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 TCG patch queue, plus one target/sh4 patch that Yoshinori Sato asked me to process. r~ The following changes since commit efbf38d73e5dcc4d5f8b98c6e7a12be1f3b91745: Merge tag 'for-upstream' of git://repo.or.cz/qemu/kevin into staging (2022-10-03 15:06:07 -0400) are available in the Git repository at: https://gitlab.com/rth7680/qemu.git tags/pull-tcg-20221004 for you to fetch changes up to ab419fd8a035a65942de4e63effcd55ccbf1a9fe: target/sh4: Fix TB_FLAG_UNALIGN (2022-10-04 12:33:05 -0700) ---------------------------------------------------------------- Cache CPUClass for use in hot code paths. Add CPUTLBEntryFull, probe_access_full, tlb_set_page_full. Add generic support for TARGET_TB_PCREL. tcg/ppc: Optimize 26-bit jumps using STQ for POWER 2.07 target/sh4: Fix TB_FLAG_UNALIGN ---------------------------------------------------------------- Alex Bennée (3): cpu: cache CPUClass in CPUState for hot code paths hw/core/cpu-sysemu: used cached class in cpu_asidx_from_attrs cputlb: used cached CPUClass in our hot-paths Leandro Lupori (1): tcg/ppc: Optimize 26-bit jumps Richard Henderson (16): accel/tcg: Rename CPUIOTLBEntry to CPUTLBEntryFull accel/tcg: Drop addr member from SavedIOTLB accel/tcg: Suppress auto-invalidate in probe_access_internal accel/tcg: Introduce probe_access_full accel/tcg: Introduce tlb_set_page_full include/exec: Introduce TARGET_PAGE_ENTRY_EXTRA accel/tcg: Remove PageDesc code_bitmap accel/tcg: Use bool for page_find_alloc accel/tcg: Use DisasContextBase in plugin_gen_tb_start accel/tcg: Do not align tb->page_addr[0] accel/tcg: Inline tb_flush_jmp_cache include/hw/core: Create struct CPUJumpCache hw/core: Add CPUClass.get_pc accel/tcg: Introduce tb_pc and log_pc accel/tcg: Introduce TARGET_TB_PCREL target/sh4: Fix TB_FLAG_UNALIGN accel/tcg/internal.h | 10 ++ accel/tcg/tb-hash.h | 1 + accel/tcg/tb-jmp-cache.h | 65 ++++++++ include/exec/cpu-common.h | 1 + include/exec/cpu-defs.h | 48 ++++-- include/exec/exec-all.h | 75 ++++++++- include/exec/plugin-gen.h | 7 +- include/hw/core/cpu.h | 28 ++-- include/qemu/typedefs.h | 2 + include/tcg/tcg.h | 2 +- target/sh4/cpu.h | 56 ++++--- accel/stubs/tcg-stub.c | 4 + accel/tcg/cpu-exec.c | 80 +++++----- accel/tcg/cputlb.c | 259 ++++++++++++++++++-------------- accel/tcg/plugin-gen.c | 22 +-- accel/tcg/translate-all.c | 214 ++++++++++++-------------- accel/tcg/translator.c | 2 +- cpu.c | 9 +- hw/core/cpu-common.c | 3 +- hw/core/cpu-sysemu.c | 5 +- linux-user/sh4/signal.c | 6 +- plugins/core.c | 2 +- target/alpha/cpu.c | 9 ++ target/arm/cpu.c | 17 ++- target/arm/mte_helper.c | 14 +- target/arm/sve_helper.c | 4 +- target/arm/translate-a64.c | 2 +- target/avr/cpu.c | 10 +- target/cris/cpu.c | 8 + target/hexagon/cpu.c | 10 +- target/hppa/cpu.c | 12 +- target/i386/cpu.c | 9 ++ target/i386/tcg/tcg-cpu.c | 2 +- target/loongarch/cpu.c | 11 +- target/m68k/cpu.c | 8 + target/microblaze/cpu.c | 10 +- target/mips/cpu.c | 8 + target/mips/tcg/exception.c | 2 +- target/mips/tcg/sysemu/special_helper.c | 2 +- target/nios2/cpu.c | 9 ++ target/openrisc/cpu.c | 10 +- target/ppc/cpu_init.c | 8 + target/riscv/cpu.c | 17 ++- target/rx/cpu.c | 10 +- target/s390x/cpu.c | 8 + target/s390x/tcg/mem_helper.c | 4 - target/sh4/cpu.c | 18 ++- target/sh4/helper.c | 6 +- target/sh4/translate.c | 90 +++++------ target/sparc/cpu.c | 10 +- target/tricore/cpu.c | 11 +- target/xtensa/cpu.c | 8 + tcg/tcg.c | 8 +- trace/control-target.c | 2 +- tcg/ppc/tcg-target.c.inc | 119 +++++++++++---- 55 files changed, 915 insertions(+), 462 deletions(-) create mode 100644 accel/tcg/tb-jmp-cache.h From: Alex Bennée <alex.bennee@linaro.org> The class cast checkers are quite expensive and always on (unlike the dynamic case who's checks are gated by CONFIG_QOM_CAST_DEBUG). To avoid the overhead of repeatedly checking something which should never change we cache the CPUClass reference for use in the hot code paths. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-3-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-3-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/core/cpu.h | 9 +++++++++ cpu.c | 9 ++++----- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ typedef int (*WriteCoreDumpFunction)(const void *buf, size_t size, */ #define CPU(obj) ((CPUState *)(obj)) +/* + * The class checkers bring in CPU_GET_CLASS() which is potentially + * expensive given the eventual call to + * object_class_dynamic_cast_assert(). Because of this the CPUState + * has a cached value for the class in cs->cc which is set up in + * cpu_exec_realizefn() for use in hot code paths. + */ typedef struct CPUClass CPUClass; DECLARE_CLASS_CHECKERS(CPUClass, CPU, TYPE_CPU) @@ -XXX,XX +XXX,XX @@ struct qemu_work_item; struct CPUState { /*< private >*/ DeviceState parent_obj; + /* cache to avoid expensive CPU_GET_CLASS */ + CPUClass *cc; /*< public >*/ int nr_cores; diff --git a/cpu.c b/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/cpu.c +++ b/cpu.c @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_cpu_common = { void cpu_exec_realizefn(CPUState *cpu, Error **errp) { -#ifndef CONFIG_USER_ONLY - CPUClass *cc = CPU_GET_CLASS(cpu); -#endif + /* cache the cpu class for the hotpath */ + cpu->cc = CPU_GET_CLASS(cpu); cpu_list_add(cpu); if (!accel_cpu_realizefn(cpu, errp)) { @@ -XXX,XX +XXX,XX @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu); } - if (cc->sysemu_ops->legacy_vmsd != NULL) { - vmstate_register(NULL, cpu->cpu_index, cc->sysemu_ops->legacy_vmsd, cpu); + if (cpu->cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_register(NULL, cpu->cpu_index, cpu->cc->sysemu_ops->legacy_vmsd, cpu); } #endif /* CONFIG_USER_ONLY */ } -- 2.34.1 From: Alex Bennée <alex.bennee@linaro.org> This is a heavily used function so lets avoid the cost of CPU_GET_CLASS. On the romulus-bmc run it has a modest effect: Before: 36.812 s ± 0.506 s After: 35.912 s ± 0.168 s Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-4-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-4-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- hw/core/cpu-sysemu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/hw/core/cpu-sysemu.c b/hw/core/cpu-sysemu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/cpu-sysemu.c +++ b/hw/core/cpu-sysemu.c @@ -XXX,XX +XXX,XX @@ hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) { - CPUClass *cc = CPU_GET_CLASS(cpu); int ret = 0; - if (cc->sysemu_ops->asidx_from_attrs) { - ret = cc->sysemu_ops->asidx_from_attrs(cpu, attrs); + if (cpu->cc->sysemu_ops->asidx_from_attrs) { + ret = cpu->cc->sysemu_ops->asidx_from_attrs(cpu, attrs); assert(ret < cpu->num_ases && ret >= 0); } return ret; -- 2.34.1 From: Alex Bennée <alex.bennee@linaro.org> Before: 35.912 s ± 0.168 s After: 35.565 s ± 0.087 s Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220811151413.3350684-5-alex.bennee@linaro.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20220923084803.498337-5-clg@kaod.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) 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 tlb_set_page(CPUState *cpu, target_ulong vaddr, static void tlb_fill(CPUState *cpu, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { - CPUClass *cc = CPU_GET_CLASS(cpu); bool ok; /* * This is not a probe, so only valid return is success; failure * should result in exception + longjmp to the cpu loop. */ - ok = cc->tcg_ops->tlb_fill(cpu, addr, size, - access_type, mmu_idx, false, retaddr); + ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, size, + access_type, mmu_idx, false, retaddr); assert(ok); } @@ -XXX,XX +XXX,XX @@ static inline void cpu_unaligned_access(CPUState *cpu, vaddr addr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { - CPUClass *cc = CPU_GET_CLASS(cpu); - - cc->tcg_ops->do_unaligned_access(cpu, addr, access_type, mmu_idx, retaddr); + cpu->cc->tcg_ops->do_unaligned_access(cpu, addr, access_type, + mmu_idx, retaddr); } static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr, @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, if (!tlb_hit_page(tlb_addr, page_addr)) { if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) { CPUState *cs = env_cpu(env); - CPUClass *cc = CPU_GET_CLASS(cs); - if (!cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type, - mmu_idx, nonfault, retaddr)) { + if (!cs->cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type, + mmu_idx, nonfault, retaddr)) { /* Non-faulting page table read failed. */ *phost = NULL; return TLB_INVALID_MASK; -- 2.34.1 This structure will shortly contain more than just data for accessing MMIO. Rename the 'addr' member to 'xlat_section' to more clearly indicate its purpose. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 22 ++++---- accel/tcg/cputlb.c | 102 +++++++++++++++++++------------------ target/arm/mte_helper.c | 14 ++--- target/arm/sve_helper.c | 4 +- target/arm/translate-a64.c | 2 +- 5 files changed, 73 insertions(+), 71 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef uint64_t target_ulong; # endif # endif +/* Minimalized TLB entry for use by TCG fast path. */ typedef struct CPUTLBEntry { /* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address bit TARGET_PAGE_BITS-1..4 : Nonzero for accesses that should not @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntry { QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS)); -/* The IOTLB is not accessed directly inline by generated TCG code, - * so the CPUIOTLBEntry layout is not as critical as that of the - * CPUTLBEntry. (This is also why we don't want to combine the two - * structs into one.) +/* + * The full TLB entry, which is not accessed by generated TCG code, + * so the layout is not as critical as that of CPUTLBEntry. This is + * also why we don't want to combine the two structs. */ -typedef struct CPUIOTLBEntry { +typedef struct CPUTLBEntryFull { /* - * @addr contains: + * @xlat_section contains: * - in the lower TARGET_PAGE_BITS, a physical section number * - with the lower TARGET_PAGE_BITS masked off, an offset which * must be added to the virtual address to obtain: @@ -XXX,XX +XXX,XX @@ typedef struct CPUIOTLBEntry { * number is PHYS_SECTION_NOTDIRTY or PHYS_SECTION_ROM) * + the offset within the target MemoryRegion (otherwise) */ - hwaddr addr; + hwaddr xlat_section; MemTxAttrs attrs; -} CPUIOTLBEntry; +} CPUTLBEntryFull; /* * Data elements that are per MMU mode, minus the bits accessed by @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBDesc { size_t vindex; /* The tlb victim table, in two parts. */ CPUTLBEntry vtable[CPU_VTLB_SIZE]; - CPUIOTLBEntry viotlb[CPU_VTLB_SIZE]; - /* The iotlb. */ - CPUIOTLBEntry *iotlb; + CPUTLBEntryFull vfulltlb[CPU_VTLB_SIZE]; + CPUTLBEntryFull *fulltlb; } CPUTLBDesc; /* 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 @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, } g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); tlb_window_reset(desc, now, 0); /* desc->n_used_entries is cleared by the caller */ fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS; fast->table = g_try_new(CPUTLBEntry, new_size); - desc->iotlb = g_try_new(CPUIOTLBEntry, new_size); + desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size); /* * If the allocations fail, try smaller sizes. We just freed some @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, * allocations to fail though, so we progressively reduce the allocation * size, aborting if we cannot even allocate the smallest TLB we support. */ - while (fast->table == NULL || desc->iotlb == NULL) { + while (fast->table == NULL || desc->fulltlb == NULL) { if (new_size == (1 << CPU_TLB_DYN_MIN_BITS)) { error_report("%s: %s", __func__, strerror(errno)); abort(); @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast, fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS; g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); fast->table = g_try_new(CPUTLBEntry, new_size); - desc->iotlb = g_try_new(CPUIOTLBEntry, new_size); + desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size); } } @@ -XXX,XX +XXX,XX @@ static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now) desc->n_used_entries = 0; fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS; fast->table = g_new(CPUTLBEntry, n_entries); - desc->iotlb = g_new(CPUIOTLBEntry, n_entries); + desc->fulltlb = g_new(CPUTLBEntryFull, n_entries); tlb_mmu_flush_locked(desc, fast); } @@ -XXX,XX +XXX,XX @@ void tlb_destroy(CPUState *cpu) CPUTLBDescFast *fast = &env_tlb(env)->f[i]; g_free(fast->table); - g_free(desc->iotlb); + g_free(desc->fulltlb); } } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, /* Evict the old entry into the victim tlb. */ copy_tlb_helper_locked(tv, te); - desc->viotlb[vidx] = desc->iotlb[index]; + desc->vfulltlb[vidx] = desc->fulltlb[index]; tlb_n_used_entries_dec(env, mmu_idx); } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * subtract here is that of the page base, and not the same as the * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). */ - desc->iotlb[index].addr = iotlb - vaddr_page; - desc->iotlb[index].attrs = attrs; + desc->fulltlb[index].xlat_section = iotlb - vaddr_page; + desc->fulltlb[index].attrs = attrs; /* Now calculate the new entry */ tn.addend = addend - vaddr_page; @@ -XXX,XX +XXX,XX @@ static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr, } } -static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, +static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full, int mmu_idx, target_ulong addr, uintptr_t retaddr, MMUAccessType access_type, MemOp op) { @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; - section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + section = iotlb_to_section(cpu, full->xlat_section, full->attrs); mr = section->mr; - mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; cpu->mem_io_pc = retaddr; if (!cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_read(mr, mr_offset, &val, op, iotlbentry->attrs); + r = memory_region_dispatch_read(mr, mr_offset, &val, op, full->attrs); if (r != MEMTX_OK) { hwaddr physaddr = mr_offset + section->offset_within_address_space - section->offset_within_region; cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), access_type, - mmu_idx, iotlbentry->attrs, r, retaddr); + mmu_idx, full->attrs, r, retaddr); } if (locked) { qemu_mutex_unlock_iothread(); @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, } /* - * Save a potentially trashed IOTLB entry for later lookup by plugin. - * This is read by tlb_plugin_lookup if the iotlb entry doesn't match + * Save a potentially trashed CPUTLBEntryFull for later lookup by plugin. + * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match * because of the side effect of io_writex changing memory layout. */ static void save_iotlb_data(CPUState *cs, hwaddr addr, @@ -XXX,XX +XXX,XX @@ static void save_iotlb_data(CPUState *cs, hwaddr addr, #endif } -static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, +static void io_writex(CPUArchState *env, CPUTLBEntryFull *full, int mmu_idx, uint64_t val, target_ulong addr, uintptr_t retaddr, MemOp op) { @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; - section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); + section = iotlb_to_section(cpu, full->xlat_section, full->attrs); mr = section->mr; - mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; if (!cpu->can_do_io) { cpu_io_recompile(cpu, retaddr); } @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, * The memory_region_dispatch may trigger a flush/resize * so for plugins we save the iotlb_data just in case. */ - save_iotlb_data(cpu, iotlbentry->addr, section, mr_offset); + save_iotlb_data(cpu, full->xlat_section, section, mr_offset); if (!qemu_mutex_iothread_locked()) { qemu_mutex_lock_iothread(); locked = true; } - r = memory_region_dispatch_write(mr, mr_offset, val, op, iotlbentry->attrs); + r = memory_region_dispatch_write(mr, mr_offset, val, op, full->attrs); if (r != MEMTX_OK) { hwaddr physaddr = mr_offset + section->offset_within_address_space - section->offset_within_region; cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), - MMU_DATA_STORE, mmu_idx, iotlbentry->attrs, r, + MMU_DATA_STORE, mmu_idx, full->attrs, r, retaddr); } if (locked) { @@ -XXX,XX +XXX,XX @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, copy_tlb_helper_locked(vtlb, &tmptlb); qemu_spin_unlock(&env_tlb(env)->c.lock); - CPUIOTLBEntry tmpio, *io = &env_tlb(env)->d[mmu_idx].iotlb[index]; - CPUIOTLBEntry *vio = &env_tlb(env)->d[mmu_idx].viotlb[vidx]; - tmpio = *io; *io = *vio; *vio = tmpio; + CPUTLBEntryFull *f1 = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + CPUTLBEntryFull *f2 = &env_tlb(env)->d[mmu_idx].vfulltlb[vidx]; + CPUTLBEntryFull tmpf; + tmpf = *f1; *f1 = *f2; *f2 = tmpf; return true; } } @@ -XXX,XX +XXX,XX @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, (ADDR) & TARGET_PAGE_MASK) static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size, - CPUIOTLBEntry *iotlbentry, uintptr_t retaddr) + CPUTLBEntryFull *full, uintptr_t retaddr) { - ram_addr_t ram_addr = mem_vaddr + iotlbentry->addr; + ram_addr_t ram_addr = mem_vaddr + full->xlat_section; trace_memory_notdirty_write_access(mem_vaddr, ram_addr, size); @@ -XXX,XX +XXX,XX @@ int probe_access_flags(CPUArchState *env, target_ulong addr, /* Handle clean RAM pages. */ if (unlikely(flags & TLB_NOTDIRTY)) { uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, 1, full, retaddr); flags &= ~TLB_NOTDIRTY; } @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) { uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (flags & TLB_WATCHPOINT) { int wp_access = (access_type == MMU_DATA_STORE ? BP_MEM_WRITE : BP_MEM_READ); cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, wp_access, retaddr); + full->attrs, wp_access, retaddr); } /* Handle clean RAM pages. */ if (flags & TLB_NOTDIRTY) { - notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, 1, full, retaddr); } } @@ -XXX,XX +XXX,XX @@ tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr, * should have just filled the TLB. The one corner case is io_writex * which can cause TLB flushes and potential resizing of the TLBs * losing the information we need. In those cases we need to recover - * data from a copy of the iotlbentry. As long as this always occurs + * data from a copy of the CPUTLBEntryFull. As long as this always occurs * from the same thread (which a mem callback will be) this is safe. */ @@ -XXX,XX +XXX,XX @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx, if (likely(tlb_hit(tlb_addr, addr))) { /* We must have an iotlb entry for MMIO */ if (tlb_addr & TLB_MMIO) { - CPUIOTLBEntry *iotlbentry; - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + CPUTLBEntryFull *full; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; data->is_io = true; - data->v.io.section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); - data->v.io.offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; + data->v.io.section = + iotlb_to_section(cpu, full->xlat_section, full->attrs); + data->v.io.offset = (full->xlat_section & TARGET_PAGE_MASK) + addr; } else { data->is_io = false; data->v.ram.hostaddr = (void *)((uintptr_t)addr + tlbe->addend); @@ -XXX,XX +XXX,XX @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, if (unlikely(tlb_addr & TLB_NOTDIRTY)) { notdirty_write(env_cpu(env), addr, size, - &env_tlb(env)->d[mmu_idx].iotlb[index], retaddr); + &env_tlb(env)->d[mmu_idx].fulltlb[index], retaddr); } return hostaddr; @@ -XXX,XX +XXX,XX @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi, /* Handle anything that isn't just a straight memory access. */ if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) { - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; bool need_swap; /* For anything that is unaligned, recurse through full_load. */ @@ -XXX,XX +XXX,XX @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi, goto do_unaligned_access; } - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { /* On watchpoint hit, this will longjmp out. */ cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, BP_MEM_READ, retaddr); + full->attrs, BP_MEM_READ, retaddr); } need_swap = size > 1 && (tlb_addr & TLB_BSWAP); /* Handle I/O access. */ if (likely(tlb_addr & TLB_MMIO)) { - return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, + return io_readx(env, full, mmu_idx, addr, retaddr, access_type, op ^ (need_swap * MO_BSWAP)); } @@ -XXX,XX +XXX,XX @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val, */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { cpu_check_watchpoint(env_cpu(env), addr, size - size2, - env_tlb(env)->d[mmu_idx].iotlb[index].attrs, + env_tlb(env)->d[mmu_idx].fulltlb[index].attrs, BP_MEM_WRITE, retaddr); } if (unlikely(tlb_addr2 & TLB_WATCHPOINT)) { cpu_check_watchpoint(env_cpu(env), page2, size2, - env_tlb(env)->d[mmu_idx].iotlb[index2].attrs, + env_tlb(env)->d[mmu_idx].fulltlb[index2].attrs, BP_MEM_WRITE, retaddr); } @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, /* Handle anything that isn't just a straight memory access. */ if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) { - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; bool need_swap; /* For anything that is unaligned, recurse through byte stores. */ @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, goto do_unaligned_access; } - iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; /* Handle watchpoints. */ if (unlikely(tlb_addr & TLB_WATCHPOINT)) { /* On watchpoint hit, this will longjmp out. */ cpu_check_watchpoint(env_cpu(env), addr, size, - iotlbentry->attrs, BP_MEM_WRITE, retaddr); + full->attrs, BP_MEM_WRITE, retaddr); } need_swap = size > 1 && (tlb_addr & TLB_BSWAP); /* Handle I/O access. */ if (tlb_addr & TLB_MMIO) { - io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr, + io_writex(env, full, mmu_idx, val, addr, retaddr, op ^ (need_swap * MO_BSWAP)); return; } @@ -XXX,XX +XXX,XX @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, /* Handle clean RAM pages. */ if (tlb_addr & TLB_NOTDIRTY) { - notdirty_write(env_cpu(env), addr, size, iotlbentry, retaddr); + notdirty_write(env_cpu(env), addr, size, full, retaddr); } haddr = (void *)((uintptr_t)addr + entry->addend); diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, return tags + index; #else uintptr_t index; - CPUIOTLBEntry *iotlbentry; + CPUTLBEntryFull *full; int in_page, flags; ram_addr_t ptr_ra; hwaddr ptr_paddr, tag_paddr, xlat; @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, assert(!(flags & TLB_INVALID_MASK)); /* - * Find the iotlbentry for ptr. This *must* be present in the TLB + * Find the CPUTLBEntryFull for ptr. This *must* be present in the TLB * because we just found the mapping. * TODO: Perhaps there should be a cputlb helper that returns a * matching tlb entry + iotlb entry. @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, g_assert(tlb_hit(comparator, ptr)); } # endif - iotlbentry = &env_tlb(env)->d[ptr_mmu_idx].iotlb[index]; + full = &env_tlb(env)->d[ptr_mmu_idx].fulltlb[index]; /* If the virtual page MemAttr != Tagged, access unchecked. */ - if (!arm_tlb_mte_tagged(&iotlbentry->attrs)) { + if (!arm_tlb_mte_tagged(&full->attrs)) { return NULL; } @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, int wp = ptr_access == MMU_DATA_LOAD ? BP_MEM_READ : BP_MEM_WRITE; assert(ra != 0); cpu_check_watchpoint(env_cpu(env), ptr, ptr_size, - iotlbentry->attrs, wp, ra); + full->attrs, wp, ra); } /* @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, tag_paddr = ptr_paddr >> (LOG2_TAG_GRANULE + 1); /* Look up the address in tag space. */ - tag_asi = iotlbentry->attrs.secure ? ARMASIdx_TagS : ARMASIdx_TagNS; + tag_asi = full->attrs.secure ? ARMASIdx_TagS : ARMASIdx_TagNS; tag_as = cpu_get_address_space(env_cpu(env), tag_asi); mr = address_space_translate(tag_as, tag_paddr, &xlat, NULL, tag_access == MMU_DATA_STORE, - iotlbentry->attrs); + full->attrs); /* * Note that @mr will never be NULL. If there is nothing in the address 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 @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, g_assert(tlb_hit(comparator, addr)); # endif - CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index]; - info->attrs = iotlbentry->attrs; + CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + info->attrs = full->attrs; } #endif 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 @@ static bool is_guarded_page(CPUARMState *env, DisasContext *s) * table entry even for that case. */ return (tlb_hit(entry->addr_code, addr) && - arm_tlb_bti_gp(&env_tlb(env)->d[mmu_idx].iotlb[index].attrs)); + arm_tlb_bti_gp(&env_tlb(env)->d[mmu_idx].fulltlb[index].attrs)); #endif } -- 2.34.1 This field is only written, not read; remove it. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/core/cpu.h | 1 - accel/tcg/cputlb.c | 7 +++---- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct CPUWatchpoint { * the memory regions get moved around by io_writex. */ typedef struct SavedIOTLB { - hwaddr addr; MemoryRegionSection *section; hwaddr mr_offset; } SavedIOTLB; 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 @@ static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full, * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match * because of the side effect of io_writex changing memory layout. */ -static void save_iotlb_data(CPUState *cs, hwaddr addr, - MemoryRegionSection *section, hwaddr mr_offset) +static void save_iotlb_data(CPUState *cs, MemoryRegionSection *section, + hwaddr mr_offset) { #ifdef CONFIG_PLUGIN SavedIOTLB *saved = &cs->saved_iotlb; - saved->addr = addr; saved->section = section; saved->mr_offset = mr_offset; #endif @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUTLBEntryFull *full, * The memory_region_dispatch may trigger a flush/resize * so for plugins we save the iotlb_data just in case. */ - save_iotlb_data(cpu, full->xlat_section, section, mr_offset); + save_iotlb_data(cpu, section, mr_offset); if (!qemu_mutex_iothread_locked()) { qemu_mutex_lock_iothread(); -- 2.34.1 When PAGE_WRITE_INV is set when calling tlb_set_page, we immediately set TLB_INVALID_MASK in order to force tlb_fill to be called on the next lookup. Here in probe_access_internal, we have just called tlb_fill and eliminated true misses, thus the lookup must be valid. This allows us to remove a warning comment from s390x. There doesn't seem to be a reason to change the code though. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 10 +++++++++- target/s390x/tcg/mem_helper.c | 4 ---- 2 files changed, 9 insertions(+), 5 deletions(-) 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 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, } tlb_addr = tlb_read_ofs(entry, elt_ofs); + flags = TLB_FLAGS_MASK; page_addr = addr & TARGET_PAGE_MASK; if (!tlb_hit_page(tlb_addr, page_addr)) { if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) { @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, /* TLB resize via tlb_fill may have moved the entry. */ entry = tlb_entry(env, mmu_idx, addr); + + /* + * With PAGE_WRITE_INV, we set TLB_INVALID_MASK immediately, + * to force the next access through tlb_fill. We've just + * called tlb_fill, so we know that this entry *is* valid. + */ + flags &= ~TLB_INVALID_MASK; } tlb_addr = tlb_read_ofs(entry, elt_ofs); } - flags = tlb_addr & TLB_FLAGS_MASK; + flags &= tlb_addr; /* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */ if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) { diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/tcg/mem_helper.c +++ b/target/s390x/tcg/mem_helper.c @@ -XXX,XX +XXX,XX @@ static int s390_probe_access(CPUArchState *env, target_ulong addr, int size, #else int flags; - /* - * For !CONFIG_USER_ONLY, we cannot rely on TLB_INVALID_MASK or haddr==NULL - * to detect if there was an exception during tlb_fill(). - */ env->tlb_fill_exc = 0; flags = probe_access_flags(env, addr, access_type, mmu_idx, nonfault, phost, ra); -- 2.34.1 Add an interface to return the CPUTLBEntryFull struct that goes with the lookup. The result is not intended to be valid across multiple lookups, so the user must use the results immediately. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 15 +++++++++++++ include/qemu/typedefs.h | 1 + accel/tcg/cputlb.c | 47 +++++++++++++++++++++++++---------------- 3 files changed, 45 insertions(+), 18 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ int probe_access_flags(CPUArchState *env, target_ulong addr, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr); +#ifndef CONFIG_USER_ONLY +/** + * probe_access_full: + * Like probe_access_flags, except also return into @pfull. + * + * The CPUTLBEntryFull structure returned via @pfull is transient + * and must be consumed or copied immediately, before any further + * access or changes to TLB @mmu_idx. + */ +int probe_access_full(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, + CPUTLBEntryFull **pfull, uintptr_t retaddr); +#endif + #define CODE_GEN_ALIGN 16 /* must be >= of the size of a icache line */ /* Estimated block size for TB allocation. */ diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -XXX,XX +XXX,XX @@ typedef struct ConfidentialGuestSupport ConfidentialGuestSupport; typedef struct CPUAddressSpace CPUAddressSpace; typedef struct CPUArchState CPUArchState; typedef struct CPUState CPUState; +typedef struct CPUTLBEntryFull CPUTLBEntryFull; typedef struct DeviceListener DeviceListener; typedef struct DeviceState DeviceState; typedef struct DirtyBitmapSnapshot DirtyBitmapSnapshot; 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 @@ static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size, static int probe_access_internal(CPUArchState *env, target_ulong addr, int fault_size, MMUAccessType access_type, int mmu_idx, bool nonfault, - void **phost, uintptr_t retaddr) + void **phost, CPUTLBEntryFull **pfull, + uintptr_t retaddr) { uintptr_t index = tlb_index(env, mmu_idx, addr); CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr); @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, mmu_idx, nonfault, retaddr)) { /* Non-faulting page table read failed. */ *phost = NULL; + *pfull = NULL; return TLB_INVALID_MASK; } /* TLB resize via tlb_fill may have moved the entry. */ + index = tlb_index(env, mmu_idx, addr); entry = tlb_entry(env, mmu_idx, addr); /* @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, } flags &= tlb_addr; + *pfull = &env_tlb(env)->d[mmu_idx].fulltlb[index]; + /* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */ if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) { *phost = NULL; @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUArchState *env, target_ulong addr, return flags; } -int probe_access_flags(CPUArchState *env, target_ulong addr, - MMUAccessType access_type, int mmu_idx, - bool nonfault, void **phost, uintptr_t retaddr) +int probe_access_full(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, CPUTLBEntryFull **pfull, + uintptr_t retaddr) { - int flags; - - flags = probe_access_internal(env, addr, 0, access_type, mmu_idx, - nonfault, phost, retaddr); + int flags = probe_access_internal(env, addr, 0, access_type, mmu_idx, + nonfault, phost, pfull, retaddr); /* Handle clean RAM pages. */ if (unlikely(flags & TLB_NOTDIRTY)) { - uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - - notdirty_write(env_cpu(env), addr, 1, full, retaddr); + notdirty_write(env_cpu(env), addr, 1, *pfull, retaddr); flags &= ~TLB_NOTDIRTY; } return flags; } +int probe_access_flags(CPUArchState *env, target_ulong addr, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, uintptr_t retaddr) +{ + CPUTLBEntryFull *full; + + return probe_access_full(env, addr, access_type, mmu_idx, + nonfault, phost, &full, retaddr); +} + void *probe_access(CPUArchState *env, target_ulong addr, int size, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) { + CPUTLBEntryFull *full; void *host; int flags; g_assert(-(addr | TARGET_PAGE_MASK) >= size); flags = probe_access_internal(env, addr, size, access_type, mmu_idx, - false, &host, retaddr); + false, &host, &full, retaddr); /* Per the interface, size == 0 merely faults the access. */ if (size == 0) { @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, } if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) { - uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUTLBEntryFull *full = &env_tlb(env)->d[mmu_idx].fulltlb[index]; - /* Handle watchpoints. */ if (flags & TLB_WATCHPOINT) { int wp_access = (access_type == MMU_DATA_STORE @@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, MMUAccessType access_type, int mmu_idx) { + CPUTLBEntryFull *full; void *host; int flags; flags = probe_access_internal(env, addr, 0, access_type, - mmu_idx, true, &host, 0); + mmu_idx, true, &host, &full, 0); /* No combination of flags are expected by the caller. */ return flags ? NULL : host; @@ -XXX,XX +XXX,XX @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr, void **hostp) { + CPUTLBEntryFull *full; void *p; (void)probe_access_internal(env, addr, 1, MMU_INST_FETCH, - cpu_mmu_index(env, true), false, &p, 0); + cpu_mmu_index(env, true), false, &p, &full, 0); if (p == NULL) { return -1; } -- 2.34.1 Now that we have collected all of the page data into CPUTLBEntryFull, provide an interface to record that all in one go, instead of using 4 arguments. This interface allows CPUTLBEntryFull to be extended without having to change the number of arguments. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 14 +++++++++++ include/exec/exec-all.h | 22 ++++++++++++++++++ accel/tcg/cputlb.c | 51 ++++++++++++++++++++++++++--------------- 3 files changed, 69 insertions(+), 18 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntryFull { * + the offset within the target MemoryRegion (otherwise) */ hwaddr xlat_section; + + /* + * @phys_addr contains the physical address in the address space + * given by cpu_asidx_from_attrs(cpu, @attrs). + */ + hwaddr phys_addr; + + /* @attrs contains the memory transaction attributes for the page. */ MemTxAttrs attrs; + + /* @prot contains the complete protections for the page. */ + uint8_t prot; + + /* @lg_page_size contains the log2 of the page size. */ + uint8_t lg_page_size; } CPUTLBEntryFull; /* diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap, unsigned bits); +/** + * tlb_set_page_full: + * @cpu: CPU context + * @mmu_idx: mmu index of the tlb to modify + * @vaddr: virtual address of the entry to add + * @full: the details of the tlb entry + * + * Add an entry to @cpu tlb index @mmu_idx. All of the fields of + * @full must be filled, except for xlat_section, and constitute + * the complete description of the translated page. + * + * This is generally called by the target tlb_fill function after + * having performed a successful page table walk to find the physical + * address and attributes for the translation. + * + * At most one entry for a given virtual address is permitted. Only a + * single TARGET_PAGE_SIZE region is mapped; @full->lg_page_size is only + * used by tlb_flush_page. + */ +void tlb_set_page_full(CPUState *cpu, int mmu_idx, target_ulong vaddr, + CPUTLBEntryFull *full); + /** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for 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 @@ static void tlb_add_large_page(CPUArchState *env, int mmu_idx, env_tlb(env)->d[mmu_idx].large_page_mask = lp_mask; } -/* Add a new TLB entry. At most one entry for a given virtual address +/* + * Add a new TLB entry. At most one entry for a given virtual address * is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the * supplied size is only used by tlb_flush_page. * * Called from TCG-generated code, which is under an RCU read-side * critical section. */ -void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, - hwaddr paddr, MemTxAttrs attrs, int prot, - int mmu_idx, target_ulong size) +void tlb_set_page_full(CPUState *cpu, int mmu_idx, + target_ulong vaddr, CPUTLBEntryFull *full) { CPUArchState *env = cpu->env_ptr; CPUTLB *tlb = env_tlb(env); @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, CPUTLBEntry *te, tn; hwaddr iotlb, xlat, sz, paddr_page; target_ulong vaddr_page; - int asidx = cpu_asidx_from_attrs(cpu, attrs); - int wp_flags; + int asidx, wp_flags, prot; bool is_ram, is_romd; assert_cpu_is_self(cpu); - if (size <= TARGET_PAGE_SIZE) { + if (full->lg_page_size <= TARGET_PAGE_BITS) { sz = TARGET_PAGE_SIZE; } else { - tlb_add_large_page(env, mmu_idx, vaddr, size); - sz = size; + sz = (hwaddr)1 << full->lg_page_size; + tlb_add_large_page(env, mmu_idx, vaddr, sz); } vaddr_page = vaddr & TARGET_PAGE_MASK; - paddr_page = paddr & TARGET_PAGE_MASK; + paddr_page = full->phys_addr & TARGET_PAGE_MASK; + prot = full->prot; + asidx = cpu_asidx_from_attrs(cpu, full->attrs); section = address_space_translate_for_iotlb(cpu, asidx, paddr_page, - &xlat, &sz, attrs, &prot); + &xlat, &sz, full->attrs, &prot); assert(sz >= TARGET_PAGE_SIZE); tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx " prot=%x idx=%d\n", - vaddr, paddr, prot, mmu_idx); + vaddr, full->phys_addr, prot, mmu_idx); address = vaddr_page; - if (size < TARGET_PAGE_SIZE) { + if (full->lg_page_size < TARGET_PAGE_BITS) { /* Repeat the MMU check and TLB fill on every access. */ address |= TLB_INVALID_MASK; } - if (attrs.byte_swap) { + if (full->attrs.byte_swap) { address |= TLB_BSWAP; } @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * subtract here is that of the page base, and not the same as the * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). */ + desc->fulltlb[index] = *full; desc->fulltlb[index].xlat_section = iotlb - vaddr_page; - desc->fulltlb[index].attrs = attrs; + desc->fulltlb[index].phys_addr = paddr_page; + desc->fulltlb[index].prot = prot; /* Now calculate the new entry */ tn.addend = addend - vaddr_page; @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, qemu_spin_unlock(&tlb->c.lock); } -/* Add a new TLB entry, but without specifying the memory - * transaction attributes to be used. - */ +void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, + hwaddr paddr, MemTxAttrs attrs, int prot, + int mmu_idx, target_ulong size) +{ + CPUTLBEntryFull full = { + .phys_addr = paddr, + .attrs = attrs, + .prot = prot, + .lg_page_size = ctz64(size) + }; + + assert(is_power_of_2(size)); + tlb_set_page_full(cpu, mmu_idx, vaddr, &full); +} + void tlb_set_page(CPUState *cpu, target_ulong vaddr, hwaddr paddr, int prot, int mmu_idx, target_ulong size) -- 2.34.1 Allow the target to cache items from the guest page tables. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/cpu-defs.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntryFull { /* @lg_page_size contains the log2 of the page size. */ uint8_t lg_page_size; + + /* + * Allow target-specific additions to this structure. + * This may be used to cache items from the guest cpu + * page tables for later use by the implementation. + */ +#ifdef TARGET_PAGE_ENTRY_EXTRA + TARGET_PAGE_ENTRY_EXTRA +#endif } CPUTLBEntryFull; /* -- 2.34.1 This bitmap is created and discarded immediately. We gain nothing by its existence. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-Id: <20220822232338.1727934-2-richard.henderson@linaro.org> --- accel/tcg/translate-all.c | 78 ++------------------------------------- 1 file changed, 4 insertions(+), 74 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 @@ #define assert_memory_lock() tcg_debug_assert(have_mmap_lock()) #endif -#define SMC_BITMAP_USE_THRESHOLD 10 - typedef struct PageDesc { /* list of TBs intersecting this ram page */ uintptr_t first_tb; -#ifdef CONFIG_SOFTMMU - /* in order to optimize self modifying code, we count the number - of lookups we do to a given page to use a bitmap */ - unsigned long *code_bitmap; - unsigned int code_write_count; -#else +#ifdef CONFIG_USER_ONLY unsigned long flags; void *target_data; #endif -#ifndef CONFIG_USER_ONLY +#ifdef CONFIG_SOFTMMU QemuSpin lock; #endif } PageDesc; @@ -XXX,XX +XXX,XX @@ void tb_htable_init(void) qht_init(&tb_ctx.htable, tb_cmp, CODE_GEN_HTABLE_SIZE, mode); } -/* call with @p->lock held */ -static inline void invalidate_page_bitmap(PageDesc *p) -{ - assert_page_locked(p); -#ifdef CONFIG_SOFTMMU - g_free(p->code_bitmap); - p->code_bitmap = NULL; - p->code_write_count = 0; -#endif -} - /* Set to NULL all the 'first_tb' fields in all PageDescs. */ static void page_flush_tb_1(int level, void **lp) { @@ -XXX,XX +XXX,XX @@ static void page_flush_tb_1(int level, void **lp) for (i = 0; i < V_L2_SIZE; ++i) { page_lock(&pd[i]); pd[i].first_tb = (uintptr_t)NULL; - invalidate_page_bitmap(pd + i); page_unlock(&pd[i]); } } else { @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) if (rm_from_page_list) { p = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS); tb_page_remove(p, tb); - invalidate_page_bitmap(p); if (tb->page_addr[1] != -1) { p = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS); tb_page_remove(p, tb); - invalidate_page_bitmap(p); } } @@ -XXX,XX +XXX,XX @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr) } } -#ifdef CONFIG_SOFTMMU -/* call with @p->lock held */ -static void build_page_bitmap(PageDesc *p) -{ - int n, tb_start, tb_end; - TranslationBlock *tb; - - assert_page_locked(p); - p->code_bitmap = bitmap_new(TARGET_PAGE_SIZE); - - PAGE_FOR_EACH_TB(p, tb, n) { - /* NOTE: this is subtle as a TB may span two physical pages */ - if (n == 0) { - /* NOTE: tb_end may be after the end of the page, but - it is not a problem */ - tb_start = tb->pc & ~TARGET_PAGE_MASK; - tb_end = tb_start + tb->size; - if (tb_end > TARGET_PAGE_SIZE) { - tb_end = TARGET_PAGE_SIZE; - } - } else { - tb_start = 0; - tb_end = ((tb->pc + tb->size) & ~TARGET_PAGE_MASK); - } - bitmap_set(p->code_bitmap, tb_start, tb_end - tb_start); - } -} -#endif - /* add the tb in the target page and protect it if necessary * * Called with mmap_lock held for user-mode emulation. @@ -XXX,XX +XXX,XX @@ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb, page_already_protected = p->first_tb != (uintptr_t)NULL; #endif p->first_tb = (uintptr_t)tb | n; - invalidate_page_bitmap(p); #if defined(CONFIG_USER_ONLY) /* translator_loop() must have made all TB pages non-writable */ @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, /* remove TB from the page(s) if we couldn't insert it */ if (unlikely(existing_tb)) { tb_page_remove(p, tb); - invalidate_page_bitmap(p); if (p2) { tb_page_remove(p2, tb); - invalidate_page_bitmap(p2); } tb = existing_tb; } @@ -XXX,XX +XXX,XX @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages, #if !defined(CONFIG_USER_ONLY) /* if no code remaining, no need to continue to use slow writes */ if (!p->first_tb) { - invalidate_page_bitmap(p); tlb_unprotect_code(start); } #endif @@ -XXX,XX +XXX,XX @@ void tb_invalidate_phys_page_fast(struct page_collection *pages, } assert_page_locked(p); - if (!p->code_bitmap && - ++p->code_write_count >= SMC_BITMAP_USE_THRESHOLD) { - build_page_bitmap(p); - } - if (p->code_bitmap) { - unsigned int nr; - unsigned long b; - - nr = start & ~TARGET_PAGE_MASK; - b = p->code_bitmap[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1)); - if (b & ((1 << len) - 1)) { - goto do_invalidate; - } - } else { - do_invalidate: - tb_invalidate_phys_page_range__locked(pages, p, start, start + len, - retaddr); - } + tb_invalidate_phys_page_range__locked(pages, p, start, start + len, + retaddr); } #else /* Called with mmap_lock held. If pc is not 0 then it indicates the -- 2.34.1 Bool is more appropriate type for the alloc parameter. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/translate-all.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 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 @@ void page_init(void) #endif } -static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc) +static PageDesc *page_find_alloc(tb_page_addr_t index, bool alloc) { PageDesc *pd; void **lp; @@ -XXX,XX +XXX,XX @@ static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc) static inline PageDesc *page_find(tb_page_addr_t index) { - return page_find_alloc(index, 0); + return page_find_alloc(index, false); } static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, - PageDesc **ret_p2, tb_page_addr_t phys2, int alloc); + PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc); /* In user-mode page locks aren't used; mmap_lock is enough */ #ifdef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static inline void page_unlock(PageDesc *pd) /* lock the page(s) of a TB in the correct acquisition order */ static inline void page_lock_tb(const TranslationBlock *tb) { - page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], 0); + page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], false); } static inline void page_unlock_tb(const TranslationBlock *tb) @@ -XXX,XX +XXX,XX @@ void page_collection_unlock(struct page_collection *set) #endif /* !CONFIG_USER_ONLY */ static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, - PageDesc **ret_p2, tb_page_addr_t phys2, int alloc) + PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc) { PageDesc *p1, *p2; tb_page_addr_t page1; @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, * Note that inserting into the hash table first isn't an option, since * we can only insert TBs that are fully initialized. */ - page_lock_pair(&p, phys_pc, &p2, phys_page2, 1); + page_lock_pair(&p, phys_pc, &p2, phys_page2, true); tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); if (p2) { tb_page_add(p2, tb, 1, phys_page2); @@ -XXX,XX +XXX,XX @@ void page_set_flags(target_ulong start, target_ulong end, int flags) for (addr = start, len = end - start; len != 0; len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) { - PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, 1); + PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, true); /* If the write protection bit is set, then we invalidate the code inside. */ -- 2.34.1 Use the pc coming from db->pc_first rather than the TB. Use the cached host_addr rather than re-computing for the first page. We still need a separate lookup for the second page because it won't be computed for DisasContextBase until the translator actually performs a read from the page. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/plugin-gen.h | 7 ++++--- accel/tcg/plugin-gen.c | 22 +++++++++++----------- accel/tcg/translator.c | 2 +- 3 files changed, 16 insertions(+), 15 deletions(-) diff --git a/include/exec/plugin-gen.h b/include/exec/plugin-gen.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/plugin-gen.h +++ b/include/exec/plugin-gen.h @@ -XXX,XX +XXX,XX @@ struct DisasContextBase; #ifdef CONFIG_PLUGIN -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool supress); +bool plugin_gen_tb_start(CPUState *cpu, const struct DisasContextBase *db, + bool supress); void plugin_gen_tb_end(CPUState *cpu); void plugin_gen_insn_start(CPUState *cpu, const struct DisasContextBase *db); void plugin_gen_insn_end(void); @@ -XXX,XX +XXX,XX @@ static inline void plugin_insn_append(abi_ptr pc, const void *from, size_t size) #else /* !CONFIG_PLUGIN */ -static inline -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool supress) +static inline bool +plugin_gen_tb_start(CPUState *cpu, const struct DisasContextBase *db, bool sup) { return false; } 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 plugin_gen_inject(const struct qemu_plugin_tb *plugin_tb) pr_ops(); } -bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_only) +bool plugin_gen_tb_start(CPUState *cpu, const DisasContextBase *db, + bool mem_only) { bool ret = false; @@ -XXX,XX +XXX,XX @@ bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_onl ret = true; - ptb->vaddr = tb->pc; + ptb->vaddr = db->pc_first; ptb->vaddr2 = -1; - get_page_addr_code_hostp(cpu->env_ptr, tb->pc, &ptb->haddr1); + ptb->haddr1 = db->host_addr[0]; ptb->haddr2 = NULL; ptb->mem_only = mem_only; @@ -XXX,XX +XXX,XX @@ void plugin_gen_insn_start(CPUState *cpu, const DisasContextBase *db) * Note that we skip this when haddr1 == NULL, e.g. when we're * fetching instructions from a region not backed by RAM. */ - if (likely(ptb->haddr1 != NULL && ptb->vaddr2 == -1) && - unlikely((db->pc_next & TARGET_PAGE_MASK) != - (db->pc_first & TARGET_PAGE_MASK))) { - get_page_addr_code_hostp(cpu->env_ptr, db->pc_next, - &ptb->haddr2); - ptb->vaddr2 = db->pc_next; - } - if (likely(ptb->vaddr2 == -1)) { + if (ptb->haddr1 == NULL) { + pinsn->haddr = NULL; + } else if (is_same_page(db, db->pc_next)) { pinsn->haddr = ptb->haddr1 + pinsn->vaddr - ptb->vaddr; } else { + if (ptb->vaddr2 == -1) { + ptb->vaddr2 = TARGET_PAGE_ALIGN(db->pc_first); + get_page_addr_code_hostp(cpu->env_ptr, ptb->vaddr2, &ptb->haddr2); + } pinsn->haddr = ptb->haddr2 + pinsn->vaddr - ptb->vaddr2; } } diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -XXX,XX +XXX,XX @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns, ops->tb_start(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ - plugin_enabled = plugin_gen_tb_start(cpu, tb, cflags & CF_MEMI_ONLY); + plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY); while (true) { db->num_insns++; -- 2.34.1 Let tb->page_addr[0] contain the address of the first byte of the translated block, rather than the address of the page containing the start of the translated block. We need to recover this value anyway at various points, and it is easier to discard a page offset when it is not needed, which happens naturally via the existing find_page shift. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cpu-exec.c | 16 ++++++++-------- accel/tcg/cputlb.c | 3 ++- accel/tcg/translate-all.c | 9 +++++---- 3 files changed, 15 insertions(+), 13 deletions(-) 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 @@ struct tb_desc { target_ulong pc; target_ulong cs_base; CPUArchState *env; - tb_page_addr_t phys_page1; + tb_page_addr_t page_addr0; uint32_t flags; uint32_t cflags; uint32_t trace_vcpu_dstate; @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) const struct tb_desc *desc = d; if (tb->pc == desc->pc && - tb->page_addr[0] == desc->phys_page1 && + tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && tb->trace_vcpu_dstate == desc->trace_vcpu_dstate && @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) if (tb->page_addr[1] == -1) { return true; } else { - tb_page_addr_t phys_page2; - target_ulong virt_page2; + tb_page_addr_t phys_page1; + target_ulong virt_page1; /* * We know that the first page matched, and an otherwise valid TB @@ -XXX,XX +XXX,XX @@ static bool tb_lookup_cmp(const void *p, const void *d) * is different for the new TB. Therefore any exception raised * here by the faulting lookup is not premature. */ - virt_page2 = TARGET_PAGE_ALIGN(desc->pc); - phys_page2 = get_page_addr_code(desc->env, virt_page2); - if (tb->page_addr[1] == phys_page2) { + virt_page1 = TARGET_PAGE_ALIGN(desc->pc); + phys_page1 = get_page_addr_code(desc->env, virt_page1); + if (tb->page_addr[1] == phys_page1) { return true; } } @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, if (phys_pc == -1) { return NULL; } - desc.phys_page1 = phys_pc & TARGET_PAGE_MASK; + desc.page_addr0 = phys_pc; h = tb_hash_func(phys_pc, pc, flags, cflags, *cpu->trace_dstate); return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } 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 tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, can be detected */ void tlb_protect_code(ram_addr_t ram_addr) { - cpu_physical_memory_test_and_clear_dirty(ram_addr, TARGET_PAGE_SIZE, + cpu_physical_memory_test_and_clear_dirty(ram_addr & TARGET_PAGE_MASK, + TARGET_PAGE_SIZE, DIRTY_MEMORY_CODE); } 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 void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) qemu_spin_unlock(&tb->jmp_lock); /* remove the TB from the hash list */ - phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); + phys_pc = tb->page_addr[0]; h = tb_hash_func(phys_pc, tb->pc, tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, * we can only insert TBs that are fully initialized. */ page_lock_pair(&p, phys_pc, &p2, phys_page2, true); - tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); + tb_page_add(p, tb, 0, phys_pc); if (p2) { tb_page_add(p2, tb, 1, phys_page2); } else { @@ -XXX,XX +XXX,XX @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages, if (n == 0) { /* NOTE: tb_end may be after the end of the page, but it is not a problem */ - tb_start = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); + tb_start = tb->page_addr[0]; tb_end = tb_start + tb->size; } else { tb_start = tb->page_addr[1]; - tb_end = tb_start + ((tb->pc + tb->size) & ~TARGET_PAGE_MASK); + tb_end = tb_start + ((tb->page_addr[0] + tb->size) + & ~TARGET_PAGE_MASK); } if (!(tb_end <= start || tb_start >= end)) { #ifdef TARGET_HAS_PRECISE_SMC -- 2.34.1 This function has two users, who use it incompatibly. In tlb_flush_page_by_mmuidx_async_0, when flushing a single page, we need to flush exactly two pages. In tlb_flush_range_by_mmuidx_async_0, when flushing a range of pages, we need to flush N+1 pages. This avoids double-flushing of jmp cache pages in a range. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/cputlb.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) 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 @@ static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr) } } -static void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr) -{ - /* Discard jump cache entries for any tb which might potentially - overlap the flushed page. */ - tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE); - tb_jmp_cache_clear_page(cpu, addr); -} - /** * tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary * @desc: The CPUTLBDesc portion of the TLB @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_by_mmuidx_async_0(CPUState *cpu, } qemu_spin_unlock(&env_tlb(env)->c.lock); - tb_flush_jmp_cache(cpu, addr); + /* + * Discard jump cache entries for any tb which might potentially + * overlap the flushed page, which includes the previous. + */ + tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE); + tb_jmp_cache_clear_page(cpu, addr); } /** @@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, return; } - for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) { - tb_flush_jmp_cache(cpu, d.addr + i); + /* + * Discard jump cache entries for any tb which might potentially + * overlap the flushed pages, which includes the previous. + */ + d.addr -= TARGET_PAGE_SIZE; + for (target_ulong i = 0, n = d.len / TARGET_PAGE_SIZE + 1; i < n; i++) { + tb_jmp_cache_clear_page(cpu, d.addr); + d.addr += TARGET_PAGE_SIZE; } } -- 2.34.1 Wrap the bare TranslationBlock pointer into a structure. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/tb-hash.h | 1 + accel/tcg/tb-jmp-cache.h | 24 ++++++++++++++++++++++++ include/exec/cpu-common.h | 1 + include/hw/core/cpu.h | 15 +-------------- include/qemu/typedefs.h | 1 + accel/stubs/tcg-stub.c | 4 ++++ accel/tcg/cpu-exec.c | 10 +++++++--- accel/tcg/cputlb.c | 9 +++++---- accel/tcg/translate-all.c | 28 +++++++++++++++++++++++++--- hw/core/cpu-common.c | 3 +-- plugins/core.c | 2 +- trace/control-target.c | 2 +- 12 files changed, 72 insertions(+), 28 deletions(-) create mode 100644 accel/tcg/tb-jmp-cache.h diff --git a/accel/tcg/tb-hash.h b/accel/tcg/tb-hash.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tb-hash.h +++ b/accel/tcg/tb-hash.h @@ -XXX,XX +XXX,XX @@ #include "exec/cpu-defs.h" #include "exec/exec-all.h" #include "qemu/xxhash.h" +#include "tb-jmp-cache.h" #ifdef CONFIG_SOFTMMU diff --git a/accel/tcg/tb-jmp-cache.h b/accel/tcg/tb-jmp-cache.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/accel/tcg/tb-jmp-cache.h @@ -XXX,XX +XXX,XX @@ +/* + * The per-CPU TranslationBlock jump cache. + * + * Copyright (c) 2003 Fabrice Bellard + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ACCEL_TCG_TB_JMP_CACHE_H +#define ACCEL_TCG_TB_JMP_CACHE_H + +#define TB_JMP_CACHE_BITS 12 +#define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) + +/* + * Accessed in parallel; all accesses to 'tb' must be atomic. + */ +struct CPUJumpCache { + struct { + TranslationBlock *tb; + } array[TB_JMP_CACHE_SIZE]; +}; + +#endif /* ACCEL_TCG_TB_JMP_CACHE_H */ diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -XXX,XX +XXX,XX @@ void cpu_list_unlock(void); unsigned int cpu_list_generation_id_get(void); void tcg_flush_softmmu_tlb(CPUState *cs); +void tcg_flush_jmp_cache(CPUState *cs); void tcg_iommu_init_notifier_list(CPUState *cpu); void tcg_iommu_free_notifier_list(CPUState *cpu); diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct kvm_run; struct hax_vcpu_state; struct hvf_vcpu_state; -#define TB_JMP_CACHE_BITS 12 -#define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) - /* work queue */ /* The union type allows passing of 64 bit target pointers on 32 bit @@ -XXX,XX +XXX,XX @@ struct CPUState { CPUArchState *env_ptr; IcountDecr *icount_decr_ptr; - /* Accessed in parallel; all accesses must be atomic */ - TranslationBlock *tb_jmp_cache[TB_JMP_CACHE_SIZE]; + CPUJumpCache *tb_jmp_cache; struct GDBRegisterState *gdb_regs; int gdb_num_regs; @@ -XXX,XX +XXX,XX @@ extern CPUTailQ cpus; extern __thread CPUState *current_cpu; -static inline void cpu_tb_jmp_cache_clear(CPUState *cpu) -{ - unsigned int i; - - for (i = 0; i < TB_JMP_CACHE_SIZE; i++) { - qatomic_set(&cpu->tb_jmp_cache[i], NULL); - } -} - /** * qemu_tcg_mttcg_enabled: * Check whether we are running MultiThread TCG or not. diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -XXX,XX +XXX,XX @@ typedef struct CoMutex CoMutex; typedef struct ConfidentialGuestSupport ConfidentialGuestSupport; typedef struct CPUAddressSpace CPUAddressSpace; typedef struct CPUArchState CPUArchState; +typedef struct CPUJumpCache CPUJumpCache; typedef struct CPUState CPUState; typedef struct CPUTLBEntryFull CPUTLBEntryFull; typedef struct DeviceListener DeviceListener; diff --git a/accel/stubs/tcg-stub.c b/accel/stubs/tcg-stub.c index XXXXXXX..XXXXXXX 100644 --- a/accel/stubs/tcg-stub.c +++ b/accel/stubs/tcg-stub.c @@ -XXX,XX +XXX,XX @@ void tlb_set_dirty(CPUState *cpu, target_ulong vaddr) { } +void tcg_flush_jmp_cache(CPUState *cpu) +{ +} + int probe_access_flags(CPUArchState *env, target_ulong addr, MMUAccessType access_type, int mmu_idx, bool nonfault, void **phost, uintptr_t retaddr) 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 "sysemu/replay.h" #include "sysemu/tcg.h" #include "exec/helper-proto.h" +#include "tb-jmp-cache.h" #include "tb-hash.h" #include "tb-context.h" #include "internal.h" @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, tcg_debug_assert(!(cflags & CF_INVALID)); hash = tb_jmp_cache_hash_func(pc); - tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]); + tb = qatomic_rcu_read(&cpu->tb_jmp_cache->array[hash].tb); if (likely(tb && tb->pc == pc && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, if (tb == NULL) { return NULL; } - qatomic_set(&cpu->tb_jmp_cache[hash], tb); + qatomic_set(&cpu->tb_jmp_cache->array[hash].tb, tb); return tb; } @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) tb = tb_lookup(cpu, pc, cs_base, flags, cflags); if (tb == NULL) { + uint32_t h; + mmap_lock(); tb = tb_gen_code(cpu, pc, cs_base, flags, cflags); mmap_unlock(); @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) * We add the TB in the virtual pc hash table * for the fast lookup */ - qatomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb); + h = tb_jmp_cache_hash_func(pc); + qatomic_set(&cpu->tb_jmp_cache->array[h].tb, tb); } #ifndef CONFIG_USER_ONLY 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 @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns, static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr) { - unsigned int i, i0 = tb_jmp_cache_hash_page(page_addr); + int i, i0 = tb_jmp_cache_hash_page(page_addr); + CPUJumpCache *jc = cpu->tb_jmp_cache; for (i = 0; i < TB_JMP_PAGE_SIZE; i++) { - qatomic_set(&cpu->tb_jmp_cache[i0 + i], NULL); + qatomic_set(&jc->array[i0 + i].tb, NULL); } } @@ -XXX,XX +XXX,XX @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data) qemu_spin_unlock(&env_tlb(env)->c.lock); - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); if (to_clean == ALL_MMUIDX_BITS) { qatomic_set(&env_tlb(env)->c.full_flush_count, @@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, * longer to clear each entry individually than it will to clear it all. */ if (d.len >= (TARGET_PAGE_SIZE * TB_JMP_CACHE_SIZE)) { - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); return; } 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 "sysemu/tcg.h" #include "qapi/error.h" #include "hw/core/tcg-cpu-ops.h" +#include "tb-jmp-cache.h" #include "tb-hash.h" #include "tb-context.h" #include "internal.h" @@ -XXX,XX +XXX,XX @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count) } CPU_FOREACH(cpu) { - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); } qht_reset_size(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE); @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ h = tb_jmp_cache_hash_func(tb->pc); CPU_FOREACH(cpu) { - if (qatomic_read(&cpu->tb_jmp_cache[h]) == tb) { - qatomic_set(&cpu->tb_jmp_cache[h], NULL); + CPUJumpCache *jc = cpu->tb_jmp_cache; + if (qatomic_read(&jc->array[h].tb) == tb) { + qatomic_set(&jc->array[h].tb, NULL); } } @@ -XXX,XX +XXX,XX @@ int page_unprotect(target_ulong address, uintptr_t pc) } #endif /* CONFIG_USER_ONLY */ +/* + * Called by generic code at e.g. cpu reset after cpu creation, + * therefore we must be prepared to allocate the jump cache. + */ +void tcg_flush_jmp_cache(CPUState *cpu) +{ + CPUJumpCache *jc = cpu->tb_jmp_cache; + + if (likely(jc)) { + for (int i = 0; i < TB_JMP_CACHE_SIZE; i++) { + qatomic_set(&jc->array[i].tb, NULL); + } + } else { + /* This should happen once during realize, and thus never race. */ + jc = g_new0(CPUJumpCache, 1); + jc = qatomic_xchg(&cpu->tb_jmp_cache, jc); + assert(jc == NULL); + } +} + /* This is a wrapper for common code that can not use CONFIG_SOFTMMU */ void tcg_flush_softmmu_tlb(CPUState *cs) { diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/cpu-common.c +++ b/hw/core/cpu-common.c @@ -XXX,XX +XXX,XX @@ static void cpu_common_reset(DeviceState *dev) cpu->cflags_next_tb = -1; if (tcg_enabled()) { - cpu_tb_jmp_cache_clear(cpu); - + tcg_flush_jmp_cache(cpu); tcg_flush_softmmu_tlb(cpu); } } diff --git a/plugins/core.c b/plugins/core.c index XXXXXXX..XXXXXXX 100644 --- a/plugins/core.c +++ b/plugins/core.c @@ -XXX,XX +XXX,XX @@ struct qemu_plugin_ctx *plugin_id_to_ctx_locked(qemu_plugin_id_t id) static void plugin_cpu_update__async(CPUState *cpu, run_on_cpu_data data) { bitmap_copy(cpu->plugin_mask, &data.host_ulong, QEMU_PLUGIN_EV_MAX); - cpu_tb_jmp_cache_clear(cpu); + tcg_flush_jmp_cache(cpu); } static void plugin_cpu_update__locked(gpointer k, gpointer v, gpointer udata) diff --git a/trace/control-target.c b/trace/control-target.c index XXXXXXX..XXXXXXX 100644 --- a/trace/control-target.c +++ b/trace/control-target.c @@ -XXX,XX +XXX,XX @@ static void trace_event_synchronize_vcpu_state_dynamic( { bitmap_copy(vcpu->trace_dstate, vcpu->trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); - cpu_tb_jmp_cache_clear(vcpu); + tcg_flush_jmp_cache(vcpu); } void trace_event_set_vcpu_state_dynamic(CPUState *vcpu, -- 2.34.1 Populate this new method for all targets. Always match the result that would be given by cpu_get_tb_cpu_state, as we will want these values to correspond in the logs. Reviewed-by: Taylor Simpson <tsimpson@quicinc.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> (target/sparc) Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- Cc: Eduardo Habkost <eduardo@habkost.net> (supporter:Machine core) Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> (supporter:Machine core) Cc: "Philippe Mathieu-Daudé" <f4bug@amsat.org> (reviewer:Machine core) Cc: Yanan Wang <wangyanan55@huawei.com> (reviewer:Machine core) Cc: Michael Rolnik <mrolnik@gmail.com> (maintainer:AVR TCG CPUs) Cc: "Edgar E. Iglesias" <edgar.iglesias@gmail.com> (maintainer:CRIS TCG CPUs) Cc: Taylor Simpson <tsimpson@quicinc.com> (supporter:Hexagon TCG CPUs) Cc: Song Gao <gaosong@loongson.cn> (maintainer:LoongArch TCG CPUs) Cc: Xiaojuan Yang <yangxiaojuan@loongson.cn> (maintainer:LoongArch TCG CPUs) Cc: Laurent Vivier <laurent@vivier.eu> (maintainer:M68K TCG CPUs) Cc: Jiaxun Yang <jiaxun.yang@flygoat.com> (reviewer:MIPS TCG CPUs) Cc: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> (reviewer:MIPS TCG CPUs) Cc: Chris Wulff <crwulff@gmail.com> (maintainer:NiosII TCG CPUs) Cc: Marek Vasut <marex@denx.de> (maintainer:NiosII TCG CPUs) Cc: Stafford Horne <shorne@gmail.com> (odd fixer:OpenRISC TCG CPUs) Cc: Yoshinori Sato <ysato@users.sourceforge.jp> (reviewer:RENESAS RX CPUs) Cc: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> (maintainer:SPARC TCG CPUs) Cc: Bastian Koppelmann <kbastian@mail.uni-paderborn.de> (maintainer:TriCore TCG CPUs) Cc: Max Filippov <jcmvbkbc@gmail.com> (maintainer:Xtensa TCG CPUs) Cc: qemu-arm@nongnu.org (open list:ARM TCG CPUs) Cc: qemu-ppc@nongnu.org (open list:PowerPC TCG CPUs) Cc: qemu-riscv@nongnu.org (open list:RISC-V TCG CPUs) Cc: qemu-s390x@nongnu.org (open list:S390 TCG CPUs) --- include/hw/core/cpu.h | 3 +++ target/alpha/cpu.c | 9 +++++++++ target/arm/cpu.c | 13 +++++++++++++ target/avr/cpu.c | 8 ++++++++ target/cris/cpu.c | 8 ++++++++ target/hexagon/cpu.c | 8 ++++++++ target/hppa/cpu.c | 8 ++++++++ target/i386/cpu.c | 9 +++++++++ target/loongarch/cpu.c | 9 +++++++++ target/m68k/cpu.c | 8 ++++++++ target/microblaze/cpu.c | 8 ++++++++ target/mips/cpu.c | 8 ++++++++ target/nios2/cpu.c | 9 +++++++++ target/openrisc/cpu.c | 8 ++++++++ target/ppc/cpu_init.c | 8 ++++++++ target/riscv/cpu.c | 13 +++++++++++++ target/rx/cpu.c | 8 ++++++++ target/s390x/cpu.c | 8 ++++++++ target/sh4/cpu.c | 8 ++++++++ target/sparc/cpu.c | 8 ++++++++ target/tricore/cpu.c | 9 +++++++++ target/xtensa/cpu.c | 8 ++++++++ 22 files changed, 186 insertions(+) diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ struct SysemuCPUOps; * If the target behaviour here is anything other than "set * the PC register to the value passed in" then the target must * also implement the synchronize_from_tb hook. + * @get_pc: Callback for getting the Program Counter register. + * As above, with the semantics of the target architecture. * @gdb_read_register: Callback for letting GDB read a register. * @gdb_write_register: Callback for letting GDB write a register. * @gdb_adjust_breakpoint: Callback for adjusting the address of a @@ -XXX,XX +XXX,XX @@ struct CPUClass { void (*dump_state)(CPUState *cpu, FILE *, int flags); int64_t (*get_arch_id)(CPUState *cpu); void (*set_pc)(CPUState *cpu, vaddr value); + vaddr (*get_pc)(CPUState *cpu); int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg); int (*gdb_write_register)(CPUState *cpu, uint8_t *buf, int reg); vaddr (*gdb_adjust_breakpoint)(CPUState *cpu, vaddr addr); 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 void alpha_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr alpha_cpu_get_pc(CPUState *cs) +{ + AlphaCPU *cpu = ALPHA_CPU(cs); + + return cpu->env.pc; +} + + static bool alpha_cpu_has_work(CPUState *cs) { /* Here we are checking to see if the CPU should wake up from HALT. @@ -XXX,XX +XXX,XX @@ static void alpha_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = alpha_cpu_has_work; cc->dump_state = alpha_cpu_dump_state; cc->set_pc = alpha_cpu_set_pc; + cc->get_pc = alpha_cpu_get_pc; cc->gdb_read_register = alpha_cpu_gdb_read_register; cc->gdb_write_register = alpha_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void arm_cpu_set_pc(CPUState *cs, vaddr value) } } +static vaddr arm_cpu_get_pc(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + if (is_a64(env)) { + return env->pc; + } else { + return env->regs[15]; + } +} + #ifdef CONFIG_TCG void arm_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = arm_cpu_has_work; cc->dump_state = arm_cpu_dump_state; cc->set_pc = arm_cpu_set_pc; + cc->get_pc = arm_cpu_get_pc; cc->gdb_read_register = arm_cpu_gdb_read_register; cc->gdb_write_register = arm_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void avr_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc_w = value / 2; /* internally PC points to words */ } +static vaddr avr_cpu_get_pc(CPUState *cs) +{ + AVRCPU *cpu = AVR_CPU(cs); + + return cpu->env.pc_w * 2; +} + static bool avr_cpu_has_work(CPUState *cs) { AVRCPU *cpu = AVR_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void avr_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = avr_cpu_has_work; cc->dump_state = avr_cpu_dump_state; cc->set_pc = avr_cpu_set_pc; + cc->get_pc = avr_cpu_get_pc; dc->vmsd = &vms_avr_cpu; cc->sysemu_ops = &avr_sysemu_ops; cc->disas_set_info = avr_cpu_disas_set_info; diff --git a/target/cris/cpu.c b/target/cris/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/cpu.c +++ b/target/cris/cpu.c @@ -XXX,XX +XXX,XX @@ static void cris_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr cris_cpu_get_pc(CPUState *cs) +{ + CRISCPU *cpu = CRIS_CPU(cs); + + return cpu->env.pc; +} + static bool cris_cpu_has_work(CPUState *cs) { return cs->interrupt_request & (CPU_INTERRUPT_HARD | CPU_INTERRUPT_NMI); @@ -XXX,XX +XXX,XX @@ static void cris_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = cris_cpu_has_work; cc->dump_state = cris_cpu_dump_state; cc->set_pc = cris_cpu_set_pc; + cc->get_pc = cris_cpu_get_pc; cc->gdb_read_register = cris_cpu_gdb_read_register; cc->gdb_write_register = cris_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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_set_pc(CPUState *cs, vaddr value) env->gpr[HEX_REG_PC] = value; } +static vaddr hexagon_cpu_get_pc(CPUState *cs) +{ + HexagonCPU *cpu = HEXAGON_CPU(cs); + CPUHexagonState *env = &cpu->env; + return env->gpr[HEX_REG_PC]; +} + static void hexagon_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_class_init(ObjectClass *c, void *data) cc->has_work = hexagon_cpu_has_work; cc->dump_state = hexagon_dump_state; cc->set_pc = hexagon_cpu_set_pc; + cc->get_pc = hexagon_cpu_get_pc; cc->gdb_read_register = hexagon_gdb_read_register; cc->gdb_write_register = hexagon_gdb_write_register; cc->gdb_num_core_regs = TOTAL_PER_THREAD_REGS + NUM_VREGS + NUM_QREGS; 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 void hppa_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.iaoq_b = value + 4; } +static vaddr hppa_cpu_get_pc(CPUState *cs) +{ + HPPACPU *cpu = HPPA_CPU(cs); + + return cpu->env.iaoq_f; +} + static void hppa_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = hppa_cpu_has_work; cc->dump_state = hppa_cpu_dump_state; cc->set_pc = hppa_cpu_set_pc; + cc->get_pc = hppa_cpu_get_pc; cc->gdb_read_register = hppa_cpu_gdb_read_register; cc->gdb_write_register = hppa_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/i386/cpu.c b/target/i386/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -XXX,XX +XXX,XX @@ static void x86_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.eip = value; } +static vaddr x86_cpu_get_pc(CPUState *cs) +{ + X86CPU *cpu = X86_CPU(cs); + + /* Match cpu_get_tb_cpu_state. */ + return cpu->env.eip + cpu->env.segs[R_CS].base; +} + int x86_cpu_pending_interrupt(CPUState *cs, int interrupt_request) { X86CPU *cpu = X86_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data) cc->has_work = x86_cpu_has_work; cc->dump_state = x86_cpu_dump_state; cc->set_pc = x86_cpu_set_pc; + cc->get_pc = x86_cpu_get_pc; cc->gdb_read_register = x86_cpu_gdb_read_register; cc->gdb_write_register = x86_cpu_gdb_write_register; cc->get_arch_id = x86_cpu_get_arch_id; 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_set_pc(CPUState *cs, vaddr value) env->pc = value; } +static vaddr loongarch_cpu_get_pc(CPUState *cs) +{ + LoongArchCPU *cpu = LOONGARCH_CPU(cs); + CPULoongArchState *env = &cpu->env; + + return env->pc; +} + #ifndef CONFIG_USER_ONLY #include "hw/loongarch/virt.h" @@ -XXX,XX +XXX,XX @@ static void loongarch_cpu_class_init(ObjectClass *c, void *data) cc->has_work = loongarch_cpu_has_work; cc->dump_state = loongarch_cpu_dump_state; cc->set_pc = loongarch_cpu_set_pc; + cc->get_pc = loongarch_cpu_get_pc; #ifndef CONFIG_USER_ONLY dc->vmsd = &vmstate_loongarch_cpu; cc->sysemu_ops = &loongarch_sysemu_ops; 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 void m68k_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr m68k_cpu_get_pc(CPUState *cs) +{ + M68kCPU *cpu = M68K_CPU(cs); + + return cpu->env.pc; +} + static bool m68k_cpu_has_work(CPUState *cs) { return cs->interrupt_request & CPU_INTERRUPT_HARD; @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_class_init(ObjectClass *c, void *data) cc->has_work = m68k_cpu_has_work; cc->dump_state = m68k_cpu_dump_state; cc->set_pc = m68k_cpu_set_pc; + cc->get_pc = m68k_cpu_get_pc; cc->gdb_read_register = m68k_cpu_gdb_read_register; cc->gdb_write_register = m68k_cpu_gdb_write_register; #if defined(CONFIG_SOFTMMU) 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 void mb_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.iflags = 0; } +static vaddr mb_cpu_get_pc(CPUState *cs) +{ + MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); + + return cpu->env.pc; +} + static void mb_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void mb_cpu_class_init(ObjectClass *oc, void *data) cc->dump_state = mb_cpu_dump_state; cc->set_pc = mb_cpu_set_pc; + cc->get_pc = mb_cpu_get_pc; cc->gdb_read_register = mb_cpu_gdb_read_register; cc->gdb_write_register = mb_cpu_gdb_write_register; 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 void mips_cpu_set_pc(CPUState *cs, vaddr value) mips_env_set_pc(&cpu->env, value); } +static vaddr mips_cpu_get_pc(CPUState *cs) +{ + MIPSCPU *cpu = MIPS_CPU(cs); + + return cpu->env.active_tc.PC; +} + static bool mips_cpu_has_work(CPUState *cs) { MIPSCPU *cpu = MIPS_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void mips_cpu_class_init(ObjectClass *c, void *data) cc->has_work = mips_cpu_has_work; cc->dump_state = mips_cpu_dump_state; cc->set_pc = mips_cpu_set_pc; + cc->get_pc = mips_cpu_get_pc; cc->gdb_read_register = mips_cpu_gdb_read_register; cc->gdb_write_register = mips_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_set_pc(CPUState *cs, vaddr value) env->pc = value; } +static vaddr nios2_cpu_get_pc(CPUState *cs) +{ + Nios2CPU *cpu = NIOS2_CPU(cs); + CPUNios2State *env = &cpu->env; + + return env->pc; +} + static bool nios2_cpu_has_work(CPUState *cs) { return cs->interrupt_request & CPU_INTERRUPT_HARD; @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = nios2_cpu_has_work; cc->dump_state = nios2_cpu_dump_state; cc->set_pc = nios2_cpu_set_pc; + cc->get_pc = nios2_cpu_get_pc; cc->disas_set_info = nios2_cpu_disas_set_info; #ifndef CONFIG_USER_ONLY cc->sysemu_ops = &nios2_sysemu_ops; 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 void openrisc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.dflag = 0; } +static vaddr openrisc_cpu_get_pc(CPUState *cs) +{ + OpenRISCCPU *cpu = OPENRISC_CPU(cs); + + return cpu->env.pc; +} + static void openrisc_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = openrisc_cpu_has_work; cc->dump_state = openrisc_cpu_dump_state; cc->set_pc = openrisc_cpu_set_pc; + cc->get_pc = openrisc_cpu_get_pc; cc->gdb_read_register = openrisc_cpu_gdb_read_register; cc->gdb_write_register = openrisc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void ppc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.nip = value; } +static vaddr ppc_cpu_get_pc(CPUState *cs) +{ + PowerPCCPU *cpu = POWERPC_CPU(cs); + + return cpu->env.nip; +} + static bool ppc_cpu_has_work(CPUState *cs) { PowerPCCPU *cpu = POWERPC_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = ppc_cpu_has_work; cc->dump_state = ppc_cpu_dump_state; cc->set_pc = ppc_cpu_set_pc; + cc->get_pc = ppc_cpu_get_pc; cc->gdb_read_register = ppc_cpu_gdb_read_register; cc->gdb_write_register = ppc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_set_pc(CPUState *cs, vaddr value) } } +static vaddr riscv_cpu_get_pc(CPUState *cs) +{ + RISCVCPU *cpu = RISCV_CPU(cs); + CPURISCVState *env = &cpu->env; + + /* Match cpu_get_tb_cpu_state. */ + if (env->xl == MXL_RV32) { + return env->pc & UINT32_MAX; + } + return env->pc; +} + static void riscv_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_class_init(ObjectClass *c, void *data) cc->has_work = riscv_cpu_has_work; cc->dump_state = riscv_cpu_dump_state; cc->set_pc = riscv_cpu_set_pc; + cc->get_pc = riscv_cpu_get_pc; cc->gdb_read_register = riscv_cpu_gdb_read_register; cc->gdb_write_register = riscv_cpu_gdb_write_register; cc->gdb_num_core_regs = 33; 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 void rx_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr rx_cpu_get_pc(CPUState *cs) +{ + RXCPU *cpu = RX_CPU(cs); + + return cpu->env.pc; +} + static void rx_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void rx_cpu_class_init(ObjectClass *klass, void *data) cc->has_work = rx_cpu_has_work; cc->dump_state = rx_cpu_dump_state; cc->set_pc = rx_cpu_set_pc; + cc->get_pc = rx_cpu_get_pc; #ifndef CONFIG_USER_ONLY cc->sysemu_ops = &rx_sysemu_ops; 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 @@ static void s390_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.psw.addr = value; } +static vaddr s390_cpu_get_pc(CPUState *cs) +{ + S390CPU *cpu = S390_CPU(cs); + + return cpu->env.psw.addr; +} + static bool s390_cpu_has_work(CPUState *cs) { S390CPU *cpu = S390_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void s390_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = s390_cpu_has_work; cc->dump_state = s390_cpu_dump_state; cc->set_pc = s390_cpu_set_pc; + cc->get_pc = s390_cpu_get_pc; cc->gdb_read_register = s390_cpu_gdb_read_register; cc->gdb_write_register = s390_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void superh_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr superh_cpu_get_pc(CPUState *cs) +{ + SuperHCPU *cpu = SUPERH_CPU(cs); + + return cpu->env.pc; +} + static void superh_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void superh_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = superh_cpu_has_work; cc->dump_state = superh_cpu_dump_state; cc->set_pc = superh_cpu_set_pc; + cc->get_pc = superh_cpu_get_pc; cc->gdb_read_register = superh_cpu_gdb_read_register; cc->gdb_write_register = superh_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void sparc_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.npc = value + 4; } +static vaddr sparc_cpu_get_pc(CPUState *cs) +{ + SPARCCPU *cpu = SPARC_CPU(cs); + + return cpu->env.pc; +} + static void sparc_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_class_init(ObjectClass *oc, void *data) cc->memory_rw_debug = sparc_cpu_memory_rw_debug; #endif cc->set_pc = sparc_cpu_set_pc; + cc->get_pc = sparc_cpu_get_pc; cc->gdb_read_register = sparc_cpu_gdb_read_register; cc->gdb_write_register = sparc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY 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 void tricore_cpu_set_pc(CPUState *cs, vaddr value) env->PC = value & ~(target_ulong)1; } +static vaddr tricore_cpu_get_pc(CPUState *cs) +{ + TriCoreCPU *cpu = TRICORE_CPU(cs); + CPUTriCoreState *env = &cpu->env; + + return env->PC; +} + static void tricore_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) { @@ -XXX,XX +XXX,XX @@ static void tricore_cpu_class_init(ObjectClass *c, void *data) cc->dump_state = tricore_cpu_dump_state; cc->set_pc = tricore_cpu_set_pc; + cc->get_pc = tricore_cpu_get_pc; cc->sysemu_ops = &tricore_sysemu_ops; cc->tcg_ops = &tricore_tcg_ops; } 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 void xtensa_cpu_set_pc(CPUState *cs, vaddr value) cpu->env.pc = value; } +static vaddr xtensa_cpu_get_pc(CPUState *cs) +{ + XtensaCPU *cpu = XTENSA_CPU(cs); + + return cpu->env.pc; +} + static bool xtensa_cpu_has_work(CPUState *cs) { #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_class_init(ObjectClass *oc, void *data) cc->has_work = xtensa_cpu_has_work; cc->dump_state = xtensa_cpu_dump_state; cc->set_pc = xtensa_cpu_set_pc; + cc->get_pc = xtensa_cpu_get_pc; cc->gdb_read_register = xtensa_cpu_gdb_read_register; cc->gdb_write_register = xtensa_cpu_gdb_write_register; cc->gdb_stop_before_watchpoint = true; -- 2.34.1 The availability of tb->pc will shortly be conditional. Introduce accessor functions to minimize ifdefs. Pass around a known pc to places like tcg_gen_code, where the caller must already have the value. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/internal.h | 6 ++++ include/exec/exec-all.h | 6 ++++ include/tcg/tcg.h | 2 +- accel/tcg/cpu-exec.c | 46 ++++++++++++++----------- accel/tcg/translate-all.c | 37 +++++++++++--------- target/arm/cpu.c | 4 +-- target/avr/cpu.c | 2 +- target/hexagon/cpu.c | 2 +- target/hppa/cpu.c | 4 +-- target/i386/tcg/tcg-cpu.c | 2 +- target/loongarch/cpu.c | 2 +- target/microblaze/cpu.c | 2 +- target/mips/tcg/exception.c | 2 +- target/mips/tcg/sysemu/special_helper.c | 2 +- target/openrisc/cpu.c | 2 +- target/riscv/cpu.c | 4 +-- target/rx/cpu.c | 2 +- target/sh4/cpu.c | 4 +-- target/sparc/cpu.c | 2 +- target/tricore/cpu.c | 2 +- tcg/tcg.c | 8 ++--- 21 files changed, 82 insertions(+), 61 deletions(-) diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -XXX,XX +XXX,XX @@ G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr); void page_init(void); void tb_htable_init(void); +/* Return the current PC from CPU, which may be cached in TB. */ +static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) +{ + return tb_pc(tb); +} + #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { uintptr_t jmp_dest[2]; }; +/* Hide the read to avoid ifdefs for TARGET_TB_PCREL. */ +static inline target_ulong tb_pc(const TranslationBlock *tb) +{ + return tb->pc; +} + /* Hide the qatomic_read to make code a little easier on the eyes */ static inline uint32_t tb_cflags(const TranslationBlock *tb) { diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index XXXXXXX..XXXXXXX 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -XXX,XX +XXX,XX @@ void tcg_register_thread(void); void tcg_prologue_init(TCGContext *s); void tcg_func_start(TCGContext *s); -int tcg_gen_code(TCGContext *s, TranslationBlock *tb); +int tcg_gen_code(TCGContext *s, TranslationBlock *tb, target_ulong pc_start); void tcg_set_frame(TCGContext *s, TCGReg reg, intptr_t start, intptr_t size); 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 @@ static bool tb_lookup_cmp(const void *p, const void *d) const TranslationBlock *tb = p; const struct tb_desc *desc = d; - if (tb->pc == desc->pc && + if (tb_pc(tb) == desc->pc && tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, return tb; } -static inline void log_cpu_exec(target_ulong pc, CPUState *cpu, - const TranslationBlock *tb) +static void log_cpu_exec(target_ulong pc, CPUState *cpu, + const TranslationBlock *tb) { - if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) - && qemu_log_in_addr_range(pc)) { - + if (qemu_log_in_addr_range(pc)) { qemu_log_mask(CPU_LOG_EXEC, "Trace %d: %p [" TARGET_FMT_lx "/" TARGET_FMT_lx "/%08x/%08x] %s\n", @@ -XXX,XX +XXX,XX @@ const void *HELPER(lookup_tb_ptr)(CPUArchState *env) return tcg_code_gen_epilogue; } - log_cpu_exec(pc, cpu, tb); + if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) { + log_cpu_exec(pc, cpu, tb); + } return tb->tc.ptr; } @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) TranslationBlock *last_tb; const void *tb_ptr = itb->tc.ptr; - log_cpu_exec(itb->pc, cpu, itb); + if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) { + log_cpu_exec(log_pc(cpu, itb), cpu, itb); + } qemu_thread_jit_execute(); ret = tcg_qemu_tb_exec(env, tb_ptr); @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) * of the start of the TB. */ CPUClass *cc = CPU_GET_CLASS(cpu); - qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc, - "Stopped execution of TB chain before %p [" - TARGET_FMT_lx "] %s\n", - last_tb->tc.ptr, last_tb->pc, - lookup_symbol(last_tb->pc)); + if (cc->tcg_ops->synchronize_from_tb) { cc->tcg_ops->synchronize_from_tb(cpu, last_tb); } else { assert(cc->set_pc); - cc->set_pc(cpu, last_tb->pc); + cc->set_pc(cpu, tb_pc(last_tb)); + } + if (qemu_loglevel_mask(CPU_LOG_EXEC)) { + target_ulong pc = log_pc(cpu, last_tb); + if (qemu_log_in_addr_range(pc)) { + qemu_log("Stopped execution of TB chain before %p [" + TARGET_FMT_lx "] %s\n", + last_tb->tc.ptr, pc, lookup_symbol(pc)); + } } } @@ -XXX,XX +XXX,XX @@ static inline void tb_add_jump(TranslationBlock *tb, int n, qemu_spin_unlock(&tb_next->jmp_lock); - qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc, - "Linking TBs %p [" TARGET_FMT_lx - "] index %d -> %p [" TARGET_FMT_lx "]\n", - tb->tc.ptr, tb->pc, n, - tb_next->tc.ptr, tb_next->pc); + qemu_log_mask(CPU_LOG_EXEC, "Linking TBs %p index %d -> %p\n", + tb->tc.ptr, n, tb_next->tc.ptr); return; out_unlock_next: @@ -XXX,XX +XXX,XX @@ static inline bool cpu_handle_interrupt(CPUState *cpu, } static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb, + target_ulong pc, TranslationBlock **last_tb, int *tb_exit) { int32_t insns_left; - trace_exec_tb(tb, tb->pc); + trace_exec_tb(tb, pc); tb = cpu_tb_exec(cpu, tb, tb_exit); if (*tb_exit != TB_EXIT_REQUESTED) { *last_tb = tb; @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) tb_add_jump(last_tb, tb_exit, tb); } - cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit); + cpu_loop_exec_tb(cpu, tb, pc, &last_tb, &tb_exit); /* Try to align the host and virtual clocks if the guest is in advance */ 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 encode_search(TranslationBlock *tb, uint8_t *block) for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { - prev = (j == 0 ? tb->pc : 0); + prev = (j == 0 ? tb_pc(tb) : 0); } else { prev = tcg_ctx->gen_insn_data[i - 1][j]; } @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, uintptr_t searched_pc, bool reset_icount) { - target_ulong data[TARGET_INSN_START_WORDS] = { tb->pc }; + target_ulong data[TARGET_INSN_START_WORDS] = { tb_pc(tb) }; uintptr_t host_pc = (uintptr_t)tb->tc.ptr; CPUArchState *env = cpu->env_ptr; const uint8_t *p = tb->tc.ptr + tb->tc.size; @@ -XXX,XX +XXX,XX @@ static bool tb_cmp(const void *ap, const void *bp) const TranslationBlock *a = ap; const TranslationBlock *b = bp; - return a->pc == b->pc && + return tb_pc(a) == tb_pc(b) && a->cs_base == b->cs_base && a->flags == b->flags && (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && @@ -XXX,XX +XXX,XX @@ static void do_tb_invalidate_check(void *p, uint32_t hash, void *userp) TranslationBlock *tb = p; target_ulong addr = *(target_ulong *)userp; - if (!(addr + TARGET_PAGE_SIZE <= tb->pc || addr >= tb->pc + tb->size)) { + if (!(addr + TARGET_PAGE_SIZE <= tb_pc(tb) || + addr >= tb_pc(tb) + tb->size)) { printf("ERROR invalidate: address=" TARGET_FMT_lx - " PC=%08lx size=%04x\n", addr, (long)tb->pc, tb->size); + " PC=%08lx size=%04x\n", addr, (long)tb_pc(tb), tb->size); } } @@ -XXX,XX +XXX,XX @@ static void do_tb_page_check(void *p, uint32_t hash, void *userp) TranslationBlock *tb = p; int flags1, flags2; - flags1 = page_get_flags(tb->pc); - flags2 = page_get_flags(tb->pc + tb->size - 1); + flags1 = page_get_flags(tb_pc(tb)); + flags2 = page_get_flags(tb_pc(tb) + tb->size - 1); if ((flags1 & PAGE_WRITE) || (flags2 & PAGE_WRITE)) { printf("ERROR page flags: PC=%08lx size=%04x f1=%x f2=%x\n", - (long)tb->pc, tb->size, flags1, flags2); + (long)tb_pc(tb), tb->size, flags1, flags2); } } @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ phys_pc = tb->page_addr[0]; - h = tb_hash_func(phys_pc, tb->pc, tb->flags, orig_cflags, + h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, } /* add in the hash table */ - h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags, + h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, tb->cflags, tb->trace_vcpu_dstate); qht_insert(&tb_ctx.htable, tb, h, &existing_tb); @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_ctx->cpu = NULL; max_insns = tb->icount; - trace_translate_block(tb, tb->pc, tb->tc.ptr); + trace_translate_block(tb, pc, tb->tc.ptr); /* generate machine code */ tb->jmp_reset_offset[0] = TB_JMP_RESET_OFFSET_INVALID; @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, ti = profile_getclock(); #endif - gen_code_size = tcg_gen_code(tcg_ctx, tb); + gen_code_size = tcg_gen_code(tcg_ctx, tb, pc); if (unlikely(gen_code_size < 0)) { error_return: switch (gen_code_size) { @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, #ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) && - qemu_log_in_addr_range(tb->pc)) { + qemu_log_in_addr_range(pc)) { FILE *logfile = qemu_log_trylock(); if (logfile) { int code_size, data_size; @@ -XXX,XX +XXX,XX @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr) */ cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | CF_LAST_IO | n; - qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc, - "cpu_io_recompile: rewound execution of TB to " - TARGET_FMT_lx "\n", tb->pc); + if (qemu_loglevel_mask(CPU_LOG_EXEC)) { + target_ulong pc = log_pc(cpu, tb); + if (qemu_log_in_addr_range(pc)) { + qemu_log("cpu_io_recompile: rewound execution of TB to " + TARGET_FMT_lx "\n", pc); + } + } cpu_loop_exit_noexc(cpu); } 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 @@ void arm_cpu_synchronize_from_tb(CPUState *cs, * never possible for an AArch64 TB to chain to an AArch32 TB. */ if (is_a64(env)) { - env->pc = tb->pc; + env->pc = tb_pc(tb); } else { - env->regs[15] = tb->pc; + env->regs[15] = tb_pc(tb); } } #endif /* CONFIG_TCG */ 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 void avr_cpu_synchronize_from_tb(CPUState *cs, AVRCPU *cpu = AVR_CPU(cs); CPUAVRState *env = &cpu->env; - env->pc_w = tb->pc / 2; /* internally PC points to words */ + env->pc_w = tb_pc(tb) / 2; /* internally PC points to words */ } static void avr_cpu_reset(DeviceState *ds) 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_synchronize_from_tb(CPUState *cs, { HexagonCPU *cpu = HEXAGON_CPU(cs); CPUHexagonState *env = &cpu->env; - env->gpr[HEX_REG_PC] = tb->pc; + env->gpr[HEX_REG_PC] = tb_pc(tb); } static bool hexagon_cpu_has_work(CPUState *cs) 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 void hppa_cpu_synchronize_from_tb(CPUState *cs, HPPACPU *cpu = HPPA_CPU(cs); #ifdef CONFIG_USER_ONLY - cpu->env.iaoq_f = tb->pc; + cpu->env.iaoq_f = tb_pc(tb); cpu->env.iaoq_b = tb->cs_base; #else /* Recover the IAOQ values from the GVA + PRIV. */ @@ -XXX,XX +XXX,XX @@ static void hppa_cpu_synchronize_from_tb(CPUState *cs, int32_t diff = cs_base; cpu->env.iasq_f = iasq_f; - cpu->env.iaoq_f = (tb->pc & ~iasq_f) + priv; + cpu->env.iaoq_f = (tb_pc(tb) & ~iasq_f) + priv; if (diff) { cpu->env.iaoq_b = cpu->env.iaoq_f + diff; } 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 void x86_cpu_synchronize_from_tb(CPUState *cs, { X86CPU *cpu = X86_CPU(cs); - cpu->env.eip = tb->pc - tb->cs_base; + cpu->env.eip = tb_pc(tb) - tb->cs_base; } #ifndef CONFIG_USER_ONLY 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_synchronize_from_tb(CPUState *cs, LoongArchCPU *cpu = LOONGARCH_CPU(cs); CPULoongArchState *env = &cpu->env; - env->pc = tb->pc; + env->pc = tb_pc(tb); } #endif /* CONFIG_TCG */ 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 void mb_cpu_synchronize_from_tb(CPUState *cs, { MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.iflags = tb->flags & IFLAGS_TB_MASK; } diff --git a/target/mips/tcg/exception.c b/target/mips/tcg/exception.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/exception.c +++ b/target/mips/tcg/exception.c @@ -XXX,XX +XXX,XX @@ void mips_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) MIPSCPU *cpu = MIPS_CPU(cs); CPUMIPSState *env = &cpu->env; - env->active_tc.PC = tb->pc; + env->active_tc.PC = tb_pc(tb); env->hflags &= ~MIPS_HFLAG_BMASK; env->hflags |= tb->flags & MIPS_HFLAG_BMASK; } diff --git a/target/mips/tcg/sysemu/special_helper.c b/target/mips/tcg/sysemu/special_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/sysemu/special_helper.c +++ b/target/mips/tcg/sysemu/special_helper.c @@ -XXX,XX +XXX,XX @@ bool mips_io_recompile_replay_branch(CPUState *cs, const TranslationBlock *tb) CPUMIPSState *env = &cpu->env; if ((env->hflags & MIPS_HFLAG_BMASK) != 0 - && env->active_tc.PC != tb->pc) { + && env->active_tc.PC != tb_pc(tb)) { env->active_tc.PC -= (env->hflags & MIPS_HFLAG_B16 ? 2 : 4); env->hflags &= ~MIPS_HFLAG_BMASK; return true; 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 void openrisc_cpu_synchronize_from_tb(CPUState *cs, { OpenRISCCPU *cpu = OPENRISC_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); } diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_synchronize_from_tb(CPUState *cs, RISCVMXL xl = FIELD_EX32(tb->flags, TB_FLAGS, XL); if (xl == MXL_RV32) { - env->pc = (int32_t)tb->pc; + env->pc = (int32_t)tb_pc(tb); } else { - env->pc = tb->pc; + env->pc = tb_pc(tb); } } 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 void rx_cpu_synchronize_from_tb(CPUState *cs, { RXCPU *cpu = RX_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); } static bool rx_cpu_has_work(CPUState *cs) 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 void superh_cpu_synchronize_from_tb(CPUState *cs, { SuperHCPU *cpu = SUPERH_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.flags = tb->flags & TB_FLAG_ENVFLAGS_MASK; } @@ -XXX,XX +XXX,XX @@ static bool superh_io_recompile_replay_branch(CPUState *cs, CPUSH4State *env = &cpu->env; if ((env->flags & ((DELAY_SLOT | DELAY_SLOT_CONDITIONAL))) != 0 - && env->pc != tb->pc) { + && env->pc != tb_pc(tb)) { env->pc -= 2; env->flags &= ~(DELAY_SLOT | DELAY_SLOT_CONDITIONAL); return true; 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 void sparc_cpu_synchronize_from_tb(CPUState *cs, { SPARCCPU *cpu = SPARC_CPU(cs); - cpu->env.pc = tb->pc; + cpu->env.pc = tb_pc(tb); cpu->env.npc = tb->cs_base; } 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 void tricore_cpu_synchronize_from_tb(CPUState *cs, TriCoreCPU *cpu = TRICORE_CPU(cs); CPUTriCoreState *env = &cpu->env; - env->PC = tb->pc; + env->PC = tb_pc(tb); } static void tricore_cpu_reset(DeviceState *dev) 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 @@ int64_t tcg_cpu_exec_time(void) #endif -int tcg_gen_code(TCGContext *s, TranslationBlock *tb) +int tcg_gen_code(TCGContext *s, TranslationBlock *tb, target_ulong pc_start) { #ifdef CONFIG_PROFILER TCGProfile *prof = &s->prof; @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP:\n"); @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) if (s->nb_indirects > 0) { #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_IND) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP before indirect lowering:\n"); @@ -XXX,XX +XXX,XX @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb) #ifdef DEBUG_DISAS if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_OPT) - && qemu_log_in_addr_range(tb->pc))) { + && qemu_log_in_addr_range(pc_start))) { FILE *logfile = qemu_log_trylock(); if (logfile) { fprintf(logfile, "OP after optimization and liveness analysis:\n"); -- 2.34.1 Prepare for targets to be able to produce TBs that can run in more than one virtual context. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- accel/tcg/internal.h | 4 +++ accel/tcg/tb-jmp-cache.h | 41 +++++++++++++++++++++++++ include/exec/cpu-defs.h | 3 ++ include/exec/exec-all.h | 32 ++++++++++++++++++-- accel/tcg/cpu-exec.c | 16 ++++++---- accel/tcg/translate-all.c | 64 ++++++++++++++++++++++++++------------- 6 files changed, 131 insertions(+), 29 deletions(-) diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -XXX,XX +XXX,XX @@ void tb_htable_init(void); /* Return the current PC from CPU, which may be cached in TB. */ static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) { +#if TARGET_TB_PCREL + return cpu->cc->get_pc(cpu); +#else return tb_pc(tb); +#endif } #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/accel/tcg/tb-jmp-cache.h b/accel/tcg/tb-jmp-cache.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tb-jmp-cache.h +++ b/accel/tcg/tb-jmp-cache.h @@ -XXX,XX +XXX,XX @@ /* * Accessed in parallel; all accesses to 'tb' must be atomic. + * For TARGET_TB_PCREL, accesses to 'pc' must be protected by + * a load_acquire/store_release to 'tb'. */ struct CPUJumpCache { struct { TranslationBlock *tb; +#if TARGET_TB_PCREL + target_ulong pc; +#endif } array[TB_JMP_CACHE_SIZE]; }; +static inline TranslationBlock * +tb_jmp_cache_get_tb(CPUJumpCache *jc, uint32_t hash) +{ +#if TARGET_TB_PCREL + /* Use acquire to ensure current load of pc from jc. */ + return qatomic_load_acquire(&jc->array[hash].tb); +#else + /* Use rcu_read to ensure current load of pc from *tb. */ + return qatomic_rcu_read(&jc->array[hash].tb); +#endif +} + +static inline target_ulong +tb_jmp_cache_get_pc(CPUJumpCache *jc, uint32_t hash, TranslationBlock *tb) +{ +#if TARGET_TB_PCREL + return jc->array[hash].pc; +#else + return tb_pc(tb); +#endif +} + +static inline void +tb_jmp_cache_set(CPUJumpCache *jc, uint32_t hash, + TranslationBlock *tb, target_ulong pc) +{ +#if TARGET_TB_PCREL + jc->array[hash].pc = pc; + /* Use store_release on tb to ensure pc is written first. */ + qatomic_store_release(&jc->array[hash].tb, tb); +#else + /* Use the pc value already stored in tb->pc. */ + qatomic_set(&jc->array[hash].tb, tb); +#endif +} + #endif /* ACCEL_TCG_TB_JMP_CACHE_H */ diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -XXX,XX +XXX,XX @@ # error TARGET_PAGE_BITS must be defined in cpu-param.h # endif #endif +#ifndef TARGET_TB_PCREL +# define TARGET_TB_PCREL 0 +#endif #define TARGET_LONG_SIZE (TARGET_LONG_BITS / 8) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ struct tb_tc { }; struct TranslationBlock { - target_ulong pc; /* simulated PC corresponding to this block (EIP + CS base) */ - target_ulong cs_base; /* CS base for this block */ +#if !TARGET_TB_PCREL + /* + * Guest PC corresponding to this block. This must be the true + * virtual address. Therefore e.g. x86 stores EIP + CS_BASE, and + * targets like Arm, MIPS, HP-PA, which reuse low bits for ISA or + * privilege, must store those bits elsewhere. + * + * If TARGET_TB_PCREL, the opcodes for the TranslationBlock are + * written such that the TB is associated only with the physical + * page and may be run in any virtual address context. In this case, + * PC must always be taken from ENV in a target-specific manner. + * Unwind information is taken as offsets from the page, to be + * deposited into the "current" PC. + */ + target_ulong pc; +#endif + + /* + * Target-specific data associated with the TranslationBlock, e.g.: + * x86: the original user, the Code Segment virtual base, + * arm: an extension of tb->flags, + * s390x: instruction data for EXECUTE, + * sparc: the next pc of the instruction queue (for delay slots). + */ + target_ulong cs_base; + uint32_t flags; /* flags defining in which context the code was generated */ uint32_t cflags; /* compile flags */ @@ -XXX,XX +XXX,XX @@ struct TranslationBlock { /* Hide the read to avoid ifdefs for TARGET_TB_PCREL. */ static inline target_ulong tb_pc(const TranslationBlock *tb) { +#if TARGET_TB_PCREL + qemu_build_not_reached(); +#else return tb->pc; +#endif } /* Hide the qatomic_read to make code a little easier on the eyes */ 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 @@ static bool tb_lookup_cmp(const void *p, const void *d) const TranslationBlock *tb = p; const struct tb_desc *desc = d; - if (tb_pc(tb) == desc->pc && + if ((TARGET_TB_PCREL || tb_pc(tb) == desc->pc) && tb->page_addr[0] == desc->page_addr0 && tb->cs_base == desc->cs_base && tb->flags == desc->flags && @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, return NULL; } desc.page_addr0 = phys_pc; - h = tb_hash_func(phys_pc, pc, flags, cflags, *cpu->trace_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : pc), + flags, cflags, *cpu->trace_dstate); return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, uint32_t flags, uint32_t cflags) { TranslationBlock *tb; + CPUJumpCache *jc; uint32_t hash; /* we should never be trying to look up an INVALID tb */ tcg_debug_assert(!(cflags & CF_INVALID)); hash = tb_jmp_cache_hash_func(pc); - tb = qatomic_rcu_read(&cpu->tb_jmp_cache->array[hash].tb); + jc = cpu->tb_jmp_cache; + tb = tb_jmp_cache_get_tb(jc, hash); if (likely(tb && - tb->pc == pc && + tb_jmp_cache_get_pc(jc, hash, tb) == pc && tb->cs_base == cs_base && tb->flags == flags && tb->trace_vcpu_dstate == *cpu->trace_dstate && @@ -XXX,XX +XXX,XX @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, if (tb == NULL) { return NULL; } - qatomic_set(&cpu->tb_jmp_cache->array[hash].tb, tb); + tb_jmp_cache_set(jc, hash, tb, pc); return tb; } @@ -XXX,XX +XXX,XX @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) if (cc->tcg_ops->synchronize_from_tb) { cc->tcg_ops->synchronize_from_tb(cpu, last_tb); } else { + assert(!TARGET_TB_PCREL); assert(cc->set_pc); cc->set_pc(cpu, tb_pc(last_tb)); } @@ -XXX,XX +XXX,XX @@ int cpu_exec(CPUState *cpu) * for the fast lookup */ h = tb_jmp_cache_hash_func(pc); - qatomic_set(&cpu->tb_jmp_cache->array[h].tb, tb); + tb_jmp_cache_set(cpu->tb_jmp_cache, h, tb, pc); } #ifndef CONFIG_USER_ONLY 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 encode_search(TranslationBlock *tb, uint8_t *block) for (j = 0; j < TARGET_INSN_START_WORDS; ++j) { if (i == 0) { - prev = (j == 0 ? tb_pc(tb) : 0); + prev = (!TARGET_TB_PCREL && j == 0 ? tb_pc(tb) : 0); } else { prev = tcg_ctx->gen_insn_data[i - 1][j]; } @@ -XXX,XX +XXX,XX @@ static int encode_search(TranslationBlock *tb, uint8_t *block) static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, uintptr_t searched_pc, bool reset_icount) { - target_ulong data[TARGET_INSN_START_WORDS] = { tb_pc(tb) }; + target_ulong data[TARGET_INSN_START_WORDS]; uintptr_t host_pc = (uintptr_t)tb->tc.ptr; CPUArchState *env = cpu->env_ptr; const uint8_t *p = tb->tc.ptr + tb->tc.size; @@ -XXX,XX +XXX,XX @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, return -1; } + memset(data, 0, sizeof(data)); + if (!TARGET_TB_PCREL) { + data[0] = tb_pc(tb); + } + /* Reconstruct the stored insn data while looking for the point at which the end of the insn exceeds the searched_pc. */ for (i = 0; i < num_insns; ++i) { @@ -XXX,XX +XXX,XX @@ static bool tb_cmp(const void *ap, const void *bp) const TranslationBlock *a = ap; const TranslationBlock *b = bp; - return tb_pc(a) == tb_pc(b) && - a->cs_base == b->cs_base && - a->flags == b->flags && - (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && - a->trace_vcpu_dstate == b->trace_vcpu_dstate && - a->page_addr[0] == b->page_addr[0] && - a->page_addr[1] == b->page_addr[1]; + return ((TARGET_TB_PCREL || tb_pc(a) == tb_pc(b)) && + a->cs_base == b->cs_base && + a->flags == b->flags && + (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) && + a->trace_vcpu_dstate == b->trace_vcpu_dstate && + a->page_addr[0] == b->page_addr[0] && + a->page_addr[1] == b->page_addr[1]); } void tb_htable_init(void) @@ -XXX,XX +XXX,XX @@ static inline void tb_jmp_unlink(TranslationBlock *dest) qemu_spin_unlock(&dest->jmp_lock); } +static void tb_jmp_cache_inval_tb(TranslationBlock *tb) +{ + CPUState *cpu; + + if (TARGET_TB_PCREL) { + /* A TB may be at any virtual address */ + CPU_FOREACH(cpu) { + tcg_flush_jmp_cache(cpu); + } + } else { + uint32_t h = tb_jmp_cache_hash_func(tb_pc(tb)); + + CPU_FOREACH(cpu) { + CPUJumpCache *jc = cpu->tb_jmp_cache; + + if (qatomic_read(&jc->array[h].tb) == tb) { + qatomic_set(&jc->array[h].tb, NULL); + } + } + } +} + /* * In user-mode, call with mmap_lock held. * In !user-mode, if @rm_from_page_list is set, call with the TB's pages' @@ -XXX,XX +XXX,XX @@ static inline void tb_jmp_unlink(TranslationBlock *dest) */ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) { - CPUState *cpu; PageDesc *p; uint32_t h; tb_page_addr_t phys_pc; @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* remove the TB from the hash list */ phys_pc = tb->page_addr[0]; - h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, orig_cflags, - tb->trace_vcpu_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + tb->flags, orig_cflags, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; } @@ -XXX,XX +XXX,XX @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) } /* remove the TB from the hash list */ - h = tb_jmp_cache_hash_func(tb->pc); - CPU_FOREACH(cpu) { - CPUJumpCache *jc = cpu->tb_jmp_cache; - if (qatomic_read(&jc->array[h].tb) == tb) { - qatomic_set(&jc->array[h].tb, NULL); - } - } + tb_jmp_cache_inval_tb(tb); /* suppress this TB from the two jump lists */ tb_remove_from_jmp_list(tb, 0); @@ -XXX,XX +XXX,XX @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, } /* add in the hash table */ - h = tb_hash_func(phys_pc, tb_pc(tb), tb->flags, tb->cflags, - tb->trace_vcpu_dstate); + h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)), + tb->flags, tb->cflags, tb->trace_vcpu_dstate); qht_insert(&tb_ctx.htable, tb, h, &existing_tb); /* remove TB from the page(s) if we couldn't insert it */ @@ -XXX,XX +XXX,XX @@ TranslationBlock *tb_gen_code(CPUState *cpu, gen_code_buf = tcg_ctx->code_gen_ptr; tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf); +#if !TARGET_TB_PCREL tb->pc = pc; +#endif tb->cs_base = cs_base; tb->flags = flags; tb->cflags = cflags; -- 2.34.1 From: Leandro Lupori <leandro.lupori@eldorado.org.br> PowerPC64 processors handle direct branches better than indirect ones, resulting in less stalled cycles and branch misses. However, PPC's tb_target_set_jmp_target() was only using direct branches for 16-bit jumps, while PowerPC64's unconditional branch instructions are able to handle displacements of up to 26 bits. To take advantage of this, now jumps whose displacements fit in between 17 and 26 bits are also converted to direct branches. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Leandro Lupori <leandro.lupori@eldorado.org.br> [rth: Expanded some commentary.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 119 +++++++++++++++++++++++++++++---------- 1 file changed, 88 insertions(+), 31 deletions(-) diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index XXXXXXX..XXXXXXX 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -XXX,XX +XXX,XX @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) tcg_out32(s, insn); } +static inline uint64_t make_pair(tcg_insn_unit i1, tcg_insn_unit i2) +{ + if (HOST_BIG_ENDIAN) { + return (uint64_t)i1 << 32 | i2; + } + return (uint64_t)i2 << 32 | i1; +} + +static inline void ppc64_replace2(uintptr_t rx, uintptr_t rw, + tcg_insn_unit i0, tcg_insn_unit i1) +{ +#if TCG_TARGET_REG_BITS == 64 + qatomic_set((uint64_t *)rw, make_pair(i0, i1)); + flush_idcache_range(rx, rw, 8); +#else + qemu_build_not_reached(); +#endif +} + +static inline void ppc64_replace4(uintptr_t rx, uintptr_t rw, + tcg_insn_unit i0, tcg_insn_unit i1, + tcg_insn_unit i2, tcg_insn_unit i3) +{ + uint64_t p[2]; + + p[!HOST_BIG_ENDIAN] = make_pair(i0, i1); + p[HOST_BIG_ENDIAN] = make_pair(i2, i3); + + /* + * There's no convenient way to get the compiler to allocate a pair + * of registers at an even index, so copy into r6/r7 and clobber. + */ + asm("mr %%r6, %1\n\t" + "mr %%r7, %2\n\t" + "stq %%r6, %0" + : "=Q"(*(__int128 *)rw) : "r"(p[0]), "r"(p[1]) : "r6", "r7"); + flush_idcache_range(rx, rw, 16); +} + void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_rx, uintptr_t jmp_rw, uintptr_t addr) { - if (TCG_TARGET_REG_BITS == 64) { - tcg_insn_unit i1, i2; - intptr_t tb_diff = addr - tc_ptr; - intptr_t br_diff = addr - (jmp_rx + 4); - uint64_t pair; + tcg_insn_unit i0, i1, i2, i3; + intptr_t tb_diff = addr - tc_ptr; + intptr_t br_diff = addr - (jmp_rx + 4); + intptr_t lo, hi; - /* This does not exercise the range of the branch, but we do - still need to be able to load the new value of TCG_REG_TB. - But this does still happen quite often. */ - if (tb_diff == (int16_t)tb_diff) { - i1 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, tb_diff); - i2 = B | (br_diff & 0x3fffffc); - } else { - intptr_t lo = (int16_t)tb_diff; - intptr_t hi = (int32_t)(tb_diff - lo); - assert(tb_diff == hi + lo); - i1 = ADDIS | TAI(TCG_REG_TB, TCG_REG_TB, hi >> 16); - i2 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, lo); - } -#if HOST_BIG_ENDIAN - pair = (uint64_t)i1 << 32 | i2; -#else - pair = (uint64_t)i2 << 32 | i1; -#endif - - /* As per the enclosing if, this is ppc64. Avoid the _Static_assert - within qatomic_set that would fail to build a ppc32 host. */ - qatomic_set__nocheck((uint64_t *)jmp_rw, pair); - flush_idcache_range(jmp_rx, jmp_rw, 8); - } else { + if (TCG_TARGET_REG_BITS == 32) { intptr_t diff = addr - jmp_rx; tcg_debug_assert(in_range_b(diff)); qatomic_set((uint32_t *)jmp_rw, B | (diff & 0x3fffffc)); flush_idcache_range(jmp_rx, jmp_rw, 4); + return; } + + /* + * For 16-bit displacements, we can use a single add + branch. + * This happens quite often. + */ + if (tb_diff == (int16_t)tb_diff) { + i0 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, tb_diff); + i1 = B | (br_diff & 0x3fffffc); + ppc64_replace2(jmp_rx, jmp_rw, i0, i1); + return; + } + + lo = (int16_t)tb_diff; + hi = (int32_t)(tb_diff - lo); + assert(tb_diff == hi + lo); + i0 = ADDIS | TAI(TCG_REG_TB, TCG_REG_TB, hi >> 16); + i1 = ADDI | TAI(TCG_REG_TB, TCG_REG_TB, lo); + + /* + * Without stq from 2.07, we can only update two insns, + * and those must be the ones that load the target address. + */ + if (!have_isa_2_07) { + ppc64_replace2(jmp_rx, jmp_rw, i0, i1); + return; + } + + /* + * For 26-bit displacements, we can use a direct branch. + * Otherwise we still need the indirect branch, which we + * must restore after a potential direct branch write. + */ + br_diff -= 4; + if (in_range_b(br_diff)) { + i2 = B | (br_diff & 0x3fffffc); + i3 = NOP; + } else { + i2 = MTSPR | RS(TCG_REG_TB) | CTR; + i3 = BCCTR | BO_ALWAYS; + } + ppc64_replace4(jmp_rx, jmp_rw, i0, i1, i2, i3); } static void tcg_out_call_int(TCGContext *s, int lk, @@ -XXX,XX +XXX,XX @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, if (s->tb_jmp_insn_offset) { /* Direct jump. */ if (TCG_TARGET_REG_BITS == 64) { - /* Ensure the next insns are 8-byte aligned. */ - if ((uintptr_t)s->code_ptr & 7) { + /* Ensure the next insns are 8 or 16-byte aligned. */ + while ((uintptr_t)s->code_ptr & (have_isa_2_07 ? 15 : 7)) { tcg_out32(s, NOP); } s->tb_jmp_insn_offset[args[0]] = tcg_current_code_size(s); -- 2.34.1 The value previously chosen overlaps GUSA_MASK. Rename all DELAY_SLOT_* and GUSA_* defines to emphasize that they are included in TB_FLAGs. Add aliases for the FPSCR and SR bits that are included in TB_FLAGS, so that we don't accidentally reassign those bits. Fixes: 4da06fb3062 ("target/sh4: Implement prctl_unalign_sigbus") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/856 Reviewed-by: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sh4/cpu.h | 56 +++++++++++++------------ linux-user/sh4/signal.c | 6 +-- target/sh4/cpu.c | 6 +-- target/sh4/helper.c | 6 +-- target/sh4/translate.c | 90 ++++++++++++++++++++++------------------- 5 files changed, 88 insertions(+), 76 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 @@ #define FPSCR_RM_NEAREST (0 << 0) #define FPSCR_RM_ZERO (1 << 0) -#define DELAY_SLOT_MASK 0x7 -#define DELAY_SLOT (1 << 0) -#define DELAY_SLOT_CONDITIONAL (1 << 1) -#define DELAY_SLOT_RTE (1 << 2) +#define TB_FLAG_DELAY_SLOT (1 << 0) +#define TB_FLAG_DELAY_SLOT_COND (1 << 1) +#define TB_FLAG_DELAY_SLOT_RTE (1 << 2) +#define TB_FLAG_PENDING_MOVCA (1 << 3) +#define TB_FLAG_GUSA_SHIFT 4 /* [11:4] */ +#define TB_FLAG_GUSA_EXCLUSIVE (1 << 12) +#define TB_FLAG_UNALIGN (1 << 13) +#define TB_FLAG_SR_FD (1 << SR_FD) /* 15 */ +#define TB_FLAG_FPSCR_PR FPSCR_PR /* 19 */ +#define TB_FLAG_FPSCR_SZ FPSCR_SZ /* 20 */ +#define TB_FLAG_FPSCR_FR FPSCR_FR /* 21 */ +#define TB_FLAG_SR_RB (1 << SR_RB) /* 29 */ +#define TB_FLAG_SR_MD (1 << SR_MD) /* 30 */ -#define TB_FLAG_PENDING_MOVCA (1 << 3) -#define TB_FLAG_UNALIGN (1 << 4) - -#define GUSA_SHIFT 4 -#ifdef CONFIG_USER_ONLY -#define GUSA_EXCLUSIVE (1 << 12) -#define GUSA_MASK ((0xff << GUSA_SHIFT) | GUSA_EXCLUSIVE) -#else -/* Provide dummy versions of the above to allow tests against tbflags - to be elided while avoiding ifdefs. */ -#define GUSA_EXCLUSIVE 0 -#define GUSA_MASK 0 -#endif - -#define TB_FLAG_ENVFLAGS_MASK (DELAY_SLOT_MASK | GUSA_MASK) +#define TB_FLAG_DELAY_SLOT_MASK (TB_FLAG_DELAY_SLOT | \ + TB_FLAG_DELAY_SLOT_COND | \ + TB_FLAG_DELAY_SLOT_RTE) +#define TB_FLAG_GUSA_MASK ((0xff << TB_FLAG_GUSA_SHIFT) | \ + TB_FLAG_GUSA_EXCLUSIVE) +#define TB_FLAG_FPSCR_MASK (TB_FLAG_FPSCR_PR | \ + TB_FLAG_FPSCR_SZ | \ + TB_FLAG_FPSCR_FR) +#define TB_FLAG_SR_MASK (TB_FLAG_SR_FD | \ + TB_FLAG_SR_RB | \ + TB_FLAG_SR_MD) +#define TB_FLAG_ENVFLAGS_MASK (TB_FLAG_DELAY_SLOT_MASK | \ + TB_FLAG_GUSA_MASK) typedef struct tlb_t { uint32_t vpn; /* virtual page number */ @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index (CPUSH4State *env, bool ifetch) { /* The instruction in a RTE delay slot is fetched in privileged mode, but executed in user mode. */ - if (ifetch && (env->flags & DELAY_SLOT_RTE)) { + if (ifetch && (env->flags & TB_FLAG_DELAY_SLOT_RTE)) { return 0; } else { return (env->sr & (1u << SR_MD)) == 0 ? 1 : 0; @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUSH4State *env, target_ulong *pc, { *pc = env->pc; /* For a gUSA region, notice the end of the region. */ - *cs_base = env->flags & GUSA_MASK ? env->gregs[0] : 0; - *flags = env->flags /* TB_FLAG_ENVFLAGS_MASK: bits 0-2, 4-12 */ - | (env->fpscr & (FPSCR_FR | FPSCR_SZ | FPSCR_PR)) /* Bits 19-21 */ - | (env->sr & ((1u << SR_MD) | (1u << SR_RB))) /* Bits 29-30 */ - | (env->sr & (1u << SR_FD)) /* Bit 15 */ + *cs_base = env->flags & TB_FLAG_GUSA_MASK ? env->gregs[0] : 0; + *flags = env->flags + | (env->fpscr & TB_FLAG_FPSCR_MASK) + | (env->sr & TB_FLAG_SR_MASK) | (env->movcal_backup ? TB_FLAG_PENDING_MOVCA : 0); /* Bit 3 */ #ifdef CONFIG_USER_ONLY *flags |= TB_FLAG_UNALIGN * !env_cpu(env)->prctl_unalign_sigbus; diff --git a/linux-user/sh4/signal.c b/linux-user/sh4/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/sh4/signal.c +++ b/linux-user/sh4/signal.c @@ -XXX,XX +XXX,XX @@ static void restore_sigcontext(CPUSH4State *regs, struct target_sigcontext *sc) __get_user(regs->fpul, &sc->sc_fpul); regs->tra = -1; /* disable syscall checks */ - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags = 0; } void setup_frame(int sig, struct target_sigaction *ka, @@ -XXX,XX +XXX,XX @@ void setup_frame(int sig, struct target_sigaction *ka, regs->gregs[5] = 0; regs->gregs[6] = frame_addr += offsetof(typeof(*frame), sc); regs->pc = (unsigned long) ka->_sa_handler; - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags &= ~(TB_FLAG_DELAY_SLOT_MASK | TB_FLAG_GUSA_MASK); unlock_user_struct(frame, frame_addr, 1); return; @@ -XXX,XX +XXX,XX @@ void setup_rt_frame(int sig, struct target_sigaction *ka, regs->gregs[5] = frame_addr + offsetof(typeof(*frame), info); regs->gregs[6] = frame_addr + offsetof(typeof(*frame), uc); regs->pc = (unsigned long) ka->_sa_handler; - regs->flags &= ~(DELAY_SLOT_MASK | GUSA_MASK); + regs->flags &= ~(TB_FLAG_DELAY_SLOT_MASK | TB_FLAG_GUSA_MASK); unlock_user_struct(frame, frame_addr, 1); return; 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 void superh_cpu_synchronize_from_tb(CPUState *cs, SuperHCPU *cpu = SUPERH_CPU(cs); cpu->env.pc = tb_pc(tb); - cpu->env.flags = tb->flags & TB_FLAG_ENVFLAGS_MASK; + cpu->env.flags = tb->flags; } #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static bool superh_io_recompile_replay_branch(CPUState *cs, SuperHCPU *cpu = SUPERH_CPU(cs); CPUSH4State *env = &cpu->env; - if ((env->flags & ((DELAY_SLOT | DELAY_SLOT_CONDITIONAL))) != 0 + if ((env->flags & (TB_FLAG_DELAY_SLOT | TB_FLAG_DELAY_SLOT_COND)) && env->pc != tb_pc(tb)) { env->pc -= 2; - env->flags &= ~(DELAY_SLOT | DELAY_SLOT_CONDITIONAL); + env->flags &= ~(TB_FLAG_DELAY_SLOT | TB_FLAG_DELAY_SLOT_COND); return true; } return false; diff --git a/target/sh4/helper.c b/target/sh4/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/helper.c +++ b/target/sh4/helper.c @@ -XXX,XX +XXX,XX @@ void superh_cpu_do_interrupt(CPUState *cs) env->sr |= (1u << SR_BL) | (1u << SR_MD) | (1u << SR_RB); env->lock_addr = -1; - if (env->flags & DELAY_SLOT_MASK) { + if (env->flags & TB_FLAG_DELAY_SLOT_MASK) { /* Branch instruction should be executed again before delay slot. */ env->spc -= 2; /* Clear flags for exception/interrupt routine. */ - env->flags &= ~DELAY_SLOT_MASK; + env->flags &= ~TB_FLAG_DELAY_SLOT_MASK; } if (do_exp) { @@ -XXX,XX +XXX,XX @@ bool superh_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUSH4State *env = &cpu->env; /* Delay slots are indivisible, ignore interrupts */ - if (env->flags & DELAY_SLOT_MASK) { + if (env->flags & TB_FLAG_DELAY_SLOT_MASK) { return false; } else { superh_cpu_do_interrupt(cs); 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 @@ void superh_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, env->gregs[i], i + 1, env->gregs[i + 1], i + 2, env->gregs[i + 2], i + 3, env->gregs[i + 3]); } - if (env->flags & DELAY_SLOT) { + if (env->flags & TB_FLAG_DELAY_SLOT) { qemu_printf("in delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); - } else if (env->flags & DELAY_SLOT_CONDITIONAL) { + } else if (env->flags & TB_FLAG_DELAY_SLOT_COND) { qemu_printf("in conditional delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); - } else if (env->flags & DELAY_SLOT_RTE) { + } else if (env->flags & TB_FLAG_DELAY_SLOT_RTE) { qemu_fprintf(f, "in rte delay slot (delayed_pc=0x%08x)\n", env->delayed_pc); } @@ -XXX,XX +XXX,XX @@ static inline void gen_save_cpu_state(DisasContext *ctx, bool save_pc) static inline bool use_exit_tb(DisasContext *ctx) { - return (ctx->tbflags & GUSA_EXCLUSIVE) != 0; + return (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) != 0; } static bool use_goto_tb(DisasContext *ctx, target_ulong dest) @@ -XXX,XX +XXX,XX @@ static void gen_conditional_jump(DisasContext *ctx, target_ulong dest, TCGLabel *l1 = gen_new_label(); TCGCond cond_not_taken = jump_if_true ? TCG_COND_EQ : TCG_COND_NE; - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* When in an exclusive region, we must continue to the end. Therefore, exit the region on a taken branch, but otherwise fall through to the next instruction. */ tcg_gen_brcondi_i32(cond_not_taken, cpu_sr_t, 0, l1); - tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~GUSA_MASK); + tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~TB_FLAG_GUSA_MASK); /* Note that this won't actually use a goto_tb opcode because we disallow it in use_goto_tb, but it handles exit + singlestep. */ gen_goto_tb(ctx, 0, dest); @@ -XXX,XX +XXX,XX @@ static void gen_delayed_conditional_jump(DisasContext * ctx) tcg_gen_mov_i32(ds, cpu_delayed_cond); tcg_gen_discard_i32(cpu_delayed_cond); - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* When in an exclusive region, we must continue to the end. Therefore, exit the region on a taken branch, but otherwise fall through to the next instruction. */ tcg_gen_brcondi_i32(TCG_COND_EQ, ds, 0, l1); /* Leave the gUSA region. */ - tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~GUSA_MASK); + tcg_gen_movi_i32(cpu_flags, ctx->envflags & ~TB_FLAG_GUSA_MASK); gen_jump(ctx); gen_set_label(l1); @@ -XXX,XX +XXX,XX @@ static inline void gen_store_fpr64(DisasContext *ctx, TCGv_i64 t, int reg) #define XHACK(x) ((((x) & 1 ) << 4) | ((x) & 0xe)) #define CHECK_NOT_DELAY_SLOT \ - if (ctx->envflags & DELAY_SLOT_MASK) { \ - goto do_illegal_slot; \ + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { \ + goto do_illegal_slot; \ } #define CHECK_PRIVILEGED \ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x000b: /* rts */ CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_pc, cpu_pr); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x0028: /* clrmac */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT gen_write_sr(cpu_ssr); tcg_gen_mov_i32(cpu_delayed_pc, cpu_spc); - ctx->envflags |= DELAY_SLOT_RTE; + ctx->envflags |= TB_FLAG_DELAY_SLOT_RTE; ctx->delayed_pc = (uint32_t) - 1; ctx->base.is_jmp = DISAS_STOP; return; @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) return; case 0xe000: /* mov #imm,Rn */ #ifdef CONFIG_USER_ONLY - /* Detect the start of a gUSA region. If so, update envflags - and end the TB. This will allow us to see the end of the - region (stored in R0) in the next TB. */ + /* + * Detect the start of a gUSA region (mov #-n, r15). + * If so, update envflags and end the TB. This will allow us + * to see the end of the region (stored in R0) in the next TB. + */ if (B11_8 == 15 && B7_0s < 0 && (tb_cflags(ctx->base.tb) & CF_PARALLEL)) { - ctx->envflags = deposit32(ctx->envflags, GUSA_SHIFT, 8, B7_0s); + ctx->envflags = + deposit32(ctx->envflags, TB_FLAG_GUSA_SHIFT, 8, B7_0s); ctx->base.is_jmp = DISAS_STOP; } #endif @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0xa000: /* bra disp */ CHECK_NOT_DELAY_SLOT ctx->delayed_pc = ctx->base.pc_next + 4 + B11_0s * 2; - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; return; case 0xb000: /* bsr disp */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); ctx->delayed_pc = ctx->base.pc_next + 4 + B11_0s * 2; - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; return; } @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT tcg_gen_xori_i32(cpu_delayed_cond, cpu_sr_t, 1); ctx->delayed_pc = ctx->base.pc_next + 4 + B7_0s * 2; - ctx->envflags |= DELAY_SLOT_CONDITIONAL; + ctx->envflags |= TB_FLAG_DELAY_SLOT_COND; return; case 0x8900: /* bt label */ CHECK_NOT_DELAY_SLOT @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_cond, cpu_sr_t); ctx->delayed_pc = ctx->base.pc_next + 4 + B7_0s * 2; - ctx->envflags |= DELAY_SLOT_CONDITIONAL; + ctx->envflags |= TB_FLAG_DELAY_SLOT_COND; return; case 0x8800: /* cmp/eq #imm,R0 */ tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_sr_t, REG(0), B7_0s); @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x0023: /* braf Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_addi_i32(cpu_delayed_pc, REG(B11_8), ctx->base.pc_next + 4); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x0003: /* bsrf Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); tcg_gen_add_i32(cpu_delayed_pc, REG(B11_8), cpu_pr); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x4015: /* cmp/pl Rn */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) case 0x402b: /* jmp @Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_mov_i32(cpu_delayed_pc, REG(B11_8)); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x400b: /* jsr @Rn */ CHECK_NOT_DELAY_SLOT tcg_gen_movi_i32(cpu_pr, ctx->base.pc_next + 4); tcg_gen_mov_i32(cpu_delayed_pc, REG(B11_8)); - ctx->envflags |= DELAY_SLOT; + ctx->envflags |= TB_FLAG_DELAY_SLOT; ctx->delayed_pc = (uint32_t) - 1; return; case 0x400e: /* ldc Rm,SR */ @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) fflush(stderr); #endif do_illegal: - if (ctx->envflags & DELAY_SLOT_MASK) { + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { do_illegal_slot: gen_save_cpu_state(ctx, true); gen_helper_raise_slot_illegal_instruction(cpu_env); @@ -XXX,XX +XXX,XX @@ static void _decode_opc(DisasContext * ctx) do_fpu_disabled: gen_save_cpu_state(ctx, true); - if (ctx->envflags & DELAY_SLOT_MASK) { + if (ctx->envflags & TB_FLAG_DELAY_SLOT_MASK) { gen_helper_raise_slot_fpu_disable(cpu_env); } else { gen_helper_raise_fpu_disable(cpu_env); @@ -XXX,XX +XXX,XX @@ static void decode_opc(DisasContext * ctx) _decode_opc(ctx); - if (old_flags & DELAY_SLOT_MASK) { + if (old_flags & TB_FLAG_DELAY_SLOT_MASK) { /* go out of the delay slot */ - ctx->envflags &= ~DELAY_SLOT_MASK; + ctx->envflags &= ~TB_FLAG_DELAY_SLOT_MASK; /* When in an exclusive region, we must continue to the end for conditional branches. */ - if (ctx->tbflags & GUSA_EXCLUSIVE - && old_flags & DELAY_SLOT_CONDITIONAL) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE + && old_flags & TB_FLAG_DELAY_SLOT_COND) { gen_delayed_conditional_jump(ctx); return; } /* Otherwise this is probably an invalid gUSA region. Drop the GUSA bits so the next TB doesn't see them. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; tcg_gen_movi_i32(cpu_flags, ctx->envflags); - if (old_flags & DELAY_SLOT_CONDITIONAL) { + if (old_flags & TB_FLAG_DELAY_SLOT_COND) { gen_delayed_conditional_jump(ctx); } else { gen_jump(ctx); @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) } /* The entire region has been translated. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; ctx->base.pc_next = pc_end; ctx->base.num_insns += max_insns - 1; return; @@ -XXX,XX +XXX,XX @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) /* Restart with the EXCLUSIVE bit set, within a TB run via cpu_exec_step_atomic holding the exclusive lock. */ - ctx->envflags |= GUSA_EXCLUSIVE; + ctx->envflags |= TB_FLAG_GUSA_EXCLUSIVE; gen_save_cpu_state(ctx, false); gen_helper_exclusive(cpu_env); ctx->base.is_jmp = DISAS_NORETURN; @@ -XXX,XX +XXX,XX @@ static void sh4_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) (tbflags & (1 << SR_RB))) * 0x10; ctx->fbank = tbflags & FPSCR_FR ? 0x10 : 0; - if (tbflags & GUSA_MASK) { +#ifdef CONFIG_USER_ONLY + if (tbflags & TB_FLAG_GUSA_MASK) { + /* In gUSA exclusive region. */ uint32_t pc = ctx->base.pc_next; uint32_t pc_end = ctx->base.tb->cs_base; - int backup = sextract32(ctx->tbflags, GUSA_SHIFT, 8); + int backup = sextract32(ctx->tbflags, TB_FLAG_GUSA_SHIFT, 8); int max_insns = (pc_end - pc) / 2; if (pc != pc_end + backup || max_insns < 2) { /* This is a malformed gUSA region. Don't do anything special, since the interpreter is likely to get confused. */ - ctx->envflags &= ~GUSA_MASK; - } else if (tbflags & GUSA_EXCLUSIVE) { + ctx->envflags &= ~TB_FLAG_GUSA_MASK; + } else if (tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* Regardless of single-stepping or the end of the page, we must complete execution of the gUSA region while holding the exclusive lock. */ @@ -XXX,XX +XXX,XX @@ static void sh4_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) return; } } +#endif /* Since the ISA is fixed-width, we can bound by the number of instructions remaining on the page. */ @@ -XXX,XX +XXX,XX @@ static void sh4_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) DisasContext *ctx = container_of(dcbase, DisasContext, base); #ifdef CONFIG_USER_ONLY - if (unlikely(ctx->envflags & GUSA_MASK) - && !(ctx->envflags & GUSA_EXCLUSIVE)) { + if (unlikely(ctx->envflags & TB_FLAG_GUSA_MASK) + && !(ctx->envflags & TB_FLAG_GUSA_EXCLUSIVE)) { /* We're in an gUSA region, and we have not already fallen back on using an exclusive region. Attempt to parse the region into a single supported atomic operation. Failure @@ -XXX,XX +XXX,XX @@ static void sh4_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) { DisasContext *ctx = container_of(dcbase, DisasContext, base); - if (ctx->tbflags & GUSA_EXCLUSIVE) { + if (ctx->tbflags & TB_FLAG_GUSA_EXCLUSIVE) { /* Ending the region of exclusivity. Clear the bits. */ - ctx->envflags &= ~GUSA_MASK; + ctx->envflags &= ~TB_FLAG_GUSA_MASK; } switch (ctx->base.is_jmp) { -- 2.34.1