
+
+	// Load ZA if it's enabled - uses x12 as scratch due to SME LDR
+	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	mov	w12, #0
+	ldr	x2, =za_in
+2:	_ldr_za 12, 2
+	add	x2, x2, x1
+	add	x12, x12, #1
+	cmp	x1, x12
+	bne	2b
+1:
+
 	// Load GPRs x8-x28, and save our SP/FP for later comparison
 	ldr	x2, =gpr_in
 	add	x2, x2, #64
@@ -68,7 +113,7 @@ do_syscall:
 	ldp	q30, q31, [x2, #16 * 30]
 1:
 
-	// Load the SVE registers if we're doing SVE
+	// Load the SVE registers if we're doing SVE/SME
 	cbz	x0, 1f
 
 	ldr	x2, =z_in
@@ -105,9 +150,14 @@ do_syscall:
 	ldr	z30, [x2, #30, MUL VL]
 	ldr	z31, [x2, #31, MUL VL]
 
+	// Only set a non-zero FFR, test patterns must be zero since the
+	// syscall should clear it - this lets us handle FA64.
 	ldr	x2, =ffr_in
 	ldr	p0, [x2, #0]
+	ldr	x2, [x2, #0]
+	cbz	x2, 2f
 	wrffr	p0.b
+2:
 
 	ldr	x2, =p_in
 	ldr	p0, [x2, #0, MUL VL]
@@ -169,6 +219,24 @@ do_syscall:
 	stp	q28, q29, [x2, #16 * 28]
 	stp	q30, q31, [x2, #16 * 30]
 
+	// Save SVCR if we're doing SME
+	cbz	x1, 1f
+	mrs	x2, S3_3_C4_C2_2
+	adrp	x3, svcr_out
+	str	x2, [x3, :lo12:svcr_out]
+1:
+
+	// Save ZA if it's enabled - uses x12 as scratch due to SME STR
+	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	mov	w12, #0
+	ldr	x2, =za_out
+2:	_str_za 12, 2
+	add	x2, x2, x1
+	add	x12, x12, #1
+	cmp	x1, x12
+	bne	2b
+1:
+
 	// Save the SVE state if we have some
 	cbz	x0, 1f
 
@@ -224,6 +292,10 @@ do_syscall:
 	str	p14, [x2, #14, MUL VL]
 	str	p15, [x2, #15, MUL VL]
 
+	// Only save FFR if we wrote a value for SME
+	ldr	x2, =ffr_in
+	ldr	x2, [x2, #0]
+	cbz	x2, 1f
 	ldr	x2, =ffr_out
 	rdffr	p0.b
 	str	p0, [x2, #0]
@@ -237,4 +309,9 @@ do_syscall:
 	ldp	x27, x28, [sp, #96]
 	ldp	x29, x30, [sp], #112
 
+	// Clear SVCR if we were doing SME so future tests don't have ZA
+	cbz	x1, 1f
+	msr	S3_3_C4_C2_2, xzr
+1:
+
 	ret