summaryrefslogtreecommitdiffstats
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/selftests/android/Makefile2
-rw-r--r--tools/testing/selftests/futex/functional/Makefile1
-rw-r--r--tools/testing/selftests/gpio/Makefile6
-rw-r--r--tools/testing/selftests/kvm/Makefile5
-rw-r--r--tools/testing/selftests/kvm/clear_dirty_log_test.c2
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c165
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h8
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c18
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c67
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h1
-rw-r--r--tools/testing/selftests/kvm/lib/ucall.c36
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c157
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c4
-rw-r--r--tools/testing/selftests/lib.mk8
-rw-r--r--tools/testing/selftests/networking/timestamping/Makefile1
-rw-r--r--tools/testing/selftests/powerpc/include/utils.h10
-rw-r--r--tools/testing/selftests/powerpc/ptrace/core-pkey.c5
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c2
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c4
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c2
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c3
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c2
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c2
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c3
-rw-r--r--tools/testing/selftests/powerpc/tm/.gitignore1
-rw-r--r--tools/testing/selftests/powerpc/tm/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c46
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh8
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/mkinitrd.sh136
-rw-r--r--tools/testing/selftests/rcutorture/bin/nolibc.h2197
-rw-r--r--tools/testing/selftests/rcutorture/doc/initrd.txt99
-rw-r--r--tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h4
-rw-r--r--tools/testing/selftests/tc-testing/bpf/Makefile1
-rw-r--r--tools/testing/selftests/vm/Makefile1
35 files changed, 2809 insertions, 204 deletions
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index d9a725478375..72c25a3cb658 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -6,7 +6,7 @@ TEST_PROGS := run.sh
include ../lib.mk
-all: khdr
+all:
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index ad1eeb14fda7..30996306cabc 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -19,6 +19,7 @@ TEST_GEN_FILES := \
TEST_PROGS := run.sh
top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
include ../../lib.mk
$(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 46648427d537..07f572a1bd3f 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -10,8 +10,6 @@ TEST_PROGS_EXTENDED := gpio-mockup-chardev
GPIODIR := $(realpath ../../../gpio)
GPIOOBJ := gpio-utils.o
-include ../lib.mk
-
all: $(TEST_PROGS_EXTENDED)
override define CLEAN
@@ -19,7 +17,9 @@ override define CLEAN
$(MAKE) -C $(GPIODIR) OUTPUT=$(GPIODIR)/ clean
endef
-$(TEST_PROGS_EXTENDED):| khdr
+KSFT_KHDR_INSTALL := 1
+include ../lib.mk
+
$(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
$(GPIODIR)/$(GPIOOBJ):
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 01a219229238..f9a0e9938480 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,6 +1,7 @@
all:
top_srcdir = ../../../..
+KSFT_KHDR_INSTALL := 1
UNAME_M := $(shell uname -m)
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
@@ -14,9 +15,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
+TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
@@ -44,7 +48,6 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
all: $(STATIC_LIBS)
$(TEST_GEN_PROGS): $(STATIC_LIBS)
-$(STATIC_LIBS):| khdr
cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
cscope:
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
new file mode 100644
index 000000000000..749336937d37
--- /dev/null
+++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c
@@ -0,0 +1,2 @@
+#define USE_CLEAR_DIRTY_LOG
+#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index aeff95a91b15..4715cfba20dc 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -51,10 +51,17 @@ static uint64_t random_array[TEST_PAGES_PER_LOOP];
static uint64_t iteration;
/*
- * GPA offset of the testing memory slot. Must be bigger than
- * DEFAULT_GUEST_PHY_PAGES.
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
*/
-static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
/*
* Continuously write to the first 8 bytes of a random pages within
@@ -66,7 +73,7 @@ static void guest_code(void)
while (true) {
for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
- uint64_t addr = guest_test_mem;
+ uint64_t addr = guest_test_virt_mem;
addr += (READ_ONCE(random_array[i]) % guest_num_pages)
* guest_page_size;
addr &= ~(host_page_size - 1);
@@ -209,12 +216,14 @@ static void vm_dirty_log_verify(unsigned long *bmap)
}
static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
- uint64_t extra_mem_pages, void *guest_code)
+ uint64_t extra_mem_pages, void *guest_code,
+ unsigned long type)
{
struct kvm_vm *vm;
uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
- vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+ vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
+ O_RDWR, type);
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
#ifdef __x86_64__
vm_create_irqchip(vm);
@@ -224,13 +233,14 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
}
static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- unsigned long interval, bool top_offset)
+ unsigned long interval, uint64_t phys_offset)
{
unsigned int guest_pa_bits, guest_page_shift;
pthread_t vcpu_thread;
struct kvm_vm *vm;
uint64_t max_gfn;
unsigned long *bmap;
+ unsigned long type = 0;
switch (mode) {
case VM_MODE_P52V48_4K:
@@ -241,6 +251,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
guest_pa_bits = 52;
guest_page_shift = 16;
break;
+ case VM_MODE_P48V48_4K:
+ guest_pa_bits = 48;
+ guest_page_shift = 12;
+ break;
+ case VM_MODE_P48V48_64K:
+ guest_pa_bits = 48;
+ guest_page_shift = 16;
+ break;
case VM_MODE_P40V48_4K:
guest_pa_bits = 40;
guest_page_shift = 12;
@@ -255,6 +273,19 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+#ifdef __x86_64__
+ /*
+ * FIXME
+ * The x86_64 kvm selftests framework currently only supports a
+ * single PML4 which restricts the number of physical address
+ * bits we can change to 39.
+ */
+ guest_pa_bits = 39;
+#endif
+#ifdef __aarch64__
+ if (guest_pa_bits != 40)
+ type = KVM_VM_TYPE_ARM_IPA_SIZE(guest_pa_bits);
+#endif
max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
guest_page_size = (1ul << guest_page_shift);
/* 1G of guest page sized pages */
@@ -263,31 +294,41 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
!!((guest_num_pages * guest_page_size) % host_page_size);
- if (top_offset) {
- guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
- guest_test_mem &= ~(host_page_size - 1);
+ if (!phys_offset) {
+ guest_test_phys_mem = (max_gfn - guest_num_pages) * guest_page_size;
+ guest_test_phys_mem &= ~(host_page_size - 1);
+ } else {
+ guest_test_phys_mem = phys_offset;
}
- DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
+ DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
bmap = bitmap_alloc(host_num_pages);
host_bmap_track = bitmap_alloc(host_num_pages);
- vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
+ vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code, type);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ struct kvm_enable_cap cap = {};
+
+ cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT;
+ cap.args[0] = 1;
+ vm_enable_cap(vm, &cap);
+#endif
/* Add an extra memory slot for testing dirty logging */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- guest_test_mem,
+ guest_test_phys_mem,
TEST_MEM_SLOT_INDEX,
guest_num_pages,
KVM_MEM_LOG_DIRTY_PAGES);
- /* Do 1:1 mapping for the dirty track memory slot */
- virt_map(vm, guest_test_mem, guest_test_mem,
+ /* Do mapping for the dirty track memory slot */
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem,
guest_num_pages * guest_page_size, 0);
/* Cache the HVA pointer of the region */
- host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
+ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
#ifdef __x86_64__
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -299,7 +340,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
/* Export the shared variables to the guest */
sync_global_to_guest(vm, host_page_size);
sync_global_to_guest(vm, guest_page_size);
- sync_global_to_guest(vm, guest_test_mem);
+ sync_global_to_guest(vm, guest_test_virt_mem);
sync_global_to_guest(vm, guest_num_pages);
/* Start the iterations */
@@ -316,6 +357,10 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
/* Give the vcpu thread some time to dirty some pages */
usleep(interval * 1000);
kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+#ifdef USE_CLEAR_DIRTY_LOG
+ kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+ DIV_ROUND_UP(host_num_pages, 64) * 64);
+#endif
vm_dirty_log_verify(bmap);
iteration++;
sync_global_to_guest(vm, iteration);
@@ -335,23 +380,16 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
kvm_vm_free(vm);
}
-static struct vm_guest_modes {
- enum vm_guest_mode mode;
+struct vm_guest_mode_params {
bool supported;
bool enabled;
-} vm_guest_modes[NUM_VM_MODES] = {
-#if defined(__x86_64__)
- { VM_MODE_P52V48_4K, 1, 1, },
- { VM_MODE_P52V48_64K, 0, 0, },
- { VM_MODE_P40V48_4K, 0, 0, },
- { VM_MODE_P40V48_64K, 0, 0, },
-#elif defined(__aarch64__)
- { VM_MODE_P52V48_4K, 0, 0, },
- { VM_MODE_P52V48_64K, 0, 0, },
- { VM_MODE_P40V48_4K, 1, 1, },
- { VM_MODE_P40V48_64K, 1, 1, },
-#endif
};
+struct vm_guest_mode_params vm_guest_mode_params[NUM_VM_MODES];
+
+#define vm_guest_mode_params_init(mode, supported, enabled) \
+({ \
+ vm_guest_mode_params[mode] = (struct vm_guest_mode_params){ supported, enabled }; \
+})
static void help(char *name)
{
@@ -359,25 +397,21 @@ static void help(char *name)
puts("");
printf("usage: %s [-h] [-i iterations] [-I interval] "
- "[-o offset] [-t] [-m mode]\n", name);
+ "[-p offset] [-m mode]\n", name);
puts("");
printf(" -i: specify iteration counts (default: %"PRIu64")\n",
TEST_HOST_LOOP_N);
printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
TEST_HOST_LOOP_INTERVAL);
- printf(" -o: guest test memory offset (default: 0x%lx)\n",
- DEFAULT_GUEST_TEST_MEM);
- printf(" -t: map guest test memory at the top of the allowed "
- "physical address range\n");
+ printf(" -p: specify guest physical test memory offset\n"
+ " Warning: a low offset can conflict with the loaded test code.\n");
printf(" -m: specify the guest mode ID to test "
"(default: test all supported modes)\n"
" This option may be used multiple times.\n"
" Guest mode IDs:\n");
for (i = 0; i < NUM_VM_MODES; ++i) {
- printf(" %d: %s%s\n",
- vm_guest_modes[i].mode,
- vm_guest_mode_string(vm_guest_modes[i].mode),
- vm_guest_modes[i].supported ? " (supported)" : "");
+ printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
+ vm_guest_mode_params[i].supported ? " (supported)" : "");
}
puts("");
exit(0);
@@ -388,11 +422,34 @@ int main(int argc, char *argv[])
unsigned long iterations = TEST_HOST_LOOP_N;
unsigned long interval = TEST_HOST_LOOP_INTERVAL;
bool mode_selected = false;
- bool top_offset = false;
- unsigned int mode;
+ uint64_t phys_offset = 0;
+ unsigned int mode, host_ipa_limit;
int opt, i;
- while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
+#ifdef USE_CLEAR_DIRTY_LOG
+ if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT)) {
+ fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n");
+ exit(KSFT_SKIP);
+ }
+#endif
+
+#ifdef __x86_64__
+ vm_guest_mode_params_init(VM_MODE_P52V48_4K, true, true);
+#endif
+#ifdef __aarch64__
+ vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
+ vm_guest_mode_params_init(VM_MODE_P40V48_64K, true, true);
+
+ host_ipa_limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ if (host_ipa_limit >= 52)
+ vm_guest_mode_params_init(VM_MODE_P52V48_64K, true, true);
+ if (host_ipa_limit >= 48) {
+ vm_guest_mode_params_init(VM_MODE_P48V48_4K, true, true);
+ vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true);
+ }
+#endif
+
+ while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
switch (opt) {
case 'i':
iterations = strtol(optarg, NULL, 10);
@@ -400,22 +457,19 @@ int main(int argc, char *argv[])
case 'I':
interval = strtol(optarg, NULL, 10);
break;
- case 'o':
- guest_test_mem = strtoull(optarg, NULL, 0);
- break;
- case 't':
- top_offset = true;
+ case 'p':
+ phys_offset = strtoull(optarg, NULL, 0);
break;
case 'm':
if (!mode_selected) {
for (i = 0; i < NUM_VM_MODES; ++i)
- vm_guest_modes[i].enabled = 0;
+ vm_guest_mode_params[i].enabled = false;
mode_selected = true;
}
mode = strtoul(optarg, NULL, 10);
TEST_ASSERT(mode < NUM_VM_MODES,
"Guest mode ID %d too big", mode);
- vm_guest_modes[mode].enabled = 1;
+ vm_guest_mode_params[mode].enabled = true;
break;
case 'h':
default:
@@ -426,8 +480,6 @@ int main(int argc, char *argv[])
TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
TEST_ASSERT(interval > 0, "Interval must be greater than zero");
- TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
- "Cannot use both -o [offset] and -t at the same time");
DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
iterations, interval);
@@ -435,13 +487,12 @@ int main(int argc, char *argv[])
srandom(time(0));
for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!vm_guest_modes[i].enabled)
+ if (!vm_guest_mode_params[i].enabled)
continue;
- TEST_ASSERT(vm_guest_modes[i].supported,
+ TEST_ASSERT(vm_guest_mode_params[i].supported,
"Guest mode ID %d (%s) not supported.",
- vm_guest_modes[i].mode,
- vm_guest_mode_string(vm_guest_modes[i].mode));
- run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
+ i, vm_guest_mode_string(i));
+ run_test(i, iterations, interval, phys_offset);
}
return 0;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a4e59e3b4826..a84785b02557 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -36,6 +36,8 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
enum vm_guest_mode {
VM_MODE_P52V48_4K,
VM_MODE_P52V48_64K,
+ VM_MODE_P48V48_4K,
+ VM_MODE_P48V48_64K,
VM_MODE_P40V48_4K,
VM_MODE_P40V48_64K,
NUM_VM_MODES,
@@ -54,10 +56,14 @@ int kvm_check_cap(long cap);
int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
+struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages,
+ int perm, unsigned long type);
void kvm_vm_free(struct kvm_vm *vmp);
void kvm_vm_restart(struct kvm_vm *vmp, int perm);
void kvm_vm_release(struct kvm_vm *vmp);
void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+ uint64_t first_page, uint32_t num_pages);
int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
size_t len);
@@ -78,6 +84,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
void *arg);
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b6022e2f116e..e8c42506a09d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -268,13 +268,20 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
switch (vm->mode) {
case VM_MODE_P52V48_4K:
- tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
- tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
- break;
+ TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
+ "with 52-bit physical address ranges");
case VM_MODE_P52V48_64K:
tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
break;
+ case VM_MODE_P48V48_4K:
+ tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+ tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+ break;
+ case VM_MODE_P48V48_64K:
+ tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+ tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+ break;
case VM_MODE_P40V48_4K:
tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
@@ -305,7 +312,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
- fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
- indent, "", pstate, pc);
-
+ fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+ indent, "", pstate, pc);
}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1b41e71283d5..23022e9d32eb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -85,13 +85,13 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
return ret;
}
-static void vm_open(struct kvm_vm *vm, int perm)
+static void vm_open(struct kvm_vm *vm, int perm, unsigned long type)
{
vm->kvm_fd = open(KVM_DEV_PATH, perm);
if (vm->kvm_fd < 0)
exit(KSFT_SKIP);
- vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL);
+ vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
"rc: %i errno: %i", vm->fd, errno);
}
@@ -99,9 +99,13 @@ static void vm_open(struct kvm_vm *vm, int perm)
const char * const vm_guest_mode_string[] = {
"PA-bits:52, VA-bits:48, 4K pages",
"PA-bits:52, VA-bits:48, 64K pages",
+ "PA-bits:48, VA-bits:48, 4K pages",
+ "PA-bits:48, VA-bits:48, 64K pages",
"PA-bits:40, VA-bits:48, 4K pages",
"PA-bits:40, VA-bits:48, 64K pages",
};
+_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
+ "Missing new mode strings?");
/*
* VM Create
@@ -122,7 +126,8 @@ const char * const vm_guest_mode_string[] = {
* descriptor to control the created VM is created with the permissions
* given by perm (e.g. O_RDWR).
*/
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages,
+ int perm, unsigned long type)
{
struct kvm_vm *vm;
int kvm_fd;
@@ -131,22 +136,38 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
TEST_ASSERT(vm != NULL, "Insufficient Memory");
vm->mode = mode;
- vm_open(vm, perm);
+ vm->type = type;
+ vm_open(vm, perm, type);
/* Setup mode specific traits. */
switch (vm->mode) {
case VM_MODE_P52V48_4K:
vm->pgtable_levels = 4;
+ vm->pa_bits = 52;
+ vm->va_bits = 48;
vm->page_size = 0x1000;
vm->page_shift = 12;
- vm->va_bits = 48;
break;
case VM_MODE_P52V48_64K:
vm->pgtable_levels = 3;
vm->pa_bits = 52;
+ vm->va_bits = 48;
vm->page_size = 0x10000;
vm->page_shift = 16;
+ break;
+ case VM_MODE_P48V48_4K:
+ vm->pgtable_levels = 4;
+ vm->pa_bits = 48;
+ vm->va_bits = 48;
+ vm->page_size = 0x1000;
+ vm->page_shift = 12;
+ break;
+ case VM_MODE_P48V48_64K:
+ vm->pgtable_levels = 3;
+ vm->pa_bits = 48;
vm->va_bits = 48;
+ vm->page_size = 0x10000;
+ vm->page_shift = 16;
break;
case VM_MODE_P40V48_4K:
vm->pgtable_levels = 4;
@@ -186,6 +207,11 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
return vm;
}
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+{
+ return _vm_create(mode, phy_pages, perm, 0);
+}
+
/*
* VM Restart
*
@@ -203,7 +229,7 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
{
struct userspace_mem_region *region;
- vm_open(vmp, perm);
+ vm_open(vmp, perm, vmp->type);
if (vmp->has_irqchip)
vm_create_irqchip(vmp);
@@ -231,6 +257,19 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
strerror(-ret));
}
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+ uint64_t first_page, uint32_t num_pages)
+{
+ struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
+ .first_page = first_page,
+ .num_pages = num_pages };
+ int ret;
+
+ ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
+ TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s",
+ strerror(-ret));
+}
+
/*
* Userspace Memory Region Find
*
@@ -1270,14 +1309,24 @@ int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
unsigned long cmd, void *arg)
{
+ int ret;
+
+ ret = _vcpu_ioctl(vm, vcpuid, cmd, arg);
+ TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
+ cmd, ret, errno, strerror(errno));
+}
+
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
+ unsigned long cmd, void *arg)
+{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
ret = ioctl(vcpu->fd, cmd, arg);
- TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
- cmd, ret, errno, strerror(errno));
+
+ return ret;
}
/*
@@ -1422,7 +1471,7 @@ const char *exit_reason_str(unsigned int exit_reason)
*
* Within the VM specified by vm, locates a range of available physical
* pages at or above paddr_min. If found, the pages are marked as in use
- * and thier base address is returned. A TEST_ASSERT failure occurs if
+ * and their base address is returned. A TEST_ASSERT failure occurs if
* not enough pages are available at or above paddr_min.
*/
vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 52701db0f253..4595e42c6e29 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -44,6 +44,7 @@ struct vcpu {
struct kvm_vm {
int mode;
+ unsigned long type;
int kvm_fd;
int fd;
unsigned int pgtable_levels;
diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c
index 4777f9bb5194..a2ab38be2f47 100644
--- a/tools/testing/selftests/kvm/lib/ucall.c
+++ b/tools/testing/selftests/kvm/lib/ucall.c
@@ -34,7 +34,8 @@ void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
return;
if (type == UCALL_MMIO) {
- vm_paddr_t gpa, start, end, step;
+ vm_paddr_t gpa, start, end, step, offset;
+ unsigned bits;
bool ret;
if (arg) {
@@ -45,25 +46,30 @@ void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
}
/*
- * Find an address within the allowed virtual address space,
- * that does _not_ have a KVM memory region associated with it.
- * Identity mapping an address like this allows the guest to
+ * Find an address within the allowed physical and virtual address
+ * spaces, that does _not_ have a KVM memory region associated with
+ * it. Identity mapping an address like this allows the guest to
* access it, but as KVM doesn't know what to do with it, it
* will assume it's something userspace handles and exit with
* KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
- * Here we start with a guess that the addresses around two
- * thirds of the VA space are unmapped and then work both down
- * and up from there in 1/6 VA space sized steps.
+ * Here we start with a guess that the addresses around 5/8th
+ * of the allowed space are unmapped and then work both down and
+ * up from there in 1/16th allowed space sized steps.
+ *
+ * Note, we need to use VA-bits - 1 when calculating the allowed
+ * virtual address space for an identity mapping because the upper
+ * half of the virtual address space is the two's complement of the
+ * lower and won't match physical addresses.
*/
- start = 1ul << (vm->va_bits * 2 / 3);
- end = 1ul << vm->va_bits;
- step = 1ul << (vm->va_bits / 6);
- for (gpa = start; gpa >= 0; gpa -= step) {
- if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+ bits = vm->va_bits - 1;
+ bits = vm->pa_bits < bits ? vm->pa_bits : bits;
+ end = 1ul << bits;
+ start = end * 5 / 8;
+ step = end / 16;
+ for (offset = 0; offset < end - start; offset += step) {
+ if (ucall_mmio_init(vm, start - offset))
return;
- }
- for (gpa = start + step; gpa < end; gpa += step) {
- if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+ if (ucall_mmio_init(vm, start + offset))
return;
}
TEST_ASSERT(false, "Can't find a ucall mmio address");
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 92c2cfd1b182..ea3c73e8f4f6 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -113,8 +113,8 @@ int main(int argc, char *argv[])
for (stage = 1;; stage++) {
_vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Unexpected exit reason: %u (%s),\n",
- run->exit_reason,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
exit_reason_str(run->exit_reason));
memset(&regs1, 0, sizeof(regs1));
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
new file mode 100644
index 000000000000..264425f75806
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_CAP_HYPERV_CPUID
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+static void guest_code(void)
+{
+}
+
+static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
+ int evmcs_enabled)
+{
+ int i;
+
+ if (!evmcs_enabled)
+ TEST_ASSERT(hv_cpuid_entries->nent == 6,
+ "KVM_GET_SUPPORTED_HV_CPUID should return 6 entries"
+ " when Enlightened VMCS is disabled (returned %d)",
+ hv_cpuid_entries->nent);
+ else
+ TEST_ASSERT(hv_cpuid_entries->nent == 7,
+ "KVM_GET_SUPPORTED_HV_CPUID should return 7 entries"
+ " when Enlightened VMCS is enabled (returned %d)",
+ hv_cpuid_entries->nent);
+
+ for (i = 0; i < hv_cpuid_entries->nent; i++) {
+ struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
+
+ TEST_ASSERT((entry->function >= 0x40000000) &&
+ (entry->function <= 0x4000000A),
+ "function %lx is our of supported range",
+ entry->function);
+
+ TEST_ASSERT(entry->index == 0,
+ ".index field should be zero");
+
+ TEST_ASSERT(entry->index == 0,
+ ".index field should be zero");
+
+ TEST_ASSERT(entry->flags == 0,
+ ".flags field should be zero");
+
+ TEST_ASSERT(entry->padding[0] == entry->padding[1]
+ == entry->padding[2] == 0,
+ ".index field should be zero");
+
+ /*
+ * If needed for debug:
+ * fprintf(stdout,
+ * "CPUID%lx EAX=0x%lx EBX=0x%lx ECX=0x%lx EDX=0x%lx\n",
+ * entry->function, entry->eax, entry->ebx, entry->ecx,
+ * entry->edx);
+ */
+ }
+
+}
+
+void test_hv_cpuid_e2big(struct kvm_vm *vm)
+{
+ static struct kvm_cpuid2 cpuid = {.nent = 0};
+ int ret;
+
+ ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+
+ TEST_ASSERT(ret == -1 && errno == E2BIG,
+ "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
+ " it should have: %d %d", ret, errno);
+}
+
+
+struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
+{
+ int nent = 20; /* should be enough */
+ static struct kvm_cpuid2 *cpuid;
+ int ret;
+
+ cpuid = malloc(sizeof(*cpuid) + nent * sizeof(struct kvm_cpuid_entry2));
+
+ if (!cpuid) {
+ perror("malloc");
+ abort();
+ }
+
+ cpuid->nent = nent;
+
+ vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+
+ return cpuid;
+}
+
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ int rv;
+ uint16_t evmcs_ver;
+ struct kvm_cpuid2 *hv_cpuid_entries;
+ struct kvm_enable_cap enable_evmcs_cap = {
+ .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+ .args[0] = (unsigned long)&evmcs_ver
+ };
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
+ if (!rv) {
+ fprintf(stderr,
+ "KVM_CAP_HYPERV_CPUID not supported, skip test\n");
+ exit(KSFT_SKIP);
+ }
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ test_hv_cpuid_e2big(vm);
+
+ hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+ if (!hv_cpuid_entries)
+ return 1;
+
+ test_hv_cpuid(hv_cpuid_entries, 0);
+
+ free(hv_cpuid_entries);
+
+ vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+ hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+ if (!hv_cpuid_entries)
+ return 1;
+
+ test_hv_cpuid(hv_cpuid_entries, 1);
+
+ free(hv_cpuid_entries);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 03da41f0f736..4b3f556265f1 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -152,8 +152,8 @@ int main(int argc, char *argv[])
for (stage = 1;; stage++) {
_vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Unexpected exit reason: %u (%s),\n",
- run->exit_reason,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
exit_reason_str(run->exit_reason));
memset(&regs1, 0, sizeof(regs1));
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 0a8e75886224..8b0f16409ed7 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -16,18 +16,18 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
+ifdef KSFT_KHDR_INSTALL
top_srcdir ?= ../../../..
include $(top_srcdir)/scripts/subarch.include
ARCH ?= $(SUBARCH)
-all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
-
.PHONY: khdr
khdr:
make ARCH=$(ARCH) -C $(top_srcdir) headers_install
-ifdef KSFT_KHDR_INSTALL
-$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr
+all: khdr $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+else
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
endif
.ONESHELL:
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index 6c17a93c4e03..9050eeea5f5f 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -7,6 +7,7 @@ TEST_PROGS := txtimestamp.sh
all: $(TEST_PROGS)
top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
include ../../lib.mk
clean:
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index 49621822d7c3..ae43a614835d 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -82,6 +82,16 @@ do { \
} \
} while (0)
+#define SKIP_IF_MSG(x, msg) \
+do { \
+ if ((x)) { \
+ fprintf(stderr, \
+ "[SKIP] Test skipped on line %d: %s\n", \
+ __LINE__, msg); \
+ return MAGIC_SKIP_RETURN_VALUE; \
+ } \
+} while (0)
+
#define _str(s) #s
#define str(s) _str(s)
diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
index e23e2e199eb4..d5c64fee032d 100644
--- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
@@ -352,10 +352,7 @@ static int write_core_pattern(const char *core_pattern)
FILE *f;
f = fopen(core_pattern_file, "w");
- if (!f) {
- perror("Error writing to core_pattern file");
- return TEST_FAIL;
- }
+ SKIP_IF_MSG(!f, "Try with root privileges");
ret = fwrite(core_pattern, 1, len, f);
fclose(f);
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c
index 0b4ebcc2f485..ca29fafeed5d 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c
@@ -31,7 +31,7 @@ void gpr(void)
ASM_LOAD_GPR_IMMED(gpr_1)
ASM_LOAD_FPR_SINGLE_PRECISION(flt_1)
:
- : [gpr_1]"i"(GPR_1), [flt_1] "r" (&a)
+ : [gpr_1]"i"(GPR_1), [flt_1] "b" (&a)
: "memory", "r6", "r7", "r8", "r9", "r10",
"r11", "r12", "r13", "r14", "r15", "r16", "r17",
"r18", "r19", "r20", "r21", "r22", "r23", "r24",
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
index 59206b96e98a..a08a91594dbe 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c
@@ -59,8 +59,8 @@ trans:
"3: ;"
: [res] "=r" (result), [texasr] "=r" (texasr)
: [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2),
- [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "r" (&a),
- [flt_2] "r" (&b), [cptr1] "r" (&cptr[1])
+ [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a),
+ [flt_2] "b" (&b), [cptr1] "b" (&cptr[1])
: "memory", "r7", "r8", "r9", "r10",
"r11", "r12", "r13", "r14", "r15", "r16",
"r17", "r18", "r19", "r20", "r21", "r22",
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
index b3c061dc9512..f47174746231 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c
@@ -72,7 +72,7 @@ trans:
"3: ;"
: [res] "=r" (result), [texasr] "=r" (texasr)
- : [val] "r" (cptr[1]), [sprn_dscr]"i"(SPRN_DSCR),
+ : [sprn_dscr]"i"(SPRN_DSCR),
[sprn_tar]"i"(SPRN_TAR), [sprn_ppr]"i"(SPRN_PPR),
[sprn_texasr]"i"(SPRN_TEXASR), [tar_1]"i"(TAR_1),
[dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2), [dscr_2]"i"(DSCR_2),
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
index 277dade1b382..18a685bf6a09 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c
@@ -77,8 +77,7 @@ trans:
"3: ;"
: [res] "=r" (result), [texasr] "=r" (texasr)
- : [fp_load] "r" (fp_load), [fp_load_ckpt] "r" (fp_load_ckpt),
- [sprn_texasr] "i" (SPRN_TEXASR)
+ : [sprn_texasr] "i" (SPRN_TEXASR)
: "memory", "r0", "r1", "r3", "r4",
"r7", "r8", "r9", "r10", "r11"
);
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
index 51427a2465f6..ba04999254e3 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c
@@ -74,7 +74,7 @@ trans:
"3: ;"
: [tfhar] "=r" (tfhar), [res] "=r" (result),
- [texasr] "=r" (texasr), [cptr1] "=r" (cptr1)
+ [texasr] "=r" (texasr), [cptr1] "=b" (cptr1)
: [sprn_texasr] "i" (SPRN_TEXASR)
: "memory", "r0", "r8", "r31"
);
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
index 48b462f75023..f70023b25e6e 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c
@@ -65,7 +65,7 @@ trans:
: [sprn_dscr]"i"(SPRN_DSCR), [sprn_tar]"i"(SPRN_TAR),
[sprn_ppr]"i"(SPRN_PPR), [sprn_texasr]"i"(SPRN_TEXASR),
[tar_1]"i"(TAR_1), [dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2),
- [dscr_2]"i"(DSCR_2), [cptr1] "r" (&cptr[1])
+ [dscr_2]"i"(DSCR_2), [cptr1] "b" (&cptr[1])
: "memory", "r0", "r1", "r3", "r4", "r5", "r6"
);
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
index 17c23cabac3e..dfba80058977 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c
@@ -65,8 +65,7 @@ trans:
"3: ;"
: [res] "=r" (result), [texasr] "=r" (texasr)
- : [fp_load] "r" (fp_load), [fp_load_ckpt] "r" (fp_load_ckpt),
- [sprn_texasr] "i" (SPRN_TEXASR), [cptr1] "r" (&cptr[1])
+ : [sprn_texasr] "i" (SPRN_TEXASR), [cptr1] "b" (&cptr[1])
: "memory", "r0", "r1", "r3", "r4",
"r7", "r8", "r9", "r10", "r11"
);
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index c3ee8393dae8..208452a93e2c 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -11,6 +11,7 @@ tm-signal-context-chk-fpu
tm-signal-context-chk-gpr
tm-signal-context-chk-vmx
tm-signal-context-chk-vsx
+tm-signal-sigreturn-nt
tm-vmx-unavail
tm-unavailable
tm-trap
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 9fc2cf6fbc92..75a685359129 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -4,7 +4,7 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu
TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \
- $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn
+ $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt
top_srcdir = ../../../../..
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c
new file mode 100644
index 000000000000..56fbf9f6bbf3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018, Breno Leitao, Gustavo Romero, IBM Corp.
+ *
+ * A test case that creates a signal and starts a suspended transaction
+ * inside the signal handler.
+ *
+ * It returns from the signal handler with the CPU at suspended state, but
+ * without setting usercontext MSR Transaction State (TS) fields.
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <signal.h>
+
+#include "utils.h"
+
+void trap_signal_handler(int signo, siginfo_t *si, void *uc)
+{
+ ucontext_t *ucp = (ucontext_t *) uc;
+
+ asm("tbegin.; tsuspend.;");
+
+ /* Skip 'trap' instruction if it succeed */
+ ucp->uc_mcontext.regs->nip += 4;
+}
+
+int tm_signal_sigreturn_nt(void)
+{
+ struct sigaction trap_sa;
+
+ trap_sa.sa_flags = SA_SIGINFO;
+ trap_sa.sa_sigaction = trap_signal_handler;
+
+ sigaction(SIGTRAP, &trap_sa, NULL);
+
+ raise(SIGTRAP);
+
+ return EXIT_SUCCESS;
+}
+
+int main(int argc, char **argv)
+{
+ test_harness(tm_signal_sigreturn_nt, "tm_signal_sigreturn_nt");
+}
+
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 5a7a62d76a50..19864f1cb27a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -194,6 +194,14 @@ do
shift
done
+if test -z "$TORTURE_INITRD" || tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+then
+ :
+else
+ echo No initrd and unable to create one, aborting test >&2
+ exit 1
+fi
+
CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
if test -z "$configs"
diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
new file mode 100755
index 000000000000..da298394daa2
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -0,0 +1,136 @@
+#!/bin/bash
+#
+# Create an initrd directory if one does not already exist.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Author: Connor Shu <Connor.Shu@ibm.com>
+
+D=tools/testing/selftests/rcutorture
+
+# Prerequisite checks
+[ -z "$D" ] && echo >&2 "No argument supplied" && exit 1
+if [ ! -d "$D" ]; then
+ echo >&2 "$D does not exist: Malformed kernel source tree?"
+ exit 1
+fi
+if [ -s "$D/initrd/init" ]; then
+ echo "$D/initrd/init already exists, no need to create it"
+ exit 0
+fi
+
+T=${TMPDIR-/tmp}/mkinitrd.sh.$$
+trap 'rm -rf $T' 0 2
+mkdir $T
+
+cat > $T/init << '__EOF___'
+#!/bin/sh
+# Run in userspace a few milliseconds every second. This helps to
+# exercise the NO_HZ_FULL portions of RCU.
+while :
+do
+ q=
+ for i in \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
+ a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
+ do
+ q="$q $i"
+ done
+ sleep 1
+done
+__EOF___
+
+# Try using dracut to create initrd
+if command -v dracut >/dev/null 2>&1
+then
+ echo Creating $D/initrd using dracut.
+ # Filesystem creation
+ dracut --force --no-hostonly --no-hostonly-cmdline --module "base" $T/initramfs.img
+ cd $D
+ mkdir -p initrd
+ cd initrd
+ zcat $T/initramfs.img | cpio -id
+ cp $T/init init
+ chmod +x init
+ echo Done creating $D/initrd using dracut
+ exit 0
+fi
+
+# No dracut, so create a C-language initrd/init program and statically
+# link it. This results in a very small initrd, but might be a bit less
+# future-proof than dracut.
+echo "Could not find dracut, attempting C initrd"
+cd $D
+mkdir -p initrd
+cd initrd
+cat > init.c << '___EOF___'
+#ifndef NOLIBC
+#include <unistd.h>
+#include <sys/time.h>
+#endif
+
+volatile unsigned long delaycount;
+
+int main(int argc, int argv[])
+{
+ int i;
+ struct timeval tv;
+ struct timeval tvb;
+
+ for (;;) {
+ sleep(1);
+ /* Need some userspace time. */
+ if (gettimeofday(&tvb, NULL))
+ continue;
+ do {
+ for (i = 0; i < 1000 * 100; i++)
+ delaycount = i * i;
+ if (gettimeofday(&tv, NULL))
+ break;
+ tv.tv_sec -= tvb.tv_sec;
+ if (tv.tv_sec > 1)
+ break;
+ tv.tv_usec += tv.tv_sec * 1000 * 1000;
+ tv.tv_usec -= tvb.tv_usec;
+ } while (tv.tv_usec < 1000);
+ }
+ return 0;
+}
+___EOF___
+
+# build using nolibc on supported archs (smaller executable) and fall
+# back to regular glibc on other ones.
+if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \
+ "||__ARM_EABI__||__aarch64__\nyes\n#endif" \
+ | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \
+ | grep -q '^yes'; then
+ # architecture supported by nolibc
+ ${CROSS_COMPILE}gcc -fno-asynchronous-unwind-tables -fno-ident \
+ -nostdlib -include ../bin/nolibc.h -lgcc -s -static -Os \
+ -o init init.c
+else
+ ${CROSS_COMPILE}gcc -s -static -Os -o init init.c
+fi
+
+rm init.c
+echo "Done creating a statically linked C-language initrd"
+
+exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/nolibc.h b/tools/testing/selftests/rcutorture/bin/nolibc.h
new file mode 100644
index 000000000000..f98f5b92d3eb
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/nolibc.h
@@ -0,0 +1,2197 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/* nolibc.h
+ * Copyright (C) 2017-2018 Willy Tarreau <w@1wt.eu>
+ */
+
+/* some archs (at least aarch64) don't expose the regular syscalls anymore by
+ * default, either because they have an "_at" replacement, or because there are
+ * more modern alternatives. For now we'd rather still use them.
+ */
+#define __ARCH_WANT_SYSCALL_NO_AT
+#define __ARCH_WANT_SYSCALL_NO_FLAGS
+#define __ARCH_WANT_SYSCALL_DEPRECATED
+
+#include <asm/unistd.h>
+#include <asm/ioctls.h>
+#include <asm/errno.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+
+#define NOLIBC
+
+/* Build a static executable this way :
+ * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ * -static -include nolibc.h -lgcc -o hello hello.c
+ *
+ * Useful calling convention table found here :
+ * http://man7.org/linux/man-pages/man2/syscall.2.html
+ *
+ * This doc is even better :
+ * https://w3challs.com/syscalls/
+ */
+
+
+/* this way it will be removed if unused */
+static int errno;
+
+#ifndef NOLIBC_IGNORE_ERRNO
+#define SET_ERRNO(v) do { errno = (v); } while (0)
+#else
+#define SET_ERRNO(v) do { } while (0)
+#endif
+
+/* errno codes all ensure that they will not conflict with a valid pointer
+ * because they all correspond to the highest addressable memry page.
+ */
+#define MAX_ERRNO 4095
+
+/* Declare a few quite common macros and types that usually are in stdlib.h,
+ * stdint.h, ctype.h, unistd.h and a few other common locations.
+ */
+
+#define NULL ((void *)0)
+
+/* stdint types */
+typedef unsigned char uint8_t;
+typedef signed char int8_t;
+typedef unsigned short uint16_t;
+typedef signed short int16_t;
+typedef unsigned int uint32_t;
+typedef signed int int32_t;
+typedef unsigned long long uint64_t;
+typedef signed long long int64_t;
+typedef unsigned long size_t;
+typedef signed long ssize_t;
+typedef unsigned long uintptr_t;
+typedef signed long intptr_t;
+typedef signed long ptrdiff_t;
+
+/* for stat() */
+typedef unsigned int dev_t;
+typedef unsigned long ino_t;
+typedef unsigned int mode_t;
+typedef signed int pid_t;
+typedef unsigned int uid_t;
+typedef unsigned int gid_t;
+typedef unsigned long nlink_t;
+typedef signed long off_t;
+typedef signed long blksize_t;
+typedef signed long blkcnt_t;
+typedef signed long time_t;
+
+/* for poll() */
+struct pollfd {
+ int fd;
+ short int events;
+ short int revents;
+};
+
+/* for select() */
+struct timeval {
+ long tv_sec;
+ long tv_usec;
+};
+
+/* for pselect() */
+struct timespec {
+ long tv_sec;
+ long tv_nsec;
+};
+
+/* for gettimeofday() */
+struct timezone {
+ int tz_minuteswest;
+ int tz_dsttime;
+};
+
+/* for getdents64() */
+struct linux_dirent64 {
+ uint64_t d_ino;
+ int64_t d_off;
+ unsigned short d_reclen;
+ unsigned char d_type;
+ char d_name[];
+};
+
+/* commonly an fd_set represents 256 FDs */
+#define FD_SETSIZE 256
+typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set;
+
+/* needed by wait4() */
+struct rusage {
+ struct timeval ru_utime;
+ struct timeval ru_stime;
+ long ru_maxrss;
+ long ru_ixrss;
+ long ru_idrss;
+ long ru_isrss;
+ long ru_minflt;
+ long ru_majflt;
+ long ru_nswap;
+ long ru_inblock;
+ long ru_oublock;
+ long ru_msgsnd;
+ long ru_msgrcv;
+ long ru_nsignals;
+ long ru_nvcsw;
+ long ru_nivcsw;
+};
+
+/* stat flags (WARNING, octal here) */
+#define S_IFDIR 0040000
+#define S_IFCHR 0020000
+#define S_IFBLK 0060000
+#define S_IFREG 0100000
+#define S_IFIFO 0010000
+#define S_IFLNK 0120000
+#define S_IFSOCK 0140000
+#define S_IFMT 0170000
+
+#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+
+#define DT_UNKNOWN 0
+#define DT_FIFO 1
+#define DT_CHR 2
+#define DT_DIR 4
+#define DT_BLK 6
+#define DT_REG 8
+#define DT_LNK 10
+#define DT_SOCK 12
+
+/* all the *at functions */
+#ifndef AT_FDWCD
+#define AT_FDCWD -100
+#endif
+
+/* lseek */
+#define SEEK_SET 0
+#define SEEK_CUR 1
+#define SEEK_END 2
+
+/* reboot */
+#define LINUX_REBOOT_MAGIC1 0xfee1dead
+#define LINUX_REBOOT_MAGIC2 0x28121969
+#define LINUX_REBOOT_CMD_HALT 0xcdef0123
+#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc
+#define LINUX_REBOOT_CMD_RESTART 0x01234567
+#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2
+
+
+/* The format of the struct as returned by the libc to the application, which
+ * significantly differs from the format returned by the stat() syscall flavours.
+ */
+struct stat {
+ dev_t st_dev; /* ID of device containing file */
+ ino_t st_ino; /* inode number */
+ mode_t st_mode; /* protection */
+ nlink_t st_nlink; /* number of hard links */
+ uid_t st_uid; /* user ID of owner */
+ gid_t st_gid; /* group ID of owner */
+ dev_t st_rdev; /* device ID (if special file) */
+ off_t st_size; /* total size, in bytes */
+ blksize_t st_blksize; /* blocksize for file system I/O */
+ blkcnt_t st_blocks; /* number of 512B blocks allocated */
+ time_t st_atime; /* time of last access */
+ time_t st_mtime; /* time of last modification */
+ time_t st_ctime; /* time of last status change */
+};
+
+#define WEXITSTATUS(status) (((status) & 0xff00) >> 8)
+#define WIFEXITED(status) (((status) & 0x7f) == 0)
+
+
+/* Below comes the architecture-specific code. For each architecture, we have
+ * the syscall declarations and the _start code definition. This is the only
+ * global part. On all architectures the kernel puts everything in the stack
+ * before jumping to _start just above us, without any return address (_start
+ * is not a function but an entry pint). So at the stack pointer we find argc.
+ * Then argv[] begins, and ends at the first NULL. Then we have envp which
+ * starts and ends with a NULL as well. So envp=argv+argc+1.
+ */
+
+#if defined(__x86_64__)
+/* Syscalls for x86_64 :
+ * - registers are 64-bit
+ * - syscall number is passed in rax
+ * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
+ * - the system call is performed by calling the syscall instruction
+ * - syscall return comes in rax
+ * - rcx and r8..r11 may be clobbered, others are preserved.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ */
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret) \
+ : "0"(_num) \
+ : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ register long _arg2 asm("rsi") = (long)(arg2); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ register long _arg2 asm("rsi") = (long)(arg2); \
+ register long _arg3 asm("rdx") = (long)(arg3); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "rcx", "r8", "r9", "r10", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ register long _arg2 asm("rsi") = (long)(arg2); \
+ register long _arg3 asm("rdx") = (long)(arg3); \
+ register long _arg4 asm("r10") = (long)(arg4); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret), "=r"(_arg4) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "rcx", "r8", "r9", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ register long _arg2 asm("rsi") = (long)(arg2); \
+ register long _arg3 asm("rdx") = (long)(arg3); \
+ register long _arg4 asm("r10") = (long)(arg4); \
+ register long _arg5 asm("r8") = (long)(arg5); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "rcx", "r9", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ long _ret; \
+ register long _num asm("rax") = (num); \
+ register long _arg1 asm("rdi") = (long)(arg1); \
+ register long _arg2 asm("rsi") = (long)(arg2); \
+ register long _arg3 asm("rdx") = (long)(arg3); \
+ register long _arg4 asm("r10") = (long)(arg4); \
+ register long _arg5 asm("r8") = (long)(arg5); \
+ register long _arg6 asm("r9") = (long)(arg6); \
+ \
+ asm volatile ( \
+ "syscall\n" \
+ : "=a" (_ret), "=r"(_arg4), "=r"(_arg5) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+/* startup code */
+asm(".section .text\n"
+ ".global _start\n"
+ "_start:\n"
+ "pop %rdi\n" // argc (first arg, %rdi)
+ "mov %rsp, %rsi\n" // argv[] (second arg, %rsi)
+ "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
+ "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned when
+ "sub $8, %rsp\n" // entering the callee
+ "call main\n" // main() returns the status code, we'll exit with it.
+ "movzb %al, %rdi\n" // retrieve exit code from 8 lower bits
+ "mov $60, %rax\n" // NR_exit == 60
+ "syscall\n" // really exit
+ "hlt\n" // ensure it does not return
+ "");
+
+/* fcntl / open */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall, equivalent to stat64(). The
+ * syscall returns 116 bytes and stops in the middle of __unused.
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned long st_nlink;
+ unsigned int st_mode;
+ unsigned int st_uid;
+
+ unsigned int st_gid;
+ unsigned int __pad0;
+ unsigned long st_rdev;
+ long st_size;
+ long st_blksize;
+
+ long st_blocks;
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+
+ unsigned long st_mtime_nsec;
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ long __unused[3];
+};
+
+#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
+/* Syscalls for i386 :
+ * - mostly similar to x86_64
+ * - registers are 32-bit
+ * - syscall number is passed in eax
+ * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
+ * - all registers are preserved (except eax of course)
+ * - the system call is performed by calling int $0x80
+ * - syscall return comes in eax
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, i386 supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ register long _arg1 asm("ebx") = (long)(arg1); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ register long _arg1 asm("ebx") = (long)(arg1); \
+ register long _arg2 asm("ecx") = (long)(arg2); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ register long _arg1 asm("ebx") = (long)(arg1); \
+ register long _arg2 asm("ecx") = (long)(arg2); \
+ register long _arg3 asm("edx") = (long)(arg3); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ register long _arg1 asm("ebx") = (long)(arg1); \
+ register long _arg2 asm("ecx") = (long)(arg2); \
+ register long _arg3 asm("edx") = (long)(arg3); \
+ register long _arg4 asm("esi") = (long)(arg4); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num asm("eax") = (num); \
+ register long _arg1 asm("ebx") = (long)(arg1); \
+ register long _arg2 asm("ecx") = (long)(arg2); \
+ register long _arg3 asm("edx") = (long)(arg3); \
+ register long _arg4 asm("esi") = (long)(arg4); \
+ register long _arg5 asm("edi") = (long)(arg5); \
+ \
+ asm volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+/* startup code */
+asm(".section .text\n"
+ ".global _start\n"
+ "_start:\n"
+ "pop %eax\n" // argc (first arg, %eax)
+ "mov %esp, %ebx\n" // argv[] (second arg, %ebx)
+ "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
+ "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned when
+ "push %ecx\n" // push all registers on the stack so that we
+ "push %ebx\n" // support both regparm and plain stack modes
+ "push %eax\n"
+ "call main\n" // main() returns the status code in %eax
+ "movzbl %al, %ebx\n" // retrieve exit code from lower 8 bits
+ "movl $1, %eax\n" // NR_exit == 1
+ "int $0x80\n" // exit now
+ "hlt\n" // ensure it does not
+ "");
+
+/* fcntl / open */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array).
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+
+ unsigned long st_rdev;
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+ unsigned long st_mtime_nsec;
+
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned long __unused[2];
+};
+
+#elif defined(__ARM_EABI__)
+/* Syscalls for ARM in ARM or Thumb modes :
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
+ * - syscall number is passed in r7
+ * - arguments are in r0, r1, r2, r3, r4, r5
+ * - the system call is performed by calling svc #0
+ * - syscall return comes in r0.
+ * - only lr is clobbered.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, ARM supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0"); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0") = (long)(arg1); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0") = (long)(arg1); \
+ register long _arg2 asm("r1") = (long)(arg2); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0") = (long)(arg1); \
+ register long _arg2 asm("r1") = (long)(arg2); \
+ register long _arg3 asm("r2") = (long)(arg3); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0") = (long)(arg1); \
+ register long _arg2 asm("r1") = (long)(arg2); \
+ register long _arg3 asm("r2") = (long)(arg3); \
+ register long _arg4 asm("r3") = (long)(arg4); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num asm("r7") = (num); \
+ register long _arg1 asm("r0") = (long)(arg1); \
+ register long _arg2 asm("r1") = (long)(arg2); \
+ register long _arg3 asm("r2") = (long)(arg3); \
+ register long _arg4 asm("r3") = (long)(arg4); \
+ register long _arg5 asm("r4") = (long)(arg5); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+asm(".section .text\n"
+ ".global _start\n"
+ "_start:\n"
+#if defined(__THUMBEB__) || defined(__THUMBEL__)
+ /* We enter here in 32-bit mode but if some previous functions were in
+ * 16-bit mode, the assembler cannot know, so we need to tell it we're in
+ * 32-bit now, then switch to 16-bit (is there a better way to do it than
+ * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that
+ * it generates correct instructions. Note that we do not support thumb1.
+ */
+ ".code 32\n"
+ "add r0, pc, #1\n"
+ "bx r0\n"
+ ".code 16\n"
+#endif
+ "pop {%r0}\n" // argc was in the stack
+ "mov %r1, %sp\n" // argv = sp
+ "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ...
+ "add %r2, %r2, $4\n" // ... + 4
+ "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the
+ "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc)
+ "bl main\n" // main() returns the status code, we'll exit with it.
+ "and %r0, %r0, $0xff\n" // limit exit code to 8 bits
+ "movs r7, $1\n" // NR_exit == 1
+ "svc $0x00\n"
+ "");
+
+/* fcntl / open */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x4000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array). In big endian, the format
+ * differs as devices are returned as short only.
+ */
+struct sys_stat_struct {
+#if defined(__ARMEB__)
+ unsigned short st_dev;
+ unsigned short __pad1;
+#else
+ unsigned long st_dev;
+#endif
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+#if defined(__ARMEB__)
+ unsigned short st_rdev;
+ unsigned short __pad2;
+#else
+ unsigned long st_rdev;
+#endif
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+ unsigned long st_mtime_nsec;
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned long __unused[2];
+};
+
+#elif defined(__aarch64__)
+/* Syscalls for AARCH64 :
+ * - registers are 64-bit
+ * - stack is 16-byte aligned
+ * - syscall number is passed in x8
+ * - arguments are in x0, x1, x2, x3, x4, x5
+ * - the system call is performed by calling svc 0
+ * - syscall return comes in x0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ *
+ * On aarch64, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0"); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ register long _arg2 asm("x1") = (long)(arg2); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ register long _arg2 asm("x1") = (long)(arg2); \
+ register long _arg3 asm("x2") = (long)(arg3); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ register long _arg2 asm("x1") = (long)(arg2); \
+ register long _arg3 asm("x2") = (long)(arg3); \
+ register long _arg4 asm("x3") = (long)(arg4); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ register long _arg2 asm("x1") = (long)(arg2); \
+ register long _arg3 asm("x2") = (long)(arg3); \
+ register long _arg4 asm("x3") = (long)(arg4); \
+ register long _arg5 asm("x4") = (long)(arg5); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num asm("x8") = (num); \
+ register long _arg1 asm("x0") = (long)(arg1); \
+ register long _arg2 asm("x1") = (long)(arg2); \
+ register long _arg3 asm("x2") = (long)(arg3); \
+ register long _arg4 asm("x3") = (long)(arg4); \
+ register long _arg5 asm("x4") = (long)(arg5); \
+ register long _arg6 asm("x5") = (long)(arg6); \
+ \
+ asm volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+asm(".section .text\n"
+ ".global _start\n"
+ "_start:\n"
+ "ldr x0, [sp]\n" // argc (x0) was in the stack
+ "add x1, sp, 8\n" // argv (x1) = sp
+ "lsl x2, x0, 3\n" // envp (x2) = 8*argc ...
+ "add x2, x2, 8\n" // + 8 (skip null)
+ "add x2, x2, x1\n" // + argv
+ "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee
+ "bl main\n" // main() returns the status code, we'll exit with it.
+ "and x0, x0, 0xff\n" // limit exit code to 8 bits
+ "mov x8, 93\n" // NR_exit == 93
+ "svc #0\n"
+ "");
+
+/* fcntl / open */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x4000
+
+/* The struct returned by the newfstatat() syscall. Differs slightly from the
+ * x86_64's stat one by field ordering, so be careful.
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned int st_mode;
+ unsigned int st_nlink;
+ unsigned int st_uid;
+ unsigned int st_gid;
+
+ unsigned long st_rdev;
+ unsigned long __pad1;
+ long st_size;
+ int st_blksize;
+ int __pad2;
+
+ long st_blocks;
+ long st_atime;
+ unsigned long st_atime_nsec;
+ long st_mtime;
+
+ unsigned long st_mtime_nsec;
+ long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned int __unused[2];
+};
+
+#elif defined(__mips__) && defined(_ABIO32)
+/* Syscalls for MIPS ABI O32 :
+ * - WARNING! there's always a delayed slot!
+ * - WARNING again, the syntax is different, registers take a '$' and numbers
+ * do not.
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * - syscall number is passed in v0 (starts at 0xfa0).
+ * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
+ * leave some room in the stack for the callee to save a0..a3 if needed.
+ * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
+ * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
+ * scall32-o32.S in the kernel sources.
+ * - the system call is performed by calling "syscall"
+ * - syscall return comes in v0, and register a3 needs to be checked to know
+ * if an error occured, in which case errno is in v0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ */
+
+#define my_syscall0(num) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg4 asm("a3"); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "r"(_num) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg1 asm("a0") = (long)(arg1); \
+ register long _arg4 asm("a3"); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg1 asm("a0") = (long)(arg1); \
+ register long _arg2 asm("a1") = (long)(arg2); \
+ register long _arg4 asm("a3"); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg1 asm("a0") = (long)(arg1); \
+ register long _arg2 asm("a1") = (long)(arg2); \
+ register long _arg3 asm("a2") = (long)(arg3); \
+ register long _arg4 asm("a3"); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg1 asm("a0") = (long)(arg1); \
+ register long _arg2 asm("a1") = (long)(arg2); \
+ register long _arg3 asm("a2") = (long)(arg3); \
+ register long _arg4 asm("a3") = (long)(arg4); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num asm("v0") = (num); \
+ register long _arg1 asm("a0") = (long)(arg1); \
+ register long _arg2 asm("a1") = (long)(arg2); \
+ register long _arg3 asm("a2") = (long)(arg3); \
+ register long _arg4 asm("a3") = (long)(arg4); \
+ register long _arg5 = (long)(arg5); \
+ \
+ asm volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "sw %7, 16($sp)\n" \
+ "syscall\n " \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+/* startup code, note that it's called __start on MIPS */
+asm(".section .text\n"
+ ".set nomips16\n"
+ ".global __start\n"
+ ".set noreorder\n"
+ ".option pic0\n"
+ ".ent __start\n"
+ "__start:\n"
+ "lw $a0,($sp)\n" // argc was in the stack
+ "addiu $a1, $sp, 4\n" // argv = sp + 4
+ "sll $a2, $a0, 2\n" // a2 = argc * 4
+ "add $a2, $a2, $a1\n" // envp = argv + 4*argc ...
+ "addiu $a2, $a2, 4\n" // ... + 4
+ "li $t0, -8\n"
+ "and $sp, $sp, $t0\n" // sp must be 8-byte aligned
+ "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there!
+ "jal main\n" // main() returns the status code, we'll exit with it.
+ "nop\n" // delayed slot
+ "and $a0, $v0, 0xff\n" // limit exit code to 8 bits
+ "li $v0, 4001\n" // NR_exit == 4001
+ "syscall\n"
+ ".end __start\n"
+ "");
+
+/* fcntl / open */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_APPEND 0x0008
+#define O_NONBLOCK 0x0080
+#define O_CREAT 0x0100
+#define O_TRUNC 0x0200
+#define O_EXCL 0x0400
+#define O_NOCTTY 0x0800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall. 88 bytes are returned by the
+ * syscall.
+ */
+struct sys_stat_struct {
+ unsigned int st_dev;
+ long st_pad1[3];
+ unsigned long st_ino;
+ unsigned int st_mode;
+ unsigned int st_nlink;
+ unsigned int st_uid;
+ unsigned int st_gid;
+ unsigned int st_rdev;
+ long st_pad2[2];
+ long st_size;
+ long st_pad3;
+ long st_atime;
+ long st_atime_nsec;
+ long st_mtime;
+ long st_mtime_nsec;
+ long st_ctime;
+ long st_ctime_nsec;
+ long st_blksize;
+ long st_blocks;
+ long st_pad4[14];
+};
+
+#endif
+
+
+/* Below are the C functions used to declare the raw syscalls. They try to be
+ * architecture-agnostic, and return either a success or -errno. Declaring them
+ * static will lead to them being inlined in most cases, but it's still possible
+ * to reference them by a pointer if needed.
+ */
+static __attribute__((unused))
+void *sys_brk(void *addr)
+{
+ return (void *)my_syscall1(__NR_brk, addr);
+}
+
+static __attribute__((noreturn,unused))
+void sys_exit(int status)
+{
+ my_syscall1(__NR_exit, status & 255);
+ while(1); // shut the "noreturn" warnings.
+}
+
+static __attribute__((unused))
+int sys_chdir(const char *path)
+{
+ return my_syscall1(__NR_chdir, path);
+}
+
+static __attribute__((unused))
+int sys_chmod(const char *path, mode_t mode)
+{
+#ifdef __NR_fchmodat
+ return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
+#else
+ return my_syscall2(__NR_chmod, path, mode);
+#endif
+}
+
+static __attribute__((unused))
+int sys_chown(const char *path, uid_t owner, gid_t group)
+{
+#ifdef __NR_fchownat
+ return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
+#else
+ return my_syscall3(__NR_chown, path, owner, group);
+#endif
+}
+
+static __attribute__((unused))
+int sys_chroot(const char *path)
+{
+ return my_syscall1(__NR_chroot, path);
+}
+
+static __attribute__((unused))
+int sys_close(int fd)
+{
+ return my_syscall1(__NR_close, fd);
+}
+
+static __attribute__((unused))
+int sys_dup(int fd)
+{
+ return my_syscall1(__NR_dup, fd);
+}
+
+static __attribute__((unused))
+int sys_dup2(int old, int new)
+{
+ return my_syscall2(__NR_dup2, old, new);
+}
+
+static __attribute__((unused))
+int sys_execve(const char *filename, char *const argv[], char *const envp[])
+{
+ return my_syscall3(__NR_execve, filename, argv, envp);
+}
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+ return my_syscall0(__NR_fork);
+}
+
+static __attribute__((unused))
+int sys_fsync(int fd)
+{
+ return my_syscall1(__NR_fsync, fd);
+}
+
+static __attribute__((unused))
+int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ return my_syscall3(__NR_getdents64, fd, dirp, count);
+}
+
+static __attribute__((unused))
+pid_t sys_getpgrp(void)
+{
+ return my_syscall0(__NR_getpgrp);
+}
+
+static __attribute__((unused))
+pid_t sys_getpid(void)
+{
+ return my_syscall0(__NR_getpid);
+}
+
+static __attribute__((unused))
+int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ return my_syscall2(__NR_gettimeofday, tv, tz);
+}
+
+static __attribute__((unused))
+int sys_ioctl(int fd, unsigned long req, void *value)
+{
+ return my_syscall3(__NR_ioctl, fd, req, value);
+}
+
+static __attribute__((unused))
+int sys_kill(pid_t pid, int signal)
+{
+ return my_syscall2(__NR_kill, pid, signal);
+}
+
+static __attribute__((unused))
+int sys_link(const char *old, const char *new)
+{
+#ifdef __NR_linkat
+ return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
+#else
+ return my_syscall2(__NR_link, old, new);
+#endif
+}
+
+static __attribute__((unused))
+off_t sys_lseek(int fd, off_t offset, int whence)
+{
+ return my_syscall3(__NR_lseek, fd, offset, whence);
+}
+
+static __attribute__((unused))
+int sys_mkdir(const char *path, mode_t mode)
+{
+#ifdef __NR_mkdirat
+ return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
+#else
+ return my_syscall2(__NR_mkdir, path, mode);
+#endif
+}
+
+static __attribute__((unused))
+long sys_mknod(const char *path, mode_t mode, dev_t dev)
+{
+#ifdef __NR_mknodat
+ return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
+#else
+ return my_syscall3(__NR_mknod, path, mode, dev);
+#endif
+}
+
+static __attribute__((unused))
+int sys_mount(const char *src, const char *tgt, const char *fst,
+ unsigned long flags, const void *data)
+{
+ return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
+}
+
+static __attribute__((unused))
+int sys_open(const char *path, int flags, mode_t mode)
+{
+#ifdef __NR_openat
+ return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
+#else
+ return my_syscall3(__NR_open, path, flags, mode);
+#endif
+}
+
+static __attribute__((unused))
+int sys_pivot_root(const char *new, const char *old)
+{
+ return my_syscall2(__NR_pivot_root, new, old);
+}
+
+static __attribute__((unused))
+int sys_poll(struct pollfd *fds, int nfds, int timeout)
+{
+ return my_syscall3(__NR_poll, fds, nfds, timeout);
+}
+
+static __attribute__((unused))
+ssize_t sys_read(int fd, void *buf, size_t count)
+{
+ return my_syscall3(__NR_read, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
+{
+ return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
+}
+
+static __attribute__((unused))
+int sys_sched_yield(void)
+{
+ return my_syscall0(__NR_sched_yield);
+}
+
+static __attribute__((unused))
+int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
+ struct sel_arg_struct {
+ unsigned long n;
+ fd_set *r, *w, *e;
+ struct timeval *t;
+ } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
+ return my_syscall1(__NR_select, &arg);
+#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
+ struct timespec t;
+
+ if (timeout) {
+ t.tv_sec = timeout->tv_sec;
+ t.tv_nsec = timeout->tv_usec * 1000;
+ }
+ return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
+#else
+#ifndef __NR__newselect
+#define __NR__newselect __NR_select
+#endif
+ return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
+#endif
+}
+
+static __attribute__((unused))
+int sys_setpgid(pid_t pid, pid_t pgid)
+{
+ return my_syscall2(__NR_setpgid, pid, pgid);
+}
+
+static __attribute__((unused))
+pid_t sys_setsid(void)
+{
+ return my_syscall0(__NR_setsid);
+}
+
+static __attribute__((unused))
+int sys_stat(const char *path, struct stat *buf)
+{
+ struct sys_stat_struct stat;
+ long ret;
+
+#ifdef __NR_newfstatat
+ /* only solution for arm64 */
+ ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
+#else
+ ret = my_syscall2(__NR_stat, path, &stat);
+#endif
+ buf->st_dev = stat.st_dev;
+ buf->st_ino = stat.st_ino;
+ buf->st_mode = stat.st_mode;
+ buf->st_nlink = stat.st_nlink;
+ buf->st_uid = stat.st_uid;
+ buf->st_gid = stat.st_gid;
+ buf->st_rdev = stat.st_rdev;
+ buf->st_size = stat.st_size;
+ buf->st_blksize = stat.st_blksize;
+ buf->st_blocks = stat.st_blocks;
+ buf->st_atime = stat.st_atime;
+ buf->st_mtime = stat.st_mtime;
+ buf->st_ctime = stat.st_ctime;
+ return ret;
+}
+
+
+static __attribute__((unused))
+int sys_symlink(const char *old, const char *new)
+{
+#ifdef __NR_symlinkat
+ return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
+#else
+ return my_syscall2(__NR_symlink, old, new);
+#endif
+}
+
+static __attribute__((unused))
+mode_t sys_umask(mode_t mode)
+{
+ return my_syscall1(__NR_umask, mode);
+}
+
+static __attribute__((unused))
+int sys_umount2(const char *path, int flags)
+{
+ return my_syscall2(__NR_umount2, path, flags);
+}
+
+static __attribute__((unused))
+int sys_unlink(const char *path)
+{
+#ifdef __NR_unlinkat
+ return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
+#else
+ return my_syscall1(__NR_unlink, path);
+#endif
+}
+
+static __attribute__((unused))
+pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+ return my_syscall4(__NR_wait4, pid, status, options, rusage);
+}
+
+static __attribute__((unused))
+pid_t sys_waitpid(pid_t pid, int *status, int options)
+{
+ return sys_wait4(pid, status, options, 0);
+}
+
+static __attribute__((unused))
+pid_t sys_wait(int *status)
+{
+ return sys_waitpid(-1, status, 0);
+}
+
+static __attribute__((unused))
+ssize_t sys_write(int fd, const void *buf, size_t count)
+{
+ return my_syscall3(__NR_write, fd, buf, count);
+}
+
+
+/* Below are the libc-compatible syscalls which return x or -1 and set errno.
+ * They rely on the functions above. Similarly they're marked static so that it
+ * is possible to assign pointers to them if needed.
+ */
+
+static __attribute__((unused))
+int brk(void *addr)
+{
+ void *ret = sys_brk(addr);
+
+ if (!ret) {
+ SET_ERRNO(ENOMEM);
+ return -1;
+ }
+ return 0;
+}
+
+static __attribute__((noreturn,unused))
+void exit(int status)
+{
+ sys_exit(status);
+}
+
+static __attribute__((unused))
+int chdir(const char *path)
+{
+ int ret = sys_chdir(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int chmod(const char *path, mode_t mode)
+{
+ int ret = sys_chmod(path, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int chown(const char *path, uid_t owner, gid_t group)
+{
+ int ret = sys_chown(path, owner, group);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int chroot(const char *path)
+{
+ int ret = sys_chroot(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int close(int fd)
+{
+ int ret = sys_close(fd);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int dup2(int old, int new)
+{
+ int ret = sys_dup2(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int execve(const char *filename, char *const argv[], char *const envp[])
+{
+ int ret = sys_execve(filename, argv, envp);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t fork(void)
+{
+ pid_t ret = sys_fork();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int fsync(int fd)
+{
+ int ret = sys_fsync(fd);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ int ret = sys_getdents64(fd, dirp, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t getpgrp(void)
+{
+ pid_t ret = sys_getpgrp();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t getpid(void)
+{
+ pid_t ret = sys_getpid();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ int ret = sys_gettimeofday(tv, tz);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int ioctl(int fd, unsigned long req, void *value)
+{
+ int ret = sys_ioctl(fd, req, value);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int kill(pid_t pid, int signal)
+{
+ int ret = sys_kill(pid, signal);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int link(const char *old, const char *new)
+{
+ int ret = sys_link(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+off_t lseek(int fd, off_t offset, int whence)
+{
+ off_t ret = sys_lseek(fd, offset, whence);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int mkdir(const char *path, mode_t mode)
+{
+ int ret = sys_mkdir(path, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int mknod(const char *path, mode_t mode, dev_t dev)
+{
+ int ret = sys_mknod(path, mode, dev);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int mount(const char *src, const char *tgt,
+ const char *fst, unsigned long flags,
+ const void *data)
+{
+ int ret = sys_mount(src, tgt, fst, flags, data);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int open(const char *path, int flags, mode_t mode)
+{
+ int ret = sys_open(path, flags, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int pivot_root(const char *new, const char *old)
+{
+ int ret = sys_pivot_root(new, old);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int poll(struct pollfd *fds, int nfds, int timeout)
+{
+ int ret = sys_poll(fds, nfds, timeout);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+ssize_t read(int fd, void *buf, size_t count)
+{
+ ssize_t ret = sys_read(fd, buf, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int reboot(int cmd)
+{
+ int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+void *sbrk(intptr_t inc)
+{
+ void *ret;
+
+ /* first call to find current end */
+ if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
+ return ret + inc;
+
+ SET_ERRNO(ENOMEM);
+ return (void *)-1;
+}
+
+static __attribute__((unused))
+int sched_yield(void)
+{
+ int ret = sys_sched_yield();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+ int ret = sys_select(nfds, rfds, wfds, efds, timeout);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int setpgid(pid_t pid, pid_t pgid)
+{
+ int ret = sys_setpgid(pid, pgid);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t setsid(void)
+{
+ pid_t ret = sys_setsid();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+unsigned int sleep(unsigned int seconds)
+{
+ struct timeval my_timeval = { seconds, 0 };
+
+ if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+ return my_timeval.tv_sec + !!my_timeval.tv_usec;
+ else
+ return 0;
+}
+
+static __attribute__((unused))
+int stat(const char *path, struct stat *buf)
+{
+ int ret = sys_stat(path, buf);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int symlink(const char *old, const char *new)
+{
+ int ret = sys_symlink(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int tcsetpgrp(int fd, pid_t pid)
+{
+ return ioctl(fd, TIOCSPGRP, &pid);
+}
+
+static __attribute__((unused))
+mode_t umask(mode_t mode)
+{
+ return sys_umask(mode);
+}
+
+static __attribute__((unused))
+int umount2(const char *path, int flags)
+{
+ int ret = sys_umount2(path, flags);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int unlink(const char *path)
+{
+ int ret = sys_unlink(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+ pid_t ret = sys_wait4(pid, status, options, rusage);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t waitpid(pid_t pid, int *status, int options)
+{
+ pid_t ret = sys_waitpid(pid, status, options);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t wait(int *status)
+{
+ pid_t ret = sys_wait(status);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+ssize_t write(int fd, const void *buf, size_t count)
+{
+ ssize_t ret = sys_write(fd, buf, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+/* some size-optimized reimplementations of a few common str* and mem*
+ * functions. They're marked static, except memcpy() and raise() which are used
+ * by libgcc on ARM, so they are marked weak instead in order not to cause an
+ * error when building a program made of multiple files (not recommended).
+ */
+
+static __attribute__((unused))
+void *memmove(void *dst, const void *src, size_t len)
+{
+ ssize_t pos = (dst <= src) ? -1 : (long)len;
+ void *ret = dst;
+
+ while (len--) {
+ pos += (dst <= src) ? 1 : -1;
+ ((char *)dst)[pos] = ((char *)src)[pos];
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+void *memset(void *dst, int b, size_t len)
+{
+ char *p = dst;
+
+ while (len--)
+ *(p++) = b;
+ return dst;
+}
+
+static __attribute__((unused))
+int memcmp(const void *s1, const void *s2, size_t n)
+{
+ size_t ofs = 0;
+ char c1 = 0;
+
+ while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
+ ofs++;
+ }
+ return c1;
+}
+
+static __attribute__((unused))
+char *strcpy(char *dst, const char *src)
+{
+ char *ret = dst;
+
+ while ((*dst++ = *src++));
+ return ret;
+}
+
+static __attribute__((unused))
+char *strchr(const char *s, int c)
+{
+ while (*s) {
+ if (*s == (char)c)
+ return (char *)s;
+ s++;
+ }
+ return NULL;
+}
+
+static __attribute__((unused))
+char *strrchr(const char *s, int c)
+{
+ const char *ret = NULL;
+
+ while (*s) {
+ if (*s == (char)c)
+ ret = s;
+ s++;
+ }
+ return (char *)ret;
+}
+
+static __attribute__((unused))
+size_t nolibc_strlen(const char *str)
+{
+ size_t len;
+
+ for (len = 0; str[len]; len++);
+ return len;
+}
+
+#define strlen(str) ({ \
+ __builtin_constant_p((str)) ? \
+ __builtin_strlen((str)) : \
+ nolibc_strlen((str)); \
+})
+
+static __attribute__((unused))
+int isdigit(int c)
+{
+ return (unsigned int)(c - '0') <= 9;
+}
+
+static __attribute__((unused))
+long atol(const char *s)
+{
+ unsigned long ret = 0;
+ unsigned long d;
+ int neg = 0;
+
+ if (*s == '-') {
+ neg = 1;
+ s++;
+ }
+
+ while (1) {
+ d = (*s++) - '0';
+ if (d > 9)
+ break;
+ ret *= 10;
+ ret += d;
+ }
+
+ return neg ? -ret : ret;
+}
+
+static __attribute__((unused))
+int atoi(const char *s)
+{
+ return atol(s);
+}
+
+static __attribute__((unused))
+const char *ltoa(long in)
+{
+ /* large enough for -9223372036854775808 */
+ static char buffer[21];
+ char *pos = buffer + sizeof(buffer) - 1;
+ int neg = in < 0;
+ unsigned long n = neg ? -in : in;
+
+ *pos-- = '\0';
+ do {
+ *pos-- = '0' + n % 10;
+ n /= 10;
+ if (pos < buffer)
+ return pos + 1;
+ } while (n);
+
+ if (neg)
+ *pos-- = '-';
+ return pos + 1;
+}
+
+__attribute__((weak,unused))
+void *memcpy(void *dst, const void *src, size_t len)
+{
+ return memmove(dst, src, len);
+}
+
+/* needed by libgcc for divide by zero */
+__attribute__((weak,unused))
+int raise(int signal)
+{
+ return kill(getpid(), signal);
+}
+
+/* Here come a few helper functions */
+
+static __attribute__((unused))
+void FD_ZERO(fd_set *set)
+{
+ memset(set, 0, sizeof(*set));
+}
+
+static __attribute__((unused))
+void FD_SET(int fd, fd_set *set)
+{
+ if (fd < 0 || fd >= FD_SETSIZE)
+ return;
+ set->fd32[fd / 32] |= 1 << (fd & 31);
+}
+
+/* WARNING, it only deals with the 4096 first majors and 256 first minors */
+static __attribute__((unused))
+dev_t makedev(unsigned int major, unsigned int minor)
+{
+ return ((major & 0xfff) << 8) | (minor & 0xff);
+}
diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt
index 833f826d6ec2..933b4fd12327 100644
--- a/tools/testing/selftests/rcutorture/doc/initrd.txt
+++ b/tools/testing/selftests/rcutorture/doc/initrd.txt
@@ -1,9 +1,12 @@
-This document describes one way to create the initrd directory hierarchy
-in order to allow an initrd to be built into your kernel. The trick
-here is to steal the initrd file used on your Linux laptop, Ubuntu in
-this case. There are probably much better ways of doing this.
+The rcutorture scripting tools automatically create the needed initrd
+directory using dracut. Failing that, this tool will create an initrd
+containing a single statically linked binary named "init" that loops
+over a very long sleep() call. In both cases, this creation is done
+by tools/testing/selftests/rcutorture/bin/mkinitrd.sh.
-That said, here are the commands:
+However, if you are attempting to run rcutorture on a system that does
+not have dracut installed, and if you don't like the notion of static
+linking, you might wish to press an existing initrd into service:
------------------------------------------------------------------------
cd tools/testing/selftests/rcutorture
@@ -11,22 +14,7 @@ zcat /initrd.img > /tmp/initrd.img.zcat
mkdir initrd
cd initrd
cpio -id < /tmp/initrd.img.zcat
-------------------------------------------------------------------------
-
-Another way to create an initramfs image is using "dracut"[1], which is
-available on many distros, however the initramfs dracut generates is a cpio
-archive with another cpio archive in it, so an extra step is needed to create
-the initrd directory hierarchy.
-
-Here are the commands to create a initrd directory for rcutorture using
-dracut:
-
-------------------------------------------------------------------------
-dracut --no-hostonly --no-hostonly-cmdline --module "base bash shutdown" /tmp/initramfs.img
-cd tools/testing/selftests/rcutorture
-mkdir initrd
-cd initrd
-/usr/lib/dracut/skipcpio /tmp/initramfs.img | zcat | cpio -id < /tmp/initramfs.img
+# Manually verify that initrd contains needed binaries and libraries.
------------------------------------------------------------------------
Interestingly enough, if you are running rcutorture, you don't really
@@ -39,75 +27,12 @@ with 0755 mode.
------------------------------------------------------------------------
#!/bin/sh
-[ -d /dev ] || mkdir -m 0755 /dev
-[ -d /root ] || mkdir -m 0700 /root
-[ -d /sys ] || mkdir /sys
-[ -d /proc ] || mkdir /proc
-[ -d /tmp ] || mkdir /tmp
-mkdir -p /var/lock
-mount -t sysfs -o nodev,noexec,nosuid sysfs /sys
-mount -t proc -o nodev,noexec,nosuid proc /proc
-# Some things don't work properly without /etc/mtab.
-ln -sf /proc/mounts /etc/mtab
-
-# Note that this only becomes /dev on the real filesystem if udev's scripts
-# are used; which they will be, but it's worth pointing out
-if ! mount -t devtmpfs -o mode=0755 udev /dev; then
- echo "W: devtmpfs not available, falling back to tmpfs for /dev"
- mount -t tmpfs -o mode=0755 udev /dev
- [ -e /dev/console ] || mknod --mode=600 /dev/console c 5 1
- [ -e /dev/kmsg ] || mknod --mode=644 /dev/kmsg c 1 11
- [ -e /dev/null ] || mknod --mode=666 /dev/null c 1 3
-fi
-
-mkdir /dev/pts
-mount -t devpts -o noexec,nosuid,gid=5,mode=0620 devpts /dev/pts || true
-mount -t tmpfs -o "nosuid,size=20%,mode=0755" tmpfs /run
-mkdir /run/initramfs
-# compatibility symlink for the pre-oneiric locations
-ln -s /run/initramfs /dev/.initramfs
-
-# Export relevant variables
-export ROOT=
-export ROOTDELAY=
-export ROOTFLAGS=
-export ROOTFSTYPE=
-export IP=
-export BOOT=
-export BOOTIF=
-export UBIMTD=
-export break=
-export init=/sbin/init
-export quiet=n
-export readonly=y
-export rootmnt=/root
-export debug=
-export panic=
-export blacklist=
-export resume=
-export resume_offset=
-export recovery=
-
-for i in /sys/devices/system/cpu/cpu*/online
-do
- case $i in
- '/sys/devices/system/cpu/cpu0/online')
- ;;
- '/sys/devices/system/cpu/cpu*/online')
- ;;
- *)
- echo 1 > $i
- ;;
- esac
-done
-
while :
do
sleep 10
done
------------------------------------------------------------------------
-References:
-[1]: https://dracut.wiki.kernel.org/index.php/Main_Page
-[2]: http://blog.elastocloud.org/2015/06/rapid-linux-kernel-devtest-with-qemu.html
-[3]: https://www.centos.org/forums/viewtopic.php?t=51621
+This approach also allows most of the binaries and libraries in the
+initrd filesystem to be dispensed with, which can save significant
+space in rcutorture's "res" directory.
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
index 891ad13e95b2..d27285f8ee82 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
@@ -131,8 +131,8 @@ struct hlist_node {
* weird ABI and we need to ask it explicitly.
*
* The alignment is required to guarantee that bits 0 and 1 of @next will be
- * clear under normal conditions -- as long as we use call_rcu(),
- * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
+ * clear under normal conditions -- as long as we use call_rcu() or
+ * call_srcu() to queue callback.
*
* This guarantee is important for few reasons:
* - future call_rcu_lazy() will make use of lower bits in the pointer;
diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile
index dc92eb271d9a..be5a5e542804 100644
--- a/tools/testing/selftests/tc-testing/bpf/Makefile
+++ b/tools/testing/selftests/tc-testing/bpf/Makefile
@@ -4,6 +4,7 @@ APIDIR := ../../../../include/uapi
TEST_GEN_FILES = action.o
top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
include ../../lib.mk
CLANG ?= clang
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 6e67e726e5a5..e13eb6cc8901 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -25,6 +25,7 @@ TEST_GEN_FILES += virtual_address_range
TEST_PROGS := run_vmtests
+KSFT_KHDR_INSTALL := 1
include ../lib.mk
$(OUTPUT)/userfaultfd: LDLIBS += -lpthread