kselftest/arm64: Add a GCS stress test

Add a stress test which runs one more process than we have CPUs spinning
through a very recursive function with frequent syscalls immediately prior
to return and signals being injected every 100ms. The goal is to flag up
any scheduling related issues, for example failure to ensure that barriers
are inserted when moving a GCS using task to another CPU. The test runs for
a configurable amount of time, defaulting to 10 seconds.

Reviewed-by: Thiago Jung Bauermann <thiago.bauermann@linaro.org>
Tested-by: Thiago Jung Bauermann <thiago.bauermann@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241001-arm64-gcs-v13-38-222b78d87eee@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: broonie

tools/testing/selftests/arm64/gcs/.gitignore

@@ -1,3 +1,5 @@
 basic-gcs
 libc-gcs
 gcs-locking
+gcs-stress
+gcs-stress-thread

tools/testing/selftests/arm64/gcs/Makefile

@@ -6,7 +6,8 @@
 # nolibc.
 #
 
-TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking
+TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking gcs-stress
+TEST_GEN_PROGS_EXTENDED := gcs-stress-thread
 
 LDLIBS+=-lpthread
 
@@ -18,3 +19,6 @@ $(OUTPUT)/basic-gcs: basic-gcs.c
 		-I../../../../../usr/include \
 		-std=gnu99 -I../.. -g \
 		-ffreestanding -Wall $^ -o $@ -lgcc
+
+$(OUTPUT)/gcs-stress-thread: gcs-stress-thread.S
+	$(CC) -nostdlib $^ -o $@

tools/testing/selftests/arm64/gcs/asm-offsets.h

@@ -0,0 +1,311 @@
+// Program that loops for ever doing lots of recursions and system calls,
+// intended to be used as part of a stress test for GCS context switching.
+//
+// Copyright 2015-2023 Arm Ltd
+
+#include <asm/unistd.h>
+
+#define sa_sz 32
+#define sa_flags 8
+#define sa_handler 0
+#define sa_mask_sz 8
+
+#define si_code 8
+
+#define SIGINT 2
+#define SIGABRT 6
+#define SIGUSR1 10
+#define SIGSEGV 11
+#define SIGUSR2 12
+#define SIGTERM 15
+#define SEGV_CPERR 10
+
+#define SA_NODEFER 1073741824
+#define SA_SIGINFO 4
+#define ucontext_regs 184
+
+#define PR_SET_SHADOW_STACK_STATUS      75
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+
+#define	GCSPR_EL0 S3_3_C2_C5_1
+
+.macro function name
+	.macro endfunction
+		.type \name, @function
+		.purgem endfunction
+	.endm
+\name:
+.endm
+
+// Print a single character x0 to stdout
+// Clobbers x0-x2,x8
+function putc
+	str	x0, [sp, #-16]!
+
+	mov	x0, #1			// STDOUT_FILENO
+	mov	x1, sp
+	mov	x2, #1
+	mov	x8, #__NR_write
+	svc	#0
+
+	add	sp, sp, #16
+	ret
+endfunction
+.globl	putc
+
+// Print a NUL-terminated string starting at address x0 to stdout
+// Clobbers x0-x3,x8
+function puts
+	mov	x1, x0
+
+	mov	x2, #0
+0:	ldrb	w3, [x0], #1
+	cbz	w3, 1f
+	add	x2, x2, #1
+	b	0b
+
+1:	mov	w0, #1			// STDOUT_FILENO
+	mov	x8, #__NR_write
+	svc	#0
+
+	ret
+endfunction
+.globl	puts
+
+// Utility macro to print a literal string
+// Clobbers x0-x4,x8
+.macro puts string
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
+.L__puts_literal\@: .string "\string"
+	.popsection
+
+	ldr	x0, =.L__puts_literal\@
+	bl	puts
+.endm
+
+// Print an unsigned decimal number x0 to stdout
+// Clobbers x0-x4,x8
+function putdec
+	mov	x1, sp
+	str	x30, [sp, #-32]!	// Result can't be > 20 digits
+
+	mov	x2, #0
+	strb	w2, [x1, #-1]!		// Write the NUL terminator
+
+	mov	x2, #10
+0:	udiv	x3, x0, x2		// div-mod loop to generate the digits
+	msub	x0, x3, x2, x0
+	add	w0, w0, #'0'
+	strb	w0, [x1, #-1]!
+	mov	x0, x3
+	cbnz	x3, 0b
+
+	ldrb	w0, [x1]
+	cbnz	w0, 1f
+	mov	w0, #'0'		// Print "0" for 0, not ""
+	strb	w0, [x1, #-1]!
+
+1:	mov	x0, x1
+	bl	puts
+
+	ldr	x30, [sp], #32
+	ret
+endfunction
+.globl	putdec
+
+// Print an unsigned decimal number x0 to stdout, followed by a newline
+// Clobbers x0-x5,x8
+function putdecn
+	mov	x5, x30
+
+	bl	putdec
+	mov	x0, #'\n'
+	bl	putc
+
+	ret	x5
+endfunction
+.globl	putdecn
+
+// Fill x1 bytes starting at x0 with 0.
+// Clobbers x1, x2.
+function memclr
+	mov	w2, #0
+endfunction
+.globl	memclr
+	// fall through to memfill
+
+// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2
+// Clobbers x1
+function memfill
+	cmp	x1, #0
+	b.eq	1f
+
+0:	strb	w2, [x0], #1
+	subs	x1, x1, #1
+	b.ne	0b
+
+1:	ret
+endfunction
+.globl	memfill
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	abort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+
+function tickle_handler
+	// Perhaps collect GCSPR_EL0 here in future?
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error\n"
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+function segv_handler
+	// stash the siginfo_t *
+	mov	x20, x1
+
+	// Disable GCS, we don't want additional faults logging things
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+
+	puts	"Got SIGSEGV code "
+
+	ldr	x21, [x20, #si_code]
+	mov	x0, x21
+	bl	putdec
+
+	// GCS faults should have si_code SEGV_CPERR
+	cmp	x21, #SEGV_CPERR
+	bne	1f
+
+	puts	" (GCS violation)"
+1:
+	mov	x0, '\n'
+	bl	putc
+	b	abort
+endfunction
+
+// Recurse x20 times
+.macro recurse id
+function recurse\id
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+
+	cmp	x20, 0
+	beq	1f
+	sub	x20, x20, 1
+	bl	recurse\id
+
+1:
+	ldp	x29, x30, [sp], #16
+
+	// Do a syscall immediately prior to returning to try to provoke
+	// scheduling and migration at a point where coherency issues
+	// might trigger.
+	mov	x8, #__NR_getpid
+	svc	#0
+
+	ret
+endfunction
+.endm
+
+// Generate and use two copies so we're changing the GCS contents
+recurse 1
+recurse 2
+
+.globl _start
+function _start
+	// Run with GCS
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, PR_SHADOW_STACK_ENABLE
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+	cbz	x0, 1f
+	puts	"Failed to enable GCS\n"
+	b	abort
+1:
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGSEGV
+	adr	x1, segv_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	puts	"Running\n"
+
+loop:
+	// Small recursion depth so we're frequently flipping between
+	// the two recursors and changing what's on the stack
+	mov	x20, #5
+	bl	recurse1
+	mov	x20, #5
+	bl	recurse2
+	b	loop
+endfunction
+
+abort:
+	mov	x0, #255
+	mov	x8, #__NR_exit
+	svc	#0