The following changes since commit 035eed4c0d257c905a556fa0f4865a0c077b4e7f: Merge remote-tracking branch 'remotes/vivier/tags/q800-for-5.0-pull-request' into staging (2020-01-07 17:08:21 +0000) are available in the Git repository at: https://github.com/rth7680/qemu.git tags/pull-tcg-20200108 for you to fetch changes up to 5e7ef51cbe47e726f76bfbc208e167085cf398c4: MAINTAINERS: Replace Claudio Fontana for tcg/aarch64 (2020-01-08 11:54:12 +1100) ---------------------------------------------------------------- Improve -static and -pie linking Add cpu_{ld,st}*_mmuidx_ra Remove MMU_MODE*_SUFFIX Move tcg headers under include/ ---------------------------------------------------------------- Philippe Mathieu-Daudé (4): tcg: Search includes from the project root source directory tcg: Search includes in the parent source directory tcg: Move TCG headers to include/tcg/ configure: Remove tcg/ from the preprocessor include search list Richard Henderson (37): configure: Drop adjustment of textseg tcg: Remove softmmu code_gen_buffer fixed address configure: Do not force pie=no for non-x86 configure: Always detect -no-pie toolchain support configure: Unnest detection of -z,relro and -z,now configure: Override the os default with --disable-pie configure: Support -static-pie if requested target/xtensa: Use probe_access for itlb_hit_test cputlb: Use trace_mem_get_info instead of trace_mem_build_info trace: Remove trace_mem_build_info_no_se_[bl]e target/s390x: Include tcg.h in mem_helper.c target/arm: Include tcg.h in sve_helper.c accel/tcg: Include tcg.h in tcg-runtime.c linux-user: Include tcg.h in syscall.c linux-user: Include trace-root.h in syscall-trace.h plugins: Include trace/mem.h in api.c cputlb: Move body of cpu_ldst_template.h out of line translator: Use cpu_ld*_code instead of open-coding cputlb: Rename helper_ret_ld*_cmmu to cpu_ld*_code cputlb: Provide cpu_(ld,st}*_mmuidx_ra for user-only target/i386: Use cpu_*_mmuidx_ra instead of templates cputlb: Expand cpu_ldst_useronly_template.h in user-exec.c target/nios2: Remove MMU_MODE{0,1}_SUFFIX target/alpha: Remove MMU_MODE{0,1}_SUFFIX target/cris: Remove MMU_MODE{0,1}_SUFFIX target/i386: Remove MMU_MODE{0,1,2}_SUFFIX target/microblaze: Remove MMU_MODE{0,1,2}_SUFFIX target/sh4: Remove MMU_MODE{0,1}_SUFFIX target/unicore32: Remove MMU_MODE{0,1}_SUFFIX target/xtensa: Remove MMU_MODE{0,1,2,3}_SUFFIX target/m68k: Use cpu_*_mmuidx_ra instead of MMU_MODE{0,1}_SUFFIX target/mips: Use cpu_*_mmuidx_ra instead of MMU_MODE*_SUFFIX target/s390x: Use cpu_*_mmuidx_ra instead of MMU_MODE*_SUFFIX target/ppc: Use cpu_*_mmuidx_ra instead of MMU_MODE*_SUFFIX cputlb: Remove support for MMU_MODE*_SUFFIX cputlb: Expand cpu_ldst_template.h in cputlb.c MAINTAINERS: Replace Claudio Fontana for tcg/aarch64 Makefile | 2 +- accel/tcg/atomic_template.h | 67 ++--- include/exec/cpu_ldst.h | 446 +++++++++--------------------- include/exec/cpu_ldst_template.h | 211 -------------- include/exec/cpu_ldst_useronly_template.h | 159 ----------- include/exec/translator.h | 48 +--- {tcg => include/tcg}/tcg-gvec-desc.h | 0 {tcg => include/tcg}/tcg-mo.h | 0 {tcg => include/tcg}/tcg-op-gvec.h | 0 {tcg => include/tcg}/tcg-op.h | 2 +- {tcg => include/tcg}/tcg-opc.h | 0 {tcg => include/tcg}/tcg.h | 33 +-- include/user/syscall-trace.h | 2 + target/alpha/cpu.h | 2 - target/cris/cpu.h | 2 - target/i386/cpu.h | 3 - target/m68k/cpu.h | 2 - target/microblaze/cpu.h | 3 - target/mips/cpu.h | 4 - target/nios2/cpu.h | 2 - target/ppc/cpu.h | 2 - target/s390x/cpu.h | 5 - target/sh4/cpu.h | 2 - target/unicore32/cpu.h | 2 - target/xtensa/cpu.h | 4 - tcg/i386/tcg-target.h | 2 +- trace/mem-internal.h | 17 -- accel/tcg/cpu-exec.c | 2 +- accel/tcg/cputlb.c | 315 ++++++++++++++++----- accel/tcg/tcg-runtime-gvec.c | 2 +- accel/tcg/tcg-runtime.c | 1 + accel/tcg/translate-all.c | 39 +-- accel/tcg/user-exec.c | 238 +++++++++++++++- bsd-user/main.c | 2 +- cpus.c | 2 +- exec.c | 2 +- linux-user/main.c | 2 +- linux-user/syscall.c | 1 + plugins/api.c | 1 + target/alpha/translate.c | 2 +- target/arm/helper-a64.c | 2 +- target/arm/sve_helper.c | 1 + target/arm/translate-a64.c | 4 +- target/arm/translate-sve.c | 6 +- target/arm/translate.c | 4 +- target/cris/translate.c | 2 +- target/hppa/translate.c | 2 +- target/i386/mem_helper.c | 2 +- target/i386/seg_helper.c | 56 ++-- target/i386/translate.c | 2 +- target/lm32/translate.c | 2 +- target/m68k/op_helper.c | 77 ++++-- target/m68k/translate.c | 2 +- target/microblaze/translate.c | 2 +- target/mips/op_helper.c | 182 ++++-------- target/mips/translate.c | 2 +- target/moxie/translate.c | 2 +- target/nios2/translate.c | 2 +- target/openrisc/translate.c | 2 +- target/ppc/mem_helper.c | 13 +- target/ppc/translate.c | 4 +- target/riscv/cpu_helper.c | 2 +- target/riscv/translate.c | 2 +- target/s390x/mem_helper.c | 11 +- target/s390x/translate.c | 4 +- target/sh4/translate.c | 2 +- target/sparc/ldst_helper.c | 2 +- target/sparc/translate.c | 2 +- target/tilegx/translate.c | 2 +- target/tricore/translate.c | 2 +- target/unicore32/translate.c | 2 +- target/xtensa/mmu_helper.c | 5 +- target/xtensa/translate.c | 2 +- tcg/aarch64/tcg-target.inc.c | 4 +- tcg/arm/tcg-target.inc.c | 4 +- tcg/i386/tcg-target.inc.c | 4 +- tcg/mips/tcg-target.inc.c | 2 +- tcg/optimize.c | 2 +- tcg/ppc/tcg-target.inc.c | 4 +- tcg/riscv/tcg-target.inc.c | 4 +- tcg/s390/tcg-target.inc.c | 4 +- tcg/sparc/tcg-target.inc.c | 2 +- tcg/tcg-common.c | 2 +- tcg/tcg-op-gvec.c | 8 +- tcg/tcg-op-vec.c | 6 +- tcg/tcg-op.c | 6 +- tcg/tcg.c | 2 +- tcg/tci.c | 2 +- MAINTAINERS | 4 +- configure | 117 +++----- docs/devel/loads-stores.rst | 215 ++++++++++---- 91 files changed, 1075 insertions(+), 1357 deletions(-) delete mode 100644 include/exec/cpu_ldst_template.h delete mode 100644 include/exec/cpu_ldst_useronly_template.h rename {tcg => include/tcg}/tcg-gvec-desc.h (100%) rename {tcg => include/tcg}/tcg-mo.h (100%) rename {tcg => include/tcg}/tcg-op-gvec.h (100%) rename {tcg => include/tcg}/tcg-op.h (99%) rename {tcg => include/tcg}/tcg-opc.h (100%) rename {tcg => include/tcg}/tcg.h (96%) This adjustment was random and unnecessary. The user mode startup code in probe_guest_base() will choose a value for guest_base that allows the host qemu binary to not conflict with the guest binary. With modern distributions, this isn't even used, as the default is PIE, which does the same job in a more portable way. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Remove mention of config-host.ld from make distclean --- Makefile | 2 +- configure | 47 ----------------------------------------------- 2 files changed, 1 insertion(+), 48 deletions(-) diff --git a/Makefile b/Makefile index XXXXXXX..XXXXXXX 100644 --- a/Makefile +++ b/Makefile @@ -XXX,XX +XXX,XX @@ rm -f $(MANUAL_BUILDDIR)/$1/objects.inv $(MANUAL_BUILDDIR)/$1/searchindex.js $(M endef distclean: clean - rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi qemu-monitor-info.texi + rm -f config-host.mak config-host.h* $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi qemu-monitor-info.texi rm -f tests/tcg/config-*.mak rm -f config-all-devices.mak config-all-disas.mak config.status rm -f $(SUBDIR_DEVICES_MAK) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if test "$cpu" = "s390x" ; then fi fi -# Probe for the need for relocating the user-only binary. -if ( [ "$linux_user" = yes ] || [ "$bsd_user" = yes ] ) && [ "$pie" = no ]; then - textseg_addr= - case "$cpu" in - arm | i386 | ppc* | s390* | sparc* | x86_64 | x32) - # ??? Rationale for choosing this address - textseg_addr=0x60000000 - ;; - mips) - # A 256M aligned address, high in the address space, with enough - # room for the code_gen_buffer above it before the stack. - textseg_addr=0x60000000 - ;; - esac - if [ -n "$textseg_addr" ]; then - cat > $TMPC <<EOF - int main(void) { return 0; } -EOF - textseg_ldflags="-Wl,-Ttext-segment=$textseg_addr" - if ! compile_prog "" "$textseg_ldflags"; then - # In case ld does not support -Ttext-segment, edit the default linker - # script via sed to set the .text start addr. This is needed on FreeBSD - # at least. - if ! $ld --verbose >/dev/null 2>&1; then - error_exit \ - "We need to link the QEMU user mode binaries at a" \ - "specific text address. Unfortunately your linker" \ - "doesn't support either the -Ttext-segment option or" \ - "printing the default linker script with --verbose." \ - "If you don't want the user mode binaries, pass the" \ - "--disable-user option to configure." - fi - - $ld --verbose | sed \ - -e '1,/==================================================/d' \ - -e '/==================================================/,$d' \ - -e "s/[.] = [0-9a-fx]* [+] SIZEOF_HEADERS/. = $textseg_addr + SIZEOF_HEADERS/" \ - -e "s/__executable_start = [0-9a-fx]*/__executable_start = $textseg_addr/" > config-host.ld - textseg_ldflags="-Wl,-T../config-host.ld" - fi - fi -fi - # Check that the C++ compiler exists and works with the C compiler. # All the QEMU_CXXFLAGS are based on QEMU_CFLAGS. Keep this at the end to don't miss any other that could be added. if has $cxx; then @@ -XXX,XX +XXX,XX @@ if test "$gprof" = "yes" ; then fi fi -if test "$target_linux_user" = "yes" || test "$target_bsd_user" = "yes" ; then - ldflags="$ldflags $textseg_ldflags" -fi - # Newer kernels on s390 check for an S390_PGSTE program header and # enable the pgste page table extensions in that case. This makes # the vm.allocate_pgste sysctl unnecessary. We enable this program -- 2.20.1 The commentary talks about "in concert with the addresses assigned in the relevant linker script", except there is no linker script for softmmu, nor has there been for some time. (Do not confuse the user-only linker script editing that was removed in the previous patch, because user-only does not use this code_gen_buffer allocation method.) Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/translate-all.c | 37 +++++-------------------------------- 1 file changed, 5 insertions(+), 32 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static inline void *alloc_code_gen_buffer(void) { int prot = PROT_WRITE | PROT_READ | PROT_EXEC; int flags = MAP_PRIVATE | MAP_ANONYMOUS; - uintptr_t start = 0; size_t size = tcg_ctx->code_gen_buffer_size; void *buf; - /* Constrain the position of the buffer based on the host cpu. - Note that these addresses are chosen in concert with the - addresses assigned in the relevant linker script file. */ -# if defined(__PIE__) || defined(__PIC__) - /* Don't bother setting a preferred location if we're building - a position-independent executable. We're more likely to get - an address near the main executable if we let the kernel - choose the address. */ -# elif defined(__x86_64__) && defined(MAP_32BIT) - /* Force the memory down into low memory with the executable. - Leave the choice of exact location with the kernel. */ - flags |= MAP_32BIT; - /* Cannot expect to map more than 800MB in low memory. */ - if (size > 800u * 1024 * 1024) { - tcg_ctx->code_gen_buffer_size = size = 800u * 1024 * 1024; - } -# elif defined(__sparc__) - start = 0x40000000ul; -# elif defined(__s390x__) - start = 0x90000000ul; -# elif defined(__mips__) -# if _MIPS_SIM == _ABI64 - start = 0x128000000ul; -# else - start = 0x08000000ul; -# endif -# endif - - buf = mmap((void *)start, size, prot, flags, -1, 0); + buf = mmap(NULL, size, prot, flags, -1, 0); if (buf == MAP_FAILED) { return NULL; } #ifdef __mips__ if (cross_256mb(buf, size)) { - /* Try again, with the original still mapped, to avoid re-acquiring - that 256mb crossing. This time don't specify an address. */ + /* + * Try again, with the original still mapped, to avoid re-acquiring + * the same 256mb crossing. + */ size_t size2; void *buf2 = mmap(NULL, size, prot, flags, -1, 0); switch ((int)(buf2 != MAP_FAILED)) { -- 2.20.1 PIE is supported on many other hosts besides x86. The default for non-x86 is now the same as x86: pie is used if supported, and may be forced via --enable/--disable-pie. The original commit (40d6444e91c) said: "Non-x86 are not changed, as they require TCG changes" but I think that's wrong -- there's nothing about PIE that affects TCG one way or another. Tested on aarch64 (bionic) and ppc64le (centos 7) hosts. Tested-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configure | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if ! compile_prog "-Werror" "" ; then "Thread-Local Storage (TLS). Please upgrade to a version that does." fi -if test "$pie" = ""; then - case "$cpu-$targetos" in - i386-Linux|x86_64-Linux|x32-Linux|i386-OpenBSD|x86_64-OpenBSD) - ;; - *) - pie="no" - ;; - esac -fi - if test "$pie" != "no" ; then cat > $TMPC << EOF -- 2.20.1 The CFLAGS_NOPIE and LDFLAGS_NOPIE variables are used in pc-bios/optionrom/Makefile, which has nothing to do with the PIE setting of the main qemu executables. This overrides any operating system default to build all executables as PIE, which is important for ROMs. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configure | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if ! compile_prog "-Werror" "" ; then "Thread-Local Storage (TLS). Please upgrade to a version that does." fi -if test "$pie" != "no" ; then - cat > $TMPC << EOF +cat > $TMPC << EOF #ifdef __linux__ # define THREAD __thread #else # define THREAD #endif - static THREAD int tls_var; - int main(void) { return tls_var; } - EOF - # check we support --no-pie first... - if compile_prog "-Werror -fno-pie" "-no-pie"; then - CFLAGS_NOPIE="-fno-pie" - LDFLAGS_NOPIE="-nopie" - fi +# Check we support --no-pie first; we will need this for building ROMs. +if compile_prog "-Werror -fno-pie" "-no-pie"; then + CFLAGS_NOPIE="-fno-pie" + LDFLAGS_NOPIE="-no-pie" +fi + +if test "$pie" != "no" ; then if compile_prog "-fPIE -DPIE" "-pie"; then QEMU_CFLAGS="-fPIE -DPIE $QEMU_CFLAGS" LDFLAGS="-pie $LDFLAGS" -- 2.20.1 There is nothing about these options that is related to PIE. Use them unconditionally. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Fangrui Song <i@maskray.me> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Do not split into two tests. --- configure | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if test "$pie" != "no" ; then QEMU_CFLAGS="-fPIE -DPIE $QEMU_CFLAGS" LDFLAGS="-pie $LDFLAGS" pie="yes" - if compile_prog "" "-Wl,-z,relro -Wl,-z,now" ; then - LDFLAGS="-Wl,-z,relro -Wl,-z,now $LDFLAGS" - fi else if test "$pie" = "yes"; then error_exit "PIE not available due to missing toolchain support" @@ -XXX,XX +XXX,XX @@ if test "$pie" != "no" ; then fi fi +# Detect support for PT_GNU_RELRO + DT_BIND_NOW. +# The combination is known as "full relro", because .got.plt is read-only too. +if compile_prog "" "-Wl,-z,relro -Wl,-z,now" ; then + LDFLAGS="-Wl,-z,relro -Wl,-z,now $LDFLAGS" +fi + ########################################## # __sync_fetch_and_and requires at least -march=i486. Many toolchains # use i686 as default anyway, but for those that don't, an explicit -- 2.20.1 Some distributions, e.g. Ubuntu 19.10, enable PIE by default. If for some reason one wishes to build a non-pie binary, we must provide additional options to override. At the same time, reorg the code to an elif chain. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configure | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if compile_prog "-Werror -fno-pie" "-no-pie"; then LDFLAGS_NOPIE="-no-pie" fi -if test "$pie" != "no" ; then - if compile_prog "-fPIE -DPIE" "-pie"; then - QEMU_CFLAGS="-fPIE -DPIE $QEMU_CFLAGS" - LDFLAGS="-pie $LDFLAGS" - pie="yes" - else - if test "$pie" = "yes"; then - error_exit "PIE not available due to missing toolchain support" - else - echo "Disabling PIE due to missing toolchain support" - pie="no" - fi - fi +if test "$pie" = "no"; then + QEMU_CFLAGS="$CFLAGS_NOPIE $QEMU_CFLAGS" + LDFLAGS="$LDFLAGS_NOPIE $LDFLAGS" +elif compile_prog "-fPIE -DPIE" "-pie"; then + QEMU_CFLAGS="-fPIE -DPIE $QEMU_CFLAGS" + LDFLAGS="-pie $LDFLAGS" + pie="yes" +elif test "$pie" = "yes"; then + error_exit "PIE not available due to missing toolchain support" +else + echo "Disabling PIE due to missing toolchain support" + pie="no" fi # Detect support for PT_GNU_RELRO + DT_BIND_NOW. -- 2.20.1 Recent toolchains support static and pie at the same time. As with normal dynamic builds, allow --static to default to PIE if supported by the toolchain. Allow --enable/--disable-pie to override the default. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Fix --disable-pie --static --- configure | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ for opt do ;; --static) static="yes" - LDFLAGS="-static $LDFLAGS" QEMU_PKG_CONFIG_FLAGS="--static $QEMU_PKG_CONFIG_FLAGS" ;; --mandir=*) mandir="$optarg" @@ -XXX,XX +XXX,XX @@ if test "$static" = "yes" ; then if test "$modules" = "yes" ; then error_exit "static and modules are mutually incompatible" fi - if test "$pie" = "yes" ; then - error_exit "static and pie are mutually incompatible" - else - pie="no" - fi fi # Unconditional check for compiler __thread support @@ -XXX,XX +XXX,XX @@ if compile_prog "-Werror -fno-pie" "-no-pie"; then LDFLAGS_NOPIE="-no-pie" fi -if test "$pie" = "no"; then +if test "$static" = "yes"; then + if test "$pie" != "no" && compile_prog "-fPIE -DPIE" "-static-pie"; then + QEMU_CFLAGS="-fPIE -DPIE $QEMU_CFLAGS" + LDFLAGS="-static-pie $LDFLAGS" + pie="yes" + elif test "$pie" = "yes"; then + error_exit "-static-pie not available due to missing toolchain support" + else + LDFLAGS="-static $LDFLAGS" + pie="no" + fi +elif test "$pie" = "no"; then QEMU_CFLAGS="$CFLAGS_NOPIE $QEMU_CFLAGS" LDFLAGS="$LDFLAGS_NOPIE $LDFLAGS" elif compile_prog "-fPIE -DPIE" "-pie"; then -- 2.20.1 We don't actually need the result of the read, only to probe that the memory mapping exists. This is exactly what probe_access does. This is also the only user of any cpu_ld*_code_ra function. Removing this allows the interface to be removed shortly. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Max Filippov <jcmvbkbc@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/xtensa/mmu_helper.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/target/xtensa/mmu_helper.c b/target/xtensa/mmu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/mmu_helper.c +++ b/target/xtensa/mmu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(itlb_hit_test)(CPUXtensaState *env, uint32_t vaddr) { /* - * Attempt the memory load; we don't care about the result but + * Probe the memory; we don't care about the result but * only the side-effects (ie any MMU or other exception) */ - cpu_ldub_code_ra(env, vaddr, GETPC()); + probe_access(env, vaddr, 1, MMU_INST_FETCH, + cpu_mmu_index(env, true), GETPC()); } void HELPER(wsr_rasid)(CPUXtensaState *env, uint32_t v) -- 2.20.1 In the cpu_ldst templates, we already require a MemOp, and it is cleaner and clearer to pass that instead of 3 separate arguments describing the memory operation. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst_template.h | 22 +++++++++++----------- include/exec/cpu_ldst_useronly_template.h | 12 ++++++------ 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst_template.h +++ b/include/exec/cpu_ldst_template.h @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, RES_TYPE res; target_ulong addr; int mmu_idx = CPU_MMU_INDEX; - TCGMemOpIdx oi; + MemOp op = MO_TE | SHIFT; #if !defined(SOFTMMU_CODE_ACCESS) - uint16_t meminfo = trace_mem_build_info(SHIFT, false, MO_TE, false, mmu_idx); + uint16_t meminfo = trace_mem_get_info(op, mmu_idx, false); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); #endif @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, entry = tlb_entry(env, mmu_idx, addr); if (unlikely(entry->ADDR_READ != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - oi = make_memop_idx(SHIFT, mmu_idx); + TCGMemOpIdx oi = make_memop_idx(op, mmu_idx); res = glue(glue(helper_ret_ld, URETSUFFIX), MMUSUFFIX)(env, addr, - oi, retaddr); + oi, retaddr); } else { uintptr_t hostaddr = addr + entry->addend; res = glue(glue(ld, USUFFIX), _p)((uint8_t *)hostaddr); @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, int res; target_ulong addr; int mmu_idx = CPU_MMU_INDEX; - TCGMemOpIdx oi; -#if !defined(SOFTMMU_CODE_ACCESS) - uint16_t meminfo = trace_mem_build_info(SHIFT, true, MO_TE, false, mmu_idx); + MemOp op = MO_TE | MO_SIGN | SHIFT; +#ifndef SOFTMMU_CODE_ACCESS + uint16_t meminfo = trace_mem_get_info(op, mmu_idx, false); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); #endif @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, entry = tlb_entry(env, mmu_idx, addr); if (unlikely(entry->ADDR_READ != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - oi = make_memop_idx(SHIFT, mmu_idx); + TCGMemOpIdx oi = make_memop_idx(op & ~MO_SIGN, mmu_idx); res = (DATA_STYPE)glue(glue(helper_ret_ld, SRETSUFFIX), MMUSUFFIX)(env, addr, oi, retaddr); } else { @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, CPUTLBEntry *entry; target_ulong addr; int mmu_idx = CPU_MMU_INDEX; - TCGMemOpIdx oi; + MemOp op = MO_TE | SHIFT; #if !defined(SOFTMMU_CODE_ACCESS) - uint16_t meminfo = trace_mem_build_info(SHIFT, false, MO_TE, true, mmu_idx); + uint16_t meminfo = trace_mem_get_info(op, mmu_idx, true); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); #endif @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, entry = tlb_entry(env, mmu_idx, addr); if (unlikely(tlb_addr_write(entry) != (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - oi = make_memop_idx(SHIFT, mmu_idx); + TCGMemOpIdx oi = make_memop_idx(op, mmu_idx); glue(glue(helper_ret_st, SUFFIX), MMUSUFFIX)(env, addr, v, oi, retaddr); } else { diff --git a/include/exec/cpu_ldst_useronly_template.h b/include/exec/cpu_ldst_useronly_template.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst_useronly_template.h +++ b/include/exec/cpu_ldst_useronly_template.h @@ -XXX,XX +XXX,XX @@ glue(glue(cpu_ld, USUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr) ret = glue(glue(ld, USUFFIX), _p)(g2h(ptr)); clear_helper_retaddr(); #else - uint16_t meminfo = trace_mem_build_info(SHIFT, false, MO_TE, false, - MMU_USER_IDX); + MemOp op = MO_TE | SHIFT; + uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, false); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); ret = glue(glue(ld, USUFFIX), _p)(g2h(ptr)); #endif @@ -XXX,XX +XXX,XX @@ glue(glue(cpu_lds, SUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr) ret = glue(glue(lds, SUFFIX), _p)(g2h(ptr)); clear_helper_retaddr(); #else - uint16_t meminfo = trace_mem_build_info(SHIFT, true, MO_TE, false, - MMU_USER_IDX); + MemOp op = MO_TE | MO_SIGN | SHIFT; + uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, false); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); ret = glue(glue(lds, SUFFIX), _p)(g2h(ptr)); qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); @@ -XXX,XX +XXX,XX @@ static inline void glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr, RES_TYPE v) { - uint16_t meminfo = trace_mem_build_info(SHIFT, false, MO_TE, true, - MMU_USER_IDX); + MemOp op = MO_TE | SHIFT; + uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, true); trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); glue(glue(st, SUFFIX), _p)(g2h(ptr), v); qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -- 2.20.1 It is easy for the atomic helpers to use trace_mem_build_info directly, without resorting to symbol pasting. For this usage, we cannot use trace_mem_get_info, because the MemOp does not support 16-byte accesses. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/atomic_template.h | 67 +++++++++++++------------------------ trace/mem-internal.h | 17 ---------- 2 files changed, 24 insertions(+), 60 deletions(-) diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/atomic_template.h +++ b/accel/tcg/atomic_template.h @@ -XXX,XX +XXX,XX @@ the ATOMIC_NAME macro, and redefined below. */ #if DATA_SIZE == 1 # define END -# define MEND _be /* either le or be would be fine */ #elif defined(HOST_WORDS_BIGENDIAN) # define END _be -# define MEND _be #else # define END _le -# define MEND _le #endif ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; DATA_TYPE ret; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, + ATOMIC_MMU_IDX); atomic_trace_rmw_pre(env, addr, info); #if DATA_SIZE == 16 @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS) { ATOMIC_MMU_DECLS; DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, + ATOMIC_MMU_IDX); atomic_trace_ld_pre(env, addr, info); val = atomic16_read(haddr); @@ -XXX,XX +XXX,XX @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, { ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, true, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, 0, true, + ATOMIC_MMU_IDX); atomic_trace_st_pre(env, addr, info); atomic16_set(haddr, val); @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; DATA_TYPE ret; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, + ATOMIC_MMU_IDX); atomic_trace_rmw_pre(env, addr, info); ret = atomic_xchg__nocheck(haddr, val); @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ATOMIC_MMU_DECLS; \ DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ DATA_TYPE ret; \ - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, \ - false, \ - ATOMIC_MMU_IDX); \ - \ + uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, \ + ATOMIC_MMU_IDX); \ atomic_trace_rmw_pre(env, addr, info); \ ret = atomic_##X(haddr, val); \ ATOMIC_MMU_CLEANUP; \ @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ATOMIC_MMU_DECLS; \ XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ XDATA_TYPE cmp, old, new, val = xval; \ - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, \ - false, \ - ATOMIC_MMU_IDX); \ - \ + uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, \ + ATOMIC_MMU_IDX); \ atomic_trace_rmw_pre(env, addr, info); \ smp_mb(); \ cmp = atomic_read__nocheck(haddr); \ @@ -XXX,XX +XXX,XX @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) #endif /* DATA SIZE >= 16 */ #undef END -#undef MEND #if DATA_SIZE > 1 @@ -XXX,XX +XXX,XX @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) within the ATOMIC_NAME macro. */ #ifdef HOST_WORDS_BIGENDIAN # define END _le -# define MEND _le #else # define END _be -# define MEND _be #endif ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; DATA_TYPE ret; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, - false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, + ATOMIC_MMU_IDX); atomic_trace_rmw_pre(env, addr, info); #if DATA_SIZE == 16 @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS) { ATOMIC_MMU_DECLS; DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, - false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, + ATOMIC_MMU_IDX); atomic_trace_ld_pre(env, addr, info); val = atomic16_read(haddr); @@ -XXX,XX +XXX,XX @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, { ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, - true, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, true, + ATOMIC_MMU_IDX); val = BSWAP(val); atomic_trace_st_pre(env, addr, info); @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ATOMIC_MMU_DECLS; DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; ABI_TYPE ret; - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, - false, - ATOMIC_MMU_IDX); + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, + ATOMIC_MMU_IDX); atomic_trace_rmw_pre(env, addr, info); ret = atomic_xchg__nocheck(haddr, BSWAP(val)); @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ATOMIC_MMU_DECLS; \ DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ DATA_TYPE ret; \ - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, \ - false, \ - ATOMIC_MMU_IDX); \ - \ + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, \ + false, ATOMIC_MMU_IDX); \ atomic_trace_rmw_pre(env, addr, info); \ ret = atomic_##X(haddr, BSWAP(val)); \ ATOMIC_MMU_CLEANUP; \ @@ -XXX,XX +XXX,XX @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ATOMIC_MMU_DECLS; \ XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ XDATA_TYPE ldo, ldn, old, new, val = xval; \ - uint16_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, \ - false, \ - ATOMIC_MMU_IDX); \ - \ + uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, \ + false, ATOMIC_MMU_IDX); \ atomic_trace_rmw_pre(env, addr, info); \ smp_mb(); \ ldn = atomic_read__nocheck(haddr); \ @@ -XXX,XX +XXX,XX @@ GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new) #endif /* DATA_SIZE >= 16 */ #undef END -#undef MEND #endif /* DATA_SIZE > 1 */ #undef BSWAP diff --git a/trace/mem-internal.h b/trace/mem-internal.h index XXXXXXX..XXXXXXX 100644 --- a/trace/mem-internal.h +++ b/trace/mem-internal.h @@ -XXX,XX +XXX,XX @@ static inline uint16_t trace_mem_get_info(MemOp op, mmu_idx); } -/* Used by the atomic helpers */ -static inline -uint16_t trace_mem_build_info_no_se_be(int size_shift, bool store, - TCGMemOpIdx oi) -{ - return trace_mem_build_info(size_shift, false, MO_BE, store, - get_mmuidx(oi)); -} - -static inline -uint16_t trace_mem_build_info_no_se_le(int size_shift, bool store, - TCGMemOpIdx oi) -{ - return trace_mem_build_info(size_shift, false, MO_LE, store, - get_mmuidx(oi)); -} - #endif /* TRACE__MEM_INTERNAL_H */ -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on tcg.h being included indirectly. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/s390x/mem_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/mem_helper.c +++ b/target/s390x/mem_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "qemu/int128.h" #include "qemu/atomic128.h" +#include "tcg.h" #if !defined(CONFIG_USER_ONLY) #include "hw/s390x/storage-keys.h" -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on tcg.h being included indirectly. Cc: Peter Maydell <peter.maydell@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/sve_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" +#include "tcg.h" /* Note that vector data is stored in host-endian 64-bit chunks, -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on tcg.h being included indirectly. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/tcg-runtime.c | 1 + 1 file changed, 1 insertion(+) diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -XXX,XX +XXX,XX @@ #include "exec/tb-lookup.h" #include "disas/disas.h" #include "exec/log.h" +#include "tcg.h" /* 32-bit helpers */ -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on tcg.h being included indirectly. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/syscall.c | 1 + 1 file changed, 1 insertion(+) diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ #include "user/syscall-trace.h" #include "qapi/error.h" #include "fd-trans.h" +#include "tcg.h" #ifndef CLONE_IO #define CLONE_IO 0x80000000 /* Clone io context */ -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on trace-root.h being included beforehand. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/user/syscall-trace.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/user/syscall-trace.h b/include/user/syscall-trace.h index XXXXXXX..XXXXXXX 100644 --- a/include/user/syscall-trace.h +++ b/include/user/syscall-trace.h @@ -XXX,XX +XXX,XX @@ #ifndef _SYSCALL_TRACE_H_ #define _SYSCALL_TRACE_H_ +#include "trace-root.h" + /* * These helpers just provide a common place for the various * subsystems that want to track syscalls to put their hooks in. We -- 2.20.1 Code movement in an upcoming patch will show that this file was implicitly depending on trace/mem.h being included beforehand. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reported-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- plugins/api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/plugins/api.c b/plugins/api.c index XXXXXXX..XXXXXXX 100644 --- a/plugins/api.c +++ b/plugins/api.c @@ -XXX,XX +XXX,XX @@ #include "qemu/plugin-memory.h" #include "hw/boards.h" #endif +#include "trace/mem.h" /* Uninstall and Reset handlers */ -- 2.20.1 With the tracing hooks, the inline functions are no longer so simple. Once out-of-line, the current tlb_entry lookup is redundant with the one in the main load/store_helper. This also begins the introduction of a new target facing interface, with suffix *_mmuidx_ra. This is not yet official because the interface is not done for user-only. Use abi_ptr instead of target_ulong in preparation for user-only; the two types are identical for softmmu. What remains in cpu_ldst_template.h are the expansions for _code, _data, and MMU_MODE<N>_SUFFIX. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 25 ++++++- include/exec/cpu_ldst_template.h | 125 +++++++------------------------ accel/tcg/cputlb.c | 116 ++++++++++++++++++++++++++++ 3 files changed, 166 insertions(+), 100 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline void clear_helper_retaddr(void) #else -/* The memory helpers for tcg-generated code need tcg_target_long etc. */ +/* Needed for TCG_OVERSIZED_GUEST */ #include "tcg.h" static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry) @@ -XXX,XX +XXX,XX @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, return &env_tlb(env)->f[mmu_idx].table[tlb_index(env, mmu_idx, addr)]; } +uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); +uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); +uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); +uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); + +int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); +int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra); + +void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t retaddr); +void cpu_stw_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t retaddr); +void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t retaddr); +void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, + int mmu_idx, uintptr_t retaddr); + #ifdef MMU_MODE0_SUFFIX #define CPU_MMU_INDEX 0 #define MEMSUFFIX MMU_MODE0_SUFFIX diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst_template.h +++ b/include/exec/cpu_ldst_template.h @@ -XXX,XX +XXX,XX @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -#if !defined(SOFTMMU_CODE_ACCESS) -#include "trace-root.h" -#endif - -#include "qemu/plugin.h" -#include "trace/mem.h" - #if DATA_SIZE == 8 #define SUFFIX q #define USUFFIX q @@ -XXX,XX +XXX,XX @@ #define RES_TYPE uint32_t #endif +/* generic load/store macros */ + #ifdef SOFTMMU_CODE_ACCESS -#define ADDR_READ addr_code -#define MMUSUFFIX _cmmu -#define URETSUFFIX USUFFIX -#define SRETSUFFIX glue(s, SUFFIX) -#else -#define ADDR_READ addr_read -#define MMUSUFFIX _mmu -#define URETSUFFIX USUFFIX -#define SRETSUFFIX glue(s, SUFFIX) + +static inline RES_TYPE +glue(glue(cpu_ld, USUFFIX), _code)(CPUArchState *env, target_ulong ptr) +{ + TCGMemOpIdx oi = make_memop_idx(MO_TE | SHIFT, CPU_MMU_INDEX); + return glue(glue(helper_ret_ld, USUFFIX), _cmmu)(env, ptr, oi, 0); +} + +#if DATA_SIZE <= 2 +static inline int +glue(glue(cpu_lds, SUFFIX), _code)(CPUArchState *env, target_ulong ptr) +{ + return (DATA_STYPE)glue(glue(cpu_ld, USUFFIX), _code)(env, ptr); +} #endif -/* generic load/store macros */ +#else static inline RES_TYPE glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) { - CPUTLBEntry *entry; - RES_TYPE res; - target_ulong addr; - int mmu_idx = CPU_MMU_INDEX; - MemOp op = MO_TE | SHIFT; -#if !defined(SOFTMMU_CODE_ACCESS) - uint16_t meminfo = trace_mem_get_info(op, mmu_idx, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); -#endif - - addr = ptr; - entry = tlb_entry(env, mmu_idx, addr); - if (unlikely(entry->ADDR_READ != - (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - TCGMemOpIdx oi = make_memop_idx(op, mmu_idx); - res = glue(glue(helper_ret_ld, URETSUFFIX), MMUSUFFIX)(env, addr, - oi, retaddr); - } else { - uintptr_t hostaddr = addr + entry->addend; - res = glue(glue(ld, USUFFIX), _p)((uint8_t *)hostaddr); - } -#ifndef SOFTMMU_CODE_ACCESS - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -#endif - return res; + return glue(glue(cpu_ld, USUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, + retaddr); } static inline RES_TYPE glue(glue(cpu_ld, USUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr) { - return glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(env, ptr, 0); + return glue(glue(cpu_ld, USUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, 0); } #if DATA_SIZE <= 2 @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) { - CPUTLBEntry *entry; - int res; - target_ulong addr; - int mmu_idx = CPU_MMU_INDEX; - MemOp op = MO_TE | MO_SIGN | SHIFT; -#ifndef SOFTMMU_CODE_ACCESS - uint16_t meminfo = trace_mem_get_info(op, mmu_idx, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); -#endif - - addr = ptr; - entry = tlb_entry(env, mmu_idx, addr); - if (unlikely(entry->ADDR_READ != - (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - TCGMemOpIdx oi = make_memop_idx(op & ~MO_SIGN, mmu_idx); - res = (DATA_STYPE)glue(glue(helper_ret_ld, SRETSUFFIX), - MMUSUFFIX)(env, addr, oi, retaddr); - } else { - uintptr_t hostaddr = addr + entry->addend; - res = glue(glue(lds, SUFFIX), _p)((uint8_t *)hostaddr); - } -#ifndef SOFTMMU_CODE_ACCESS - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -#endif - return res; + return glue(glue(cpu_lds, SUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, + retaddr); } static inline int glue(glue(cpu_lds, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr) { - return glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(env, ptr, 0); + return glue(glue(cpu_lds, SUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, 0); } #endif -#ifndef SOFTMMU_CODE_ACCESS - /* generic store macro */ static inline void @@ -XXX,XX +XXX,XX @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, RES_TYPE v, uintptr_t retaddr) { - CPUTLBEntry *entry; - target_ulong addr; - int mmu_idx = CPU_MMU_INDEX; - MemOp op = MO_TE | SHIFT; -#if !defined(SOFTMMU_CODE_ACCESS) - uint16_t meminfo = trace_mem_get_info(op, mmu_idx, true); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); -#endif - - addr = ptr; - entry = tlb_entry(env, mmu_idx, addr); - if (unlikely(tlb_addr_write(entry) != - (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) { - TCGMemOpIdx oi = make_memop_idx(op, mmu_idx); - glue(glue(helper_ret_st, SUFFIX), MMUSUFFIX)(env, addr, v, oi, - retaddr); - } else { - uintptr_t hostaddr = addr + entry->addend; - glue(glue(st, SUFFIX), _p)((uint8_t *)hostaddr, v); - } -#ifndef SOFTMMU_CODE_ACCESS - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -#endif + glue(glue(cpu_st, SUFFIX), _mmuidx_ra)(env, ptr, v, CPU_MMU_INDEX, + retaddr); } static inline void glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr, RES_TYPE v) { - glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(env, ptr, v, 0); + glue(glue(cpu_st, SUFFIX), _mmuidx_ra)(env, ptr, v, CPU_MMU_INDEX, 0); } #endif /* !SOFTMMU_CODE_ACCESS */ @@ -XXX,XX +XXX,XX @@ glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr, #undef SUFFIX #undef USUFFIX #undef DATA_SIZE -#undef MMUSUFFIX -#undef ADDR_READ -#undef URETSUFFIX -#undef SRETSUFFIX #undef SHIFT diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ #include "qemu/atomic.h" #include "qemu/atomic128.h" #include "translate-all.h" +#include "trace-root.h" +#include "qemu/plugin.h" +#include "trace/mem.h" #ifdef CONFIG_PLUGIN #include "qemu/plugin-memory.h" #endif @@ -XXX,XX +XXX,XX @@ tcg_target_ulong helper_be_ldsl_mmu(CPUArchState *env, target_ulong addr, return (int32_t)helper_be_ldul_mmu(env, addr, oi, retaddr); } +/* + * Load helpers for cpu_ldst.h. + */ + +static inline uint64_t cpu_load_helper(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t retaddr, + MemOp op, FullLoadHelper *full_load) +{ + uint16_t meminfo; + TCGMemOpIdx oi; + uint64_t ret; + + meminfo = trace_mem_get_info(op, mmu_idx, false); + trace_guest_mem_before_exec(env_cpu(env), addr, meminfo); + + op &= ~MO_SIGN; + oi = make_memop_idx(op, mmu_idx); + ret = full_load(env, addr, oi, retaddr); + + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, meminfo); + + return ret; +} + +uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_load_helper(env, addr, mmu_idx, ra, MO_UB, full_ldub_mmu); +} + +int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return (int8_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_SB, + full_ldub_mmu); +} + +uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEUW, + MO_TE == MO_LE + ? full_le_lduw_mmu : full_be_lduw_mmu); +} + +int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_TESW, + MO_TE == MO_LE + ? full_le_lduw_mmu : full_be_lduw_mmu); +} + +uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEUL, + MO_TE == MO_LE + ? full_le_ldul_mmu : full_be_ldul_mmu); +} + +uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEQ, + MO_TE == MO_LE + ? helper_le_ldq_mmu : helper_be_ldq_mmu); +} + /* * Store Helpers */ @@ -XXX,XX +XXX,XX @@ void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, store_helper(env, addr, val, oi, retaddr, MO_BEQ); } +/* + * Store Helpers for cpu_ldst.h + */ + +static inline void QEMU_ALWAYS_INLINE +cpu_store_helper(CPUArchState *env, target_ulong addr, uint64_t val, + int mmu_idx, uintptr_t retaddr, MemOp op) +{ + TCGMemOpIdx oi; + uint16_t meminfo; + + meminfo = trace_mem_get_info(op, mmu_idx, true); + trace_guest_mem_before_exec(env_cpu(env), addr, meminfo); + + oi = make_memop_idx(op, mmu_idx); + store_helper(env, addr, val, oi, retaddr, op); + + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, meminfo); +} + +void cpu_stb_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val, + int mmu_idx, uintptr_t retaddr) +{ + cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_UB); +} + +void cpu_stw_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val, + int mmu_idx, uintptr_t retaddr) +{ + cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEUW); +} + +void cpu_stl_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val, + int mmu_idx, uintptr_t retaddr) +{ + cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEUL); +} + +void cpu_stq_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val, + int mmu_idx, uintptr_t retaddr) +{ + cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEQ); +} + /* First set of helpers allows passing in of OI and RETADDR. This makes them callable from other helpers. */ -- 2.20.1 The DO_LOAD macros replicate the distinction already performed by the cpu_ldst.h functions. Use them. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 11 --------- include/exec/translator.h | 48 +++++++++++---------------------------- 2 files changed, 13 insertions(+), 46 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline void clear_helper_retaddr(void) #include "exec/cpu_ldst_useronly_template.h" #undef MEMSUFFIX -/* - * Code access is deprecated in favour of translator_ld* functions - * (see translator.h). However there are still users that need to - * converted so for now these stay. - */ #define MEMSUFFIX _code #define CODE_ACCESS #define DATA_SIZE 1 @@ -XXX,XX +XXX,XX @@ void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, #undef CPU_MMU_INDEX #undef MEMSUFFIX -/* - * Code access is deprecated in favour of translator_ld* functions - * (see translator.h). However there are still users that need to - * converted so for now these stay. - */ - #define CPU_MMU_INDEX (cpu_mmu_index(env, true)) #define MEMSUFFIX _code #define SOFTMMU_CODE_ACCESS diff --git a/include/exec/translator.h b/include/exec/translator.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -XXX,XX +XXX,XX @@ void translator_loop_temp_check(DisasContextBase *db); /* * Translator Load Functions * - * These are intended to replace the old cpu_ld*_code functions and - * are mandatory for front-ends that have been migrated to the common - * translator_loop. These functions are only intended to be called - * from the translation stage and should not be called from helper - * functions. Those functions should be converted to encode the - * relevant information at translation time. + * These are intended to replace the direct usage of the cpu_ld*_code + * functions and are mandatory for front-ends that have been migrated + * to the common translator_loop. These functions are only intended + * to be called from the translation stage and should not be called + * from helper functions. Those functions should be converted to encode + * the relevant information at translation time. */ -#ifdef CONFIG_USER_ONLY - -#define DO_LOAD(type, name, shift) \ - do { \ - set_helper_retaddr(1); \ - ret = name ## _p(g2h(pc)); \ - clear_helper_retaddr(); \ - } while (0) - -#else - -#define DO_LOAD(type, name, shift) \ - do { \ - int mmu_idx = cpu_mmu_index(env, true); \ - TCGMemOpIdx oi = make_memop_idx(shift, mmu_idx); \ - ret = helper_ret_ ## name ## _cmmu(env, pc, oi, 0); \ - } while (0) - -#endif - -#define GEN_TRANSLATOR_LD(fullname, name, type, shift, swap_fn) \ +#define GEN_TRANSLATOR_LD(fullname, type, load_fn, swap_fn) \ static inline type \ fullname ## _swap(CPUArchState *env, abi_ptr pc, bool do_swap) \ { \ - type ret; \ - DO_LOAD(type, name, shift); \ - \ + type ret = load_fn(env, pc); \ if (do_swap) { \ ret = swap_fn(ret); \ } \ @@ -XXX,XX +XXX,XX @@ void translator_loop_temp_check(DisasContextBase *db); return fullname ## _swap(env, pc, false); \ } -GEN_TRANSLATOR_LD(translator_ldub, ldub, uint8_t, 0, /* no swap */ ) -GEN_TRANSLATOR_LD(translator_ldsw, ldsw, int16_t, 1, bswap16) -GEN_TRANSLATOR_LD(translator_lduw, lduw, uint16_t, 1, bswap16) -GEN_TRANSLATOR_LD(translator_ldl, ldl, uint32_t, 2, bswap32) -GEN_TRANSLATOR_LD(translator_ldq, ldq, uint64_t, 3, bswap64) +GEN_TRANSLATOR_LD(translator_ldub, uint8_t, cpu_ldub_code, /* no swap */) +GEN_TRANSLATOR_LD(translator_ldsw, int16_t, cpu_ldsw_code, bswap16) +GEN_TRANSLATOR_LD(translator_lduw, uint16_t, cpu_lduw_code, bswap16) +GEN_TRANSLATOR_LD(translator_ldl, uint32_t, cpu_ldl_code, bswap32) +GEN_TRANSLATOR_LD(translator_ldq, uint64_t, cpu_ldq_code, bswap64) #undef GEN_TRANSLATOR_LD #endif /* EXEC__TRANSLATOR_H */ -- 2.20.1 There are no uses of the *_cmmu names other than the bare wrapping within the *_code inlines. Therefore rename the functions so we can drop the inlines. Use abi_ptr instead of target_ulong in preparation for user-only; the two types are identical for softmmu. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 29 ++++------ include/exec/cpu_ldst_template.h | 21 ------- tcg/tcg.h | 29 ---------- accel/tcg/cputlb.c | 94 ++++++++------------------------ docs/devel/loads-stores.rst | 4 +- 5 files changed, 36 insertions(+), 141 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, #undef CPU_MMU_INDEX #undef MEMSUFFIX -#define CPU_MMU_INDEX (cpu_mmu_index(env, true)) -#define MEMSUFFIX _code -#define SOFTMMU_CODE_ACCESS +uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr); +uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr); +uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr); +uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr); -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" +static inline int cpu_ldsb_code(CPUArchState *env, abi_ptr addr) +{ + return (int8_t)cpu_ldub_code(env, addr); +} -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" - -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#undef SOFTMMU_CODE_ACCESS +static inline int cpu_ldsw_code(CPUArchState *env, abi_ptr addr) +{ + return (int16_t)cpu_lduw_code(env, addr); +} #endif /* defined(CONFIG_USER_ONLY) */ diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst_template.h +++ b/include/exec/cpu_ldst_template.h @@ -XXX,XX +XXX,XX @@ /* generic load/store macros */ -#ifdef SOFTMMU_CODE_ACCESS - -static inline RES_TYPE -glue(glue(cpu_ld, USUFFIX), _code)(CPUArchState *env, target_ulong ptr) -{ - TCGMemOpIdx oi = make_memop_idx(MO_TE | SHIFT, CPU_MMU_INDEX); - return glue(glue(helper_ret_ld, USUFFIX), _cmmu)(env, ptr, oi, 0); -} - -#if DATA_SIZE <= 2 -static inline int -glue(glue(cpu_lds, SUFFIX), _code)(CPUArchState *env, target_ulong ptr) -{ - return (DATA_STYPE)glue(glue(cpu_ld, USUFFIX), _code)(env, ptr); -} -#endif - -#else - static inline RES_TYPE glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, target_ulong ptr, @@ -XXX,XX +XXX,XX @@ glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr, glue(glue(cpu_st, SUFFIX), _mmuidx_ra)(env, ptr, v, CPU_MMU_INDEX, 0); } -#endif /* !SOFTMMU_CODE_ACCESS */ - #undef RES_TYPE #undef DATA_TYPE #undef DATA_STYPE diff --git a/tcg/tcg.h b/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ void helper_be_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, TCGMemOpIdx oi, uintptr_t retaddr); -uint8_t helper_ret_ldub_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -int8_t helper_ret_ldsb_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint16_t helper_le_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -int16_t helper_le_ldsw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_le_ldl_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint64_t helper_le_ldq_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint16_t helper_be_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -int16_t helper_be_ldsw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_be_ldl_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -uint64_t helper_be_ldq_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); - /* Temporary aliases until backends are converted. */ #ifdef TARGET_WORDS_BIGENDIAN # define helper_ret_ldsw_mmu helper_be_ldsw_mmu @@ -XXX,XX +XXX,XX @@ uint64_t helper_be_ldq_cmmu(CPUArchState *env, target_ulong addr, # define helper_ret_stw_mmu helper_be_stw_mmu # define helper_ret_stl_mmu helper_be_stl_mmu # define helper_ret_stq_mmu helper_be_stq_mmu -# define helper_ret_lduw_cmmu helper_be_lduw_cmmu -# define helper_ret_ldsw_cmmu helper_be_ldsw_cmmu -# define helper_ret_ldl_cmmu helper_be_ldl_cmmu -# define helper_ret_ldq_cmmu helper_be_ldq_cmmu #else # define helper_ret_ldsw_mmu helper_le_ldsw_mmu # define helper_ret_lduw_mmu helper_le_lduw_mmu @@ -XXX,XX +XXX,XX @@ uint64_t helper_be_ldq_cmmu(CPUArchState *env, target_ulong addr, # define helper_ret_stw_mmu helper_le_stw_mmu # define helper_ret_stl_mmu helper_le_stl_mmu # define helper_ret_stq_mmu helper_le_stq_mmu -# define helper_ret_lduw_cmmu helper_le_lduw_cmmu -# define helper_ret_ldsw_cmmu helper_le_ldsw_cmmu -# define helper_ret_ldl_cmmu helper_le_ldl_cmmu -# define helper_ret_ldq_cmmu helper_le_ldq_cmmu #endif uint32_t helper_atomic_cmpxchgb_mmu(CPUArchState *env, target_ulong addr, diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void cpu_stq_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val, /* Code access functions. */ -static uint64_t full_ldub_cmmu(CPUArchState *env, target_ulong addr, +static uint64_t full_ldub_code(CPUArchState *env, target_ulong addr, TCGMemOpIdx oi, uintptr_t retaddr) { - return load_helper(env, addr, oi, retaddr, MO_8, true, full_ldub_cmmu); + return load_helper(env, addr, oi, retaddr, MO_8, true, full_ldub_code); } -uint8_t helper_ret_ldub_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr) { - return full_ldub_cmmu(env, addr, oi, retaddr); + TCGMemOpIdx oi = make_memop_idx(MO_UB, cpu_mmu_index(env, true)); + return full_ldub_code(env, addr, oi, 0); } -int8_t helper_ret_ldsb_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +static uint64_t full_lduw_code(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr) { - return (int8_t) full_ldub_cmmu(env, addr, oi, retaddr); + return load_helper(env, addr, oi, retaddr, MO_TEUW, true, full_lduw_code); } -static uint64_t full_le_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr) { - return load_helper(env, addr, oi, retaddr, MO_LEUW, true, - full_le_lduw_cmmu); + TCGMemOpIdx oi = make_memop_idx(MO_TEUW, cpu_mmu_index(env, true)); + return full_lduw_code(env, addr, oi, 0); } -uint16_t helper_le_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +static uint64_t full_ldl_code(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr) { - return full_le_lduw_cmmu(env, addr, oi, retaddr); + return load_helper(env, addr, oi, retaddr, MO_TEUL, true, full_ldl_code); } -int16_t helper_le_ldsw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr) { - return (int16_t) full_le_lduw_cmmu(env, addr, oi, retaddr); + TCGMemOpIdx oi = make_memop_idx(MO_TEUL, cpu_mmu_index(env, true)); + return full_ldl_code(env, addr, oi, 0); } -static uint64_t full_be_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +static uint64_t full_ldq_code(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr) { - return load_helper(env, addr, oi, retaddr, MO_BEUW, true, - full_be_lduw_cmmu); + return load_helper(env, addr, oi, retaddr, MO_TEQ, true, full_ldq_code); } -uint16_t helper_be_lduw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) +uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr) { - return full_be_lduw_cmmu(env, addr, oi, retaddr); -} - -int16_t helper_be_ldsw_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return (int16_t) full_be_lduw_cmmu(env, addr, oi, retaddr); -} - -static uint64_t full_le_ldul_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return load_helper(env, addr, oi, retaddr, MO_LEUL, true, - full_le_ldul_cmmu); -} - -uint32_t helper_le_ldl_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return full_le_ldul_cmmu(env, addr, oi, retaddr); -} - -static uint64_t full_be_ldul_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return load_helper(env, addr, oi, retaddr, MO_BEUL, true, - full_be_ldul_cmmu); -} - -uint32_t helper_be_ldl_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return full_be_ldul_cmmu(env, addr, oi, retaddr); -} - -uint64_t helper_le_ldq_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return load_helper(env, addr, oi, retaddr, MO_LEQ, true, - helper_le_ldq_cmmu); -} - -uint64_t helper_be_ldq_cmmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) -{ - return load_helper(env, addr, oi, retaddr, MO_BEQ, true, - helper_be_ldq_cmmu); + TCGMemOpIdx oi = make_memop_idx(MO_TEQ, cpu_mmu_index(env, true)); + return full_ldq_code(env, addr, oi, 0); } diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/loads-stores.rst +++ b/docs/devel/loads-stores.rst @@ -XXX,XX +XXX,XX @@ more in line with the other memory access functions. load: ``helper_{endian}_ld{sign}{size}_mmu(env, addr, opindex, retaddr)`` -load (code): ``helper_{endian}_ld{sign}{size}_cmmu(env, addr, opindex, retaddr)`` - store: ``helper_{endian}_st{size}_mmu(env, addr, val, opindex, retaddr)`` ``sign`` @@ -XXX,XX +XXX,XX @@ store: ``helper_{endian}_st{size}_mmu(env, addr, val, opindex, retaddr)`` - ``ret`` : target endianness Regexes for git grep - - ``\<helper_\(le\|be\|ret\)_ld[us]\?[bwlq]_c\?mmu\>`` + - ``\<helper_\(le\|be\|ret\)_ld[us]\?[bwlq]_mmu\>`` - ``\<helper_\(le\|be\|ret\)_st[bwlq]_mmu\>`` ``address_space_*`` -- 2.20.1 This finishes the new interface began with the previous patch. Document the interface and deprecate MMU_MODE<N>_SUFFIX. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 80 +++++++++++++- docs/devel/loads-stores.rst | 211 ++++++++++++++++++++++++++---------- 2 files changed, 230 insertions(+), 61 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ * * The syntax for the accessors is: * - * load: cpu_ld{sign}{size}_{mmusuffix}(env, ptr) + * load: cpu_ld{sign}{size}_{mmusuffix}(env, ptr) + * cpu_ld{sign}{size}_{mmusuffix}_ra(env, ptr, retaddr) + * cpu_ld{sign}{size}_mmuidx_ra(env, ptr, mmu_idx, retaddr) * - * store: cpu_st{sign}{size}_{mmusuffix}(env, ptr, val) + * store: cpu_st{size}_{mmusuffix}(env, ptr, val) + * cpu_st{size}_{mmusuffix}_ra(env, ptr, val, retaddr) + * cpu_st{size}_mmuidx_ra(env, ptr, val, mmu_idx, retaddr) * * sign is: * (empty): for 32 and 64 bit sizes @@ -XXX,XX +XXX,XX @@ * l: 32 bits * q: 64 bits * - * mmusuffix is one of the generic suffixes "data" or "code", or - * (for softmmu configs) a target-specific MMU mode suffix as defined - * in target cpu.h. + * mmusuffix is one of the generic suffixes "data" or "code", or "mmuidx". + * The "mmuidx" suffix carries an extra mmu_idx argument that specifies + * the index to use; the "data" and "code" suffixes take the index from + * cpu_mmu_index(). */ #ifndef CPU_LDST_H #define CPU_LDST_H @@ -XXX,XX +XXX,XX @@ static inline void clear_helper_retaddr(void) #undef MEMSUFFIX #undef CODE_ACCESS +/* + * Provide the same *_mmuidx_ra interface as for softmmu. + * The mmu_idx argument is ignored. + */ + +static inline uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_ldub_data_ra(env, addr, ra); +} + +static inline uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_lduw_data_ra(env, addr, ra); +} + +static inline uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_ldl_data_ra(env, addr, ra); +} + +static inline uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_ldq_data_ra(env, addr, ra); +} + +static inline int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_ldsb_data_ra(env, addr, ra); +} + +static inline int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return cpu_ldsw_data_ra(env, addr, ra); +} + +static inline void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, + uint32_t val, int mmu_idx, uintptr_t ra) +{ + cpu_stb_data_ra(env, addr, val, ra); +} + +static inline void cpu_stw_mmuidx_ra(CPUArchState *env, abi_ptr addr, + uint32_t val, int mmu_idx, uintptr_t ra) +{ + cpu_stw_data_ra(env, addr, val, ra); +} + +static inline void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr, + uint32_t val, int mmu_idx, uintptr_t ra) +{ + cpu_stl_data_ra(env, addr, val, ra); +} + +static inline void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, + uint64_t val, int mmu_idx, uintptr_t ra) +{ + cpu_stq_data_ra(env, addr, val, ra); +} + #else /* Needed for TCG_OVERSIZED_GUEST */ diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/loads-stores.rst +++ b/docs/devel/loads-stores.rst @@ -XXX,XX +XXX,XX @@ Regexes for git grep - ``\<ldn_\([hbl]e\)?_p\>`` - ``\<stn_\([hbl]e\)?_p\>`` -``cpu_{ld,st}_*`` -~~~~~~~~~~~~~~~~~ +``cpu_{ld,st}*_mmuidx_ra`` +~~~~~~~~~~~~~~~~~~~~~~~~~~ -These functions operate on a guest virtual address. Be aware -that these functions may cause a guest CPU exception to be -taken (e.g. for an alignment fault or MMU fault) which will -result in guest CPU state being updated and control longjumping -out of the function call. They should therefore only be used -in code that is implementing emulation of the target CPU. +These functions operate on a guest virtual address plus a context, +known as a "mmu index" or ``mmuidx``, which controls how that virtual +address is translated. The meaning of the indexes are target specific, +but specifying a particular index might be necessary if, for instance, +the helper requires an "always as non-privileged" access rather that +the default access for the current state of the guest CPU. -These functions may throw an exception (longjmp() back out -to the top level TCG loop). This means they must only be used -from helper functions where the translator has saved all -necessary CPU state before generating the helper function call. -It's usually better to use the ``_ra`` variants described below -from helper functions, but these functions are the right choice -for calls made from hooks like the CPU do_interrupt hook or -when you know for certain that the translator had to save all -the CPU state that ``cpu_restore_state()`` would restore anyway. +These functions may cause a guest CPU exception to be taken +(e.g. for an alignment fault or MMU fault) which will result in +guest CPU state being updated and control longjmp'ing out of the +function call. They should therefore only be used in code that is +implementing emulation of the guest CPU. + +The ``retaddr`` parameter is used to control unwinding of the +guest CPU state in case of a guest CPU exception. This is passed +to ``cpu_restore_state()``. Therefore the value should either be 0, +to indicate that the guest CPU state is already synchronized, or +the result of ``GETPC()`` from the top level ``HELPER(foo)`` +function, which is a return address into the generated code. Function names follow the pattern: -load: ``cpu_ld{sign}{size}_{mmusuffix}(env, ptr)`` +load: ``cpu_ld{sign}{size}_mmuidx_ra(env, ptr, mmuidx, retaddr)`` -store: ``cpu_st{size}_{mmusuffix}(env, ptr, val)`` +store: ``cpu_st{size}_mmuidx_ra(env, ptr, val, mmuidx, retaddr)`` ``sign`` - (empty) : for 32 or 64 bit sizes @@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}_{mmusuffix}(env, ptr, val)`` - ``l`` : 32 bits - ``q`` : 64 bits -``mmusuffix`` is one of the generic suffixes ``data`` or ``code``, or -(for softmmu configs) a target-specific MMU mode suffix as defined -in the target's ``cpu.h``. +Regexes for git grep: + - ``\<cpu_ld[us]\?[bwlq]_mmuidx_ra\>`` + - ``\<cpu_st[bwlq]_mmuidx_ra\>`` -Regexes for git grep - - ``\<cpu_ld[us]\?[bwlq]_[a-zA-Z0-9]\+\>`` - - ``\<cpu_st[bwlq]_[a-zA-Z0-9]\+\>`` +``cpu_{ld,st}*_data_ra`` +~~~~~~~~~~~~~~~~~~~~~~~~ -``cpu_{ld,st}_*_ra`` -~~~~~~~~~~~~~~~~~~~~ - -These functions work like the ``cpu_{ld,st}_*`` functions except -that they also take a ``retaddr`` argument. This extra argument -allows for correct unwinding of any exception that is taken, -and should generally be the result of GETPC() called directly -from the top level HELPER(foo) function (i.e. the return address -in the generated code). +These functions work like the ``cpu_{ld,st}_mmuidx_ra`` functions +except that the ``mmuidx`` parameter is taken from the current mode +of the guest CPU, as determined by ``cpu_mmu_index(env, false)``. These are generally the preferred way to do accesses by guest -virtual address from helper functions; see the documentation -of the non-``_ra`` variants for when those would be better. - -Calling these functions with a ``retaddr`` argument of 0 is -equivalent to calling the non-``_ra`` version of the function. +virtual address from helper functions, unless the access should +be performed with a context other than the default. Function names follow the pattern: -load: ``cpu_ld{sign}{size}_{mmusuffix}_ra(env, ptr, retaddr)`` +load: ``cpu_ld{sign}{size}_data_ra(env, ptr, ra)`` -store: ``cpu_st{sign}{size}_{mmusuffix}_ra(env, ptr, val, retaddr)`` +store: ``cpu_st{size}_data_ra(env, ptr, val, ra)`` + +``sign`` + - (empty) : for 32 or 64 bit sizes + - ``u`` : unsigned + - ``s`` : signed + +``size`` + - ``b`` : 8 bits + - ``w`` : 16 bits + - ``l`` : 32 bits + - ``q`` : 64 bits + +Regexes for git grep: + - ``\<cpu_ld[us]\?[bwlq]_data_ra\>`` + - ``\<cpu_st[bwlq]_data_ra\>`` + +``cpu_{ld,st}*_data`` +~~~~~~~~~~~~~~~~~~~~~ + +These functions work like the ``cpu_{ld,st}_data_ra`` functions +except that the ``retaddr`` parameter is 0, and thus does not +unwind guest CPU state. + +This means they must only be used from helper functions where the +translator has saved all necessary CPU state. These functions are +the right choice for calls made from hooks like the CPU ``do_interrupt`` +hook or when you know for certain that the translator had to save all +the CPU state anyway. + +Function names follow the pattern: + +load: ``cpu_ld{sign}{size}_data(env, ptr)`` + +store: ``cpu_st{size}_data(env, ptr, val)`` + +``sign`` + - (empty) : for 32 or 64 bit sizes + - ``u`` : unsigned + - ``s`` : signed + +``size`` + - ``b`` : 8 bits + - ``w`` : 16 bits + - ``l`` : 32 bits + - ``q`` : 64 bits Regexes for git grep - - ``\<cpu_ld[us]\?[bwlq]_[a-zA-Z0-9]\+_ra\>`` - - ``\<cpu_st[bwlq]_[a-zA-Z0-9]\+_ra\>`` + - ``\<cpu_ld[us]\?[bwlq]_data\>`` + - ``\<cpu_st[bwlq]_data\+\>`` -``helper_*_{ld,st}*mmu`` -~~~~~~~~~~~~~~~~~~~~~~~~ +``cpu_ld*_code`` +~~~~~~~~~~~~~~~~ + +These functions perform a read for instruction execution. The ``mmuidx`` +parameter is taken from the current mode of the guest CPU, as determined +by ``cpu_mmu_index(env, true)``. The ``retaddr`` parameter is 0, and +thus does not unwind guest CPU state, because CPU state is always +synchronized while translating instructions. Any guest CPU exception +that is raised will indicate an instruction execution fault rather than +a data read fault. + +In general these functions should not be used directly during translation. +There are wrapper functions that are to be used which also take care of +plugins for tracing. + +Function names follow the pattern: + +load: ``cpu_ld{sign}{size}_code(env, ptr)`` + +``sign`` + - (empty) : for 32 or 64 bit sizes + - ``u`` : unsigned + - ``s`` : signed + +``size`` + - ``b`` : 8 bits + - ``w`` : 16 bits + - ``l`` : 32 bits + - ``q`` : 64 bits + +Regexes for git grep: + - ``\<cpu_ld[us]\?[bwlq]_code\>`` + +``translator_ld*`` +~~~~~~~~~~~~~~~~~~ + +These functions are a wrapper for ``cpu_ld*_code`` which also perform +any actions required by any tracing plugins. They are only to be +called during the translator callback ``translate_insn``. + +There is a set of functions ending in ``_swap`` which, if the parameter +is true, returns the value in the endianness that is the reverse of +the guest native endianness, as determined by ``TARGET_WORDS_BIGENDIAN``. + +Function names follow the pattern: + +load: ``translator_ld{sign}{size}(env, ptr)`` + +swap: ``translator_ld{sign}{size}_swap(env, ptr, swap)`` + +``sign`` + - (empty) : for 32 or 64 bit sizes + - ``u`` : unsigned + - ``s`` : signed + +``size`` + - ``b`` : 8 bits + - ``w`` : 16 bits + - ``l`` : 32 bits + - ``q`` : 64 bits + +Regexes for git grep + - ``\<translator_ld[us]\?[bwlq]\(_swap\)\?\>`` + +``helper_*_{ld,st}*_mmu`` +~~~~~~~~~~~~~~~~~~~~~~~~~ These functions are intended primarily to be called by the code generated by the TCG backend. They may also be called by target -CPU helper function code. Like the ``cpu_{ld,st}_*_ra`` functions -they perform accesses by guest virtual address; the difference is -that these functions allow you to specify an ``opindex`` parameter -which encodes (among other things) the mmu index to use for the -access. This is necessary if your helper needs to make an access -via a specific mmu index (for instance, an "always as non-privileged" -access) rather than using the default mmu index for the current state -of the guest CPU. +CPU helper function code. Like the ``cpu_{ld,st}_mmuidx_ra`` functions +they perform accesses by guest virtual address, with a given ``mmuidx``. -The ``opindex`` parameter should be created by calling ``make_memop_idx()``. +These functions specify an ``opindex`` parameter which encodes +(among other things) the mmu index to use for the access. This parameter +should be created by calling ``make_memop_idx()``. The ``retaddr`` parameter should be the result of GETPC() called directly from the top level HELPER(foo) function (or 0 if no guest CPU state @@ -XXX,XX +XXX,XX @@ unwinding is required). **TODO** The names of these functions are a bit odd for historical reasons because they were originally expected to be called only from -within generated code. We should rename them to bring them -more in line with the other memory access functions. +within generated code. We should rename them to bring them more in +line with the other memory access functions. The explicit endianness +is the only feature they have beyond ``*_mmuidx_ra``. load: ``helper_{endian}_ld{sign}{size}_mmu(env, addr, opindex, retaddr)`` -- 2.20.1 Do not use exec/cpu_ldst_{,useronly_}template.h directly, but instead use the functional interface. Cc: Eduardo Habkost <ehabkost@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/i386/seg_helper.c | 56 ++++++++++++++++++++-------------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/target/i386/seg_helper.c b/target/i386/seg_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/seg_helper.c +++ b/target/i386/seg_helper.c @@ -XXX,XX +XXX,XX @@ # define LOG_PCALL_STATE(cpu) do { } while (0) #endif -#ifdef CONFIG_USER_ONLY -#define MEMSUFFIX _kernel -#define DATA_SIZE 1 -#include "exec/cpu_ldst_useronly_template.h" +/* + * TODO: Convert callers to compute cpu_mmu_index_kernel once + * and use *_mmuidx_ra directly. + */ +#define cpu_ldub_kernel_ra(e, p, r) \ + cpu_ldub_mmuidx_ra(e, p, cpu_mmu_index_kernel(e), r) +#define cpu_lduw_kernel_ra(e, p, r) \ + cpu_lduw_mmuidx_ra(e, p, cpu_mmu_index_kernel(e), r) +#define cpu_ldl_kernel_ra(e, p, r) \ + cpu_ldl_mmuidx_ra(e, p, cpu_mmu_index_kernel(e), r) +#define cpu_ldq_kernel_ra(e, p, r) \ + cpu_ldq_mmuidx_ra(e, p, cpu_mmu_index_kernel(e), r) -#define DATA_SIZE 2 -#include "exec/cpu_ldst_useronly_template.h" +#define cpu_stb_kernel_ra(e, p, v, r) \ + cpu_stb_mmuidx_ra(e, p, v, cpu_mmu_index_kernel(e), r) +#define cpu_stw_kernel_ra(e, p, v, r) \ + cpu_stw_mmuidx_ra(e, p, v, cpu_mmu_index_kernel(e), r) +#define cpu_stl_kernel_ra(e, p, v, r) \ + cpu_stl_mmuidx_ra(e, p, v, cpu_mmu_index_kernel(e), r) +#define cpu_stq_kernel_ra(e, p, v, r) \ + cpu_stq_mmuidx_ra(e, p, v, cpu_mmu_index_kernel(e), r) -#define DATA_SIZE 4 -#include "exec/cpu_ldst_useronly_template.h" +#define cpu_ldub_kernel(e, p) cpu_ldub_kernel_ra(e, p, 0) +#define cpu_lduw_kernel(e, p) cpu_lduw_kernel_ra(e, p, 0) +#define cpu_ldl_kernel(e, p) cpu_ldl_kernel_ra(e, p, 0) +#define cpu_ldq_kernel(e, p) cpu_ldq_kernel_ra(e, p, 0) -#define DATA_SIZE 8 -#include "exec/cpu_ldst_useronly_template.h" -#undef MEMSUFFIX -#else -#define CPU_MMU_INDEX (cpu_mmu_index_kernel(env)) -#define MEMSUFFIX _kernel -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif +#define cpu_stb_kernel(e, p, v) cpu_stb_kernel_ra(e, p, v, 0) +#define cpu_stw_kernel(e, p, v) cpu_stw_kernel_ra(e, p, v, 0) +#define cpu_stl_kernel(e, p, v) cpu_stl_kernel_ra(e, p, v, 0) +#define cpu_stq_kernel(e, p, v) cpu_stq_kernel_ra(e, p, v, 0) /* return non zero if error */ static inline int load_segment_ra(CPUX86State *env, uint32_t *e1_ptr, -- 2.20.1 With the tracing hooks, the inline functions are no longer so simple. Reduce the amount of preprocessor obfuscation by expanding the text of each of the functions generated. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 54 +++-- include/exec/cpu_ldst_useronly_template.h | 159 --------------- accel/tcg/user-exec.c | 236 ++++++++++++++++++++++ 3 files changed, 262 insertions(+), 187 deletions(-) delete mode 100644 include/exec/cpu_ldst_useronly_template.h diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline void clear_helper_retaddr(void) /* In user-only mode we provide only the _code and _data accessors. */ -#define MEMSUFFIX _data -#define DATA_SIZE 1 -#include "exec/cpu_ldst_useronly_template.h" +uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr); +uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr); +uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr); +uint64_t cpu_ldq_data(CPUArchState *env, abi_ptr ptr); +int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr); +int cpu_ldsw_data(CPUArchState *env, abi_ptr ptr); -#define DATA_SIZE 2 -#include "exec/cpu_ldst_useronly_template.h" +uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); +uint32_t cpu_lduw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); +uint32_t cpu_ldl_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); +uint64_t cpu_ldq_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); +int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); +int cpu_ldsw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr); -#define DATA_SIZE 4 -#include "exec/cpu_ldst_useronly_template.h" +void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val); +void cpu_stw_data(CPUArchState *env, abi_ptr ptr, uint32_t val); +void cpu_stl_data(CPUArchState *env, abi_ptr ptr, uint32_t val); +void cpu_stq_data(CPUArchState *env, abi_ptr ptr, uint64_t val); -#define DATA_SIZE 8 -#include "exec/cpu_ldst_useronly_template.h" -#undef MEMSUFFIX - -#define MEMSUFFIX _code -#define CODE_ACCESS -#define DATA_SIZE 1 -#include "exec/cpu_ldst_useronly_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_useronly_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_useronly_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_useronly_template.h" -#undef MEMSUFFIX -#undef CODE_ACCESS +void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr); +void cpu_stw_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr); +void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr); +void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr, + uint64_t val, uintptr_t retaddr); /* * Provide the same *_mmuidx_ra interface as for softmmu. @@ -XXX,XX +XXX,XX @@ void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, #undef CPU_MMU_INDEX #undef MEMSUFFIX +#endif /* defined(CONFIG_USER_ONLY) */ + uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr); uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr); uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr); @@ -XXX,XX +XXX,XX @@ static inline int cpu_ldsw_code(CPUArchState *env, abi_ptr addr) return (int16_t)cpu_lduw_code(env, addr); } -#endif /* defined(CONFIG_USER_ONLY) */ - /** * tlb_vaddr_to_host: * @env: CPUArchState diff --git a/include/exec/cpu_ldst_useronly_template.h b/include/exec/cpu_ldst_useronly_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/exec/cpu_ldst_useronly_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * User-only accessor function support - * - * Generate inline load/store functions for one data size. - * - * Generate a store function as well as signed and unsigned loads. - * - * Not used directly but included from cpu_ldst.h. - * - * Copyright (c) 2015 Linaro Limited - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library 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 - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -#if !defined(CODE_ACCESS) -#include "trace-root.h" -#endif - -#include "trace/mem.h" - -#if DATA_SIZE == 8 -#define SUFFIX q -#define USUFFIX q -#define DATA_TYPE uint64_t -#define SHIFT 3 -#elif DATA_SIZE == 4 -#define SUFFIX l -#define USUFFIX l -#define DATA_TYPE uint32_t -#define SHIFT 2 -#elif DATA_SIZE == 2 -#define SUFFIX w -#define USUFFIX uw -#define DATA_TYPE uint16_t -#define DATA_STYPE int16_t -#define SHIFT 1 -#elif DATA_SIZE == 1 -#define SUFFIX b -#define USUFFIX ub -#define DATA_TYPE uint8_t -#define DATA_STYPE int8_t -#define SHIFT 0 -#else -#error unsupported data size -#endif - -#if DATA_SIZE == 8 -#define RES_TYPE uint64_t -#else -#define RES_TYPE uint32_t -#endif - -static inline RES_TYPE -glue(glue(cpu_ld, USUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr) -{ - RES_TYPE ret; -#ifdef CODE_ACCESS - set_helper_retaddr(1); - ret = glue(glue(ld, USUFFIX), _p)(g2h(ptr)); - clear_helper_retaddr(); -#else - MemOp op = MO_TE | SHIFT; - uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - ret = glue(glue(ld, USUFFIX), _p)(g2h(ptr)); -#endif - return ret; -} - -#ifndef CODE_ACCESS -static inline RES_TYPE -glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - abi_ptr ptr, - uintptr_t retaddr) -{ - RES_TYPE ret; - set_helper_retaddr(retaddr); - ret = glue(glue(cpu_ld, USUFFIX), MEMSUFFIX)(env, ptr); - clear_helper_retaddr(); - return ret; -} -#endif - -#if DATA_SIZE <= 2 -static inline int -glue(glue(cpu_lds, SUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr) -{ - int ret; -#ifdef CODE_ACCESS - set_helper_retaddr(1); - ret = glue(glue(lds, SUFFIX), _p)(g2h(ptr)); - clear_helper_retaddr(); -#else - MemOp op = MO_TE | MO_SIGN | SHIFT; - uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - ret = glue(glue(lds, SUFFIX), _p)(g2h(ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -#endif - return ret; -} - -#ifndef CODE_ACCESS -static inline int -glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - abi_ptr ptr, - uintptr_t retaddr) -{ - int ret; - set_helper_retaddr(retaddr); - ret = glue(glue(cpu_lds, SUFFIX), MEMSUFFIX)(env, ptr); - clear_helper_retaddr(); - return ret; -} -#endif /* CODE_ACCESS */ -#endif /* DATA_SIZE <= 2 */ - -#ifndef CODE_ACCESS -static inline void -glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, abi_ptr ptr, - RES_TYPE v) -{ - MemOp op = MO_TE | SHIFT; - uint16_t meminfo = trace_mem_get_info(op, MMU_USER_IDX, true); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - glue(glue(st, SUFFIX), _p)(g2h(ptr), v); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); -} - -static inline void -glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - abi_ptr ptr, - RES_TYPE v, - uintptr_t retaddr) -{ - set_helper_retaddr(retaddr); - glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(env, ptr, v); - clear_helper_retaddr(); -} -#endif - -#undef RES_TYPE -#undef DATA_TYPE -#undef DATA_STYPE -#undef SUFFIX -#undef USUFFIX -#undef DATA_SIZE -#undef SHIFT diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -XXX,XX +XXX,XX @@ #include "translate-all.h" #include "exec/helper-proto.h" #include "qemu/atomic128.h" +#include "trace-root.h" +#include "trace/mem.h" #undef EAX #undef ECX @@ -XXX,XX +XXX,XX @@ int cpu_signal_handler(int host_signum, void *pinfo, /* The softmmu versions of these helpers are in cputlb.c. */ +uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = ldub_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr) +{ + int ret; + uint16_t meminfo = trace_mem_get_info(MO_SB, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = ldsb_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = lduw_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +int cpu_ldsw_data(CPUArchState *env, abi_ptr ptr) +{ + int ret; + uint16_t meminfo = trace_mem_get_info(MO_TESW, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = ldsw_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = ldl_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +uint64_t cpu_ldq_data(CPUArchState *env, abi_ptr ptr) +{ + uint64_t ret; + uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, false); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + ret = ldq_p(g2h(ptr)); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + return ret; +} + +uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + uint32_t ret; + + set_helper_retaddr(retaddr); + ret = cpu_ldub_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + int ret; + + set_helper_retaddr(retaddr); + ret = cpu_ldsb_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +uint32_t cpu_lduw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + uint32_t ret; + + set_helper_retaddr(retaddr); + ret = cpu_lduw_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +int cpu_ldsw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + int ret; + + set_helper_retaddr(retaddr); + ret = cpu_ldsw_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +uint32_t cpu_ldl_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + uint32_t ret; + + set_helper_retaddr(retaddr); + ret = cpu_ldl_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +uint64_t cpu_ldq_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) +{ + uint64_t ret; + + set_helper_retaddr(retaddr); + ret = cpu_ldq_data(env, ptr); + clear_helper_retaddr(); + return ret; +} + +void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val) +{ + uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, true); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + stb_p(g2h(ptr), val); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); +} + +void cpu_stw_data(CPUArchState *env, abi_ptr ptr, uint32_t val) +{ + uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, true); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + stw_p(g2h(ptr), val); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); +} + +void cpu_stl_data(CPUArchState *env, abi_ptr ptr, uint32_t val) +{ + uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, true); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + stl_p(g2h(ptr), val); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); +} + +void cpu_stq_data(CPUArchState *env, abi_ptr ptr, uint64_t val) +{ + uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, true); + + trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + stq_p(g2h(ptr), val); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); +} + +void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr) +{ + set_helper_retaddr(retaddr); + cpu_stb_data(env, ptr, val); + clear_helper_retaddr(); +} + +void cpu_stw_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr) +{ + set_helper_retaddr(retaddr); + cpu_stw_data(env, ptr, val); + clear_helper_retaddr(); +} + +void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr, + uint32_t val, uintptr_t retaddr) +{ + set_helper_retaddr(retaddr); + cpu_stl_data(env, ptr, val); + clear_helper_retaddr(); +} + +void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr, + uint64_t val, uintptr_t retaddr) +{ + set_helper_retaddr(retaddr); + cpu_stq_data(env, ptr, val); + clear_helper_retaddr(); +} + +uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + + set_helper_retaddr(1); + ret = ldub_p(g2h(ptr)); + clear_helper_retaddr(); + return ret; +} + +uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + + set_helper_retaddr(1); + ret = lduw_p(g2h(ptr)); + clear_helper_retaddr(); + return ret; +} + +uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr ptr) +{ + uint32_t ret; + + set_helper_retaddr(1); + ret = ldl_p(g2h(ptr)); + clear_helper_retaddr(); + return ret; +} + +uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr) +{ + uint64_t ret; + + set_helper_retaddr(1); + ret = ldq_p(g2h(ptr)); + clear_helper_retaddr(); + return ret; +} + /* Do not allow unaligned operations to proceed. Return the host address. */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, int size, uintptr_t retaddr) -- 2.20.1 The functions generated by these macros are unused. Cc: Chris Wulff <crwulff@gmail.com> Cc: Marek Vasut <marex@denx.de> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/nios2/cpu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/nios2/cpu.h b/target/nios2/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.h +++ b/target/nios2/cpu.h @@ -XXX,XX +XXX,XX @@ void do_nios2_semihosting(CPUNios2State *env); #define CPU_SAVE_VERSION 1 /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_SUPERVISOR_IDX 0 #define MMU_USER_IDX 1 -- 2.20.1 The functions generated by these macros are unused. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/alpha/cpu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/alpha/cpu.h b/target/alpha/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.h +++ b/target/alpha/cpu.h @@ -XXX,XX +XXX,XX @@ enum { PALcode cheats and usees the KSEG mapping for its code+data rather than physical addresses. */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_KERNEL_IDX 0 #define MMU_USER_IDX 1 #define MMU_PHYS_IDX 2 -- 2.20.1 The functions generated by these macros are unused. Cc: Edgar E. Iglesias <edgar.iglesias@gmail.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/cris/cpu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/cris/cpu.h b/target/cris/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/cris/cpu.h +++ b/target/cris/cpu.h @@ -XXX,XX +XXX,XX @@ enum { #define cpu_signal_handler cpu_cris_signal_handler /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_USER_IDX 1 static inline int cpu_mmu_index (CPUCRISState *env, bool ifetch) { -- 2.20.1 The functions generated by these macros are unused. Cc: Eduardo Habkost <ehabkost@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/i386/cpu.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/target/i386/cpu.h b/target/i386/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -XXX,XX +XXX,XX @@ uint64_t cpu_get_tsc(CPUX86State *env); #define cpu_list x86_cpu_list /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _ksmap -#define MMU_MODE1_SUFFIX _user -#define MMU_MODE2_SUFFIX _knosmap /* SMAP disabled or CPL<3 && AC=1 */ #define MMU_KSMAP_IDX 0 #define MMU_USER_IDX 1 #define MMU_KNOSMAP_IDX 2 -- 2.20.1 The functions generated by these macros are unused. Cc: Edgar E. Iglesias <edgar.iglesias@gmail.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/microblaze/cpu.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/target/microblaze/cpu.h b/target/microblaze/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.h +++ b/target/microblaze/cpu.h @@ -XXX,XX +XXX,XX @@ int cpu_mb_signal_handler(int host_signum, void *pinfo, #define cpu_signal_handler cpu_mb_signal_handler /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _nommu -#define MMU_MODE1_SUFFIX _kernel -#define MMU_MODE2_SUFFIX _user #define MMU_NOMMU_IDX 0 #define MMU_KERNEL_IDX 1 #define MMU_USER_IDX 2 -- 2.20.1 The functions generated by these macros are unused. Cc: Aurelien Jarno <aurelien@aurel32.net> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sh4/cpu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.h +++ b/target/sh4/cpu.h @@ -XXX,XX +XXX,XX @@ void cpu_load_tlb(CPUSH4State * env); #define cpu_list sh4_cpu_list /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_USER_IDX 1 static inline int cpu_mmu_index (CPUSH4State *env, bool ifetch) { -- 2.20.1 The functions generated by these macros are unused. Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/unicore32/cpu.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/unicore32/cpu.h b/target/unicore32/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/unicore32/cpu.h +++ b/target/unicore32/cpu.h @@ -XXX,XX +XXX,XX @@ void cpu_asr_write(CPUUniCore32State *env1, target_ulong val, target_ulong mask) int uc32_cpu_signal_handler(int host_signum, void *pinfo, void *puc); /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_USER_IDX 1 static inline int cpu_mmu_index(CPUUniCore32State *env, bool ifetch) { -- 2.20.1 The functions generated by these macros are unused. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Max Filippov <jcmvbkbc@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/xtensa/cpu.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/target/xtensa/cpu.h b/target/xtensa/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.h +++ b/target/xtensa/cpu.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t xtensa_replicate_windowstart(CPUXtensaState *env) } /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _ring0 -#define MMU_MODE1_SUFFIX _ring1 -#define MMU_MODE2_SUFFIX _ring2 -#define MMU_MODE3_SUFFIX _ring3 #define MMU_USER_IDX 3 static inline int cpu_mmu_index(CPUXtensaState *env, bool ifetch) -- 2.20.1 The generated *_user functions are unused. The *_kernel functions have a couple of users in op_helper.c; use *_mmuidx_ra instead, with MMU_KERNEL_IDX. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Use *_mmuidx_ra directly, without intermediate macros. --- target/m68k/cpu.h | 2 -- target/m68k/op_helper.c | 77 +++++++++++++++++++++++++---------------- 2 files changed, 47 insertions(+), 32 deletions(-) diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.h +++ b/target/m68k/cpu.h @@ -XXX,XX +XXX,XX @@ enum { #define cpu_list m68k_cpu_list /* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _user #define MMU_KERNEL_IDX 0 #define MMU_USER_IDX 1 static inline int cpu_mmu_index (CPUM68KState *env, bool ifetch) diff --git a/target/m68k/op_helper.c b/target/m68k/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/op_helper.c +++ b/target/m68k/op_helper.c @@ -XXX,XX +XXX,XX @@ static void cf_rte(CPUM68KState *env) uint32_t fmt; sp = env->aregs[7]; - fmt = cpu_ldl_kernel(env, sp); - env->pc = cpu_ldl_kernel(env, sp + 4); + fmt = cpu_ldl_mmuidx_ra(env, sp, MMU_KERNEL_IDX, 0); + env->pc = cpu_ldl_mmuidx_ra(env, sp + 4, MMU_KERNEL_IDX, 0); sp |= (fmt >> 28) & 3; env->aregs[7] = sp + 8; @@ -XXX,XX +XXX,XX @@ static void m68k_rte(CPUM68KState *env) sp = env->aregs[7]; throwaway: - sr = cpu_lduw_kernel(env, sp); + sr = cpu_lduw_mmuidx_ra(env, sp, MMU_KERNEL_IDX, 0); sp += 2; - env->pc = cpu_ldl_kernel(env, sp); + env->pc = cpu_ldl_mmuidx_ra(env, sp, MMU_KERNEL_IDX, 0); sp += 4; if (m68k_feature(env, M68K_FEATURE_QUAD_MULDIV)) { /* all except 68000 */ - fmt = cpu_lduw_kernel(env, sp); + fmt = cpu_lduw_mmuidx_ra(env, sp, MMU_KERNEL_IDX, 0); sp += 2; switch (fmt >> 12) { case 0: @@ -XXX,XX +XXX,XX @@ static void cf_interrupt_all(CPUM68KState *env, int is_hw) /* ??? This could cause MMU faults. */ sp &= ~3; sp -= 4; - cpu_stl_kernel(env, sp, retaddr); + cpu_stl_mmuidx_ra(env, sp, retaddr, MMU_KERNEL_IDX, 0); sp -= 4; - cpu_stl_kernel(env, sp, fmt); + cpu_stl_mmuidx_ra(env, sp, fmt, MMU_KERNEL_IDX, 0); env->aregs[7] = sp; /* Jump to vector. */ - env->pc = cpu_ldl_kernel(env, env->vbr + vector); + env->pc = cpu_ldl_mmuidx_ra(env, env->vbr + vector, MMU_KERNEL_IDX, 0); } static inline void do_stack_frame(CPUM68KState *env, uint32_t *sp, @@ -XXX,XX +XXX,XX @@ static inline void do_stack_frame(CPUM68KState *env, uint32_t *sp, switch (format) { case 4: *sp -= 4; - cpu_stl_kernel(env, *sp, env->pc); + cpu_stl_mmuidx_ra(env, *sp, env->pc, MMU_KERNEL_IDX, 0); *sp -= 4; - cpu_stl_kernel(env, *sp, addr); + cpu_stl_mmuidx_ra(env, *sp, addr, MMU_KERNEL_IDX, 0); break; case 3: case 2: *sp -= 4; - cpu_stl_kernel(env, *sp, addr); + cpu_stl_mmuidx_ra(env, *sp, addr, MMU_KERNEL_IDX, 0); break; } *sp -= 2; - cpu_stw_kernel(env, *sp, (format << 12) + (cs->exception_index << 2)); + cpu_stw_mmuidx_ra(env, *sp, (format << 12) + (cs->exception_index << 2), + MMU_KERNEL_IDX, 0); } *sp -= 4; - cpu_stl_kernel(env, *sp, retaddr); + cpu_stl_mmuidx_ra(env, *sp, retaddr, MMU_KERNEL_IDX, 0); *sp -= 2; - cpu_stw_kernel(env, *sp, sr); + cpu_stw_mmuidx_ra(env, *sp, sr, MMU_KERNEL_IDX, 0); } static void m68k_interrupt_all(CPUM68KState *env, int is_hw) @@ -XXX,XX +XXX,XX @@ static void m68k_interrupt_all(CPUM68KState *env, int is_hw) cpu_abort(cs, "DOUBLE MMU FAULT\n"); } env->mmu.fault = true; + /* push data 3 */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* push data 3 */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* push data 2 */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* push data 2 */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* push data 1 */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* push data 1 */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 1 / push data 0 */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* write back 1 / push data 0 */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 1 address */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* write back 1 address */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 2 data */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* write back 2 data */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 2 address */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* write back 2 address */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 3 data */ sp -= 4; - cpu_stl_kernel(env, sp, 0); /* write back 3 data */ + cpu_stl_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 3 address */ sp -= 4; - cpu_stl_kernel(env, sp, env->mmu.ar); /* write back 3 address */ + cpu_stl_mmuidx_ra(env, sp, env->mmu.ar, MMU_KERNEL_IDX, 0); + /* fault address */ sp -= 4; - cpu_stl_kernel(env, sp, env->mmu.ar); /* fault address */ + cpu_stl_mmuidx_ra(env, sp, env->mmu.ar, MMU_KERNEL_IDX, 0); + /* write back 1 status */ sp -= 2; - cpu_stw_kernel(env, sp, 0); /* write back 1 status */ + cpu_stw_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 2 status */ sp -= 2; - cpu_stw_kernel(env, sp, 0); /* write back 2 status */ + cpu_stw_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* write back 3 status */ sp -= 2; - cpu_stw_kernel(env, sp, 0); /* write back 3 status */ + cpu_stw_mmuidx_ra(env, sp, 0, MMU_KERNEL_IDX, 0); + /* special status word */ sp -= 2; - cpu_stw_kernel(env, sp, env->mmu.ssw); /* special status word */ + cpu_stw_mmuidx_ra(env, sp, env->mmu.ssw, MMU_KERNEL_IDX, 0); + /* effective address */ sp -= 4; - cpu_stl_kernel(env, sp, env->mmu.ar); /* effective address */ + cpu_stl_mmuidx_ra(env, sp, env->mmu.ar, MMU_KERNEL_IDX, 0); + do_stack_frame(env, &sp, 7, oldsr, 0, retaddr); env->mmu.fault = false; if (qemu_loglevel_mask(CPU_LOG_INT)) { @@ -XXX,XX +XXX,XX @@ static void m68k_interrupt_all(CPUM68KState *env, int is_hw) env->aregs[7] = sp; /* Jump to vector. */ - env->pc = cpu_ldl_kernel(env, env->vbr + vector); + env->pc = cpu_ldl_mmuidx_ra(env, env->vbr + vector, MMU_KERNEL_IDX, 0); } static void do_interrupt_all(CPUM68KState *env, int is_hw) -- 2.20.1 The separate suffixed functions were used to construct some do_##insn function switched on mmu_idx. The interface is exactly identical to the *_mmuidx_ra functions. Replace them directly and remove the constructions. Cc: Aurelien Jarno <aurelien@aurel32.net> Cc: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/mips/cpu.h | 4 - target/mips/op_helper.c | 182 +++++++++++++--------------------------- 2 files changed, 60 insertions(+), 126 deletions(-) diff --git a/target/mips/cpu.h b/target/mips/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/cpu.h +++ b/target/mips/cpu.h @@ -XXX,XX +XXX,XX @@ extern uint32_t cpu_rddsp(uint32_t mask_num, CPUMIPSState *env); * MMU modes definitions. We carefully match the indices with our * hflags layout. */ -#define MMU_MODE0_SUFFIX _kernel -#define MMU_MODE1_SUFFIX _super -#define MMU_MODE2_SUFFIX _user -#define MMU_MODE3_SUFFIX _error #define MMU_USER_IDX 2 static inline int hflags_mmu_index(uint32_t hflags) diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/op_helper.c +++ b/target/mips/op_helper.c @@ -XXX,XX +XXX,XX @@ static void raise_exception(CPUMIPSState *env, uint32_t exception) do_raise_exception(env, exception, 0); } -#if defined(CONFIG_USER_ONLY) -#define HELPER_LD(name, insn, type) \ -static inline type do_##name(CPUMIPSState *env, target_ulong addr, \ - int mem_idx, uintptr_t retaddr) \ -{ \ - return (type) cpu_##insn##_data_ra(env, addr, retaddr); \ -} -#else -#define HELPER_LD(name, insn, type) \ -static inline type do_##name(CPUMIPSState *env, target_ulong addr, \ - int mem_idx, uintptr_t retaddr) \ -{ \ - switch (mem_idx) { \ - case 0: return (type) cpu_##insn##_kernel_ra(env, addr, retaddr); \ - case 1: return (type) cpu_##insn##_super_ra(env, addr, retaddr); \ - default: \ - case 2: return (type) cpu_##insn##_user_ra(env, addr, retaddr); \ - case 3: return (type) cpu_##insn##_error_ra(env, addr, retaddr); \ - } \ -} -#endif -HELPER_LD(lw, ldl, int32_t) -#if defined(TARGET_MIPS64) -HELPER_LD(ld, ldq, int64_t) -#endif -#undef HELPER_LD - -#if defined(CONFIG_USER_ONLY) -#define HELPER_ST(name, insn, type) \ -static inline void do_##name(CPUMIPSState *env, target_ulong addr, \ - type val, int mem_idx, uintptr_t retaddr) \ -{ \ - cpu_##insn##_data_ra(env, addr, val, retaddr); \ -} -#else -#define HELPER_ST(name, insn, type) \ -static inline void do_##name(CPUMIPSState *env, target_ulong addr, \ - type val, int mem_idx, uintptr_t retaddr) \ -{ \ - switch (mem_idx) { \ - case 0: \ - cpu_##insn##_kernel_ra(env, addr, val, retaddr); \ - break; \ - case 1: \ - cpu_##insn##_super_ra(env, addr, val, retaddr); \ - break; \ - default: \ - case 2: \ - cpu_##insn##_user_ra(env, addr, val, retaddr); \ - break; \ - case 3: \ - cpu_##insn##_error_ra(env, addr, val, retaddr); \ - break; \ - } \ -} -#endif -HELPER_ST(sb, stb, uint8_t) -HELPER_ST(sw, stl, uint32_t) -#if defined(TARGET_MIPS64) -HELPER_ST(sd, stq, uint64_t) -#endif -#undef HELPER_ST - /* 64 bits arithmetic for 32 bits hosts */ static inline uint64_t get_HILO(CPUMIPSState *env) { @@ -XXX,XX +XXX,XX @@ target_ulong helper_##name(CPUMIPSState *env, target_ulong arg, int mem_idx) \ } \ env->CP0_LLAddr = do_translate_address(env, arg, 0, GETPC()); \ env->lladdr = arg; \ - env->llval = do_##insn(env, arg, mem_idx, GETPC()); \ + env->llval = cpu_##insn##_mmuidx_ra(env, arg, mem_idx, GETPC()); \ return env->llval; \ } -HELPER_LD_ATOMIC(ll, lw, 0x3) +HELPER_LD_ATOMIC(ll, ldl, 0x3) #ifdef TARGET_MIPS64 -HELPER_LD_ATOMIC(lld, ld, 0x7) +HELPER_LD_ATOMIC(lld, ldq, 0x7) #endif #undef HELPER_LD_ATOMIC #endif @@ -XXX,XX +XXX,XX @@ HELPER_LD_ATOMIC(lld, ld, 0x7) void helper_swl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, int mem_idx) { - do_sb(env, arg2, (uint8_t)(arg1 >> 24), mem_idx, GETPC()); + cpu_stb_mmuidx_ra(env, arg2, (uint8_t)(arg1 >> 24), mem_idx, GETPC()); if (GET_LMASK(arg2) <= 2) { - do_sb(env, GET_OFFSET(arg2, 1), (uint8_t)(arg1 >> 16), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 1), (uint8_t)(arg1 >> 16), + mem_idx, GETPC()); } if (GET_LMASK(arg2) <= 1) { - do_sb(env, GET_OFFSET(arg2, 2), (uint8_t)(arg1 >> 8), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 2), (uint8_t)(arg1 >> 8), + mem_idx, GETPC()); } if (GET_LMASK(arg2) == 0) { - do_sb(env, GET_OFFSET(arg2, 3), (uint8_t)arg1, mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 3), (uint8_t)arg1, + mem_idx, GETPC()); } } void helper_swr(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, int mem_idx) { - do_sb(env, arg2, (uint8_t)arg1, mem_idx, GETPC()); + cpu_stb_mmuidx_ra(env, arg2, (uint8_t)arg1, mem_idx, GETPC()); if (GET_LMASK(arg2) >= 1) { - do_sb(env, GET_OFFSET(arg2, -1), (uint8_t)(arg1 >> 8), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -1), (uint8_t)(arg1 >> 8), + mem_idx, GETPC()); } if (GET_LMASK(arg2) >= 2) { - do_sb(env, GET_OFFSET(arg2, -2), (uint8_t)(arg1 >> 16), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -2), (uint8_t)(arg1 >> 16), + mem_idx, GETPC()); } if (GET_LMASK(arg2) == 3) { - do_sb(env, GET_OFFSET(arg2, -3), (uint8_t)(arg1 >> 24), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -3), (uint8_t)(arg1 >> 24), + mem_idx, GETPC()); } } @@ -XXX,XX +XXX,XX @@ void helper_swr(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, void helper_sdl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, int mem_idx) { - do_sb(env, arg2, (uint8_t)(arg1 >> 56), mem_idx, GETPC()); + cpu_stb_mmuidx_ra(env, arg2, (uint8_t)(arg1 >> 56), mem_idx, GETPC()); if (GET_LMASK64(arg2) <= 6) { - do_sb(env, GET_OFFSET(arg2, 1), (uint8_t)(arg1 >> 48), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 1), (uint8_t)(arg1 >> 48), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 5) { - do_sb(env, GET_OFFSET(arg2, 2), (uint8_t)(arg1 >> 40), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 2), (uint8_t)(arg1 >> 40), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 4) { - do_sb(env, GET_OFFSET(arg2, 3), (uint8_t)(arg1 >> 32), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 3), (uint8_t)(arg1 >> 32), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 3) { - do_sb(env, GET_OFFSET(arg2, 4), (uint8_t)(arg1 >> 24), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 4), (uint8_t)(arg1 >> 24), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 2) { - do_sb(env, GET_OFFSET(arg2, 5), (uint8_t)(arg1 >> 16), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 5), (uint8_t)(arg1 >> 16), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 1) { - do_sb(env, GET_OFFSET(arg2, 6), (uint8_t)(arg1 >> 8), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 6), (uint8_t)(arg1 >> 8), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) <= 0) { - do_sb(env, GET_OFFSET(arg2, 7), (uint8_t)arg1, mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, 7), (uint8_t)arg1, + mem_idx, GETPC()); } } void helper_sdr(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, int mem_idx) { - do_sb(env, arg2, (uint8_t)arg1, mem_idx, GETPC()); + cpu_stb_mmuidx_ra(env, arg2, (uint8_t)arg1, mem_idx, GETPC()); if (GET_LMASK64(arg2) >= 1) { - do_sb(env, GET_OFFSET(arg2, -1), (uint8_t)(arg1 >> 8), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -1), (uint8_t)(arg1 >> 8), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) >= 2) { - do_sb(env, GET_OFFSET(arg2, -2), (uint8_t)(arg1 >> 16), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -2), (uint8_t)(arg1 >> 16), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) >= 3) { - do_sb(env, GET_OFFSET(arg2, -3), (uint8_t)(arg1 >> 24), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -3), (uint8_t)(arg1 >> 24), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) >= 4) { - do_sb(env, GET_OFFSET(arg2, -4), (uint8_t)(arg1 >> 32), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -4), (uint8_t)(arg1 >> 32), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) >= 5) { - do_sb(env, GET_OFFSET(arg2, -5), (uint8_t)(arg1 >> 40), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -5), (uint8_t)(arg1 >> 40), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) >= 6) { - do_sb(env, GET_OFFSET(arg2, -6), (uint8_t)(arg1 >> 48), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -6), (uint8_t)(arg1 >> 48), + mem_idx, GETPC()); } if (GET_LMASK64(arg2) == 7) { - do_sb(env, GET_OFFSET(arg2, -7), (uint8_t)(arg1 >> 56), mem_idx, - GETPC()); + cpu_stb_mmuidx_ra(env, GET_OFFSET(arg2, -7), (uint8_t)(arg1 >> 56), + mem_idx, GETPC()); } } #endif /* TARGET_MIPS64 */ @@ -XXX,XX +XXX,XX @@ void helper_lwm(CPUMIPSState *env, target_ulong addr, target_ulong reglist, for (i = 0; i < base_reglist; i++) { env->active_tc.gpr[multiple_regs[i]] = - (target_long)do_lw(env, addr, mem_idx, GETPC()); + (target_long)cpu_ldl_mmuidx_ra(env, addr, mem_idx, GETPC()); addr += 4; } } if (do_r31) { - env->active_tc.gpr[31] = (target_long)do_lw(env, addr, mem_idx, - GETPC()); + env->active_tc.gpr[31] = + (target_long)cpu_ldl_mmuidx_ra(env, addr, mem_idx, GETPC()); } } @@ -XXX,XX +XXX,XX @@ void helper_swm(CPUMIPSState *env, target_ulong addr, target_ulong reglist, target_ulong i; for (i = 0; i < base_reglist; i++) { - do_sw(env, addr, env->active_tc.gpr[multiple_regs[i]], mem_idx, - GETPC()); + cpu_stw_mmuidx_ra(env, addr, env->active_tc.gpr[multiple_regs[i]], + mem_idx, GETPC()); addr += 4; } } if (do_r31) { - do_sw(env, addr, env->active_tc.gpr[31], mem_idx, GETPC()); + cpu_stw_mmuidx_ra(env, addr, env->active_tc.gpr[31], mem_idx, GETPC()); } } @@ -XXX,XX +XXX,XX @@ void helper_ldm(CPUMIPSState *env, target_ulong addr, target_ulong reglist, target_ulong i; for (i = 0; i < base_reglist; i++) { - env->active_tc.gpr[multiple_regs[i]] = do_ld(env, addr, mem_idx, - GETPC()); + env->active_tc.gpr[multiple_regs[i]] = + cpu_ldq_mmuidx_ra(env, addr, mem_idx, GETPC()); addr += 8; } } if (do_r31) { - env->active_tc.gpr[31] = do_ld(env, addr, mem_idx, GETPC()); + env->active_tc.gpr[31] = + cpu_ldq_mmuidx_ra(env, addr, mem_idx, GETPC()); } } @@ -XXX,XX +XXX,XX @@ void helper_sdm(CPUMIPSState *env, target_ulong addr, target_ulong reglist, target_ulong i; for (i = 0; i < base_reglist; i++) { - do_sd(env, addr, env->active_tc.gpr[multiple_regs[i]], mem_idx, - GETPC()); + cpu_stq_mmuidx_ra(env, addr, env->active_tc.gpr[multiple_regs[i]], + mem_idx, GETPC()); addr += 8; } } if (do_r31) { - do_sd(env, addr, env->active_tc.gpr[31], mem_idx, GETPC()); + cpu_stq_mmuidx_ra(env, addr, env->active_tc.gpr[31], mem_idx, GETPC()); } } #endif -- 2.20.1 The generated functions aside from *_real are unused. The *_real functions have a couple of users in mem_helper.c; use *_mmuidx_ra instead, with MMU_REAL_IDX. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Use *_mmuidx_ra directly, without intermediate macros. --- target/s390x/cpu.h | 5 ----- target/s390x/mem_helper.c | 10 +++++----- 2 files changed, 5 insertions(+), 10 deletions(-) diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -XXX,XX +XXX,XX @@ #define TARGET_INSN_START_EXTRA_WORDS 2 -#define MMU_MODE0_SUFFIX _primary -#define MMU_MODE1_SUFFIX _secondary -#define MMU_MODE2_SUFFIX _home -#define MMU_MODE3_SUFFIX _real - #define MMU_USER_IDX 0 #define S390_MAX_CPUS 248 diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/mem_helper.c +++ b/target/s390x/mem_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(testblock)(CPUS390XState *env, uint64_t real_addr) real_addr = wrap_address(env, real_addr) & TARGET_PAGE_MASK; for (i = 0; i < TARGET_PAGE_SIZE; i += 8) { - cpu_stq_real_ra(env, real_addr + i, 0, ra); + cpu_stq_mmuidx_ra(env, real_addr + i, 0, MMU_REAL_IDX, ra); } return 0; @@ -XXX,XX +XXX,XX @@ void HELPER(idte)(CPUS390XState *env, uint64_t r1, uint64_t r2, uint32_t m4) for (i = 0; i < entries; i++) { /* addresses are not wrapped in 24/31bit mode but table index is */ raddr = table + ((index + i) & 0x7ff) * sizeof(entry); - entry = cpu_ldq_real_ra(env, raddr, ra); + entry = cpu_ldq_mmuidx_ra(env, raddr, MMU_REAL_IDX, ra); if (!(entry & REGION_ENTRY_I)) { /* we are allowed to not store if already invalid */ entry |= REGION_ENTRY_I; - cpu_stq_real_ra(env, raddr, entry, ra); + cpu_stq_mmuidx_ra(env, raddr, entry, MMU_REAL_IDX, ra); } } } @@ -XXX,XX +XXX,XX @@ void HELPER(ipte)(CPUS390XState *env, uint64_t pto, uint64_t vaddr, pte_addr += VADDR_PAGE_TX(vaddr) * 8; /* Mark the page table entry as invalid */ - pte = cpu_ldq_real_ra(env, pte_addr, ra); + pte = cpu_ldq_mmuidx_ra(env, pte_addr, MMU_REAL_IDX, ra); pte |= PAGE_ENTRY_I; - cpu_stq_real_ra(env, pte_addr, pte, ra); + cpu_stq_mmuidx_ra(env, pte_addr, pte, MMU_REAL_IDX, ra); /* XXX we exploit the fact that Linux passes the exact virtual address here - it's not obliged to! */ -- 2.20.1 There are only two uses. Within dcbz_common, the local variable mmu_idx already contains the epid computation, and we can avoid repeating it for the store. Within helper_icbiep, the usage is trivially expanded using PPC_TLB_EPID_LOAD. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/ppc/cpu.h | 2 -- target/ppc/mem_helper.c | 11 ++--------- 2 files changed, 2 insertions(+), 11 deletions(-) diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -XXX,XX +XXX,XX @@ struct ppc_radix_page_info { * + real/paged mode combinations. The other two modes are for * external PID load/store. */ -#define MMU_MODE8_SUFFIX _epl -#define MMU_MODE9_SUFFIX _eps #define PPC_TLB_EPID_LOAD 8 #define PPC_TLB_EPID_STORE 9 diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/mem_helper.c +++ b/target/ppc/mem_helper.c @@ -XXX,XX +XXX,XX @@ static void dcbz_common(CPUPPCState *env, target_ulong addr, } else { /* Slow path */ for (i = 0; i < dcbz_size; i += 8) { - if (epid) { -#if !defined(CONFIG_USER_ONLY) - /* Does not make sense on USER_ONLY config */ - cpu_stq_eps_ra(env, addr + i, 0, retaddr); -#endif - } else { - cpu_stq_data_ra(env, addr + i, 0, retaddr); - } + cpu_stq_mmuidx_ra(env, addr + i, 0, mmu_idx, retaddr); } } } @@ -XXX,XX +XXX,XX @@ void helper_icbiep(CPUPPCState *env, target_ulong addr) #if !defined(CONFIG_USER_ONLY) /* See comments above */ addr &= ~(env->dcache_line_size - 1); - cpu_ldl_epl_ra(env, addr, GETPC()); + cpu_ldl_mmuidx_ra(env, addr, PPC_TLB_EPID_LOAD, GETPC()); #endif } -- 2.20.1 All users have now been converted to cpu_*_mmuidx_ra. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 230 ---------------------------------------- 1 file changed, 230 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, int mmu_idx, uintptr_t retaddr); -#ifdef MMU_MODE0_SUFFIX -#define CPU_MMU_INDEX 0 -#define MEMSUFFIX MMU_MODE0_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif - -#if (NB_MMU_MODES >= 2) && defined(MMU_MODE1_SUFFIX) -#define CPU_MMU_INDEX 1 -#define MEMSUFFIX MMU_MODE1_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif - -#if (NB_MMU_MODES >= 3) && defined(MMU_MODE2_SUFFIX) - -#define CPU_MMU_INDEX 2 -#define MEMSUFFIX MMU_MODE2_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 3) */ - -#if (NB_MMU_MODES >= 4) && defined(MMU_MODE3_SUFFIX) - -#define CPU_MMU_INDEX 3 -#define MEMSUFFIX MMU_MODE3_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 4) */ - -#if (NB_MMU_MODES >= 5) && defined(MMU_MODE4_SUFFIX) - -#define CPU_MMU_INDEX 4 -#define MEMSUFFIX MMU_MODE4_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 5) */ - -#if (NB_MMU_MODES >= 6) && defined(MMU_MODE5_SUFFIX) - -#define CPU_MMU_INDEX 5 -#define MEMSUFFIX MMU_MODE5_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 6) */ - -#if (NB_MMU_MODES >= 7) && defined(MMU_MODE6_SUFFIX) - -#define CPU_MMU_INDEX 6 -#define MEMSUFFIX MMU_MODE6_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 7) */ - -#if (NB_MMU_MODES >= 8) && defined(MMU_MODE7_SUFFIX) - -#define CPU_MMU_INDEX 7 -#define MEMSUFFIX MMU_MODE7_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 8) */ - -#if (NB_MMU_MODES >= 9) && defined(MMU_MODE8_SUFFIX) - -#define CPU_MMU_INDEX 8 -#define MEMSUFFIX MMU_MODE8_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 9) */ - -#if (NB_MMU_MODES >= 10) && defined(MMU_MODE9_SUFFIX) - -#define CPU_MMU_INDEX 9 -#define MEMSUFFIX MMU_MODE9_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 10) */ - -#if (NB_MMU_MODES >= 11) && defined(MMU_MODE10_SUFFIX) - -#define CPU_MMU_INDEX 10 -#define MEMSUFFIX MMU_MODE10_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 11) */ - -#if (NB_MMU_MODES >= 12) && defined(MMU_MODE11_SUFFIX) - -#define CPU_MMU_INDEX 11 -#define MEMSUFFIX MMU_MODE11_SUFFIX -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX -#endif /* (NB_MMU_MODES >= 12) */ - -#if (NB_MMU_MODES > 12) -#error "NB_MMU_MODES > 12 is not supported for now" -#endif /* (NB_MMU_MODES > 12) */ - /* these access are slower, they must be as rare as possible */ #define CPU_MMU_INDEX (cpu_mmu_index(env, false)) #define MEMSUFFIX _data -- 2.20.1 Reduce the amount of preprocessor obfuscation by expanding the text of each of the functions generated. The result is only slightly smaller than the original. Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 67 +++++++----------- include/exec/cpu_ldst_template.h | 117 ------------------------------- accel/tcg/cputlb.c | 107 +++++++++++++++++++++++++++- 3 files changed, 130 insertions(+), 161 deletions(-) delete mode 100644 include/exec/cpu_ldst_template.h diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ typedef target_ulong abi_ptr; #define TARGET_ABI_FMT_ptr TARGET_ABI_FMT_lx #endif -#if defined(CONFIG_USER_ONLY) - -extern __thread uintptr_t helper_retaddr; - -static inline void set_helper_retaddr(uintptr_t ra) -{ - helper_retaddr = ra; - /* - * Ensure that this write is visible to the SIGSEGV handler that - * may be invoked due to a subsequent invalid memory operation. - */ - signal_barrier(); -} - -static inline void clear_helper_retaddr(void) -{ - /* - * Ensure that previous memory operations have succeeded before - * removing the data visible to the signal handler. - */ - signal_barrier(); - helper_retaddr = 0; -} - -/* In user-only mode we provide only the _code and _data accessors. */ - uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr); uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr); uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr); @@ -XXX,XX +XXX,XX @@ void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr, void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr, uint64_t val, uintptr_t retaddr); +#if defined(CONFIG_USER_ONLY) + +extern __thread uintptr_t helper_retaddr; + +static inline void set_helper_retaddr(uintptr_t ra) +{ + helper_retaddr = ra; + /* + * Ensure that this write is visible to the SIGSEGV handler that + * may be invoked due to a subsequent invalid memory operation. + */ + signal_barrier(); +} + +static inline void clear_helper_retaddr(void) +{ + /* + * Ensure that previous memory operations have succeeded before + * removing the data visible to the signal handler. + */ + signal_barrier(); + helper_retaddr = 0; +} + /* * Provide the same *_mmuidx_ra interface as for softmmu. * The mmu_idx argument is ignored. @@ -XXX,XX +XXX,XX @@ void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, int mmu_idx, uintptr_t retaddr); -/* these access are slower, they must be as rare as possible */ -#define CPU_MMU_INDEX (cpu_mmu_index(env, false)) -#define MEMSUFFIX _data -#define DATA_SIZE 1 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 2 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 4 -#include "exec/cpu_ldst_template.h" - -#define DATA_SIZE 8 -#include "exec/cpu_ldst_template.h" -#undef CPU_MMU_INDEX -#undef MEMSUFFIX - #endif /* defined(CONFIG_USER_ONLY) */ uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr); diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/exec/cpu_ldst_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Software MMU support - * - * Generate inline load/store functions for one MMU mode and data - * size. - * - * Generate a store function as well as signed and unsigned loads. - * - * Not used directly but included from cpu_ldst.h. - * - * Copyright (c) 2003 Fabrice Bellard - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library 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 - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -#if DATA_SIZE == 8 -#define SUFFIX q -#define USUFFIX q -#define DATA_TYPE uint64_t -#define SHIFT 3 -#elif DATA_SIZE == 4 -#define SUFFIX l -#define USUFFIX l -#define DATA_TYPE uint32_t -#define SHIFT 2 -#elif DATA_SIZE == 2 -#define SUFFIX w -#define USUFFIX uw -#define DATA_TYPE uint16_t -#define DATA_STYPE int16_t -#define SHIFT 1 -#elif DATA_SIZE == 1 -#define SUFFIX b -#define USUFFIX ub -#define DATA_TYPE uint8_t -#define DATA_STYPE int8_t -#define SHIFT 0 -#else -#error unsupported data size -#endif - -#if DATA_SIZE == 8 -#define RES_TYPE uint64_t -#else -#define RES_TYPE uint32_t -#endif - -/* generic load/store macros */ - -static inline RES_TYPE -glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - target_ulong ptr, - uintptr_t retaddr) -{ - return glue(glue(cpu_ld, USUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, - retaddr); -} - -static inline RES_TYPE -glue(glue(cpu_ld, USUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr) -{ - return glue(glue(cpu_ld, USUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, 0); -} - -#if DATA_SIZE <= 2 -static inline int -glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - target_ulong ptr, - uintptr_t retaddr) -{ - return glue(glue(cpu_lds, SUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, - retaddr); -} - -static inline int -glue(glue(cpu_lds, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr) -{ - return glue(glue(cpu_lds, SUFFIX), _mmuidx_ra)(env, ptr, CPU_MMU_INDEX, 0); -} -#endif - -/* generic store macro */ - -static inline void -glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env, - target_ulong ptr, - RES_TYPE v, uintptr_t retaddr) -{ - glue(glue(cpu_st, SUFFIX), _mmuidx_ra)(env, ptr, v, CPU_MMU_INDEX, - retaddr); -} - -static inline void -glue(glue(cpu_st, SUFFIX), MEMSUFFIX)(CPUArchState *env, target_ulong ptr, - RES_TYPE v) -{ - glue(glue(cpu_st, SUFFIX), _mmuidx_ra)(env, ptr, v, CPU_MMU_INDEX, 0); -} - -#undef RES_TYPE -#undef DATA_TYPE -#undef DATA_STYPE -#undef SUFFIX -#undef USUFFIX -#undef DATA_SIZE -#undef SHIFT diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ #include "qemu/atomic128.h" #include "translate-all.h" #include "trace-root.h" -#include "qemu/plugin.h" #include "trace/mem.h" #ifdef CONFIG_PLUGIN #include "qemu/plugin-memory.h" @@ -XXX,XX +XXX,XX @@ uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr, ? helper_le_ldq_mmu : helper_be_ldq_mmu); } +uint32_t cpu_ldub_data_ra(CPUArchState *env, target_ulong ptr, + uintptr_t retaddr) +{ + return cpu_ldub_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +int cpu_ldsb_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) +{ + return cpu_ldsb_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +uint32_t cpu_lduw_data_ra(CPUArchState *env, target_ulong ptr, + uintptr_t retaddr) +{ + return cpu_lduw_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +int cpu_ldsw_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) +{ + return cpu_ldsw_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +uint32_t cpu_ldl_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) +{ + return cpu_ldl_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +uint64_t cpu_ldq_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr) +{ + return cpu_ldq_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr); +} + +uint32_t cpu_ldub_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_ldub_data_ra(env, ptr, 0); +} + +int cpu_ldsb_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_ldsb_data_ra(env, ptr, 0); +} + +uint32_t cpu_lduw_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_lduw_data_ra(env, ptr, 0); +} + +int cpu_ldsw_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_ldsw_data_ra(env, ptr, 0); +} + +uint32_t cpu_ldl_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_ldl_data_ra(env, ptr, 0); +} + +uint64_t cpu_ldq_data(CPUArchState *env, target_ulong ptr) +{ + return cpu_ldq_data_ra(env, ptr, 0); +} + /* * Store Helpers */ @@ -XXX,XX +XXX,XX @@ void cpu_stq_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val, cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEQ); } +void cpu_stb_data_ra(CPUArchState *env, target_ulong ptr, + uint32_t val, uintptr_t retaddr) +{ + cpu_stb_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr); +} + +void cpu_stw_data_ra(CPUArchState *env, target_ulong ptr, + uint32_t val, uintptr_t retaddr) +{ + cpu_stw_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr); +} + +void cpu_stl_data_ra(CPUArchState *env, target_ulong ptr, + uint32_t val, uintptr_t retaddr) +{ + cpu_stl_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr); +} + +void cpu_stq_data_ra(CPUArchState *env, target_ulong ptr, + uint64_t val, uintptr_t retaddr) +{ + cpu_stq_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr); +} + +void cpu_stb_data(CPUArchState *env, target_ulong ptr, uint32_t val) +{ + cpu_stb_data_ra(env, ptr, val, 0); +} + +void cpu_stw_data(CPUArchState *env, target_ulong ptr, uint32_t val) +{ + cpu_stw_data_ra(env, ptr, val, 0); +} + +void cpu_stl_data(CPUArchState *env, target_ulong ptr, uint32_t val) +{ + cpu_stl_data_ra(env, ptr, val, 0); +} + +void cpu_stq_data(CPUArchState *env, target_ulong ptr, uint64_t val) +{ + cpu_stq_data_ra(env, ptr, val, 0); +} + /* First set of helpers allows passing in of OI and RETADDR. This makes them callable from other helpers. */ -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> We currently search both the root and the tcg/ directories for tcg files: $ git grep '#include "tcg/' | wc -l 28 $ git grep '#include "tcg[^/]' | wc -l 94 To simplify the preprocessor search path, unify by expliciting the tcg/ directory. Patch created mechanically by running: $ for x in \ tcg.h tcg-mo.h tcg-op.h tcg-opc.h \ tcg-op-gvec.h tcg-gvec-desc.h; do \ sed -i "s,#include \"$x\",#include \"tcg/$x\"," \ $(git grep -l "#include \"$x\""); \ done Acked-by: David Gibson <david@gibson.dropbear.id.au> (ppc parts) Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Stefan Weil <sw@weilnetz.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200101112303.20724-2-philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu_ldst.h | 2 +- tcg/i386/tcg-target.h | 2 +- tcg/tcg-op.h | 2 +- tcg/tcg.h | 4 ++-- accel/tcg/cpu-exec.c | 2 +- accel/tcg/tcg-runtime-gvec.c | 2 +- accel/tcg/tcg-runtime.c | 2 +- accel/tcg/translate-all.c | 2 +- accel/tcg/user-exec.c | 2 +- bsd-user/main.c | 2 +- cpus.c | 2 +- exec.c | 2 +- linux-user/main.c | 2 +- linux-user/syscall.c | 2 +- target/alpha/translate.c | 2 +- target/arm/helper-a64.c | 2 +- target/arm/sve_helper.c | 2 +- target/arm/translate-a64.c | 4 ++-- target/arm/translate-sve.c | 6 +++--- target/arm/translate.c | 4 ++-- target/cris/translate.c | 2 +- target/hppa/translate.c | 2 +- target/i386/mem_helper.c | 2 +- target/i386/translate.c | 2 +- target/lm32/translate.c | 2 +- target/m68k/translate.c | 2 +- target/microblaze/translate.c | 2 +- target/mips/translate.c | 2 +- target/moxie/translate.c | 2 +- target/nios2/translate.c | 2 +- target/openrisc/translate.c | 2 +- target/ppc/mem_helper.c | 2 +- target/ppc/translate.c | 4 ++-- target/riscv/cpu_helper.c | 2 +- target/riscv/translate.c | 2 +- target/s390x/mem_helper.c | 2 +- target/s390x/translate.c | 4 ++-- target/sh4/translate.c | 2 +- target/sparc/ldst_helper.c | 2 +- target/sparc/translate.c | 2 +- target/tilegx/translate.c | 2 +- target/tricore/translate.c | 2 +- target/unicore32/translate.c | 2 +- target/xtensa/translate.c | 2 +- tcg/optimize.c | 2 +- tcg/tcg-common.c | 2 +- tcg/tcg-op-gvec.c | 8 ++++---- tcg/tcg-op-vec.c | 6 +++--- tcg/tcg-op.c | 6 +++--- tcg/tcg.c | 2 +- tcg/tci.c | 2 +- 51 files changed, 65 insertions(+), 65 deletions(-) diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -XXX,XX +XXX,XX @@ static inline void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, #else /* Needed for TCG_OVERSIZED_GUEST */ -#include "tcg.h" +#include "tcg/tcg.h" static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry) { diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -XXX,XX +XXX,XX @@ static inline void tb_target_set_jmp_target(uintptr_t tc_ptr, * The x86 has a pretty strong memory ordering which only really * allows for some stores to be re-ordered after loads. */ -#include "tcg-mo.h" +#include "tcg/tcg-mo.h" #define TCG_TARGET_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD) diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op.h +++ b/tcg/tcg-op.h @@ -XXX,XX +XXX,XX @@ #ifndef TCG_TCG_OP_H #define TCG_TCG_OP_H -#include "tcg.h" +#include "tcg/tcg.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" diff --git a/tcg/tcg.h b/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ #include "qemu/bitops.h" #include "qemu/plugin.h" #include "qemu/queue.h" -#include "tcg-mo.h" +#include "tcg/tcg-mo.h" #include "tcg-target.h" #include "qemu/int128.h" @@ -XXX,XX +XXX,XX @@ typedef uint64_t TCGRegSet; typedef enum TCGOpcode { #define DEF(name, oargs, iargs, cargs, flags) INDEX_op_ ## name, -#include "tcg-opc.h" +#include "tcg/tcg-opc.h" #undef DEF NB_OPS, } TCGOpcode; diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "qemu/atomic.h" #include "sysemu/qtest.h" #include "qemu/timer.h" diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/host-utils.h" #include "cpu.h" #include "exec/helper-proto.h" -#include "tcg-gvec-desc.h" +#include "tcg/tcg-gvec-desc.h" /* Virtually all hosts support 16-byte vectors. Those that don't can emulate diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -XXX,XX +XXX,XX @@ #include "exec/tb-lookup.h" #include "disas/disas.h" #include "exec/log.h" -#include "tcg.h" +#include "tcg/tcg.h" /* 32-bit helpers */ diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg.h" +#include "tcg/tcg.h" #if defined(CONFIG_USER_ONLY) #include "qemu.h" #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "qemu/bitops.h" #include "exec/cpu_ldst.h" #include "translate-all.h" diff --git a/bsd-user/main.c b/bsd-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "cpu.h" #include "exec/exec-all.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "qemu/timer.h" #include "qemu/envlist.h" #include "exec/log.h" diff --git a/cpus.c b/cpus.c index XXXXXXX..XXXXXXX 100644 --- a/cpus.c +++ b/cpus.c @@ -XXX,XX +XXX,XX @@ #include "qemu/bitmap.h" #include "qemu/seqlock.h" #include "qemu/guest-random.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "hw/nmi.h" #include "sysemu/replay.h" #include "sysemu/runstate.h" diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" #include "exec/target_page.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "hw/qdev-core.h" #include "hw/qdev-properties.h" #if !defined(CONFIG_USER_ONLY) diff --git a/linux-user/main.c b/linux-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -XXX,XX +XXX,XX @@ #include "qemu/plugin.h" #include "cpu.h" #include "exec/exec-all.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "qemu/timer.h" #include "qemu/envlist.h" #include "qemu/guest-random.h" diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ #include "user/syscall-trace.h" #include "qapi/error.h" #include "fd-trans.h" -#include "tcg.h" +#include "tcg/tcg.h" #ifndef CLONE_IO #define CLONE_IO 0x80000000 /* Clone io context */ diff --git a/target/alpha/translate.c b/target/alpha/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/translate.c +++ b/target/alpha/translate.c @@ -XXX,XX +XXX,XX @@ #include "disas/disas.h" #include "qemu/host-utils.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "qemu/int128.h" #include "qemu/atomic128.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "fpu/softfloat.h" #include <zlib.h> /* For crc32 */ diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" -#include "tcg.h" +#include "tcg/tcg.h" /* Note that vector data is stored in host-endian 64-bit chunks, diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "qemu/log.h" #include "arm_ldst.h" #include "translate.h" diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "exec/exec-all.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" -#include "tcg-gvec-desc.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "tcg/tcg-gvec-desc.h" #include "qemu/log.h" #include "arm_ldst.h" #include "translate.h" diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ #include "internals.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "qemu/log.h" #include "qemu/bitops.h" #include "arm_ldst.h" diff --git a/target/cris/translate.c b/target/cris/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/translate.c +++ b/target/cris/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/helper-proto.h" #include "mmu.h" #include "exec/cpu_ldst.h" diff --git a/target/hppa/translate.c b/target/hppa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/translate.c +++ b/target/hppa/translate.c @@ -XXX,XX +XXX,XX @@ #include "disas/disas.h" #include "qemu/host-utils.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" diff --git a/target/i386/mem_helper.c b/target/i386/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/mem_helper.c +++ b/target/i386/mem_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "qemu/int128.h" #include "qemu/atomic128.h" -#include "tcg.h" +#include "tcg/tcg.h" void helper_cmpxchg8b_unlocked(CPUX86State *env, target_ulong a0) { diff --git a/target/i386/translate.c b/target/i386/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/translate.c +++ b/target/i386/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "exec/translator.h" diff --git a/target/lm32/translate.c b/target/lm32/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/lm32/translate.c +++ b/target/lm32/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "exec/translator.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "qemu/qemu-print.h" #include "exec/cpu_ldst.h" diff --git a/target/m68k/translate.c b/target/m68k/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "qemu/log.h" #include "qemu/qemu-print.h" #include "exec/cpu_ldst.h" diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/translate.c +++ b/target/microblaze/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/helper-proto.h" #include "microblaze-decode.h" #include "exec/cpu_ldst.h" diff --git a/target/mips/translate.c b/target/mips/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -XXX,XX +XXX,XX @@ #include "internal.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "hw/mips/cpudevs.h" diff --git a/target/moxie/translate.c b/target/moxie/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/moxie/translate.c +++ b/target/moxie/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" #include "disas/disas.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "qemu/qemu-print.h" diff --git a/target/nios2/translate.c b/target/nios2/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/translate.c +++ b/target/nios2/translate.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/exec-all.h" #include "disas/disas.h" #include "exec/helper-proto.h" diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/translate.c +++ b/target/openrisc/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" #include "disas/disas.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "qemu/log.h" #include "qemu/bitops.h" #include "qemu/qemu-print.h" diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/mem_helper.c +++ b/target/ppc/mem_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "helper_regs.h" #include "exec/cpu_ldst.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "internal.h" #include "qemu/atomic128.h" diff --git a/target/ppc/translate.c b/target/ppc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -XXX,XX +XXX,XX @@ #include "internal.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "qemu/host-utils.h" #include "qemu/main-loop.h" #include "exec/cpu_ldst.h" diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu_helper.c +++ b/target/riscv/cpu_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/main-loop.h" #include "cpu.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "trace.h" int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch) diff --git a/target/riscv/translate.c b/target/riscv/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "cpu.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "disas/disas.h" #include "exec/cpu_ldst.h" #include "exec/exec-all.h" diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/mem_helper.c +++ b/target/s390x/mem_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "qemu/int128.h" #include "qemu/atomic128.h" -#include "tcg.h" +#include "tcg/tcg.h" #if !defined(CONFIG_USER_ONLY) #include "hw/s390x/storage-keys.h" diff --git a/target/s390x/translate.c b/target/s390x/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/translate.c +++ b/target/s390x/translate.c @@ -XXX,XX +XXX,XX @@ #include "internal.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "qemu/log.h" #include "qemu/host-utils.h" #include "exec/cpu_ldst.h" diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" #include "exec/helper-gen.h" diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/ldst_helper.c +++ b/target/sparc/ldst_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "tcg.h" +#include "tcg/tcg.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ #include "disas/disas.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "exec/helper-gen.h" diff --git a/target/tilegx/translate.c b/target/tilegx/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/tilegx/translate.c +++ b/target/tilegx/translate.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "linux-user/syscall_defs.h" diff --git a/target/tricore/translate.c b/target/tricore/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/translate.c +++ b/target/tricore/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "exec/cpu_ldst.h" #include "qemu/qemu-print.h" diff --git a/target/unicore32/translate.c b/target/unicore32/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/unicore32/translate.c +++ b/target/unicore32/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "disas/disas.h" #include "exec/exec-all.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "qemu/log.h" #include "exec/cpu_ldst.h" #include "exec/translator.h" diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/exec-all.h" #include "disas/disas.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #include "qemu/log.h" #include "qemu/qemu-print.h" #include "exec/cpu_ldst.h" diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" #define CASE_OP_32_64(x) \ glue(glue(case INDEX_op_, x), _i32): \ diff --git a/tcg/tcg-common.c b/tcg/tcg-common.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-common.c +++ b/tcg/tcg-common.c @@ -XXX,XX +XXX,XX @@ uintptr_t tci_tb_ptr; TCGOpDef tcg_op_defs[] = { #define DEF(s, oargs, iargs, cargs, flags) \ { #s, oargs, iargs, cargs, iargs + oargs + cargs, flags }, -#include "tcg-opc.h" +#include "tcg/tcg-opc.h" #undef DEF }; const size_t tcg_op_defs_max = ARRAY_SIZE(tcg_op_defs); diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "tcg.h" -#include "tcg-op.h" -#include "tcg-op-gvec.h" +#include "tcg/tcg.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" #include "qemu/main-loop.h" -#include "tcg-gvec-desc.h" +#include "tcg/tcg-gvec-desc.h" #define MAX_UNROLL 4 diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "tcg.h" -#include "tcg-op.h" -#include "tcg-mo.h" +#include "tcg/tcg.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-mo.h" /* Reduce the number of ifdefs below. This assumes that all uses of TCGV_HIGH and TCGV_LOW are properly protected by a conditional that diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "exec/exec-all.h" -#include "tcg.h" -#include "tcg-op.h" -#include "tcg-mo.h" +#include "tcg/tcg.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-mo.h" #include "trace-tcg.h" #include "trace/mem.h" #include "exec/plugin-gen.h" diff --git a/tcg/tcg.c b/tcg/tcg.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #endif -#include "tcg-op.h" +#include "tcg/tcg-op.h" #if UINTPTR_MAX == UINT32_MAX # define ELF_CLASS ELFCLASS32 diff --git a/tcg/tci.c b/tcg/tci.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/tci.c +++ b/tcg/tci.c @@ -XXX,XX +XXX,XX @@ #include "qemu-common.h" #include "tcg/tcg.h" /* MAX_OPC_PARAM_IARGS */ #include "exec/cpu_ldst.h" -#include "tcg-op.h" +#include "tcg/tcg-op.h" /* Marker for missing code. */ #define TODO() \ -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> All the *.inc.c files included by tcg/$TARGET/tcg-target.inc.c are in tcg/, their parent directory. To simplify the preprocessor search path, include the relative parent path: '..'. Patch created mechanically by running: $ for x in tcg-pool.inc.c tcg-ldst.inc.c; do \ sed -i "s,#include \"$x\",#include \"../$x\"," \ $(git grep -l "#include \"$x\""); \ done Acked-by: David Gibson <david@gibson.dropbear.id.au> (ppc parts) Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Stefan Weil <sw@weilnetz.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200101112303.20724-3-philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/aarch64/tcg-target.inc.c | 4 ++-- tcg/arm/tcg-target.inc.c | 4 ++-- tcg/i386/tcg-target.inc.c | 4 ++-- tcg/mips/tcg-target.inc.c | 2 +- tcg/ppc/tcg-target.inc.c | 4 ++-- tcg/riscv/tcg-target.inc.c | 4 ++-- tcg/s390/tcg-target.inc.c | 4 ++-- tcg/sparc/tcg-target.inc.c | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/aarch64/tcg-target.inc.c +++ b/tcg/aarch64/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ * See the COPYING file in the top-level directory for details. */ -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #include "qemu/bitops.h" /* We're going to re-use TCGType in setting of the SF bit, which controls @@ -XXX,XX +XXX,XX @@ static void tcg_out_cltz(TCGContext *s, TCGType ext, TCGReg d, } #ifdef CONFIG_SOFTMMU -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * TCGMemOpIdx oi, uintptr_t ra) diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/arm/tcg-target.inc.c +++ b/tcg/arm/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ */ #include "elf.h" -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" int arm_arch = __ARM_ARCH; @@ -XXX,XX +XXX,XX @@ static TCGCond tcg_out_cmp2(TCGContext *s, const TCGArg *args, } #ifdef CONFIG_SOFTMMU -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/i386/tcg-target.inc.c +++ b/tcg/i386/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #ifdef CONFIG_DEBUG_TCG static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { @@ -XXX,XX +XXX,XX @@ static void tcg_out_nopn(TCGContext *s, int n) } #if defined(CONFIG_SOFTMMU) -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) diff --git a/tcg/mips/tcg-target.inc.c b/tcg/mips/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/mips/tcg-target.inc.c +++ b/tcg/mips/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg) } #if defined(CONFIG_SOFTMMU) -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" static void * const qemu_ld_helpers[16] = { [MO_UB] = helper_ret_ldub_mmu, diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.inc.c +++ b/tcg/ppc/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ */ #include "elf.h" -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #if defined _CALL_DARWIN || defined __APPLE__ #define TCG_TARGET_CALL_DARWIN @@ -XXX,XX +XXX,XX @@ static const uint32_t qemu_exts_opc[4] = { }; #if defined (CONFIG_SOFTMMU) -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) diff --git a/tcg/riscv/tcg-target.inc.c b/tcg/riscv/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/riscv/tcg-target.inc.c +++ b/tcg/riscv/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #ifdef CONFIG_DEBUG_TCG static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { @@ -XXX,XX +XXX,XX @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) */ #if defined(CONFIG_SOFTMMU) -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * TCGMemOpIdx oi, uintptr_t ra) diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/s390/tcg-target.inc.c +++ b/tcg/s390/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ #error "unsupported code generation mode" #endif -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #include "elf.h" /* ??? The translation blocks produced by TCG are generally small enough to @@ -XXX,XX +XXX,XX @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg data, } #if defined(CONFIG_SOFTMMU) -#include "tcg-ldst.inc.c" +#include "../tcg-ldst.inc.c" /* We're expecting to use a 20-bit negative offset on the tlb memory ops. */ QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); diff --git a/tcg/sparc/tcg-target.inc.c b/tcg/sparc/tcg-target.inc.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/sparc/tcg-target.inc.c +++ b/tcg/sparc/tcg-target.inc.c @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ -#include "tcg-pool.inc.c" +#include "../tcg-pool.inc.c" #ifdef CONFIG_DEBUG_TCG static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Stefan Weil <sw@weilnetz.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200101112303.20724-4-philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- {tcg => include/tcg}/tcg-gvec-desc.h | 0 {tcg => include/tcg}/tcg-mo.h | 0 {tcg => include/tcg}/tcg-op-gvec.h | 0 {tcg => include/tcg}/tcg-op.h | 0 {tcg => include/tcg}/tcg-opc.h | 0 {tcg => include/tcg}/tcg.h | 0 MAINTAINERS | 1 + 7 files changed, 1 insertion(+) rename {tcg => include/tcg}/tcg-gvec-desc.h (100%) rename {tcg => include/tcg}/tcg-mo.h (100%) rename {tcg => include/tcg}/tcg-op-gvec.h (100%) rename {tcg => include/tcg}/tcg-op.h (100%) rename {tcg => include/tcg}/tcg-opc.h (100%) rename {tcg => include/tcg}/tcg.h (100%) diff --git a/tcg/tcg-gvec-desc.h b/include/tcg/tcg-gvec-desc.h similarity index 100% rename from tcg/tcg-gvec-desc.h rename to include/tcg/tcg-gvec-desc.h diff --git a/tcg/tcg-mo.h b/include/tcg/tcg-mo.h similarity index 100% rename from tcg/tcg-mo.h rename to include/tcg/tcg-mo.h diff --git a/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h similarity index 100% rename from tcg/tcg-op-gvec.h rename to include/tcg/tcg-op-gvec.h diff --git a/tcg/tcg-op.h b/include/tcg/tcg-op.h similarity index 100% rename from tcg/tcg-op.h rename to include/tcg/tcg-op.h diff --git a/tcg/tcg-opc.h b/include/tcg/tcg-opc.h similarity index 100% rename from tcg/tcg-opc.h rename to include/tcg/tcg-opc.h diff --git a/tcg/tcg.h b/include/tcg/tcg.h similarity index 100% rename from tcg/tcg.h rename to include/tcg/tcg.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ Common TCG code M: Richard Henderson <rth@twiddle.net> S: Maintained F: tcg/ +F: include/tcg/ TCG Plugins M: Alex Bennée <alex.bennee@linaro.org> -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> All tcg includes are relative to the repository root directory, we can safely remove the tcg/ directory from the include search path list. Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Stefan Weil <sw@weilnetz.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200101112303.20724-5-philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- configure | 1 - 1 file changed, 1 deletion(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ elif test "$ARCH" = "riscv32" || test "$ARCH" = "riscv64" ; then else QEMU_INCLUDES="-iquote \$(SRC_PATH)/tcg/\$(ARCH) $QEMU_INCLUDES" fi -QEMU_INCLUDES="-iquote \$(SRC_PATH)/tcg $QEMU_INCLUDES" echo "TOOLS=$tools" >> $config_host_mak echo "ROMS=$roms" >> $config_host_mak -- 2.20.1 Claudio's Huawei address has been defunct for quite a while. In https://lists.gnu.org/archive/html/qemu-devel/2019-05/msg06872.html he asked for his personal address to be removed as well. I will take over officially. Cc: Claudio Fontana <claudio.fontana@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: plugins/ F: tests/plugin AArch64 TCG target -M: Claudio Fontana <claudio.fontana@huawei.com> -M: Claudio Fontana <claudio.fontana@gmail.com> +M: Richard Henderson <richard.henderson@linaro.org> S: Maintained L: qemu-arm@nongnu.org F: tcg/aarch64/ -- 2.20.1 The following changes since commit aa3a285b5bc56a4208b3b57d4a55291e9c260107: Merge tag 'mem-2024-12-21' of https://github.com/davidhildenbrand/qemu into staging (2024-12-22 14:33:27 -0500) are available in the Git repository at: https://gitlab.com/rth7680/qemu.git tags/pull-tcg-20241224 for you to fetch changes up to e4a8e093dc74be049f4829831dce76e5edab0003: accel/tcg: Move gen_intermediate_code to TCGCPUOps.translate_core (2024-12-24 08:32:15 -0800) ---------------------------------------------------------------- tcg/optimize: Remove in-flight mask data from OptContext fpu: Add float*_muladd_scalbn fpu: Remove float_muladd_halve_result fpu: Add float_round_nearest_even_max fpu: Add float_muladd_suppress_add_product_zero target/hexagon: Use float32_muladd accel/tcg: Move gen_intermediate_code to TCGCPUOps.translate_core ---------------------------------------------------------------- Ilya Leoshkevich (1): tests/tcg: Do not use inttypes.h in multiarch/system/memory.c Pierrick Bouvier (1): plugins: optimize cpu_index code generation Richard Henderson (70): tcg/optimize: Split out finish_bb, finish_ebb tcg/optimize: Split out fold_affected_mask tcg/optimize: Copy mask writeback to fold_masks tcg/optimize: Split out fold_masks_zs tcg/optimize: Augment s_mask from z_mask in fold_masks_zs tcg/optimize: Change representation of s_mask tcg/optimize: Use finish_folding in fold_add, fold_add_vec, fold_addsub2 tcg/optimize: Introduce const value accessors for TempOptInfo tcg/optimize: Use fold_masks_zs in fold_and tcg/optimize: Use fold_masks_zs in fold_andc tcg/optimize: Use fold_masks_zs in fold_bswap tcg/optimize: Use fold_masks_zs in fold_count_zeros tcg/optimize: Use fold_masks_z in fold_ctpop tcg/optimize: Use fold_and and fold_masks_z in fold_deposit tcg/optimize: Compute sign mask in fold_deposit tcg/optimize: Use finish_folding in fold_divide tcg/optimize: Use finish_folding in fold_dup, fold_dup2 tcg/optimize: Use fold_masks_s in fold_eqv tcg/optimize: Use fold_masks_z in fold_extract tcg/optimize: Use finish_folding in fold_extract2 tcg/optimize: Use fold_masks_zs in fold_exts tcg/optimize: Use fold_masks_z in fold_extu tcg/optimize: Use fold_masks_zs in fold_movcond tcg/optimize: Use finish_folding in fold_mul* tcg/optimize: Use fold_masks_s in fold_nand tcg/optimize: Use fold_masks_z in fold_neg_no_const tcg/optimize: Use fold_masks_s in fold_nor tcg/optimize: Use fold_masks_s in fold_not tcg/optimize: Use fold_masks_zs in fold_or tcg/optimize: Use fold_masks_zs in fold_orc tcg/optimize: Use fold_masks_zs in fold_qemu_ld tcg/optimize: Return true from fold_qemu_st, fold_tcg_st tcg/optimize: Use finish_folding in fold_remainder tcg/optimize: Distinguish simplification in fold_setcond_zmask tcg/optimize: Use fold_masks_z in fold_setcond tcg/optimize: Use fold_masks_s in fold_negsetcond tcg/optimize: Use fold_masks_z in fold_setcond2 tcg/optimize: Use finish_folding in fold_cmp_vec tcg/optimize: Use finish_folding in fold_cmpsel_vec tcg/optimize: Use fold_masks_zs in fold_sextract tcg/optimize: Use fold_masks_zs, fold_masks_s in fold_shift tcg/optimize: Simplify sign bit test in fold_shift tcg/optimize: Use finish_folding in fold_sub, fold_sub_vec tcg/optimize: Use fold_masks_zs in fold_tcg_ld tcg/optimize: Use finish_folding in fold_tcg_ld_memcopy tcg/optimize: Use fold_masks_zs in fold_xor tcg/optimize: Use finish_folding in fold_bitsel_vec tcg/optimize: Use finish_folding as default in tcg_optimize tcg/optimize: Remove z_mask, s_mask from OptContext tcg/optimize: Re-enable sign-mask optimizations tcg/optimize: Move fold_bitsel_vec into alphabetic sort tcg/optimize: Move fold_cmp_vec, fold_cmpsel_vec into alphabetic sort softfloat: Add float{16,32,64}_muladd_scalbn target/arm: Use float*_muladd_scalbn target/sparc: Use float*_muladd_scalbn softfloat: Remove float_muladd_halve_result softfloat: Add float_round_nearest_even_max softfloat: Add float_muladd_suppress_add_product_zero target/hexagon: Use float32_mul in helper_sfmpy target/hexagon: Use float32_muladd for helper_sffma target/hexagon: Use float32_muladd for helper_sffms target/hexagon: Use float32_muladd_scalbn for helper_sffma_sc target/hexagon: Use float32_muladd for helper_sffm[as]_lib target/hexagon: Remove internal_fmafx target/hexagon: Expand GEN_XF_ROUND target/hexagon: Remove Float target/hexagon: Remove Double target/hexagon: Use mulu64 for int128_mul_6464 target/hexagon: Simplify internal_mpyhh setup accel/tcg: Move gen_intermediate_code to TCGCPUOps.translate_core include/exec/translator.h | 14 - include/fpu/softfloat-types.h | 2 + include/fpu/softfloat.h | 14 +- include/hw/core/tcg-cpu-ops.h | 13 + target/alpha/cpu.h | 2 + target/arm/internals.h | 2 + target/avr/cpu.h | 2 + target/hexagon/cpu.h | 2 + target/hexagon/fma_emu.h | 3 - target/hppa/cpu.h | 2 + target/i386/tcg/helper-tcg.h | 2 + target/loongarch/internals.h | 2 + target/m68k/cpu.h | 2 + target/microblaze/cpu.h | 2 + target/mips/tcg/tcg-internal.h | 2 + target/openrisc/cpu.h | 2 + target/ppc/cpu.h | 2 + target/riscv/cpu.h | 3 + target/rx/cpu.h | 2 + target/s390x/s390x-internal.h | 2 + target/sh4/cpu.h | 2 + target/sparc/cpu.h | 2 + target/sparc/helper.h | 4 +- target/tricore/cpu.h | 2 + target/xtensa/cpu.h | 2 + accel/tcg/cpu-exec.c | 8 +- accel/tcg/plugin-gen.c | 9 + accel/tcg/translate-all.c | 8 +- fpu/softfloat.c | 63 +-- target/alpha/cpu.c | 1 + target/alpha/translate.c | 4 +- target/arm/cpu.c | 1 + target/arm/tcg/cpu-v7m.c | 1 + target/arm/tcg/helper-a64.c | 6 +- target/arm/tcg/translate.c | 5 +- target/avr/cpu.c | 1 + target/avr/translate.c | 6 +- target/hexagon/cpu.c | 1 + target/hexagon/fma_emu.c | 496 ++++++--------------- target/hexagon/op_helper.c | 125 ++---- target/hexagon/translate.c | 4 +- target/hppa/cpu.c | 1 + target/hppa/translate.c | 4 +- target/i386/tcg/tcg-cpu.c | 1 + target/i386/tcg/translate.c | 5 +- target/loongarch/cpu.c | 1 + target/loongarch/tcg/translate.c | 4 +- target/m68k/cpu.c | 1 + target/m68k/translate.c | 4 +- target/microblaze/cpu.c | 1 + target/microblaze/translate.c | 4 +- target/mips/cpu.c | 1 + target/mips/tcg/translate.c | 4 +- target/openrisc/cpu.c | 1 + target/openrisc/translate.c | 4 +- target/ppc/cpu_init.c | 1 + target/ppc/translate.c | 4 +- target/riscv/tcg/tcg-cpu.c | 1 + target/riscv/translate.c | 4 +- target/rx/cpu.c | 1 + target/rx/translate.c | 4 +- target/s390x/cpu.c | 1 + target/s390x/tcg/translate.c | 4 +- target/sh4/cpu.c | 1 + target/sh4/translate.c | 4 +- target/sparc/cpu.c | 1 + target/sparc/fop_helper.c | 8 +- target/sparc/translate.c | 84 ++-- target/tricore/cpu.c | 1 + target/tricore/translate.c | 5 +- target/xtensa/cpu.c | 1 + target/xtensa/translate.c | 4 +- tcg/optimize.c | 857 +++++++++++++++++++----------------- tests/tcg/multiarch/system/memory.c | 9 +- fpu/softfloat-parts.c.inc | 16 +- 75 files changed, 866 insertions(+), 1009 deletions(-) From: Ilya Leoshkevich <iii@linux.ibm.com> make check-tcg fails on Fedora with the following error message: alpha-linux-gnu-gcc [...] qemu/tests/tcg/multiarch/system/memory.c -o memory [...] qemu/tests/tcg/multiarch/system/memory.c:17:10: fatal error: inttypes.h: No such file or directory 17 | #include <inttypes.h> | ^~~~~~~~~~~~ compilation terminated. The reason is that Fedora has cross-compilers, but no cross-glibc headers. Fix by hardcoding the format specifiers and dropping the include. An alternative fix would be to introduce a configure check for inttypes.h. But this would make it impossible to use Fedora cross-compilers for softmmu tests, which used to work so far. Fixes: ecbcc9ead2f8 ("tests/tcg: add a system test to check memory instrumentation") Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-ID: <20241010085906.226249-1-iii@linux.ibm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tests/tcg/multiarch/system/memory.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tests/tcg/multiarch/system/memory.c b/tests/tcg/multiarch/system/memory.c index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/multiarch/system/memory.c +++ b/tests/tcg/multiarch/system/memory.c @@ -XXX,XX +XXX,XX @@ #include <stdint.h> #include <stdbool.h> -#include <inttypes.h> #include <minilib.h> #ifndef CHECK_UNALIGNED @@ -XXX,XX +XXX,XX @@ int main(void) int i; bool ok = true; - ml_printf("Test data start: 0x%"PRIxPTR"\n", &test_data[0]); - ml_printf("Test data end: 0x%"PRIxPTR"\n", &test_data[TEST_SIZE]); + ml_printf("Test data start: 0x%lx\n", (unsigned long)&test_data[0]); + ml_printf("Test data end: 0x%lx\n", (unsigned long)&test_data[TEST_SIZE]); /* Run through the unsigned tests first */ for (i = 0; i < ARRAY_SIZE(init_ufns) && ok; i++) { @@ -XXX,XX +XXX,XX @@ int main(void) ok = do_signed_reads(true); } - ml_printf("Test data read: %"PRId32"\n", test_read_count); - ml_printf("Test data write: %"PRId32"\n", test_write_count); + ml_printf("Test data read: %lu\n", (unsigned long)test_read_count); + ml_printf("Test data write: %lu\n", (unsigned long)test_write_count); ml_printf("Test complete: %s\n", ok ? "PASSED" : "FAILED"); return ok ? 0 : -1; } -- 2.43.0 From: Pierrick Bouvier <pierrick.bouvier@linaro.org> When running with a single vcpu, we can return a constant instead of a load when accessing cpu_index. A side effect is that all tcg operations using it are optimized, most notably scoreboard access. When running a simple loop in user-mode, the speedup is around 20%. Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-ID: <20241128213843.1023080-1-pierrick.bouvier@linaro.org> --- accel/tcg/plugin-gen.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -XXX,XX +XXX,XX @@ static void gen_disable_mem_helper(void) static TCGv_i32 gen_cpu_index(void) { + /* + * Optimize when we run with a single vcpu. All values using cpu_index, + * including scoreboard index, will be optimized out. + * User-mode calls tb_flush when setting this flag. In system-mode, all + * vcpus are created before generating code. + */ + if (!tcg_cflags_has(current_cpu, CF_PARALLEL)) { + return tcg_constant_i32(current_cpu->cpu_index); + } TCGv_i32 cpu_index = tcg_temp_ebb_new_i32(); tcg_gen_ld_i32(cpu_index, tcg_env, -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index)); -- 2.43.0 Call them directly from the opcode switch statement in tcg_optimize, rather than in finish_folding based on opcode flags. Adjust folding of conditional branches to match. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 47 +++++++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 16 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static void copy_propagate(OptContext *ctx, TCGOp *op, } } +static void finish_bb(OptContext *ctx) +{ + /* We only optimize memory barriers across basic blocks. */ + ctx->prev_mb = NULL; +} + +static void finish_ebb(OptContext *ctx) +{ + finish_bb(ctx); + /* We only optimize across extended basic blocks. */ + memset(&ctx->temps_used, 0, sizeof(ctx->temps_used)); + remove_mem_copy_all(ctx); +} + static void finish_folding(OptContext *ctx, TCGOp *op) { const TCGOpDef *def = &tcg_op_defs[op->opc]; int i, nb_oargs; - /* - * We only optimize extended basic blocks. If the opcode ends a BB - * and is not a conditional branch, reset all temp data. - */ - if (def->flags & TCG_OPF_BB_END) { - ctx->prev_mb = NULL; - if (!(def->flags & TCG_OPF_COND_BRANCH)) { - memset(&ctx->temps_used, 0, sizeof(ctx->temps_used)); - remove_mem_copy_all(ctx); - } - return; - } - nb_oargs = def->nb_oargs; for (i = 0; i < nb_oargs; i++) { TCGTemp *ts = arg_temp(op->args[i]); @@ -XXX,XX +XXX,XX @@ static bool fold_brcond(OptContext *ctx, TCGOp *op) if (i > 0) { op->opc = INDEX_op_br; op->args[0] = op->args[3]; + finish_ebb(ctx); + } else { + finish_bb(ctx); } - return false; + return true; } static bool fold_brcond2(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_brcond2(OptContext *ctx, TCGOp *op) } op->opc = INDEX_op_br; op->args[0] = label; - break; + finish_ebb(ctx); + return true; } - return false; + + finish_bb(ctx); + return true; } static bool fold_bswap(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ void tcg_optimize(TCGContext *s) CASE_OP_32_64_VEC(xor): done = fold_xor(&ctx, op); break; + case INDEX_op_set_label: + case INDEX_op_br: + case INDEX_op_exit_tb: + case INDEX_op_goto_tb: + case INDEX_op_goto_ptr: + finish_ebb(&ctx); + done = true; + break; default: break; } -- 2.43.0 There are only a few logical operations which can compute an "affected" mask. Split out handling of this optimization to a separate function, only to be called when applicable. Remove the a_mask field from OptContext, as the mask is no longer stored anywhere. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 42 +++++++++++++++++++++++++++--------------- 1 file changed, 27 insertions(+), 15 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ typedef struct OptContext { QSIMPLEQ_HEAD(, MemCopyInfo) mem_free; /* In flight values from optimization. */ - uint64_t a_mask; /* mask bit is 0 iff value identical to first input */ uint64_t z_mask; /* mask bit is 0 iff value bit is 0 */ uint64_t s_mask; /* mask of clrsb(value) bits */ TCGType type; @@ -XXX,XX +XXX,XX @@ static bool fold_const2_commutative(OptContext *ctx, TCGOp *op) static bool fold_masks(OptContext *ctx, TCGOp *op) { - uint64_t a_mask = ctx->a_mask; uint64_t z_mask = ctx->z_mask; uint64_t s_mask = ctx->s_mask; @@ -XXX,XX +XXX,XX @@ static bool fold_masks(OptContext *ctx, TCGOp *op) * type changing opcodes. */ if (ctx->type == TCG_TYPE_I32) { - a_mask = (int32_t)a_mask; z_mask = (int32_t)z_mask; s_mask |= MAKE_64BIT_MASK(32, 32); ctx->z_mask = z_mask; @@ -XXX,XX +XXX,XX @@ static bool fold_masks(OptContext *ctx, TCGOp *op) if (z_mask == 0) { return tcg_opt_gen_movi(ctx, op, op->args[0], 0); } + return false; +} + +/* + * An "affected" mask bit is 0 if and only if the result is identical + * to the first input. Thus if the entire mask is 0, the operation + * is equivalent to a copy. + */ +static bool fold_affected_mask(OptContext *ctx, TCGOp *op, uint64_t a_mask) +{ + if (ctx->type == TCG_TYPE_I32) { + a_mask = (uint32_t)a_mask; + } if (a_mask == 0) { return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[1]); } @@ -XXX,XX +XXX,XX @@ static bool fold_and(OptContext *ctx, TCGOp *op) * Known-zeros does not imply known-ones. Therefore unless * arg2 is constant, we can't infer affected bits from it. */ - if (arg_is_const(op->args[2])) { - ctx->a_mask = z1 & ~z2; + if (arg_is_const(op->args[2]) && + fold_affected_mask(ctx, op, z1 & ~z2)) { + return true; } return fold_masks(ctx, op); @@ -XXX,XX +XXX,XX @@ static bool fold_andc(OptContext *ctx, TCGOp *op) */ if (arg_is_const(op->args[2])) { uint64_t z2 = ~arg_info(op->args[2])->z_mask; - ctx->a_mask = z1 & ~z2; + if (fold_affected_mask(ctx, op, z1 & ~z2)) { + return true; + } z1 &= z2; } ctx->z_mask = z1; @@ -XXX,XX +XXX,XX @@ static bool fold_extract(OptContext *ctx, TCGOp *op) z_mask_old = arg_info(op->args[1])->z_mask; z_mask = extract64(z_mask_old, pos, len); - if (pos == 0) { - ctx->a_mask = z_mask_old ^ z_mask; + if (pos == 0 && fold_affected_mask(ctx, op, z_mask_old ^ z_mask)) { + return true; } ctx->z_mask = z_mask; ctx->s_mask = smask_from_zmask(z_mask); @@ -XXX,XX +XXX,XX @@ static bool fold_exts(OptContext *ctx, TCGOp *op) ctx->z_mask = z_mask; ctx->s_mask = s_mask; - if (!type_change) { - ctx->a_mask = s_mask & ~s_mask_old; + if (!type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + return true; } return fold_masks(ctx, op); @@ -XXX,XX +XXX,XX @@ static bool fold_extu(OptContext *ctx, TCGOp *op) ctx->z_mask = z_mask; ctx->s_mask = smask_from_zmask(z_mask); - if (!type_change) { - ctx->a_mask = z_mask_old ^ z_mask; + if (!type_change && fold_affected_mask(ctx, op, z_mask_old ^ z_mask)) { + return true; } return fold_masks(ctx, op); } @@ -XXX,XX +XXX,XX @@ static bool fold_sextract(OptContext *ctx, TCGOp *op) s_mask |= MAKE_64BIT_MASK(len, 64 - len); ctx->s_mask = s_mask; - if (pos == 0) { - ctx->a_mask = s_mask & ~s_mask_old; + if (pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + return true; } return fold_masks(ctx, op); @@ -XXX,XX +XXX,XX @@ void tcg_optimize(TCGContext *s) } /* Assume all bits affected, no bits known zero, no sign reps. */ - ctx.a_mask = -1; ctx.z_mask = -1; ctx.s_mask = 0; -- 2.43.0 Use of fold_masks should be restricted to those opcodes that can reliably make use of it -- those with a single output, and from higher-level folders that set up the masks. Prepare for conversion of each folder in turn. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_masks(OptContext *ctx, TCGOp *op) { uint64_t z_mask = ctx->z_mask; uint64_t s_mask = ctx->s_mask; + const TCGOpDef *def = &tcg_op_defs[op->opc]; + TCGTemp *ts; + TempOptInfo *ti; + + /* Only single-output opcodes are supported here. */ + tcg_debug_assert(def->nb_oargs == 1); /* * 32-bit ops generate 32-bit results, which for the purpose of @@ -XXX,XX +XXX,XX @@ static bool fold_masks(OptContext *ctx, TCGOp *op) if (ctx->type == TCG_TYPE_I32) { z_mask = (int32_t)z_mask; s_mask |= MAKE_64BIT_MASK(32, 32); - ctx->z_mask = z_mask; - ctx->s_mask = s_mask; } if (z_mask == 0) { return tcg_opt_gen_movi(ctx, op, op->args[0], 0); } - return false; + + ts = arg_temp(op->args[0]); + reset_ts(ctx, ts); + + ti = ts_info(ts); + ti->z_mask = z_mask; + ti->s_mask = s_mask; + return true; } /* -- 2.43.0 Add a routine to which masks can be passed directly, rather than storing them into OptContext. To be used in upcoming patches. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_const2_commutative(OptContext *ctx, TCGOp *op) return fold_const2(ctx, op); } -static bool fold_masks(OptContext *ctx, TCGOp *op) +/* + * Record "zero" and "sign" masks for the single output of @op. + * See TempOptInfo definition of z_mask and s_mask. + * If z_mask allows, fold the output to constant zero. + */ +static bool fold_masks_zs(OptContext *ctx, TCGOp *op, + uint64_t z_mask, uint64_t s_mask) { - uint64_t z_mask = ctx->z_mask; - uint64_t s_mask = ctx->s_mask; const TCGOpDef *def = &tcg_op_defs[op->opc]; TCGTemp *ts; TempOptInfo *ti; @@ -XXX,XX +XXX,XX @@ static bool fold_masks(OptContext *ctx, TCGOp *op) return true; } +static bool fold_masks(OptContext *ctx, TCGOp *op) +{ + return fold_masks_zs(ctx, op, ctx->z_mask, ctx->s_mask); +} + /* * An "affected" mask bit is 0 if and only if the result is identical * to the first input. Thus if the entire mask is 0, the operation -- 2.43.0 Consider the passed s_mask to be a minimum deduced from either existing s_mask or from a sign-extension operation. We may be able to deduce more from the set of known zeros. Remove identical logic from several opcode folders. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_const2_commutative(OptContext *ctx, TCGOp *op) * Record "zero" and "sign" masks for the single output of @op. * See TempOptInfo definition of z_mask and s_mask. * If z_mask allows, fold the output to constant zero. + * The passed s_mask may be augmented by z_mask. */ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, uint64_t z_mask, uint64_t s_mask) @@ -XXX,XX +XXX,XX @@ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, ti = ts_info(ts); ti->z_mask = z_mask; - ti->s_mask = s_mask; + ti->s_mask = s_mask | smask_from_zmask(z_mask); return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) default: g_assert_not_reached(); } - s_mask = smask_from_zmask(z_mask); + s_mask = 0; switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) { case TCG_BSWAP_OZ: break; @@ -XXX,XX +XXX,XX @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) default: /* The high bits are undefined: force all bits above the sign to 1. */ z_mask |= sign << 1; - s_mask = 0; break; } ctx->z_mask = z_mask; @@ -XXX,XX +XXX,XX @@ static bool fold_count_zeros(OptContext *ctx, TCGOp *op) g_assert_not_reached(); } ctx->z_mask = arg_info(op->args[2])->z_mask | z_mask; - ctx->s_mask = smask_from_zmask(ctx->z_mask); return false; } @@ -XXX,XX +XXX,XX @@ static bool fold_ctpop(OptContext *ctx, TCGOp *op) default: g_assert_not_reached(); } - ctx->s_mask = smask_from_zmask(ctx->z_mask); return false; } @@ -XXX,XX +XXX,XX @@ static bool fold_extract(OptContext *ctx, TCGOp *op) return true; } ctx->z_mask = z_mask; - ctx->s_mask = smask_from_zmask(z_mask); return fold_masks(ctx, op); } @@ -XXX,XX +XXX,XX @@ static bool fold_extu(OptContext *ctx, TCGOp *op) } ctx->z_mask = z_mask; - ctx->s_mask = smask_from_zmask(z_mask); if (!type_change && fold_affected_mask(ctx, op, z_mask_old ^ z_mask)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_qemu_ld(OptContext *ctx, TCGOp *op) int width = 8 * memop_size(mop); if (width < 64) { - ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width); - if (!(mop & MO_SIGN)) { + if (mop & MO_SIGN) { + ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width); + } else { ctx->z_mask = MAKE_64BIT_MASK(0, width); - ctx->s_mask <<= 1; } } @@ -XXX,XX +XXX,XX @@ static bool fold_setcond(OptContext *ctx, TCGOp *op) fold_setcond_tst_pow2(ctx, op, false); ctx->z_mask = 1; - ctx->s_mask = smask_from_zmask(1); return false; } @@ -XXX,XX +XXX,XX @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op) } ctx->z_mask = 1; - ctx->s_mask = smask_from_zmask(1); return false; do_setcond_const: @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op) break; CASE_OP_32_64(ld8u): ctx->z_mask = MAKE_64BIT_MASK(0, 8); - ctx->s_mask = MAKE_64BIT_MASK(9, 55); break; CASE_OP_32_64(ld16s): ctx->s_mask = MAKE_64BIT_MASK(16, 48); break; CASE_OP_32_64(ld16u): ctx->z_mask = MAKE_64BIT_MASK(0, 16); - ctx->s_mask = MAKE_64BIT_MASK(17, 47); break; case INDEX_op_ld32s_i64: ctx->s_mask = MAKE_64BIT_MASK(32, 32); break; case INDEX_op_ld32u_i64: ctx->z_mask = MAKE_64BIT_MASK(0, 32); - ctx->s_mask = MAKE_64BIT_MASK(33, 31); break; default: g_assert_not_reached(); -- 2.43.0 Change the representation from sign bit repetitions to all bits equal to the sign bit, including the sign bit itself. The previous format has a problem in that it is difficult to recreate a valid sign mask after a shift operation: the "repetitions" part of the previous format meant that applying the same shift as for the value lead to an off-by-one value. The new format, including the sign bit itself, means that the sign mask can be manipulated in exactly the same way as the value, canonicalization is easier. Canonicalize the s_mask in fold_masks_zs, rather than requiring callers to do so. Treat 0 as a non-canonical but typeless input for no sign information, which will be reset as appropriate for the data type. We can easily fold in the data from z_mask while canonicalizing. Temporarily disable optimizations using s_mask while each operation is converted to use fold_masks_zs and to the new form. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 64 ++++++++++++-------------------------------------- 1 file changed, 15 insertions(+), 49 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ typedef struct TempOptInfo { QSIMPLEQ_HEAD(, MemCopyInfo) mem_copy; uint64_t val; uint64_t z_mask; /* mask bit is 0 if and only if value bit is 0 */ - uint64_t s_mask; /* a left-aligned mask of clrsb(value) bits. */ + uint64_t s_mask; /* mask bit is 1 if value bit matches msb */ } TempOptInfo; typedef struct OptContext { @@ -XXX,XX +XXX,XX @@ typedef struct OptContext { /* In flight values from optimization. */ uint64_t z_mask; /* mask bit is 0 iff value bit is 0 */ - uint64_t s_mask; /* mask of clrsb(value) bits */ + uint64_t s_mask; /* mask bit is 1 if value bit matches msb */ TCGType type; } OptContext; -/* Calculate the smask for a specific value. */ -static uint64_t smask_from_value(uint64_t value) -{ - int rep = clrsb64(value); - return ~(~0ull >> rep); -} - -/* - * Calculate the smask for a given set of known-zeros. - * If there are lots of zeros on the left, we can consider the remainder - * an unsigned field, and thus the corresponding signed field is one bit - * larger. - */ -static uint64_t smask_from_zmask(uint64_t zmask) -{ - /* - * Only the 0 bits are significant for zmask, thus the msb itself - * must be zero, else we have no sign information. - */ - int rep = clz64(zmask); - if (rep == 0) { - return 0; - } - rep -= 1; - return ~(~0ull >> rep); -} - -/* - * Recreate a properly left-aligned smask after manipulation. - * Some bit-shuffling, particularly shifts and rotates, may - * retain sign bits on the left, but may scatter disconnected - * sign bits on the right. Retain only what remains to the left. - */ -static uint64_t smask_from_smask(int64_t smask) -{ - /* Only the 1 bits are significant for smask */ - return smask_from_zmask(~smask); -} - static inline TempOptInfo *ts_info(TCGTemp *ts) { return ts->state_ptr; @@ -XXX,XX +XXX,XX @@ static void init_ts_info(OptContext *ctx, TCGTemp *ts) ti->is_const = true; ti->val = ts->val; ti->z_mask = ts->val; - ti->s_mask = smask_from_value(ts->val); + ti->s_mask = INT64_MIN >> clrsb64(ts->val); } else { ti->is_const = false; ti->z_mask = -1; @@ -XXX,XX +XXX,XX @@ static void finish_folding(OptContext *ctx, TCGOp *op) */ if (i == 0) { ts_info(ts)->z_mask = ctx->z_mask; - ts_info(ts)->s_mask = ctx->s_mask; } } } @@ -XXX,XX +XXX,XX @@ static bool fold_const2_commutative(OptContext *ctx, TCGOp *op) * The passed s_mask may be augmented by z_mask. */ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, - uint64_t z_mask, uint64_t s_mask) + uint64_t z_mask, int64_t s_mask) { const TCGOpDef *def = &tcg_op_defs[op->opc]; TCGTemp *ts; TempOptInfo *ti; + int rep; /* Only single-output opcodes are supported here. */ tcg_debug_assert(def->nb_oargs == 1); @@ -XXX,XX +XXX,XX @@ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, */ if (ctx->type == TCG_TYPE_I32) { z_mask = (int32_t)z_mask; - s_mask |= MAKE_64BIT_MASK(32, 32); + s_mask |= INT32_MIN; } if (z_mask == 0) { @@ -XXX,XX +XXX,XX @@ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, ti = ts_info(ts); ti->z_mask = z_mask; - ti->s_mask = s_mask | smask_from_zmask(z_mask); + + /* Canonicalize s_mask and incorporate data from z_mask. */ + rep = clz64(~s_mask); + rep = MAX(rep, clz64(z_mask)); + rep = MAX(rep - 1, 0); + ti->s_mask = INT64_MIN >> rep; + return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_exts(OptContext *ctx, TCGOp *op) ctx->z_mask = z_mask; ctx->s_mask = s_mask; - if (!type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + if (0 && !type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_sextract(OptContext *ctx, TCGOp *op) s_mask |= MAKE_64BIT_MASK(len, 64 - len); ctx->s_mask = s_mask; - if (pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + if (0 && pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_shift(OptContext *ctx, TCGOp *op) ctx->z_mask = do_constant_folding(op->opc, ctx->type, z_mask, sh); s_mask = do_constant_folding(op->opc, ctx->type, s_mask, sh); - ctx->s_mask = smask_from_smask(s_mask); return fold_masks(ctx, op); } -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static void finish_ebb(OptContext *ctx) remove_mem_copy_all(ctx); } -static void finish_folding(OptContext *ctx, TCGOp *op) +static bool finish_folding(OptContext *ctx, TCGOp *op) { const TCGOpDef *def = &tcg_op_defs[op->opc]; int i, nb_oargs; @@ -XXX,XX +XXX,XX @@ static void finish_folding(OptContext *ctx, TCGOp *op) ts_info(ts)->z_mask = ctx->z_mask; } } + return true; } /* @@ -XXX,XX +XXX,XX @@ static bool fold_add(OptContext *ctx, TCGOp *op) fold_xi_to_x(ctx, op, 0)) { return true; } - return false; + return finish_folding(ctx, op); } /* We cannot as yet do_constant_folding with vectors. */ @@ -XXX,XX +XXX,XX @@ static bool fold_add_vec(OptContext *ctx, TCGOp *op) fold_xi_to_x(ctx, op, 0)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_addsub2(OptContext *ctx, TCGOp *op, bool add) @@ -XXX,XX +XXX,XX @@ static bool fold_addsub2(OptContext *ctx, TCGOp *op, bool add) op->args[4] = arg_new_constant(ctx, bl); op->args[5] = arg_new_constant(ctx, bh); } - return false; + return finish_folding(ctx, op); } static bool fold_add2(OptContext *ctx, TCGOp *op) -- 2.43.0 Introduce ti_is_const, ti_const_val, ti_is_const_val. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static inline TempOptInfo *arg_info(TCGArg arg) return ts_info(arg_temp(arg)); } +static inline bool ti_is_const(TempOptInfo *ti) +{ + return ti->is_const; +} + +static inline uint64_t ti_const_val(TempOptInfo *ti) +{ + return ti->val; +} + +static inline bool ti_is_const_val(TempOptInfo *ti, uint64_t val) +{ + return ti_is_const(ti) && ti_const_val(ti) == val; +} + static inline bool ts_is_const(TCGTemp *ts) { - return ts_info(ts)->is_const; + return ti_is_const(ts_info(ts)); } static inline bool ts_is_const_val(TCGTemp *ts, uint64_t val) { - TempOptInfo *ti = ts_info(ts); - return ti->is_const && ti->val == val; + return ti_is_const_val(ts_info(ts), val); } static inline bool arg_is_const(TCGArg arg) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Sink mask computation below fold_affected_mask early exit. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_add2(OptContext *ctx, TCGOp *op) static bool fold_and(OptContext *ctx, TCGOp *op) { - uint64_t z1, z2; + uint64_t z1, z2, z_mask, s_mask; + TempOptInfo *t1, *t2; if (fold_const2_commutative(ctx, op) || fold_xi_to_i(ctx, op, 0) || @@ -XXX,XX +XXX,XX @@ static bool fold_and(OptContext *ctx, TCGOp *op) return true; } - z1 = arg_info(op->args[1])->z_mask; - z2 = arg_info(op->args[2])->z_mask; - ctx->z_mask = z1 & z2; - - /* - * Sign repetitions are perforce all identical, whether they are 1 or 0. - * Bitwise operations preserve the relative quantity of the repetitions. - */ - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; + t1 = arg_info(op->args[1]); + t2 = arg_info(op->args[2]); + z1 = t1->z_mask; + z2 = t2->z_mask; /* * Known-zeros does not imply known-ones. Therefore unless * arg2 is constant, we can't infer affected bits from it. */ - if (arg_is_const(op->args[2]) && - fold_affected_mask(ctx, op, z1 & ~z2)) { + if (ti_is_const(t2) && fold_affected_mask(ctx, op, z1 & ~z2)) { return true; } - return fold_masks(ctx, op); + z_mask = z1 & z2; + + /* + * Sign repetitions are perforce all identical, whether they are 1 or 0. + * Bitwise operations preserve the relative quantity of the repetitions. + */ + s_mask = t1->s_mask & t2->s_mask; + + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_andc(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Avoid double inversion of the value of second const operand. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_and(OptContext *ctx, TCGOp *op) static bool fold_andc(OptContext *ctx, TCGOp *op) { - uint64_t z1; + uint64_t z_mask, s_mask; + TempOptInfo *t1, *t2; if (fold_const2(ctx, op) || fold_xx_to_i(ctx, op, 0) || @@ -XXX,XX +XXX,XX @@ static bool fold_andc(OptContext *ctx, TCGOp *op) return true; } - z1 = arg_info(op->args[1])->z_mask; + t1 = arg_info(op->args[1]); + t2 = arg_info(op->args[2]); + z_mask = t1->z_mask; /* * Known-zeros does not imply known-ones. Therefore unless * arg2 is constant, we can't infer anything from it. */ - if (arg_is_const(op->args[2])) { - uint64_t z2 = ~arg_info(op->args[2])->z_mask; - if (fold_affected_mask(ctx, op, z1 & ~z2)) { + if (ti_is_const(t2)) { + uint64_t v2 = ti_const_val(t2); + if (fold_affected_mask(ctx, op, z_mask & v2)) { return true; } - z1 &= z2; + z_mask &= ~v2; } - ctx->z_mask = z1; - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return fold_masks(ctx, op); + s_mask = t1->s_mask & t2->s_mask; + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_brcond(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Always set s_mask along the BSWAP_OS path, since the result is being explicitly sign-extended. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_brcond2(OptContext *ctx, TCGOp *op) static bool fold_bswap(OptContext *ctx, TCGOp *op) { uint64_t z_mask, s_mask, sign; + TempOptInfo *t1 = arg_info(op->args[1]); - if (arg_is_const(op->args[1])) { - uint64_t t = arg_info(op->args[1])->val; - - t = do_constant_folding(op->opc, ctx->type, t, op->args[2]); - return tcg_opt_gen_movi(ctx, op, op->args[0], t); + if (ti_is_const(t1)) { + return tcg_opt_gen_movi(ctx, op, op->args[0], + do_constant_folding(op->opc, ctx->type, + ti_const_val(t1), + op->args[2])); } - z_mask = arg_info(op->args[1])->z_mask; - + z_mask = t1->z_mask; switch (op->opc) { case INDEX_op_bswap16_i32: case INDEX_op_bswap16_i64: @@ -XXX,XX +XXX,XX @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) /* If the sign bit may be 1, force all the bits above to 1. */ if (z_mask & sign) { z_mask |= sign; - s_mask = sign << 1; } + /* The value and therefore s_mask is explicitly sign-extended. */ + s_mask = sign; break; default: /* The high bits are undefined: force all bits above the sign to 1. */ z_mask |= sign << 1; break; } - ctx->z_mask = z_mask; - ctx->s_mask = s_mask; - return fold_masks(ctx, op); + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_call(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Compute s_mask from the union of the maximum count and the op2 fallback for op1 being zero. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_call(OptContext *ctx, TCGOp *op) static bool fold_count_zeros(OptContext *ctx, TCGOp *op) { - uint64_t z_mask; + uint64_t z_mask, s_mask; + TempOptInfo *t1 = arg_info(op->args[1]); + TempOptInfo *t2 = arg_info(op->args[2]); - if (arg_is_const(op->args[1])) { - uint64_t t = arg_info(op->args[1])->val; + if (ti_is_const(t1)) { + uint64_t t = ti_const_val(t1); if (t != 0) { t = do_constant_folding(op->opc, ctx->type, t, 0); @@ -XXX,XX +XXX,XX @@ static bool fold_count_zeros(OptContext *ctx, TCGOp *op) default: g_assert_not_reached(); } - ctx->z_mask = arg_info(op->args[2])->z_mask | z_mask; - return false; + s_mask = ~z_mask; + z_mask |= t2->z_mask; + s_mask &= t2->s_mask; + + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_ctpop(OptContext *ctx, TCGOp *op) -- 2.43.0 Add fold_masks_z as a trivial wrapper around fold_masks_zs. Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_masks_zs(OptContext *ctx, TCGOp *op, return true; } +static bool fold_masks_z(OptContext *ctx, TCGOp *op, uint64_t z_mask) +{ + return fold_masks_zs(ctx, op, z_mask, 0); +} + static bool fold_masks(OptContext *ctx, TCGOp *op) { return fold_masks_zs(ctx, op, ctx->z_mask, ctx->s_mask); @@ -XXX,XX +XXX,XX @@ static bool fold_count_zeros(OptContext *ctx, TCGOp *op) static bool fold_ctpop(OptContext *ctx, TCGOp *op) { + uint64_t z_mask; + if (fold_const1(ctx, op)) { return true; } switch (ctx->type) { case TCG_TYPE_I32: - ctx->z_mask = 32 | 31; + z_mask = 32 | 31; break; case TCG_TYPE_I64: - ctx->z_mask = 64 | 63; + z_mask = 64 | 63; break; default: g_assert_not_reached(); } - return false; + return fold_masks_z(ctx, op, z_mask); } static bool fold_deposit(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. When we fold to and, use fold_and. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_ctpop(OptContext *ctx, TCGOp *op) static bool fold_deposit(OptContext *ctx, TCGOp *op) { + TempOptInfo *t1 = arg_info(op->args[1]); + TempOptInfo *t2 = arg_info(op->args[2]); + int ofs = op->args[3]; + int len = op->args[4]; TCGOpcode and_opc; + uint64_t z_mask; - if (arg_is_const(op->args[1]) && arg_is_const(op->args[2])) { - uint64_t t1 = arg_info(op->args[1])->val; - uint64_t t2 = arg_info(op->args[2])->val; - - t1 = deposit64(t1, op->args[3], op->args[4], t2); - return tcg_opt_gen_movi(ctx, op, op->args[0], t1); + if (ti_is_const(t1) && ti_is_const(t2)) { + return tcg_opt_gen_movi(ctx, op, op->args[0], + deposit64(ti_const_val(t1), ofs, len, + ti_const_val(t2))); } switch (ctx->type) { @@ -XXX,XX +XXX,XX @@ static bool fold_deposit(OptContext *ctx, TCGOp *op) } /* Inserting a value into zero at offset 0. */ - if (arg_is_const_val(op->args[1], 0) && op->args[3] == 0) { - uint64_t mask = MAKE_64BIT_MASK(0, op->args[4]); + if (ti_is_const_val(t1, 0) && ofs == 0) { + uint64_t mask = MAKE_64BIT_MASK(0, len); op->opc = and_opc; op->args[1] = op->args[2]; op->args[2] = arg_new_constant(ctx, mask); - ctx->z_mask = mask & arg_info(op->args[1])->z_mask; - return false; + return fold_and(ctx, op); } /* Inserting zero into a value. */ - if (arg_is_const_val(op->args[2], 0)) { - uint64_t mask = deposit64(-1, op->args[3], op->args[4], 0); + if (ti_is_const_val(t2, 0)) { + uint64_t mask = deposit64(-1, ofs, len, 0); op->opc = and_opc; op->args[2] = arg_new_constant(ctx, mask); - ctx->z_mask = mask & arg_info(op->args[1])->z_mask; - return false; + return fold_and(ctx, op); } - ctx->z_mask = deposit64(arg_info(op->args[1])->z_mask, - op->args[3], op->args[4], - arg_info(op->args[2])->z_mask); - return false; + z_mask = deposit64(t1->z_mask, ofs, len, t2->z_mask); + return fold_masks_z(ctx, op, z_mask); } static bool fold_divide(OptContext *ctx, TCGOp *op) -- 2.43.0 The input which overlaps the sign bit of the output can have its input s_mask propagated to the output s_mask. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_deposit(OptContext *ctx, TCGOp *op) TempOptInfo *t2 = arg_info(op->args[2]); int ofs = op->args[3]; int len = op->args[4]; + int width; TCGOpcode and_opc; - uint64_t z_mask; + uint64_t z_mask, s_mask; if (ti_is_const(t1) && ti_is_const(t2)) { return tcg_opt_gen_movi(ctx, op, op->args[0], @@ -XXX,XX +XXX,XX @@ static bool fold_deposit(OptContext *ctx, TCGOp *op) switch (ctx->type) { case TCG_TYPE_I32: and_opc = INDEX_op_and_i32; + width = 32; break; case TCG_TYPE_I64: and_opc = INDEX_op_and_i64; + width = 64; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static bool fold_deposit(OptContext *ctx, TCGOp *op) return fold_and(ctx, op); } + /* The s_mask from the top portion of the deposit is still valid. */ + if (ofs + len == width) { + s_mask = t2->s_mask << ofs; + } else { + s_mask = t1->s_mask & ~MAKE_64BIT_MASK(0, ofs + len); + } + z_mask = deposit64(t1->z_mask, ofs, len, t2->z_mask); - return fold_masks_z(ctx, op, z_mask); + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_divide(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_divide(OptContext *ctx, TCGOp *op) fold_xi_to_x(ctx, op, 1)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_dup(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_dup(OptContext *ctx, TCGOp *op) t = dup_const(TCGOP_VECE(op), t); return tcg_opt_gen_movi(ctx, op, op->args[0], t); } - return false; + return finish_folding(ctx, op); } static bool fold_dup2(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_dup2(OptContext *ctx, TCGOp *op) op->opc = INDEX_op_dup_vec; TCGOP_VECE(op) = MO_32; } - return false; + return finish_folding(ctx, op); } static bool fold_eqv(OptContext *ctx, TCGOp *op) -- 2.43.0 Add fold_masks_s as a trivial wrapper around fold_masks_zs. Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_masks_z(OptContext *ctx, TCGOp *op, uint64_t z_mask) return fold_masks_zs(ctx, op, z_mask, 0); } +static bool fold_masks_s(OptContext *ctx, TCGOp *op, uint64_t s_mask) +{ + return fold_masks_zs(ctx, op, -1, s_mask); +} + static bool fold_masks(OptContext *ctx, TCGOp *op) { return fold_masks_zs(ctx, op, ctx->z_mask, ctx->s_mask); @@ -XXX,XX +XXX,XX @@ static bool fold_dup2(OptContext *ctx, TCGOp *op) static bool fold_eqv(OptContext *ctx, TCGOp *op) { + uint64_t s_mask; + if (fold_const2_commutative(ctx, op) || fold_xi_to_x(ctx, op, -1) || fold_xi_to_not(ctx, op, 0)) { return true; } - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return false; + s_mask = arg_info(op->args[1])->s_mask + & arg_info(op->args[2])->s_mask; + return fold_masks_s(ctx, op, s_mask); } static bool fold_extract(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_eqv(OptContext *ctx, TCGOp *op) static bool fold_extract(OptContext *ctx, TCGOp *op) { uint64_t z_mask_old, z_mask; + TempOptInfo *t1 = arg_info(op->args[1]); int pos = op->args[2]; int len = op->args[3]; - if (arg_is_const(op->args[1])) { - uint64_t t; - - t = arg_info(op->args[1])->val; - t = extract64(t, pos, len); - return tcg_opt_gen_movi(ctx, op, op->args[0], t); + if (ti_is_const(t1)) { + return tcg_opt_gen_movi(ctx, op, op->args[0], + extract64(ti_const_val(t1), pos, len)); } - z_mask_old = arg_info(op->args[1])->z_mask; + z_mask_old = t1->z_mask; z_mask = extract64(z_mask_old, pos, len); if (pos == 0 && fold_affected_mask(ctx, op, z_mask_old ^ z_mask)) { return true; } - ctx->z_mask = z_mask; - return fold_masks(ctx, op); + return fold_masks_z(ctx, op, z_mask); } static bool fold_extract2(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_extract2(OptContext *ctx, TCGOp *op) } return tcg_opt_gen_movi(ctx, op, op->args[0], v1 | v2); } - return false; + return finish_folding(ctx, op); } static bool fold_exts(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Explicitly sign-extend z_mask instead of doing that manually. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_extract2(OptContext *ctx, TCGOp *op) static bool fold_exts(OptContext *ctx, TCGOp *op) { - uint64_t s_mask_old, s_mask, z_mask, sign; + uint64_t s_mask_old, s_mask, z_mask; bool type_change = false; + TempOptInfo *t1; if (fold_const1(ctx, op)) { return true; } - z_mask = arg_info(op->args[1])->z_mask; - s_mask = arg_info(op->args[1])->s_mask; + t1 = arg_info(op->args[1]); + z_mask = t1->z_mask; + s_mask = t1->s_mask; s_mask_old = s_mask; switch (op->opc) { CASE_OP_32_64(ext8s): - sign = INT8_MIN; - z_mask = (uint8_t)z_mask; + s_mask |= INT8_MIN; + z_mask = (int8_t)z_mask; break; CASE_OP_32_64(ext16s): - sign = INT16_MIN; - z_mask = (uint16_t)z_mask; + s_mask |= INT16_MIN; + z_mask = (int16_t)z_mask; break; case INDEX_op_ext_i32_i64: type_change = true; QEMU_FALLTHROUGH; case INDEX_op_ext32s_i64: - sign = INT32_MIN; - z_mask = (uint32_t)z_mask; + s_mask |= INT32_MIN; + z_mask = (int32_t)z_mask; break; default: g_assert_not_reached(); } - if (z_mask & sign) { - z_mask |= sign; - } - s_mask |= sign << 1; - - ctx->z_mask = z_mask; - ctx->s_mask = s_mask; if (0 && !type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } - return fold_masks(ctx, op); + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_extu(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_extu(OptContext *ctx, TCGOp *op) g_assert_not_reached(); } - ctx->z_mask = z_mask; if (!type_change && fold_affected_mask(ctx, op, z_mask_old ^ z_mask)) { return true; } - return fold_masks(ctx, op); + + return fold_masks_z(ctx, op, z_mask); } static bool fold_mb(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_mov(OptContext *ctx, TCGOp *op) static bool fold_movcond(OptContext *ctx, TCGOp *op) { + uint64_t z_mask, s_mask; + TempOptInfo *tt, *ft; int i; /* If true and false values are the same, eliminate the cmp. */ @@ -XXX,XX +XXX,XX @@ static bool fold_movcond(OptContext *ctx, TCGOp *op) return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[4 - i]); } - ctx->z_mask = arg_info(op->args[3])->z_mask - | arg_info(op->args[4])->z_mask; - ctx->s_mask = arg_info(op->args[3])->s_mask - & arg_info(op->args[4])->s_mask; + tt = arg_info(op->args[3]); + ft = arg_info(op->args[4]); + z_mask = tt->z_mask | ft->z_mask; + s_mask = tt->s_mask & ft->s_mask; - if (arg_is_const(op->args[3]) && arg_is_const(op->args[4])) { - uint64_t tv = arg_info(op->args[3])->val; - uint64_t fv = arg_info(op->args[4])->val; + if (ti_is_const(tt) && ti_is_const(ft)) { + uint64_t tv = ti_const_val(tt); + uint64_t fv = ti_const_val(ft); TCGOpcode opc, negopc = 0; TCGCond cond = op->args[5]; @@ -XXX,XX +XXX,XX @@ static bool fold_movcond(OptContext *ctx, TCGOp *op) } } } - return false; + + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_mul(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_mul(OptContext *ctx, TCGOp *op) fold_xi_to_x(ctx, op, 1)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_mul_highpart(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_mul_highpart(OptContext *ctx, TCGOp *op) fold_xi_to_i(ctx, op, 0)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_multiply2(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_multiply2(OptContext *ctx, TCGOp *op) tcg_opt_gen_movi(ctx, op2, rh, h); return true; } - return false; + return finish_folding(ctx, op); } static bool fold_nand(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_multiply2(OptContext *ctx, TCGOp *op) static bool fold_nand(OptContext *ctx, TCGOp *op) { + uint64_t s_mask; + if (fold_const2_commutative(ctx, op) || fold_xi_to_not(ctx, op, -1)) { return true; } - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return false; + s_mask = arg_info(op->args[1])->s_mask + & arg_info(op->args[2])->s_mask; + return fold_masks_s(ctx, op, s_mask); } static bool fold_neg_no_const(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_neg_no_const(OptContext *ctx, TCGOp *op) { /* Set to 1 all bits to the left of the rightmost. */ uint64_t z_mask = arg_info(op->args[1])->z_mask; - ctx->z_mask = -(z_mask & -z_mask); + z_mask = -(z_mask & -z_mask); - /* - * Because of fold_sub_to_neg, we want to always return true, - * via finish_folding. - */ - finish_folding(ctx, op); - return true; + return fold_masks_z(ctx, op, z_mask); } static bool fold_neg(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_neg(OptContext *ctx, TCGOp *op) static bool fold_nor(OptContext *ctx, TCGOp *op) { + uint64_t s_mask; + if (fold_const2_commutative(ctx, op) || fold_xi_to_not(ctx, op, 0)) { return true; } - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return false; + s_mask = arg_info(op->args[1])->s_mask + & arg_info(op->args[2])->s_mask; + return fold_masks_s(ctx, op, s_mask); } static bool fold_not(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_not(OptContext *ctx, TCGOp *op) if (fold_const1(ctx, op)) { return true; } - - ctx->s_mask = arg_info(op->args[1])->s_mask; - - /* Because of fold_to_not, we want to always return true, via finish. */ - finish_folding(ctx, op); - return true; + return fold_masks_s(ctx, op, arg_info(op->args[1])->s_mask); } static bool fold_or(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_not(OptContext *ctx, TCGOp *op) static bool fold_or(OptContext *ctx, TCGOp *op) { + uint64_t z_mask, s_mask; + TempOptInfo *t1, *t2; + if (fold_const2_commutative(ctx, op) || fold_xi_to_x(ctx, op, 0) || fold_xx_to_x(ctx, op)) { return true; } - ctx->z_mask = arg_info(op->args[1])->z_mask - | arg_info(op->args[2])->z_mask; - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return fold_masks(ctx, op); + t1 = arg_info(op->args[1]); + t2 = arg_info(op->args[2]); + z_mask = t1->z_mask | t2->z_mask; + s_mask = t1->s_mask & t2->s_mask; + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_orc(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_or(OptContext *ctx, TCGOp *op) static bool fold_orc(OptContext *ctx, TCGOp *op) { + uint64_t s_mask; + if (fold_const2(ctx, op) || fold_xx_to_i(ctx, op, -1) || fold_xi_to_x(ctx, op, -1) || @@ -XXX,XX +XXX,XX @@ static bool fold_orc(OptContext *ctx, TCGOp *op) return true; } - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return false; + s_mask = arg_info(op->args[1])->s_mask + & arg_info(op->args[2])->s_mask; + return fold_masks_s(ctx, op, s_mask); } static bool fold_qemu_ld(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Be careful not to call fold_masks_zs when the memory operation is wide enough to require multiple outputs, so split into two functions: fold_qemu_ld_1reg and fold_qemu_ld_2reg. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_orc(OptContext *ctx, TCGOp *op) return fold_masks_s(ctx, op, s_mask); } -static bool fold_qemu_ld(OptContext *ctx, TCGOp *op) +static bool fold_qemu_ld_1reg(OptContext *ctx, TCGOp *op) { const TCGOpDef *def = &tcg_op_defs[op->opc]; MemOpIdx oi = op->args[def->nb_oargs + def->nb_iargs]; MemOp mop = get_memop(oi); int width = 8 * memop_size(mop); + uint64_t z_mask = -1, s_mask = 0; if (width < 64) { if (mop & MO_SIGN) { - ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width); + s_mask = MAKE_64BIT_MASK(width - 1, 64 - (width - 1)); } else { - ctx->z_mask = MAKE_64BIT_MASK(0, width); + z_mask = MAKE_64BIT_MASK(0, width); } } /* Opcodes that touch guest memory stop the mb optimization. */ ctx->prev_mb = NULL; - return false; + + return fold_masks_zs(ctx, op, z_mask, s_mask); +} + +static bool fold_qemu_ld_2reg(OptContext *ctx, TCGOp *op) +{ + /* Opcodes that touch guest memory stop the mb optimization. */ + ctx->prev_mb = NULL; + return finish_folding(ctx, op); } static bool fold_qemu_st(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ void tcg_optimize(TCGContext *s) break; case INDEX_op_qemu_ld_a32_i32: case INDEX_op_qemu_ld_a64_i32: + done = fold_qemu_ld_1reg(&ctx, op); + break; case INDEX_op_qemu_ld_a32_i64: case INDEX_op_qemu_ld_a64_i64: + if (TCG_TARGET_REG_BITS == 64) { + done = fold_qemu_ld_1reg(&ctx, op); + break; + } + QEMU_FALLTHROUGH; case INDEX_op_qemu_ld_a32_i128: case INDEX_op_qemu_ld_a64_i128: - done = fold_qemu_ld(&ctx, op); + done = fold_qemu_ld_2reg(&ctx, op); break; case INDEX_op_qemu_st8_a32_i32: case INDEX_op_qemu_st8_a64_i32: -- 2.43.0 Stores have no output operands, and so need no further work. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_qemu_st(OptContext *ctx, TCGOp *op) { /* Opcodes that touch guest memory stop the mb optimization. */ ctx->prev_mb = NULL; - return false; + return true; } static bool fold_remainder(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_st(OptContext *ctx, TCGOp *op) if (op->args[1] != tcgv_ptr_arg(tcg_env)) { remove_mem_copy_all(ctx); - return false; + return true; } switch (op->opc) { @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_st(OptContext *ctx, TCGOp *op) g_assert_not_reached(); } remove_mem_copy_in(ctx, ofs, ofs + lm1); - return false; + return true; } static bool fold_tcg_st_memcopy(OptContext *ctx, TCGOp *op) @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_st_memcopy(OptContext *ctx, TCGOp *op) TCGType type; if (op->args[1] != tcgv_ptr_arg(tcg_env)) { - fold_tcg_st(ctx, op); - return false; + return fold_tcg_st(ctx, op); } src = arg_temp(op->args[0]); @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_st_memcopy(OptContext *ctx, TCGOp *op) last = ofs + tcg_type_size(type) - 1; remove_mem_copy_in(ctx, ofs, last); record_mem_copy(ctx, type, src, ofs, last); - return false; + return true; } static bool fold_xor(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_remainder(OptContext *ctx, TCGOp *op) fold_xx_to_i(ctx, op, 0)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_setcond_zmask(OptContext *ctx, TCGOp *op, bool neg) -- 2.43.0 Change return from bool to int; distinguish between complete folding, simplification, and no change. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_remainder(OptContext *ctx, TCGOp *op) return finish_folding(ctx, op); } -static bool fold_setcond_zmask(OptContext *ctx, TCGOp *op, bool neg) +/* Return 1 if finished, -1 if simplified, 0 if unchanged. */ +static int fold_setcond_zmask(OptContext *ctx, TCGOp *op, bool neg) { uint64_t a_zmask, b_val; TCGCond cond; @@ -XXX,XX +XXX,XX @@ static bool fold_setcond_zmask(OptContext *ctx, TCGOp *op, bool neg) op->opc = xor_opc; op->args[2] = arg_new_constant(ctx, 1); } - return false; + return -1; } } - - return false; + return 0; } static void fold_setcond_tst_pow2(OptContext *ctx, TCGOp *op, bool neg) @@ -XXX,XX +XXX,XX @@ static bool fold_setcond(OptContext *ctx, TCGOp *op) return tcg_opt_gen_movi(ctx, op, op->args[0], i); } - if (fold_setcond_zmask(ctx, op, false)) { + i = fold_setcond_zmask(ctx, op, false); + if (i > 0) { return true; } - fold_setcond_tst_pow2(ctx, op, false); + if (i == 0) { + fold_setcond_tst_pow2(ctx, op, false); + } ctx->z_mask = 1; return false; @@ -XXX,XX +XXX,XX @@ static bool fold_negsetcond(OptContext *ctx, TCGOp *op) return tcg_opt_gen_movi(ctx, op, op->args[0], -i); } - if (fold_setcond_zmask(ctx, op, true)) { + i = fold_setcond_zmask(ctx, op, true); + if (i > 0) { return true; } - fold_setcond_tst_pow2(ctx, op, true); + if (i == 0) { + fold_setcond_tst_pow2(ctx, op, true); + } /* Value is {0,-1} so all bits are repetitions of the sign. */ ctx->s_mask = -1; -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_setcond(OptContext *ctx, TCGOp *op) fold_setcond_tst_pow2(ctx, op, false); } - ctx->z_mask = 1; - return false; + return fold_masks_z(ctx, op, 1); } static bool fold_negsetcond(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_negsetcond(OptContext *ctx, TCGOp *op) } /* Value is {0,-1} so all bits are repetitions of the sign. */ - ctx->s_mask = -1; - return false; + return fold_masks_s(ctx, op, -1); } static bool fold_setcond2(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op) return fold_setcond(ctx, op); } - ctx->z_mask = 1; - return false; + return fold_masks_z(ctx, op, 1); do_setcond_const: return tcg_opt_gen_movi(ctx, op, op->args[0], i); -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_cmp_vec(OptContext *ctx, TCGOp *op) if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) { op->args[3] = tcg_swap_cond(op->args[3]); } - return false; + return finish_folding(ctx, op); } static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op) if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) { op->args[5] = tcg_invert_cond(op->args[5]); } - return false; + return finish_folding(ctx, op); } static bool fold_sextract(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op) static bool fold_sextract(OptContext *ctx, TCGOp *op) { uint64_t z_mask, s_mask, s_mask_old; + TempOptInfo *t1 = arg_info(op->args[1]); int pos = op->args[2]; int len = op->args[3]; - if (arg_is_const(op->args[1])) { - uint64_t t; - - t = arg_info(op->args[1])->val; - t = sextract64(t, pos, len); - return tcg_opt_gen_movi(ctx, op, op->args[0], t); + if (ti_is_const(t1)) { + return tcg_opt_gen_movi(ctx, op, op->args[0], + sextract64(ti_const_val(t1), pos, len)); } - z_mask = arg_info(op->args[1])->z_mask; - z_mask = sextract64(z_mask, pos, len); - ctx->z_mask = z_mask; - - s_mask_old = arg_info(op->args[1])->s_mask; - s_mask = sextract64(s_mask_old, pos, len); - s_mask |= MAKE_64BIT_MASK(len, 64 - len); - ctx->s_mask = s_mask; + s_mask_old = t1->s_mask; + s_mask = s_mask_old >> pos; + s_mask |= -1ull << (len - 1); if (0 && pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } - return fold_masks(ctx, op); + z_mask = sextract64(t1->z_mask, pos, len); + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_shift(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_sextract(OptContext *ctx, TCGOp *op) static bool fold_shift(OptContext *ctx, TCGOp *op) { uint64_t s_mask, z_mask, sign; + TempOptInfo *t1, *t2; if (fold_const2(ctx, op) || fold_ix_to_i(ctx, op, 0) || @@ -XXX,XX +XXX,XX @@ static bool fold_shift(OptContext *ctx, TCGOp *op) return true; } - s_mask = arg_info(op->args[1])->s_mask; - z_mask = arg_info(op->args[1])->z_mask; + t1 = arg_info(op->args[1]); + t2 = arg_info(op->args[2]); + s_mask = t1->s_mask; + z_mask = t1->z_mask; - if (arg_is_const(op->args[2])) { - int sh = arg_info(op->args[2])->val; - - ctx->z_mask = do_constant_folding(op->opc, ctx->type, z_mask, sh); + if (ti_is_const(t2)) { + int sh = ti_const_val(t2); + z_mask = do_constant_folding(op->opc, ctx->type, z_mask, sh); s_mask = do_constant_folding(op->opc, ctx->type, s_mask, sh); - return fold_masks(ctx, op); + return fold_masks_zs(ctx, op, z_mask, s_mask); } switch (op->opc) { @@ -XXX,XX +XXX,XX @@ static bool fold_shift(OptContext *ctx, TCGOp *op) * Arithmetic right shift will not reduce the number of * input sign repetitions. */ - ctx->s_mask = s_mask; - break; + return fold_masks_s(ctx, op, s_mask); CASE_OP_32_64(shr): /* * If the sign bit is known zero, then logical right shift - * will not reduced the number of input sign repetitions. + * will not reduce the number of input sign repetitions. */ - sign = (s_mask & -s_mask) >> 1; + sign = -s_mask; if (sign && !(z_mask & sign)) { - ctx->s_mask = s_mask; + return fold_masks_s(ctx, op, s_mask); } break; default: break; } - return false; + return finish_folding(ctx, op); } static bool fold_sub_to_neg(OptContext *ctx, TCGOp *op) -- 2.43.0 Merge the two conditions, sign != 0 && !(z_mask & sign), by testing ~z_mask & sign. If sign == 0, the logical and will produce false. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_sextract(OptContext *ctx, TCGOp *op) static bool fold_shift(OptContext *ctx, TCGOp *op) { - uint64_t s_mask, z_mask, sign; + uint64_t s_mask, z_mask; TempOptInfo *t1, *t2; if (fold_const2(ctx, op) || @@ -XXX,XX +XXX,XX @@ static bool fold_shift(OptContext *ctx, TCGOp *op) * If the sign bit is known zero, then logical right shift * will not reduce the number of input sign repetitions. */ - sign = -s_mask; - if (sign && !(z_mask & sign)) { + if (~z_mask & -s_mask) { return fold_masks_s(ctx, op, s_mask); } break; -- 2.43.0 Duplicate fold_sub_vec into fold_sub instead of calling it, now that fold_sub_vec always returns true. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_sub_vec(OptContext *ctx, TCGOp *op) fold_sub_to_neg(ctx, op)) { return true; } - return false; + return finish_folding(ctx, op); } static bool fold_sub(OptContext *ctx, TCGOp *op) { - if (fold_const2(ctx, op) || fold_sub_vec(ctx, op)) { + if (fold_const2(ctx, op) || + fold_xx_to_i(ctx, op, 0) || + fold_xi_to_x(ctx, op, 0) || + fold_sub_to_neg(ctx, op)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_sub(OptContext *ctx, TCGOp *op) ? INDEX_op_add_i32 : INDEX_op_add_i64); op->args[2] = arg_new_constant(ctx, -val); } - return false; + return finish_folding(ctx, op); } static bool fold_sub2(OptContext *ctx, TCGOp *op) -- 2.43.0 Avoid the use of the OptContext slots. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_sub2(OptContext *ctx, TCGOp *op) static bool fold_tcg_ld(OptContext *ctx, TCGOp *op) { + uint64_t z_mask = -1, s_mask = 0; + /* We can't do any folding with a load, but we can record bits. */ switch (op->opc) { CASE_OP_32_64(ld8s): - ctx->s_mask = MAKE_64BIT_MASK(8, 56); + s_mask = INT8_MIN; break; CASE_OP_32_64(ld8u): - ctx->z_mask = MAKE_64BIT_MASK(0, 8); + z_mask = MAKE_64BIT_MASK(0, 8); break; CASE_OP_32_64(ld16s): - ctx->s_mask = MAKE_64BIT_MASK(16, 48); + s_mask = INT16_MIN; break; CASE_OP_32_64(ld16u): - ctx->z_mask = MAKE_64BIT_MASK(0, 16); + z_mask = MAKE_64BIT_MASK(0, 16); break; case INDEX_op_ld32s_i64: - ctx->s_mask = MAKE_64BIT_MASK(32, 32); + s_mask = INT32_MIN; break; case INDEX_op_ld32u_i64: - ctx->z_mask = MAKE_64BIT_MASK(0, 32); + z_mask = MAKE_64BIT_MASK(0, 32); break; default: g_assert_not_reached(); } - return false; + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_tcg_ld_memcopy(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_ld_memcopy(OptContext *ctx, TCGOp *op) TCGType type; if (op->args[1] != tcgv_ptr_arg(tcg_env)) { - return false; + return finish_folding(ctx, op); } type = ctx->type; -- 2.43.0 Avoid the use of the OptContext slots. Find TempOptInfo once. Remove fold_masks as the function becomes unused. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_masks_s(OptContext *ctx, TCGOp *op, uint64_t s_mask) return fold_masks_zs(ctx, op, -1, s_mask); } -static bool fold_masks(OptContext *ctx, TCGOp *op) -{ - return fold_masks_zs(ctx, op, ctx->z_mask, ctx->s_mask); -} - /* * An "affected" mask bit is 0 if and only if the result is identical * to the first input. Thus if the entire mask is 0, the operation @@ -XXX,XX +XXX,XX @@ static bool fold_tcg_st_memcopy(OptContext *ctx, TCGOp *op) static bool fold_xor(OptContext *ctx, TCGOp *op) { + uint64_t z_mask, s_mask; + TempOptInfo *t1, *t2; + if (fold_const2_commutative(ctx, op) || fold_xx_to_i(ctx, op, 0) || fold_xi_to_x(ctx, op, 0) || @@ -XXX,XX +XXX,XX @@ static bool fold_xor(OptContext *ctx, TCGOp *op) return true; } - ctx->z_mask = arg_info(op->args[1])->z_mask - | arg_info(op->args[2])->z_mask; - ctx->s_mask = arg_info(op->args[1])->s_mask - & arg_info(op->args[2])->s_mask; - return fold_masks(ctx, op); + t1 = arg_info(op->args[1]); + t2 = arg_info(op->args[2]); + z_mask = t1->z_mask | t2->z_mask; + s_mask = t1->s_mask & t2->s_mask; + return fold_masks_zs(ctx, op, z_mask, s_mask); } static bool fold_bitsel_vec(OptContext *ctx, TCGOp *op) -- 2.43.0 Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_bitsel_vec(OptContext *ctx, TCGOp *op) return fold_orc(ctx, op); } } - return false; + return finish_folding(ctx, op); } /* Propagate constants and copies, fold constant expressions. */ -- 2.43.0 All non-default cases now finish folding within each function. Do the same with the default case and assert it is done after. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ void tcg_optimize(TCGContext *s) done = true; break; default: + done = finish_folding(&ctx, op); break; } - - if (!done) { - finish_folding(&ctx, op); - } + tcg_debug_assert(done); } } -- 2.43.0 All mask setting is now done with parameters via fold_masks_*. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ typedef struct OptContext { QSIMPLEQ_HEAD(, MemCopyInfo) mem_free; /* In flight values from optimization. */ - uint64_t z_mask; /* mask bit is 0 iff value bit is 0 */ - uint64_t s_mask; /* mask bit is 1 if value bit matches msb */ TCGType type; } OptContext; @@ -XXX,XX +XXX,XX @@ static bool finish_folding(OptContext *ctx, TCGOp *op) for (i = 0; i < nb_oargs; i++) { TCGTemp *ts = arg_temp(op->args[i]); reset_ts(ctx, ts); - /* - * Save the corresponding known-zero/sign bits mask for the - * first output argument (only one supported so far). - */ - if (i == 0) { - ts_info(ts)->z_mask = ctx->z_mask; - } } return true; } @@ -XXX,XX +XXX,XX @@ void tcg_optimize(TCGContext *s) ctx.type = TCG_TYPE_I32; } - /* Assume all bits affected, no bits known zero, no sign reps. */ - ctx.z_mask = -1; - ctx.s_mask = 0; - /* * Process each opcode. * Sorted alphabetically by opcode as much as possible. -- 2.43.0 All instances of s_mask have been converted to the new representation. We can now re-enable usage. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_exts(OptContext *ctx, TCGOp *op) g_assert_not_reached(); } - if (0 && !type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + if (!type_change && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool fold_sextract(OptContext *ctx, TCGOp *op) s_mask = s_mask_old >> pos; s_mask |= -1ull << (len - 1); - if (0 && pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { + if (pos == 0 && fold_affected_mask(ctx, op, s_mask & ~s_mask_old)) { return true; } -- 2.43.0 The big comment just above says functions should be sorted. Add forward declarations as needed. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 114 +++++++++++++++++++++++++------------------------ 1 file changed, 59 insertions(+), 55 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_xx_to_x(OptContext *ctx, TCGOp *op) * 3) those that produce information about the result value. */ +static bool fold_or(OptContext *ctx, TCGOp *op); +static bool fold_orc(OptContext *ctx, TCGOp *op); +static bool fold_xor(OptContext *ctx, TCGOp *op); + static bool fold_add(OptContext *ctx, TCGOp *op) { if (fold_const2_commutative(ctx, op) || @@ -XXX,XX +XXX,XX @@ static bool fold_andc(OptContext *ctx, TCGOp *op) return fold_masks_zs(ctx, op, z_mask, s_mask); } +static bool fold_bitsel_vec(OptContext *ctx, TCGOp *op) +{ + /* If true and false values are the same, eliminate the cmp. */ + if (args_are_copies(op->args[2], op->args[3])) { + return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[2]); + } + + if (arg_is_const(op->args[2]) && arg_is_const(op->args[3])) { + uint64_t tv = arg_info(op->args[2])->val; + uint64_t fv = arg_info(op->args[3])->val; + + if (tv == -1 && fv == 0) { + return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[1]); + } + if (tv == 0 && fv == -1) { + if (TCG_TARGET_HAS_not_vec) { + op->opc = INDEX_op_not_vec; + return fold_not(ctx, op); + } else { + op->opc = INDEX_op_xor_vec; + op->args[2] = arg_new_constant(ctx, -1); + return fold_xor(ctx, op); + } + } + } + if (arg_is_const(op->args[2])) { + uint64_t tv = arg_info(op->args[2])->val; + if (tv == -1) { + op->opc = INDEX_op_or_vec; + op->args[2] = op->args[3]; + return fold_or(ctx, op); + } + if (tv == 0 && TCG_TARGET_HAS_andc_vec) { + op->opc = INDEX_op_andc_vec; + op->args[2] = op->args[1]; + op->args[1] = op->args[3]; + return fold_andc(ctx, op); + } + } + if (arg_is_const(op->args[3])) { + uint64_t fv = arg_info(op->args[3])->val; + if (fv == 0) { + op->opc = INDEX_op_and_vec; + return fold_and(ctx, op); + } + if (fv == -1 && TCG_TARGET_HAS_orc_vec) { + op->opc = INDEX_op_orc_vec; + op->args[2] = op->args[1]; + op->args[1] = op->args[3]; + return fold_orc(ctx, op); + } + } + return finish_folding(ctx, op); +} + static bool fold_brcond(OptContext *ctx, TCGOp *op) { int i = do_constant_folding_cond1(ctx, op, NO_DEST, &op->args[0], @@ -XXX,XX +XXX,XX @@ static bool fold_xor(OptContext *ctx, TCGOp *op) return fold_masks_zs(ctx, op, z_mask, s_mask); } -static bool fold_bitsel_vec(OptContext *ctx, TCGOp *op) -{ - /* If true and false values are the same, eliminate the cmp. */ - if (args_are_copies(op->args[2], op->args[3])) { - return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[2]); - } - - if (arg_is_const(op->args[2]) && arg_is_const(op->args[3])) { - uint64_t tv = arg_info(op->args[2])->val; - uint64_t fv = arg_info(op->args[3])->val; - - if (tv == -1 && fv == 0) { - return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[1]); - } - if (tv == 0 && fv == -1) { - if (TCG_TARGET_HAS_not_vec) { - op->opc = INDEX_op_not_vec; - return fold_not(ctx, op); - } else { - op->opc = INDEX_op_xor_vec; - op->args[2] = arg_new_constant(ctx, -1); - return fold_xor(ctx, op); - } - } - } - if (arg_is_const(op->args[2])) { - uint64_t tv = arg_info(op->args[2])->val; - if (tv == -1) { - op->opc = INDEX_op_or_vec; - op->args[2] = op->args[3]; - return fold_or(ctx, op); - } - if (tv == 0 && TCG_TARGET_HAS_andc_vec) { - op->opc = INDEX_op_andc_vec; - op->args[2] = op->args[1]; - op->args[1] = op->args[3]; - return fold_andc(ctx, op); - } - } - if (arg_is_const(op->args[3])) { - uint64_t fv = arg_info(op->args[3])->val; - if (fv == 0) { - op->opc = INDEX_op_and_vec; - return fold_and(ctx, op); - } - if (fv == -1 && TCG_TARGET_HAS_orc_vec) { - op->opc = INDEX_op_orc_vec; - op->args[2] = op->args[1]; - op->args[1] = op->args[3]; - return fold_orc(ctx, op); - } - } - return finish_folding(ctx, op); -} - /* Propagate constants and copies, fold constant expressions. */ void tcg_optimize(TCGContext *s) { -- 2.43.0 The big comment just above says functions should be sorted. Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 60 +++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index XXXXXXX..XXXXXXX 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -XXX,XX +XXX,XX @@ static bool fold_call(OptContext *ctx, TCGOp *op) return true; } +static bool fold_cmp_vec(OptContext *ctx, TCGOp *op) +{ + /* Canonicalize the comparison to put immediate second. */ + if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) { + op->args[3] = tcg_swap_cond(op->args[3]); + } + return finish_folding(ctx, op); +} + +static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op) +{ + /* If true and false values are the same, eliminate the cmp. */ + if (args_are_copies(op->args[3], op->args[4])) { + return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[3]); + } + + /* Canonicalize the comparison to put immediate second. */ + if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) { + op->args[5] = tcg_swap_cond(op->args[5]); + } + /* + * Canonicalize the "false" input reg to match the destination, + * so that the tcg backend can implement "move if true". + */ + if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) { + op->args[5] = tcg_invert_cond(op->args[5]); + } + return finish_folding(ctx, op); +} + static bool fold_count_zeros(OptContext *ctx, TCGOp *op) { uint64_t z_mask, s_mask; @@ -XXX,XX +XXX,XX @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op) return tcg_opt_gen_movi(ctx, op, op->args[0], i); } -static bool fold_cmp_vec(OptContext *ctx, TCGOp *op) -{ - /* Canonicalize the comparison to put immediate second. */ - if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) { - op->args[3] = tcg_swap_cond(op->args[3]); - } - return finish_folding(ctx, op); -} - -static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op) -{ - /* If true and false values are the same, eliminate the cmp. */ - if (args_are_copies(op->args[3], op->args[4])) { - return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[3]); - } - - /* Canonicalize the comparison to put immediate second. */ - if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) { - op->args[5] = tcg_swap_cond(op->args[5]); - } - /* - * Canonicalize the "false" input reg to match the destination, - * so that the tcg backend can implement "move if true". - */ - if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) { - op->args[5] = tcg_invert_cond(op->args[5]); - } - return finish_folding(ctx, op); -} - static bool fold_sextract(OptContext *ctx, TCGOp *op) { uint64_t z_mask, s_mask, s_mask_old; -- 2.43.0 We currently have a flag, float_muladd_halve_result, to scale the result by 2**-1. Extend this to handle arbitrary scaling. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/fpu/softfloat.h | 6 ++++ fpu/softfloat.c | 58 ++++++++++++++++++++++----------------- fpu/softfloat-parts.c.inc | 7 +++-- 3 files changed, 44 insertions(+), 27 deletions(-) diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -XXX,XX +XXX,XX @@ float16 float16_add(float16, float16, float_status *status); float16 float16_sub(float16, float16, float_status *status); float16 float16_mul(float16, float16, float_status *status); float16 float16_muladd(float16, float16, float16, int, float_status *status); +float16 float16_muladd_scalbn(float16, float16, float16, + int, int, float_status *status); float16 float16_div(float16, float16, float_status *status); float16 float16_scalbn(float16, int, float_status *status); float16 float16_min(float16, float16, float_status *status); @@ -XXX,XX +XXX,XX @@ float32 float32_mul(float32, float32, float_status *status); float32 float32_div(float32, float32, float_status *status); float32 float32_rem(float32, float32, float_status *status); float32 float32_muladd(float32, float32, float32, int, float_status *status); +float32 float32_muladd_scalbn(float32, float32, float32, + int, int, float_status *status); float32 float32_sqrt(float32, float_status *status); float32 float32_exp2(float32, float_status *status); float32 float32_log2(float32, float_status *status); @@ -XXX,XX +XXX,XX @@ float64 float64_mul(float64, float64, float_status *status); float64 float64_div(float64, float64, float_status *status); float64 float64_rem(float64, float64, float_status *status); float64 float64_muladd(float64, float64, float64, int, float_status *status); +float64 float64_muladd_scalbn(float64, float64, float64, + int, int, float_status *status); float64 float64_sqrt(float64, float_status *status); float64 float64_log2(float64, float_status *status); FloatRelation float64_compare(float64, float64, float_status *status); diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ static FloatParts128 *parts128_mul(FloatParts128 *a, FloatParts128 *b, #define parts_mul(A, B, S) \ PARTS_GENERIC_64_128(mul, A)(A, B, S) -static FloatParts64 *parts64_muladd(FloatParts64 *a, FloatParts64 *b, - FloatParts64 *c, int flags, - float_status *s); -static FloatParts128 *parts128_muladd(FloatParts128 *a, FloatParts128 *b, - FloatParts128 *c, int flags, - float_status *s); +static FloatParts64 *parts64_muladd_scalbn(FloatParts64 *a, FloatParts64 *b, + FloatParts64 *c, int scale, + int flags, float_status *s); +static FloatParts128 *parts128_muladd_scalbn(FloatParts128 *a, FloatParts128 *b, + FloatParts128 *c, int scale, + int flags, float_status *s); -#define parts_muladd(A, B, C, Z, S) \ - PARTS_GENERIC_64_128(muladd, A)(A, B, C, Z, S) +#define parts_muladd_scalbn(A, B, C, Z, Y, S) \ + PARTS_GENERIC_64_128(muladd_scalbn, A)(A, B, C, Z, Y, S) static FloatParts64 *parts64_div(FloatParts64 *a, FloatParts64 *b, float_status *s); @@ -XXX,XX +XXX,XX @@ floatx80_mul(floatx80 a, floatx80 b, float_status *status) * Fused multiply-add */ -float16 QEMU_FLATTEN float16_muladd(float16 a, float16 b, float16 c, - int flags, float_status *status) +float16 QEMU_FLATTEN +float16_muladd_scalbn(float16 a, float16 b, float16 c, + int scale, int flags, float_status *status) { FloatParts64 pa, pb, pc, *pr; float16_unpack_canonical(&pa, a, status); float16_unpack_canonical(&pb, b, status); float16_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status); return float16_round_pack_canonical(pr, status); } -static float32 QEMU_SOFTFLOAT_ATTR -soft_f32_muladd(float32 a, float32 b, float32 c, int flags, - float_status *status) +float16 float16_muladd(float16 a, float16 b, float16 c, + int flags, float_status *status) +{ + return float16_muladd_scalbn(a, b, c, 0, flags, status); +} + +float32 QEMU_SOFTFLOAT_ATTR +float32_muladd_scalbn(float32 a, float32 b, float32 c, + int scale, int flags, float_status *status) { FloatParts64 pa, pb, pc, *pr; float32_unpack_canonical(&pa, a, status); float32_unpack_canonical(&pb, b, status); float32_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status); return float32_round_pack_canonical(pr, status); } -static float64 QEMU_SOFTFLOAT_ATTR -soft_f64_muladd(float64 a, float64 b, float64 c, int flags, - float_status *status) +float64 QEMU_SOFTFLOAT_ATTR +float64_muladd_scalbn(float64 a, float64 b, float64 c, + int scale, int flags, float_status *status) { FloatParts64 pa, pb, pc, *pr; float64_unpack_canonical(&pa, a, status); float64_unpack_canonical(&pb, b, status); float64_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, scale, flags, status); return float64_round_pack_canonical(pr, status); } @@ -XXX,XX +XXX,XX @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s) return ur.s; soft: - return soft_f32_muladd(ua.s, ub.s, uc.s, flags, s); + return float32_muladd_scalbn(ua.s, ub.s, uc.s, 0, flags, s); } float64 QEMU_FLATTEN @@ -XXX,XX +XXX,XX @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s) return ur.s; soft: - return soft_f64_muladd(ua.s, ub.s, uc.s, flags, s); + return float64_muladd_scalbn(ua.s, ub.s, uc.s, 0, flags, s); } float64 float64r32_muladd(float64 a, float64 b, float64 c, @@ -XXX,XX +XXX,XX @@ float64 float64r32_muladd(float64 a, float64 b, float64 c, float64_unpack_canonical(&pa, a, status); float64_unpack_canonical(&pb, b, status); float64_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status); return float64r32_round_pack_canonical(pr, status); } @@ -XXX,XX +XXX,XX @@ bfloat16 QEMU_FLATTEN bfloat16_muladd(bfloat16 a, bfloat16 b, bfloat16 c, bfloat16_unpack_canonical(&pa, a, status); bfloat16_unpack_canonical(&pb, b, status); bfloat16_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status); return bfloat16_round_pack_canonical(pr, status); } @@ -XXX,XX +XXX,XX @@ float128 QEMU_FLATTEN float128_muladd(float128 a, float128 b, float128 c, float128_unpack_canonical(&pa, a, status); float128_unpack_canonical(&pb, b, status); float128_unpack_canonical(&pc, c, status); - pr = parts_muladd(&pa, &pb, &pc, flags, status); + pr = parts_muladd_scalbn(&pa, &pb, &pc, 0, flags, status); return float128_round_pack_canonical(pr, status); } @@ -XXX,XX +XXX,XX @@ float32 float32_exp2(float32 a, float_status *status) float64_unpack_canonical(&rp, float64_one, status); for (i = 0 ; i < 15 ; i++) { + float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status); - rp = *parts_muladd(&tp, &xnp, &rp, 0, status); + rp = *parts_muladd_scalbn(&tp, &xnp, &rp, 0, 0, status); xnp = *parts_mul(&xnp, &xp, status); } diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(mul)(FloatPartsN *a, FloatPartsN *b, * Requires A and C extracted into a double-sized structure to provide the * extra space for the widening multiply. */ -static FloatPartsN *partsN(muladd)(FloatPartsN *a, FloatPartsN *b, - FloatPartsN *c, int flags, float_status *s) +static FloatPartsN *partsN(muladd_scalbn)(FloatPartsN *a, FloatPartsN *b, + FloatPartsN *c, int scale, + int flags, float_status *s) { int ab_mask, abc_mask; FloatPartsW p_widen, c_widen; @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(muladd)(FloatPartsN *a, FloatPartsN *b, a->exp = p_widen.exp; return_normal: + /* TODO: Replace all use of float_muladd_halve_result with scale. */ if (flags & float_muladd_halve_result) { a->exp -= 1; } + a->exp += scale; finish_sign: if (flags & float_muladd_negate_result) { a->sign ^= 1; -- 2.43.0 Use the scalbn interface instead of float_muladd_halve_result. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/helper-a64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, float_status *fpst) (float16_is_infinity(b) && float16_is_zero(a))) { return float16_one_point_five; } - return float16_muladd(a, b, float16_three, float_muladd_halve_result, fpst); + return float16_muladd_scalbn(a, b, float16_three, -1, 0, fpst); } float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, float_status *fpst) @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, float_status *fpst) (float32_is_infinity(b) && float32_is_zero(a))) { return float32_one_point_five; } - return float32_muladd(a, b, float32_three, float_muladd_halve_result, fpst); + return float32_muladd_scalbn(a, b, float32_three, -1, 0, fpst); } float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, float_status *fpst) @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, float_status *fpst) (float64_is_infinity(b) && float64_is_zero(a))) { return float64_one_point_five; } - return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst); + return float64_muladd_scalbn(a, b, float64_three, -1, 0, fpst); } /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */ -- 2.43.0 Use the scalbn interface instead of float_muladd_halve_result. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sparc/helper.h | 4 +- target/sparc/fop_helper.c | 8 ++-- target/sparc/translate.c | 80 +++++++++++++++++++++++---------------- 3 files changed, 54 insertions(+), 38 deletions(-) diff --git a/target/sparc/helper.h b/target/sparc/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/helper.h +++ b/target/sparc/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(faddd, TCG_CALL_NO_WG, f64, env, f64, f64) DEF_HELPER_FLAGS_3(fsubd, TCG_CALL_NO_WG, f64, env, f64, f64) DEF_HELPER_FLAGS_3(fmuld, TCG_CALL_NO_WG, f64, env, f64, f64) DEF_HELPER_FLAGS_3(fdivd, TCG_CALL_NO_WG, f64, env, f64, f64) -DEF_HELPER_FLAGS_5(fmaddd, TCG_CALL_NO_WG, f64, env, f64, f64, f64, i32) +DEF_HELPER_FLAGS_6(fmaddd, TCG_CALL_NO_WG, f64, env, f64, f64, f64, s32, i32) DEF_HELPER_FLAGS_3(fnaddd, TCG_CALL_NO_WG, f64, env, f64, f64) DEF_HELPER_FLAGS_3(fnmuld, TCG_CALL_NO_WG, f64, env, f64, f64) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(fadds, TCG_CALL_NO_WG, f32, env, f32, f32) DEF_HELPER_FLAGS_3(fsubs, TCG_CALL_NO_WG, f32, env, f32, f32) DEF_HELPER_FLAGS_3(fmuls, TCG_CALL_NO_WG, f32, env, f32, f32) DEF_HELPER_FLAGS_3(fdivs, TCG_CALL_NO_WG, f32, env, f32, f32) -DEF_HELPER_FLAGS_5(fmadds, TCG_CALL_NO_WG, f32, env, f32, f32, f32, i32) +DEF_HELPER_FLAGS_6(fmadds, TCG_CALL_NO_WG, f32, env, f32, f32, f32, s32, i32) DEF_HELPER_FLAGS_3(fnadds, TCG_CALL_NO_WG, f32, env, f32, f32) DEF_HELPER_FLAGS_3(fnmuls, TCG_CALL_NO_WG, f32, env, f32, f32) diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/fop_helper.c +++ b/target/sparc/fop_helper.c @@ -XXX,XX +XXX,XX @@ Int128 helper_fsqrtq(CPUSPARCState *env, Int128 src) } float32 helper_fmadds(CPUSPARCState *env, float32 s1, - float32 s2, float32 s3, uint32_t op) + float32 s2, float32 s3, int32_t sc, uint32_t op) { - float32 ret = float32_muladd(s1, s2, s3, op, &env->fp_status); + float32 ret = float32_muladd_scalbn(s1, s2, s3, sc, op, &env->fp_status); check_ieee_exceptions(env, GETPC()); return ret; } float64 helper_fmaddd(CPUSPARCState *env, float64 s1, - float64 s2, float64 s3, uint32_t op) + float64 s2, float64 s3, int32_t sc, uint32_t op) { - float64 ret = float64_muladd(s1, s2, s3, op, &env->fp_status); + float64 ret = float64_muladd_scalbn(s1, s2, s3, sc, op, &env->fp_status); check_ieee_exceptions(env, GETPC()); return ret; } diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_op_fabsq(TCGv_i128 dst, TCGv_i128 src) static void gen_op_fmadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2, TCGv_i32 s3) { - gen_helper_fmadds(d, tcg_env, s1, s2, s3, tcg_constant_i32(0)); + TCGv_i32 z = tcg_constant_i32(0); + gen_helper_fmadds(d, tcg_env, s1, s2, s3, z, z); } static void gen_op_fmaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3) { - gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(0)); + TCGv_i32 z = tcg_constant_i32(0); + gen_helper_fmaddd(d, tcg_env, s1, s2, s3, z, z); } static void gen_op_fmsubs(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2, TCGv_i32 s3) { - int op = float_muladd_negate_c; - gen_helper_fmadds(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c); + gen_helper_fmadds(d, tcg_env, s1, s2, s3, z, op); } static void gen_op_fmsubd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3) { - int op = float_muladd_negate_c; - gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c); + gen_helper_fmaddd(d, tcg_env, s1, s2, s3, z, op); } static void gen_op_fnmsubs(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2, TCGv_i32 s3) { - int op = float_muladd_negate_c | float_muladd_negate_result; - gen_helper_fmadds(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c | + float_muladd_negate_result); + gen_helper_fmadds(d, tcg_env, s1, s2, s3, z, op); } static void gen_op_fnmsubd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3) { - int op = float_muladd_negate_c | float_muladd_negate_result; - gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c | + float_muladd_negate_result); + gen_helper_fmaddd(d, tcg_env, s1, s2, s3, z, op); } static void gen_op_fnmadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2, TCGv_i32 s3) { - int op = float_muladd_negate_result; - gen_helper_fmadds(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_result); + gen_helper_fmadds(d, tcg_env, s1, s2, s3, z, op); } static void gen_op_fnmaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3) { - int op = float_muladd_negate_result; - gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(op)); + TCGv_i32 z = tcg_constant_i32(0); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_result); + gen_helper_fmaddd(d, tcg_env, s1, s2, s3, z, op); } /* Use muladd to compute (1 * src1) + src2 / 2 with one rounding. */ static void gen_op_fhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2) { - TCGv_i32 one = tcg_constant_i32(float32_one); - int op = float_muladd_halve_result; - gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i32 fone = tcg_constant_i32(float32_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(0); + gen_helper_fmadds(d, tcg_env, fone, s1, s2, mone, op); } static void gen_op_fhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2) { - TCGv_i64 one = tcg_constant_i64(float64_one); - int op = float_muladd_halve_result; - gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i64 fone = tcg_constant_i64(float64_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(0); + gen_helper_fmaddd(d, tcg_env, fone, s1, s2, mone, op); } /* Use muladd to compute (1 * src1) - src2 / 2 with one rounding. */ static void gen_op_fhsubs(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2) { - TCGv_i32 one = tcg_constant_i32(float32_one); - int op = float_muladd_negate_c | float_muladd_halve_result; - gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i32 fone = tcg_constant_i32(float32_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c); + gen_helper_fmadds(d, tcg_env, fone, s1, s2, mone, op); } static void gen_op_fhsubd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2) { - TCGv_i64 one = tcg_constant_i64(float64_one); - int op = float_muladd_negate_c | float_muladd_halve_result; - gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i64 fone = tcg_constant_i64(float64_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_c); + gen_helper_fmaddd(d, tcg_env, fone, s1, s2, mone, op); } /* Use muladd to compute -((1 * src1) + src2 / 2) with one rounding. */ static void gen_op_fnhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2) { - TCGv_i32 one = tcg_constant_i32(float32_one); - int op = float_muladd_negate_result | float_muladd_halve_result; - gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i32 fone = tcg_constant_i32(float32_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_result); + gen_helper_fmadds(d, tcg_env, fone, s1, s2, mone, op); } static void gen_op_fnhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2) { - TCGv_i64 one = tcg_constant_i64(float64_one); - int op = float_muladd_negate_result | float_muladd_halve_result; - gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op)); + TCGv_i64 fone = tcg_constant_i64(float64_one); + TCGv_i32 mone = tcg_constant_i32(-1); + TCGv_i32 op = tcg_constant_i32(float_muladd_negate_result); + gen_helper_fmaddd(d, tcg_env, fone, s1, s2, mone, op); } static void gen_op_fpexception_im(DisasContext *dc, int ftt) -- 2.43.0 All uses have been convered to float*_muladd_scalbn. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/fpu/softfloat.h | 3 --- fpu/softfloat.c | 6 ------ fpu/softfloat-parts.c.inc | 4 ---- 3 files changed, 13 deletions(-) diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -XXX,XX +XXX,XX @@ bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status); | Using these differs from negating an input or output before calling | the muladd function in that this means that a NaN doesn't have its | sign bit inverted before it is propagated. -| We also support halving the result before rounding, as a special -| case to support the ARM fused-sqrt-step instruction FRSQRTS. *----------------------------------------------------------------------------*/ enum { float_muladd_negate_c = 1, float_muladd_negate_product = 2, float_muladd_negate_result = 4, - float_muladd_halve_result = 8, }; /*---------------------------------------------------------------------------- diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s) if (unlikely(!can_use_fpu(s))) { goto soft; } - if (unlikely(flags & float_muladd_halve_result)) { - goto soft; - } float32_input_flush3(&ua.s, &ub.s, &uc.s, s); if (unlikely(!f32_is_zon3(ua, ub, uc))) { @@ -XXX,XX +XXX,XX @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s) if (unlikely(!can_use_fpu(s))) { goto soft; } - if (unlikely(flags & float_muladd_halve_result)) { - goto soft; - } float64_input_flush3(&ua.s, &ub.s, &uc.s, s); if (unlikely(!f64_is_zon3(ua, ub, uc))) { diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(muladd_scalbn)(FloatPartsN *a, FloatPartsN *b, a->exp = p_widen.exp; return_normal: - /* TODO: Replace all use of float_muladd_halve_result with scale. */ - if (flags & float_muladd_halve_result) { - a->exp -= 1; - } a->exp += scale; finish_sign: if (flags & float_muladd_negate_result) { -- 2.43.0 This rounding mode is used by Hexagon. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/fpu/softfloat-types.h | 2 ++ fpu/softfloat-parts.c.inc | 3 +++ 2 files changed, 5 insertions(+) diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) { float_round_to_odd = 5, /* Not an IEEE rounding mode: round to closest odd, overflow to inf */ float_round_to_odd_inf = 6, + /* Not an IEEE rounding mode: round to nearest even, overflow to max */ + float_round_nearest_even_max = 7, } FloatRoundMode; /* diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static void partsN(uncanon_normal)(FloatPartsN *p, float_status *s, int exp, flags = 0; switch (s->float_rounding_mode) { + case float_round_nearest_even_max: + overflow_norm = true; + /* fall through */ case float_round_nearest_even: if (N > 64 && frac_lsb == 0) { inc = ((p->frac_hi & 1) || (p->frac_lo & round_mask) != frac_lsbm1 -- 2.43.0 Certain Hexagon instructions suppress changes to the result when the product of fma() is a true zero. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/fpu/softfloat.h | 5 +++++ fpu/softfloat.c | 3 +++ fpu/softfloat-parts.c.inc | 4 +++- 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -XXX,XX +XXX,XX @@ bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status); | Using these differs from negating an input or output before calling | the muladd function in that this means that a NaN doesn't have its | sign bit inverted before it is propagated. +| +| With float_muladd_suppress_add_product_zero, if A or B is zero +| such that the product is a true zero, then return C without addition. +| This preserves the sign of C when C is +/- 0. Used for Hexagon. *----------------------------------------------------------------------------*/ enum { float_muladd_negate_c = 1, float_muladd_negate_product = 2, float_muladd_negate_result = 4, + float_muladd_suppress_add_product_zero = 8, }; /*---------------------------------------------------------------------------- diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s) if (unlikely(!can_use_fpu(s))) { goto soft; } + if (unlikely(flags & float_muladd_suppress_add_product_zero)) { + goto soft; + } float32_input_flush3(&ua.s, &ub.s, &uc.s, s); if (unlikely(!f32_is_zon3(ua, ub, uc))) { diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(muladd_scalbn)(FloatPartsN *a, FloatPartsN *b, goto return_normal; } if (c->cls == float_class_zero) { - if (a->sign != c->sign) { + if (flags & float_muladd_suppress_add_product_zero) { + a->sign = c->sign; + } else if (a->sign != c->sign) { goto return_sub_zero; } goto return_zero; -- 2.43.0 There are no special cases for this instruction. Remove internal_mpyf as unused. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.h | 1 - target/hexagon/fma_emu.c | 8 -------- target/hexagon/op_helper.c | 2 +- 3 files changed, 1 insertion(+), 10 deletions(-) diff --git a/target/hexagon/fma_emu.h b/target/hexagon/fma_emu.h index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.h +++ b/target/hexagon/fma_emu.h @@ -XXX,XX +XXX,XX @@ int32_t float32_getexp(float32 f32); float32 infinite_float32(uint8_t sign); float32 internal_fmafx(float32 a, float32 b, float32 c, int scale, float_status *fp_status); -float32 internal_mpyf(float32 a, float32 b, float_status *fp_status); float64 internal_mpyhh(float64 a, float64 b, unsigned long long int accumulated, float_status *fp_status); diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ float32 internal_fmafx(float32 a, float32 b, float32 c, int scale, return accum_round_float32(result, fp_status); } -float32 internal_mpyf(float32 a, float32 b, float_status *fp_status) -{ - if (float32_is_zero(a) || float32_is_zero(b)) { - return float32_mul(a, b, fp_status); - } - return internal_fmafx(a, b, float32_zero, 0, fp_status); -} - float64 internal_mpyhh(float64 a, float64 b, unsigned long long int accumulated, float_status *fp_status) diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -XXX,XX +XXX,XX @@ float32 HELPER(sfmpy)(CPUHexagonState *env, float32 RsV, float32 RtV) { float32 RdV; arch_fpop_start(env); - RdV = internal_mpyf(RsV, RtV, &env->fp_status); + RdV = float32_mul(RsV, RtV, &env->fp_status); arch_fpop_end(env); return RdV; } -- 2.43.0 There are no special cases for this instruction. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/op_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -XXX,XX +XXX,XX @@ float32 HELPER(sffma)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { arch_fpop_start(env); - RxV = internal_fmafx(RsV, RtV, RxV, 0, &env->fp_status); + RxV = float32_muladd(RsV, RtV, RxV, 0, &env->fp_status); arch_fpop_end(env); return RxV; } -- 2.43.0 There are no special cases for this instruction. Since hexagon always uses default-nan mode, explicitly negating the first input is unnecessary. Use float_muladd_negate_product instead. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/op_helper.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -XXX,XX +XXX,XX @@ float32 HELPER(sffma_sc)(CPUHexagonState *env, float32 RxV, float32 HELPER(sffms)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { - float32 neg_RsV; arch_fpop_start(env); - neg_RsV = float32_set_sign(RsV, float32_is_neg(RsV) ? 0 : 1); - RxV = internal_fmafx(neg_RsV, RtV, RxV, 0, &env->fp_status); + RxV = float32_muladd(RsV, RtV, RxV, float_muladd_negate_product, + &env->fp_status); arch_fpop_end(env); return RxV; } -- 2.43.0 This instruction has a special case that 0 * x + c returns c without the normal sign folding that comes with 0 + -0. Use the new float_muladd_suppress_add_product_zero to describe this. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/op_helper.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -XXX,XX +XXX,XX @@ static float32 check_nan(float32 dst, float32 x, float_status *fp_status) float32 HELPER(sffma_sc)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV, float32 PuV) { - size4s_t tmp; arch_fpop_start(env); - RxV = check_nan(RxV, RxV, &env->fp_status); - RxV = check_nan(RxV, RsV, &env->fp_status); - RxV = check_nan(RxV, RtV, &env->fp_status); - tmp = internal_fmafx(RsV, RtV, RxV, fSXTN(8, 64, PuV), &env->fp_status); - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { - RxV = tmp; - } + RxV = float32_muladd_scalbn(RsV, RtV, RxV, fSXTN(8, 64, PuV), + float_muladd_suppress_add_product_zero, + &env->fp_status); arch_fpop_end(env); return RxV; } -- 2.43.0 There are multiple special cases for this instruction. (1) The saturate to normal maximum instead of overflow to infinity is handled by the new float_round_nearest_even_max rounding mode. (2) The 0 * n + c special case is handled by the new float_muladd_suppress_add_product_zero flag. (3) The Inf - Inf -> 0 special case can be detected after the fact by examining float_flag_invalid_isi. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/op_helper.c | 105 +++++++++---------------------------- 1 file changed, 26 insertions(+), 79 deletions(-) diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -XXX,XX +XXX,XX @@ float32 HELPER(sffma)(CPUHexagonState *env, float32 RxV, return RxV; } -static bool is_zero_prod(float32 a, float32 b) -{ - return ((float32_is_zero(a) && is_finite(b)) || - (float32_is_zero(b) && is_finite(a))); -} - -static float32 check_nan(float32 dst, float32 x, float_status *fp_status) -{ - float32 ret = dst; - if (float32_is_any_nan(x)) { - if (extract32(x, 22, 1) == 0) { - float_raise(float_flag_invalid, fp_status); - } - ret = make_float32(0xffffffff); /* nan */ - } - return ret; -} - float32 HELPER(sffma_sc)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV, float32 PuV) { @@ -XXX,XX +XXX,XX @@ float32 HELPER(sffms)(CPUHexagonState *env, float32 RxV, return RxV; } -static bool is_inf_prod(int32_t a, int32_t b) +static float32 do_sffma_lib(CPUHexagonState *env, float32 RxV, + float32 RsV, float32 RtV, int negate) { - return (float32_is_infinity(a) && float32_is_infinity(b)) || - (float32_is_infinity(a) && is_finite(b) && !float32_is_zero(b)) || - (float32_is_infinity(b) && is_finite(a) && !float32_is_zero(a)); + int flags; + + arch_fpop_start(env); + + set_float_rounding_mode(float_round_nearest_even_max, &env->fp_status); + RxV = float32_muladd(RsV, RtV, RxV, + negate | float_muladd_suppress_add_product_zero, + &env->fp_status); + + flags = get_float_exception_flags(&env->fp_status); + if (flags) { + /* Flags are suppressed by this instruction. */ + set_float_exception_flags(0, &env->fp_status); + + /* Return 0 for Inf - Inf. */ + if (flags & float_flag_invalid_isi) { + RxV = 0; + } + } + + arch_fpop_end(env); + return RxV; } float32 HELPER(sffma_lib)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { - bool infinp; - bool infminusinf; - float32 tmp; - - arch_fpop_start(env); - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); - infminusinf = float32_is_infinity(RxV) && - is_inf_prod(RsV, RtV) && - (fGETBIT(31, RsV ^ RxV ^ RtV) != 0); - infinp = float32_is_infinity(RxV) || - float32_is_infinity(RtV) || - float32_is_infinity(RsV); - RxV = check_nan(RxV, RxV, &env->fp_status); - RxV = check_nan(RxV, RsV, &env->fp_status); - RxV = check_nan(RxV, RtV, &env->fp_status); - tmp = internal_fmafx(RsV, RtV, RxV, 0, &env->fp_status); - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { - RxV = tmp; - } - set_float_exception_flags(0, &env->fp_status); - if (float32_is_infinity(RxV) && !infinp) { - RxV = RxV - 1; - } - if (infminusinf) { - RxV = 0; - } - arch_fpop_end(env); - return RxV; + return do_sffma_lib(env, RxV, RsV, RtV, 0); } float32 HELPER(sffms_lib)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { - bool infinp; - bool infminusinf; - float32 tmp; - - arch_fpop_start(env); - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); - infminusinf = float32_is_infinity(RxV) && - is_inf_prod(RsV, RtV) && - (fGETBIT(31, RsV ^ RxV ^ RtV) == 0); - infinp = float32_is_infinity(RxV) || - float32_is_infinity(RtV) || - float32_is_infinity(RsV); - RxV = check_nan(RxV, RxV, &env->fp_status); - RxV = check_nan(RxV, RsV, &env->fp_status); - RxV = check_nan(RxV, RtV, &env->fp_status); - float32 minus_RsV = float32_sub(float32_zero, RsV, &env->fp_status); - tmp = internal_fmafx(minus_RsV, RtV, RxV, 0, &env->fp_status); - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { - RxV = tmp; - } - set_float_exception_flags(0, &env->fp_status); - if (float32_is_infinity(RxV) && !infinp) { - RxV = RxV - 1; - } - if (infminusinf) { - RxV = 0; - } - arch_fpop_end(env); - return RxV; + return do_sffma_lib(env, RxV, RsV, RtV, float_muladd_negate_product); } float64 HELPER(dfmpyfix)(CPUHexagonState *env, float64 RssV, float64 RttV) -- 2.43.0 The function is now unused. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.h | 2 - target/hexagon/fma_emu.c | 171 --------------------------------------- 2 files changed, 173 deletions(-) diff --git a/target/hexagon/fma_emu.h b/target/hexagon/fma_emu.h index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.h +++ b/target/hexagon/fma_emu.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t float32_getexp_raw(float32 f32) } int32_t float32_getexp(float32 f32); float32 infinite_float32(uint8_t sign); -float32 internal_fmafx(float32 a, float32 b, float32 c, - int scale, float_status *fp_status); float64 internal_mpyhh(float64 a, float64 b, unsigned long long int accumulated, float_status *fp_status); diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ int32_t float64_getexp(float64 f64) return -1; } -static uint64_t float32_getmant(float32 f32) -{ - Float a = { .i = f32 }; - if (float32_is_normal(f32)) { - return a.mant | 1ULL << 23; - } - if (float32_is_zero(f32)) { - return 0; - } - if (float32_is_denormal(f32)) { - return a.mant; - } - return ~0ULL; -} - int32_t float32_getexp(float32 f32) { Float a = { .i = f32 }; @@ -XXX,XX +XXX,XX @@ float32 infinite_float32(uint8_t sign) } /* Return a maximum finite value with the requested sign */ -static float32 maxfinite_float32(uint8_t sign) -{ - if (sign) { - return make_float32(SF_MINUS_MAXF); - } else { - return make_float32(SF_MAXF); - } -} - -/* Return a zero value with requested sign */ -static float32 zero_float32(uint8_t sign) -{ - if (sign) { - return make_float32(0x80000000); - } else { - return float32_zero; - } -} - #define GEN_XF_ROUND(SUFFIX, MANTBITS, INF_EXP, INTERNAL_TYPE) \ static SUFFIX accum_round_##SUFFIX(Accum a, float_status * fp_status) \ { \ @@ -XXX,XX +XXX,XX @@ static SUFFIX accum_round_##SUFFIX(Accum a, float_status * fp_status) \ } GEN_XF_ROUND(float64, DF_MANTBITS, DF_INF_EXP, Double) -GEN_XF_ROUND(float32, SF_MANTBITS, SF_INF_EXP, Float) - -static bool is_inf_prod(float64 a, float64 b) -{ - return ((float64_is_infinity(a) && float64_is_infinity(b)) || - (float64_is_infinity(a) && is_finite(b) && (!float64_is_zero(b))) || - (float64_is_infinity(b) && is_finite(a) && (!float64_is_zero(a)))); -} - -static float64 special_fma(float64 a, float64 b, float64 c, - float_status *fp_status) -{ - float64 ret = make_float64(0); - - /* - * If A multiplied by B is an exact infinity and C is also an infinity - * but with the opposite sign, FMA returns NaN and raises invalid. - */ - uint8_t a_sign = float64_is_neg(a); - uint8_t b_sign = float64_is_neg(b); - uint8_t c_sign = float64_is_neg(c); - if (is_inf_prod(a, b) && float64_is_infinity(c)) { - if ((a_sign ^ b_sign) != c_sign) { - ret = make_float64(DF_NAN); - float_raise(float_flag_invalid, fp_status); - return ret; - } - } - if ((float64_is_infinity(a) && float64_is_zero(b)) || - (float64_is_zero(a) && float64_is_infinity(b))) { - ret = make_float64(DF_NAN); - float_raise(float_flag_invalid, fp_status); - return ret; - } - /* - * If none of the above checks are true and C is a NaN, - * a NaN shall be returned - * If A or B are NaN, a NAN shall be returned. - */ - if (float64_is_any_nan(a) || - float64_is_any_nan(b) || - float64_is_any_nan(c)) { - if (float64_is_any_nan(a) && (fGETBIT(51, a) == 0)) { - float_raise(float_flag_invalid, fp_status); - } - if (float64_is_any_nan(b) && (fGETBIT(51, b) == 0)) { - float_raise(float_flag_invalid, fp_status); - } - if (float64_is_any_nan(c) && (fGETBIT(51, c) == 0)) { - float_raise(float_flag_invalid, fp_status); - } - ret = make_float64(DF_NAN); - return ret; - } - /* - * We have checked for adding opposite-signed infinities. - * Other infinities return infinity with the correct sign - */ - if (float64_is_infinity(c)) { - ret = infinite_float64(c_sign); - return ret; - } - if (float64_is_infinity(a) || float64_is_infinity(b)) { - ret = infinite_float64(a_sign ^ b_sign); - return ret; - } - g_assert_not_reached(); -} - -static float32 special_fmaf(float32 a, float32 b, float32 c, - float_status *fp_status) -{ - float64 aa, bb, cc; - aa = float32_to_float64(a, fp_status); - bb = float32_to_float64(b, fp_status); - cc = float32_to_float64(c, fp_status); - return float64_to_float32(special_fma(aa, bb, cc, fp_status), fp_status); -} - -float32 internal_fmafx(float32 a, float32 b, float32 c, int scale, - float_status *fp_status) -{ - Accum prod; - Accum acc; - Accum result; - accum_init(&prod); - accum_init(&acc); - accum_init(&result); - - uint8_t a_sign = float32_is_neg(a); - uint8_t b_sign = float32_is_neg(b); - uint8_t c_sign = float32_is_neg(c); - if (float32_is_infinity(a) || - float32_is_infinity(b) || - float32_is_infinity(c)) { - return special_fmaf(a, b, c, fp_status); - } - if (float32_is_any_nan(a) || - float32_is_any_nan(b) || - float32_is_any_nan(c)) { - return special_fmaf(a, b, c, fp_status); - } - if ((scale == 0) && (float32_is_zero(a) || float32_is_zero(b))) { - float32 tmp = float32_mul(a, b, fp_status); - tmp = float32_add(tmp, c, fp_status); - return tmp; - } - - /* (a * 2**b) * (c * 2**d) == a*c * 2**(b+d) */ - prod.mant = int128_mul_6464(float32_getmant(a), float32_getmant(b)); - - /* - * Note: extracting the mantissa into an int is multiplying by - * 2**23, so adjust here - */ - prod.exp = float32_getexp(a) + float32_getexp(b) - SF_BIAS - 23; - prod.sign = a_sign ^ b_sign; - if (float32_is_zero(a) || float32_is_zero(b)) { - prod.exp = -2 * WAY_BIG_EXP; - } - if ((scale > 0) && float32_is_denormal(c)) { - acc.mant = int128_mul_6464(0, 0); - acc.exp = -WAY_BIG_EXP; - acc.sign = c_sign; - acc.sticky = 1; - result = accum_add(prod, acc); - } else if (!float32_is_zero(c)) { - acc.mant = int128_mul_6464(float32_getmant(c), 1); - acc.exp = float32_getexp(c); - acc.sign = c_sign; - result = accum_add(prod, acc); - } else { - result = prod; - } - result.exp += scale; - return accum_round_float32(result, fp_status); -} float64 internal_mpyhh(float64 a, float64 b, unsigned long long int accumulated, -- 2.43.0 This massive macro is now only used once. Expand it for use only by float64. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.c | 255 +++++++++++++++++++-------------------- 1 file changed, 127 insertions(+), 128 deletions(-) diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ float32 infinite_float32(uint8_t sign) } /* Return a maximum finite value with the requested sign */ -#define GEN_XF_ROUND(SUFFIX, MANTBITS, INF_EXP, INTERNAL_TYPE) \ -static SUFFIX accum_round_##SUFFIX(Accum a, float_status * fp_status) \ -{ \ - if ((int128_gethi(a.mant) == 0) && (int128_getlo(a.mant) == 0) \ - && ((a.guard | a.round | a.sticky) == 0)) { \ - /* result zero */ \ - switch (fp_status->float_rounding_mode) { \ - case float_round_down: \ - return zero_##SUFFIX(1); \ - default: \ - return zero_##SUFFIX(0); \ - } \ - } \ - /* Normalize right */ \ - /* We want MANTBITS bits of mantissa plus the leading one. */ \ - /* That means that we want MANTBITS+1 bits, or 0x000000000000FF_FFFF */ \ - /* So we need to normalize right while the high word is non-zero and \ - * while the low word is nonzero when masked with 0xffe0_0000_0000_0000 */ \ - while ((int128_gethi(a.mant) != 0) || \ - ((int128_getlo(a.mant) >> (MANTBITS + 1)) != 0)) { \ - a = accum_norm_right(a, 1); \ - } \ - /* \ - * OK, now normalize left \ - * We want to normalize left until we have a leading one in bit 24 \ - * Theoretically, we only need to shift a maximum of one to the left if we \ - * shifted out lots of bits from B, or if we had no shift / 1 shift sticky \ - * should be 0 \ - */ \ - while ((int128_getlo(a.mant) & (1ULL << MANTBITS)) == 0) { \ - a = accum_norm_left(a); \ - } \ - /* \ - * OK, now we might need to denormalize because of potential underflow. \ - * We need to do this before rounding, and rounding might make us normal \ - * again \ - */ \ - while (a.exp <= 0) { \ - a = accum_norm_right(a, 1 - a.exp); \ - /* \ - * Do we have underflow? \ - * That's when we get an inexact answer because we ran out of bits \ - * in a denormal. \ - */ \ - if (a.guard || a.round || a.sticky) { \ - float_raise(float_flag_underflow, fp_status); \ - } \ - } \ - /* OK, we're relatively canonical... now we need to round */ \ - if (a.guard || a.round || a.sticky) { \ - float_raise(float_flag_inexact, fp_status); \ - switch (fp_status->float_rounding_mode) { \ - case float_round_to_zero: \ - /* Chop and we're done */ \ - break; \ - case float_round_up: \ - if (a.sign == 0) { \ - a.mant = int128_add(a.mant, int128_one()); \ - } \ - break; \ - case float_round_down: \ - if (a.sign != 0) { \ - a.mant = int128_add(a.mant, int128_one()); \ - } \ - break; \ - default: \ - if (a.round || a.sticky) { \ - /* round up if guard is 1, down if guard is zero */ \ - a.mant = int128_add(a.mant, int128_make64(a.guard)); \ - } else if (a.guard) { \ - /* exactly .5, round up if odd */ \ - a.mant = int128_add(a.mant, int128_and(a.mant, int128_one())); \ - } \ - break; \ - } \ - } \ - /* \ - * OK, now we might have carried all the way up. \ - * So we might need to shr once \ - * at least we know that the lsb should be zero if we rounded and \ - * got a carry out... \ - */ \ - if ((int128_getlo(a.mant) >> (MANTBITS + 1)) != 0) { \ - a = accum_norm_right(a, 1); \ - } \ - /* Overflow? */ \ - if (a.exp >= INF_EXP) { \ - /* Yep, inf result */ \ - float_raise(float_flag_overflow, fp_status); \ - float_raise(float_flag_inexact, fp_status); \ - switch (fp_status->float_rounding_mode) { \ - case float_round_to_zero: \ - return maxfinite_##SUFFIX(a.sign); \ - case float_round_up: \ - if (a.sign == 0) { \ - return infinite_##SUFFIX(a.sign); \ - } else { \ - return maxfinite_##SUFFIX(a.sign); \ - } \ - case float_round_down: \ - if (a.sign != 0) { \ - return infinite_##SUFFIX(a.sign); \ - } else { \ - return maxfinite_##SUFFIX(a.sign); \ - } \ - default: \ - return infinite_##SUFFIX(a.sign); \ - } \ - } \ - /* Underflow? */ \ - if (int128_getlo(a.mant) & (1ULL << MANTBITS)) { \ - /* Leading one means: No, we're normal. So, we should be done... */ \ - INTERNAL_TYPE ret; \ - ret.i = 0; \ - ret.sign = a.sign; \ - ret.exp = a.exp; \ - ret.mant = int128_getlo(a.mant); \ - return ret.i; \ - } \ - assert(a.exp == 1); \ - INTERNAL_TYPE ret; \ - ret.i = 0; \ - ret.sign = a.sign; \ - ret.exp = 0; \ - ret.mant = int128_getlo(a.mant); \ - return ret.i; \ +static float64 accum_round_float64(Accum a, float_status *fp_status) +{ + if ((int128_gethi(a.mant) == 0) && (int128_getlo(a.mant) == 0) + && ((a.guard | a.round | a.sticky) == 0)) { + /* result zero */ + switch (fp_status->float_rounding_mode) { + case float_round_down: + return zero_float64(1); + default: + return zero_float64(0); + } + } + /* + * Normalize right + * We want DF_MANTBITS bits of mantissa plus the leading one. + * That means that we want DF_MANTBITS+1 bits, or 0x000000000000FF_FFFF + * So we need to normalize right while the high word is non-zero and + * while the low word is nonzero when masked with 0xffe0_0000_0000_0000 + */ + while ((int128_gethi(a.mant) != 0) || + ((int128_getlo(a.mant) >> (DF_MANTBITS + 1)) != 0)) { + a = accum_norm_right(a, 1); + } + /* + * OK, now normalize left + * We want to normalize left until we have a leading one in bit 24 + * Theoretically, we only need to shift a maximum of one to the left if we + * shifted out lots of bits from B, or if we had no shift / 1 shift sticky + * should be 0 + */ + while ((int128_getlo(a.mant) & (1ULL << DF_MANTBITS)) == 0) { + a = accum_norm_left(a); + } + /* + * OK, now we might need to denormalize because of potential underflow. + * We need to do this before rounding, and rounding might make us normal + * again + */ + while (a.exp <= 0) { + a = accum_norm_right(a, 1 - a.exp); + /* + * Do we have underflow? + * That's when we get an inexact answer because we ran out of bits + * in a denormal. + */ + if (a.guard || a.round || a.sticky) { + float_raise(float_flag_underflow, fp_status); + } + } + /* OK, we're relatively canonical... now we need to round */ + if (a.guard || a.round || a.sticky) { + float_raise(float_flag_inexact, fp_status); + switch (fp_status->float_rounding_mode) { + case float_round_to_zero: + /* Chop and we're done */ + break; + case float_round_up: + if (a.sign == 0) { + a.mant = int128_add(a.mant, int128_one()); + } + break; + case float_round_down: + if (a.sign != 0) { + a.mant = int128_add(a.mant, int128_one()); + } + break; + default: + if (a.round || a.sticky) { + /* round up if guard is 1, down if guard is zero */ + a.mant = int128_add(a.mant, int128_make64(a.guard)); + } else if (a.guard) { + /* exactly .5, round up if odd */ + a.mant = int128_add(a.mant, int128_and(a.mant, int128_one())); + } + break; + } + } + /* + * OK, now we might have carried all the way up. + * So we might need to shr once + * at least we know that the lsb should be zero if we rounded and + * got a carry out... + */ + if ((int128_getlo(a.mant) >> (DF_MANTBITS + 1)) != 0) { + a = accum_norm_right(a, 1); + } + /* Overflow? */ + if (a.exp >= DF_INF_EXP) { + /* Yep, inf result */ + float_raise(float_flag_overflow, fp_status); + float_raise(float_flag_inexact, fp_status); + switch (fp_status->float_rounding_mode) { + case float_round_to_zero: + return maxfinite_float64(a.sign); + case float_round_up: + if (a.sign == 0) { + return infinite_float64(a.sign); + } else { + return maxfinite_float64(a.sign); + } + case float_round_down: + if (a.sign != 0) { + return infinite_float64(a.sign); + } else { + return maxfinite_float64(a.sign); + } + default: + return infinite_float64(a.sign); + } + } + /* Underflow? */ + if (int128_getlo(a.mant) & (1ULL << DF_MANTBITS)) { + /* Leading one means: No, we're normal. So, we should be done... */ + Double ret; + ret.i = 0; + ret.sign = a.sign; + ret.exp = a.exp; + ret.mant = int128_getlo(a.mant); + return ret.i; + } + assert(a.exp == 1); + Double ret; + ret.i = 0; + ret.sign = a.sign; + ret.exp = 0; + ret.mant = int128_getlo(a.mant); + return ret.i; } -GEN_XF_ROUND(float64, DF_MANTBITS, DF_INF_EXP, Double) - float64 internal_mpyhh(float64 a, float64 b, unsigned long long int accumulated, float_status *fp_status) -- 2.43.0 This structure, with bitfields, is incorrect for big-endian. Use the existing float32_getexp_raw which uses extract32. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ typedef union { }; } Double; -typedef union { - float f; - uint32_t i; - struct { - uint32_t mant:23; - uint32_t exp:8; - uint32_t sign:1; - }; -} Float; - static uint64_t float64_getmant(float64 f64) { Double a = { .i = f64 }; @@ -XXX,XX +XXX,XX @@ int32_t float64_getexp(float64 f64) int32_t float32_getexp(float32 f32) { - Float a = { .i = f32 }; + int exp = float32_getexp_raw(f32); if (float32_is_normal(f32)) { - return a.exp; + return exp; } if (float32_is_denormal(f32)) { - return a.exp + 1; + return exp + 1; } return -1; } -- 2.43.0 This structure, with bitfields, is incorrect for big-endian. Use extract64 and deposit64 instead. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.c | 46 ++++++++++++++-------------------------- 1 file changed, 16 insertions(+), 30 deletions(-) diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ #define WAY_BIG_EXP 4096 -typedef union { - double f; - uint64_t i; - struct { - uint64_t mant:52; - uint64_t exp:11; - uint64_t sign:1; - }; -} Double; - static uint64_t float64_getmant(float64 f64) { - Double a = { .i = f64 }; + uint64_t mant = extract64(f64, 0, 52); if (float64_is_normal(f64)) { - return a.mant | 1ULL << 52; + return mant | 1ULL << 52; } if (float64_is_zero(f64)) { return 0; } if (float64_is_denormal(f64)) { - return a.mant; + return mant; } return ~0ULL; } int32_t float64_getexp(float64 f64) { - Double a = { .i = f64 }; + int exp = extract64(f64, 52, 11); if (float64_is_normal(f64)) { - return a.exp; + return exp; } if (float64_is_denormal(f64)) { - return a.exp + 1; + return exp + 1; } return -1; } @@ -XXX,XX +XXX,XX @@ float32 infinite_float32(uint8_t sign) /* Return a maximum finite value with the requested sign */ static float64 accum_round_float64(Accum a, float_status *fp_status) { + uint64_t ret; + if ((int128_gethi(a.mant) == 0) && (int128_getlo(a.mant) == 0) && ((a.guard | a.round | a.sticky) == 0)) { /* result zero */ @@ -XXX,XX +XXX,XX @@ static float64 accum_round_float64(Accum a, float_status *fp_status) } } /* Underflow? */ - if (int128_getlo(a.mant) & (1ULL << DF_MANTBITS)) { + ret = int128_getlo(a.mant); + if (ret & (1ULL << DF_MANTBITS)) { /* Leading one means: No, we're normal. So, we should be done... */ - Double ret; - ret.i = 0; - ret.sign = a.sign; - ret.exp = a.exp; - ret.mant = int128_getlo(a.mant); - return ret.i; + ret = deposit64(ret, 52, 11, a.exp); + } else { + assert(a.exp == 1); + ret = deposit64(ret, 52, 11, 0); } - assert(a.exp == 1); - Double ret; - ret.i = 0; - ret.sign = a.sign; - ret.exp = 0; - ret.mant = int128_getlo(a.mant); - return ret.i; + ret = deposit64(ret, 63, 1, a.sign); + return ret; } float64 internal_mpyhh(float64 a, float64 b, -- 2.43.0 No need to open-code 64x64->128-bit multiplication. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.c | 32 +++----------------------------- 1 file changed, 3 insertions(+), 29 deletions(-) diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ int32_t float32_getexp(float32 f32) return -1; } -static uint32_t int128_getw0(Int128 x) -{ - return int128_getlo(x); -} - -static uint32_t int128_getw1(Int128 x) -{ - return int128_getlo(x) >> 32; -} - static Int128 int128_mul_6464(uint64_t ai, uint64_t bi) { - Int128 a, b; - uint64_t pp0, pp1a, pp1b, pp1s, pp2; + uint64_t l, h; - a = int128_make64(ai); - b = int128_make64(bi); - pp0 = (uint64_t)int128_getw0(a) * (uint64_t)int128_getw0(b); - pp1a = (uint64_t)int128_getw1(a) * (uint64_t)int128_getw0(b); - pp1b = (uint64_t)int128_getw1(b) * (uint64_t)int128_getw0(a); - pp2 = (uint64_t)int128_getw1(a) * (uint64_t)int128_getw1(b); - - pp1s = pp1a + pp1b; - if ((pp1s < pp1a) || (pp1s < pp1b)) { - pp2 += (1ULL << 32); - } - uint64_t ret_low = pp0 + (pp1s << 32); - if ((ret_low < pp0) || (ret_low < (pp1s << 32))) { - pp2 += 1; - } - - return int128_make128(ret_low, pp2 + (pp1s >> 32)); + mulu64(&l, &h, ai, bi); + return int128_make128(l, h); } static Int128 int128_sub_borrow(Int128 a, Int128 b, int borrow) -- 2.43.0 Initialize x with accumulated via direct assignment, rather than multiplying by 1. Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/fma_emu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/hexagon/fma_emu.c b/target/hexagon/fma_emu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/fma_emu.c +++ b/target/hexagon/fma_emu.c @@ -XXX,XX +XXX,XX @@ float64 internal_mpyhh(float64 a, float64 b, float64_is_infinity(b)) { return float64_mul(a, b, fp_status); } - x.mant = int128_mul_6464(accumulated, 1); + x.mant = int128_make64(accumulated); x.sticky = sticky; prod = fGETUWORD(1, float64_getmant(a)) * fGETUWORD(1, float64_getmant(b)); x.mant = int128_add(x.mant, int128_mul_6464(prod, 0x100000000ULL)); -- 2.43.0 Convert all targets simultaneously, as the gen_intermediate_code function disappears from the target. While there are possible workarounds, they're larger than simply performing the conversion. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/translator.h | 14 -------------- include/hw/core/tcg-cpu-ops.h | 13 +++++++++++++ target/alpha/cpu.h | 2 ++ target/arm/internals.h | 2 ++ target/avr/cpu.h | 2 ++ target/hexagon/cpu.h | 2 ++ target/hppa/cpu.h | 2 ++ target/i386/tcg/helper-tcg.h | 2 ++ target/loongarch/internals.h | 2 ++ target/m68k/cpu.h | 2 ++ target/microblaze/cpu.h | 2 ++ target/mips/tcg/tcg-internal.h | 2 ++ target/openrisc/cpu.h | 2 ++ target/ppc/cpu.h | 2 ++ target/riscv/cpu.h | 3 +++ target/rx/cpu.h | 2 ++ target/s390x/s390x-internal.h | 2 ++ target/sh4/cpu.h | 2 ++ target/sparc/cpu.h | 2 ++ target/tricore/cpu.h | 2 ++ target/xtensa/cpu.h | 2 ++ accel/tcg/cpu-exec.c | 8 +++++--- accel/tcg/translate-all.c | 8 +++++--- target/alpha/cpu.c | 1 + target/alpha/translate.c | 4 ++-- target/arm/cpu.c | 1 + target/arm/tcg/cpu-v7m.c | 1 + target/arm/tcg/translate.c | 5 ++--- target/avr/cpu.c | 1 + target/avr/translate.c | 6 +++--- target/hexagon/cpu.c | 1 + target/hexagon/translate.c | 4 ++-- target/hppa/cpu.c | 1 + target/hppa/translate.c | 4 ++-- target/i386/tcg/tcg-cpu.c | 1 + target/i386/tcg/translate.c | 5 ++--- target/loongarch/cpu.c | 1 + target/loongarch/tcg/translate.c | 4 ++-- target/m68k/cpu.c | 1 + target/m68k/translate.c | 4 ++-- target/microblaze/cpu.c | 1 + target/microblaze/translate.c | 4 ++-- target/mips/cpu.c | 1 + target/mips/tcg/translate.c | 4 ++-- target/openrisc/cpu.c | 1 + target/openrisc/translate.c | 4 ++-- target/ppc/cpu_init.c | 1 + target/ppc/translate.c | 4 ++-- target/riscv/tcg/tcg-cpu.c | 1 + target/riscv/translate.c | 4 ++-- target/rx/cpu.c | 1 + target/rx/translate.c | 4 ++-- target/s390x/cpu.c | 1 + target/s390x/tcg/translate.c | 4 ++-- target/sh4/cpu.c | 1 + target/sh4/translate.c | 4 ++-- target/sparc/cpu.c | 1 + target/sparc/translate.c | 4 ++-- target/tricore/cpu.c | 1 + target/tricore/translate.c | 5 ++--- target/xtensa/cpu.c | 1 + target/xtensa/translate.c | 4 ++-- 62 files changed, 121 insertions(+), 62 deletions(-) diff --git a/include/exec/translator.h b/include/exec/translator.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -XXX,XX +XXX,XX @@ #include "qemu/bswap.h" #include "exec/vaddr.h" -/** - * gen_intermediate_code - * @cpu: cpu context - * @tb: translation block - * @max_insns: max number of instructions to translate - * @pc: guest virtual program counter address - * @host_pc: host physical program counter address - * - * This function must be provided by the target, which should create - * the target-specific DisasContext, and then invoke translator_loop. - */ -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc); - /** * DisasJumpType: * @DISAS_NEXT: Next instruction in program order. diff --git a/include/hw/core/tcg-cpu-ops.h b/include/hw/core/tcg-cpu-ops.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/tcg-cpu-ops.h +++ b/include/hw/core/tcg-cpu-ops.h @@ -XXX,XX +XXX,XX @@ struct TCGCPUOps { * Called when the first CPU is realized. */ void (*initialize)(void); + /** + * @translate_code: Translate guest instructions to TCGOps + * @cpu: cpu context + * @tb: translation block + * @max_insns: max number of instructions to translate + * @pc: guest virtual program counter address + * @host_pc: host physical program counter address + * + * This function must be provided by the target, which should create + * the target-specific DisasContext, and then invoke translator_loop. + */ + void (*translate_code)(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); /** * @synchronize_from_tb: Synchronize state from a TCG #TranslationBlock * diff --git a/target/alpha/cpu.h b/target/alpha/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.h +++ b/target/alpha/cpu.h @@ -XXX,XX +XXX,XX @@ enum { }; void alpha_translate_init(void); +void alpha_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #define CPU_RESOLVING_TYPE TYPE_ALPHA_CPU diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void init_cpreg_list(ARMCPU *cpu); void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu); void arm_translate_init(void); +void arm_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void arm_cpu_register_gdb_commands(ARMCPU *cpu); void aarch64_cpu_register_gdb_commands(ARMCPU *cpu, GString *, diff --git a/target/avr/cpu.h b/target/avr/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.h +++ b/target/avr/cpu.h @@ -XXX,XX +XXX,XX @@ static inline void set_avr_feature(CPUAVRState *env, int feature) } void avr_cpu_tcg_init(void); +void avr_cpu_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); int cpu_avr_exec(CPUState *cpu); diff --git a/target/hexagon/cpu.h b/target/hexagon/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.h +++ b/target/hexagon/cpu.h @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUHexagonState *env, vaddr *pc, typedef HexagonCPU ArchCPU; void hexagon_translate_init(void); +void hexagon_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #include "exec/cpu-all.h" diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/cpu.h +++ b/target/hppa/cpu.h @@ -XXX,XX +XXX,XX @@ static inline int HPPA_BTLB_ENTRIES(CPUHPPAState *env) } void hppa_translate_init(void); +void hppa_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #define CPU_RESOLVING_TYPE TYPE_HPPA_CPU diff --git a/target/i386/tcg/helper-tcg.h b/target/i386/tcg/helper-tcg.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/helper-tcg.h +++ b/target/i386/tcg/helper-tcg.h @@ -XXX,XX +XXX,XX @@ static inline target_long lshift(target_long x, int n) /* translate.c */ void tcg_x86_init(void); +void x86_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); /* excp_helper.c */ G_NORETURN void raise_exception(CPUX86State *env, int exception_index); diff --git a/target/loongarch/internals.h b/target/loongarch/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/internals.h +++ b/target/loongarch/internals.h @@ -XXX,XX +XXX,XX @@ #define TARGET_VIRT_MASK MAKE_64BIT_MASK(0, TARGET_VIRT_ADDR_SPACE_BITS) void loongarch_translate_init(void); +void loongarch_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void G_NORETURN do_raise_exception(CPULoongArchState *env, uint32_t exception, diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.h +++ b/target/m68k/cpu.h @@ -XXX,XX +XXX,XX @@ int m68k_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int m68k_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void m68k_tcg_init(void); +void m68k_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void m68k_cpu_init_gdb(M68kCPU *cpu); uint32_t cpu_m68k_get_ccr(CPUM68KState *env); void cpu_m68k_set_ccr(CPUM68KState *env, uint32_t); diff --git a/target/microblaze/cpu.h b/target/microblaze/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.h +++ b/target/microblaze/cpu.h @@ -XXX,XX +XXX,XX @@ static inline void mb_cpu_write_msr(CPUMBState *env, uint32_t val) } void mb_tcg_init(void); +void mb_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #define CPU_RESOLVING_TYPE TYPE_MICROBLAZE_CPU diff --git a/target/mips/tcg/tcg-internal.h b/target/mips/tcg/tcg-internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/tcg-internal.h +++ b/target/mips/tcg/tcg-internal.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" void mips_tcg_init(void); +void mips_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void mips_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb); G_NORETURN void mips_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, diff --git a/target/openrisc/cpu.h b/target/openrisc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.h +++ b/target/openrisc/cpu.h @@ -XXX,XX +XXX,XX @@ void openrisc_cpu_dump_state(CPUState *cpu, FILE *f, int flags); int openrisc_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int openrisc_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void openrisc_translate_init(void); +void openrisc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); int print_insn_or1k(bfd_vma addr, disassemble_info *info); #ifndef CONFIG_USER_ONLY diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -XXX,XX +XXX,XX @@ extern const VMStateDescription vmstate_ppc_cpu; /*****************************************************************************/ void ppc_translate_init(void); +void ppc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #if !defined(CONFIG_USER_ONLY) void ppc_store_sdr1(CPUPPCState *env, target_ulong value); diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.h +++ b/target/riscv/cpu.h @@ -XXX,XX +XXX,XX @@ RISCVException smstateen_acc_ok(CPURISCVState *env, int index, uint64_t bit); void riscv_cpu_set_mode(CPURISCVState *env, target_ulong newpriv, bool virt_en); void riscv_translate_init(void); +void riscv_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); + G_NORETURN void riscv_raise_exception(CPURISCVState *env, uint32_t exception, uintptr_t pc); diff --git a/target/rx/cpu.h b/target/rx/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.h +++ b/target/rx/cpu.h @@ -XXX,XX +XXX,XX @@ int rx_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int rx_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void rx_translate_init(void); +void rx_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void rx_cpu_unpack_psw(CPURXState *env, uint32_t psw, int rte); #include "exec/cpu-all.h" diff --git a/target/s390x/s390x-internal.h b/target/s390x/s390x-internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/s390x-internal.h +++ b/target/s390x/s390x-internal.h @@ -XXX,XX +XXX,XX @@ void handle_diag_308(CPUS390XState *env, uint64_t r1, uint64_t r3, /* translate.c */ void s390x_translate_init(void); +void s390x_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void s390x_restore_state_to_opc(CPUState *cs, const TranslationBlock *tb, const uint64_t *data); diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.h +++ b/target/sh4/cpu.h @@ -XXX,XX +XXX,XX @@ G_NORETURN void superh_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, uintptr_t retaddr); void sh4_translate_init(void); +void sh4_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); #if !defined(CONFIG_USER_ONLY) hwaddr superh_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); diff --git a/target/sparc/cpu.h b/target/sparc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.h +++ b/target/sparc/cpu.h @@ -XXX,XX +XXX,XX @@ int sparc_cpu_memory_rw_debug(CPUState *cpu, vaddr addr, /* translate.c */ void sparc_tcg_init(void); +void sparc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); /* fop_helper.c */ target_ulong cpu_get_fsr(CPUSPARCState *); diff --git a/target/tricore/cpu.h b/target/tricore/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.h +++ b/target/tricore/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TB_FLAGS, PRIV, 0, 2) void cpu_state_reset(CPUTriCoreState *s); void tricore_tcg_init(void); +void tricore_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); static inline void cpu_get_tb_cpu_state(CPUTriCoreState *env, vaddr *pc, uint64_t *cs_base, uint32_t *flags) diff --git a/target/xtensa/cpu.h b/target/xtensa/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.h +++ b/target/xtensa/cpu.h @@ -XXX,XX +XXX,XX @@ G_NORETURN void xtensa_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, void xtensa_collect_sr_names(const XtensaConfig *config); void xtensa_translate_init(void); +void xtensa_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc); void **xtensa_get_regfile_by_name(const char *name, int entries, int bits); void xtensa_breakpoint_handler(CPUState *cs); void xtensa_register_core(XtensaConfigList *node); diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ bool tcg_exec_realizefn(CPUState *cpu, Error **errp) if (!tcg_target_initialized) { /* Check mandatory TCGCPUOps handlers */ + const TCGCPUOps *tcg_ops = cpu->cc->tcg_ops; #ifndef CONFIG_USER_ONLY - assert(cpu->cc->tcg_ops->cpu_exec_halt); - assert(cpu->cc->tcg_ops->cpu_exec_interrupt); + assert(tcg_ops->cpu_exec_halt); + assert(tcg_ops->cpu_exec_interrupt); #endif /* !CONFIG_USER_ONLY */ - cpu->cc->tcg_ops->initialize(); + assert(tcg_ops->translate_code); + tcg_ops->initialize(); tcg_target_initialized = true; } diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static int setjmp_gen_code(CPUArchState *env, TranslationBlock *tb, tcg_func_start(tcg_ctx); - tcg_ctx->cpu = env_cpu(env); - gen_intermediate_code(env_cpu(env), tb, max_insns, pc, host_pc); + CPUState *cs = env_cpu(env); + tcg_ctx->cpu = cs; + cs->cc->tcg_ops->translate_code(cs, tb, max_insns, pc, host_pc); + assert(tb->size != 0); tcg_ctx->cpu = NULL; *max_insns = tb->icount; @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, /* * Overflow of code_gen_buffer, or the current slice of it. * - * TODO: We don't need to re-do gen_intermediate_code, nor + * TODO: We don't need to re-do tcg_ops->translate_code, nor * should we re-do the tcg optimization currently hidden * inside tcg_gen_code. All that should be required is to * flush the TBs, allocate a new TB, re-initialize it per diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps alpha_sysemu_ops = { static const TCGCPUOps alpha_tcg_ops = { .initialize = alpha_translate_init, + .translate_code = alpha_translate_code, .synchronize_from_tb = alpha_cpu_synchronize_from_tb, .restore_state_to_opc = alpha_restore_state_to_opc, diff --git a/target/alpha/translate.c b/target/alpha/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/translate.c +++ b/target/alpha/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps alpha_tr_ops = { .tb_stop = alpha_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void alpha_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; translator_loop(cpu, tb, max_insns, pc, host_pc, &alpha_tr_ops, &dc.base); diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps arm_sysemu_ops = { #ifdef CONFIG_TCG static const TCGCPUOps arm_tcg_ops = { .initialize = arm_translate_init, + .translate_code = arm_translate_code, .synchronize_from_tb = arm_cpu_synchronize_from_tb, .debug_excp_handler = arm_debug_excp_handler, .restore_state_to_opc = arm_restore_state_to_opc, diff --git a/target/arm/tcg/cpu-v7m.c b/target/arm/tcg/cpu-v7m.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu-v7m.c +++ b/target/arm/tcg/cpu-v7m.c @@ -XXX,XX +XXX,XX @@ static void cortex_m55_initfn(Object *obj) static const TCGCPUOps arm_v7m_tcg_ops = { .initialize = arm_translate_init, + .translate_code = arm_translate_code, .synchronize_from_tb = arm_cpu_synchronize_from_tb, .debug_excp_handler = arm_debug_excp_handler, .restore_state_to_opc = arm_restore_state_to_opc, diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps thumb_translator_ops = { .tb_stop = arm_tr_tb_stop, }; -/* generate intermediate code for basic block 'tb'. */ -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void arm_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc = { }; const TranslatorOps *ops = &arm_translator_ops; diff --git a/target/avr/cpu.c b/target/avr/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps avr_sysemu_ops = { static const TCGCPUOps avr_tcg_ops = { .initialize = avr_cpu_tcg_init, + .translate_code = avr_cpu_translate_code, .synchronize_from_tb = avr_cpu_synchronize_from_tb, .restore_state_to_opc = avr_restore_state_to_opc, .cpu_exec_interrupt = avr_cpu_exec_interrupt, diff --git a/target/avr/translate.c b/target/avr/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/translate.c +++ b/target/avr/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_WDR(DisasContext *ctx, arg_WDR *a) * * - translate() * - canonicalize_skip() - * - gen_intermediate_code() + * - translate_code() * - restore_state_to_opc() * */ @@ -XXX,XX +XXX,XX @@ static const TranslatorOps avr_tr_ops = { .tb_stop = avr_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void avr_cpu_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc = { }; translator_loop(cs, tb, max_insns, pc, host_pc, &avr_tr_ops, &dc.base); diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_init(Object *obj) static const TCGCPUOps hexagon_tcg_ops = { .initialize = hexagon_translate_init, + .translate_code = hexagon_translate_code, .synchronize_from_tb = hexagon_cpu_synchronize_from_tb, .restore_state_to_opc = hexagon_restore_state_to_opc, }; diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps hexagon_tr_ops = { .tb_stop = hexagon_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void hexagon_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps hppa_sysemu_ops = { static const TCGCPUOps hppa_tcg_ops = { .initialize = hppa_translate_init, + .translate_code = hppa_translate_code, .synchronize_from_tb = hppa_cpu_synchronize_from_tb, .restore_state_to_opc = hppa_restore_state_to_opc, diff --git a/target/hppa/translate.c b/target/hppa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/translate.c +++ b/target/hppa/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps hppa_tr_ops = { #endif }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void hppa_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx = { }; translator_loop(cs, tb, max_insns, pc, host_pc, &hppa_tr_ops, &ctx.base); diff --git a/target/i386/tcg/tcg-cpu.c b/target/i386/tcg/tcg-cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/tcg-cpu.c +++ b/target/i386/tcg/tcg-cpu.c @@ -XXX,XX +XXX,XX @@ static bool x86_debug_check_breakpoint(CPUState *cs) static const TCGCPUOps x86_tcg_ops = { .initialize = tcg_x86_init, + .translate_code = x86_translate_code, .synchronize_from_tb = x86_cpu_synchronize_from_tb, .restore_state_to_opc = x86_restore_state_to_opc, .cpu_exec_enter = x86_cpu_exec_enter, diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps i386_tr_ops = { .tb_stop = i386_tr_tb_stop, }; -/* generate intermediate code for basic block 'tb'. */ -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void x86_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/cpu.c +++ b/target/loongarch/cpu.c @@ -XXX,XX +XXX,XX @@ static void loongarch_cpu_dump_state(CPUState *cs, FILE *f, int flags) static const TCGCPUOps loongarch_tcg_ops = { .initialize = loongarch_translate_init, + .translate_code = loongarch_translate_code, .synchronize_from_tb = loongarch_cpu_synchronize_from_tb, .restore_state_to_opc = loongarch_restore_state_to_opc, diff --git a/target/loongarch/tcg/translate.c b/target/loongarch/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/translate.c +++ b/target/loongarch/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps loongarch_tr_ops = { .tb_stop = loongarch_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void loongarch_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps m68k_sysemu_ops = { static const TCGCPUOps m68k_tcg_ops = { .initialize = m68k_tcg_init, + .translate_code = m68k_translate_code, .restore_state_to_opc = m68k_restore_state_to_opc, #ifndef CONFIG_USER_ONLY diff --git a/target/m68k/translate.c b/target/m68k/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps m68k_tr_ops = { .tb_stop = m68k_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void m68k_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; translator_loop(cpu, tb, max_insns, pc, host_pc, &m68k_tr_ops, &dc.base); diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps mb_sysemu_ops = { static const TCGCPUOps mb_tcg_ops = { .initialize = mb_tcg_init, + .translate_code = mb_translate_code, .synchronize_from_tb = mb_cpu_synchronize_from_tb, .restore_state_to_opc = mb_restore_state_to_opc, diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/translate.c +++ b/target/microblaze/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps mb_tr_ops = { .tb_stop = mb_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void mb_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; translator_loop(cpu, tb, max_insns, pc, host_pc, &mb_tr_ops, &dc.base); diff --git a/target/mips/cpu.c b/target/mips/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -XXX,XX +XXX,XX @@ static const Property mips_cpu_properties[] = { #include "hw/core/tcg-cpu-ops.h" static const TCGCPUOps mips_tcg_ops = { .initialize = mips_tcg_init, + .translate_code = mips_translate_code, .synchronize_from_tb = mips_cpu_synchronize_from_tb, .restore_state_to_opc = mips_restore_state_to_opc, diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps mips_tr_ops = { .tb_stop = mips_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void mips_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps openrisc_sysemu_ops = { static const TCGCPUOps openrisc_tcg_ops = { .initialize = openrisc_translate_init, + .translate_code = openrisc_translate_code, .synchronize_from_tb = openrisc_cpu_synchronize_from_tb, .restore_state_to_opc = openrisc_restore_state_to_opc, diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/translate.c +++ b/target/openrisc/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps openrisc_tr_ops = { .tb_stop = openrisc_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void openrisc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps ppc_sysemu_ops = { static const TCGCPUOps ppc_tcg_ops = { .initialize = ppc_translate_init, + .translate_code = ppc_translate_code, .restore_state_to_opc = ppc_restore_state_to_opc, #ifdef CONFIG_USER_ONLY diff --git a/target/ppc/translate.c b/target/ppc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps ppc_tr_ops = { .tb_stop = ppc_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void ppc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/tcg/tcg-cpu.c +++ b/target/riscv/tcg/tcg-cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_restore_state_to_opc(CPUState *cs, static const TCGCPUOps riscv_tcg_ops = { .initialize = riscv_translate_init, + .translate_code = riscv_translate_code, .synchronize_from_tb = riscv_cpu_synchronize_from_tb, .restore_state_to_opc = riscv_restore_state_to_opc, diff --git a/target/riscv/translate.c b/target/riscv/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps riscv_tr_ops = { .tb_stop = riscv_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void riscv_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps rx_sysemu_ops = { static const TCGCPUOps rx_tcg_ops = { .initialize = rx_translate_init, + .translate_code = rx_translate_code, .synchronize_from_tb = rx_cpu_synchronize_from_tb, .restore_state_to_opc = rx_restore_state_to_opc, .tlb_fill = rx_cpu_tlb_fill, diff --git a/target/rx/translate.c b/target/rx/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/translate.c +++ b/target/rx/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps rx_tr_ops = { .tb_stop = rx_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void rx_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUS390XState *env, vaddr *pc, static const TCGCPUOps s390_tcg_ops = { .initialize = s390x_translate_init, + .translate_code = s390x_translate_code, .restore_state_to_opc = s390x_restore_state_to_opc, #ifdef CONFIG_USER_ONLY diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/tcg/translate.c +++ b/target/s390x/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps s390x_tr_ops = { .disas_log = s390x_tr_disas_log, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void s390x_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc; diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps sh4_sysemu_ops = { static const TCGCPUOps superh_tcg_ops = { .initialize = sh4_translate_init, + .translate_code = sh4_translate_code, .synchronize_from_tb = superh_cpu_synchronize_from_tb, .restore_state_to_opc = superh_restore_state_to_opc, diff --git a/target/sh4/translate.c b/target/sh4/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps sh4_tr_ops = { .tb_stop = sh4_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void sh4_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps sparc_sysemu_ops = { static const TCGCPUOps sparc_tcg_ops = { .initialize = sparc_tcg_init, + .translate_code = sparc_translate_code, .synchronize_from_tb = sparc_cpu_synchronize_from_tb, .restore_state_to_opc = sparc_restore_state_to_opc, diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps sparc_tr_ops = { .tb_stop = sparc_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void sparc_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc = {}; diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps tricore_sysemu_ops = { static const TCGCPUOps tricore_tcg_ops = { .initialize = tricore_tcg_init, + .translate_code = tricore_translate_code, .synchronize_from_tb = tricore_cpu_synchronize_from_tb, .restore_state_to_opc = tricore_restore_state_to_opc, .tlb_fill = tricore_cpu_tlb_fill, diff --git a/target/tricore/translate.c b/target/tricore/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/translate.c +++ b/target/tricore/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps tricore_tr_ops = { .tb_stop = tricore_tr_tb_stop, }; - -void gen_intermediate_code(CPUState *cs, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void tricore_translate_code(CPUState *cs, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext ctx; translator_loop(cs, tb, max_insns, pc, host_pc, diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static const struct SysemuCPUOps xtensa_sysemu_ops = { static const TCGCPUOps xtensa_tcg_ops = { .initialize = xtensa_translate_init, + .translate_code = xtensa_translate_code, .debug_excp_handler = xtensa_breakpoint_handler, .restore_state_to_opc = xtensa_restore_state_to_opc, diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -XXX,XX +XXX,XX @@ static const TranslatorOps xtensa_translator_ops = { .tb_stop = xtensa_tr_tb_stop, }; -void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int *max_insns, - vaddr pc, void *host_pc) +void xtensa_translate_code(CPUState *cpu, TranslationBlock *tb, + int *max_insns, vaddr pc, void *host_pc) { DisasContext dc = {}; translator_loop(cpu, tb, max_insns, pc, host_pc, -- 2.43.0