The way we exit from a guest to userspace is very specific to the architecture: On x86, we use PIO, on aarch64 we are using MMIO and on s390x we're going to use an instruction instead. The possibility to select a type via the ucall_type_t enum is currently also completely unused, so the code in ucall.c currently looks more complex than required. Let's split this up into architecture specific ucall.c files instead, so we can get rid of the #ifdefs and the unnecessary ucall_type_t handling.

Reviewed-by: Andrew Jones drjones@redhat.com Signed-off-by: Thomas Huth thuth@redhat.com --- tools/testing/selftests/kvm/Makefile | 6 +- tools/testing/selftests/kvm/dirty_log_test.c | 2 +- .../testing/selftests/kvm/include/kvm_util.h | 8 +- .../testing/selftests/kvm/lib/aarch64/ucall.c | 112 +++++++++++++ tools/testing/selftests/kvm/lib/ucall.c | 157 ------------------ .../testing/selftests/kvm/lib/x86_64/ucall.c | 56 +++++++ 6 files changed, 173 insertions(+), 168 deletions(-) create mode 100644 tools/testing/selftests/kvm/lib/aarch64/ucall.c delete mode 100644 tools/testing/selftests/kvm/lib/ucall.c create mode 100644 tools/testing/selftests/kvm/lib/x86_64/ucall.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index ba7849751989..a51e3b83df40 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -7,9 +7,9 @@ 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 -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c -LIBKVM_aarch64 = lib/aarch64/processor.c +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.c +LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c

TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index ceb52b952637..5d5ae1be4984 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -337,7 +337,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); #endif #ifdef __aarch64__ - ucall_init(vm, UCALL_MMIO, NULL); + ucall_init(vm, NULL); #endif

/* Export the shared variables to the guest */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index e0e66b115ef2..5463b7896a0a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -165,12 +165,6 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ })

-/* ucall implementation types */ -typedef enum { - UCALL_PIO, - UCALL_MMIO, -} ucall_type_t; - /* Common ucalls */ enum { UCALL_NONE, @@ -186,7 +180,7 @@ struct ucall { uint64_t args[UCALL_MAX_ARGS]; };

-void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg); +void ucall_init(struct kvm_vm *vm, void *arg); void ucall_uninit(struct kvm_vm *vm); void ucall(uint64_t cmd, int nargs, ...); uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c new file mode 100644 index 000000000000..6cd91970fbad --- /dev/null +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2018, Red Hat, Inc. + */ +#include "kvm_util.h" +#include "../kvm_util_internal.h" + +static vm_vaddr_t *ucall_exit_mmio_addr; + +static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa) +{ + if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1)) + return false; + + virt_pg_map(vm, gpa, gpa, 0); + + ucall_exit_mmio_addr = (vm_vaddr_t *)gpa; + sync_global_to_guest(vm, ucall_exit_mmio_addr); + + return true; +} + +void ucall_init(struct kvm_vm *vm, void *arg) +{ + vm_paddr_t gpa, start, end, step, offset; + unsigned int bits; + bool ret; + + if (arg) { + gpa = (vm_paddr_t)arg; + ret = ucall_mmio_init(vm, gpa); + TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa); + return; + } + + /* + * 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 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. + */ + 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; + if (ucall_mmio_init(vm, start + offset)) + return; + } + TEST_ASSERT(false, "Can't find a ucall mmio address"); +} + +void ucall_uninit(struct kvm_vm *vm) +{ + ucall_exit_mmio_addr = 0; + sync_global_to_guest(vm, ucall_exit_mmio_addr); +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + uc.args[i] = va_arg(va, uint64_t); + va_end(va); + + *ucall_exit_mmio_addr = (vm_vaddr_t)&uc; +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct ucall ucall = {}; + + if (run->exit_reason == KVM_EXIT_MMIO && + run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { + vm_vaddr_t gva; + + TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, + "Unexpected ucall exit mmio address access"); + memcpy(&gva, run->mmio.data, sizeof(gva)); + memcpy(&ucall, addr_gva2hva(vm, gva), sizeof(ucall)); + + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); + } + + return ucall.cmd; +} diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c deleted file mode 100644 index dd9a66700f96..000000000000 --- a/tools/testing/selftests/kvm/lib/ucall.c +++ /dev/null @@ -1,157 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * ucall support. A ucall is a "hypercall to userspace". - * - * Copyright (C) 2018, Red Hat, Inc. - */ -#include "kvm_util.h" -#include "kvm_util_internal.h" - -#define UCALL_PIO_PORT ((uint16_t)0x1000) - -static ucall_type_t ucall_type; -static vm_vaddr_t *ucall_exit_mmio_addr; - -static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa) -{ - if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1)) - return false; - - virt_pg_map(vm, gpa, gpa, 0); - - ucall_exit_mmio_addr = (vm_vaddr_t *)gpa; - sync_global_to_guest(vm, ucall_exit_mmio_addr); - - return true; -} - -void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg) -{ - ucall_type = type; - sync_global_to_guest(vm, ucall_type); - - if (type == UCALL_PIO) - return; - - if (type == UCALL_MMIO) { - vm_paddr_t gpa, start, end, step, offset; - unsigned bits; - bool ret; - - if (arg) { - gpa = (vm_paddr_t)arg; - ret = ucall_mmio_init(vm, gpa); - TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa); - return; - } - - /* - * 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 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. - */ - 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; - if (ucall_mmio_init(vm, start + offset)) - return; - } - TEST_ASSERT(false, "Can't find a ucall mmio address"); - } -} - -void ucall_uninit(struct kvm_vm *vm) -{ - ucall_type = 0; - sync_global_to_guest(vm, ucall_type); - ucall_exit_mmio_addr = 0; - sync_global_to_guest(vm, ucall_exit_mmio_addr); -} - -static void ucall_pio_exit(struct ucall *uc) -{ -#ifdef __x86_64__ - asm volatile("in %[port], %%al" - : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax"); -#endif -} - -static void ucall_mmio_exit(struct ucall *uc) -{ - *ucall_exit_mmio_addr = (vm_vaddr_t)uc; -} - -void ucall(uint64_t cmd, int nargs, ...) -{ - struct ucall uc = { - .cmd = cmd, - }; - va_list va; - int i; - - nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); - va_end(va); - - switch (ucall_type) { - case UCALL_PIO: - ucall_pio_exit(&uc); - break; - case UCALL_MMIO: - ucall_mmio_exit(&uc); - break; - }; -} - -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) -{ - struct kvm_run *run = vcpu_state(vm, vcpu_id); - struct ucall ucall = {}; - bool got_ucall = false; - -#ifdef __x86_64__ - if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO && - run->io.port == UCALL_PIO_PORT) { - struct kvm_regs regs; - vcpu_regs_get(vm, vcpu_id, &regs); - memcpy(&ucall, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(ucall)); - got_ucall = true; - } -#endif - if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO && - run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { - vm_vaddr_t gva; - TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, - "Unexpected ucall exit mmio address access"); - memcpy(&gva, run->mmio.data, sizeof(gva)); - memcpy(&ucall, addr_gva2hva(vm, gva), sizeof(ucall)); - got_ucall = true; - } - - if (got_ucall) { - vcpu_run_complete_io(vm, vcpu_id); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); - } - - return ucall.cmd; -} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c new file mode 100644 index 000000000000..4bfc9a90b1de --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2018, Red Hat, Inc. + */ +#include "kvm_util.h" + +#define UCALL_PIO_PORT ((uint16_t)0x1000) + +void ucall_init(struct kvm_vm *vm, void *arg) +{ +} + +void ucall_uninit(struct kvm_vm *vm) +{ +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + uc.args[i] = va_arg(va, uint64_t); + va_end(va); + + asm volatile("in %[port], %%al" + : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax"); +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct ucall ucall = {}; + + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { + struct kvm_regs regs; + + vcpu_regs_get(vm, vcpu_id, &regs); + memcpy(&ucall, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), + sizeof(ucall)); + + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); + } + + return ucall.cmd; +}

To run the dirty_log_test on s390x, we have to make sure that we access the dirty log bitmap with little endian byte ordering and we have to properly align the memslot of the guest. Also all dirty bits of a segment are set once on s390x when one of the pages of a segment are written to for the first time, so we have to make sure that we touch all pages during the first iteration to keep the test in sync here. DEFAULT_GUEST_TEST_MEM needs an adjustment, too. On some s390x distributions, the ELF binary is linked to address 0x80000000, so we have to avoid that our test region overlaps into this area. 0xc0000000 seems to be a good alternative that should work on x86 and aarch64, too.

Acked-by: Paolo Bonzini pbonzini@redhat.com Reviewed-by: Andrew Jones drjones@redhat.com Signed-off-by: Thomas Huth thuth@redhat.com --- tools/testing/selftests/kvm/Makefile | 1 + tools/testing/selftests/kvm/dirty_log_test.c | 59 +++++++++++++++++--- 2 files changed, 53 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 75ea1ecbf85a..1b48a94b4350 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,6 +33,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus

TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus

TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 5d5ae1be4984..dc3346e090f5 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -26,8 +26,8 @@ /* The memory slot index to track dirty pages */ #define TEST_MEM_SLOT_INDEX 1

-/* Default guest test memory offset, 1G */ -#define DEFAULT_GUEST_TEST_MEM 0x40000000 +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000

/* How many pages to dirty for each guest loop */ #define TEST_PAGES_PER_LOOP 1024 @@ -38,6 +38,27 @@ /* Interval for each host loop (ms) */ #define TEST_HOST_LOOP_INTERVAL 10UL

+/* Dirty bitmaps are always little endian, so we need to swap on big endian */ +#if defined(__s390x__) +# define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) +# define test_bit_le(nr, addr) \ + test_bit((nr) ^ BITOP_LE_SWIZZLE, addr) +# define set_bit_le(nr, addr) \ + set_bit((nr) ^ BITOP_LE_SWIZZLE, addr) +# define clear_bit_le(nr, addr) \ + clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr) +# define test_and_set_bit_le(nr, addr) \ + test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, addr) +# define test_and_clear_bit_le(nr, addr) \ + test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr) +#else +# define test_bit_le test_bit +# define set_bit_le set_bit +# define clear_bit_le clear_bit +# define test_and_set_bit_le test_and_set_bit +# define test_and_clear_bit_le test_and_clear_bit +#endif + /* * Guest/Host shared variables. Ensure addr_gva2hva() and/or * sync_global_to/from_guest() are used when accessing from @@ -69,11 +90,23 @@ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; */ static void guest_code(void) { + uint64_t addr; int i;

+ /* + * On s390x, all pages of a 1M segment are initially marked as dirty + * when a page of the segment is written to for the very first time. + * To compensate this specialty in this test, we need to touch all + * pages during the first iteration. + */ + for (i = 0; i < guest_num_pages; i++) { + addr = guest_test_virt_mem + i * guest_page_size; + *(uint64_t *)addr = READ_ONCE(iteration); + } + while (true) { for (i = 0; i < TEST_PAGES_PER_LOOP; i++) { - uint64_t addr = guest_test_virt_mem; + addr = guest_test_virt_mem; addr += (READ_ONCE(random_array[i]) % guest_num_pages) * guest_page_size; addr &= ~(host_page_size - 1); @@ -158,15 +191,15 @@ static void vm_dirty_log_verify(unsigned long *bmap) value_ptr = host_test_mem + page * host_page_size;

/* If this is a special page that we were tracking... */ - if (test_and_clear_bit(page, host_bmap_track)) { + if (test_and_clear_bit_le(page, host_bmap_track)) { host_track_next_count++; - TEST_ASSERT(test_bit(page, bmap), + TEST_ASSERT(test_bit_le(page, bmap), "Page %"PRIu64" should have its dirty bit " "set in this iteration but it is missing", page); }

- if (test_bit(page, bmap)) { + if (test_bit_le(page, bmap)) { host_dirty_count++; /* * If the bit is set, the value written onto @@ -209,7 +242,7 @@ static void vm_dirty_log_verify(unsigned long *bmap) * should report its dirtyness in the * next run */ - set_bit(page, host_bmap_track); + set_bit_le(page, host_bmap_track); } } } @@ -293,6 +326,10 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, * case where the size is not aligned to 64 pages. */ guest_num_pages = (1ul << (30 - guest_page_shift)) + 16; +#ifdef __s390x__ + /* Round up to multiple of 1M (segment size) */ + guest_num_pages = (guest_num_pages + 0xff) & ~0xffUL; +#endif host_page_size = getpagesize(); host_num_pages = (guest_num_pages * guest_page_size) / host_page_size + !!((guest_num_pages * guest_page_size) % host_page_size); @@ -304,6 +341,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, guest_test_phys_mem = phys_offset; }

+#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);

bmap = bitmap_alloc(host_num_pages); @@ -454,6 +496,9 @@ int main(int argc, char *argv[]) vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true); } #endif +#ifdef __s390x__ + vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true); +#endif

while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { switch (opt) {