diff options
173 files changed, 3963 insertions, 1101 deletions
diff --git a/.gitlab-ci.d/custom-runners.yml b/.gitlab-ci.d/custom-runners.yml index 0d3e4a7b4b..a89a20da48 100644 --- a/.gitlab-ci.d/custom-runners.yml +++ b/.gitlab-ci.d/custom-runners.yml @@ -17,7 +17,6 @@ variables: # setup by the scripts/ci/setup/build-environment.yml task # "Install basic packages to build QEMU on Ubuntu 18.04/20.04" ubuntu-18.04-s390x-all-linux-static: - allow_failure: true needs: [] stage: build tags: @@ -37,7 +36,6 @@ ubuntu-18.04-s390x-all-linux-static: - make --output-sync -j`nproc` check-tcg V=1 ubuntu-18.04-s390x-all: - allow_failure: true needs: [] stage: build tags: @@ -54,7 +52,6 @@ ubuntu-18.04-s390x-all: - make --output-sync -j`nproc` check V=1 ubuntu-18.04-s390x-alldbg: - allow_failure: true needs: [] stage: build tags: @@ -62,7 +59,11 @@ ubuntu-18.04-s390x-alldbg: - s390x rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + allow_failure: true - if: "$S390X_RUNNER_AVAILABLE" + when: manual + allow_failure: true script: - mkdir build - cd build @@ -72,7 +73,6 @@ ubuntu-18.04-s390x-alldbg: - make --output-sync -j`nproc` check V=1 ubuntu-18.04-s390x-clang: - allow_failure: true needs: [] stage: build tags: @@ -81,8 +81,10 @@ ubuntu-18.04-s390x-clang: rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' when: manual + allow_failure: true - if: "$S390X_RUNNER_AVAILABLE" when: manual + allow_failure: true script: - mkdir build - cd build @@ -91,7 +93,6 @@ ubuntu-18.04-s390x-clang: - make --output-sync -j`nproc` check V=1 ubuntu-18.04-s390x-tci: - allow_failure: true needs: [] stage: build tags: @@ -99,7 +100,11 @@ ubuntu-18.04-s390x-tci: - s390x rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + allow_failure: true - if: "$S390X_RUNNER_AVAILABLE" + when: manual + allow_failure: true script: - mkdir build - cd build @@ -107,7 +112,6 @@ ubuntu-18.04-s390x-tci: - make --output-sync -j`nproc` ubuntu-18.04-s390x-notcg: - allow_failure: true needs: [] stage: build tags: @@ -116,8 +120,10 @@ ubuntu-18.04-s390x-notcg: rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' when: manual + allow_failure: true - if: "$S390X_RUNNER_AVAILABLE" when: manual + allow_failure: true script: - mkdir build - cd build @@ -129,7 +135,6 @@ ubuntu-18.04-s390x-notcg: # setup by the scripts/ci/setup/qemu/build-environment.yml task # "Install basic packages to build QEMU on Ubuntu 18.04/20.04" ubuntu-20.04-aarch64-all-linux-static: - allow_failure: true needs: [] stage: build tags: @@ -149,7 +154,6 @@ ubuntu-20.04-aarch64-all-linux-static: - make --output-sync -j`nproc` check-tcg V=1 ubuntu-20.04-aarch64-all: - allow_failure: true needs: [] stage: build tags: @@ -157,7 +161,11 @@ ubuntu-20.04-aarch64-all: - aarch64 rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + allow_failure: true - if: "$AARCH64_RUNNER_AVAILABLE" + when: manual + allow_failure: true script: - mkdir build - cd build @@ -166,7 +174,6 @@ ubuntu-20.04-aarch64-all: - make --output-sync -j`nproc` check V=1 ubuntu-20.04-aarch64-alldbg: - allow_failure: true needs: [] stage: build tags: @@ -184,7 +191,6 @@ ubuntu-20.04-aarch64-alldbg: - make --output-sync -j`nproc` check V=1 ubuntu-20.04-aarch64-clang: - allow_failure: true needs: [] stage: build tags: @@ -193,8 +199,10 @@ ubuntu-20.04-aarch64-clang: rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' when: manual + allow_failure: true - if: "$AARCH64_RUNNER_AVAILABLE" when: manual + allow_failure: true script: - mkdir build - cd build @@ -203,7 +211,6 @@ ubuntu-20.04-aarch64-clang: - make --output-sync -j`nproc` check V=1 ubuntu-20.04-aarch64-tci: - allow_failure: true needs: [] stage: build tags: @@ -211,7 +218,11 @@ ubuntu-20.04-aarch64-tci: - aarch64 rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + allow_failure: true - if: "$AARCH64_RUNNER_AVAILABLE" + when: manual + allow_failure: true script: - mkdir build - cd build @@ -219,7 +230,6 @@ ubuntu-20.04-aarch64-tci: - make --output-sync -j`nproc` ubuntu-20.04-aarch64-notcg: - allow_failure: true needs: [] stage: build tags: @@ -228,8 +238,10 @@ ubuntu-20.04-aarch64-notcg: rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' when: manual + allow_failure: true - if: "$AARCH64_RUNNER_AVAILABLE" when: manual + allow_failure: true script: - mkdir build - cd build diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 0125c17edb..cace5ffe64 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -2469,7 +2469,7 @@ static int kvm_init(MachineState *ms) ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING, 0, ring_bytes); if (ret) { error_report("Enabling of KVM dirty ring failed: %s. " - "Suggested mininum value is 1024.", strerror(-ret)); + "Suggested minimum value is 1024.", strerror(-ret)); goto err; } diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index e5c0ccd1a2..75dbc1e4e3 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -651,8 +651,8 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret) loop */ #if defined(TARGET_I386) CPUClass *cc = CPU_GET_CLASS(cpu); - cc->tcg_ops->do_interrupt(cpu); -#endif + cc->tcg_ops->fake_user_interrupt(cpu); +#endif /* TARGET_I386 */ *ret = cpu->exception_index; cpu->exception_index = -1; return true; @@ -685,6 +685,7 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret) return false; } +#ifndef CONFIG_USER_ONLY /* * CPU_INTERRUPT_POLL is a virtual event which gets converted into a * "real" interrupt event later. It does not need to be recorded for @@ -698,12 +699,11 @@ static inline bool need_replay_interrupt(int interrupt_request) return true; #endif } +#endif /* !CONFIG_USER_ONLY */ static inline bool cpu_handle_interrupt(CPUState *cpu, TranslationBlock **last_tb) { - CPUClass *cc = CPU_GET_CLASS(cpu); - /* Clear the interrupt flag now since we're processing * cpu->interrupt_request and cpu->exit_request. * Ensure zeroing happens before reading cpu->exit_request or @@ -725,6 +725,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu, qemu_mutex_unlock_iothread(); return true; } +#if !defined(CONFIG_USER_ONLY) if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) { /* Do nothing */ } else if (interrupt_request & CPU_INTERRUPT_HALT) { @@ -753,12 +754,14 @@ static inline bool cpu_handle_interrupt(CPUState *cpu, qemu_mutex_unlock_iothread(); return true; } -#endif +#endif /* !TARGET_I386 */ /* The target hook has 3 exit conditions: False when the interrupt isn't processed, True when it is, and we should restart on a new TB, and via longjmp via cpu_loop_exit. */ else { + CPUClass *cc = CPU_GET_CLASS(cpu); + if (cc->tcg_ops->cpu_exec_interrupt && cc->tcg_ops->cpu_exec_interrupt(cpu, interrupt_request)) { if (need_replay_interrupt(interrupt_request)) { @@ -777,6 +780,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu, * reload the 'interrupt_request' value */ interrupt_request = cpu->interrupt_request; } +#endif /* !CONFIG_USER_ONLY */ if (interrupt_request & CPU_INTERRUPT_EXITTB) { cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB; /* ensure that no TB jump will be modified as diff --git a/accel/tcg/tcg-accel-ops-rr.c b/accel/tcg/tcg-accel-ops-rr.c index c02c061ecb..a5fd26190e 100644 --- a/accel/tcg/tcg-accel-ops-rr.c +++ b/accel/tcg/tcg-accel-ops-rr.c @@ -60,8 +60,6 @@ void rr_kick_vcpu_thread(CPUState *unused) static QEMUTimer *rr_kick_vcpu_timer; static CPUState *rr_current_cpu; -#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10) - static inline int64_t rr_next_kick_time(void) { return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD; diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index bbfcfb698c..fb9ebfad9e 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1297,31 +1297,8 @@ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb, invalidate_page_bitmap(p); #if defined(CONFIG_USER_ONLY) - if (p->flags & PAGE_WRITE) { - target_ulong addr; - PageDesc *p2; - int prot; - - /* force the host page as non writable (writes will have a - page fault + mprotect overhead) */ - page_addr &= qemu_host_page_mask; - prot = 0; - for (addr = page_addr; addr < page_addr + qemu_host_page_size; - addr += TARGET_PAGE_SIZE) { - - p2 = page_find(addr >> TARGET_PAGE_BITS); - if (!p2) { - continue; - } - prot |= p2->flags; - p2->flags &= ~PAGE_WRITE; - } - mprotect(g2h_untagged(page_addr), qemu_host_page_size, - (prot & PAGE_BITS) & ~PAGE_WRITE); - if (DEBUG_TB_INVALIDATE_GATE) { - printf("protecting code page: 0x" TB_PAGE_ADDR_FMT "\n", page_addr); - } - } + /* translator_loop() must have made all TB pages non-writable */ + assert(!(p->flags & PAGE_WRITE)); #else /* if some code is already present, then the pages are already protected. So we handle the case where only the first TB is @@ -2394,6 +2371,38 @@ int page_check_range(target_ulong start, target_ulong len, int flags) return 0; } +void page_protect(tb_page_addr_t page_addr) +{ + target_ulong addr; + PageDesc *p; + int prot; + + p = page_find(page_addr >> TARGET_PAGE_BITS); + if (p && (p->flags & PAGE_WRITE)) { + /* + * Force the host page as non writable (writes will have a page fault + + * mprotect overhead). + */ + page_addr &= qemu_host_page_mask; + prot = 0; + for (addr = page_addr; addr < page_addr + qemu_host_page_size; + addr += TARGET_PAGE_SIZE) { + + p = page_find(addr >> TARGET_PAGE_BITS); + if (!p) { + continue; + } + prot |= p->flags; + p->flags &= ~PAGE_WRITE; + } + mprotect(g2h_untagged(page_addr), qemu_host_page_size, + (prot & PAGE_BITS) & ~PAGE_WRITE); + if (DEBUG_TB_INVALIDATE_GATE) { + printf("protecting code page: 0x" TB_PAGE_ADDR_FMT "\n", page_addr); + } + } +} + /* called from signal handler: invalidate the code and unprotect the * page. Return 0 if the fault was not handled, 1 if it was handled, * and 2 if it was handled but the caller must cause the TB to be diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index c53a7f8e44..390bd9db0a 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -42,6 +42,15 @@ bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest) return ((db->pc_first ^ dest) & TARGET_PAGE_MASK) == 0; } +static inline void translator_page_protect(DisasContextBase *dcbase, + target_ulong pc) +{ +#ifdef CONFIG_USER_ONLY + dcbase->page_protect_end = pc | ~TARGET_PAGE_MASK; + page_protect(pc); +#endif +} + void translator_loop(const TranslatorOps *ops, DisasContextBase *db, CPUState *cpu, TranslationBlock *tb, int max_insns) { @@ -56,6 +65,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, db->num_insns = 0; db->max_insns = max_insns; db->singlestep_enabled = cflags & CF_SINGLE_STEP; + translator_page_protect(db, db->pc_next); ops->init_disas_context(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ @@ -137,3 +147,32 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, } #endif } + +static inline void translator_maybe_page_protect(DisasContextBase *dcbase, + target_ulong pc, size_t len) +{ +#ifdef CONFIG_USER_ONLY + target_ulong end = pc + len - 1; + + if (end > dcbase->page_protect_end) { + translator_page_protect(dcbase, end); + } +#endif +} + +#define GEN_TRANSLATOR_LD(fullname, type, load_fn, swap_fn) \ + type fullname ## _swap(CPUArchState *env, DisasContextBase *dcbase, \ + abi_ptr pc, bool do_swap) \ + { \ + translator_maybe_page_protect(dcbase, pc, sizeof(type)); \ + type ret = load_fn(env, pc); \ + if (do_swap) { \ + ret = swap_fn(ret); \ + } \ + plugin_insn_append(&ret, sizeof(ret)); \ + return ret; \ + } + +FOR_EACH_TRANSLATOR_LD(GEN_TRANSLATOR_LD) + +#undef GEN_TRANSLATOR_LD diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index 90d1a2d327..8fed542622 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -680,18 +680,26 @@ int cpu_signal_handler(int host_signum, void *pinfo, pc = uc->uc_mcontext.psw.addr; - /* ??? On linux, the non-rt signal handler has 4 (!) arguments instead - of the normal 2 arguments. The 3rd argument contains the "int_code" - from the hardware which does in fact contain the is_write value. - The rt signal handler, as far as I can tell, does not give this value - at all. Not that we could get to it from here even if it were. */ - /* ??? This is not even close to complete, since it ignores all - of the read-modify-write instructions. */ + /* + * ??? On linux, the non-rt signal handler has 4 (!) arguments instead + * of the normal 2 arguments. The 4th argument contains the "Translation- + * Exception Identification for DAT Exceptions" from the hardware (aka + * "int_parm_long"), which does in fact contain the is_write value. + * The rt signal handler, as far as I can tell, does not give this value + * at all. Not that we could get to it from here even if it were. + * So fall back to parsing instructions. Treat read-modify-write ones as + * writes, which is not fully correct, but for tracking self-modifying code + * this is better than treating them as reads. Checking si_addr page flags + * might be a viable improvement, albeit a racy one. + */ + /* ??? This is not even close to complete. */ pinsn = (uint16_t *)pc; switch (pinsn[0] >> 8) { case 0x50: /* ST */ case 0x42: /* STC */ case 0x40: /* STH */ + case 0xba: /* CS */ + case 0xbb: /* CDS */ is_write = 1; break; case 0xc4: /* RIL format insns */ @@ -702,6 +710,12 @@ int cpu_signal_handler(int host_signum, void *pinfo, is_write = 1; } break; + case 0xc8: /* SSF format insns */ + switch (pinsn[0] & 0xf) { + case 0x2: /* CSST */ + is_write = 1; + } + break; case 0xe3: /* RXY format insns */ switch (pinsn[2] & 0xff) { case 0x50: /* STY */ @@ -715,7 +729,27 @@ int cpu_signal_handler(int host_signum, void *pinfo, is_write = 1; } break; + case 0xeb: /* RSY format insns */ + switch (pinsn[2] & 0xff) { + case 0x14: /* CSY */ + case 0x30: /* CSG */ + case 0x31: /* CDSY */ + case 0x3e: /* CDSG */ + case 0xe4: /* LANG */ + case 0xe6: /* LAOG */ + case 0xe7: /* LAXG */ + case 0xe8: /* LAAG */ + case 0xea: /* LAALG */ + case 0xf4: /* LAN */ + case 0xf6: /* LAO */ + case 0xf7: /* LAX */ + case 0xfa: /* LAAL */ + case 0xf8: /* LAA */ + is_write = 1; + } + break; } + return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask); } @@ -49,6 +49,8 @@ #include "qemu/timer.h" #include "qemu/cutils.h" #include "qemu/id.h" +#include "qemu/range.h" +#include "qemu/rcu.h" #include "block/coroutines.h" #ifdef CONFIG_BSD @@ -401,6 +403,9 @@ BlockDriverState *bdrv_new(void) qemu_co_queue_init(&bs->flush_queue); + qemu_co_mutex_init(&bs->bsc_modify_lock); + bs->block_status_cache = g_new0(BdrvBlockStatusCache, 1); + for (i = 0; i < bdrv_drain_all_count; i++) { bdrv_drained_begin(bs); } @@ -4694,6 +4699,8 @@ static void bdrv_close(BlockDriverState *bs) bs->explicit_options = NULL; qobject_unref(bs->full_open_options); bs->full_open_options = NULL; + g_free(bs->block_status_cache); + bs->block_status_cache = NULL; bdrv_release_named_dirty_bitmaps(bs); assert(QLIST_EMPTY(&bs->dirty_bitmaps)); @@ -6319,6 +6326,7 @@ static int bdrv_inactivate_recurse(BlockDriverState *bs) { BdrvChild *child, *parent; int ret; + uint64_t cumulative_perms, cumulative_shared_perms; if (!bs->drv) { return -ENOMEDIUM; @@ -6349,6 +6357,13 @@ static int bdrv_inactivate_recurse(BlockDriverState *bs) } } + bdrv_get_cumulative_perm(bs, &cumulative_perms, + &cumulative_shared_perms); + if (cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) { + /* Our inactive parents still need write access. Inactivation failed. */ + return -EPERM; + } + bs->open_flags |= BDRV_O_INACTIVE; /* @@ -7684,3 +7699,76 @@ BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs) { return bdrv_skip_filters(bdrv_cow_bs(bdrv_skip_filters(bs))); } + +/** + * Check whether [offset, offset + bytes) overlaps with the cached + * block-status data region. + * + * If so, and @pnum is not NULL, set *pnum to `bsc.data_end - offset`, + * which is what bdrv_bsc_is_data()'s interface needs. + * Otherwise, *pnum is not touched. + */ +static bool bdrv_bsc_range_overlaps_locked(BlockDriverState *bs, + int64_t offset, int64_t bytes, + int64_t *pnum) +{ + BdrvBlockStatusCache *bsc = qatomic_rcu_read(&bs->block_status_cache); + bool overlaps; + + overlaps = + qatomic_read(&bsc->valid) && + ranges_overlap(offset, bytes, bsc->data_start, + bsc->data_end - bsc->data_start); + + if (overlaps && pnum) { + *pnum = bsc->data_end - offset; + } + + return overlaps; +} + +/** + * See block_int.h for this function's documentation. + */ +bool bdrv_bsc_is_data(BlockDriverState *bs, int64_t offset, int64_t *pnum) +{ + RCU_READ_LOCK_GUARD(); + + return bdrv_bsc_range_overlaps_locked(bs, offset, 1, pnum); +} + +/** + * See block_int.h for this function's documentation. + */ +void bdrv_bsc_invalidate_range(BlockDriverState *bs, + int64_t offset, int64_t bytes) +{ + RCU_READ_LOCK_GUARD(); + + if (bdrv_bsc_range_overlaps_locked(bs, offset, bytes, NULL)) { + qatomic_set(&bs->block_status_cache->valid, false); + } +} + +/** + * See block_int.h for this function's documentation. + */ +void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes) +{ + BdrvBlockStatusCache *new_bsc = g_new(BdrvBlockStatusCache, 1); + BdrvBlockStatusCache *old_bsc; + + *new_bsc = (BdrvBlockStatusCache) { + .valid = true, + .data_start = offset, + .data_end = offset + bytes, + }; + + QEMU_LOCK_GUARD(&bs->bsc_modify_lock); + + old_bsc = qatomic_rcu_read(&bs->block_status_cache); + qatomic_rcu_set(&bs->block_status_cache, new_bsc); + if (old_bsc) { + g_free_rcu(old_bsc, rcu); + } +} diff --git a/block/file-posix.c b/block/file-posix.c index cb9bffe047..d81e15efa4 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1705,7 +1705,7 @@ static int handle_aiocb_write_zeroes(void *opaque) */ warn_report_once("Your file system is misbehaving: " "fallocate(FALLOC_FL_PUNCH_HOLE) returned EINVAL. " - "Please report this bug to your file sytem " + "Please report this bug to your file system " "vendor."); } else if (ret != -ENOTSUP) { return ret; @@ -2744,7 +2744,8 @@ static int find_allocation(BlockDriverState *bs, off_t start, * the specified offset) that are known to be in the same * allocated/unallocated state. * - * 'bytes' is the max value 'pnum' should be set to. + * 'bytes' is a soft cap for 'pnum'. If the information is free, 'pnum' may + * well exceed it. */ static int coroutine_fn raw_co_block_status(BlockDriverState *bs, bool want_zero, @@ -2782,7 +2783,7 @@ static int coroutine_fn raw_co_block_status(BlockDriverState *bs, } else if (data == offset) { /* On a data extent, compute bytes to the end of the extent, * possibly including a partial sector at EOF. */ - *pnum = MIN(bytes, hole - offset); + *pnum = hole - offset; /* * We are not allowed to return partial sectors, though, so @@ -2801,7 +2802,7 @@ static int coroutine_fn raw_co_block_status(BlockDriverState *bs, } else { /* On a hole, compute bytes to the beginning of the next extent. */ assert(hole == offset); - *pnum = MIN(bytes, data - offset); + *pnum = data - offset; ret = BDRV_BLOCK_ZERO; } *map = offset; diff --git a/block/gluster.c b/block/gluster.c index e8ee14c8e9..d51938e447 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -1461,7 +1461,8 @@ exit: * the specified offset) that are known to be in the same * allocated/unallocated state. * - * 'bytes' is the max value 'pnum' should be set to. + * 'bytes' is a soft cap for 'pnum'. If the information is free, 'pnum' may + * well exceed it. * * (Based on raw_co_block_status() from file-posix.c.) */ @@ -1477,6 +1478,8 @@ static int coroutine_fn qemu_gluster_co_block_status(BlockDriverState *bs, off_t data = 0, hole = 0; int ret = -EINVAL; + assert(QEMU_IS_ALIGNED(offset | bytes, bs->bl.request_alignment)); + if (!s->fd) { return ret; } @@ -1500,12 +1503,26 @@ static int coroutine_fn qemu_gluster_co_block_status(BlockDriverState *bs, } else if (data == offset) { /* On a data extent, compute bytes to the end of the extent, * possibly including a partial sector at EOF. */ - *pnum = MIN(bytes, hole - offset); + *pnum = hole - offset; + + /* + * We are not allowed to return partial sectors, though, so + * round up if necessary. + */ + if (!QEMU_IS_ALIGNED(*pnum, bs->bl.request_alignment)) { + int64_t file_length = qemu_gluster_getlength(bs); + if (file_length > 0) { + /* Ignore errors, this is just a safeguard */ + assert(hole == file_length); + } + *pnum = ROUND_UP(*pnum, bs->bl.request_alignment); + } + ret = BDRV_BLOCK_DATA; } else { /* On a hole, compute bytes to the beginning of the next extent. */ assert(hole == offset); - *pnum = MIN(bytes, data - offset); + *pnum = data - offset; ret = BDRV_BLOCK_ZERO; } diff --git a/block/io.c b/block/io.c index a19942718b..99ee182ca4 100644 --- a/block/io.c +++ b/block/io.c @@ -1883,6 +1883,9 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, return -ENOTSUP; } + /* Invalidate the cached block-status data range if this write overlaps */ + bdrv_bsc_invalidate_range(bs, offset, bytes); + assert(alignment % bs->bl.request_alignment == 0); head = offset % alignment; tail = (offset + bytes) % alignment; @@ -2447,9 +2450,65 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset; if (bs->drv->bdrv_co_block_status) { - ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset, - aligned_bytes, pnum, &local_map, - &local_file); + /* + * Use the block-status cache only for protocol nodes: Format + * drivers are generally quick to inquire the status, but protocol + * drivers often need to get information from outside of qemu, so + * we do not have control over the actual implementation. There + * have been cases where inquiring the status took an unreasonably + * long time, and we can do nothing in qemu to fix it. + * This is especially problematic for images with large data areas, + * because finding the few holes in them and giving them special + * treatment does not gain much performance. Therefore, we try to + * cache the last-identified data region. + * + * Second, limiting ourselves to protocol nodes allows us to assume + * the block status for data regions to be DATA | OFFSET_VALID, and + * that the host offset is the same as the guest offset. + * + * Note that it is possible that external writers zero parts of + * the cached regions without the cache being invalidated, and so + * we may report zeroes as data. This is not catastrophic, + * however, because reporting zeroes as data is fine. + */ + if (QLIST_EMPTY(&bs->children) && + bdrv_bsc_is_data(bs, aligned_offset, pnum)) + { + ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID; + local_file = bs; + local_map = aligned_offset; + } else { + ret = bs->drv->bdrv_co_block_status(bs, want_zero, aligned_offset, + aligned_bytes, pnum, &local_map, + &local_file); + + /* + * Note that checking QLIST_EMPTY(&bs->children) is also done when + * the cache is queried above. Technically, we do not need to check + * it here; the worst that can happen is that we fill the cache for + * non-protocol nodes, and then it is never used. However, filling + * the cache requires an RCU update, so double check here to avoid + * such an update if possible. + */ + if (ret == (BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID) && + QLIST_EMPTY(&bs->children)) + { + /* + * When a protocol driver reports BLOCK_OFFSET_VALID, the + * returned local_map value must be the same as the offset we + * have passed (aligned_offset), and local_bs must be the node + * itself. + * Assert this, because we follow this rule when reading from + * the cache (see the `local_file = bs` and + * `local_map = aligned_offset` assignments above), and the + * result the cache delivers must be the same as the driver + * would deliver. + */ + assert(local_file == bs); + assert(local_map == aligned_offset); + bdrv_bsc_fill(bs, aligned_offset, *pnum); + } + } } else { /* Default code for filters */ @@ -3002,6 +3061,9 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, return 0; } + /* Invalidate the cached block-status data range if this discard overlaps */ + bdrv_bsc_invalidate_range(bs, offset, bytes); + /* Discard is advisory, but some devices track and coalesce * unaligned requests, so we must pass everything down rather than * round here. Still, most devices will just silently ignore diff --git a/block/iscsi.c b/block/iscsi.c index 4d2a416ce7..852384086b 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -781,9 +781,6 @@ retry: iscsi_allocmap_set_allocated(iscsilun, offset, *pnum); } - if (*pnum > bytes) { - *pnum = bytes; - } out_unlock: qemu_mutex_unlock(&iscsilun->mutex); g_free(iTask.err_str); diff --git a/block/mirror.c b/block/mirror.c index 98fc66eabf..85b781bc21 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -160,18 +160,25 @@ static void coroutine_fn mirror_wait_on_conflicts(MirrorOp *self, if (ranges_overlap(self_start_chunk, self_nb_chunks, op_start_chunk, op_nb_chunks)) { - /* - * If the operation is already (indirectly) waiting for us, or - * will wait for us as soon as it wakes up, then just go on - * (instead of producing a deadlock in the former case). - */ - if (op->waiting_for_op) { - continue; + if (self) { + /* + * If the operation is already (indirectly) waiting for us, + * or will wait for us as soon as it wakes up, then just go + * on (instead of producing a deadlock in the former case). + */ + if (op->waiting_for_op) { + continue; + } + + self->waiting_for_op = op; } - self->waiting_for_op = op; qemu_co_queue_wait(&op->waiting_requests, NULL); - self->waiting_for_op = NULL; + + if (self) { + self->waiting_for_op = NULL; + } + break; } } diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index bd0597842f..4ebb49a087 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -556,8 +556,7 @@ static int coroutine_fn do_perform_cow_write(BlockDriverState *bs, * offset needs to be aligned to a cluster boundary. * * If the cluster is unallocated then *host_offset will be 0. - * If the cluster is compressed then *host_offset will contain the - * complete compressed cluster descriptor. + * If the cluster is compressed then *host_offset will contain the l2 entry. * * On entry, *bytes is the maximum number of contiguous bytes starting at * offset that we are interested in. @@ -660,7 +659,7 @@ int qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset, ret = -EIO; goto fail; } - *host_offset = l2_entry & L2E_COMPRESSED_OFFSET_SIZE_MASK; + *host_offset = l2_entry; break; case QCOW2_SUBCLUSTER_ZERO_PLAIN: case QCOW2_SUBCLUSTER_UNALLOCATED_PLAIN: @@ -1400,29 +1399,47 @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset, if (end <= old_start || start >= old_end) { /* No intersection */ + continue; + } + + if (old_alloc->keep_old_clusters && + (end <= l2meta_cow_start(old_alloc) || + start >= l2meta_cow_end(old_alloc))) + { + /* + * Clusters intersect but COW areas don't. And cluster itself is + * already allocated. So, there is no actual conflict. + */ + continue; + } + + /* Conflict */ + + if (start < old_start) { + /* Stop at the start of a running allocation */ + bytes = old_start - start; } else { - if (start < old_start) { - /* Stop at the start of a running allocation */ - bytes = old_start - start; - } else { - bytes = 0; - } + bytes = 0; + } - /* Stop if already an l2meta exists. After yielding, it wouldn't - * be valid any more, so we'd have to clean up the old L2Metas - * and deal with requests depending on them before starting to - * gather new ones. Not worth the trouble. */ - if (bytes == 0 && *m) { - *cur_bytes = 0; - return 0; - } + /* + * Stop if an l2meta already exists. After yielding, it wouldn't + * be valid any more, so we'd have to clean up the old L2Metas + * and deal with requests depending on them before starting to + * gather new ones. Not worth the trouble. + */ + if (bytes == 0 && *m) { + *cur_bytes = 0; + return 0; + } - if (bytes == 0) { - /* Wait for the dependency to complete. We need to recheck - * the free/allocated clusters when we continue. */ - qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock); - return -EAGAIN; - } + if (bytes == 0) { + /* + * Wait for the dependency to complete. We need to recheck + * the free/allocated clusters when we continue. + */ + qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock); + return -EAGAIN; } } @@ -2463,3 +2480,18 @@ fail: g_free(l1_table); return ret; } + +void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry, + uint64_t *coffset, int *csize) +{ + BDRVQcow2State *s = bs->opaque; + int nb_csectors; + + assert(qcow2_get_cluster_type(bs, l2_entry) == QCOW2_CLUSTER_COMPRESSED); + + *coffset = l2_entry & s->cluster_offset_mask; + + nb_csectors = ((l2_entry >> s->csize_shift) & s->csize_mask) + 1; + *csize = nb_csectors * QCOW2_COMPRESSED_SECTOR_SIZE - + (*coffset & (QCOW2_COMPRESSED_SECTOR_SIZE - 1)); +} diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index 8e649b008e..4614572252 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -1177,11 +1177,11 @@ void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry, switch (ctype) { case QCOW2_CLUSTER_COMPRESSED: { - int64_t offset = (l2_entry & s->cluster_offset_mask) - & QCOW2_COMPRESSED_SECTOR_MASK; - int size = QCOW2_COMPRESSED_SECTOR_SIZE * - (((l2_entry >> s->csize_shift) & s->csize_mask) + 1); - qcow2_free_clusters(bs, offset, size, type); + uint64_t coffset; + int csize; + + qcow2_parse_compressed_l2_entry(bs, l2_entry, &coffset, &csize); + qcow2_free_clusters(bs, coffset, csize, type); } break; case QCOW2_CLUSTER_NORMAL: @@ -1247,7 +1247,7 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, bool l1_allocated = false; int64_t old_entry, old_l2_offset; unsigned slice, slice_size2, n_slices; - int i, j, l1_modified = 0, nb_csectors; + int i, j, l1_modified = 0; int ret; assert(addend >= -1 && addend <= 1); @@ -1318,14 +1318,14 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, switch (qcow2_get_cluster_type(bs, entry)) { case QCOW2_CLUSTER_COMPRESSED: - nb_csectors = ((entry >> s->csize_shift) & - s->csize_mask) + 1; if (addend != 0) { - uint64_t coffset = (entry & s->cluster_offset_mask) - & QCOW2_COMPRESSED_SECTOR_MASK; + uint64_t coffset; + int csize; + + qcow2_parse_compressed_l2_entry(bs, entry, + &coffset, &csize); ret = update_refcount( - bs, coffset, - nb_csectors * QCOW2_COMPRESSED_SECTOR_SIZE, + bs, coffset, csize, abs(addend), addend < 0, QCOW2_DISCARD_SNAPSHOT); if (ret < 0) { @@ -1588,6 +1588,66 @@ enum { }; /* + * Fix L2 entry by making it QCOW2_CLUSTER_ZERO_PLAIN (or making all its present + * subclusters QCOW2_SUBCLUSTER_ZERO_PLAIN). + * + * This function decrements res->corruptions on success, so the caller is + * responsible to increment res->corruptions prior to the call. + * + * On failure in-memory @l2_table may be modified. + */ +static int fix_l2_entry_by_zero(BlockDriverState *bs, BdrvCheckResult *res, + uint64_t l2_offset, + uint64_t *l2_table, int l2_index, bool active, + bool *metadata_overlap) +{ + BDRVQcow2State *s = bs->opaque; + int ret; + int idx = l2_index * (l2_entry_size(s) / sizeof(uint64_t)); + uint64_t l2e_offset = l2_offset + (uint64_t)l2_index * l2_entry_size(s); + int ign = active ? QCOW2_OL_ACTIVE_L2 : QCOW2_OL_INACTIVE_L2; + + if (has_subclusters(s)) { + uint64_t l2_bitmap = get_l2_bitmap(s, l2_table, l2_index); + + /* Allocated subclusters become zero */ + l2_bitmap |= l2_bitmap << 32; + l2_bitmap &= QCOW_L2_BITMAP_ALL_ZEROES; + + set_l2_bitmap(s, l2_table, l2_index, l2_bitmap); + set_l2_entry(s, l2_table, l2_index, 0); + } else { + set_l2_entry(s, l2_table, l2_index, QCOW_OFLAG_ZERO); + } + + ret = qcow2_pre_write_overlap_check(bs, ign, l2e_offset, l2_entry_size(s), + false); + if (metadata_overlap) { + *metadata_overlap = ret < 0; + } + if (ret < 0) { + fprintf(stderr, "ERROR: Overlap check failed\n"); + goto fail; + } + + ret = bdrv_pwrite_sync(bs->file, l2e_offset, &l2_table[idx], + l2_entry_size(s)); + if (ret < 0) { + fprintf(stderr, "ERROR: Failed to overwrite L2 " + "table entry: %s\n", strerror(-ret)); + goto fail; + } + + res->corruptions--; + res->corruptions_fixed++; + return 0; + +fail: + res->check_errors++; + return ret; +} + +/* * Increases the refcount in the given refcount table for the all clusters * referenced in the L2 table. While doing so, performs some checks on L2 * entries. @@ -1601,26 +1661,41 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, int flags, BdrvCheckMode fix, bool active) { BDRVQcow2State *s = bs->opaque; - uint64_t *l2_table, l2_entry; + uint64_t l2_entry, l2_bitmap; uint64_t next_contiguous_offset = 0; - int i, l2_size, nb_csectors, ret; + int i, ret; + size_t l2_size_bytes = s->l2_size * l2_entry_size(s); + g_autofree uint64_t *l2_table = g_malloc(l2_size_bytes); + bool metadata_overlap; /* Read L2 table from disk */ - l2_size = s->l2_size * l2_entry_size(s); - l2_table = g_malloc(l2_size); - - ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size); + ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size_bytes); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n"); res->check_errors++; - goto fail; + return ret; } /* Do the actual checks */ - for(i = 0; i < s->l2_size; i++) { + for (i = 0; i < s->l2_size; i++) { + uint64_t coffset; + int csize; + QCow2ClusterType type; + l2_entry = get_l2_entry(s, l2_table, i); + l2_bitmap = get_l2_bitmap(s, l2_table, i); + type = qcow2_get_cluster_type(bs, l2_entry); + + if (type != QCOW2_CLUSTER_COMPRESSED) { + /* Check reserved bits of Standard Cluster Descriptor */ + if (l2_entry & L2E_STD_RESERVED_MASK) { + fprintf(stderr, "ERROR found l2 entry with reserved bits set: " + "%" PRIx64 "\n", l2_entry); + res->corruptions++; + } + } - switch (qcow2_get_cluster_type(bs, l2_entry)) { + switch (type) { case QCOW2_CLUSTER_COMPRESSED: /* Compressed clusters don't have QCOW_OFLAG_COPIED */ if (l2_entry & QCOW_OFLAG_COPIED) { @@ -1638,23 +1713,28 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, break; } + if (l2_bitmap) { + fprintf(stderr, "ERROR compressed cluster %d with non-zero " + "subcluster allocation bitmap, entry=0x%" PRIx64 "\n", + i, l2_entry); + res->corruptions++; + break; + } + /* Mark cluster as used */ - nb_csectors = ((l2_entry >> s->csize_shift) & - s->csize_mask) + 1; - l2_entry &= s->cluster_offset_mask; + qcow2_parse_compressed_l2_entry(bs, l2_entry, &coffset, &csize); ret = qcow2_inc_refcounts_imrt( - bs, res, refcount_table, refcount_table_size, - l2_entry & QCOW2_COMPRESSED_SECTOR_MASK, - nb_csectors * QCOW2_COMPRESSED_SECTOR_SIZE); + bs, res, refcount_table, refcount_table_size, coffset, csize); if (ret < 0) { - goto fail; + return ret; } if (flags & CHECK_FRAG_INFO) { res->bfi.allocated_clusters++; res->bfi.compressed_clusters++; - /* Compressed clusters are fragmented by nature. Since they + /* + * Compressed clusters are fragmented by nature. Since they * take up sub-sector space but we only have sector granularity * I/O we need to re-read the same sectors even for adjacent * compressed clusters. @@ -1668,13 +1748,19 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, { uint64_t offset = l2_entry & L2E_OFFSET_MASK; + if ((l2_bitmap >> 32) & l2_bitmap) { + res->corruptions++; + fprintf(stderr, "ERROR offset=%" PRIx64 ": Allocated " + "cluster has corrupted subcluster allocation bitmap\n", + offset); + } + /* Correct offsets are cluster aligned */ if (offset_into_cluster(s, offset)) { bool contains_data; res->corruptions++; if (has_subclusters(s)) { - uint64_t l2_bitmap = get_l2_bitmap(s, l2_table, i); contains_data = (l2_bitmap & QCOW_L2_BITMAP_ALL_ALLOC); } else { contains_data = !(l2_entry & QCOW_OFLAG_ZERO); @@ -1687,40 +1773,30 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR", offset); if (fix & BDRV_FIX_ERRORS) { - int idx = i * (l2_entry_size(s) / sizeof(uint64_t)); - uint64_t l2e_offset = - l2_offset + (uint64_t)i * l2_entry_size(s); - int ign = active ? QCOW2_OL_ACTIVE_L2 : - QCOW2_OL_INACTIVE_L2; - - l2_entry = has_subclusters(s) ? 0 : QCOW_OFLAG_ZERO; - set_l2_entry(s, l2_table, i, l2_entry); - ret = qcow2_pre_write_overlap_check(bs, ign, - l2e_offset, l2_entry_size(s), false); - if (ret < 0) { - fprintf(stderr, "ERROR: Overlap check failed\n"); - res->check_errors++; - /* Something is seriously wrong, so abort checking - * this L2 table */ - goto fail; + ret = fix_l2_entry_by_zero(bs, res, l2_offset, + l2_table, i, active, + &metadata_overlap); + if (metadata_overlap) { + /* + * Something is seriously wrong, so abort checking + * this L2 table. + */ + return ret; } - ret = bdrv_pwrite_sync(bs->file, l2e_offset, - &l2_table[idx], - l2_entry_size(s)); - if (ret < 0) { - fprintf(stderr, "ERROR: Failed to overwrite L2 " - "table entry: %s\n", strerror(-ret)); - res->check_errors++; - /* Do not abort, continue checking the rest of this - * L2 table's entries */ - } else { - res->corruptions--; - res->corruptions_fixed++; - /* Skip marking the cluster as used - * (it is unused now) */ + if (ret == 0) { + /* + * Skip marking the cluster as used + * (it is unused now). + */ continue; } + + /* + * Failed to fix. + * Do not abort, continue checking the rest of this + * L2 table's entries. + */ } } else { fprintf(stderr, "ERROR offset=%" PRIx64 ": Data cluster is " @@ -1743,14 +1819,23 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, refcount_table_size, offset, s->cluster_size); if (ret < 0) { - goto fail; + return ret; } } break; } case QCOW2_CLUSTER_ZERO_PLAIN: + /* Impossible when image has subclusters */ + assert(!l2_bitmap); + break; + case QCOW2_CLUSTER_UNALLOCATED: + if (l2_bitmap & QCOW_L2_BITMAP_ALL_ALLOC) { + res->corruptions++; + fprintf(stderr, "ERROR: Unallocated " + "cluster has non-zero subcluster allocation map\n"); + } break; default: @@ -1758,12 +1843,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, } } - g_free(l2_table); return 0; - -fail: - g_free(l2_table); - return ret; } /* @@ -1782,71 +1862,79 @@ static int check_refcounts_l1(BlockDriverState *bs, int flags, BdrvCheckMode fix, bool active) { BDRVQcow2State *s = bs->opaque; - uint64_t *l1_table = NULL, l2_offset, l1_size2; + size_t l1_size_bytes = l1_size * L1E_SIZE; + g_autofree uint64_t *l1_table = NULL; + uint64_t l2_offset; int i, ret; - l1_size2 = l1_size * L1E_SIZE; + if (!l1_size) { + return 0; + } /* Mark L1 table as used */ ret = qcow2_inc_refcounts_imrt(bs, res, refcount_table, refcount_table_size, - l1_table_offset, l1_size2); + l1_table_offset, l1_size_bytes); if (ret < 0) { - goto fail; + return ret; + } + + l1_table = g_try_malloc(l1_size_bytes); + if (l1_table == NULL) { + res->check_errors++; + return -ENOMEM; } /* Read L1 table entries from disk */ - if (l1_size2 > 0) { - l1_table = g_try_malloc(l1_size2); - if (l1_table == NULL) { - ret = -ENOMEM; - res->check_errors++; - goto fail; - } - ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2); - if (ret < 0) { - fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n"); - res->check_errors++; - goto fail; - } - for(i = 0;i < l1_size; i++) - be64_to_cpus(&l1_table[i]); + ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size_bytes); + if (ret < 0) { + fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n"); + res->check_errors++; + return ret; + } + + for (i = 0; i < l1_size; i++) { + be64_to_cpus(&l1_table[i]); } /* Do the actual checks */ - for(i = 0; i < l1_size; i++) { - l2_offset = l1_table[i]; - if (l2_offset) { - /* Mark L2 table as used */ - l2_offset &= L1E_OFFSET_MASK; - ret = qcow2_inc_refcounts_imrt(bs, res, - refcount_table, refcount_table_size, - l2_offset, s->cluster_size); - if (ret < 0) { - goto fail; - } + for (i = 0; i < l1_size; i++) { + if (!l1_table[i]) { + continue; + } - /* L2 tables are cluster aligned */ - if (offset_into_cluster(s, l2_offset)) { - fprintf(stderr, "ERROR l2_offset=%" PRIx64 ": Table is not " - "cluster aligned; L1 entry corrupted\n", l2_offset); - res->corruptions++; - } + if (l1_table[i] & L1E_RESERVED_MASK) { + fprintf(stderr, "ERROR found L1 entry with reserved bits set: " + "%" PRIx64 "\n", l1_table[i]); + res->corruptions++; + } - /* Process and check L2 entries */ - ret = check_refcounts_l2(bs, res, refcount_table, - refcount_table_size, l2_offset, flags, - fix, active); - if (ret < 0) { - goto fail; - } + l2_offset = l1_table[i] & L1E_OFFSET_MASK; + + /* Mark L2 table as used */ + ret = qcow2_inc_refcounts_imrt(bs, res, + refcount_table, refcount_table_size, + l2_offset, s->cluster_size); + if (ret < 0) { + return ret; + } + + /* L2 tables are cluster aligned */ + if (offset_into_cluster(s, l2_offset)) { + fprintf(stderr, "ERROR l2_offset=%" PRIx64 ": Table is not " + "cluster aligned; L1 entry corrupted\n", l2_offset); + res->corruptions++; + } + + /* Process and check L2 entries */ + ret = check_refcounts_l2(bs, res, refcount_table, + refcount_table_size, l2_offset, flags, + fix, active); + if (ret < 0) { + return ret; } } - g_free(l1_table); - return 0; -fail: - g_free(l1_table); - return ret; + return 0; } /* @@ -2001,9 +2089,17 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res, for(i = 0; i < s->refcount_table_size; i++) { uint64_t offset, cluster; - offset = s->refcount_table[i]; + offset = s->refcount_table[i] & REFT_OFFSET_MASK; cluster = offset >> s->cluster_bits; + if (s->refcount_table[i] & REFT_RESERVED_MASK) { + fprintf(stderr, "ERROR refcount table entry %" PRId64 " has " + "reserved bits set\n", i); + res->corruptions++; + *rebuild = true; + continue; + } + /* Refcount blocks are cluster aligned */ if (offset_into_cluster(s, offset)) { fprintf(stderr, "ERROR refcount block %" PRId64 " is not " diff --git a/block/qcow2.c b/block/qcow2.c index 9f1b6461c8..02f9f3e636 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -74,7 +74,7 @@ typedef struct { static int coroutine_fn qcow2_co_preadv_compressed(BlockDriverState *bs, - uint64_t cluster_descriptor, + uint64_t l2_entry, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, @@ -2205,7 +2205,7 @@ typedef struct Qcow2AioTask { BlockDriverState *bs; QCow2SubclusterType subcluster_type; /* only for read */ - uint64_t host_offset; /* or full descriptor in compressed clusters */ + uint64_t host_offset; /* or l2_entry for compressed read */ uint64_t offset; uint64_t bytes; QEMUIOVector *qiov; @@ -4693,22 +4693,19 @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs, static int coroutine_fn qcow2_co_preadv_compressed(BlockDriverState *bs, - uint64_t cluster_descriptor, + uint64_t l2_entry, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, size_t qiov_offset) { BDRVQcow2State *s = bs->opaque; - int ret = 0, csize, nb_csectors; + int ret = 0, csize; uint64_t coffset; uint8_t *buf, *out_buf; int offset_in_cluster = offset_into_cluster(s, offset); - coffset = cluster_descriptor & s->cluster_offset_mask; - nb_csectors = ((cluster_descriptor >> s->csize_shift) & s->csize_mask) + 1; - csize = nb_csectors * QCOW2_COMPRESSED_SECTOR_SIZE - - (coffset & ~QCOW2_COMPRESSED_SECTOR_MASK); + qcow2_parse_compressed_l2_entry(bs, l2_entry, &coffset, &csize); buf = g_try_malloc(csize); if (!buf) { diff --git a/block/qcow2.h b/block/qcow2.h index 0fe5f74ed3..fd48a89d45 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -110,7 +110,6 @@ /* Defined in the qcow2 spec (compressed cluster descriptor) */ #define QCOW2_COMPRESSED_SECTOR_SIZE 512U -#define QCOW2_COMPRESSED_SECTOR_MASK (~(QCOW2_COMPRESSED_SECTOR_SIZE - 1ULL)) /* Must be at least 2 to cover COW */ #define MIN_L2_CACHE_SIZE 2 /* cache entries */ @@ -587,10 +586,12 @@ typedef enum QCow2MetadataOverlap { (QCOW2_OL_CACHED | QCOW2_OL_INACTIVE_L2) #define L1E_OFFSET_MASK 0x00fffffffffffe00ULL +#define L1E_RESERVED_MASK 0x7f000000000001ffULL #define L2E_OFFSET_MASK 0x00fffffffffffe00ULL -#define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL +#define L2E_STD_RESERVED_MASK 0x3f000000000001feULL #define REFT_OFFSET_MASK 0xfffffffffffffe00ULL +#define REFT_RESERVED_MASK 0x1ffULL #define INV_OFFSET (-1ULL) @@ -914,6 +915,8 @@ int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, uint64_t offset, int compressed_size, uint64_t *host_offset); +void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry, + uint64_t *coffset, int *csize); int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m); void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m); diff --git a/bsd-user/i386/target_arch_cpu.c b/bsd-user/i386/target_arch_cpu.c index 71998e5ba5..d349e45299 100644 --- a/bsd-user/i386/target_arch_cpu.c +++ b/bsd-user/i386/target_arch_cpu.c @@ -33,11 +33,6 @@ uint64_t cpu_get_tsc(CPUX86State *env) return cpu_get_host_ticks(); } -int cpu_get_pic_interrupt(CPUX86State *env) -{ - return -1; -} - void bsd_i386_write_dt(void *ptr, unsigned long addr, unsigned long limit, int flags) { diff --git a/bsd-user/x86_64/target_arch_cpu.c b/bsd-user/x86_64/target_arch_cpu.c index db822e54c6..be7bd10720 100644 --- a/bsd-user/x86_64/target_arch_cpu.c +++ b/bsd-user/x86_64/target_arch_cpu.c @@ -33,11 +33,6 @@ uint64_t cpu_get_tsc(CPUX86State *env) return cpu_get_host_ticks(); } -int cpu_get_pic_interrupt(CPUX86State *env) -{ - return -1; -} - void bsd_x86_64_write_dt(void *ptr, unsigned long addr, unsigned long limit, int flags) { diff --git a/chardev/char-mux.c b/chardev/char-mux.c index 5baf419010..ada0c6866f 100644 --- a/chardev/char-mux.c +++ b/chardev/char-mux.c @@ -386,10 +386,9 @@ void suspend_mux_open(void) static int chardev_options_parsed_cb(Object *child, void *opaque) { Chardev *chr = (Chardev *)child; - ChardevClass *class = CHARDEV_GET_CLASS(chr); - if (!chr->be_open && class->chr_options_parsed) { - class->chr_options_parsed(chr); + if (!chr->be_open && CHARDEV_IS_MUX(chr)) { + open_muxes(chr); } return 0; @@ -412,7 +411,6 @@ static void char_mux_class_init(ObjectClass *oc, void *data) cc->chr_accept_input = mux_chr_accept_input; cc->chr_add_watch = mux_chr_add_watch; cc->chr_be_event = mux_chr_be_event; - cc->chr_options_parsed = open_muxes; cc->chr_update_read_handler = mux_chr_update_read_handlers; } diff --git a/chardev/char.c b/chardev/char.c index 4595a8d430..0169d8dde4 100644 --- a/chardev/char.c +++ b/chardev/char.c @@ -241,18 +241,15 @@ static void qemu_char_open(Chardev *chr, ChardevBackend *backend, ChardevCommon *common = backend ? backend->u.null.data : NULL; if (common && common->has_logfile) { - int flags = O_WRONLY | O_CREAT; + int flags = O_WRONLY; if (common->has_logappend && common->logappend) { flags |= O_APPEND; } else { flags |= O_TRUNC; } - chr->logfd = qemu_open_old(common->logfile, flags, 0666); + chr->logfd = qemu_create(common->logfile, flags, 0666, errp); if (chr->logfd < 0) { - error_setg_errno(errp, errno, - "Unable to open logfile %s", - common->logfile); return; } } @@ -5052,7 +5052,9 @@ for bios_file in \ $source_path/pc-bios/openbios-* \ $source_path/pc-bios/u-boot.* \ $source_path/pc-bios/edk2-*.fd.bz2 \ - $source_path/pc-bios/palcode-* + $source_path/pc-bios/palcode-* \ + $source_path/pc-bios/qemu_vga.ndrv + do LINKS="$LINKS pc-bios/$(basename $bios_file)" done diff --git a/docs/about/build-platforms.rst b/docs/about/build-platforms.rst index 692323609e..bcb1549721 100644 --- a/docs/about/build-platforms.rst +++ b/docs/about/build-platforms.rst @@ -29,6 +29,39 @@ The `Repology`_ site is a useful resource to identify currently shipped versions of software in various operating systems, though it does not cover all distros listed below. +Supported host architectures +---------------------------- + +Those hosts are officially supported, with various accelerators: + + .. list-table:: + :header-rows: 1 + + * - CPU Architecture + - Accelerators + * - Arm + - kvm (64 bit only), tcg, xen + * - MIPS + - kvm, tcg + * - PPC + - kvm, tcg + * - RISC-V + - tcg + * - s390x + - kvm, tcg + * - SPARC + - tcg + * - x86 + - hax, hvf (64 bit only), kvm, nvmm, tcg, whpx (64 bit only), xen + +Other host architectures are not supported. It is possible to build QEMU on an +unsupported host architecture using the configure ``--enable-tcg-interpreter`` +option to enable the experimental TCI support, but note that this is very slow +and is not recommended. + +Non-supported architectures may be removed in the future following the +:ref:`deprecation process<Deprecated features>`. + Linux OS, macOS, FreeBSD, NetBSD, OpenBSD ----------------------------------------- diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 9ee355ec0b..3c2be84d80 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -1,3 +1,5 @@ +.. _Deprecated features: + Deprecated features =================== diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index 69f57c2886..adf497e679 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -20,6 +20,7 @@ Hyperscale applications. The following machines are based on this chip : - ``quanta-gbs-bmc`` Quanta GBS server BMC - ``quanta-gsj`` Quanta GSJ server BMC +- ``kudo-bmc`` Fii USA Kudo server BMC There are also two more SoCs, NPCM710 and NPCM705, which are single-core variants of NPCM750 and NPCM730, respectively. These are currently not diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst index fe6c30d509..d58980aef8 100644 --- a/docs/tools/qemu-img.rst +++ b/docs/tools/qemu-img.rst @@ -415,7 +415,7 @@ Command description: 4 Error on reading data -.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps [--skip-broken-bitmaps]] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-r RATE_LIMIT] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME +.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps [--skip-broken-bitmaps]] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE [-F backing_fmt]] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-r RATE_LIMIT] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME Convert the disk image *FILENAME* or a snapshot *SNAPSHOT_PARAM* to disk image *OUTPUT_FILENAME* using format *OUTPUT_FMT*. It can @@ -439,7 +439,7 @@ Command description: You can use the *BACKING_FILE* option to force the output image to be created as a copy on write image of the specified base image; the *BACKING_FILE* should have the same content as the input's base image, - however the path, image format, etc may differ. + however the path, image format (as given by *BACKING_FMT*), etc may differ. If a relative path name is given, the backing file is looked up relative to the directory containing *OUTPUT_FILENAME*. diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index e23830f4b7..f40e854dec 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -373,6 +373,11 @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) } } +/* Union describing the device-specific extra data we pass to the devfn. */ +typedef union PPCExtraData { + bool i2c_internal; +} PPCExtraData; + /* Most of the devices in the AN505 FPGA image sit behind * Peripheral Protection Controllers. These data structures * define the layout of which devices sit behind which PPCs. @@ -382,7 +387,8 @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) */ typedef MemoryRegion *MakeDevFn(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs); + const int *irqs, + const PPCExtraData *extradata); typedef struct PPCPortInfo { const char *name; @@ -391,6 +397,7 @@ typedef struct PPCPortInfo { hwaddr addr; hwaddr size; int irqs[3]; /* currently no device needs more IRQ lines than this */ + PPCExtraData extradata; /* to pass device-specific info to the devfn */ } PPCPortInfo; typedef struct PPCInfo { @@ -401,7 +408,8 @@ typedef struct PPCInfo { static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { /* Initialize, configure and realize a TYPE_UNIMPLEMENTED_DEVICE, * and return a pointer to its MemoryRegion. @@ -417,7 +425,7 @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* The irq[] array is tx, rx, combined, in that order */ MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -441,7 +449,7 @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { MPS2SCC *scc = opaque; DeviceState *sccdev; @@ -465,7 +473,7 @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { MPS2FPGAIO *fpgaio = opaque; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -480,7 +488,8 @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { SysBusDevice *s; NICInfo *nd = &nd_table[0]; @@ -500,7 +509,8 @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, + const PPCExtraData *extradata) { /* * The AN524 makes the ethernet and USB share a PPC port. @@ -543,7 +553,7 @@ static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { TZMPC *mpc = opaque; int i = mpc - &mms->mpc[0]; @@ -615,7 +625,7 @@ static void remap_irq_fn(void *opaque, int n, int level) static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* The irq[] array is DMACINTR, DMACINTERR, DMACINTTC, in that order */ PL080State *dma = opaque; @@ -672,7 +682,7 @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { /* * The AN505 has five PL022 SPI controllers. @@ -694,7 +704,7 @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { ArmSbconI2CState *i2c = opaque; SysBusDevice *s; @@ -702,12 +712,26 @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), name, i2c, TYPE_ARM_SBCON_I2C); s = SYS_BUS_DEVICE(i2c); sysbus_realize(s, &error_fatal); + + /* + * If this is an internal-use-only i2c bus, mark it full + * so that user-created i2c devices are not plugged into it. + * If we implement models of any on-board i2c devices that + * plug in to one of the internal-use-only buses, then we will + * need to create and plugging those in here before we mark the + * bus as full. + */ + if (extradata->i2c_internal) { + BusState *qbus = qdev_get_child_bus(DEVICE(i2c), "i2c"); + qbus_mark_full(qbus); + } + return sysbus_mmio_get_region(s, 0); } static MemoryRegion *make_rtc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, - const int *irqs) + const int *irqs, const PPCExtraData *extradata) { PL031State *pl031 = opaque; SysBusDevice *s; @@ -912,10 +936,14 @@ static void mps2tz_common_init(MachineState *machine) { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000, { 36, 37, 44 } }, { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000, { 38, 39, 45 } }, { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000, { 40, 41, 46 } }, - { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 }, - { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, + { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, }, }, { .name = "apb_ppcexp2", @@ -956,15 +984,20 @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, { "spi0", make_spi, &mms->spi[0], 0x41202000, 0x1000, { 52 } }, { "spi1", make_spi, &mms->spi[1], 0x41203000, 0x1000, { 53 } }, { "spi2", make_spi, &mms->spi[2], 0x41204000, 0x1000, { 54 } }, - { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000 }, + { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, { /* port 7 reserved */ }, - { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000 }, + { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000, {}, + { .i2c_internal = true /* DDR4 EEPROM */ } }, }, }, { .name = "apb_ppcexp2", @@ -1006,15 +1039,20 @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "i2c0", make_i2c, &mms->i2c[0], 0x49200000, 0x1000 }, - { "i2c1", make_i2c, &mms->i2c[1], 0x49201000, 0x1000 }, + { "i2c0", make_i2c, &mms->i2c[0], 0x49200000, 0x1000, {}, + { .i2c_internal = true /* touchscreen */ } }, + { "i2c1", make_i2c, &mms->i2c[1], 0x49201000, 0x1000, {}, + { .i2c_internal = true /* audio conf */ } }, { "spi0", make_spi, &mms->spi[0], 0x49202000, 0x1000, { 53 } }, { "spi1", make_spi, &mms->spi[1], 0x49203000, 0x1000, { 54 } }, { "spi2", make_spi, &mms->spi[2], 0x49204000, 0x1000, { 55 } }, - { "i2c2", make_i2c, &mms->i2c[2], 0x49205000, 0x1000 }, - { "i2c3", make_i2c, &mms->i2c[3], 0x49206000, 0x1000 }, + { "i2c2", make_i2c, &mms->i2c[2], 0x49205000, 0x1000, {}, + { .i2c_internal = false /* shield 0 */ } }, + { "i2c3", make_i2c, &mms->i2c[3], 0x49206000, 0x1000, {}, + { .i2c_internal = false /* shield 1 */ } }, { /* port 7 reserved */ }, - { "i2c4", make_i2c, &mms->i2c[4], 0x49208000, 0x1000 }, + { "i2c4", make_i2c, &mms->i2c[4], 0x49208000, 0x1000, {}, + { .i2c_internal = true /* DDR4 EEPROM */ } }, }, }, { .name = "apb_ppcexp2", @@ -1084,7 +1122,7 @@ static void mps2tz_common_init(MachineState *machine) } mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size, - pinfo->irqs); + pinfo->irqs, &pinfo->extradata); portname = g_strdup_printf("port[%d]", port); object_property_set_link(OBJECT(ppc), portname, OBJECT(mr), &error_fatal); diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index 4634aa1a1c..bb76fa6889 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -428,7 +428,17 @@ static void mps2_common_init(MachineState *machine) 0x40023000, /* Audio */ 0x40029000, /* Shield0 */ 0x4002a000}; /* Shield1 */ - sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL); + DeviceState *dev; + + dev = sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL); + if (i < 2) { + /* + * internal-only bus: mark it full to avoid user-created + * i2c devices being plugged into it. + */ + BusState *qbus = qdev_get_child_bus(dev, "i2c"); + qbus_mark_full(qbus); + } } create_unimplemented_device("i2s", 0x40024000, 0x400); diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index e5a3243995..a656169f61 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -31,6 +31,7 @@ #define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff #define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff +#define KUDO_BMC_POWER_ON_STRAPS 0x00001fff static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; @@ -357,6 +358,23 @@ static void quanta_gbs_init(MachineState *machine) npcm7xx_load_kernel(machine, soc); } +static void kudo_bmc_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, KUDO_BMC_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "mx66u51235f", + drive_get(IF_MTD, 0, 0)); + npcm7xx_connect_flash(&soc->fiu[1], 0, "mx66u51235f", + drive_get(IF_MTD, 3, 0)); + + npcm7xx_load_kernel(machine, soc); +} + static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type) { NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type)); @@ -417,6 +435,18 @@ static void gbs_bmc_machine_class_init(ObjectClass *oc, void *data) mc->default_ram_size = 1 * GiB; } +static void kudo_bmc_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM730); + + mc->desc = "Kudo BMC (Cortex-A9)"; + mc->init = kudo_bmc_init; + mc->default_ram_size = 1 * GiB; +}; + static const TypeInfo npcm7xx_machine_types[] = { { .name = TYPE_NPCM7XX_MACHINE, @@ -437,6 +467,10 @@ static const TypeInfo npcm7xx_machine_types[] = { .name = MACHINE_TYPE_NAME("quanta-gbs-bmc"), .parent = TYPE_NPCM7XX_MACHINE, .class_init = gbs_bmc_machine_class_init, + }, { + .name = MACHINE_TYPE_NAME("kudo-bmc"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = kudo_bmc_machine_class_init, }, }; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 73e9c6bb7c..1d59f0e59f 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -584,6 +584,12 @@ static void create_its(VirtMachineState *vms) const char *itsclass = its_class_name(); DeviceState *dev; + if (!strcmp(itsclass, "arm-gicv3-its")) { + if (!vms->tcg_its) { + itsclass = NULL; + } + } + if (!itsclass) { /* Do nothing if not supported */ return; @@ -621,7 +627,7 @@ static void create_v2m(VirtMachineState *vms) vms->msi_controller = VIRT_MSI_CTRL_GICV2M; } -static void create_gic(VirtMachineState *vms) +static void create_gic(VirtMachineState *vms, MemoryRegion *mem) { MachineState *ms = MACHINE(vms); /* We create a standalone GIC */ @@ -655,6 +661,14 @@ static void create_gic(VirtMachineState *vms) nb_redist_regions); qdev_prop_set_uint32(vms->gic, "redist-region-count[0]", redist0_count); + if (!kvm_irqchip_in_kernel()) { + if (vms->tcg_its) { + object_property_set_link(OBJECT(vms->gic), "sysmem", + OBJECT(mem), &error_fatal); + qdev_prop_set_bit(vms->gic, "has-lpi", true); + } + } + if (nb_redist_regions == 2) { uint32_t redist1_capacity = vms->memmap[VIRT_HIGH_GIC_REDIST2].size / GICV3_REDIST_SIZE; @@ -2039,7 +2053,7 @@ static void machvirt_init(MachineState *machine) virt_flash_fdt(vms, sysmem, secure_sysmem ?: sysmem); - create_gic(vms); + create_gic(vms, sysmem); virt_cpu_post_init(vms, sysmem); @@ -2742,6 +2756,12 @@ static void virt_instance_init(Object *obj) } else { /* Default allows ITS instantiation */ vms->its = true; + + if (vmc->no_tcg_its) { + vms->tcg_its = false; + } else { + vms->tcg_its = true; + } } /* Default disallows iommu instantiation */ @@ -2791,8 +2811,13 @@ DEFINE_VIRT_MACHINE_AS_LATEST(6, 2) static void virt_machine_6_1_options(MachineClass *mc) { + VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc)); + virt_machine_6_2_options(mc); compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); + + /* qemu ITS was introduced with 6.2 */ + vmc->no_tcg_its = true; } DEFINE_VIRT_MACHINE(6, 1) diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index b4b5e8a3ee..c069a30842 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -235,8 +235,18 @@ static void uart_parameters_setup(CadenceUARTState *s) static int uart_can_receive(void *opaque) { CadenceUARTState *s = opaque; - int ret = MAX(CADENCE_UART_RX_FIFO_SIZE, CADENCE_UART_TX_FIFO_SIZE); - uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; + int ret; + uint32_t ch_mode; + + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); + return 0; + } + + ret = MAX(CADENCE_UART_RX_FIFO_SIZE, CADENCE_UART_TX_FIFO_SIZE); + ch_mode = s->r[R_MR] & UART_MR_CHMODE; if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { ret = MIN(ret, CADENCE_UART_RX_FIFO_SIZE - s->rx_count); @@ -353,11 +363,6 @@ static void uart_receive(void *opaque, const uint8_t *buf, int size) CadenceUARTState *s = opaque; uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; - /* ignore characters when unclocked or in reset */ - if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { - return; - } - if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { uart_write_rx_fifo(opaque, buf, size); } @@ -373,6 +378,8 @@ static void uart_event(void *opaque, QEMUChrEvent event) /* ignore characters when unclocked or in reset */ if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); return; } @@ -403,15 +410,22 @@ static void uart_read_rx_fifo(CadenceUARTState *s, uint32_t *c) uart_update_status(s); } -static void uart_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) +static MemTxResult uart_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size, MemTxAttrs attrs) { CadenceUARTState *s = opaque; + /* ignore access when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); + return MEMTX_ERROR; + } + DB_PRINT(" offset:%x data:%08x\n", (unsigned)offset, (unsigned)value); offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { - return; + return MEMTX_DECODE_ERROR; } switch (offset) { case R_IER: /* ier (wts imr) */ @@ -458,30 +472,41 @@ static void uart_write(void *opaque, hwaddr offset, break; } uart_update_status(s); + + return MEMTX_OK; } -static uint64_t uart_read(void *opaque, hwaddr offset, - unsigned size) +static MemTxResult uart_read(void *opaque, hwaddr offset, + uint64_t *value, unsigned size, MemTxAttrs attrs) { CadenceUARTState *s = opaque; uint32_t c = 0; + /* ignore access when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: uart is unclocked or in reset\n", + __func__); + return MEMTX_ERROR; + } + offset >>= 2; if (offset >= CADENCE_UART_R_MAX) { - c = 0; - } else if (offset == R_TX_RX) { + return MEMTX_DECODE_ERROR; + } + if (offset == R_TX_RX) { uart_read_rx_fifo(s, &c); } else { - c = s->r[offset]; + c = s->r[offset]; } DB_PRINT(" offset:%x data:%08x\n", (unsigned)(offset << 2), (unsigned)c); - return c; + *value = c; + return MEMTX_OK; } static const MemoryRegionOps uart_ops = { - .read = uart_read, - .write = uart_write, + .read_with_attrs = uart_read, + .write_with_attrs = uart_write, .endianness = DEVICE_NATIVE_ENDIAN, }; diff --git a/hw/display/qxl.c b/hw/display/qxl.c index 43482d4364..29c80b4289 100644 --- a/hw/display/qxl.c +++ b/hw/display/qxl.c @@ -2252,7 +2252,7 @@ static int qxl_pre_save(void *opaque) } else { d->last_release_offset = (uint8_t *)d->last_release - ram_start; } - if (d->last_release_offset < d->vga.vram_size) { + if (d->last_release_offset >= d->vga.vram_size) { return 1; } diff --git a/hw/display/virtio-gpu-udmabuf.c b/hw/display/virtio-gpu-udmabuf.c index 3c01a415e7..c6f7f58784 100644 --- a/hw/display/virtio-gpu-udmabuf.c +++ b/hw/display/virtio-gpu-udmabuf.c @@ -185,6 +185,7 @@ static VGPUDMABuf dmabuf->buf.stride = fb->stride; dmabuf->buf.fourcc = qemu_pixman_to_drm_format(fb->format); dmabuf->buf.fd = res->dmabuf_fd; + dmabuf->buf.allow_fences = true; dmabuf->scanout_id = scanout_id; QTAILQ_INSERT_HEAD(&g->dmabuf.bufs, dmabuf, next); diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index 72da5bf500..182e0868b0 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -985,8 +985,10 @@ void virtio_gpu_simple_process_cmd(VirtIOGPU *g, break; } if (!cmd->finished) { - virtio_gpu_ctrl_response_nodata(g, cmd, cmd->error ? cmd->error : - VIRTIO_GPU_RESP_OK_NODATA); + if (!g->parent_obj.renderer_blocked) { + virtio_gpu_ctrl_response_nodata(g, cmd, cmd->error ? cmd->error : + VIRTIO_GPU_RESP_OK_NODATA); + } } } @@ -1042,6 +1044,30 @@ void virtio_gpu_process_cmdq(VirtIOGPU *g) g->processing_cmdq = false; } +static void virtio_gpu_process_fenceq(VirtIOGPU *g) +{ + struct virtio_gpu_ctrl_command *cmd, *tmp; + + QTAILQ_FOREACH_SAFE(cmd, &g->fenceq, next, tmp) { + trace_virtio_gpu_fence_resp(cmd->cmd_hdr.fence_id); + virtio_gpu_ctrl_response_nodata(g, cmd, VIRTIO_GPU_RESP_OK_NODATA); + QTAILQ_REMOVE(&g->fenceq, cmd, next); + g_free(cmd); + g->inflight--; + if (virtio_gpu_stats_enabled(g->parent_obj.conf)) { + fprintf(stderr, "inflight: %3d (-)\r", g->inflight); + } + } +} + +static void virtio_gpu_handle_gl_flushed(VirtIOGPUBase *b) +{ + VirtIOGPU *g = container_of(b, VirtIOGPU, parent_obj); + + virtio_gpu_process_fenceq(g); + virtio_gpu_process_cmdq(g); +} + static void virtio_gpu_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) { VirtIOGPU *g = VIRTIO_GPU(vdev); @@ -1400,10 +1426,12 @@ static void virtio_gpu_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); VirtIOGPUClass *vgc = VIRTIO_GPU_CLASS(klass); + VirtIOGPUBaseClass *vgbc = &vgc->parent; vgc->handle_ctrl = virtio_gpu_handle_ctrl; vgc->process_cmd = virtio_gpu_simple_process_cmd; vgc->update_cursor_data = virtio_gpu_update_cursor_data; + vgbc->gl_flushed = virtio_gpu_handle_gl_flushed; vdc->realize = virtio_gpu_device_realize; vdc->reset = virtio_gpu_reset; diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index d1f5fa3b5a..dfaa47cdc2 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -1916,7 +1916,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) PCMachineState *pcms = PC_MACHINE(machine); int nb_numa_nodes = machine->numa_state->num_nodes; NodeInfo *numa_info = machine->numa_state->nodes; - ram_addr_t hotplugabble_address_space_size = + ram_addr_t hotpluggable_address_space_size = object_property_get_int(OBJECT(pcms), PC_MACHINE_DEVMEM_REGION_SIZE, NULL); @@ -2022,10 +2022,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) * Memory devices may override proximity set by this entry, * providing _PXM method if necessary. */ - if (hotplugabble_address_space_size) { + if (hotpluggable_address_space_size) { numamem = acpi_data_push(table_data, sizeof *numamem); build_srat_memory(numamem, machine->device_memory->base, - hotplugabble_address_space_size, nb_numa_nodes - 1, + hotpluggable_address_space_size, nb_numa_nodes - 1, MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED); } diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 209b3f5553..75f075547f 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -679,7 +679,7 @@ static inline bool vtd_pe_type_check(X86IOMMUState *x86_iommu, } break; default: - /* Unknwon type */ + /* Unknown type */ return false; } return true; @@ -692,7 +692,7 @@ static inline bool vtd_pdire_present(VTDPASIDDirEntry *pdire) /** * Caller of this function should check present bit if wants - * to use pdir entry for futher usage except for fpd bit check. + * to use pdir entry for further usage except for fpd bit check. */ static int vtd_get_pdire_from_pdir_table(dma_addr_t pasid_dir_base, uint32_t pasid, @@ -746,7 +746,7 @@ static int vtd_get_pe_in_pasid_leaf_table(IntelIOMMUState *s, /** * Caller of this function should check present bit if wants - * to use pasid entry for futher usage except for fpd bit check. + * to use pasid entry for further usage except for fpd bit check. */ static int vtd_get_pe_from_pdire(IntelIOMMUState *s, uint32_t pasid, @@ -1507,7 +1507,7 @@ static int vtd_sync_shadow_page_table(VTDAddressSpace *vtd_as) } /* - * Check if specific device is configed to bypass address + * Check if specific device is configured to bypass address * translation for DMA requests. In Scalable Mode, bypass * 1st-level translation or 2nd-level translation, it depends * on PGTT setting. diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index d63f8af604..3f24707838 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -165,6 +165,16 @@ static void gicv3_redist_update_noirqset(GICv3CPUState *cs) cs->hppi.grp = gicv3_irq_group(cs->gic, cs, cs->hppi.irq); } + if ((cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) && cs->gic->lpi_enable && + (cs->hpplpi.prio != 0xff)) { + if (irqbetter(cs, cs->hpplpi.irq, cs->hpplpi.prio)) { + cs->hppi.irq = cs->hpplpi.irq; + cs->hppi.prio = cs->hpplpi.prio; + cs->hppi.grp = cs->hpplpi.grp; + seenbetter = true; + } + } + /* If the best interrupt we just found would preempt whatever * was the previous best interrupt before this update, then * we know it's definitely the best one now. @@ -339,9 +349,13 @@ static void gicv3_set_irq(void *opaque, int irq, int level) static void arm_gicv3_post_load(GICv3State *s) { + int i; /* Recalculate our cached idea of the current highest priority * pending interrupt, but don't set IRQ or FIQ lines. */ + for (i = 0; i < s->num_cpu; i++) { + gicv3_redist_update_lpi(&s->cpu[i]); + } gicv3_full_update_noirqset(s); /* Repopulate the cache of GICv3CPUState pointers for target CPUs */ gicv3_cache_all_target_cpustates(s); diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index 58ef65f589..223db16fec 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -345,6 +345,11 @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) return; } + if (s->lpi_enable && !s->dma) { + error_setg(errp, "Redist-ITS: Guest 'sysmem' reference link not set"); + return; + } + s->cpu = g_new0(GICv3CPUState, s->num_cpu); for (i = 0; i < s->num_cpu; i++) { @@ -381,6 +386,10 @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) (1 << 24) | (i << 8) | (last << 4); + + if (s->lpi_enable) { + s->cpu[i].gicr_typer |= GICR_TYPER_PLPIS; + } } } @@ -426,6 +435,7 @@ static void arm_gicv3_common_reset(DeviceState *dev) memset(cs->gicr_ipriorityr, 0, sizeof(cs->gicr_ipriorityr)); cs->hppi.prio = 0xff; + cs->hpplpi.prio = 0xff; /* State in the CPU interface must *not* be reset here, because it * is part of the CPU's reset domain, not the GIC device's. @@ -494,9 +504,12 @@ static Property arm_gicv3_common_properties[] = { DEFINE_PROP_UINT32("num-cpu", GICv3State, num_cpu, 1), DEFINE_PROP_UINT32("num-irq", GICv3State, num_irq, 32), DEFINE_PROP_UINT32("revision", GICv3State, revision, 3), + DEFINE_PROP_BOOL("has-lpi", GICv3State, lpi_enable, 0), DEFINE_PROP_BOOL("has-security-extensions", GICv3State, security_extn, 0), DEFINE_PROP_ARRAY("redist-region-count", GICv3State, nb_redist_regions, redist_region_count, qdev_prop_uint32, uint32_t), + DEFINE_PROP_LINK("sysmem", GICv3State, dma, TYPE_MEMORY_REGION, + MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index a032d505f5..462a35f66e 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -899,10 +899,12 @@ static void icc_activate_irq(GICv3CPUState *cs, int irq) cs->gicr_iactiver0 = deposit32(cs->gicr_iactiver0, irq, 1, 1); cs->gicr_ipendr0 = deposit32(cs->gicr_ipendr0, irq, 1, 0); gicv3_redist_update(cs); - } else { + } else if (irq < GICV3_LPI_INTID_START) { gicv3_gicd_active_set(cs->gic, irq); gicv3_gicd_pending_clear(cs->gic, irq); gicv3_update(cs->gic, irq, 1); + } else { + gicv3_redist_lpi_pending(cs, irq, 0); } } @@ -1318,7 +1320,8 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1, gicv3_redist_affid(cs), value); - if (irq >= cs->gic->num_irq) { + if ((irq >= cs->gic->num_irq) && + !(cs->gic->lpi_enable && (irq >= GICV3_LPI_INTID_START))) { /* This handles two cases: * 1. If software writes the ID of a spurious interrupt [ie 1020-1023] * to the GICC_EOIR, the GIC ignores that write. diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index 5beb7c4235..4164500ea9 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -384,7 +384,9 @@ static bool gicd_readl(GICv3State *s, hwaddr offset, * A3V == 1 (non-zero values of Affinity level 3 supported) * IDbits == 0xf (we support 16-bit interrupt identifiers) * DVIS == 0 (Direct virtual LPI injection not supported) - * LPIS == 0 (LPIs not supported) + * LPIS == 1 (LPIs are supported if affinity routing is enabled) + * num_LPIs == 0b00000 (bits [15:11],Number of LPIs as indicated + * by GICD_TYPER.IDbits) * MBIS == 0 (message-based SPIs not supported) * SecurityExtn == 1 if security extns supported * CPUNumber == 0 since for us ARE is always 1 @@ -399,6 +401,7 @@ static bool gicd_readl(GICv3State *s, hwaddr offset, bool sec_extn = !(s->gicd_ctlr & GICD_CTLR_DS); *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | + (s->lpi_enable << GICD_TYPER_LPIS_SHIFT) | (0xf << 19) | itlinesnumber; return true; } diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c new file mode 100644 index 0000000000..84bcbb5f56 --- /dev/null +++ b/hw/intc/arm_gicv3_its.c @@ -0,0 +1,1322 @@ +/* + * ITS emulation for a GICv3-based system + * + * Copyright Linaro.org 2021 + * + * Authors: + * Shashi Mallela <shashi.mallela@linaro.org> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at your + * option) any later version. See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "hw/qdev-properties.h" +#include "hw/intc/arm_gicv3_its_common.h" +#include "gicv3_internal.h" +#include "qom/object.h" +#include "qapi/error.h" + +typedef struct GICv3ITSClass GICv3ITSClass; +/* This is reusing the GICv3ITSState typedef from ARM_GICV3_ITS_COMMON */ +DECLARE_OBJ_CHECKERS(GICv3ITSState, GICv3ITSClass, + ARM_GICV3_ITS, TYPE_ARM_GICV3_ITS) + +struct GICv3ITSClass { + GICv3ITSCommonClass parent_class; + void (*parent_reset)(DeviceState *dev); +}; + +/* + * This is an internal enum used to distinguish between LPI triggered + * via command queue and LPI triggered via gits_translater write. + */ +typedef enum ItsCmdType { + NONE = 0, /* internal indication for GITS_TRANSLATER write */ + CLEAR = 1, + DISCARD = 2, + INTERRUPT = 3, +} ItsCmdType; + +typedef struct { + uint32_t iteh; + uint64_t itel; +} IteEntry; + +static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) +{ + uint64_t result = 0; + + switch (page_sz) { + case GITS_PAGE_SIZE_4K: + case GITS_PAGE_SIZE_16K: + result = FIELD_EX64(value, GITS_BASER, PHYADDR) << 12; + break; + + case GITS_PAGE_SIZE_64K: + result = FIELD_EX64(value, GITS_BASER, PHYADDRL_64K) << 16; + result |= FIELD_EX64(value, GITS_BASER, PHYADDRH_64K) << 48; + break; + + default: + break; + } + return result; +} + +static bool get_cte(GICv3ITSState *s, uint16_t icid, uint64_t *cte, + MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t l2t_addr; + uint64_t value; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + + if (s->ct.indirect) { + l2t_id = icid / (s->ct.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->ct.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->ct.page_sz / s->ct.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + *cte = address_space_ldq_le(as, l2t_addr + + ((icid % max_l2_entries) * GITS_CTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + } + } else { + /* Flat level table */ + *cte = address_space_ldq_le(as, s->ct.base_addr + + (icid * GITS_CTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + + return (*cte & TABLE_ENTRY_VALID_MASK) != 0; +} + +static bool update_ite(GICv3ITSState *s, uint32_t eventid, uint64_t dte, + IteEntry ite) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t itt_addr; + MemTxResult res = MEMTX_OK; + + itt_addr = (dte & GITS_DTE_ITTADDR_MASK) >> GITS_DTE_ITTADDR_SHIFT; + itt_addr <<= ITTADDR_SHIFT; /* 256 byte aligned */ + + address_space_stq_le(as, itt_addr + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))), ite.itel, MEMTXATTRS_UNSPECIFIED, + &res); + + if (res == MEMTX_OK) { + address_space_stl_le(as, itt_addr + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))) + sizeof(uint32_t), ite.iteh, + MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool get_ite(GICv3ITSState *s, uint32_t eventid, uint64_t dte, + uint16_t *icid, uint32_t *pIntid, MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t itt_addr; + bool status = false; + IteEntry ite = {}; + + itt_addr = (dte & GITS_DTE_ITTADDR_MASK) >> GITS_DTE_ITTADDR_SHIFT; + itt_addr <<= ITTADDR_SHIFT; /* 256 byte aligned */ + + ite.itel = address_space_ldq_le(as, itt_addr + + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))), MEMTXATTRS_UNSPECIFIED, + res); + + if (*res == MEMTX_OK) { + ite.iteh = address_space_ldl_le(as, itt_addr + + (eventid * (sizeof(uint64_t) + + sizeof(uint32_t))) + sizeof(uint32_t), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + if (ite.itel & TABLE_ENTRY_VALID_MASK) { + if ((ite.itel >> ITE_ENTRY_INTTYPE_SHIFT) & + GITS_TYPE_PHYSICAL) { + *pIntid = (ite.itel & ITE_ENTRY_INTID_MASK) >> + ITE_ENTRY_INTID_SHIFT; + *icid = ite.iteh & ITE_ENTRY_ICID_MASK; + status = true; + } + } + } + } + return status; +} + +static uint64_t get_dte(GICv3ITSState *s, uint32_t devid, MemTxResult *res) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t l2t_addr; + uint64_t value; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + + if (s->dt.indirect) { + l2t_id = devid / (s->dt.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->dt.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + + if (*res == MEMTX_OK) { + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->dt.page_sz / s->dt.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + value = address_space_ldq_le(as, l2t_addr + + ((devid % max_l2_entries) * GITS_DTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + } + } else { + /* Flat level table */ + value = address_space_ldq_le(as, s->dt.base_addr + + (devid * GITS_DTE_SIZE), + MEMTXATTRS_UNSPECIFIED, res); + } + + return value; +} + +/* + * This function handles the processing of following commands based on + * the ItsCmdType parameter passed:- + * 1. triggering of lpi interrupt translation via ITS INT command + * 2. triggering of lpi interrupt translation via gits_translater register + * 3. handling of ITS CLEAR command + * 4. handling of ITS DISCARD command + */ +static bool process_its_cmd(GICv3ITSState *s, uint64_t value, uint32_t offset, + ItsCmdType cmd) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid, eventid; + MemTxResult res = MEMTX_OK; + bool dte_valid; + uint64_t dte = 0; + uint32_t max_eventid; + uint16_t icid = 0; + uint32_t pIntid = 0; + bool ite_valid = false; + uint64_t cte = 0; + bool cte_valid = false; + bool result = false; + uint64_t rdbase; + + if (cmd == NONE) { + devid = offset; + } else { + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + } + + if (res != MEMTX_OK) { + return result; + } + + eventid = (value & EVENTID_MASK); + + dte = get_dte(s, devid, &res); + + if (res != MEMTX_OK) { + return result; + } + dte_valid = dte & TABLE_ENTRY_VALID_MASK; + + if (dte_valid) { + max_eventid = (1UL << (((dte >> 1U) & SIZE_MASK) + 1)); + + ite_valid = get_ite(s, eventid, dte, &icid, &pIntid, &res); + + if (res != MEMTX_OK) { + return result; + } + + if (ite_valid) { + cte_valid = get_cte(s, icid, &cte, &res); + } + + if (res != MEMTX_OK) { + return result; + } + } + + if ((devid > s->dt.maxids.max_devids) || !dte_valid || !ite_valid || + !cte_valid || (eventid > max_eventid)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes " + "devid %d or eventid %d or invalid dte %d or" + "invalid cte %d or invalid ite %d\n", + __func__, devid, eventid, dte_valid, cte_valid, + ite_valid); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + /* + * Current implementation only supports rdbase == procnum + * Hence rdbase physical address is ignored + */ + rdbase = (cte & GITS_CTE_RDBASE_PROCNUM_MASK) >> 1U; + + if (rdbase > s->gicv3->num_cpu) { + return result; + } + + if ((cmd == CLEAR) || (cmd == DISCARD)) { + gicv3_redist_process_lpi(&s->gicv3->cpu[rdbase], pIntid, 0); + } else { + gicv3_redist_process_lpi(&s->gicv3->cpu[rdbase], pIntid, 1); + } + + if (cmd == DISCARD) { + IteEntry ite = {}; + /* remove mapping from interrupt translation table */ + result = update_ite(s, eventid, dte, ite); + } + } + + return result; +} + +static bool process_mapti(GICv3ITSState *s, uint64_t value, uint32_t offset, + bool ignore_pInt) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid, eventid; + uint32_t pIntid = 0; + uint32_t max_eventid, max_Intid; + bool dte_valid; + MemTxResult res = MEMTX_OK; + uint16_t icid = 0; + uint64_t dte = 0; + IteEntry ite; + uint32_t int_spurious = INTID_SPURIOUS; + bool result = false; + + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + eventid = (value & EVENTID_MASK); + + if (!ignore_pInt) { + pIntid = ((value & pINTID_MASK) >> pINTID_SHIFT); + } + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + icid = value & ICID_MASK; + + dte = get_dte(s, devid, &res); + + if (res != MEMTX_OK) { + return result; + } + dte_valid = dte & TABLE_ENTRY_VALID_MASK; + + max_eventid = (1UL << (((dte >> 1U) & SIZE_MASK) + 1)); + + if (!ignore_pInt) { + max_Intid = (1ULL << (GICD_TYPER_IDBITS + 1)) - 1; + } + + if ((devid > s->dt.maxids.max_devids) || (icid > s->ct.maxids.max_collids) + || !dte_valid || (eventid > max_eventid) || + (!ignore_pInt && (((pIntid < GICV3_LPI_INTID_START) || + (pIntid > max_Intid)) && (pIntid != INTID_SPURIOUS)))) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes " + "devid %d or icid %d or eventid %d or pIntid %d or" + "unmapped dte %d\n", __func__, devid, icid, eventid, + pIntid, dte_valid); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + /* add ite entry to interrupt translation table */ + ite.itel = (dte_valid & TABLE_ENTRY_VALID_MASK) | + (GITS_TYPE_PHYSICAL << ITE_ENTRY_INTTYPE_SHIFT); + + if (ignore_pInt) { + ite.itel |= (eventid << ITE_ENTRY_INTID_SHIFT); + } else { + ite.itel |= (pIntid << ITE_ENTRY_INTID_SHIFT); + } + ite.itel |= (int_spurious << ITE_ENTRY_INTSP_SHIFT); + ite.iteh = icid; + + result = update_ite(s, eventid, dte, ite); + } + + return result; +} + +static bool update_cte(GICv3ITSState *s, uint16_t icid, bool valid, + uint64_t rdbase) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t value; + uint64_t l2t_addr; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + uint64_t cte = 0; + MemTxResult res = MEMTX_OK; + + if (!s->ct.valid) { + return true; + } + + if (valid) { + /* add mapping entry to collection table */ + cte = (valid & TABLE_ENTRY_VALID_MASK) | (rdbase << 1ULL); + } + + /* + * The specification defines the format of level 1 entries of a + * 2-level table, but the format of level 2 entries and the format + * of flat-mapped tables is IMPDEF. + */ + if (s->ct.indirect) { + l2t_id = icid / (s->ct.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->ct.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return false; + } + + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->ct.page_sz / s->ct.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + address_space_stq_le(as, l2t_addr + + ((icid % max_l2_entries) * GITS_CTE_SIZE), + cte, MEMTXATTRS_UNSPECIFIED, &res); + } + } else { + /* Flat level table */ + address_space_stq_le(as, s->ct.base_addr + (icid * GITS_CTE_SIZE), + cte, MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool process_mapc(GICv3ITSState *s, uint32_t offset) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint16_t icid; + uint64_t rdbase; + bool valid; + MemTxResult res = MEMTX_OK; + bool result = false; + uint64_t value; + + offset += NUM_BYTES_IN_DW; + offset += NUM_BYTES_IN_DW; + + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + icid = value & ICID_MASK; + + rdbase = (value & R_MAPC_RDBASE_MASK) >> R_MAPC_RDBASE_SHIFT; + rdbase &= RDBASE_PROCNUM_MASK; + + valid = (value & CMD_FIELD_VALID_MASK); + + if ((icid > s->ct.maxids.max_collids) || (rdbase > s->gicv3->num_cpu)) { + qemu_log_mask(LOG_GUEST_ERROR, + "ITS MAPC: invalid collection table attributes " + "icid %d rdbase %" PRIu64 "\n", icid, rdbase); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + result = update_cte(s, icid, valid, rdbase); + } + + return result; +} + +static bool update_dte(GICv3ITSState *s, uint32_t devid, bool valid, + uint8_t size, uint64_t itt_addr) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t value; + uint64_t l2t_addr; + bool valid_l2t; + uint32_t l2t_id; + uint32_t max_l2_entries; + uint64_t dte = 0; + MemTxResult res = MEMTX_OK; + + if (s->dt.valid) { + if (valid) { + /* add mapping entry to device table */ + dte = (valid & TABLE_ENTRY_VALID_MASK) | + ((size & SIZE_MASK) << 1U) | + (itt_addr << GITS_DTE_ITTADDR_SHIFT); + } + } else { + return true; + } + + /* + * The specification defines the format of level 1 entries of a + * 2-level table, but the format of level 2 entries and the format + * of flat-mapped tables is IMPDEF. + */ + if (s->dt.indirect) { + l2t_id = devid / (s->dt.page_sz / L1TABLE_ENTRY_SIZE); + + value = address_space_ldq_le(as, + s->dt.base_addr + + (l2t_id * L1TABLE_ENTRY_SIZE), + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return false; + } + + valid_l2t = (value & L2_TABLE_VALID_MASK) != 0; + + if (valid_l2t) { + max_l2_entries = s->dt.page_sz / s->dt.entry_sz; + + l2t_addr = value & ((1ULL << 51) - 1); + + address_space_stq_le(as, l2t_addr + + ((devid % max_l2_entries) * GITS_DTE_SIZE), + dte, MEMTXATTRS_UNSPECIFIED, &res); + } + } else { + /* Flat level table */ + address_space_stq_le(as, s->dt.base_addr + (devid * GITS_DTE_SIZE), + dte, MEMTXATTRS_UNSPECIFIED, &res); + } + if (res != MEMTX_OK) { + return false; + } else { + return true; + } +} + +static bool process_mapd(GICv3ITSState *s, uint64_t value, uint32_t offset) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint32_t devid; + uint8_t size; + uint64_t itt_addr; + bool valid; + MemTxResult res = MEMTX_OK; + bool result = false; + + devid = ((value & DEVID_MASK) >> DEVID_SHIFT); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + size = (value & SIZE_MASK); + + offset += NUM_BYTES_IN_DW; + value = address_space_ldq_le(as, s->cq.base_addr + offset, + MEMTXATTRS_UNSPECIFIED, &res); + + if (res != MEMTX_OK) { + return result; + } + + itt_addr = (value & ITTADDR_MASK) >> ITTADDR_SHIFT; + + valid = (value & CMD_FIELD_VALID_MASK); + + if ((devid > s->dt.maxids.max_devids) || + (size > FIELD_EX64(s->typer, GITS_TYPER, IDBITS))) { + qemu_log_mask(LOG_GUEST_ERROR, + "ITS MAPD: invalid device table attributes " + "devid %d or size %d\n", devid, size); + /* + * in this implementation, in case of error + * we ignore this command and move onto the next + * command in the queue + */ + } else { + result = update_dte(s, devid, valid, size, itt_addr); + } + + return result; +} + +/* + * Current implementation blocks until all + * commands are processed + */ +static void process_cmdq(GICv3ITSState *s) +{ + uint32_t wr_offset = 0; + uint32_t rd_offset = 0; + uint32_t cq_offset = 0; + uint64_t data; + AddressSpace *as = &s->gicv3->dma_as; + MemTxResult res = MEMTX_OK; + bool result = true; + uint8_t cmd; + int i; + + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + return; + } + + wr_offset = FIELD_EX64(s->cwriter, GITS_CWRITER, OFFSET); + + if (wr_offset > s->cq.max_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid write offset " + "%d\n", __func__, wr_offset); + return; + } + + rd_offset = FIELD_EX64(s->creadr, GITS_CREADR, OFFSET); + + if (rd_offset > s->cq.max_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid read offset " + "%d\n", __func__, rd_offset); + return; + } + + while (wr_offset != rd_offset) { + cq_offset = (rd_offset * GITS_CMDQ_ENTRY_SIZE); + data = address_space_ldq_le(as, s->cq.base_addr + cq_offset, + MEMTXATTRS_UNSPECIFIED, &res); + if (res != MEMTX_OK) { + result = false; + } + cmd = (data & CMD_MASK); + + switch (cmd) { + case GITS_CMD_INT: + res = process_its_cmd(s, data, cq_offset, INTERRUPT); + break; + case GITS_CMD_CLEAR: + res = process_its_cmd(s, data, cq_offset, CLEAR); + break; + case GITS_CMD_SYNC: + /* + * Current implementation makes a blocking synchronous call + * for every command issued earlier, hence the internal state + * is already consistent by the time SYNC command is executed. + * Hence no further processing is required for SYNC command. + */ + break; + case GITS_CMD_MAPD: + result = process_mapd(s, data, cq_offset); + break; + case GITS_CMD_MAPC: + result = process_mapc(s, cq_offset); + break; + case GITS_CMD_MAPTI: + result = process_mapti(s, data, cq_offset, false); + break; + case GITS_CMD_MAPI: + result = process_mapti(s, data, cq_offset, true); + break; + case GITS_CMD_DISCARD: + result = process_its_cmd(s, data, cq_offset, DISCARD); + break; + case GITS_CMD_INV: + case GITS_CMD_INVALL: + /* + * Current implementation doesn't cache any ITS tables, + * but the calculated lpi priority information. We only + * need to trigger lpi priority re-calculation to be in + * sync with LPI config table or pending table changes. + */ + for (i = 0; i < s->gicv3->num_cpu; i++) { + gicv3_redist_update_lpi(&s->gicv3->cpu[i]); + } + break; + default: + break; + } + if (result) { + rd_offset++; + rd_offset %= s->cq.max_entries; + s->creadr = FIELD_DP64(s->creadr, GITS_CREADR, OFFSET, rd_offset); + } else { + /* + * in this implementation, in case of dma read/write error + * we stall the command processing + */ + s->creadr = FIELD_DP64(s->creadr, GITS_CREADR, STALLED, 1); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: %x cmd processing failed\n", __func__, cmd); + break; + } + } +} + +/* + * This function extracts the ITS Device and Collection table specific + * parameters (like base_addr, size etc) from GITS_BASER register. + * It is called during ITS enable and also during post_load migration + */ +static void extract_table_params(GICv3ITSState *s) +{ + uint16_t num_pages = 0; + uint8_t page_sz_type; + uint8_t type; + uint32_t page_sz = 0; + uint64_t value; + + for (int i = 0; i < 8; i++) { + value = s->baser[i]; + + if (!value) { + continue; + } + + page_sz_type = FIELD_EX64(value, GITS_BASER, PAGESIZE); + + switch (page_sz_type) { + case 0: + page_sz = GITS_PAGE_SIZE_4K; + break; + + case 1: + page_sz = GITS_PAGE_SIZE_16K; + break; + + case 2: + case 3: + page_sz = GITS_PAGE_SIZE_64K; + break; + + default: + g_assert_not_reached(); + } + + num_pages = FIELD_EX64(value, GITS_BASER, SIZE) + 1; + + type = FIELD_EX64(value, GITS_BASER, TYPE); + + switch (type) { + + case GITS_BASER_TYPE_DEVICE: + memset(&s->dt, 0 , sizeof(s->dt)); + s->dt.valid = FIELD_EX64(value, GITS_BASER, VALID); + + if (!s->dt.valid) { + return; + } + + s->dt.page_sz = page_sz; + s->dt.indirect = FIELD_EX64(value, GITS_BASER, INDIRECT); + s->dt.entry_sz = FIELD_EX64(value, GITS_BASER, ENTRYSIZE); + + if (!s->dt.indirect) { + s->dt.max_entries = (num_pages * page_sz) / s->dt.entry_sz; + } else { + s->dt.max_entries = (((num_pages * page_sz) / + L1TABLE_ENTRY_SIZE) * + (page_sz / s->dt.entry_sz)); + } + + s->dt.maxids.max_devids = (1UL << (FIELD_EX64(s->typer, GITS_TYPER, + DEVBITS) + 1)); + + s->dt.base_addr = baser_base_addr(value, page_sz); + + break; + + case GITS_BASER_TYPE_COLLECTION: + memset(&s->ct, 0 , sizeof(s->ct)); + s->ct.valid = FIELD_EX64(value, GITS_BASER, VALID); + + /* + * GITS_TYPER.HCC is 0 for this implementation + * hence writes are discarded if ct.valid is 0 + */ + if (!s->ct.valid) { + return; + } + + s->ct.page_sz = page_sz; + s->ct.indirect = FIELD_EX64(value, GITS_BASER, INDIRECT); + s->ct.entry_sz = FIELD_EX64(value, GITS_BASER, ENTRYSIZE); + + if (!s->ct.indirect) { + s->ct.max_entries = (num_pages * page_sz) / s->ct.entry_sz; + } else { + s->ct.max_entries = (((num_pages * page_sz) / + L1TABLE_ENTRY_SIZE) * + (page_sz / s->ct.entry_sz)); + } + + if (FIELD_EX64(s->typer, GITS_TYPER, CIL)) { + s->ct.maxids.max_collids = (1UL << (FIELD_EX64(s->typer, + GITS_TYPER, CIDBITS) + 1)); + } else { + /* 16-bit CollectionId supported when CIL == 0 */ + s->ct.maxids.max_collids = (1UL << 16); + } + + s->ct.base_addr = baser_base_addr(value, page_sz); + + break; + + default: + break; + } + } +} + +static void extract_cmdq_params(GICv3ITSState *s) +{ + uint16_t num_pages = 0; + uint64_t value = s->cbaser; + + num_pages = FIELD_EX64(value, GITS_CBASER, SIZE) + 1; + + memset(&s->cq, 0 , sizeof(s->cq)); + s->cq.valid = FIELD_EX64(value, GITS_CBASER, VALID); + + if (s->cq.valid) { + s->cq.max_entries = (num_pages * GITS_PAGE_SIZE_4K) / + GITS_CMDQ_ENTRY_SIZE; + s->cq.base_addr = FIELD_EX64(value, GITS_CBASER, PHYADDR); + s->cq.base_addr <<= R_GITS_CBASER_PHYADDR_SHIFT; + } +} + +static MemTxResult gicv3_its_translation_write(void *opaque, hwaddr offset, + uint64_t data, unsigned size, + MemTxAttrs attrs) +{ + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result = true; + uint32_t devid = 0; + + switch (offset) { + case GITS_TRANSLATER: + if (s->ctlr & ITS_CTLR_ENABLED) { + devid = attrs.requester_id; + result = process_its_cmd(s, data, devid, NONE); + } + break; + default: + break; + } + + if (result) { + return MEMTX_OK; + } else { + return MEMTX_ERROR; + } +} + +static bool its_writel(GICv3ITSState *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) +{ + bool result = true; + int index; + + switch (offset) { + case GITS_CTLR: + s->ctlr |= (value & ~(s->ctlr)); + + if (s->ctlr & ITS_CTLR_ENABLED) { + extract_table_params(s); + extract_cmdq_params(s); + s->creadr = 0; + process_cmdq(s); + } + break; + case GITS_CBASER: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = deposit64(s->cbaser, 0, 32, value); + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CBASER + 4: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = deposit64(s->cbaser, 32, 32, value); + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CWRITER: + s->cwriter = deposit64(s->cwriter, 0, 32, + (value & ~R_GITS_CWRITER_RETRY_MASK)); + if (s->cwriter != s->creadr) { + process_cmdq(s); + } + break; + case GITS_CWRITER + 4: + s->cwriter = deposit64(s->cwriter, 32, 32, value); + break; + case GITS_CREADR: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = deposit64(s->creadr, 0, 32, + (value & ~R_GITS_CREADR_STALLED_MASK)); + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_CREADR + 4: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = deposit64(s->creadr, 32, 32, value); + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_BASER ... GITS_BASER + 0x3f: + /* + * IMPDEF choice:- GITS_BASERn register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + index = (offset - GITS_BASER) / 8; + + if (offset & 7) { + value <<= 32; + value &= ~GITS_BASER_RO_MASK; + s->baser[index] &= GITS_BASER_RO_MASK | MAKE_64BIT_MASK(0, 32); + s->baser[index] |= value; + } else { + value &= ~GITS_BASER_RO_MASK; + s->baser[index] &= GITS_BASER_RO_MASK | MAKE_64BIT_MASK(32, 32); + s->baser[index] |= value; + } + } + break; + case GITS_IIDR: + case GITS_IDREGS ... GITS_IDREGS + 0x2f: + /* RO registers, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + break; + default: + result = false; + break; + } + return result; +} + +static bool its_readl(GICv3ITSState *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) +{ + bool result = true; + int index; + + switch (offset) { + case GITS_CTLR: + *data = s->ctlr; + break; + case GITS_IIDR: + *data = gicv3_iidr(); + break; + case GITS_IDREGS ... GITS_IDREGS + 0x2f: + /* ID registers */ + *data = gicv3_idreg(offset - GITS_IDREGS); + break; + case GITS_TYPER: + *data = extract64(s->typer, 0, 32); + break; + case GITS_TYPER + 4: + *data = extract64(s->typer, 32, 32); + break; + case GITS_CBASER: + *data = extract64(s->cbaser, 0, 32); + break; + case GITS_CBASER + 4: + *data = extract64(s->cbaser, 32, 32); + break; + case GITS_CREADR: + *data = extract64(s->creadr, 0, 32); + break; + case GITS_CREADR + 4: + *data = extract64(s->creadr, 32, 32); + break; + case GITS_CWRITER: + *data = extract64(s->cwriter, 0, 32); + break; + case GITS_CWRITER + 4: + *data = extract64(s->cwriter, 32, 32); + break; + case GITS_BASER ... GITS_BASER + 0x3f: + index = (offset - GITS_BASER) / 8; + if (offset & 7) { + *data = extract64(s->baser[index], 32, 32); + } else { + *data = extract64(s->baser[index], 0, 32); + } + break; + default: + result = false; + break; + } + return result; +} + +static bool its_writell(GICv3ITSState *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) +{ + bool result = true; + int index; + + switch (offset) { + case GITS_BASER ... GITS_BASER + 0x3f: + /* + * IMPDEF choice:- GITS_BASERn register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + index = (offset - GITS_BASER) / 8; + s->baser[index] &= GITS_BASER_RO_MASK; + s->baser[index] |= (value & ~GITS_BASER_RO_MASK); + } + break; + case GITS_CBASER: + /* + * IMPDEF choice:- GITS_CBASER register becomes RO if ITS is + * already enabled + */ + if (!(s->ctlr & ITS_CTLR_ENABLED)) { + s->cbaser = value; + s->creadr = 0; + s->cwriter = s->creadr; + } + break; + case GITS_CWRITER: + s->cwriter = value & ~R_GITS_CWRITER_RETRY_MASK; + if (s->cwriter != s->creadr) { + process_cmdq(s); + } + break; + case GITS_CREADR: + if (s->gicv3->gicd_ctlr & GICD_CTLR_DS) { + s->creadr = value & ~R_GITS_CREADR_STALLED_MASK; + } else { + /* RO register, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + } + break; + case GITS_TYPER: + /* RO registers, ignore the write */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write to RO register at offset " + TARGET_FMT_plx "\n", __func__, offset); + break; + default: + result = false; + break; + } + return result; +} + +static bool its_readll(GICv3ITSState *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) +{ + bool result = true; + int index; + + switch (offset) { + case GITS_TYPER: + *data = s->typer; + break; + case GITS_BASER ... GITS_BASER + 0x3f: + index = (offset - GITS_BASER) / 8; + *data = s->baser[index]; + break; + case GITS_CBASER: + *data = s->cbaser; + break; + case GITS_CREADR: + *data = s->creadr; + break; + case GITS_CWRITER: + *data = s->cwriter; + break; + default: + result = false; + break; + } + return result; +} + +static MemTxResult gicv3_its_read(void *opaque, hwaddr offset, uint64_t *data, + unsigned size, MemTxAttrs attrs) +{ + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result; + + switch (size) { + case 4: + result = its_readl(s, offset, data, attrs); + break; + case 8: + result = its_readll(s, offset, data, attrs); + break; + default: + result = false; + break; + } + + if (!result) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest read at offset " TARGET_FMT_plx + "size %u\n", __func__, offset, size); + /* + * The spec requires that reserved registers are RAZ/WI; + * so use false returns from leaf functions as a way to + * trigger the guest-error logging but don't return it to + * the caller, or we'll cause a spurious guest data abort. + */ + *data = 0; + } + return MEMTX_OK; +} + +static MemTxResult gicv3_its_write(void *opaque, hwaddr offset, uint64_t data, + unsigned size, MemTxAttrs attrs) +{ + GICv3ITSState *s = (GICv3ITSState *)opaque; + bool result; + + switch (size) { + case 4: + result = its_writel(s, offset, data, attrs); + break; + case 8: + result = its_writell(s, offset, data, attrs); + break; + default: + result = false; + break; + } + + if (!result) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid guest write at offset " TARGET_FMT_plx + "size %u\n", __func__, offset, size); + /* + * The spec requires that reserved registers are RAZ/WI; + * so use false returns from leaf functions as a way to + * trigger the guest-error logging but don't return it to + * the caller, or we'll cause a spurious guest data abort. + */ + } + return MEMTX_OK; +} + +static const MemoryRegionOps gicv3_its_control_ops = { + .read_with_attrs = gicv3_its_read, + .write_with_attrs = gicv3_its_write, + .valid.min_access_size = 4, + .valid.max_access_size = 8, + .impl.min_access_size = 4, + .impl.max_access_size = 8, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const MemoryRegionOps gicv3_its_translation_ops = { + .write_with_attrs = gicv3_its_translation_write, + .valid.min_access_size = 2, + .valid.max_access_size = 4, + .impl.min_access_size = 2, + .impl.max_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) +{ + GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev); + int i; + + for (i = 0; i < s->gicv3->num_cpu; i++) { + if (!(s->gicv3->cpu[i].gicr_typer & GICR_TYPER_PLPIS)) { + error_setg(errp, "Physical LPI not supported by CPU %d", i); + return; + } + } + + gicv3_its_init_mmio(s, &gicv3_its_control_ops, &gicv3_its_translation_ops); + + address_space_init(&s->gicv3->dma_as, s->gicv3->dma, + "gicv3-its-sysmem"); + + /* set the ITS default features supported */ + s->typer = FIELD_DP64(s->typer, GITS_TYPER, PHYSICAL, + GITS_TYPE_PHYSICAL); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, ITT_ENTRY_SIZE, + ITS_ITT_ENTRY_SIZE - 1); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, IDBITS, ITS_IDBITS); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, DEVBITS, ITS_DEVBITS); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIL, 1); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIDBITS, ITS_CIDBITS); +} + +static void gicv3_its_reset(DeviceState *dev) +{ + GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev); + GICv3ITSClass *c = ARM_GICV3_ITS_GET_CLASS(s); + + c->parent_reset(dev); + + /* Quiescent bit reset to 1 */ + s->ctlr = FIELD_DP32(s->ctlr, GITS_CTLR, QUIESCENT, 1); + + /* + * setting GITS_BASER0.Type = 0b001 (Device) + * GITS_BASER1.Type = 0b100 (Collection Table) + * GITS_BASER<n>.Type,where n = 3 to 7 are 0b00 (Unimplemented) + * GITS_BASER<0,1>.Page_Size = 64KB + * and default translation table entry size to 16 bytes + */ + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, TYPE, + GITS_BASER_TYPE_DEVICE); + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, PAGESIZE, + GITS_BASER_PAGESIZE_64K); + s->baser[0] = FIELD_DP64(s->baser[0], GITS_BASER, ENTRYSIZE, + GITS_DTE_SIZE - 1); + + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, TYPE, + GITS_BASER_TYPE_COLLECTION); + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, PAGESIZE, + GITS_BASER_PAGESIZE_64K); + s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, ENTRYSIZE, + GITS_CTE_SIZE - 1); +} + +static void gicv3_its_post_load(GICv3ITSState *s) +{ + if (s->ctlr & ITS_CTLR_ENABLED) { + extract_table_params(s); + extract_cmdq_params(s); + } +} + +static Property gicv3_its_props[] = { + DEFINE_PROP_LINK("parent-gicv3", GICv3ITSState, gicv3, "arm-gicv3", + GICv3State *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void gicv3_its_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + GICv3ITSClass *ic = ARM_GICV3_ITS_CLASS(klass); + GICv3ITSCommonClass *icc = ARM_GICV3_ITS_COMMON_CLASS(klass); + + dc->realize = gicv3_arm_its_realize; + device_class_set_props(dc, gicv3_its_props); + device_class_set_parent_reset(dc, gicv3_its_reset, &ic->parent_reset); + icc->post_load = gicv3_its_post_load; +} + +static const TypeInfo gicv3_its_info = { + .name = TYPE_ARM_GICV3_ITS, + .parent = TYPE_ARM_GICV3_ITS_COMMON, + .instance_size = sizeof(GICv3ITSState), + .class_init = gicv3_its_class_init, + .class_size = sizeof(GICv3ITSClass), +}; + +static void gicv3_its_register_types(void) +{ + type_register_static(&gicv3_its_info); +} + +type_init(gicv3_its_register_types) diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c index 66c4c6a188..7d7f3882e7 100644 --- a/hw/intc/arm_gicv3_its_common.c +++ b/hw/intc/arm_gicv3_its_common.c @@ -50,6 +50,8 @@ static int gicv3_its_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_its = { .name = "arm_gicv3_its", + .version_id = 1, + .minimum_version_id = 1, .pre_save = gicv3_its_pre_save, .post_load = gicv3_its_post_load, .priority = MIG_PRI_GICV3_ITS, @@ -99,14 +101,15 @@ static const MemoryRegionOps gicv3_its_trans_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops) +void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops, + const MemoryRegionOps *tops) { SysBusDevice *sbd = SYS_BUS_DEVICE(s); memory_region_init_io(&s->iomem_its_cntrl, OBJECT(s), ops, s, "control", ITS_CONTROL_SIZE); memory_region_init_io(&s->iomem_its_translation, OBJECT(s), - &gicv3_its_trans_ops, s, + tops ? tops : &gicv3_its_trans_ops, s, "translation", ITS_TRANS_SIZE); /* Our two regions are always adjacent, therefore we now combine them diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c index b554d2ede0..0b4cbed28b 100644 --- a/hw/intc/arm_gicv3_its_kvm.c +++ b/hw/intc/arm_gicv3_its_kvm.c @@ -106,7 +106,7 @@ static void kvm_arm_its_realize(DeviceState *dev, Error **errp) kvm_arm_register_device(&s->iomem_its_cntrl, -1, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_ITS_ADDR_TYPE, s->dev_fd, 0); - gicv3_its_init_mmio(s, NULL); + gicv3_its_init_mmio(s, NULL, NULL); if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS, GITS_CTLR)) { diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index 53da703ed8..7072bfcbb1 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -248,10 +248,19 @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, case GICR_CTLR: /* For our implementation, GICR_TYPER.DPGS is 0 and so all * the DPG bits are RAZ/WI. We don't do anything asynchronously, - * so UWP and RWP are RAZ/WI. And GICR_TYPER.LPIS is 0 (we don't - * implement LPIs) so Enable_LPIs is RES0. So there are no writable - * bits for us. + * so UWP and RWP are RAZ/WI. GICR_TYPER.LPIS is 1 (we + * implement LPIs) so Enable_LPIs is programmable. */ + if (cs->gicr_typer & GICR_TYPER_PLPIS) { + if (value & GICR_CTLR_ENABLE_LPIS) { + cs->gicr_ctlr |= GICR_CTLR_ENABLE_LPIS; + /* Check for any pending interr in pending table */ + gicv3_redist_update_lpi(cs); + gicv3_redist_update(cs); + } else { + cs->gicr_ctlr &= ~GICR_CTLR_ENABLE_LPIS; + } + } return MEMTX_OK; case GICR_STATUSR: /* RAZ/WI for our implementation */ @@ -526,6 +535,144 @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, return r; } +static void gicv3_redist_check_lpi_priority(GICv3CPUState *cs, int irq) +{ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpict_baddr; + uint8_t lpite; + uint8_t prio; + + lpict_baddr = cs->gicr_propbaser & R_GICR_PROPBASER_PHYADDR_MASK; + + address_space_read(as, lpict_baddr + ((irq - GICV3_LPI_INTID_START) * + sizeof(lpite)), MEMTXATTRS_UNSPECIFIED, &lpite, + sizeof(lpite)); + + if (!(lpite & LPI_CTE_ENABLED)) { + return; + } + + if (cs->gic->gicd_ctlr & GICD_CTLR_DS) { + prio = lpite & LPI_PRIORITY_MASK; + } else { + prio = ((lpite & LPI_PRIORITY_MASK) >> 1) | 0x80; + } + + if ((prio < cs->hpplpi.prio) || + ((prio == cs->hpplpi.prio) && (irq <= cs->hpplpi.irq))) { + cs->hpplpi.irq = irq; + cs->hpplpi.prio = prio; + /* LPIs are always non-secure Grp1 interrupts */ + cs->hpplpi.grp = GICV3_G1NS; + } +} + +void gicv3_redist_update_lpi(GICv3CPUState *cs) +{ + /* + * This function scans the LPI pending table and for each pending + * LPI, reads the corresponding entry from LPI configuration table + * to extract the priority info and determine if the current LPI + * priority is lower than the last computed high priority lpi interrupt. + * If yes, replace current LPI as the new high priority lpi interrupt. + */ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpipt_baddr; + uint32_t pendt_size = 0; + uint8_t pend; + int i, bit; + uint64_t idbits; + + idbits = MIN(FIELD_EX64(cs->gicr_propbaser, GICR_PROPBASER, IDBITS), + GICD_TYPER_IDBITS); + + if (!(cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) || !cs->gicr_propbaser || + !cs->gicr_pendbaser) { + return; + } + + cs->hpplpi.prio = 0xff; + + lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; + + /* Determine the highest priority pending interrupt among LPIs */ + pendt_size = (1ULL << (idbits + 1)); + + for (i = GICV3_LPI_INTID_START / 8; i < pendt_size / 8; i++) { + address_space_read(as, lpipt_baddr + i, MEMTXATTRS_UNSPECIFIED, &pend, + sizeof(pend)); + + while (pend) { + bit = ctz32(pend); + gicv3_redist_check_lpi_priority(cs, i * 8 + bit); + pend &= ~(1 << bit); + } + } +} + +void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level) +{ + /* + * This function updates the pending bit in lpi pending table for + * the irq being activated or deactivated. + */ + AddressSpace *as = &cs->gic->dma_as; + uint64_t lpipt_baddr; + bool ispend = false; + uint8_t pend; + + /* + * get the bit value corresponding to this irq in the + * lpi pending table + */ + lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; + + address_space_read(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), + MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); + + ispend = extract32(pend, irq % 8, 1); + + /* no change in the value of pending bit, return */ + if (ispend == level) { + return; + } + pend = deposit32(pend, irq % 8, 1, level ? 1 : 0); + + address_space_write(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), + MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); + + /* + * check if this LPI is better than the current hpplpi, if yes + * just set hpplpi.prio and .irq without doing a full rescan + */ + if (level) { + gicv3_redist_check_lpi_priority(cs, irq); + } else { + if (irq == cs->hpplpi.irq) { + gicv3_redist_update_lpi(cs); + } + } +} + +void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level) +{ + uint64_t idbits; + + idbits = MIN(FIELD_EX64(cs->gicr_propbaser, GICR_PROPBASER, IDBITS), + GICD_TYPER_IDBITS); + + if (!(cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) || !cs->gicr_propbaser || + !cs->gicr_pendbaser || (irq > (1ULL << (idbits + 1)) - 1) || + irq < GICV3_LPI_INTID_START) { + return; + } + + /* set/clear the pending bit for this irq */ + gicv3_redist_lpi_pending(cs, irq, level); + + gicv3_redist_update(cs); +} + void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level) { /* Update redistributor state for a change in an external PPI input line */ diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index 05303a55c8..a0369dace7 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -24,6 +24,7 @@ #ifndef QEMU_ARM_GICV3_INTERNAL_H #define QEMU_ARM_GICV3_INTERNAL_H +#include "hw/registerfields.h" #include "hw/intc/arm_gicv3_common.h" /* Distributor registers, as offsets from the distributor base address */ @@ -67,6 +68,11 @@ #define GICD_CTLR_E1NWF (1U << 7) #define GICD_CTLR_RWP (1U << 31) +#define GICD_TYPER_LPIS_SHIFT 17 + +/* 16 bits EventId */ +#define GICD_TYPER_IDBITS 0xf + /* * Redistributor frame offsets from RD_base */ @@ -122,17 +128,19 @@ #define GICR_WAKER_ProcessorSleep (1U << 1) #define GICR_WAKER_ChildrenAsleep (1U << 2) -#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK (7ULL << 56) -#define GICR_PROPBASER_ADDR_MASK (0xfffffffffULL << 12) -#define GICR_PROPBASER_SHAREABILITY_MASK (3U << 10) -#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7) -#define GICR_PROPBASER_IDBITS_MASK (0x1f) +FIELD(GICR_PROPBASER, IDBITS, 0, 5) +FIELD(GICR_PROPBASER, INNERCACHE, 7, 3) +FIELD(GICR_PROPBASER, SHAREABILITY, 10, 2) +FIELD(GICR_PROPBASER, PHYADDR, 12, 40) +FIELD(GICR_PROPBASER, OUTERCACHE, 56, 3) + +FIELD(GICR_PENDBASER, INNERCACHE, 7, 3) +FIELD(GICR_PENDBASER, SHAREABILITY, 10, 2) +FIELD(GICR_PENDBASER, PHYADDR, 16, 36) +FIELD(GICR_PENDBASER, OUTERCACHE, 56, 3) +FIELD(GICR_PENDBASER, PTZ, 62, 1) -#define GICR_PENDBASER_PTZ (1ULL << 62) -#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK (7ULL << 56) -#define GICR_PENDBASER_ADDR_MASK (0xffffffffULL << 16) -#define GICR_PENDBASER_SHAREABILITY_MASK (3U << 10) -#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7) +#define GICR_PROPBASER_IDBITS_THRESHOLD 0xd #define ICC_CTLR_EL1_CBPR (1U << 0) #define ICC_CTLR_EL1_EOIMODE (1U << 1) @@ -239,6 +247,163 @@ #define ICH_VTR_EL2_PREBITS_SHIFT 26 #define ICH_VTR_EL2_PRIBITS_SHIFT 29 +/* ITS Registers */ + +FIELD(GITS_BASER, SIZE, 0, 8) +FIELD(GITS_BASER, PAGESIZE, 8, 2) +FIELD(GITS_BASER, SHAREABILITY, 10, 2) +FIELD(GITS_BASER, PHYADDR, 12, 36) +FIELD(GITS_BASER, PHYADDRL_64K, 16, 32) +FIELD(GITS_BASER, PHYADDRH_64K, 12, 4) +FIELD(GITS_BASER, ENTRYSIZE, 48, 5) +FIELD(GITS_BASER, OUTERCACHE, 53, 3) +FIELD(GITS_BASER, TYPE, 56, 3) +FIELD(GITS_BASER, INNERCACHE, 59, 3) +FIELD(GITS_BASER, INDIRECT, 62, 1) +FIELD(GITS_BASER, VALID, 63, 1) + +FIELD(GITS_CBASER, SIZE, 0, 8) +FIELD(GITS_CBASER, SHAREABILITY, 10, 2) +FIELD(GITS_CBASER, PHYADDR, 12, 40) +FIELD(GITS_CBASER, OUTERCACHE, 53, 3) +FIELD(GITS_CBASER, INNERCACHE, 59, 3) +FIELD(GITS_CBASER, VALID, 63, 1) + +FIELD(GITS_CREADR, STALLED, 0, 1) +FIELD(GITS_CREADR, OFFSET, 5, 15) + +FIELD(GITS_CWRITER, RETRY, 0, 1) +FIELD(GITS_CWRITER, OFFSET, 5, 15) + +FIELD(GITS_CTLR, ENABLED, 0, 1) +FIELD(GITS_CTLR, QUIESCENT, 31, 1) + +FIELD(GITS_TYPER, PHYSICAL, 0, 1) +FIELD(GITS_TYPER, ITT_ENTRY_SIZE, 4, 4) +FIELD(GITS_TYPER, IDBITS, 8, 5) +FIELD(GITS_TYPER, DEVBITS, 13, 5) +FIELD(GITS_TYPER, SEIS, 18, 1) +FIELD(GITS_TYPER, PTA, 19, 1) +FIELD(GITS_TYPER, CIDBITS, 32, 4) +FIELD(GITS_TYPER, CIL, 36, 1) + +#define GITS_IDREGS 0xFFD0 + +#define ITS_CTLR_ENABLED (1U) /* ITS Enabled */ + +#define GITS_BASER_RO_MASK (R_GITS_BASER_ENTRYSIZE_MASK | \ + R_GITS_BASER_TYPE_MASK) + +#define GITS_BASER_PAGESIZE_4K 0 +#define GITS_BASER_PAGESIZE_16K 1 +#define GITS_BASER_PAGESIZE_64K 2 + +#define GITS_BASER_TYPE_DEVICE 1ULL +#define GITS_BASER_TYPE_COLLECTION 4ULL + +#define GITS_PAGE_SIZE_4K 0x1000 +#define GITS_PAGE_SIZE_16K 0x4000 +#define GITS_PAGE_SIZE_64K 0x10000 + +#define L1TABLE_ENTRY_SIZE 8 + +#define LPI_CTE_ENABLED TABLE_ENTRY_VALID_MASK +#define LPI_PRIORITY_MASK 0xfc + +#define GITS_CMDQ_ENTRY_SIZE 32 +#define NUM_BYTES_IN_DW 8 + +#define CMD_MASK 0xff + +/* ITS Commands */ +#define GITS_CMD_CLEAR 0x04 +#define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_INT 0x03 +#define GITS_CMD_MAPC 0x09 +#define GITS_CMD_MAPD 0x08 +#define GITS_CMD_MAPI 0x0B +#define GITS_CMD_MAPTI 0x0A +#define GITS_CMD_INV 0x0C +#define GITS_CMD_INVALL 0x0D +#define GITS_CMD_SYNC 0x05 + +/* MAPC command fields */ +#define ICID_LENGTH 16 +#define ICID_MASK ((1U << ICID_LENGTH) - 1) +FIELD(MAPC, RDBASE, 16, 32) + +#define RDBASE_PROCNUM_LENGTH 16 +#define RDBASE_PROCNUM_MASK ((1ULL << RDBASE_PROCNUM_LENGTH) - 1) + +/* MAPD command fields */ +#define ITTADDR_LENGTH 44 +#define ITTADDR_SHIFT 8 +#define ITTADDR_MASK MAKE_64BIT_MASK(ITTADDR_SHIFT, ITTADDR_LENGTH) +#define SIZE_MASK 0x1f + +/* MAPI command fields */ +#define EVENTID_MASK ((1ULL << 32) - 1) + +/* MAPTI command fields */ +#define pINTID_SHIFT 32 +#define pINTID_MASK MAKE_64BIT_MASK(32, 32) + +#define DEVID_SHIFT 32 +#define DEVID_MASK MAKE_64BIT_MASK(32, 32) + +#define VALID_SHIFT 63 +#define CMD_FIELD_VALID_MASK (1ULL << VALID_SHIFT) +#define L2_TABLE_VALID_MASK CMD_FIELD_VALID_MASK +#define TABLE_ENTRY_VALID_MASK (1ULL << 0) + +/** + * Default features advertised by this version of ITS + */ +/* Physical LPIs supported */ +#define GITS_TYPE_PHYSICAL (1U << 0) + +/* + * 12 bytes Interrupt translation Table Entry size + * as per Table 5.3 in GICv3 spec + * ITE Lower 8 Bytes + * Bits: | 49 ... 26 | 25 ... 2 | 1 | 0 | + * Values: | 1023 | IntNum | IntType | Valid | + * ITE Higher 4 Bytes + * Bits: | 31 ... 16 | 15 ...0 | + * Values: | vPEID | ICID | + */ +#define ITS_ITT_ENTRY_SIZE 0xC +#define ITE_ENTRY_INTTYPE_SHIFT 1 +#define ITE_ENTRY_INTID_SHIFT 2 +#define ITE_ENTRY_INTID_MASK MAKE_64BIT_MASK(2, 24) +#define ITE_ENTRY_INTSP_SHIFT 26 +#define ITE_ENTRY_ICID_MASK MAKE_64BIT_MASK(0, 16) + +/* 16 bits EventId */ +#define ITS_IDBITS GICD_TYPER_IDBITS + +/* 16 bits DeviceId */ +#define ITS_DEVBITS 0xF + +/* 16 bits CollectionId */ +#define ITS_CIDBITS 0xF + +/* + * 8 bytes Device Table Entry size + * Valid = 1 bit,ITTAddr = 44 bits,Size = 5 bits + */ +#define GITS_DTE_SIZE (0x8ULL) +#define GITS_DTE_ITTADDR_SHIFT 6 +#define GITS_DTE_ITTADDR_MASK MAKE_64BIT_MASK(GITS_DTE_ITTADDR_SHIFT, \ + ITTADDR_LENGTH) + +/* + * 8 bytes Collection Table Entry size + * Valid = 1 bit,RDBase = 36 bits(considering max RDBASE) + */ +#define GITS_CTE_SIZE (0x8ULL) +#define GITS_CTE_RDBASE_PROCNUM_MASK MAKE_64BIT_MASK(1, RDBASE_PROCNUM_LENGTH) + /* Special interrupt IDs */ #define INTID_SECURE 1020 #define INTID_NONSECURE 1021 @@ -296,6 +461,9 @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs); void gicv3_dist_set_irq(GICv3State *s, int irq, int level); void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level); +void gicv3_redist_update_lpi(GICv3CPUState *cs); void gicv3_redist_send_sgi(GICv3CPUState *cs, int grp, int irq, bool ns); void gicv3_init_cpuif(GICv3State *s); diff --git a/hw/intc/meson.build b/hw/intc/meson.build index 6e52a166e3..4dcfea6aa8 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -8,6 +8,7 @@ softmmu_ss.add(when: 'CONFIG_ARM_GIC', if_true: files( 'arm_gicv3_dist.c', 'arm_gicv3_its_common.c', 'arm_gicv3_redist.c', + 'arm_gicv3_its.c', )) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_pic.c')) softmmu_ss.add(when: 'CONFIG_HEATHROW_PIC', if_true: files('heathrow_pic.c')) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index 5086e6b7ed..8b70285961 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -269,6 +269,21 @@ static uint64_t zynq_slcr_compute_clock(const uint64_t periods[], zynq_slcr_compute_clock((plls), (state)->regs[reg], \ reg ## _ ## enable_field ## _SHIFT) +static void zynq_slcr_compute_clocks_internal(ZynqSLCRState *s, uint64_t ps_clk) +{ + uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); + uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); + uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); + + uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; + + /* compute uartX reference clocks */ + clock_set(s->uart0_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); + clock_set(s->uart1_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); +} + /** * Compute and set the ouputs clocks periods. * But do not propagate them further. Connected clocks @@ -283,17 +298,7 @@ static void zynq_slcr_compute_clocks(ZynqSLCRState *s) ps_clk = 0; } - uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); - uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); - uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); - - uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; - - /* compute uartX reference clocks */ - clock_set(s->uart0_ref_clk, - ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); - clock_set(s->uart1_ref_clk, - ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); + zynq_slcr_compute_clocks_internal(s, ps_clk); } /** @@ -416,7 +421,7 @@ static void zynq_slcr_reset_hold(Object *obj) ZynqSLCRState *s = ZYNQ_SLCR(obj); /* will disable all output clocks */ - zynq_slcr_compute_clocks(s); + zynq_slcr_compute_clocks_internal(s, 0); zynq_slcr_propagate_clocks(s); } @@ -425,7 +430,7 @@ static void zynq_slcr_reset_exit(Object *obj) ZynqSLCRState *s = ZYNQ_SLCR(obj); /* will compute output clocks according to ps_clk and registers */ - zynq_slcr_compute_clocks(s); + zynq_slcr_compute_clocks_internal(s, clock_get(s->ps_clk)); zynq_slcr_propagate_clocks(s); } diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c index 470205f487..d4685709a3 100644 --- a/hw/vfio/igd.c +++ b/hw/vfio/igd.c @@ -557,7 +557,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) * must allocate a 1MB aligned reserved memory region below 4GB with * the requested size (in bytes) for use by the Intel PCI class VGA * device at VM address 00:02.0. The base address of this reserved - * memory region must be written to the device BDSM regsiter at PCI + * memory region must be written to the device BDSM register at PCI * config offset 0x5C. */ bdsm_size = g_malloc(sizeof(*bdsm_size)); diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index e21a6ede11..0cf69a8c6d 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -1356,7 +1356,7 @@ static bool vfio_radeon_smc_is_running(VFIOPCIDevice *vdev) /* * The scope of a config reset is controlled by a mode bit in the misc register * and a fuse, exposed as a bit in another register. The fuse is the default - * (0 = GFX, 1 = whole GPU), the misc bit is a toggle, with the forumula + * (0 = GFX, 1 = whole GPU), the misc bit is a toggle, with the formula * scope = !(misc ^ fuse), where the resulting scope is defined the same as * the fuse. A truth table therefore tells us that if misc == fuse, we need * to flip the value of the bit in the misc register. diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index e1ea1d8a23..4feaa1cb68 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1364,7 +1364,7 @@ static void vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp) * TODO: Lookup table for known devices. * * Logically we might use an algorithm here to select the BAR adding - * the least additional MMIO space, but we cannot programatically + * the least additional MMIO space, but we cannot programmatically * predict the driver dependency on BAR ordering or sizing, therefore * 'auto' becomes a lookup for combinations reported to work. */ @@ -2158,7 +2158,7 @@ static void vfio_pci_pre_reset(VFIOPCIDevice *vdev) } /* - * Stop any ongoing DMA by disconecting I/O, MMIO, and bus master. + * Stop any ongoing DMA by disconnecting I/O, MMIO, and bus master. * Also put INTx Disable in known state. */ cmd = vfio_pci_read_config(pdev, PCI_COMMAND, 2); @@ -2384,7 +2384,7 @@ out_single: } /* - * We want to differentiate hot reset of mulitple in-use devices vs hot reset + * We want to differentiate hot reset of multiple in-use devices vs hot reset * of a single in-use device. VFIO_DEVICE_RESET will already handle the case * of doing hot resets when there is only a single device per bus. The in-use * here refers to how many VFIODevices are affected. A hot reset that affects diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index cc3f66f7e4..f8f08a0f36 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -156,7 +156,7 @@ static void vfio_mmap_set_enabled(VFIOPlatformDevice *vdev, bool enabled) * if there is no more active IRQ * @opaque: actually points to the VFIO platform device * - * Called on mmap timer timout, this function checks whether the + * Called on mmap timer timeout, this function checks whether the * IRQ is still active and if not, restores the fast path. * by construction a single eventfd is handled at a time. * if the IRQ is still active, the timer is re-programmed. diff --git a/include/block/block_int.h b/include/block/block_int.h index f1a54db0f8..5451f89b8d 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -34,6 +34,7 @@ #include "qemu/hbitmap.h" #include "block/snapshot.h" #include "qemu/throttle.h" +#include "qemu/rcu.h" #define BLOCK_FLAG_LAZY_REFCOUNTS 8 @@ -347,6 +348,15 @@ struct BlockDriver { * clamped to bdrv_getlength() and aligned to request_alignment, * as well as non-NULL pnum, map, and file; in turn, the driver * must return an error or set pnum to an aligned non-zero value. + * + * Note that @bytes is just a hint on how big of a region the + * caller wants to inspect. It is not a limit on *pnum. + * Implementations are free to return larger values of *pnum if + * doing so does not incur a performance penalty. + * + * block/io.c's bdrv_co_block_status() will utilize an unclamped + * *pnum value for the block-status cache on protocol nodes, prior + * to clamping *pnum for return to its caller. */ int coroutine_fn (*bdrv_co_block_status)(BlockDriverState *bs, bool want_zero, int64_t offset, int64_t bytes, int64_t *pnum, @@ -840,11 +850,23 @@ struct BdrvChild { }; /* - * Note: the function bdrv_append() copies and swaps contents of - * BlockDriverStates, so if you add new fields to this struct, please - * inspect bdrv_append() to determine if the new fields need to be - * copied as well. + * Allows bdrv_co_block_status() to cache one data region for a + * protocol node. + * + * @valid: Whether the cache is valid (should be accessed with atomic + * functions so this can be reset by RCU readers) + * @data_start: Offset where we know (or strongly assume) is data + * @data_end: Offset where the data region ends (which is not necessarily + * the start of a zeroed region) */ +typedef struct BdrvBlockStatusCache { + struct rcu_head rcu; + + bool valid; + int64_t data_start; + int64_t data_end; +} BdrvBlockStatusCache; + struct BlockDriverState { /* Protected by big QEMU lock or read-only after opening. No special * locking needed during I/O... @@ -1010,6 +1032,11 @@ struct BlockDriverState { /* BdrvChild links to this node may never be frozen */ bool never_freeze; + + /* Lock for block-status cache RCU writers */ + CoMutex bsc_modify_lock; + /* Always non-NULL, but must only be dereferenced under an RCU read guard */ + BdrvBlockStatusCache *block_status_cache; }; struct BlockBackendRootState { @@ -1435,4 +1462,30 @@ static inline BlockDriverState *bdrv_primary_bs(BlockDriverState *bs) */ void bdrv_drain_all_end_quiesce(BlockDriverState *bs); +/** + * Check whether the given offset is in the cached block-status data + * region. + * + * If it is, and @pnum is not NULL, *pnum is set to + * `bsc.data_end - offset`, i.e. how many bytes, starting from + * @offset, are data (according to the cache). + * Otherwise, *pnum is not touched. + */ +bool bdrv_bsc_is_data(BlockDriverState *bs, int64_t offset, int64_t *pnum); + +/** + * If [offset, offset + bytes) overlaps with the currently cached + * block-status region, invalidate the cache. + * + * (To be used by I/O paths that cause data regions to be zero or + * holes.) + */ +void bdrv_bsc_invalidate_range(BlockDriverState *bs, + int64_t offset, int64_t bytes); + +/** + * Mark the range [offset, offset + bytes) as a data region. + */ +void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes); + #endif /* BLOCK_INT_H */ diff --git a/include/chardev/char.h b/include/chardev/char.h index 7c0444f90d..a319b5fdff 100644 --- a/include/chardev/char.h +++ b/include/chardev/char.h @@ -254,26 +254,58 @@ struct ChardevClass { bool internal; /* TODO: eventually use TYPE_USER_CREATABLE */ bool supports_yank; + + /* parse command line options and populate QAPI @backend */ void (*parse)(QemuOpts *opts, ChardevBackend *backend, Error **errp); + /* called after construction, open/starts the backend */ void (*open)(Chardev *chr, ChardevBackend *backend, bool *be_opened, Error **errp); + /* write buf to the backend */ int (*chr_write)(Chardev *s, const uint8_t *buf, int len); + + /* + * Read from the backend (blocking). A typical front-end will instead rely + * on chr_can_read/chr_read being called when polling/looping. + */ int (*chr_sync_read)(Chardev *s, const uint8_t *buf, int len); + + /* create a watch on the backend */ GSource *(*chr_add_watch)(Chardev *s, GIOCondition cond); + + /* update the backend internal sources */ void (*chr_update_read_handler)(Chardev *s); + + /* send an ioctl to the backend */ int (*chr_ioctl)(Chardev *s, int cmd, void *arg); + + /* get ancillary-received fds during last read */ int (*get_msgfds)(Chardev *s, int* fds, int num); + + /* set ancillary fds to be sent with next write */ int (*set_msgfds)(Chardev *s, int *fds, int num); + + /* accept the given fd */ int (*chr_add_client)(Chardev *chr, int fd); + + /* wait for a connection */ int (*chr_wait_connected)(Chardev *chr, Error **errp); + + /* disconnect a connection */ void (*chr_disconnect)(Chardev *chr); + + /* called by frontend when it can read */ void (*chr_accept_input)(Chardev *chr); + + /* set terminal echo */ void (*chr_set_echo)(Chardev *chr, bool echo); + + /* notify the backend of frontend open state */ void (*chr_set_fe_open)(Chardev *chr, int fe_open); + + /* handle various events */ void (*chr_be_event)(Chardev *s, QEMUChrEvent event); - void (*chr_options_parsed)(Chardev *chr); }; Chardev *qemu_chardev_new(const char *id, const char *typename, diff --git a/include/exec/translate-all.h b/include/exec/translate-all.h index a557b4e2bb..9f646389af 100644 --- a/include/exec/translate-all.h +++ b/include/exec/translate-all.h @@ -33,6 +33,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end); void tb_check_watchpoint(CPUState *cpu, uintptr_t retaddr); #ifdef CONFIG_USER_ONLY +void page_protect(tb_page_addr_t page_addr); int page_unprotect(target_ulong address, uintptr_t pc); #endif diff --git a/include/exec/translator.h b/include/exec/translator.h index d318803267..9bc46eda59 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -23,6 +23,7 @@ #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/plugin-gen.h" +#include "exec/translate-all.h" #include "tcg/tcg.h" @@ -74,6 +75,17 @@ typedef struct DisasContextBase { int num_insns; int max_insns; bool singlestep_enabled; +#ifdef CONFIG_USER_ONLY + /* + * Guest address of the last byte of the last protected page. + * + * Pages containing the translated instructions are made non-writable in + * order to achieve consistency in case another thread is modifying the + * code while translate_insn() fetches the instruction bytes piecemeal. + * Such writer threads are blocked on mmap_lock() in page_unprotect(). + */ + target_ulong page_protect_end; +#endif } DisasContextBase; /** @@ -156,27 +168,23 @@ bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest); */ #define GEN_TRANSLATOR_LD(fullname, type, load_fn, swap_fn) \ - static inline type \ - fullname ## _swap(CPUArchState *env, abi_ptr pc, bool do_swap) \ + type fullname ## _swap(CPUArchState *env, DisasContextBase *dcbase, \ + abi_ptr pc, bool do_swap); \ + static inline type fullname(CPUArchState *env, \ + DisasContextBase *dcbase, abi_ptr pc) \ { \ - type ret = load_fn(env, pc); \ - if (do_swap) { \ - ret = swap_fn(ret); \ - } \ - plugin_insn_append(&ret, sizeof(ret)); \ - return ret; \ - } \ - \ - static inline type fullname(CPUArchState *env, abi_ptr pc) \ - { \ - return fullname ## _swap(env, pc, false); \ + return fullname ## _swap(env, dcbase, pc, false); \ } -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) +#define FOR_EACH_TRANSLATOR_LD(F) \ + F(translator_ldub, uint8_t, cpu_ldub_code, /* no swap */) \ + F(translator_ldsw, int16_t, cpu_ldsw_code, bswap16) \ + F(translator_lduw, uint16_t, cpu_lduw_code, bswap16) \ + F(translator_ldl, uint32_t, cpu_ldl_code, bswap32) \ + F(translator_ldq, uint64_t, cpu_ldq_code, bswap64) + +FOR_EACH_TRANSLATOR_LD(GEN_TRANSLATOR_LD) + #undef GEN_TRANSLATOR_LD #endif /* EXEC__TRANSLATOR_H */ diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index 9661c46699..b461b8d261 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -120,6 +120,7 @@ struct VirtMachineClass { MachineClass parent; bool disallow_affinity_adjustment; bool no_its; + bool no_tcg_its; bool no_pmu; bool claim_edge_triggered_timers; bool smbios_old_sys_ver; @@ -141,6 +142,7 @@ struct VirtMachineState { bool highmem; bool highmem_ecam; bool its; + bool tcg_its; bool virt; bool ras; bool mte; diff --git a/include/hw/core/tcg-cpu-ops.h b/include/hw/core/tcg-cpu-ops.h index eab27d0c03..55123cb4d2 100644 --- a/include/hw/core/tcg-cpu-ops.h +++ b/include/hw/core/tcg-cpu-ops.h @@ -35,16 +35,6 @@ struct TCGCPUOps { void (*cpu_exec_enter)(CPUState *cpu); /** @cpu_exec_exit: Callback for cpu_exec cleanup */ void (*cpu_exec_exit)(CPUState *cpu); - /** @cpu_exec_interrupt: Callback for processing interrupts in cpu_exec */ - bool (*cpu_exec_interrupt)(CPUState *cpu, int interrupt_request); - /** - * @do_interrupt: Callback for interrupt handling. - * - * note that this is in general SOFTMMU only, but it actually isn't - * because of an x86 hack (accel/tcg/cpu-exec.c), so we cannot put it - * in the SOFTMMU section in general. - */ - void (*do_interrupt)(CPUState *cpu); /** * @tlb_fill: Handle a softmmu tlb miss or user-only address fault * @@ -61,7 +51,23 @@ struct TCGCPUOps { void (*debug_excp_handler)(CPUState *cpu); #ifdef NEED_CPU_H +#if defined(CONFIG_USER_ONLY) && defined(TARGET_I386) + /** + * @fake_user_interrupt: Callback for 'fake exception' handling. + * + * Simulate 'fake exception' which will be handled outside the + * cpu execution loop (hack for x86 user mode). + */ + void (*fake_user_interrupt)(CPUState *cpu); +#else + /** + * @do_interrupt: Callback for interrupt handling. + */ + void (*do_interrupt)(CPUState *cpu); +#endif /* !CONFIG_USER_ONLY || !TARGET_I386 */ #ifdef CONFIG_SOFTMMU + /** @cpu_exec_interrupt: Callback for processing interrupts in cpu_exec */ + bool (*cpu_exec_interrupt)(CPUState *cpu, int interrupt_request); /** * @do_transaction_failed: Callback for handling failed memory transactions * (ie bus faults or external aborts; not MMU faults) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index 91491a2f66..aa4f0d6770 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -36,6 +36,8 @@ #define GICV3_MAXIRQ 1020 #define GICV3_MAXSPI (GICV3_MAXIRQ - GIC_INTERNAL) +#define GICV3_LPI_INTID_START 8192 + #define GICV3_REDIST_SIZE 0x20000 /* Number of SGI target-list bits */ @@ -202,6 +204,13 @@ struct GICv3CPUState { * real state above; it doesn't need to be migrated. */ PendingIrq hppi; + + /* + * Cached information recalculated from LPI tables + * in guest memory + */ + PendingIrq hpplpi; + /* This is temporary working state, to avoid a malloc in gicv3_update() */ bool seenbetter; }; @@ -219,6 +228,7 @@ struct GICv3State { uint32_t num_cpu; uint32_t num_irq; uint32_t revision; + bool lpi_enable; bool security_extn; bool irq_reset_nonsecure; bool gicd_no_migration_shift_bug; @@ -226,6 +236,9 @@ struct GICv3State { int dev_fd; /* kvm device fd if backed by kvm vgic support */ Error *migration_blocker; + MemoryRegion *dma; + AddressSpace dma_as; + /* Distributor */ /* for a GIC with the security extensions the NS banked version of this diff --git a/include/hw/intc/arm_gicv3_its_common.h b/include/hw/intc/arm_gicv3_its_common.h index 5a0952b404..4e79145dde 100644 --- a/include/hw/intc/arm_gicv3_its_common.h +++ b/include/hw/intc/arm_gicv3_its_common.h @@ -25,17 +25,41 @@ #include "hw/intc/arm_gicv3_common.h" #include "qom/object.h" +#define TYPE_ARM_GICV3_ITS "arm-gicv3-its" + #define ITS_CONTROL_SIZE 0x10000 #define ITS_TRANS_SIZE 0x10000 #define ITS_SIZE (ITS_CONTROL_SIZE + ITS_TRANS_SIZE) #define GITS_CTLR 0x0 #define GITS_IIDR 0x4 +#define GITS_TYPER 0x8 #define GITS_CBASER 0x80 #define GITS_CWRITER 0x88 #define GITS_CREADR 0x90 #define GITS_BASER 0x100 +#define GITS_TRANSLATER 0x0040 + +typedef struct { + bool valid; + bool indirect; + uint16_t entry_sz; + uint32_t page_sz; + uint32_t max_entries; + union { + uint32_t max_devids; + uint32_t max_collids; + } maxids; + uint64_t base_addr; +} TableDesc; + +typedef struct { + bool valid; + uint32_t max_entries; + uint64_t base_addr; +} CmdQDesc; + struct GICv3ITSState { SysBusDevice parent_obj; @@ -52,17 +76,23 @@ struct GICv3ITSState { /* Registers */ uint32_t ctlr; uint32_t iidr; + uint64_t typer; uint64_t cbaser; uint64_t cwriter; uint64_t creadr; uint64_t baser[8]; + TableDesc dt; + TableDesc ct; + CmdQDesc cq; + Error *migration_blocker; }; typedef struct GICv3ITSState GICv3ITSState; -void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops); +void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops, + const MemoryRegionOps *tops); #define TYPE_ARM_GICV3_ITS_COMMON "arm-gicv3-its-common" typedef struct GICv3ITSCommonClass GICv3ITSCommonClass; diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index bafc311bfa..34c8a7506a 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -264,6 +264,7 @@ struct BusState { HotplugHandler *hotplug_handler; int max_index; bool realized; + bool full; int num_children; /* @@ -597,6 +598,10 @@ void qdev_init_gpio_in(DeviceState *dev, qemu_irq_handler handler, int n); * * See qdev_connect_gpio_out() for how code that uses such a device * can connect to one of its output GPIO lines. + * + * There is no need to release the @pins allocated array because it + * will be automatically released when @dev calls its instance_finalize() + * handler. */ void qdev_init_gpio_out(DeviceState *dev, qemu_irq *pins, int n); /** @@ -798,6 +803,29 @@ static inline bool qbus_is_hotpluggable(BusState *bus) return bus->hotplug_handler; } +/** + * qbus_mark_full: Mark this bus as full, so no more devices can be attached + * @bus: Bus to mark as full + * + * By default, QEMU will allow devices to be plugged into a bus up + * to the bus class's device count limit. Calling this function + * marks a particular bus as full, so that no more devices can be + * plugged into it. In particular this means that the bus will not + * be considered as a candidate for plugging in devices created by + * the user on the commandline or via the monitor. + * If a machine has multiple buses of a given type, such as I2C, + * where some of those buses in the real hardware are used only for + * internal devices and some are exposed via expansion ports, you + * can use this function to mark the internal-only buses as full + * after you have created all their internal devices. Then user + * created devices will appear on the expansion-port bus where + * guest software expects them. + */ +static inline void qbus_mark_full(BusState *bus) +{ + bus->full = true; +} + void device_listener_register(DeviceListener *listener); void device_listener_unregister(DeviceListener *listener); diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index 2a654f350c..0545a6224c 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -843,7 +843,6 @@ static inline void tcg_gen_plugin_cb_end(void) #if TARGET_LONG_BITS == 32 #define tcg_temp_new() tcg_temp_new_i32() -#define tcg_global_reg_new tcg_global_reg_new_i32 #define tcg_global_mem_new tcg_global_mem_new_i32 #define tcg_temp_local_new() tcg_temp_local_new_i32() #define tcg_temp_free tcg_temp_free_i32 @@ -851,7 +850,6 @@ static inline void tcg_gen_plugin_cb_end(void) #define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i32 #else #define tcg_temp_new() tcg_temp_new_i64() -#define tcg_global_reg_new tcg_global_reg_new_i64 #define tcg_global_mem_new tcg_global_mem_new_i64 #define tcg_temp_local_new() tcg_temp_local_new_i64() #define tcg_temp_free tcg_temp_free_i64 diff --git a/include/ui/console.h b/include/ui/console.h index 3be21497a2..244664d727 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -168,6 +168,9 @@ typedef struct QemuDmaBuf { uint64_t modifier; uint32_t texture; bool y0_top; + void *sync; + int fence_fd; + bool allow_fences; } QemuDmaBuf; typedef struct DisplayState DisplayState; diff --git a/include/ui/egl-helpers.h b/include/ui/egl-helpers.h index f1bf8f97fc..2fb6e0dd6b 100644 --- a/include/ui/egl-helpers.h +++ b/include/ui/egl-helpers.h @@ -19,6 +19,7 @@ typedef struct egl_fb { GLuint texture; GLuint framebuffer; bool delete_texture; + QemuDmaBuf *dmabuf; } egl_fb; void egl_fb_destroy(egl_fb *fb); @@ -45,6 +46,8 @@ int egl_get_fd_for_texture(uint32_t tex_id, EGLint *stride, EGLint *fourcc, void egl_dmabuf_import_texture(QemuDmaBuf *dmabuf); void egl_dmabuf_release_texture(QemuDmaBuf *dmabuf); +void egl_dmabuf_create_sync(QemuDmaBuf *dmabuf); +void egl_dmabuf_create_fence(QemuDmaBuf *dmabuf); #endif diff --git a/include/ui/gtk.h b/include/ui/gtk.h index 7835ef1a71..7d22affd38 100644 --- a/include/ui/gtk.h +++ b/include/ui/gtk.h @@ -155,6 +155,7 @@ extern bool gtk_use_gl_area; /* ui/gtk.c */ void gd_update_windowsize(VirtualConsole *vc); int gd_monitor_update_interval(GtkWidget *widget); +void gd_hw_gl_flushed(void *vc); /* ui/gtk-egl.c */ void gd_egl_init(VirtualConsole *vc); @@ -181,8 +182,8 @@ void gd_egl_cursor_dmabuf(DisplayChangeListener *dcl, uint32_t hot_x, uint32_t hot_y); void gd_egl_cursor_position(DisplayChangeListener *dcl, uint32_t pos_x, uint32_t pos_y); -void gd_egl_release_dmabuf(DisplayChangeListener *dcl, - QemuDmaBuf *dmabuf); +void gd_egl_flush(DisplayChangeListener *dcl, + uint32_t x, uint32_t y, uint32_t w, uint32_t h); void gd_egl_scanout_flush(DisplayChangeListener *dcl, uint32_t x, uint32_t y, uint32_t w, uint32_t h); void gtk_egl_init(DisplayGLMode mode); diff --git a/linux-user/main.c b/linux-user/main.c index 5ce17e423d..16def5215d 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -125,13 +125,6 @@ const char *qemu_uname_release; by remapping the process stack directly at the right place */ unsigned long guest_stack_size = 8 * 1024 * 1024UL; -#if defined(TARGET_I386) -int cpu_get_pic_interrupt(CPUX86State *env) -{ - return -1; -} -#endif - /***********************************************************/ /* Helper routines for implementing atomic operations. */ diff --git a/meson.build b/meson.build index 7d7d14a4bc..2711cbb789 100644 --- a/meson.build +++ b/meson.build @@ -78,7 +78,7 @@ endif accelerator_targets = { 'CONFIG_KVM': kvm_targets } if cpu in ['x86', 'x86_64', 'arm', 'aarch64'] - # i368 emulator provides xenpv machine type for multiple architectures + # i386 emulator provides xenpv machine type for multiple architectures accelerator_targets += { 'CONFIG_XEN': ['i386-softmmu', 'x86_64-softmmu'], } diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx index b3620f29e5..4c4d94ab22 100644 --- a/qemu-img-cmds.hx +++ b/qemu-img-cmds.hx @@ -46,7 +46,7 @@ SRST ERST DEF("convert", img_convert, - "convert [--object objectdef] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps] [-U] [-C] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file] [-o options] [-l snapshot_param] [-S sparse_size] [-r rate_limit] [-m num_coroutines] [-W] [--salvage] filename [filename2 [...]] output_filename") + "convert [--object objectdef] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps] [-U] [-C] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file [-F backing_fmt]] [-o options] [-l snapshot_param] [-S sparse_size] [-r rate_limit] [-m num_coroutines] [-W] [--salvage] filename [filename2 [...]] output_filename") SRST .. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-r RATE_LIMIT] [-m NUM_COROUTINES] [-W] [--salvage] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME ERST diff --git a/qemu-img.c b/qemu-img.c index d77f3e76a9..f036a1d428 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -2183,7 +2183,8 @@ static int img_convert(int argc, char **argv) int c, bs_i, flags, src_flags = BDRV_O_NO_SHARE; const char *fmt = NULL, *out_fmt = NULL, *cache = "unsafe", *src_cache = BDRV_DEFAULT_CACHE, *out_baseimg = NULL, - *out_filename, *out_baseimg_param, *snapshot_name = NULL; + *out_filename, *out_baseimg_param, *snapshot_name = NULL, + *backing_fmt = NULL; BlockDriver *drv = NULL, *proto_drv = NULL; BlockDriverInfo bdi; BlockDriverState *out_bs; @@ -2223,7 +2224,7 @@ static int img_convert(int argc, char **argv) {"skip-broken-bitmaps", no_argument, 0, OPTION_SKIP_BROKEN}, {0, 0, 0, 0} }; - c = getopt_long(argc, argv, ":hf:O:B:Cco:l:S:pt:T:qnm:WUr:", + c = getopt_long(argc, argv, ":hf:O:B:CcF:o:l:S:pt:T:qnm:WUr:", long_options, NULL); if (c == -1) { break; @@ -2253,6 +2254,9 @@ static int img_convert(int argc, char **argv) case 'c': s.compressed = true; break; + case 'F': + backing_fmt = optarg; + break; case 'o': if (accumulate_options(&options, optarg) < 0) { goto fail_getopt; @@ -2521,7 +2525,7 @@ static int img_convert(int argc, char **argv) qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s.total_sectors * BDRV_SECTOR_SIZE, &error_abort); - ret = add_old_style_options(out_fmt, opts, out_baseimg, NULL); + ret = add_old_style_options(out_fmt, opts, out_baseimg, backing_fmt); if (ret < 0) { goto out; } @@ -2628,6 +2632,14 @@ static int img_convert(int argc, char **argv) goto out; } + if (flags & BDRV_O_NOCACHE) { + /* + * If we open the target with O_DIRECT, it may be necessary to + * extend its size to align to the physical sector size. + */ + flags |= BDRV_O_RESIZE; + } + if (skip_create) { s.target = img_open(tgt_image_opts, out_filename, out_fmt, flags, writethrough, s.quiet, false); diff --git a/scripts/simplebench/img_bench_templater.py b/scripts/simplebench/img_bench_templater.py new file mode 100755 index 0000000000..f8e1540ada --- /dev/null +++ b/scripts/simplebench/img_bench_templater.py @@ -0,0 +1,95 @@ +#!/usr/bin/env python3 +# +# Process img-bench test templates +# +# Copyright (c) 2021 Virtuozzo International GmbH. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + + +import sys +import subprocess +import re +import json + +import simplebench +from results_to_text import results_to_text +from table_templater import Templater + + +def bench_func(env, case): + test = templater.gen(env['data'], case['data']) + + p = subprocess.run(test, shell=True, stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, universal_newlines=True) + + if p.returncode == 0: + try: + m = re.search(r'Run completed in (\d+.\d+) seconds.', p.stdout) + return {'seconds': float(m.group(1))} + except Exception: + return {'error': f'failed to parse qemu-img output: {p.stdout}'} + else: + return {'error': f'qemu-img failed: {p.returncode}: {p.stdout}'} + + +if __name__ == '__main__': + if len(sys.argv) > 1: + print(""" +Usage: img_bench_templater.py < path/to/test-template.sh + +This script generates performance tests from a test template (example below), +runs them, and displays the results in a table. The template is read from +stdin. It must be written in bash and end with a `qemu-img bench` invocation +(whose result is parsed to get the test instance’s result). + +Use the following syntax in the template to create the various different test +instances: + + column templating: {var1|var2|...} - test will use different values in + different columns. You may use several {} constructions in the test, in this + case product of all choice-sets will be used. + + row templating: [var1|var2|...] - similar thing to define rows (test-cases) + +Test template example: + +Assume you want to compare two qemu-img binaries, called qemu-img-old and +qemu-img-new in your build directory in two test-cases with 4K writes and 64K +writes. The template may look like this: + +qemu_img=/path/to/qemu/build/qemu-img-{old|new} +$qemu_img create -f qcow2 /ssd/x.qcow2 1G +$qemu_img bench -c 100 -d 8 [-s 4K|-s 64K] -w -t none -n /ssd/x.qcow2 + +When passing this to stdin of img_bench_templater.py, the resulting comparison +table will contain two columns (for two binaries) and two rows (for two +test-cases). + +In addition to displaying the results, script also stores results in JSON +format into results.json file in current directory. +""") + sys.exit() + + templater = Templater(sys.stdin.read()) + + envs = [{'id': ' / '.join(x), 'data': x} for x in templater.columns] + cases = [{'id': ' / '.join(x), 'data': x} for x in templater.rows] + + result = simplebench.bench(bench_func, envs, cases, count=5, + initial_run=False) + print(results_to_text(result)) + with open('results.json', 'w') as f: + json.dump(result, f, indent=4) diff --git a/scripts/simplebench/table_templater.py b/scripts/simplebench/table_templater.py new file mode 100644 index 0000000000..950f3b3024 --- /dev/null +++ b/scripts/simplebench/table_templater.py @@ -0,0 +1,62 @@ +# Parser for test templates +# +# Copyright (c) 2021 Virtuozzo International GmbH. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import itertools +from lark import Lark + +grammar = """ +start: ( text | column_switch | row_switch )+ + +column_switch: "{" text ["|" text]+ "}" +row_switch: "[" text ["|" text]+ "]" +text: /[^|{}\[\]]+/ +""" + +parser = Lark(grammar) + +class Templater: + def __init__(self, template): + self.tree = parser.parse(template) + + c_switches = [] + r_switches = [] + for x in self.tree.children: + if x.data == 'column_switch': + c_switches.append([el.children[0].value for el in x.children]) + elif x.data == 'row_switch': + r_switches.append([el.children[0].value for el in x.children]) + + self.columns = list(itertools.product(*c_switches)) + self.rows = list(itertools.product(*r_switches)) + + def gen(self, column, row): + i = 0 + j = 0 + result = [] + + for x in self.tree.children: + if x.data == 'text': + result.append(x.children[0].value) + elif x.data == 'column_switch': + result.append(column[i]) + i += 1 + elif x.data == 'row_switch': + result.append(row[j]) + j += 1 + + return ''.join(result) diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c index a304754ab9..0705f00846 100644 --- a/softmmu/qdev-monitor.c +++ b/softmmu/qdev-monitor.c @@ -435,7 +435,12 @@ static DeviceState *qbus_find_dev(BusState *bus, char *elem) static inline bool qbus_is_full(BusState *bus) { - BusClass *bus_class = BUS_GET_CLASS(bus); + BusClass *bus_class; + + if (bus->full) { + return true; + } + bus_class = BUS_GET_CLASS(bus); return bus_class->max_dev && bus->num_children >= bus_class->max_dev; } diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index 4871ad0c0a..93e16a2ffb 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -218,10 +218,10 @@ static const struct SysemuCPUOps alpha_sysemu_ops = { static const struct TCGCPUOps alpha_tcg_ops = { .initialize = alpha_translate_init, - .cpu_exec_interrupt = alpha_cpu_exec_interrupt, .tlb_fill = alpha_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = alpha_cpu_exec_interrupt, .do_interrupt = alpha_cpu_do_interrupt, .do_transaction_failed = alpha_cpu_do_transaction_failed, .do_unaligned_access = alpha_cpu_do_unaligned_access, diff --git a/target/alpha/cpu.h b/target/alpha/cpu.h index 82df108967..4e993bd15b 100644 --- a/target/alpha/cpu.h +++ b/target/alpha/cpu.h @@ -274,10 +274,10 @@ struct AlphaCPU { #ifndef CONFIG_USER_ONLY extern const VMStateDescription vmstate_alpha_cpu; -#endif void alpha_cpu_do_interrupt(CPUState *cpu); bool alpha_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif /* !CONFIG_USER_ONLY */ void alpha_cpu_dump_state(CPUState *cs, FILE *f, int flags); hwaddr alpha_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int alpha_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); diff --git a/target/alpha/helper.c b/target/alpha/helper.c index 4f56fe4d23..81550d9e2f 100644 --- a/target/alpha/helper.c +++ b/target/alpha/helper.c @@ -293,7 +293,6 @@ bool alpha_cpu_tlb_fill(CPUState *cs, vaddr addr, int size, prot, mmu_idx, TARGET_PAGE_SIZE); return true; } -#endif /* USER_ONLY */ void alpha_cpu_do_interrupt(CPUState *cs) { @@ -348,7 +347,6 @@ void alpha_cpu_do_interrupt(CPUState *cs) cs->exception_index = -1; -#if !defined(CONFIG_USER_ONLY) switch (i) { case EXCP_RESET: i = 0x0000; @@ -404,7 +402,6 @@ void alpha_cpu_do_interrupt(CPUState *cs) /* Switch to PALmode. */ env->flags |= ENV_FLAG_PAL_MODE; -#endif /* !USER_ONLY */ } bool alpha_cpu_exec_interrupt(CPUState *cs, int interrupt_request) @@ -451,6 +448,8 @@ bool alpha_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + void alpha_cpu_dump_state(CPUState *cs, FILE *f, int flags) { static const char linux_reg_names[31][4] = { diff --git a/target/alpha/translate.c b/target/alpha/translate.c index de6c0a8439..b034206688 100644 --- a/target/alpha/translate.c +++ b/target/alpha/translate.c @@ -2971,7 +2971,7 @@ static void alpha_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *ctx = container_of(dcbase, DisasContext, base); CPUAlphaState *env = cpu->env_ptr; - uint32_t insn = translator_ldl(env, ctx->base.pc_next); + uint32_t insn = translator_ldl(env, &ctx->base, ctx->base.pc_next); ctx->base.pc_next += 4; ctx->base.is_jmp = translate_one(ctx, insn); diff --git a/target/arm/arm_ldst.h b/target/arm/arm_ldst.h index 057160e8da..cee0548a1c 100644 --- a/target/arm/arm_ldst.h +++ b/target/arm/arm_ldst.h @@ -24,15 +24,15 @@ #include "qemu/bswap.h" /* Load an instruction and return it in the standard little-endian order */ -static inline uint32_t arm_ldl_code(CPUARMState *env, target_ulong addr, - bool sctlr_b) +static inline uint32_t arm_ldl_code(CPUARMState *env, DisasContextBase *s, + target_ulong addr, bool sctlr_b) { - return translator_ldl_swap(env, addr, bswap_code(sctlr_b)); + return translator_ldl_swap(env, s, addr, bswap_code(sctlr_b)); } /* Ditto, for a halfword (Thumb) instruction */ -static inline uint16_t arm_lduw_code(CPUARMState *env, target_ulong addr, - bool sctlr_b) +static inline uint16_t arm_lduw_code(CPUARMState *env, DisasContextBase* s, + target_ulong addr, bool sctlr_b) { #ifndef CONFIG_USER_ONLY /* In big-endian (BE32) mode, adjacent Thumb instructions have been swapped @@ -41,7 +41,7 @@ static inline uint16_t arm_lduw_code(CPUARMState *env, target_ulong addr, addr ^= 2; } #endif - return translator_lduw_swap(env, addr, bswap_code(sctlr_b)); + return translator_lduw_swap(env, s, addr, bswap_code(sctlr_b)); } #endif diff --git a/target/arm/cpu.c b/target/arm/cpu.c index d631c4683c..ba0741b20e 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -440,6 +440,8 @@ static void arm_cpu_reset(DeviceState *dev) arm_rebuild_hflags(env); } +#ifndef CONFIG_USER_ONLY + static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, unsigned int target_el, unsigned int cur_el, bool secure, @@ -556,7 +558,7 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, return unmasked || pstate_unmasked; } -bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) +static bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { CPUClass *cc = CPU_GET_CLASS(cs); CPUARMState *env = cs->env_ptr; @@ -608,6 +610,7 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) cc->tcg_ops->do_interrupt(cs); return true; } +#endif /* !CONFIG_USER_ONLY */ void arm_cpu_update_virq(ARMCPU *cpu) { @@ -2010,11 +2013,11 @@ static const struct SysemuCPUOps arm_sysemu_ops = { static const struct TCGCPUOps arm_tcg_ops = { .initialize = arm_translate_init, .synchronize_from_tb = arm_cpu_synchronize_from_tb, - .cpu_exec_interrupt = arm_cpu_exec_interrupt, .tlb_fill = arm_cpu_tlb_fill, .debug_excp_handler = arm_debug_excp_handler, #if !defined(CONFIG_USER_ONLY) + .cpu_exec_interrupt = arm_cpu_exec_interrupt, .do_interrupt = arm_cpu_do_interrupt, .do_transaction_failed = arm_cpu_do_transaction_failed, .do_unaligned_access = arm_cpu_do_unaligned_access, diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 6a987f65e4..09d9027734 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -1040,11 +1040,10 @@ uint64_t arm_cpu_mp_affinity(int idx, uint8_t clustersz); #ifndef CONFIG_USER_ONLY extern const VMStateDescription vmstate_arm_cpu; -#endif void arm_cpu_do_interrupt(CPUState *cpu); void arm_v7m_cpu_do_interrupt(CPUState *cpu); -bool arm_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif /* !CONFIG_USER_ONLY */ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, MemTxAttrs *attrs); @@ -3455,6 +3454,7 @@ FIELD(TBFLAG_ANY, FPEXC_EL, 8, 2) FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 10, 2) /* Memory operations require alignment: SCTLR_ELx.A or CCR.UNALIGN_TRP */ FIELD(TBFLAG_ANY, ALIGN_MEM, 12, 1) +FIELD(TBFLAG_ANY, PSTATE__IL, 13, 1) /* * Bit usage when in AArch32 state, both A- and M-profile. diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index 33cc75af57..0d5adccf1a 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -22,7 +22,7 @@ /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) -#ifdef CONFIG_TCG +#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG) static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { CPUClass *cc = CPU_GET_CLASS(cs); @@ -46,7 +46,7 @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } return ret; } -#endif /* CONFIG_TCG */ +#endif /* !CONFIG_USER_ONLY && CONFIG_TCG */ static void arm926_initfn(Object *obj) { @@ -898,11 +898,11 @@ static void pxa270c5_initfn(Object *obj) static const struct TCGCPUOps arm_v7m_tcg_ops = { .initialize = arm_translate_init, .synchronize_from_tb = arm_cpu_synchronize_from_tb, - .cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt, .tlb_fill = arm_cpu_tlb_fill, .debug_excp_handler = arm_debug_excp_handler, #if !defined(CONFIG_USER_ONLY) + .cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt, .do_interrupt = arm_v7m_cpu_do_interrupt, .do_transaction_failed = arm_cpu_do_transaction_failed, .do_unaligned_access = arm_cpu_do_unaligned_access, diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 26f79f9141..19445b3c94 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -1071,6 +1071,7 @@ illegal_return: if (!arm_singlestep_active(env)) { env->pstate &= ~PSTATE_SS; } + helper_rebuild_hflags_a64(env, cur_el); qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); } diff --git a/target/arm/helper.c b/target/arm/helper.c index a7ae78146d..b210da2bc2 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -13462,6 +13462,10 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, DP_TBFLAG_A32(flags, HSTR_ACTIVE, 1); } + if (env->uncached_cpsr & CPSR_IL) { + DP_TBFLAG_ANY(flags, PSTATE__IL, 1); + } + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -13556,6 +13560,10 @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } } + if (env->pstate & PSTATE_IL) { + DP_TBFLAG_ANY(flags, PSTATE__IL, 1); + } + if (cpu_isar_feature(aa64_mte, env_archcpu(env))) { /* * Set MTE_ACTIVE if any access may be Checked, and leave clear diff --git a/target/arm/kvm.c b/target/arm/kvm.c index 5d55de1a49..94b970bbf9 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -70,12 +70,17 @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, struct kvm_vcpu_init *init) { int ret = 0, kvmfd = -1, vmfd = -1, cpufd = -1; + int max_vm_pa_size; kvmfd = qemu_open_old("/dev/kvm", O_RDWR); if (kvmfd < 0) { goto err; } - vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); + max_vm_pa_size = ioctl(kvmfd, KVM_CHECK_EXTENSION, KVM_CAP_ARM_VM_IPA_SIZE); + if (max_vm_pa_size < 0) { + max_vm_pa_size = 0; + } + vmfd = ioctl(kvmfd, KVM_CREATE_VM, max_vm_pa_size); if (vmfd < 0) { goto err; } diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index 34f8daa377..0613454975 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -525,8 +525,8 @@ static inline const char *its_class_name(void) /* KVM implementation requires this capability */ return kvm_direct_msi_enabled() ? "arm-its-kvm" : NULL; } else { - /* Software emulation is not implemented yet */ - return NULL; + /* Software emulation based model */ + return "arm-gicv3-its"; } } diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index 8dd88a0cb1..f30f4130a2 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -277,4 +277,9 @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) (cv << 24) | (cond << 20) | ti; } +static inline uint32_t syn_illegalstate(void) +{ + return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL; +} + #endif /* TARGET_ARM_SYNDROME_H */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 422e2ac0c9..ab6b346e35 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -14649,103 +14649,6 @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) return false; } -/* C3.1 A64 instruction index by encoding */ -static void disas_a64_insn(CPUARMState *env, DisasContext *s) -{ - uint32_t insn; - - s->pc_curr = s->base.pc_next; - insn = arm_ldl_code(env, s->base.pc_next, s->sctlr_b); - s->insn = insn; - s->base.pc_next += 4; - - s->fp_access_checked = false; - s->sve_access_checked = false; - - if (dc_isar_feature(aa64_bti, s)) { - if (s->base.num_insns == 1) { - /* - * At the first insn of the TB, compute s->guarded_page. - * We delayed computing this until successfully reading - * the first insn of the TB, above. This (mostly) ensures - * that the softmmu tlb entry has been populated, and the - * page table GP bit is available. - * - * Note that we need to compute this even if btype == 0, - * because this value is used for BR instructions later - * where ENV is not available. - */ - s->guarded_page = is_guarded_page(env, s); - - /* First insn can have btype set to non-zero. */ - tcg_debug_assert(s->btype >= 0); - - /* - * Note that the Branch Target Exception has fairly high - * priority -- below debugging exceptions but above most - * everything else. This allows us to handle this now - * instead of waiting until the insn is otherwise decoded. - */ - if (s->btype != 0 - && s->guarded_page - && !btype_destination_ok(insn, s->bt, s->btype)) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_btitrap(s->btype), - default_exception_el(s)); - return; - } - } else { - /* Not the first insn: btype must be 0. */ - tcg_debug_assert(s->btype == 0); - } - } - - switch (extract32(insn, 25, 4)) { - case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ - unallocated_encoding(s); - break; - case 0x2: - if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { - unallocated_encoding(s); - } - break; - case 0x8: case 0x9: /* Data processing - immediate */ - disas_data_proc_imm(s, insn); - break; - case 0xa: case 0xb: /* Branch, exception generation and system insns */ - disas_b_exc_sys(s, insn); - break; - case 0x4: - case 0x6: - case 0xc: - case 0xe: /* Loads and stores */ - disas_ldst(s, insn); - break; - case 0x5: - case 0xd: /* Data processing - register */ - disas_data_proc_reg(s, insn); - break; - case 0x7: - case 0xf: /* Data processing - SIMD and floating point */ - disas_data_proc_simd_fp(s, insn); - break; - default: - assert(FALSE); /* all 15 cases should be handled above */ - break; - } - - /* if we allocated any temporaries, free them here */ - free_tmp_a64(s); - - /* - * After execution of most insns, btype is reset to 0. - * Note that we set btype == -1 when the insn sets btype. - */ - if (s->btype > 0 && s->base.is_jmp != DISAS_NORETURN) { - reset_btype(s); - } -} - static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cpu) { @@ -14780,6 +14683,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); + dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL); dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); dc->sve_len = (EX_TBFLAG_A64(tb_flags, ZCR_LEN) + 1) * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); @@ -14846,10 +14750,11 @@ static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { - DisasContext *dc = container_of(dcbase, DisasContext, base); + DisasContext *s = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; + uint32_t insn; - if (dc->ss_active && !dc->pstate_ss) { + if (s->ss_active && !s->pstate_ss) { /* Singlestep state is Active-pending. * If we're in this state at the start of a TB then either * a) we just took an exception to an EL which is being debugged @@ -14860,14 +14765,114 @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) * "did not step an insn" case, and so the syndrome ISV and EX * bits should be zero. */ - assert(dc->base.num_insns == 1); - gen_swstep_exception(dc, 0, 0); - dc->base.is_jmp = DISAS_NORETURN; - } else { - disas_a64_insn(env, dc); + assert(s->base.num_insns == 1); + gen_swstep_exception(s, 0, 0); + s->base.is_jmp = DISAS_NORETURN; + return; + } + + s->pc_curr = s->base.pc_next; + insn = arm_ldl_code(env, &s->base, s->base.pc_next, s->sctlr_b); + s->insn = insn; + s->base.pc_next += 4; + + s->fp_access_checked = false; + s->sve_access_checked = false; + + if (s->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(s)); + return; + } + + if (dc_isar_feature(aa64_bti, s)) { + if (s->base.num_insns == 1) { + /* + * At the first insn of the TB, compute s->guarded_page. + * We delayed computing this until successfully reading + * the first insn of the TB, above. This (mostly) ensures + * that the softmmu tlb entry has been populated, and the + * page table GP bit is available. + * + * Note that we need to compute this even if btype == 0, + * because this value is used for BR instructions later + * where ENV is not available. + */ + s->guarded_page = is_guarded_page(env, s); + + /* First insn can have btype set to non-zero. */ + tcg_debug_assert(s->btype >= 0); + + /* + * Note that the Branch Target Exception has fairly high + * priority -- below debugging exceptions but above most + * everything else. This allows us to handle this now + * instead of waiting until the insn is otherwise decoded. + */ + if (s->btype != 0 + && s->guarded_page + && !btype_destination_ok(insn, s->bt, s->btype)) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_btitrap(s->btype), + default_exception_el(s)); + return; + } + } else { + /* Not the first insn: btype must be 0. */ + tcg_debug_assert(s->btype == 0); + } + } + + switch (extract32(insn, 25, 4)) { + case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ + unallocated_encoding(s); + break; + case 0x2: + if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { + unallocated_encoding(s); + } + break; + case 0x8: case 0x9: /* Data processing - immediate */ + disas_data_proc_imm(s, insn); + break; + case 0xa: case 0xb: /* Branch, exception generation and system insns */ + disas_b_exc_sys(s, insn); + break; + case 0x4: + case 0x6: + case 0xc: + case 0xe: /* Loads and stores */ + disas_ldst(s, insn); + break; + case 0x5: + case 0xd: /* Data processing - register */ + disas_data_proc_reg(s, insn); + break; + case 0x7: + case 0xf: /* Data processing - SIMD and floating point */ + disas_data_proc_simd_fp(s, insn); + break; + default: + assert(FALSE); /* all 15 cases should be handled above */ + break; + } + + /* if we allocated any temporaries, free them here */ + free_tmp_a64(s); + + /* + * After execution of most insns, btype is reset to 0. + * Note that we set btype == -1 when the insn sets btype. + */ + if (s->btype > 0 && s->base.is_jmp != DISAS_NORETURN) { + reset_btype(s); } - translator_loop_temp_check(&dc->base); + translator_loop_temp_check(&s->base); } static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) diff --git a/target/arm/translate.c b/target/arm/translate.c index 24b7f49d76..caefb1e1a1 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -9090,6 +9090,16 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) return; } + if (s->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(s)); + return; + } + if (cond == 0xf) { /* In ARMv3 and v4 the NV condition is UNPREDICTABLE; we * choose to UNDEF. In ARMv5 and above the space is used @@ -9302,7 +9312,7 @@ static bool insn_crosses_page(CPUARMState *env, DisasContext *s) * boundary, so we cross the page if the first 16 bits indicate * that this is a 32 bit insn. */ - uint16_t insn = arm_lduw_code(env, s->base.pc_next, s->sctlr_b); + uint16_t insn = arm_lduw_code(env, &s->base, s->base.pc_next, s->sctlr_b); return !thumb_insn_is_16bit(s, s->base.pc_next, insn); } @@ -9358,6 +9368,7 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); + dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL); if (arm_feature(env, ARM_FEATURE_M)) { dc->vfp_enabled = 1; @@ -9540,7 +9551,7 @@ static void arm_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } dc->pc_curr = dc->base.pc_next; - insn = arm_ldl_code(env, dc->base.pc_next, dc->sctlr_b); + insn = arm_ldl_code(env, &dc->base, dc->base.pc_next, dc->sctlr_b); dc->insn = insn; dc->base.pc_next += 4; disas_arm_insn(dc, insn); @@ -9610,17 +9621,28 @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } dc->pc_curr = dc->base.pc_next; - insn = arm_lduw_code(env, dc->base.pc_next, dc->sctlr_b); + insn = arm_lduw_code(env, &dc->base, dc->base.pc_next, dc->sctlr_b); is_16bit = thumb_insn_is_16bit(dc, dc->base.pc_next, insn); dc->base.pc_next += 2; if (!is_16bit) { - uint32_t insn2 = arm_lduw_code(env, dc->base.pc_next, dc->sctlr_b); + uint32_t insn2 = arm_lduw_code(env, &dc->base, dc->base.pc_next, + dc->sctlr_b); insn = insn << 16 | insn2; dc->base.pc_next += 2; } dc->insn = insn; + if (dc->pstate_il) { + /* + * Illegal execution state. This has priority over BTI + * exceptions, but comes after instruction abort exceptions. + */ + gen_exception_insn(dc, dc->pc_curr, EXCP_UDEF, + syn_illegalstate(), default_exception_el(dc)); + return; + } + if (dc->eci) { /* * For M-profile continuable instructions, ECI/ICI handling diff --git a/target/arm/translate.h b/target/arm/translate.h index 8636c20c3b..605d1f2e33 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -98,6 +98,8 @@ typedef struct DisasContext { bool hstr_active; /* True if memory operations require alignment */ bool align_mem; + /* True if PSTATE.IL is set */ + bool pstate_il; /* * >= 0, a copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. * < 0, set by the current instruction. diff --git a/target/avr/cpu.c b/target/avr/cpu.c index ea14175ca5..5d70e34dd5 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -197,10 +197,7 @@ static const struct TCGCPUOps avr_tcg_ops = { .synchronize_from_tb = avr_cpu_synchronize_from_tb, .cpu_exec_interrupt = avr_cpu_exec_interrupt, .tlb_fill = avr_cpu_tlb_fill, - -#ifndef CONFIG_USER_ONLY .do_interrupt = avr_cpu_do_interrupt, -#endif /* !CONFIG_USER_ONLY */ }; static void avr_cpu_class_init(ObjectClass *oc, void *data) diff --git a/target/avr/translate.c b/target/avr/translate.c index 1111e08b83..438e7b13c1 100644 --- a/target/avr/translate.c +++ b/target/avr/translate.c @@ -70,11 +70,9 @@ static const char reg_names[NUMBER_OF_CPU_REGISTERS][8] = { }; #define REG(x) (cpu_r[x]) -enum { - DISAS_EXIT = DISAS_TARGET_0, /* We want return to the cpu main loop. */ - DISAS_LOOKUP = DISAS_TARGET_1, /* We have a variable condition exit. */ - DISAS_CHAIN = DISAS_TARGET_2, /* We have a single condition exit. */ -}; +#define DISAS_EXIT DISAS_TARGET_0 /* We want return to the cpu main loop. */ +#define DISAS_LOOKUP DISAS_TARGET_1 /* We have a variable condition exit. */ +#define DISAS_CHAIN DISAS_TARGET_2 /* We have a single condition exit. */ typedef struct DisasContext DisasContext; diff --git a/target/cris/cpu.c b/target/cris/cpu.c index 70932b1f8c..c2e7483f5b 100644 --- a/target/cris/cpu.c +++ b/target/cris/cpu.c @@ -205,20 +205,20 @@ static const struct SysemuCPUOps cris_sysemu_ops = { static const struct TCGCPUOps crisv10_tcg_ops = { .initialize = cris_initialize_crisv10_tcg, - .cpu_exec_interrupt = cris_cpu_exec_interrupt, .tlb_fill = cris_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = cris_cpu_exec_interrupt, .do_interrupt = crisv10_cpu_do_interrupt, #endif /* !CONFIG_USER_ONLY */ }; static const struct TCGCPUOps crisv32_tcg_ops = { .initialize = cris_initialize_tcg, - .cpu_exec_interrupt = cris_cpu_exec_interrupt, .tlb_fill = cris_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = cris_cpu_exec_interrupt, .do_interrupt = cris_cpu_do_interrupt, #endif /* !CONFIG_USER_ONLY */ }; diff --git a/target/cris/cpu.h b/target/cris/cpu.h index d3b6492909..be021899ae 100644 --- a/target/cris/cpu.h +++ b/target/cris/cpu.h @@ -185,11 +185,11 @@ struct CRISCPU { #ifndef CONFIG_USER_ONLY extern const VMStateDescription vmstate_cris_cpu; -#endif void cris_cpu_do_interrupt(CPUState *cpu); void crisv10_cpu_do_interrupt(CPUState *cpu); bool cris_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif void cris_cpu_dump_state(CPUState *cs, FILE *f, int flags); diff --git a/target/cris/helper.c b/target/cris/helper.c index 911867f3b4..36926faf32 100644 --- a/target/cris/helper.c +++ b/target/cris/helper.c @@ -41,20 +41,6 @@ #if defined(CONFIG_USER_ONLY) -void cris_cpu_do_interrupt(CPUState *cs) -{ - CRISCPU *cpu = CRIS_CPU(cs); - CPUCRISState *env = &cpu->env; - - cs->exception_index = -1; - env->pregs[PR_ERP] = env->pc; -} - -void crisv10_cpu_do_interrupt(CPUState *cs) -{ - cris_cpu_do_interrupt(cs); -} - bool cris_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr) @@ -287,7 +273,6 @@ hwaddr cris_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) D(fprintf(stderr, "%s %x -> %x\n", __func__, addr, phy)); return phy; } -#endif bool cris_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { @@ -319,3 +304,5 @@ bool cris_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return ret; } + +#endif /* !CONFIG_USER_ONLY */ diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index 54fdcaa5e8..6fb4e6853c 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -112,7 +112,8 @@ static int read_packet_words(CPUHexagonState *env, DisasContext *ctx, memset(words, 0, PACKET_WORDS_MAX * sizeof(uint32_t)); for (nwords = 0; !found_end && nwords < PACKET_WORDS_MAX; nwords++) { words[nwords] = - translator_ldl(env, ctx->base.pc_next + nwords * sizeof(uint32_t)); + translator_ldl(env, &ctx->base, + ctx->base.pc_next + nwords * sizeof(uint32_t)); found_end = is_packet_end(words[nwords]); } if (!found_end) { diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index 2eace4ee12..e8edd189bf 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -144,10 +144,10 @@ static const struct SysemuCPUOps hppa_sysemu_ops = { static const struct TCGCPUOps hppa_tcg_ops = { .initialize = hppa_translate_init, .synchronize_from_tb = hppa_cpu_synchronize_from_tb, - .cpu_exec_interrupt = hppa_cpu_exec_interrupt, .tlb_fill = hppa_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = hppa_cpu_exec_interrupt, .do_interrupt = hppa_cpu_do_interrupt, .do_unaligned_access = hppa_cpu_do_unaligned_access, #endif /* !CONFIG_USER_ONLY */ diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h index 748270bfa3..7854675b90 100644 --- a/target/hppa/cpu.h +++ b/target/hppa/cpu.h @@ -325,13 +325,13 @@ int cpu_hppa_signal_handler(int host_signum, void *pinfo, void *puc); hwaddr hppa_cpu_get_phys_page_debug(CPUState *cs, vaddr addr); int hppa_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int hppa_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); -void hppa_cpu_do_interrupt(CPUState *cpu); -bool hppa_cpu_exec_interrupt(CPUState *cpu, int int_req); void hppa_cpu_dump_state(CPUState *cs, FILE *f, int); bool hppa_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr); #ifndef CONFIG_USER_ONLY +void hppa_cpu_do_interrupt(CPUState *cpu); +bool hppa_cpu_exec_interrupt(CPUState *cpu, int int_req); int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx, int type, hwaddr *pphys, int *pprot); extern const MemoryRegionOps hppa_io_eir_ops; diff --git a/target/hppa/int_helper.c b/target/hppa/int_helper.c index 349495d361..13073ae2bd 100644 --- a/target/hppa/int_helper.c +++ b/target/hppa/int_helper.c @@ -88,7 +88,6 @@ void HELPER(write_eiem)(CPUHPPAState *env, target_ureg val) eval_interrupt(env_archcpu(env)); qemu_mutex_unlock_iothread(); } -#endif /* !CONFIG_USER_ONLY */ void hppa_cpu_do_interrupt(CPUState *cs) { @@ -100,7 +99,6 @@ void hppa_cpu_do_interrupt(CPUState *cs) uint64_t iasq_f = env->iasq_f; uint64_t iasq_b = env->iasq_b; -#ifndef CONFIG_USER_ONLY target_ureg old_psw; /* As documented in pa2.0 -- interruption handling. */ @@ -187,7 +185,6 @@ void hppa_cpu_do_interrupt(CPUState *cs) env->iaoq_b = env->iaoq_f + 4; env->iasq_f = 0; env->iasq_b = 0; -#endif if (qemu_loglevel_mask(CPU_LOG_INT)) { static const char * const names[] = { @@ -248,7 +245,6 @@ void hppa_cpu_do_interrupt(CPUState *cs) bool hppa_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { -#ifndef CONFIG_USER_ONLY HPPACPU *cpu = HPPA_CPU(cs); CPUHPPAState *env = &cpu->env; @@ -258,6 +254,7 @@ bool hppa_cpu_exec_interrupt(CPUState *cs, int interrupt_request) hppa_cpu_do_interrupt(cs); return true; } -#endif return false; } + +#endif /* !CONFIG_USER_ONLY */ diff --git a/target/hppa/translate.c b/target/hppa/translate.c index b18150ef8d..c3698cf067 100644 --- a/target/hppa/translate.c +++ b/target/hppa/translate.c @@ -34,7 +34,6 @@ #undef TCGv #undef tcg_temp_new -#undef tcg_global_reg_new #undef tcg_global_mem_new #undef tcg_temp_local_new #undef tcg_temp_free @@ -59,7 +58,6 @@ #define TCGv_reg TCGv_i64 #define tcg_temp_new tcg_temp_new_i64 -#define tcg_global_reg_new tcg_global_reg_new_i64 #define tcg_global_mem_new tcg_global_mem_new_i64 #define tcg_temp_local_new tcg_temp_local_new_i64 #define tcg_temp_free tcg_temp_free_i64 @@ -155,7 +153,6 @@ #else #define TCGv_reg TCGv_i32 #define tcg_temp_new tcg_temp_new_i32 -#define tcg_global_reg_new tcg_global_reg_new_i32 #define tcg_global_mem_new tcg_global_mem_new_i32 #define tcg_temp_local_new tcg_temp_local_new_i32 #define tcg_temp_free tcg_temp_free_i32 @@ -4177,7 +4174,7 @@ static void hppa_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) { /* Always fetch the insn, even if nullified, so that we check the page permissions for execute. */ - uint32_t insn = translator_ldl(env, ctx->base.pc_next); + uint32_t insn = translator_ldl(env, &ctx->base, ctx->base.pc_next); /* Set up the IA queue for the next insn. This will be overwritten by a branch. */ diff --git a/target/i386/cpu-sysemu.c b/target/i386/cpu-sysemu.c index 1078e3d157..37b7c562f5 100644 --- a/target/i386/cpu-sysemu.c +++ b/target/i386/cpu-sysemu.c @@ -335,7 +335,7 @@ void x86_cpu_get_crash_info_qom(Object *obj, Visitor *v, GuestPanicInformation *panic_info; if (!cs->crash_occurred) { - error_setg(errp, "No crash occured"); + error_setg(errp, "No crash occurred"); return; } diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 71ae3141c3..7dd664791a 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -1836,12 +1836,15 @@ int x86_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void x86_cpu_list(void); int cpu_x86_support_mca_broadcast(CPUX86State *env); +#ifndef CONFIG_USER_ONLY int cpu_get_pic_interrupt(CPUX86State *s); + /* MSDOS compatibility mode FPU exception support */ void x86_register_ferr_irq(qemu_irq irq); void fpu_check_raise_ferr_irq(CPUX86State *s); void cpu_set_ignne(void); void cpu_clear_ignne(void); +#endif /* mpx_helper.c */ void cpu_sync_bndcs_hflags(CPUX86State *env); diff --git a/target/i386/tcg/helper-tcg.h b/target/i386/tcg/helper-tcg.h index 2510cc244e..60ca09e95e 100644 --- a/target/i386/tcg/helper-tcg.h +++ b/target/i386/tcg/helper-tcg.h @@ -38,7 +38,9 @@ QEMU_BUILD_BUG_ON(TCG_PHYS_ADDR_BITS > TARGET_PHYS_ADDR_SPACE_BITS); * @cpu: vCPU the interrupt is to be handled by. */ void x86_cpu_do_interrupt(CPUState *cpu); +#ifndef CONFIG_USER_ONLY bool x86_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif /* helper.c */ bool x86_cpu_tlb_fill(CPUState *cs, vaddr address, int size, diff --git a/target/i386/tcg/seg_helper.c b/target/i386/tcg/seg_helper.c index cef68b610a..baa905a0cd 100644 --- a/target/i386/tcg/seg_helper.c +++ b/target/i386/tcg/seg_helper.c @@ -929,9 +929,7 @@ static void do_interrupt64(CPUX86State *env, int intno, int is_int, e2); env->eip = offset; } -#endif -#ifdef TARGET_X86_64 void helper_sysret(CPUX86State *env, int dflag) { int cpl, selector; @@ -984,7 +982,7 @@ void helper_sysret(CPUX86State *env, int dflag) DESC_W_MASK | DESC_A_MASK); } } -#endif +#endif /* TARGET_X86_64 */ /* real mode interrupt */ static void do_interrupt_real(CPUX86State *env, int intno, int is_int, @@ -1112,76 +1110,6 @@ void do_interrupt_x86_hardirq(CPUX86State *env, int intno, int is_hw) do_interrupt_all(env_archcpu(env), intno, 0, 0, 0, is_hw); } -bool x86_cpu_exec_interrupt(CPUState *cs, int interrupt_request) -{ - X86CPU *cpu = X86_CPU(cs); - CPUX86State *env = &cpu->env; - int intno; - - interrupt_request = x86_cpu_pending_interrupt(cs, interrupt_request); - if (!interrupt_request) { - return false; - } - - /* Don't process multiple interrupt requests in a single call. - * This is required to make icount-driven execution deterministic. - */ - switch (interrupt_request) { -#if !defined(CONFIG_USER_ONLY) - case CPU_INTERRUPT_POLL: - cs->interrupt_request &= ~CPU_INTERRUPT_POLL; - apic_poll_irq(cpu->apic_state); - break; -#endif - case CPU_INTERRUPT_SIPI: - do_cpu_sipi(cpu); - break; - case CPU_INTERRUPT_SMI: - cpu_svm_check_intercept_param(env, SVM_EXIT_SMI, 0, 0); - cs->interrupt_request &= ~CPU_INTERRUPT_SMI; -#ifdef CONFIG_USER_ONLY - cpu_abort(CPU(cpu), "SMI interrupt: cannot enter SMM in user-mode"); -#else - do_smm_enter(cpu); -#endif /* CONFIG_USER_ONLY */ - break; - case CPU_INTERRUPT_NMI: - cpu_svm_check_intercept_param(env, SVM_EXIT_NMI, 0, 0); - cs->interrupt_request &= ~CPU_INTERRUPT_NMI; - env->hflags2 |= HF2_NMI_MASK; - do_interrupt_x86_hardirq(env, EXCP02_NMI, 1); - break; - case CPU_INTERRUPT_MCE: - cs->interrupt_request &= ~CPU_INTERRUPT_MCE; - do_interrupt_x86_hardirq(env, EXCP12_MCHK, 0); - break; - case CPU_INTERRUPT_HARD: - cpu_svm_check_intercept_param(env, SVM_EXIT_INTR, 0, 0); - cs->interrupt_request &= ~(CPU_INTERRUPT_HARD | - CPU_INTERRUPT_VIRQ); - intno = cpu_get_pic_interrupt(env); - qemu_log_mask(CPU_LOG_TB_IN_ASM, - "Servicing hardware INT=0x%02x\n", intno); - do_interrupt_x86_hardirq(env, intno, 1); - break; -#if !defined(CONFIG_USER_ONLY) - case CPU_INTERRUPT_VIRQ: - cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR, 0, 0); - intno = x86_ldl_phys(cs, env->vm_vmcb - + offsetof(struct vmcb, control.int_vector)); - qemu_log_mask(CPU_LOG_TB_IN_ASM, - "Servicing virtual hardware INT=0x%02x\n", intno); - do_interrupt_x86_hardirq(env, intno, 1); - cs->interrupt_request &= ~CPU_INTERRUPT_VIRQ; - env->int_ctl &= ~V_IRQ_MASK; - break; -#endif - } - - /* Ensure that no TB jump will be modified as the program flow was changed. */ - return true; -} - void helper_lldt(CPUX86State *env, int selector) { SegmentCache *dt; diff --git a/target/i386/tcg/sysemu/seg_helper.c b/target/i386/tcg/sysemu/seg_helper.c index 82c0856c41..bf3444c26b 100644 --- a/target/i386/tcg/sysemu/seg_helper.c +++ b/target/i386/tcg/sysemu/seg_helper.c @@ -125,6 +125,68 @@ void x86_cpu_do_interrupt(CPUState *cs) } } +bool x86_cpu_exec_interrupt(CPUState *cs, int interrupt_request) +{ + X86CPU *cpu = X86_CPU(cs); + CPUX86State *env = &cpu->env; + int intno; + + interrupt_request = x86_cpu_pending_interrupt(cs, interrupt_request); + if (!interrupt_request) { + return false; + } + + /* Don't process multiple interrupt requests in a single call. + * This is required to make icount-driven execution deterministic. + */ + switch (interrupt_request) { + case CPU_INTERRUPT_POLL: + cs->interrupt_request &= ~CPU_INTERRUPT_POLL; + apic_poll_irq(cpu->apic_state); + break; + case CPU_INTERRUPT_SIPI: + do_cpu_sipi(cpu); + break; + case CPU_INTERRUPT_SMI: + cpu_svm_check_intercept_param(env, SVM_EXIT_SMI, 0, 0); + cs->interrupt_request &= ~CPU_INTERRUPT_SMI; + do_smm_enter(cpu); + break; + case CPU_INTERRUPT_NMI: + cpu_svm_check_intercept_param(env, SVM_EXIT_NMI, 0, 0); + cs->interrupt_request &= ~CPU_INTERRUPT_NMI; + env->hflags2 |= HF2_NMI_MASK; + do_interrupt_x86_hardirq(env, EXCP02_NMI, 1); + break; + case CPU_INTERRUPT_MCE: + cs->interrupt_request &= ~CPU_INTERRUPT_MCE; + do_interrupt_x86_hardirq(env, EXCP12_MCHK, 0); + break; + case CPU_INTERRUPT_HARD: + cpu_svm_check_intercept_param(env, SVM_EXIT_INTR, 0, 0); + cs->interrupt_request &= ~(CPU_INTERRUPT_HARD | + CPU_INTERRUPT_VIRQ); + intno = cpu_get_pic_interrupt(env); + qemu_log_mask(CPU_LOG_TB_IN_ASM, + "Servicing hardware INT=0x%02x\n", intno); + do_interrupt_x86_hardirq(env, intno, 1); + break; + case CPU_INTERRUPT_VIRQ: + cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR, 0, 0); + intno = x86_ldl_phys(cs, env->vm_vmcb + + offsetof(struct vmcb, control.int_vector)); + qemu_log_mask(CPU_LOG_TB_IN_ASM, + "Servicing virtual hardware INT=0x%02x\n", intno); + do_interrupt_x86_hardirq(env, intno, 1); + cs->interrupt_request &= ~CPU_INTERRUPT_VIRQ; + env->int_ctl &= ~V_IRQ_MASK; + break; + } + + /* Ensure that no TB jump will be modified as the program flow was changed. */ + return true; +} + /* check if Port I/O is allowed in TSS */ void helper_check_io(CPUX86State *env, uint32_t addr, uint32_t size) { diff --git a/target/i386/tcg/tcg-cpu.c b/target/i386/tcg/tcg-cpu.c index 93a79a5741..3ecfae34cb 100644 --- a/target/i386/tcg/tcg-cpu.c +++ b/target/i386/tcg/tcg-cpu.c @@ -72,10 +72,12 @@ static const struct TCGCPUOps x86_tcg_ops = { .synchronize_from_tb = x86_cpu_synchronize_from_tb, .cpu_exec_enter = x86_cpu_exec_enter, .cpu_exec_exit = x86_cpu_exec_exit, - .cpu_exec_interrupt = x86_cpu_exec_interrupt, - .do_interrupt = x86_cpu_do_interrupt, .tlb_fill = x86_cpu_tlb_fill, -#ifndef CONFIG_USER_ONLY +#ifdef CONFIG_USER_ONLY + .fake_user_interrupt = x86_cpu_do_interrupt, +#else + .do_interrupt = x86_cpu_do_interrupt, + .cpu_exec_interrupt = x86_cpu_exec_interrupt, .debug_excp_handler = breakpoint_handler, .debug_check_breakpoint = x86_debug_check_breakpoint, #endif /* !CONFIG_USER_ONLY */ diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index aacb605eee..a46be75b00 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -2028,28 +2028,28 @@ static uint64_t advance_pc(CPUX86State *env, DisasContext *s, int num_bytes) static inline uint8_t x86_ldub_code(CPUX86State *env, DisasContext *s) { - return translator_ldub(env, advance_pc(env, s, 1)); + return translator_ldub(env, &s->base, advance_pc(env, s, 1)); } static inline int16_t x86_ldsw_code(CPUX86State *env, DisasContext *s) { - return translator_ldsw(env, advance_pc(env, s, 2)); + return translator_ldsw(env, &s->base, advance_pc(env, s, 2)); } static inline uint16_t x86_lduw_code(CPUX86State *env, DisasContext *s) { - return translator_lduw(env, advance_pc(env, s, 2)); + return translator_lduw(env, &s->base, advance_pc(env, s, 2)); } static inline uint32_t x86_ldl_code(CPUX86State *env, DisasContext *s) { - return translator_ldl(env, advance_pc(env, s, 4)); + return translator_ldl(env, &s->base, advance_pc(env, s, 4)); } #ifdef TARGET_X86_64 static inline uint64_t x86_ldq_code(CPUX86State *env, DisasContext *s) { - return translator_ldq(env, advance_pc(env, s, 8)); + return translator_ldq(env, &s->base, advance_pc(env, s, 8)); } #endif diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index 72de6e9726..66d22d1189 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -515,10 +515,10 @@ static const struct SysemuCPUOps m68k_sysemu_ops = { static const struct TCGCPUOps m68k_tcg_ops = { .initialize = m68k_tcg_init, - .cpu_exec_interrupt = m68k_cpu_exec_interrupt, .tlb_fill = m68k_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = m68k_cpu_exec_interrupt, .do_interrupt = m68k_cpu_do_interrupt, .do_transaction_failed = m68k_cpu_transaction_failed, #endif /* !CONFIG_USER_ONLY */ diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h index 997d588911..550eb028b6 100644 --- a/target/m68k/cpu.h +++ b/target/m68k/cpu.h @@ -166,8 +166,10 @@ struct M68kCPU { }; +#ifndef CONFIG_USER_ONLY void m68k_cpu_do_interrupt(CPUState *cpu); bool m68k_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif /* !CONFIG_USER_ONLY */ void m68k_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr m68k_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int m68k_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); diff --git a/target/m68k/op_helper.c b/target/m68k/op_helper.c index d006d1cb3e..5d624838ae 100644 --- a/target/m68k/op_helper.c +++ b/target/m68k/op_helper.c @@ -24,18 +24,7 @@ #include "semihosting/semihost.h" #include "tcg/tcg.h" -#if defined(CONFIG_USER_ONLY) - -void m68k_cpu_do_interrupt(CPUState *cs) -{ - cs->exception_index = -1; -} - -static inline void do_interrupt_m68k_hardirq(CPUM68KState *env) -{ -} - -#else +#if !defined(CONFIG_USER_ONLY) static void cf_rte(CPUM68KState *env) { @@ -516,7 +505,6 @@ void m68k_cpu_transaction_failed(CPUState *cs, hwaddr physaddr, vaddr addr, cpu_loop_exit(cs); } } -#endif bool m68k_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { @@ -538,6 +526,8 @@ bool m68k_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + static void raise_exception_ra(CPUM68KState *env, int tt, uintptr_t raddr) { CPUState *cs = env_cpu(env); diff --git a/target/m68k/translate.c b/target/m68k/translate.c index c34d9aed61..50a55f949c 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -415,7 +415,7 @@ static TCGv gen_ldst(DisasContext *s, int opsize, TCGv addr, TCGv val, static inline uint16_t read_im16(CPUM68KState *env, DisasContext *s) { uint16_t im; - im = translator_lduw(env, s->pc); + im = translator_lduw(env, &s->base, s->pc); s->pc += 2; return im; } diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index 72d8f2a0da..15db277925 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -365,10 +365,10 @@ static const struct SysemuCPUOps mb_sysemu_ops = { static const struct TCGCPUOps mb_tcg_ops = { .initialize = mb_tcg_init, .synchronize_from_tb = mb_cpu_synchronize_from_tb, - .cpu_exec_interrupt = mb_cpu_exec_interrupt, .tlb_fill = mb_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = mb_cpu_exec_interrupt, .do_interrupt = mb_cpu_do_interrupt, .do_transaction_failed = mb_cpu_transaction_failed, .do_unaligned_access = mb_cpu_do_unaligned_access, diff --git a/target/microblaze/cpu.h b/target/microblaze/cpu.h index e4bba8a755..40401c33b7 100644 --- a/target/microblaze/cpu.h +++ b/target/microblaze/cpu.h @@ -355,8 +355,10 @@ struct MicroBlazeCPU { }; +#ifndef CONFIG_USER_ONLY void mb_cpu_do_interrupt(CPUState *cs); bool mb_cpu_exec_interrupt(CPUState *cs, int int_req); +#endif /* !CONFIG_USER_ONLY */ void mb_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); diff --git a/target/microblaze/helper.c b/target/microblaze/helper.c index 20dbd67313..dd2aecd1d5 100644 --- a/target/microblaze/helper.c +++ b/target/microblaze/helper.c @@ -26,16 +26,6 @@ #if defined(CONFIG_USER_ONLY) -void mb_cpu_do_interrupt(CPUState *cs) -{ - MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); - CPUMBState *env = &cpu->env; - - cs->exception_index = -1; - env->res_addr = RES_ADDR_NONE; - env->regs[14] = env->pc; -} - bool mb_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr) @@ -271,7 +261,6 @@ hwaddr mb_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr, return paddr; } -#endif bool mb_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { @@ -289,6 +278,8 @@ bool mb_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + void mb_cpu_do_unaligned_access(CPUState *cs, vaddr addr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) diff --git a/target/mips/cpu.c b/target/mips/cpu.c index d426918291..00e0c55d0e 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -539,10 +539,10 @@ static const struct SysemuCPUOps mips_sysemu_ops = { static const struct TCGCPUOps mips_tcg_ops = { .initialize = mips_tcg_init, .synchronize_from_tb = mips_cpu_synchronize_from_tb, - .cpu_exec_interrupt = mips_cpu_exec_interrupt, .tlb_fill = mips_cpu_tlb_fill, #if !defined(CONFIG_USER_ONLY) + .cpu_exec_interrupt = mips_cpu_exec_interrupt, .do_interrupt = mips_cpu_do_interrupt, .do_transaction_failed = mips_cpu_do_transaction_failed, .do_unaligned_access = mips_cpu_do_unaligned_access, diff --git a/target/mips/tcg/exception.c b/target/mips/tcg/exception.c index 4fb8b00711..7b3026b105 100644 --- a/target/mips/tcg/exception.c +++ b/target/mips/tcg/exception.c @@ -86,24 +86,6 @@ void mips_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb) env->hflags |= tb->flags & MIPS_HFLAG_BMASK; } -bool mips_cpu_exec_interrupt(CPUState *cs, int interrupt_request) -{ - if (interrupt_request & CPU_INTERRUPT_HARD) { - MIPSCPU *cpu = MIPS_CPU(cs); - CPUMIPSState *env = &cpu->env; - - if (cpu_mips_hw_interrupts_enabled(env) && - cpu_mips_hw_interrupts_pending(env)) { - /* Raise it */ - cs->exception_index = EXCP_EXT_INTERRUPT; - env->error_code = 0; - mips_cpu_do_interrupt(cs); - return true; - } - } - return false; -} - static const char * const excp_names[EXCP_LAST + 1] = { [EXCP_RESET] = "reset", [EXCP_SRESET] = "soft reset", diff --git a/target/mips/tcg/micromips_translate.c.inc b/target/mips/tcg/micromips_translate.c.inc index 5e95f47854..0da4c802a3 100644 --- a/target/mips/tcg/micromips_translate.c.inc +++ b/target/mips/tcg/micromips_translate.c.inc @@ -1627,7 +1627,7 @@ static void decode_micromips32_opc(CPUMIPSState *env, DisasContext *ctx) uint32_t op, minor, minor2, mips32_op; uint32_t cond, fmt, cc; - insn = translator_lduw(env, ctx->base.pc_next + 2); + insn = translator_lduw(env, &ctx->base, ctx->base.pc_next + 2); ctx->opcode = (ctx->opcode << 16) | insn; rt = (ctx->opcode >> 21) & 0x1f; diff --git a/target/mips/tcg/mips16e_translate.c.inc b/target/mips/tcg/mips16e_translate.c.inc index 54071813f1..84d816603a 100644 --- a/target/mips/tcg/mips16e_translate.c.inc +++ b/target/mips/tcg/mips16e_translate.c.inc @@ -455,7 +455,7 @@ static void decode_i64_mips16(DisasContext *ctx, static int decode_extended_mips16_opc(CPUMIPSState *env, DisasContext *ctx) { - int extend = translator_lduw(env, ctx->base.pc_next + 2); + int extend = translator_lduw(env, &ctx->base, ctx->base.pc_next + 2); int op, rx, ry, funct, sa; int16_t imm, offset; @@ -688,7 +688,7 @@ static int decode_ase_mips16e(CPUMIPSState *env, DisasContext *ctx) /* No delay slot, so just process as a normal instruction */ break; case M16_OPC_JAL: - offset = translator_lduw(env, ctx->base.pc_next + 2); + offset = translator_lduw(env, &ctx->base, ctx->base.pc_next + 2); offset = (((ctx->opcode & 0x1f) << 21) | ((ctx->opcode >> 5) & 0x1f) << 16 | offset) << 2; diff --git a/target/mips/tcg/nanomips_translate.c.inc b/target/mips/tcg/nanomips_translate.c.inc index a66ae26796..ccbcecad09 100644 --- a/target/mips/tcg/nanomips_translate.c.inc +++ b/target/mips/tcg/nanomips_translate.c.inc @@ -3656,7 +3656,7 @@ static int decode_nanomips_32_48_opc(CPUMIPSState *env, DisasContext *ctx) int offset; int imm; - insn = translator_lduw(env, ctx->base.pc_next + 2); + insn = translator_lduw(env, &ctx->base, ctx->base.pc_next + 2); ctx->opcode = (ctx->opcode << 16) | insn; rt = extract32(ctx->opcode, 21, 5); @@ -3775,7 +3775,7 @@ static int decode_nanomips_32_48_opc(CPUMIPSState *env, DisasContext *ctx) break; case NM_P48I: { - insn = translator_lduw(env, ctx->base.pc_next + 4); + insn = translator_lduw(env, &ctx->base, ctx->base.pc_next + 4); target_long addr_off = extract32(ctx->opcode, 0, 16) | insn << 16; switch (extract32(ctx->opcode, 16, 5)) { case NM_LI48: diff --git a/target/mips/tcg/sysemu/tlb_helper.c b/target/mips/tcg/sysemu/tlb_helper.c index a150a014ec..73254d1929 100644 --- a/target/mips/tcg/sysemu/tlb_helper.c +++ b/target/mips/tcg/sysemu/tlb_helper.c @@ -1339,6 +1339,24 @@ void mips_cpu_do_interrupt(CPUState *cs) cs->exception_index = EXCP_NONE; } +bool mips_cpu_exec_interrupt(CPUState *cs, int interrupt_request) +{ + if (interrupt_request & CPU_INTERRUPT_HARD) { + MIPSCPU *cpu = MIPS_CPU(cs); + CPUMIPSState *env = &cpu->env; + + if (cpu_mips_hw_interrupts_enabled(env) && + cpu_mips_hw_interrupts_pending(env)) { + /* Raise it */ + cs->exception_index = EXCP_EXT_INTERRUPT; + env->error_code = 0; + mips_cpu_do_interrupt(cs); + return true; + } + } + return false; +} + void r4k_invalidate_tlb(CPUMIPSState *env, int idx, int use_extra) { CPUState *cs = env_cpu(env); diff --git a/target/mips/tcg/tcg-internal.h b/target/mips/tcg/tcg-internal.h index 81b14eb219..c7a77ddccd 100644 --- a/target/mips/tcg/tcg-internal.h +++ b/target/mips/tcg/tcg-internal.h @@ -18,8 +18,6 @@ void mips_tcg_init(void); void mips_cpu_synchronize_from_tb(CPUState *cs, const TranslationBlock *tb); -void mips_cpu_do_interrupt(CPUState *cpu); -bool mips_cpu_exec_interrupt(CPUState *cpu, int int_req); bool mips_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr); @@ -41,6 +39,9 @@ static inline void QEMU_NORETURN do_raise_exception(CPUMIPSState *env, #if !defined(CONFIG_USER_ONLY) +void mips_cpu_do_interrupt(CPUState *cpu); +bool mips_cpu_exec_interrupt(CPUState *cpu, int int_req); + void mmu_init(CPUMIPSState *env, const mips_def_t *def); void update_pagemask(CPUMIPSState *env, target_ulong arg1, int32_t *pagemask); diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c index 6f4a9a839c..148afec9dc 100644 --- a/target/mips/tcg/translate.c +++ b/target/mips/tcg/translate.c @@ -16041,17 +16041,17 @@ static void mips_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) is_slot = ctx->hflags & MIPS_HFLAG_BMASK; if (ctx->insn_flags & ISA_NANOMIPS32) { - ctx->opcode = translator_lduw(env, ctx->base.pc_next); + ctx->opcode = translator_lduw(env, &ctx->base, ctx->base.pc_next); insn_bytes = decode_isa_nanomips(env, ctx); } else if (!(ctx->hflags & MIPS_HFLAG_M16)) { - ctx->opcode = translator_ldl(env, ctx->base.pc_next); + ctx->opcode = translator_ldl(env, &ctx->base, ctx->base.pc_next); insn_bytes = 4; decode_opc(env, ctx); } else if (ctx->insn_flags & ASE_MICROMIPS) { - ctx->opcode = translator_lduw(env, ctx->base.pc_next); + ctx->opcode = translator_lduw(env, &ctx->base, ctx->base.pc_next); insn_bytes = decode_isa_micromips(env, ctx); } else if (ctx->insn_flags & ASE_MIPS16) { - ctx->opcode = translator_lduw(env, ctx->base.pc_next); + ctx->opcode = translator_lduw(env, &ctx->base, ctx->base.pc_next); insn_bytes = decode_ase_mips16e(env, ctx); } else { gen_reserved_instruction(ctx); diff --git a/target/mips/tcg/user/tlb_helper.c b/target/mips/tcg/user/tlb_helper.c index b835144b82..210c6d529e 100644 --- a/target/mips/tcg/user/tlb_helper.c +++ b/target/mips/tcg/user/tlb_helper.c @@ -57,8 +57,3 @@ bool mips_cpu_tlb_fill(CPUState *cs, vaddr address, int size, raise_mmu_exception(env, address, access_type); do_raise_exception_err(env, cs->exception_index, env->error_code, retaddr); } - -void mips_cpu_do_interrupt(CPUState *cs) -{ - cs->exception_index = EXCP_NONE; -} diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index 5e37defef8..947bb09bc1 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -127,6 +127,7 @@ static void nios2_cpu_realizefn(DeviceState *dev, Error **errp) ncc->parent_realize(dev, errp); } +#ifndef CONFIG_USER_ONLY static bool nios2_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { Nios2CPU *cpu = NIOS2_CPU(cs); @@ -140,7 +141,7 @@ static bool nios2_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } return false; } - +#endif /* !CONFIG_USER_ONLY */ static void nios2_cpu_disas_set_info(CPUState *cpu, disassemble_info *info) { @@ -219,10 +220,10 @@ static const struct SysemuCPUOps nios2_sysemu_ops = { static const struct TCGCPUOps nios2_tcg_ops = { .initialize = nios2_tcg_init, - .cpu_exec_interrupt = nios2_cpu_exec_interrupt, .tlb_fill = nios2_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = nios2_cpu_exec_interrupt, .do_interrupt = nios2_cpu_do_interrupt, .do_unaligned_access = nios2_cpu_do_unaligned_access, #endif /* !CONFIG_USER_ONLY */ diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index bd34e429ec..27cb04152f 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -186,10 +186,10 @@ static const struct SysemuCPUOps openrisc_sysemu_ops = { static const struct TCGCPUOps openrisc_tcg_ops = { .initialize = openrisc_translate_init, - .cpu_exec_interrupt = openrisc_cpu_exec_interrupt, .tlb_fill = openrisc_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = openrisc_cpu_exec_interrupt, .do_interrupt = openrisc_cpu_do_interrupt, #endif /* !CONFIG_USER_ONLY */ }; diff --git a/target/openrisc/cpu.h b/target/openrisc/cpu.h index 82cbaeb4f8..be6df81a81 100644 --- a/target/openrisc/cpu.h +++ b/target/openrisc/cpu.h @@ -312,8 +312,6 @@ struct OpenRISCCPU { void cpu_openrisc_list(void); -void openrisc_cpu_do_interrupt(CPUState *cpu); -bool openrisc_cpu_exec_interrupt(CPUState *cpu, int int_req); void openrisc_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr openrisc_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int openrisc_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); @@ -331,6 +329,9 @@ int print_insn_or1k(bfd_vma addr, disassemble_info *info); #ifndef CONFIG_USER_ONLY extern const VMStateDescription vmstate_openrisc_cpu; +void openrisc_cpu_do_interrupt(CPUState *cpu); +bool openrisc_cpu_exec_interrupt(CPUState *cpu, int int_req); + /* hw/openrisc_pic.c */ void cpu_openrisc_pic_init(OpenRISCCPU *cpu); diff --git a/target/openrisc/interrupt.c b/target/openrisc/interrupt.c index 3eab771dcd..19223e3f25 100644 --- a/target/openrisc/interrupt.c +++ b/target/openrisc/interrupt.c @@ -28,7 +28,6 @@ void openrisc_cpu_do_interrupt(CPUState *cs) { -#ifndef CONFIG_USER_ONLY OpenRISCCPU *cpu = OPENRISC_CPU(cs); CPUOpenRISCState *env = &cpu->env; int exception = cs->exception_index; @@ -96,7 +95,6 @@ void openrisc_cpu_do_interrupt(CPUState *cs) } else { cpu_abort(cs, "Unhandled exception 0x%x\n", exception); } -#endif cs->exception_index = -1; } diff --git a/target/openrisc/meson.build b/target/openrisc/meson.build index 9774a58306..e445dec4a0 100644 --- a/target/openrisc/meson.build +++ b/target/openrisc/meson.build @@ -9,7 +9,6 @@ openrisc_ss.add(files( 'exception_helper.c', 'fpu_helper.c', 'gdbstub.c', - 'interrupt.c', 'interrupt_helper.c', 'mmu.c', 'sys_helper.c', @@ -17,7 +16,10 @@ openrisc_ss.add(files( )) openrisc_softmmu_ss = ss.source_set() -openrisc_softmmu_ss.add(files('machine.c')) +openrisc_softmmu_ss.add(files( + 'interrupt.c', + 'machine.c', +)) target_arch += {'openrisc': openrisc_ss} target_softmmu_arch += {'openrisc': openrisc_softmmu_ss} diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c index d6ea536744..5f3d430245 100644 --- a/target/openrisc/translate.c +++ b/target/openrisc/translate.c @@ -1613,7 +1613,7 @@ static void openrisc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) { DisasContext *dc = container_of(dcbase, DisasContext, base); OpenRISCCPU *cpu = OPENRISC_CPU(cs); - uint32_t insn = translator_ldl(&cpu->env, dc->base.pc_next); + uint32_t insn = translator_ldl(&cpu->env, &dc->base, dc->base.pc_next); if (!decode(dc, insn)) { gen_illegal_exception(dc); diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 500205229c..362e7c4c5c 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -1254,8 +1254,6 @@ DECLARE_OBJ_CHECKERS(PPCVirtualHypervisor, PPCVirtualHypervisorClass, PPC_VIRTUAL_HYPERVISOR, TYPE_PPC_VIRTUAL_HYPERVISOR) #endif /* CONFIG_USER_ONLY */ -void ppc_cpu_do_interrupt(CPUState *cpu); -bool ppc_cpu_exec_interrupt(CPUState *cpu, int int_req); void ppc_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr ppc_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int ppc_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); @@ -1271,6 +1269,8 @@ int ppc64_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, int ppc32_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int cpuid, void *opaque); #ifndef CONFIG_USER_ONLY +void ppc_cpu_do_interrupt(CPUState *cpu); +bool ppc_cpu_exec_interrupt(CPUState *cpu, int int_req); void ppc_cpu_do_system_reset(CPUState *cs); void ppc_cpu_do_fwnmi_machine_check(CPUState *cs, target_ulong vector); extern const VMStateDescription vmstate_ppc_cpu; diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index ad7abc6041..6aad01d1d3 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -9014,10 +9014,10 @@ static const struct SysemuCPUOps ppc_sysemu_ops = { static const struct TCGCPUOps ppc_tcg_ops = { .initialize = ppc_translate_init, - .cpu_exec_interrupt = ppc_cpu_exec_interrupt, .tlb_fill = ppc_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = ppc_cpu_exec_interrupt, .do_interrupt = ppc_cpu_do_interrupt, .cpu_exec_enter = ppc_cpu_exec_enter, .cpu_exec_exit = ppc_cpu_exec_exit, diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c index 7b6ac16eef..d7e32ee107 100644 --- a/target/ppc/excp_helper.c +++ b/target/ppc/excp_helper.c @@ -40,24 +40,8 @@ /*****************************************************************************/ /* Exception processing */ -#if defined(CONFIG_USER_ONLY) -void ppc_cpu_do_interrupt(CPUState *cs) -{ - PowerPCCPU *cpu = POWERPC_CPU(cs); - CPUPPCState *env = &cpu->env; - - cs->exception_index = POWERPC_EXCP_NONE; - env->error_code = 0; -} - -static void ppc_hw_interrupt(CPUPPCState *env) -{ - CPUState *cs = env_cpu(env); +#if !defined(CONFIG_USER_ONLY) - cs->exception_index = POWERPC_EXCP_NONE; - env->error_code = 0; -} -#else /* defined(CONFIG_USER_ONLY) */ static inline void dump_syscall(CPUPPCState *env) { qemu_log_mask(CPU_LOG_INT, "syscall r0=%016" PRIx64 @@ -1113,7 +1097,6 @@ void ppc_cpu_do_fwnmi_machine_check(CPUState *cs, target_ulong vector) powerpc_set_excp_state(cpu, vector, msr); } -#endif /* !CONFIG_USER_ONLY */ bool ppc_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { @@ -1130,6 +1113,8 @@ bool ppc_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + #if defined(DEBUG_OP) static void cpu_dump_rfi(target_ulong RA, target_ulong msr) { diff --git a/target/ppc/translate.c b/target/ppc/translate.c index 171b216e17..5d8b06bd80 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -8585,7 +8585,7 @@ static void ppc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) ctx->base.pc_next, ctx->mem_idx, (int)msr_ir); ctx->cia = pc = ctx->base.pc_next; - insn = translator_ldl_swap(env, pc, need_byteswap(ctx)); + insn = translator_ldl_swap(env, dcbase, pc, need_byteswap(ctx)); ctx->base.pc_next = pc += 4; if (!is_prefix_insn(ctx, insn)) { @@ -8600,7 +8600,8 @@ static void ppc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) gen_exception_err(ctx, POWERPC_EXCP_ALIGN, POWERPC_EXCP_ALIGN_INSN); ok = true; } else { - uint32_t insn2 = translator_ldl_swap(env, pc, need_byteswap(ctx)); + uint32_t insn2 = translator_ldl_swap(env, dcbase, pc, + need_byteswap(ctx)); ctx->base.pc_next = pc += 4; ok = decode_insn64(ctx, deposit64(insn2, 32, 32, insn)); } diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 1a2b03d579..13575c1408 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -644,10 +644,10 @@ static const struct SysemuCPUOps riscv_sysemu_ops = { static const struct TCGCPUOps riscv_tcg_ops = { .initialize = riscv_translate_init, .synchronize_from_tb = riscv_cpu_synchronize_from_tb, - .cpu_exec_interrupt = riscv_cpu_exec_interrupt, .tlb_fill = riscv_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = riscv_cpu_exec_interrupt, .do_interrupt = riscv_cpu_do_interrupt, .do_transaction_failed = riscv_cpu_do_transaction_failed, .do_unaligned_access = riscv_cpu_do_unaligned_access, diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h index bf1c899c00..e735e53e26 100644 --- a/target/riscv/cpu.h +++ b/target/riscv/cpu.h @@ -334,7 +334,6 @@ int riscv_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int cpuid, void *opaque); int riscv_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int riscv_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); -bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request); bool riscv_cpu_fp_enabled(CPURISCVState *env); bool riscv_cpu_virt_enabled(CPURISCVState *env); void riscv_cpu_set_virt_enabled(CPURISCVState *env, bool enable); @@ -362,6 +361,7 @@ void riscv_cpu_list(void); #define cpu_mmu_index riscv_cpu_mmu_index #ifndef CONFIG_USER_ONLY +bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request); void riscv_cpu_swap_hypervisor_regs(CPURISCVState *env); int riscv_cpu_claim_interrupts(RISCVCPU *cpu, uint32_t interrupts); uint32_t riscv_cpu_update_mip(RISCVCPU *cpu, uint32_t mask, uint32_t value); diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c index 968cb8046f..701858d670 100644 --- a/target/riscv/cpu_helper.c +++ b/target/riscv/cpu_helper.c @@ -75,11 +75,9 @@ static int riscv_cpu_local_irq_pending(CPURISCVState *env) return RISCV_EXCP_NONE; /* indicates no pending interrupt */ } } -#endif bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { -#if !defined(CONFIG_USER_ONLY) if (interrupt_request & CPU_INTERRUPT_HARD) { RISCVCPU *cpu = RISCV_CPU(cs); CPURISCVState *env = &cpu->env; @@ -90,12 +88,9 @@ bool riscv_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return true; } } -#endif return false; } -#if !defined(CONFIG_USER_ONLY) - /* Return true is floating point support is currently enabled */ bool riscv_cpu_fp_enabled(CPURISCVState *env) { diff --git a/target/riscv/translate.c b/target/riscv/translate.c index e356fc6c46..74b33fa3c9 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -500,7 +500,8 @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode) } else { uint32_t opcode32 = opcode; opcode32 = deposit32(opcode32, 16, 16, - translator_lduw(env, ctx->base.pc_next + 2)); + translator_lduw(env, &ctx->base, + ctx->base.pc_next + 2)); ctx->pc_succ_insn = ctx->base.pc_next + 4; if (!decode_insn32(ctx, opcode32)) { gen_exception_illegal(ctx); @@ -561,7 +562,7 @@ static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *ctx = container_of(dcbase, DisasContext, base); CPURISCVState *env = cpu->env_ptr; - uint16_t opcode16 = translator_lduw(env, ctx->base.pc_next); + uint16_t opcode16 = translator_lduw(env, &ctx->base, ctx->base.pc_next); decode_opc(env, ctx, opcode16); ctx->base.pc_next = ctx->pc_succ_insn; diff --git a/target/rx/cpu.c b/target/rx/cpu.c index 96cc96e514..25a4aa2976 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -186,10 +186,10 @@ static const struct SysemuCPUOps rx_sysemu_ops = { static const struct TCGCPUOps rx_tcg_ops = { .initialize = rx_translate_init, .synchronize_from_tb = rx_cpu_synchronize_from_tb, - .cpu_exec_interrupt = rx_cpu_exec_interrupt, .tlb_fill = rx_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = rx_cpu_exec_interrupt, .do_interrupt = rx_cpu_do_interrupt, #endif /* !CONFIG_USER_ONLY */ }; diff --git a/target/rx/cpu.h b/target/rx/cpu.h index 0b4b998c7b..faa3606f52 100644 --- a/target/rx/cpu.h +++ b/target/rx/cpu.h @@ -124,8 +124,10 @@ typedef RXCPU ArchCPU; #define CPU_RESOLVING_TYPE TYPE_RX_CPU const char *rx_crname(uint8_t cr); +#ifndef CONFIG_USER_ONLY void rx_cpu_do_interrupt(CPUState *cpu); bool rx_cpu_exec_interrupt(CPUState *cpu, int int_req); +#endif /* !CONFIG_USER_ONLY */ void rx_cpu_dump_state(CPUState *cpu, FILE *f, int flags); int rx_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int rx_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); diff --git a/target/rx/helper.c b/target/rx/helper.c index db6b07e389..f34945e7e2 100644 --- a/target/rx/helper.c +++ b/target/rx/helper.c @@ -40,6 +40,8 @@ void rx_cpu_unpack_psw(CPURXState *env, uint32_t psw, int rte) env->psw_c = FIELD_EX32(psw, PSW, C); } +#ifndef CONFIG_USER_ONLY + #define INT_FLAGS (CPU_INTERRUPT_HARD | CPU_INTERRUPT_FIR) void rx_cpu_do_interrupt(CPUState *cs) { @@ -142,6 +144,8 @@ bool rx_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + hwaddr rx_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) { return addr; diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c index 0632b0374b..f284870cd2 100644 --- a/target/s390x/tcg/translate.c +++ b/target/s390x/tcg/translate.c @@ -388,14 +388,16 @@ static void update_cc_op(DisasContext *s) } } -static inline uint64_t ld_code2(CPUS390XState *env, uint64_t pc) +static inline uint64_t ld_code2(CPUS390XState *env, DisasContext *s, + uint64_t pc) { - return (uint64_t)cpu_lduw_code(env, pc); + return (uint64_t)translator_lduw(env, &s->base, pc); } -static inline uint64_t ld_code4(CPUS390XState *env, uint64_t pc) +static inline uint64_t ld_code4(CPUS390XState *env, DisasContext *s, + uint64_t pc) { - return (uint64_t)(uint32_t)cpu_ldl_code(env, pc); + return (uint64_t)(uint32_t)translator_ldl(env, &s->base, pc); } static int get_mem_index(DisasContext *s) @@ -6273,7 +6275,7 @@ static const DisasInsn *extract_insn(CPUS390XState *env, DisasContext *s) ilen = s->ex_value & 0xf; op = insn >> 56; } else { - insn = ld_code2(env, pc); + insn = ld_code2(env, s, pc); op = (insn >> 8) & 0xff; ilen = get_ilen(op); switch (ilen) { @@ -6281,10 +6283,10 @@ static const DisasInsn *extract_insn(CPUS390XState *env, DisasContext *s) insn = insn << 48; break; case 4: - insn = ld_code4(env, pc) << 32; + insn = ld_code4(env, s, pc) << 32; break; case 6: - insn = (insn << 48) | (ld_code4(env, pc + 2) << 16); + insn = (insn << 48) | (ld_code4(env, s, pc + 2) << 16); break; default: g_assert_not_reached(); diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index 8326922942..2047742d03 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -236,10 +236,10 @@ static const struct SysemuCPUOps sh4_sysemu_ops = { static const struct TCGCPUOps superh_tcg_ops = { .initialize = sh4_translate_init, .synchronize_from_tb = superh_cpu_synchronize_from_tb, - .cpu_exec_interrupt = superh_cpu_exec_interrupt, .tlb_fill = superh_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = superh_cpu_exec_interrupt, .do_interrupt = superh_cpu_do_interrupt, .do_unaligned_access = superh_cpu_do_unaligned_access, .io_recompile_replay_branch = superh_io_recompile_replay_branch, diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h index 01c4344082..017a770214 100644 --- a/target/sh4/cpu.h +++ b/target/sh4/cpu.h @@ -204,8 +204,6 @@ struct SuperHCPU { }; -void superh_cpu_do_interrupt(CPUState *cpu); -bool superh_cpu_exec_interrupt(CPUState *cpu, int int_req); void superh_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr superh_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int superh_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); @@ -223,6 +221,8 @@ bool superh_cpu_tlb_fill(CPUState *cs, vaddr address, int size, void sh4_cpu_list(void); #if !defined(CONFIG_USER_ONLY) +void superh_cpu_do_interrupt(CPUState *cpu); +bool superh_cpu_exec_interrupt(CPUState *cpu, int int_req); void cpu_sh4_invalidate_tlb(CPUSH4State *s); uint32_t cpu_sh4_read_mmaped_itlb_addr(CPUSH4State *s, hwaddr addr); diff --git a/target/sh4/helper.c b/target/sh4/helper.c index 2d622081e8..53cb9c3b63 100644 --- a/target/sh4/helper.c +++ b/target/sh4/helper.c @@ -45,11 +45,6 @@ #if defined(CONFIG_USER_ONLY) -void superh_cpu_do_interrupt(CPUState *cs) -{ - cs->exception_index = -1; -} - int cpu_sh4_is_cached(CPUSH4State *env, target_ulong addr) { /* For user mode, only U0 area is cacheable. */ @@ -784,8 +779,6 @@ int cpu_sh4_is_cached(CPUSH4State * env, target_ulong addr) return 0; } -#endif - bool superh_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { if (interrupt_request & CPU_INTERRUPT_HARD) { @@ -803,6 +796,8 @@ bool superh_cpu_exec_interrupt(CPUState *cs, int interrupt_request) return false; } +#endif /* !CONFIG_USER_ONLY */ + bool superh_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr) diff --git a/target/sh4/translate.c b/target/sh4/translate.c index 8704fea1ca..cf5fe9243d 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -1907,7 +1907,7 @@ static void decode_gusa(DisasContext *ctx, CPUSH4State *env) /* Read all of the insns for the region. */ for (i = 0; i < max_insns; ++i) { - insns[i] = translator_lduw(env, pc + i * 2); + insns[i] = translator_lduw(env, &ctx->base, pc + i * 2); } ld_adr = ld_dst = ld_mop = -1; @@ -2307,7 +2307,7 @@ static void sh4_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) } #endif - ctx->opcode = translator_lduw(env, ctx->base.pc_next); + ctx->opcode = translator_lduw(env, &ctx->base, ctx->base.pc_next); decode_opc(ctx); ctx->base.pc_next += 2; } diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index da6b30ec74..21dd27796d 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -77,6 +77,7 @@ static void sparc_cpu_reset(DeviceState *dev) env->cache_control = 0; } +#ifndef CONFIG_USER_ONLY static bool sparc_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { if (interrupt_request & CPU_INTERRUPT_HARD) { @@ -96,6 +97,7 @@ static bool sparc_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } return false; } +#endif /* !CONFIG_USER_ONLY */ static void cpu_sparc_disas_set_info(CPUState *cpu, disassemble_info *info) { @@ -610,7 +612,7 @@ static void cpu_print_cc(FILE *f, uint32_t cc) #define REGS_PER_LINE 8 #endif -void sparc_cpu_dump_state(CPUState *cs, FILE *f, int flags) +static void sparc_cpu_dump_state(CPUState *cs, FILE *f, int flags) { SPARCCPU *cpu = SPARC_CPU(cs); CPUSPARCState *env = &cpu->env; @@ -863,10 +865,10 @@ static const struct SysemuCPUOps sparc_sysemu_ops = { static const struct TCGCPUOps sparc_tcg_ops = { .initialize = sparc_tcg_init, .synchronize_from_tb = sparc_cpu_synchronize_from_tb, - .cpu_exec_interrupt = sparc_cpu_exec_interrupt, .tlb_fill = sparc_cpu_tlb_fill, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = sparc_cpu_exec_interrupt, .do_interrupt = sparc_cpu_do_interrupt, .do_transaction_failed = sparc_cpu_do_transaction_failed, .do_unaligned_access = sparc_cpu_do_unaligned_access, diff --git a/target/sparc/cpu.h b/target/sparc/cpu.h index ff8ae73002..1f40d768d8 100644 --- a/target/sparc/cpu.h +++ b/target/sparc/cpu.h @@ -571,7 +571,6 @@ extern const VMStateDescription vmstate_sparc_cpu; #endif void sparc_cpu_do_interrupt(CPUState *cpu); -void sparc_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr sparc_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int sparc_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int sparc_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); diff --git a/target/sparc/translate.c b/target/sparc/translate.c index bb70ba17de..fdb8bbe5dc 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -5855,7 +5855,7 @@ static void sparc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) CPUSPARCState *env = cs->env_ptr; unsigned int insn; - insn = translator_ldl(env, dc->pc); + insn = translator_ldl(env, &dc->base, dc->pc); dc->base.pc_next += 4; disas_sparc_insn(dc, insn); diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index 58ec3a0862..c1cbd03595 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -192,11 +192,11 @@ static const struct SysemuCPUOps xtensa_sysemu_ops = { static const struct TCGCPUOps xtensa_tcg_ops = { .initialize = xtensa_translate_init, - .cpu_exec_interrupt = xtensa_cpu_exec_interrupt, .tlb_fill = xtensa_cpu_tlb_fill, .debug_excp_handler = xtensa_breakpoint_handler, #ifndef CONFIG_USER_ONLY + .cpu_exec_interrupt = xtensa_cpu_exec_interrupt, .do_interrupt = xtensa_cpu_do_interrupt, .do_transaction_failed = xtensa_cpu_do_transaction_failed, .do_unaligned_access = xtensa_cpu_do_unaligned_access, diff --git a/target/xtensa/cpu.h b/target/xtensa/cpu.h index 2345cb59c7..cbb720e7cc 100644 --- a/target/xtensa/cpu.h +++ b/target/xtensa/cpu.h @@ -566,12 +566,14 @@ struct XtensaCPU { bool xtensa_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr); +#ifndef CONFIG_USER_ONLY void xtensa_cpu_do_interrupt(CPUState *cpu); bool xtensa_cpu_exec_interrupt(CPUState *cpu, int interrupt_request); void xtensa_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, vaddr addr, unsigned size, MMUAccessType access_type, int mmu_idx, MemTxAttrs attrs, MemTxResult response, uintptr_t retaddr); +#endif void xtensa_cpu_dump_state(CPUState *cpu, FILE *f, int flags); hwaddr xtensa_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); void xtensa_count_regs(const XtensaConfig *config, diff --git a/target/xtensa/exc_helper.c b/target/xtensa/exc_helper.c index 10e75ab070..9bc7f50d35 100644 --- a/target/xtensa/exc_helper.c +++ b/target/xtensa/exc_helper.c @@ -255,11 +255,6 @@ void xtensa_cpu_do_interrupt(CPUState *cs) } check_interrupts(env); } -#else -void xtensa_cpu_do_interrupt(CPUState *cs) -{ -} -#endif bool xtensa_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { @@ -270,3 +265,5 @@ bool xtensa_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } return false; } + +#endif /* !CONFIG_USER_ONLY */ diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c index 20399d6a04..dcf6b500ef 100644 --- a/target/xtensa/translate.c +++ b/target/xtensa/translate.c @@ -882,7 +882,8 @@ static int arg_copy_compare(const void *a, const void *b) static void disas_xtensa_insn(CPUXtensaState *env, DisasContext *dc) { xtensa_isa isa = dc->config->isa; - unsigned char b[MAX_INSN_LENGTH] = {translator_ldub(env, dc->pc)}; + unsigned char b[MAX_INSN_LENGTH] = {translator_ldub(env, &dc->base, + dc->pc)}; unsigned len = xtensa_op0_insn_len(dc, b[0]); xtensa_format fmt; int slot, slots; @@ -907,7 +908,7 @@ static void disas_xtensa_insn(CPUXtensaState *env, DisasContext *dc) dc->base.pc_next = dc->pc + len; for (i = 1; i < len; ++i) { - b[i] = translator_ldub(env, dc->pc + i); + b[i] = translator_ldub(env, &dc->base, dc->pc + i); } xtensa_insnbuf_from_chars(isa, dc->insnbuf, b, len); fmt = xtensa_format_decode(isa, dc->insnbuf); diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index 007ceee68e..d25e68b36b 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -92,7 +92,7 @@ static const int tcg_target_call_oarg_regs[2] = { #define TCG_REG_TMP TCG_REG_R12 #define TCG_VEC_TMP TCG_REG_Q15 -enum arm_cond_code_e { +typedef enum { COND_EQ = 0x0, COND_NE = 0x1, COND_CS = 0x2, /* Unsigned greater or equal */ @@ -108,7 +108,7 @@ enum arm_cond_code_e { COND_GT = 0xc, COND_LE = 0xd, COND_AL = 0xe, -}; +} ARMCond; #define TO_CPSR (1 << 20) @@ -141,6 +141,9 @@ typedef enum { INSN_CLZ = 0x016f0f10, INSN_RBIT = 0x06ff0f30, + INSN_LDMIA = 0x08b00000, + INSN_STMDB = 0x09200000, + INSN_LDR_IMM = 0x04100000, INSN_LDR_REG = 0x06100000, INSN_STR_IMM = 0x04000000, @@ -309,10 +312,10 @@ static bool reloc_pc8(tcg_insn_unit *src_rw, const tcg_insn_unit *target) { const tcg_insn_unit *src_rx = tcg_splitwx_to_rx(src_rw); ptrdiff_t offset = tcg_ptr_byte_diff(target, src_rx) - 8; - int rot = encode_imm(offset); + int imm12 = encode_imm(offset); - if (rot >= 0) { - *src_rw = deposit32(*src_rw, 0, 12, rol32(offset, rot) | (rot << 7)); + if (imm12 >= 0) { + *src_rw = deposit32(*src_rw, 0, 12, imm12); return true; } return false; @@ -366,36 +369,55 @@ static bool patch_reloc(tcg_insn_unit *code_ptr, int type, (ALL_GENERAL_REGS & ~((1 << TCG_REG_R0) | (1 << TCG_REG_R1))) #endif -static inline uint32_t rotl(uint32_t val, int n) -{ - return (val << n) | (val >> (32 - n)); -} - -/* ARM immediates for ALU instructions are made of an unsigned 8-bit - right-rotated by an even amount between 0 and 30. */ +/* + * ARM immediates for ALU instructions are made of an unsigned 8-bit + * right-rotated by an even amount between 0 and 30. + * + * Return < 0 if @imm cannot be encoded, else the entire imm12 field. + */ static int encode_imm(uint32_t imm) { - int shift; + uint32_t rot, imm8; - /* simple case, only lower bits */ - if ((imm & ~0xff) == 0) - return 0; - /* then try a simple even shift */ - shift = ctz32(imm) & ~1; - if (((imm >> shift) & ~0xff) == 0) - return 32 - shift; - /* now try harder with rotations */ - if ((rotl(imm, 2) & ~0xff) == 0) - return 2; - if ((rotl(imm, 4) & ~0xff) == 0) - return 4; - if ((rotl(imm, 6) & ~0xff) == 0) - return 6; - /* imm can't be encoded */ + /* Simple case, no rotation required. */ + if ((imm & ~0xff) == 0) { + return imm; + } + + /* Next, try a simple even shift. */ + rot = ctz32(imm) & ~1; + imm8 = imm >> rot; + rot = 32 - rot; + if ((imm8 & ~0xff) == 0) { + goto found; + } + + /* + * Finally, try harder with rotations. + * The ctz test above will have taken care of rotates >= 8. + */ + for (rot = 2; rot < 8; rot += 2) { + imm8 = rol32(imm, rot); + if ((imm8 & ~0xff) == 0) { + goto found; + } + } + /* Fail: imm cannot be encoded. */ return -1; + + found: + /* Note that rot is even, and we discard bit 0 by shifting by 7. */ + return rot << 7 | imm8; +} + +static int encode_imm_nofail(uint32_t imm) +{ + int ret = encode_imm(imm); + tcg_debug_assert(ret >= 0); + return ret; } -static inline int check_fit_imm(uint32_t imm) +static bool check_fit_imm(uint32_t imm) { return encode_imm(imm) >= 0; } @@ -525,42 +547,37 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) return 0; } -static inline void tcg_out_b(TCGContext *s, int cond, int32_t offset) +static void tcg_out_b_imm(TCGContext *s, ARMCond cond, int32_t offset) { tcg_out32(s, (cond << 28) | 0x0a000000 | (((offset - 8) >> 2) & 0x00ffffff)); } -static inline void tcg_out_bl(TCGContext *s, int cond, int32_t offset) +static void tcg_out_bl_imm(TCGContext *s, ARMCond cond, int32_t offset) { tcg_out32(s, (cond << 28) | 0x0b000000 | (((offset - 8) >> 2) & 0x00ffffff)); } -static inline void tcg_out_blx(TCGContext *s, int cond, int rn) +static void tcg_out_blx_reg(TCGContext *s, ARMCond cond, TCGReg rn) { tcg_out32(s, (cond << 28) | 0x012fff30 | rn); } -static inline void tcg_out_blx_imm(TCGContext *s, int32_t offset) +static void tcg_out_blx_imm(TCGContext *s, int32_t offset) { tcg_out32(s, 0xfa000000 | ((offset & 2) << 23) | (((offset - 8) >> 2) & 0x00ffffff)); } -static inline void tcg_out_dat_reg(TCGContext *s, - int cond, int opc, int rd, int rn, int rm, int shift) +static void tcg_out_dat_reg(TCGContext *s, ARMCond cond, ARMInsn opc, + TCGReg rd, TCGReg rn, TCGReg rm, int shift) { tcg_out32(s, (cond << 28) | (0 << 25) | opc | (rn << 16) | (rd << 12) | shift | rm); } -static inline void tcg_out_nop(TCGContext *s) -{ - tcg_out32(s, INSN_NOP); -} - -static inline void tcg_out_mov_reg(TCGContext *s, int cond, int rd, int rm) +static void tcg_out_mov_reg(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rm) { /* Simple reg-reg move, optimising out the 'do nothing' case */ if (rd != rm) { @@ -568,35 +585,47 @@ static inline void tcg_out_mov_reg(TCGContext *s, int cond, int rd, int rm) } } -static inline void tcg_out_bx(TCGContext *s, int cond, TCGReg rn) +static void tcg_out_bx_reg(TCGContext *s, ARMCond cond, TCGReg rn) +{ + tcg_out32(s, (cond << 28) | 0x012fff10 | rn); +} + +static void tcg_out_b_reg(TCGContext *s, ARMCond cond, TCGReg rn) { - /* Unless the C portion of QEMU is compiled as thumb, we don't - actually need true BX semantics; merely a branch to an address - held in a register. */ + /* + * Unless the C portion of QEMU is compiled as thumb, we don't need + * true BX semantics; merely a branch to an address held in a register. + */ if (use_armv5t_instructions) { - tcg_out32(s, (cond << 28) | 0x012fff10 | rn); + tcg_out_bx_reg(s, cond, rn); } else { tcg_out_mov_reg(s, cond, TCG_REG_PC, rn); } } -static inline void tcg_out_dat_imm(TCGContext *s, - int cond, int opc, int rd, int rn, int im) +static void tcg_out_dat_imm(TCGContext *s, ARMCond cond, ARMInsn opc, + TCGReg rd, TCGReg rn, int im) { tcg_out32(s, (cond << 28) | (1 << 25) | opc | (rn << 16) | (rd << 12) | im); } +static void tcg_out_ldstm(TCGContext *s, ARMCond cond, ARMInsn opc, + TCGReg rn, uint16_t mask) +{ + tcg_out32(s, (cond << 28) | opc | (rn << 16) | mask); +} + /* Note that this routine is used for both LDR and LDRH formats, so we do not wish to include an immediate shift at this point. */ -static void tcg_out_memop_r(TCGContext *s, int cond, ARMInsn opc, TCGReg rt, +static void tcg_out_memop_r(TCGContext *s, ARMCond cond, ARMInsn opc, TCGReg rt, TCGReg rn, TCGReg rm, bool u, bool p, bool w) { tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24) | (w << 21) | (rn << 16) | (rt << 12) | rm); } -static void tcg_out_memop_8(TCGContext *s, int cond, ARMInsn opc, TCGReg rt, +static void tcg_out_memop_8(TCGContext *s, ARMCond cond, ARMInsn opc, TCGReg rt, TCGReg rn, int imm8, bool p, bool w) { bool u = 1; @@ -608,8 +637,8 @@ static void tcg_out_memop_8(TCGContext *s, int cond, ARMInsn opc, TCGReg rt, (rn << 16) | (rt << 12) | ((imm8 & 0xf0) << 4) | (imm8 & 0xf)); } -static void tcg_out_memop_12(TCGContext *s, int cond, ARMInsn opc, TCGReg rt, - TCGReg rn, int imm12, bool p, bool w) +static void tcg_out_memop_12(TCGContext *s, ARMCond cond, ARMInsn opc, + TCGReg rt, TCGReg rn, int imm12, bool p, bool w) { bool u = 1; if (imm12 < 0) { @@ -620,167 +649,167 @@ static void tcg_out_memop_12(TCGContext *s, int cond, ARMInsn opc, TCGReg rt, (rn << 16) | (rt << 12) | imm12); } -static inline void tcg_out_ld32_12(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm12) +static void tcg_out_ld32_12(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm12) { tcg_out_memop_12(s, cond, INSN_LDR_IMM, rt, rn, imm12, 1, 0); } -static inline void tcg_out_st32_12(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm12) +static void tcg_out_st32_12(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm12) { tcg_out_memop_12(s, cond, INSN_STR_IMM, rt, rn, imm12, 1, 0); } -static inline void tcg_out_ld32_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld32_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_st32_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_st32_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_ldrd_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_ldrd_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_LDRD_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_ldrd_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ldrd_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRD_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_ldrd_rwb(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void __attribute__((unused)) +tcg_out_ldrd_rwb(TCGContext *s, ARMCond cond, TCGReg rt, TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRD_REG, rt, rn, rm, 1, 1, 1); } -static inline void tcg_out_strd_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_strd_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_STRD_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_strd_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_strd_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_STRD_REG, rt, rn, rm, 1, 1, 0); } /* Register pre-increment with base writeback. */ -static inline void tcg_out_ld32_rwb(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld32_rwb(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 1); } -static inline void tcg_out_st32_rwb(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_st32_rwb(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 1); } -static inline void tcg_out_ld16u_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_ld16u_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_LDRH_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_st16_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_st16_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_STRH_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_ld16u_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld16u_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRH_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_st16_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_st16_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_STRH_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_ld16s_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_ld16s_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_LDRSH_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_ld16s_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld16s_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRSH_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_ld8_12(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm12) +static void tcg_out_ld8_12(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm12) { tcg_out_memop_12(s, cond, INSN_LDRB_IMM, rt, rn, imm12, 1, 0); } -static inline void tcg_out_st8_12(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm12) +static void tcg_out_st8_12(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm12) { tcg_out_memop_12(s, cond, INSN_STRB_IMM, rt, rn, imm12, 1, 0); } -static inline void tcg_out_ld8_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld8_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRB_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_st8_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_st8_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_STRB_REG, rt, rn, rm, 1, 1, 0); } -static inline void tcg_out_ld8s_8(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, int imm8) +static void tcg_out_ld8s_8(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, int imm8) { tcg_out_memop_8(s, cond, INSN_LDRSB_IMM, rt, rn, imm8, 1, 0); } -static inline void tcg_out_ld8s_r(TCGContext *s, int cond, TCGReg rt, - TCGReg rn, TCGReg rm) +static void tcg_out_ld8s_r(TCGContext *s, ARMCond cond, TCGReg rt, + TCGReg rn, TCGReg rm) { tcg_out_memop_r(s, cond, INSN_LDRSB_REG, rt, rn, rm, 1, 1, 0); } -static void tcg_out_movi_pool(TCGContext *s, int cond, int rd, uint32_t arg) +static void tcg_out_movi_pool(TCGContext *s, ARMCond cond, + TCGReg rd, uint32_t arg) { new_pool_label(s, arg, R_ARM_PC13, s->code_ptr, 0); tcg_out_ld32_12(s, cond, rd, TCG_REG_PC, 0); } -static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg) +static void tcg_out_movi32(TCGContext *s, ARMCond cond, + TCGReg rd, uint32_t arg) { - int rot, diff, opc, sh1, sh2; + int imm12, diff, opc, sh1, sh2; uint32_t tt0, tt1, tt2; /* Check a single MOV/MVN before anything else. */ - rot = encode_imm(arg); - if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0, - rotl(arg, rot) | (rot << 7)); + imm12 = encode_imm(arg); + if (imm12 >= 0) { + tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0, imm12); return; } - rot = encode_imm(~arg); - if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0, - rotl(~arg, rot) | (rot << 7)); + imm12 = encode_imm(~arg); + if (imm12 >= 0) { + tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0, imm12); return; } @@ -788,17 +817,15 @@ static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg) or within the TB, which is immediately before the code block. */ diff = tcg_pcrel_diff(s, (void *)arg) - 8; if (diff >= 0) { - rot = encode_imm(diff); - if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_ADD, rd, TCG_REG_PC, - rotl(diff, rot) | (rot << 7)); + imm12 = encode_imm(diff); + if (imm12 >= 0) { + tcg_out_dat_imm(s, cond, ARITH_ADD, rd, TCG_REG_PC, imm12); return; } } else { - rot = encode_imm(-diff); - if (rot >= 0) { - tcg_out_dat_imm(s, cond, ARITH_SUB, rd, TCG_REG_PC, - rotl(-diff, rot) | (rot << 7)); + imm12 = encode_imm(-diff); + if (imm12 >= 0) { + tcg_out_dat_imm(s, cond, ARITH_SUB, rd, TCG_REG_PC, imm12); return; } } @@ -830,6 +857,8 @@ static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg) sh2 = ctz32(tt1) & ~1; tt2 = tt1 & ~(0xff << sh2); if (tt2 == 0) { + int rot; + rot = ((32 - sh1) << 7) & 0xf00; tcg_out_dat_imm(s, cond, opc, rd, 0, ((tt0 >> sh1) & 0xff) | rot); rot = ((32 - sh2) << 7) & 0xf00; @@ -842,65 +871,61 @@ static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg) tcg_out_movi_pool(s, cond, rd, arg); } -static inline void tcg_out_dat_rI(TCGContext *s, int cond, int opc, TCGArg dst, - TCGArg lhs, TCGArg rhs, int rhs_is_const) +/* + * Emit either the reg,imm or reg,reg form of a data-processing insn. + * rhs must satisfy the "rI" constraint. + */ +static void tcg_out_dat_rI(TCGContext *s, ARMCond cond, ARMInsn opc, + TCGReg dst, TCGReg lhs, TCGArg rhs, int rhs_is_const) { - /* Emit either the reg,imm or reg,reg form of a data-processing insn. - * rhs must satisfy the "rI" constraint. - */ if (rhs_is_const) { - int rot = encode_imm(rhs); - tcg_debug_assert(rot >= 0); - tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7)); + tcg_out_dat_imm(s, cond, opc, dst, lhs, encode_imm_nofail(rhs)); } else { tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0)); } } -static void tcg_out_dat_rIK(TCGContext *s, int cond, int opc, int opinv, - TCGReg dst, TCGReg lhs, TCGArg rhs, +/* + * Emit either the reg,imm or reg,reg form of a data-processing insn. + * rhs must satisfy the "rIK" constraint. + */ +static void tcg_out_dat_rIK(TCGContext *s, ARMCond cond, ARMInsn opc, + ARMInsn opinv, TCGReg dst, TCGReg lhs, TCGArg rhs, bool rhs_is_const) { - /* Emit either the reg,imm or reg,reg form of a data-processing insn. - * rhs must satisfy the "rIK" constraint. - */ if (rhs_is_const) { - int rot = encode_imm(rhs); - if (rot < 0) { - rhs = ~rhs; - rot = encode_imm(rhs); - tcg_debug_assert(rot >= 0); + int imm12 = encode_imm(rhs); + if (imm12 < 0) { + imm12 = encode_imm_nofail(~rhs); opc = opinv; } - tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7)); + tcg_out_dat_imm(s, cond, opc, dst, lhs, imm12); } else { tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0)); } } -static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg, - TCGArg dst, TCGArg lhs, TCGArg rhs, +static void tcg_out_dat_rIN(TCGContext *s, ARMCond cond, ARMInsn opc, + ARMInsn opneg, TCGReg dst, TCGReg lhs, TCGArg rhs, bool rhs_is_const) { /* Emit either the reg,imm or reg,reg form of a data-processing insn. * rhs must satisfy the "rIN" constraint. */ if (rhs_is_const) { - int rot = encode_imm(rhs); - if (rot < 0) { - rhs = -rhs; - rot = encode_imm(rhs); - tcg_debug_assert(rot >= 0); + int imm12 = encode_imm(rhs); + if (imm12 < 0) { + imm12 = encode_imm_nofail(-rhs); opc = opneg; } - tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7)); + tcg_out_dat_imm(s, cond, opc, dst, lhs, imm12); } else { tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0)); } } -static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd, - TCGReg rn, TCGReg rm) +static void tcg_out_mul32(TCGContext *s, ARMCond cond, TCGReg rd, + TCGReg rn, TCGReg rm) { /* if ArchVersion() < 6 && d == n then UNPREDICTABLE; */ if (!use_armv6_instructions && rd == rn) { @@ -917,8 +942,8 @@ static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd, tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn); } -static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0, - TCGReg rd1, TCGReg rn, TCGReg rm) +static void tcg_out_umull32(TCGContext *s, ARMCond cond, TCGReg rd0, + TCGReg rd1, TCGReg rn, TCGReg rm) { /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE; */ if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) { @@ -936,8 +961,8 @@ static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0, (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn); } -static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0, - TCGReg rd1, TCGReg rn, TCGReg rm) +static void tcg_out_smull32(TCGContext *s, ARMCond cond, TCGReg rd0, + TCGReg rd1, TCGReg rn, TCGReg rm) { /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE; */ if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) { @@ -955,18 +980,19 @@ static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0, (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn); } -static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm) +static void tcg_out_sdiv(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, TCGReg rm) { tcg_out32(s, 0x0710f010 | (cond << 28) | (rd << 16) | rn | (rm << 8)); } -static inline void tcg_out_udiv(TCGContext *s, int cond, int rd, int rn, int rm) +static void tcg_out_udiv(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, TCGReg rm) { tcg_out32(s, 0x0730f010 | (cond << 28) | (rd << 16) | rn | (rm << 8)); } -static inline void tcg_out_ext8s(TCGContext *s, int cond, - int rd, int rn) +static void tcg_out_ext8s(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rn) { if (use_armv6_instructions) { /* sxtb */ @@ -979,14 +1005,13 @@ static inline void tcg_out_ext8s(TCGContext *s, int cond, } } -static inline void tcg_out_ext8u(TCGContext *s, int cond, - int rd, int rn) +static void __attribute__((unused)) +tcg_out_ext8u(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rn) { tcg_out_dat_imm(s, cond, ARITH_AND, rd, rn, 0xff); } -static inline void tcg_out_ext16s(TCGContext *s, int cond, - int rd, int rn) +static void tcg_out_ext16s(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rn) { if (use_armv6_instructions) { /* sxth */ @@ -999,8 +1024,7 @@ static inline void tcg_out_ext16s(TCGContext *s, int cond, } } -static inline void tcg_out_ext16u(TCGContext *s, int cond, - int rd, int rn) +static void tcg_out_ext16u(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rn) { if (use_armv6_instructions) { /* uxth */ @@ -1013,7 +1037,8 @@ static inline void tcg_out_ext16u(TCGContext *s, int cond, } } -static void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn, int flags) +static void tcg_out_bswap16(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int flags) { if (use_armv6_instructions) { if (flags & TCG_BSWAP_OS) { @@ -1080,7 +1105,7 @@ static void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn, int flags) ? SHIFT_IMM_ASR(8) : SHIFT_IMM_LSR(8))); } -static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn) +static void tcg_out_bswap32(TCGContext *s, ARMCond cond, TCGReg rd, TCGReg rn) { if (use_armv6_instructions) { /* rev */ @@ -1097,8 +1122,8 @@ static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn) } } -static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd, - TCGArg a1, int ofs, int len, bool const_a1) +static void tcg_out_deposit(TCGContext *s, ARMCond cond, TCGReg rd, + TCGArg a1, int ofs, int len, bool const_a1) { if (const_a1) { /* bfi becomes bfc with rn == 15. */ @@ -1109,24 +1134,24 @@ static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd, | (ofs << 7) | ((ofs + len - 1) << 16)); } -static inline void tcg_out_extract(TCGContext *s, int cond, TCGReg rd, - TCGArg a1, int ofs, int len) +static void tcg_out_extract(TCGContext *s, ARMCond cond, TCGReg rd, + TCGReg rn, int ofs, int len) { /* ubfx */ - tcg_out32(s, 0x07e00050 | (cond << 28) | (rd << 12) | a1 + tcg_out32(s, 0x07e00050 | (cond << 28) | (rd << 12) | rn | (ofs << 7) | ((len - 1) << 16)); } -static inline void tcg_out_sextract(TCGContext *s, int cond, TCGReg rd, - TCGArg a1, int ofs, int len) +static void tcg_out_sextract(TCGContext *s, ARMCond cond, TCGReg rd, + TCGReg rn, int ofs, int len) { /* sbfx */ - tcg_out32(s, 0x07a00050 | (cond << 28) | (rd << 12) | a1 + tcg_out32(s, 0x07a00050 | (cond << 28) | (rd << 12) | rn | (ofs << 7) | ((len - 1) << 16)); } -static inline void tcg_out_ld32u(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_ld32u(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xfff || offset < -0xfff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1135,8 +1160,8 @@ static inline void tcg_out_ld32u(TCGContext *s, int cond, tcg_out_ld32_12(s, cond, rd, rn, offset); } -static inline void tcg_out_st32(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_st32(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xfff || offset < -0xfff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1145,8 +1170,8 @@ static inline void tcg_out_st32(TCGContext *s, int cond, tcg_out_st32_12(s, cond, rd, rn, offset); } -static inline void tcg_out_ld16u(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_ld16u(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xff || offset < -0xff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1155,8 +1180,8 @@ static inline void tcg_out_ld16u(TCGContext *s, int cond, tcg_out_ld16u_8(s, cond, rd, rn, offset); } -static inline void tcg_out_ld16s(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_ld16s(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xff || offset < -0xff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1165,8 +1190,8 @@ static inline void tcg_out_ld16s(TCGContext *s, int cond, tcg_out_ld16s_8(s, cond, rd, rn, offset); } -static inline void tcg_out_st16(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_st16(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xff || offset < -0xff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1175,8 +1200,8 @@ static inline void tcg_out_st16(TCGContext *s, int cond, tcg_out_st16_8(s, cond, rd, rn, offset); } -static inline void tcg_out_ld8u(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_ld8u(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xfff || offset < -0xfff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1185,8 +1210,8 @@ static inline void tcg_out_ld8u(TCGContext *s, int cond, tcg_out_ld8_12(s, cond, rd, rn, offset); } -static inline void tcg_out_ld8s(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_ld8s(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xff || offset < -0xff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1195,8 +1220,8 @@ static inline void tcg_out_ld8s(TCGContext *s, int cond, tcg_out_ld8s_8(s, cond, rd, rn, offset); } -static inline void tcg_out_st8(TCGContext *s, int cond, - int rd, int rn, int32_t offset) +static void tcg_out_st8(TCGContext *s, ARMCond cond, + TCGReg rd, TCGReg rn, int32_t offset) { if (offset > 0xfff || offset < -0xfff) { tcg_out_movi32(s, cond, TCG_REG_TMP, offset); @@ -1205,60 +1230,79 @@ static inline void tcg_out_st8(TCGContext *s, int cond, tcg_out_st8_12(s, cond, rd, rn, offset); } -/* The _goto case is normally between TBs within the same code buffer, and +/* + * The _goto case is normally between TBs within the same code buffer, and * with the code buffer limited to 16MB we wouldn't need the long case. * But we also use it for the tail-call to the qemu_ld/st helpers, which does. */ -static void tcg_out_goto(TCGContext *s, int cond, const tcg_insn_unit *addr) +static void tcg_out_goto(TCGContext *s, ARMCond cond, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr); + bool arm_mode = !(addri & 1); - if ((addri & 1) == 0 && disp - 8 < 0x01fffffd && disp - 8 > -0x01fffffd) { - tcg_out_b(s, cond, disp); + if (arm_mode && disp - 8 < 0x01fffffd && disp - 8 > -0x01fffffd) { + tcg_out_b_imm(s, cond, disp); return; } - tcg_out_movi_pool(s, cond, TCG_REG_PC, addri); + + /* LDR is interworking from v5t. */ + if (arm_mode || use_armv5t_instructions) { + tcg_out_movi_pool(s, cond, TCG_REG_PC, addri); + return; + } + + /* else v4t */ + tcg_out_movi32(s, COND_AL, TCG_REG_TMP, addri); + tcg_out_bx_reg(s, COND_AL, TCG_REG_TMP); } -/* The call case is mostly used for helpers - so it's not unreasonable - * for them to be beyond branch range */ +/* + * The call case is mostly used for helpers - so it's not unreasonable + * for them to be beyond branch range. + */ static void tcg_out_call(TCGContext *s, const tcg_insn_unit *addr) { intptr_t addri = (intptr_t)addr; ptrdiff_t disp = tcg_pcrel_diff(s, addr); + bool arm_mode = !(addri & 1); if (disp - 8 < 0x02000000 && disp - 8 >= -0x02000000) { - if (addri & 1) { - /* Use BLX if the target is in Thumb mode */ - if (!use_armv5t_instructions) { - tcg_abort(); - } + if (arm_mode) { + tcg_out_bl_imm(s, COND_AL, disp); + return; + } + if (use_armv5t_instructions) { tcg_out_blx_imm(s, disp); - } else { - tcg_out_bl(s, COND_AL, disp); + return; } - } else if (use_armv7_instructions) { + } + + if (use_armv5t_instructions) { tcg_out_movi32(s, COND_AL, TCG_REG_TMP, addri); - tcg_out_blx(s, COND_AL, TCG_REG_TMP); - } else { + tcg_out_blx_reg(s, COND_AL, TCG_REG_TMP); + } else if (arm_mode) { /* ??? Know that movi_pool emits exactly 1 insn. */ - tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R14, TCG_REG_PC, 0); + tcg_out_mov_reg(s, COND_AL, TCG_REG_R14, TCG_REG_PC); tcg_out_movi_pool(s, COND_AL, TCG_REG_PC, addri); + } else { + tcg_out_movi32(s, COND_AL, TCG_REG_TMP, addri); + tcg_out_mov_reg(s, COND_AL, TCG_REG_R14, TCG_REG_PC); + tcg_out_bx_reg(s, COND_AL, TCG_REG_TMP); } } -static inline void tcg_out_goto_label(TCGContext *s, int cond, TCGLabel *l) +static void tcg_out_goto_label(TCGContext *s, ARMCond cond, TCGLabel *l) { if (l->has_value) { tcg_out_goto(s, cond, l->u.value_ptr); } else { tcg_out_reloc(s, s->code_ptr, R_ARM_PC24, l, 0); - tcg_out_b(s, cond, 0); + tcg_out_b_imm(s, cond, 0); } } -static inline void tcg_out_mb(TCGContext *s, TCGArg a0) +static void tcg_out_mb(TCGContext *s, TCGArg a0) { if (use_armv7_instructions) { tcg_out32(s, INSN_DMB_ISH); @@ -1714,9 +1758,9 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) } #endif /* SOFTMMU */ -static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo, TCGReg addend) +static void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, + TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addend) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); @@ -1757,9 +1801,9 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, } } -static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo) +#ifndef CONFIG_SOFTMMU +static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo, + TCGReg datahi, TCGReg addrlo) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); @@ -1797,6 +1841,7 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, g_assert_not_reached(); } } +#endif static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) { @@ -1823,7 +1868,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) /* This a conditional BL only to load a pointer within this opcode into LR for the slow path. We will not be using the value for a tail call. */ label_ptr = s->code_ptr; - tcg_out_bl(s, COND_NE, 0); + tcg_out_bl_imm(s, COND_NE, 0); tcg_out_qemu_ld_index(s, opc, datalo, datahi, addrlo, addend); @@ -1839,9 +1884,9 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) #endif } -static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo, TCGReg addend) +static void tcg_out_qemu_st_index(TCGContext *s, ARMCond cond, MemOp opc, + TCGReg datalo, TCGReg datahi, + TCGReg addrlo, TCGReg addend) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); @@ -1871,9 +1916,9 @@ static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc, } } -static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, - TCGReg datalo, TCGReg datahi, - TCGReg addrlo) +#ifndef CONFIG_SOFTMMU +static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, + TCGReg datahi, TCGReg addrlo) { /* Byte swapping is left to middle-end expansion. */ tcg_debug_assert((opc & MO_BSWAP) == 0); @@ -1902,6 +1947,7 @@ static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, g_assert_not_reached(); } } +#endif static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) { @@ -1929,7 +1975,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) /* The conditional call must come last, as we're going to return here. */ label_ptr = s->code_ptr; - tcg_out_bl(s, COND_NE, 0); + tcg_out_bl_imm(s, COND_NE, 0); add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi, s->code_ptr, label_ptr); @@ -1946,9 +1992,9 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) static void tcg_out_epilogue(TCGContext *s); -static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, - const TCGArg args[TCG_MAX_OP_ARGS], - const int const_args[TCG_MAX_OP_ARGS]) +static void tcg_out_op(TCGContext *s, TCGOpcode opc, + const TCGArg args[TCG_MAX_OP_ARGS], + const int const_args[TCG_MAX_OP_ARGS]) { TCGArg a0, a1, a2, a3, a4, a5; int c; @@ -1982,7 +2028,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, } break; case INDEX_op_goto_ptr: - tcg_out_bx(s, COND_AL, args[0]); + tcg_out_b_reg(s, COND_AL, args[0]); break; case INDEX_op_br: tcg_out_goto_label(s, COND_AL, arg_label(args[0])); @@ -2505,8 +2551,8 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, } } -static inline bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, - TCGReg base, intptr_t ofs) +static bool tcg_out_sti(TCGContext *s, TCGType type, TCGArg val, + TCGReg base, intptr_t ofs) { return false; } @@ -2715,7 +2761,8 @@ static const ARMInsn vec_cmp0_insn[16] = { static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, unsigned vecl, unsigned vece, - const TCGArg *args, const int *const_args) + const TCGArg args[TCG_MAX_OP_ARGS], + const int const_args[TCG_MAX_OP_ARGS]) { TCGType type = vecl + TCG_TYPE_V64; unsigned q = vecl; @@ -3055,7 +3102,10 @@ static void tcg_target_qemu_prologue(TCGContext *s) { /* Calling convention requires us to save r4-r11 and lr. */ /* stmdb sp!, { r4 - r11, lr } */ - tcg_out32(s, (COND_AL << 28) | 0x092d4ff0); + tcg_out_ldstm(s, COND_AL, INSN_STMDB, TCG_REG_CALL_STACK, + (1 << TCG_REG_R4) | (1 << TCG_REG_R5) | (1 << TCG_REG_R6) | + (1 << TCG_REG_R7) | (1 << TCG_REG_R8) | (1 << TCG_REG_R9) | + (1 << TCG_REG_R10) | (1 << TCG_REG_R11) | (1 << TCG_REG_R14)); /* Reserve callee argument and tcg temp space. */ tcg_out_dat_rI(s, COND_AL, ARITH_SUB, TCG_REG_CALL_STACK, @@ -3065,7 +3115,7 @@ static void tcg_target_qemu_prologue(TCGContext *s) tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]); - tcg_out_bx(s, COND_AL, tcg_target_call_iarg_regs[1]); + tcg_out_b_reg(s, COND_AL, tcg_target_call_iarg_regs[1]); /* * Return path for goto_ptr. Set return value to 0, a-la exit_tb, @@ -3083,7 +3133,10 @@ static void tcg_out_epilogue(TCGContext *s) TCG_REG_CALL_STACK, STACK_ADDEND, 1); /* ldmia sp!, { r4 - r11, pc } */ - tcg_out32(s, (COND_AL << 28) | 0x08bd8ff0); + tcg_out_ldstm(s, COND_AL, INSN_LDMIA, TCG_REG_CALL_STACK, + (1 << TCG_REG_R4) | (1 << TCG_REG_R5) | (1 << TCG_REG_R6) | + (1 << TCG_REG_R7) | (1 << TCG_REG_R8) | (1 << TCG_REG_R9) | + (1 << TCG_REG_R10) | (1 << TCG_REG_R11) | (1 << TCG_REG_PC)); } typedef struct { diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h index d113b7f8db..f41b809554 100644 --- a/tcg/arm/tcg-target.h +++ b/tcg/arm/tcg-target.h @@ -26,34 +26,9 @@ #ifndef ARM_TCG_TARGET_H #define ARM_TCG_TARGET_H -/* The __ARM_ARCH define is provided by gcc 4.8. Construct it otherwise. */ -#ifndef __ARM_ARCH -# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \ - || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) \ - || defined(__ARM_ARCH_7EM__) -# define __ARM_ARCH 7 -# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \ - || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) \ - || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6T2__) -# define __ARM_ARCH 6 -# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5E__) \ - || defined(__ARM_ARCH_5T__) || defined(__ARM_ARCH_5TE__) \ - || defined(__ARM_ARCH_5TEJ__) -# define __ARM_ARCH 5 -# else -# define __ARM_ARCH 4 -# endif -#endif - extern int arm_arch; -#if defined(__ARM_ARCH_5T__) \ - || defined(__ARM_ARCH_5TE__) || defined(__ARM_ARCH_5TEJ__) -# define use_armv5t_instructions 1 -#else -# define use_armv5t_instructions use_armv6_instructions -#endif - +#define use_armv5t_instructions (__ARM_ARCH >= 5 || arm_arch >= 5) #define use_armv6_instructions (__ARM_ARCH >= 6 || arm_arch >= 6) #define use_armv7_instructions (__ARM_ARCH >= 7 || arm_arch >= 7) diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 98d924b91a..997510109d 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -241,8 +241,9 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) #define P_EXT 0x100 /* 0x0f opcode prefix */ #define P_EXT38 0x200 /* 0x0f 0x38 opcode prefix */ #define P_DATA16 0x400 /* 0x66 opcode prefix */ +#define P_VEXW 0x1000 /* Set VEX.W = 1 */ #if TCG_TARGET_REG_BITS == 64 -# define P_REXW 0x1000 /* Set REX.W = 1 */ +# define P_REXW P_VEXW /* Set REX.W = 1; match VEXW */ # define P_REXB_R 0x2000 /* REG field as byte register */ # define P_REXB_RM 0x4000 /* R/M field as byte register */ # define P_GS 0x8000 /* gs segment override */ @@ -410,13 +411,13 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) #define OPC_VPBROADCASTW (0x79 | P_EXT38 | P_DATA16) #define OPC_VPBROADCASTD (0x58 | P_EXT38 | P_DATA16) #define OPC_VPBROADCASTQ (0x59 | P_EXT38 | P_DATA16) -#define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_REXW) +#define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_VEXW) #define OPC_VPERM2I128 (0x46 | P_EXT3A | P_DATA16 | P_VEXL) #define OPC_VPSLLVD (0x47 | P_EXT38 | P_DATA16) -#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_REXW) +#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_VEXW) #define OPC_VPSRAVD (0x46 | P_EXT38 | P_DATA16) #define OPC_VPSRLVD (0x45 | P_EXT38 | P_DATA16) -#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_REXW) +#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_VEXW) #define OPC_VZEROUPPER (0x77 | P_EXT) #define OPC_XCHG_ax_r32 (0x90) @@ -576,7 +577,7 @@ static void tcg_out_vex_opc(TCGContext *s, int opc, int r, int v, /* Use the two byte form if possible, which cannot encode VEX.W, VEX.B, VEX.X, or an m-mmmm field other than P_EXT. */ - if ((opc & (P_EXT | P_EXT38 | P_EXT3A | P_REXW)) == P_EXT + if ((opc & (P_EXT | P_EXT38 | P_EXT3A | P_VEXW)) == P_EXT && ((rm | index) & 8) == 0) { /* Two byte VEX prefix. */ tcg_out8(s, 0xc5); @@ -601,7 +602,7 @@ static void tcg_out_vex_opc(TCGContext *s, int opc, int r, int v, tmp |= (rm & 8 ? 0 : 0x20); /* VEX.B */ tcg_out8(s, tmp); - tmp = (opc & P_REXW ? 0x80 : 0); /* VEX.W */ + tmp = (opc & P_VEXW ? 0x80 : 0); /* VEX.W */ } tmp |= (opc & P_VEXL ? 0x04 : 0); /* VEX.L */ diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index e0f4665213..5e1fac914a 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -25,9 +25,24 @@ #include "elf.h" #include "../tcg-pool.c.inc" -#if defined _CALL_DARWIN || defined __APPLE__ -#define TCG_TARGET_CALL_DARWIN -#endif +/* + * Standardize on the _CALL_FOO symbols used by GCC: + * Apple XCode does not define _CALL_DARWIN. + * Clang defines _CALL_ELF (64-bit) but not _CALL_SYSV (32-bit). + */ +#if !defined(_CALL_SYSV) && \ + !defined(_CALL_DARWIN) && \ + !defined(_CALL_AIX) && \ + !defined(_CALL_ELF) +# if defined(__APPLE__) +# define _CALL_DARWIN +# elif defined(__ELF__) && TCG_TARGET_REG_BITS == 32 +# define _CALL_SYSV +# else +# error "Unknown ABI" +# endif +#endif + #ifdef _CALL_SYSV # define TCG_TARGET_CALL_ALIGN_ARGS 1 #endif @@ -169,7 +184,7 @@ static const int tcg_target_call_oarg_regs[] = { }; static const int tcg_target_callee_save_regs[] = { -#ifdef TCG_TARGET_CALL_DARWIN +#ifdef _CALL_DARWIN TCG_REG_R11, #endif TCG_REG_R14, @@ -2372,7 +2387,7 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) # define LINK_AREA_SIZE (6 * SZR) # define LR_OFFSET (1 * SZR) # define TCG_TARGET_CALL_STACK_OFFSET (LINK_AREA_SIZE + 8 * SZR) -#elif defined(TCG_TARGET_CALL_DARWIN) +#elif defined(_CALL_DARWIN) # define LINK_AREA_SIZE (6 * SZR) # define LR_OFFSET (2 * SZR) #elif TCG_TARGET_REG_BITS == 64 diff --git a/tests/data/acpi/virt/IORT b/tests/data/acpi/virt/IORT Binary files differnew file mode 100644 index 0000000000..521acefe9b --- /dev/null +++ b/tests/data/acpi/virt/IORT diff --git a/tests/data/acpi/virt/IORT.memhp b/tests/data/acpi/virt/IORT.memhp Binary files differnew file mode 100644 index 0000000000..521acefe9b --- /dev/null +++ b/tests/data/acpi/virt/IORT.memhp diff --git a/tests/data/acpi/virt/IORT.numamem b/tests/data/acpi/virt/IORT.numamem Binary files differnew file mode 100644 index 0000000000..521acefe9b --- /dev/null +++ b/tests/data/acpi/virt/IORT.numamem diff --git a/tests/data/acpi/virt/IORT.pxb b/tests/data/acpi/virt/IORT.pxb Binary files differnew file mode 100644 index 0000000000..521acefe9b --- /dev/null +++ b/tests/data/acpi/virt/IORT.pxb diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122 index 5d550ed13e..efb260d822 100755 --- a/tests/qemu-iotests/122 +++ b/tests/qemu-iotests/122 @@ -67,7 +67,7 @@ echo _make_test_img -b "$TEST_IMG".base -F $IMGFMT $QEMU_IO -c "write -P 0 0 3M" "$TEST_IMG" 2>&1 | _filter_qemu_io | _filter_testdir -$QEMU_IMG convert -O $IMGFMT -B "$TEST_IMG".base -o backing_fmt=$IMGFMT \ +$QEMU_IMG convert -O $IMGFMT -B "$TEST_IMG".base -F $IMGFMT \ "$TEST_IMG" "$TEST_IMG".orig $QEMU_IO -c "read -P 0 0 3M" "$TEST_IMG".orig 2>&1 | _filter_qemu_io | _filter_testdir $QEMU_IMG convert -O $IMGFMT -c -B "$TEST_IMG".base -o backing_fmt=$IMGFMT \ diff --git a/tests/qemu-iotests/271 b/tests/qemu-iotests/271 index 599b849cc6..2775b4d130 100755 --- a/tests/qemu-iotests/271 +++ b/tests/qemu-iotests/271 @@ -893,7 +893,10 @@ EOF } _make_test_img -o extended_l2=on 1M -_concurrent_io | $QEMU_IO | _filter_qemu_io +# Second and third writes in _concurrent_io() are independent and may finish in +# different order. So, filter offset out to match both possible variants. +_concurrent_io | $QEMU_IO | _filter_qemu_io | \ + $SED -e 's/\(20480\|40960\)/OFFSET/' _concurrent_verify | $QEMU_IO | _filter_qemu_io # success, all done diff --git a/tests/qemu-iotests/271.out b/tests/qemu-iotests/271.out index 81043ba4d7..5be780de76 100644 --- a/tests/qemu-iotests/271.out +++ b/tests/qemu-iotests/271.out @@ -719,8 +719,8 @@ blkdebug: Suspended request 'A' blkdebug: Resuming request 'A' wrote 2048/2048 bytes at offset 30720 2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -wrote 2048/2048 bytes at offset 20480 +wrote 2048/2048 bytes at offset OFFSET 2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -wrote 2048/2048 bytes at offset 40960 +wrote 2048/2048 bytes at offset OFFSET 2 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) *** done diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index 345b617b34..b04cba5366 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -29,7 +29,7 @@ import iotests SKIP_FILES = ( '030', '040', '041', '044', '045', '055', '056', '057', '065', '093', '096', '118', '124', '132', '136', '139', '147', '148', '149', - '151', '152', '155', '163', '165', '169', '194', '196', '199', '202', + '151', '152', '155', '163', '165', '194', '196', '202', '203', '205', '206', '207', '208', '210', '211', '212', '213', '216', '218', '219', '224', '228', '234', '235', '236', '237', '238', '240', '242', '245', '246', '248', '255', '256', '257', '258', '260', @@ -46,7 +46,7 @@ def is_python_file(filename): if filename.endswith('.py'): return True - with open(filename) as f: + with open(filename, encoding='utf-8') as f: try: first_line = f.readline() return re.match('^#!.*python', first_line) is not None @@ -55,8 +55,9 @@ def is_python_file(filename): def run_linters(): - files = [filename for filename in (set(os.listdir('.')) - set(SKIP_FILES)) - if is_python_file(filename)] + named_tests = [f'tests/{entry}' for entry in os.listdir('tests')] + check_tests = set(os.listdir('.') + named_tests) - set(SKIP_FILES) + files = [filename for filename in check_tests if is_python_file(filename)] iotests.logger.debug('Files to be checked:') iotests.logger.debug(', '.join(sorted(files))) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index 11276f380a..ce06cf5630 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -610,7 +610,7 @@ class VM(qtest.QEMUQtestMachine): return valgrind_filename = f"{test_dir}/{self._popen.pid}.valgrind" if self.exitcode() == 99: - with open(valgrind_filename) as f: + with open(valgrind_filename, encoding='utf-8') as f: print(f.read()) else: os.remove(valgrind_filename) @@ -703,7 +703,7 @@ class VM(qtest.QEMUQtestMachine): def flatten_qmp_object(self, obj, output=None, basestr=''): if output is None: - output = dict() + output = {} if isinstance(obj, list): for i, item in enumerate(obj): self.flatten_qmp_object(item, output, basestr + str(i) + '.') @@ -716,7 +716,7 @@ class VM(qtest.QEMUQtestMachine): def qmp_to_opts(self, obj): obj = self.flatten_qmp_object(obj) - output_list = list() + output_list = [] for key in obj: output_list += [key + '=' + obj[key]] return ','.join(output_list) @@ -1121,7 +1121,8 @@ def notrun(reason): # Each test in qemu-iotests has a number ("seq") seq = os.path.basename(sys.argv[0]) - with open('%s/%s.notrun' % (output_dir, seq), 'w') as outfile: + with open('%s/%s.notrun' % (output_dir, seq), 'w', encoding='utf-8') \ + as outfile: outfile.write(reason + '\n') logger.warning("%s not run: %s", seq, reason) sys.exit(0) @@ -1135,7 +1136,8 @@ def case_notrun(reason): # Each test in qemu-iotests has a number ("seq") seq = os.path.basename(sys.argv[0]) - with open('%s/%s.casenotrun' % (output_dir, seq), 'a') as outfile: + with open('%s/%s.casenotrun' % (output_dir, seq), 'a', encoding='utf-8') \ + as outfile: outfile.write(' [case not run] ' + reason + '\n') def _verify_image_format(supported_fmts: Sequence[str] = (), diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test index 584062b412..00ebb5c251 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test @@ -132,10 +132,10 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): result = self.vm_a.qmp('x-debug-block-dirty-bitmap-sha256', node='drive0', name='bitmap0') - self.discards1_sha256 = result['return']['sha256'] + discards1_sha256 = result['return']['sha256'] # Check, that updating the bitmap by discards works - assert self.discards1_sha256 != empty_sha256 + assert discards1_sha256 != empty_sha256 # We want to calculate resulting sha256. Do it in bitmap0, so, disable # other bitmaps @@ -148,7 +148,7 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): result = self.vm_a.qmp('x-debug-block-dirty-bitmap-sha256', node='drive0', name='bitmap0') - self.all_discards_sha256 = result['return']['sha256'] + all_discards_sha256 = result['return']['sha256'] # Now, enable some bitmaps, to be updated during migration for i in range(2, nb_bitmaps, 2): @@ -173,10 +173,11 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): event_resume = self.vm_b.event_wait('RESUME') self.vm_b_events.append(event_resume) - return event_resume + return (event_resume, discards1_sha256, all_discards_sha256) def test_postcopy_success(self): - event_resume = self.start_postcopy() + event_resume, discards1_sha256, all_discards_sha256 = \ + self.start_postcopy() # enabled bitmaps should be updated apply_discards(self.vm_b, discards2) @@ -217,7 +218,7 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): for i in range(0, nb_bitmaps, 5): result = self.vm_b.qmp('x-debug-block-dirty-bitmap-sha256', node='drive0', name='bitmap{}'.format(i)) - sha = self.discards1_sha256 if i % 2 else self.all_discards_sha256 + sha = discards1_sha256 if i % 2 else all_discards_sha256 self.assert_qmp(result, 'return/sha256', sha) def test_early_shutdown_destination(self): diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-test b/tests/qemu-iotests/tests/migrate-bitmaps-test index a5c7bc83e0..dc431c35b3 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-test @@ -20,11 +20,10 @@ # import os -import iotests -import time import itertools import operator import re +import iotests from iotests import qemu_img, qemu_img_create, Timeout @@ -37,6 +36,12 @@ mig_cmd = 'exec: cat > ' + mig_file incoming_cmd = 'exec: cat ' + mig_file +def get_bitmap_hash(vm): + result = vm.qmp('x-debug-block-dirty-bitmap-sha256', + node='drive0', name='bitmap0') + return result['return']['sha256'] + + class TestDirtyBitmapMigration(iotests.QMPTestCase): def tearDown(self): self.vm_a.shutdown() @@ -62,21 +67,16 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): params['persistent'] = True result = vm.qmp('block-dirty-bitmap-add', **params) - self.assert_qmp(result, 'return', {}); - - def get_bitmap_hash(self, vm): - result = vm.qmp('x-debug-block-dirty-bitmap-sha256', - node='drive0', name='bitmap0') - return result['return']['sha256'] + self.assert_qmp(result, 'return', {}) def check_bitmap(self, vm, sha256): result = vm.qmp('x-debug-block-dirty-bitmap-sha256', node='drive0', name='bitmap0') if sha256: - self.assert_qmp(result, 'return/sha256', sha256); + self.assert_qmp(result, 'return/sha256', sha256) else: self.assert_qmp(result, 'error/desc', - "Dirty bitmap 'bitmap0' not found"); + "Dirty bitmap 'bitmap0' not found") def do_test_migration_resume_source(self, persistent, migrate_bitmaps): granularity = 512 @@ -97,7 +97,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): self.add_bitmap(self.vm_a, granularity, persistent) for r in regions: self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % r) - sha256 = self.get_bitmap_hash(self.vm_a) + sha256 = get_bitmap_hash(self.vm_a) result = self.vm_a.qmp('migrate', uri=mig_cmd) while True: @@ -106,7 +106,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): break while True: result = self.vm_a.qmp('query-status') - if (result['return']['status'] == 'postmigrate'): + if result['return']['status'] == 'postmigrate': break # test that bitmap is still here @@ -164,7 +164,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): self.add_bitmap(self.vm_a, granularity, persistent) for r in regions: self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % r) - sha256 = self.get_bitmap_hash(self.vm_a) + sha256 = get_bitmap_hash(self.vm_a) if pre_shutdown: self.vm_a.shutdown() @@ -214,16 +214,22 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): self.check_bitmap(self.vm_b, sha256 if persistent else False) -def inject_test_case(klass, name, method, *args, **kwargs): +def inject_test_case(klass, suffix, method, *args, **kwargs): mc = operator.methodcaller(method, *args, **kwargs) - setattr(klass, 'test_' + method + name, lambda self: mc(self)) + # We want to add a function attribute to `klass`, so that it is + # correctly converted to a method on instantiation. The + # methodcaller object `mc` is a callable, not a function, so we + # need the lambda to turn it into a function. + # pylint: disable=unnecessary-lambda + setattr(klass, 'test_' + method + suffix, lambda self: mc(self)) + for cmb in list(itertools.product((True, False), repeat=5)): name = ('_' if cmb[0] else '_not_') + 'persistent_' name += ('_' if cmb[1] else '_not_') + 'migbitmap_' name += '_online' if cmb[2] else '_offline' name += '_shared' if cmb[3] else '_nonshared' - if (cmb[4]): + if cmb[4]: name += '__pre_shutdown' inject_test_case(TestDirtyBitmapMigration, name, 'do_test_migration', @@ -270,7 +276,8 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): self.assert_qmp(result, 'return', {}) # Check that the bitmaps are there - for node in self.vm.qmp('query-named-block-nodes', flat=True)['return']: + nodes = self.vm.qmp('query-named-block-nodes', flat=True)['return'] + for node in nodes: if 'node0' in node['node-name']: self.assert_qmp(node, 'dirty-bitmaps[0]/name', 'bmap0') @@ -287,7 +294,7 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): """ Continue the source after migration. """ - result = self.vm.qmp('migrate', uri=f'exec: cat > /dev/null') + result = self.vm.qmp('migrate', uri='exec: cat > /dev/null') self.assert_qmp(result, 'return', {}) with Timeout(10, 'Migration timeout'): diff --git a/tests/qemu-iotests/tests/migrate-during-backup b/tests/qemu-iotests/tests/migrate-during-backup new file mode 100755 index 0000000000..34103229ee --- /dev/null +++ b/tests/qemu-iotests/tests/migrate-during-backup @@ -0,0 +1,97 @@ +#!/usr/bin/env python3 +# group: migration +# +# Copyright (c) 2021 Virtuozzo International GmbH +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +import os +import iotests +from iotests import qemu_img_create, qemu_io + + +disk_a = os.path.join(iotests.test_dir, 'disk_a') +disk_b = os.path.join(iotests.test_dir, 'disk_b') +size = '1M' +mig_file = os.path.join(iotests.test_dir, 'mig_file') +mig_cmd = 'exec: cat > ' + mig_file + + +class TestMigrateDuringBackup(iotests.QMPTestCase): + def tearDown(self): + self.vm.shutdown() + os.remove(disk_a) + os.remove(disk_b) + os.remove(mig_file) + + def setUp(self): + qemu_img_create('-f', iotests.imgfmt, disk_a, size) + qemu_img_create('-f', iotests.imgfmt, disk_b, size) + qemu_io('-c', f'write 0 {size}', disk_a) + + self.vm = iotests.VM().add_drive(disk_a) + self.vm.launch() + result = self.vm.qmp('blockdev-add', { + 'node-name': 'target', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': disk_b + } + }) + self.assert_qmp(result, 'return', {}) + + def test_migrate(self): + result = self.vm.qmp('blockdev-backup', device='drive0', + target='target', sync='full', + speed=1, x_perf={ + 'max-workers': 1, + 'max-chunk': 64 * 1024 + }) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('job-pause', id='drive0') + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('migrate-set-capabilities', + capabilities=[{'capability': 'events', + 'state': True}]) + self.assert_qmp(result, 'return', {}) + result = self.vm.qmp('migrate', uri=mig_cmd) + self.assert_qmp(result, 'return', {}) + + e = self.vm.events_wait((('MIGRATION', + {'data': {'status': 'completed'}}), + ('MIGRATION', + {'data': {'status': 'failed'}}))) + + # Don't assert that e is 'failed' now: this way we'll miss + # possible crash when backup continues :) + + result = self.vm.qmp('block-job-set-speed', device='drive0', + speed=0) + self.assert_qmp(result, 'return', {}) + result = self.vm.qmp('job-resume', id='drive0') + self.assert_qmp(result, 'return', {}) + + # For future: if something changes so that both migration + # and backup pass, let's not miss that moment, as it may + # be a bug as well as improvement. + self.assert_qmp(e, 'data/status', 'failed') + + +if __name__ == '__main__': + iotests.main(supported_fmts=['qcow2'], + supported_protocols=['file']) diff --git a/tests/qemu-iotests/tests/migrate-during-backup.out b/tests/qemu-iotests/tests/migrate-during-backup.out new file mode 100644 index 0000000000..ae1213e6f8 --- /dev/null +++ b/tests/qemu-iotests/tests/migrate-during-backup.out @@ -0,0 +1,5 @@ +. +---------------------------------------------------------------------- +Ran 1 tests + +OK diff --git a/tests/qemu-iotests/tests/mirror-top-perms b/tests/qemu-iotests/tests/mirror-top-perms index 451a0666f8..2fc8dd66e0 100755 --- a/tests/qemu-iotests/tests/mirror-top-perms +++ b/tests/qemu-iotests/tests/mirror-top-perms @@ -47,7 +47,7 @@ class TestMirrorTopPerms(iotests.QMPTestCase): def tearDown(self): try: self.vm.shutdown() - except qemu.machine.AbnormalShutdown: + except qemu.machine.machine.AbnormalShutdown: pass if self.vm_b is not None: diff --git a/tools/virtiofsd/fuse_lowlevel.h b/tools/virtiofsd/fuse_lowlevel.h index 4b4e8c9724..c55c0ca2fc 100644 --- a/tools/virtiofsd/fuse_lowlevel.h +++ b/tools/virtiofsd/fuse_lowlevel.h @@ -1603,7 +1603,7 @@ int fuse_lowlevel_notify_inval_inode(struct fuse_session *se, fuse_ino_t ino, * parent/name * * To avoid a deadlock this function must not be called in the - * execution path of a related filesytem operation or within any code + * execution path of a related filesystem operation or within any code * that could hold a lock that could be needed to execute such an * operation. As of kernel 4.18, a "related operation" is a lookup(), * symlink(), mknod(), mkdir(), unlink(), rename(), link() or create() @@ -1636,7 +1636,7 @@ int fuse_lowlevel_notify_inval_entry(struct fuse_session *se, fuse_ino_t parent, * that the dentry has been deleted. * * To avoid a deadlock this function must not be called while - * executing a related filesytem operation or while holding a lock + * executing a related filesystem operation or while holding a lock * that could be needed to execute such an operation (see the * description of fuse_lowlevel_notify_inval_entry() for more * details). diff --git a/ui/egl-helpers.c b/ui/egl-helpers.c index 6d0cb2b5cb..385a3fa752 100644 --- a/ui/egl-helpers.c +++ b/ui/egl-helpers.c @@ -287,6 +287,32 @@ void egl_dmabuf_release_texture(QemuDmaBuf *dmabuf) dmabuf->texture = 0; } +void egl_dmabuf_create_sync(QemuDmaBuf *dmabuf) +{ + EGLSyncKHR sync; + + if (epoxy_has_egl_extension(qemu_egl_display, + "EGL_KHR_fence_sync") && + epoxy_has_egl_extension(qemu_egl_display, + "EGL_ANDROID_native_fence_sync")) { + sync = eglCreateSyncKHR(qemu_egl_display, + EGL_SYNC_NATIVE_FENCE_ANDROID, NULL); + if (sync != EGL_NO_SYNC_KHR) { + dmabuf->sync = sync; + } + } +} + +void egl_dmabuf_create_fence(QemuDmaBuf *dmabuf) +{ + if (dmabuf->sync) { + dmabuf->fence_fd = eglDupNativeFenceFDANDROID(qemu_egl_display, + dmabuf->sync); + eglDestroySyncKHR(qemu_egl_display, dmabuf->sync); + dmabuf->sync = NULL; + } +} + #endif /* CONFIG_GBM */ /* ---------------------------------------------------------------------- */ diff --git a/ui/gtk-egl.c b/ui/gtk-egl.c index 2a2e6d3a17..72ce5e1f8f 100644 --- a/ui/gtk-egl.c +++ b/ui/gtk-egl.c @@ -12,6 +12,7 @@ */ #include "qemu/osdep.h" +#include "qemu/main-loop.h" #include "trace.h" @@ -94,6 +95,18 @@ void gd_egl_draw(VirtualConsole *vc) } glFlush(); +#ifdef CONFIG_GBM + if (vc->gfx.guest_fb.dmabuf) { + QemuDmaBuf *dmabuf = vc->gfx.guest_fb.dmabuf; + + egl_dmabuf_create_fence(dmabuf); + if (dmabuf->fence_fd > 0) { + qemu_set_fd_handler(dmabuf->fence_fd, gd_hw_gl_flushed, NULL, vc); + return; + } + graphic_hw_gl_block(vc->gfx.dcl.con, false); + } +#endif graphic_hw_gl_flushed(vc->gfx.dcl.con); } @@ -209,6 +222,8 @@ void gd_egl_scanout_dmabuf(DisplayChangeListener *dcl, QemuDmaBuf *dmabuf) { #ifdef CONFIG_GBM + VirtualConsole *vc = container_of(dcl, VirtualConsole, gfx.dcl); + egl_dmabuf_import_texture(dmabuf); if (!dmabuf->texture) { return; @@ -217,6 +232,10 @@ void gd_egl_scanout_dmabuf(DisplayChangeListener *dcl, gd_egl_scanout_texture(dcl, dmabuf->texture, false, dmabuf->width, dmabuf->height, 0, 0, dmabuf->width, dmabuf->height); + + if (dmabuf->allow_fences) { + vc->gfx.guest_fb.dmabuf = dmabuf; + } #endif } @@ -249,14 +268,6 @@ void gd_egl_cursor_position(DisplayChangeListener *dcl, vc->gfx.cursor_y = pos_y * vc->gfx.scale_y; } -void gd_egl_release_dmabuf(DisplayChangeListener *dcl, - QemuDmaBuf *dmabuf) -{ -#ifdef CONFIG_GBM - egl_dmabuf_release_texture(dmabuf); -#endif -} - void gd_egl_scanout_flush(DisplayChangeListener *dcl, uint32_t x, uint32_t y, uint32_t w, uint32_t h) { @@ -289,9 +300,30 @@ void gd_egl_scanout_flush(DisplayChangeListener *dcl, egl_fb_blit(&vc->gfx.win_fb, &vc->gfx.guest_fb, !vc->gfx.y0_top); } +#ifdef CONFIG_GBM + if (vc->gfx.guest_fb.dmabuf) { + egl_dmabuf_create_sync(vc->gfx.guest_fb.dmabuf); + } +#endif + eglSwapBuffers(qemu_egl_display, vc->gfx.esurface); } +void gd_egl_flush(DisplayChangeListener *dcl, + uint32_t x, uint32_t y, uint32_t w, uint32_t h) +{ + VirtualConsole *vc = container_of(dcl, VirtualConsole, gfx.dcl); + GtkWidget *area = vc->gfx.drawing_area; + + if (vc->gfx.guest_fb.dmabuf) { + graphic_hw_gl_block(vc->gfx.dcl.con, true); + gtk_widget_queue_draw_area(area, x, y, w, h); + return; + } + + gd_egl_scanout_flush(&vc->gfx.dcl, x, y, w, h); +} + void gtk_egl_init(DisplayGLMode mode) { GdkDisplay *gdk_display = gdk_display_get_default(); diff --git a/ui/gtk-gl-area.c b/ui/gtk-gl-area.c index dd5783fec7..b23523748e 100644 --- a/ui/gtk-gl-area.c +++ b/ui/gtk-gl-area.c @@ -8,6 +8,7 @@ */ #include "qemu/osdep.h" +#include "qemu/main-loop.h" #include "trace.h" @@ -71,7 +72,25 @@ void gd_gl_area_draw(VirtualConsole *vc) surface_gl_render_texture(vc->gfx.gls, vc->gfx.ds); } +#ifdef CONFIG_GBM + if (vc->gfx.guest_fb.dmabuf) { + egl_dmabuf_create_sync(vc->gfx.guest_fb.dmabuf); + } +#endif + glFlush(); +#ifdef CONFIG_GBM + if (vc->gfx.guest_fb.dmabuf) { + QemuDmaBuf *dmabuf = vc->gfx.guest_fb.dmabuf; + + egl_dmabuf_create_fence(dmabuf); + if (dmabuf->fence_fd > 0) { + qemu_set_fd_handler(dmabuf->fence_fd, gd_hw_gl_flushed, NULL, vc); + return; + } + graphic_hw_gl_block(vc->gfx.dcl.con, false); + } +#endif graphic_hw_gl_flushed(vc->gfx.dcl.con); } @@ -213,6 +232,9 @@ void gd_gl_area_scanout_flush(DisplayChangeListener *dcl, { VirtualConsole *vc = container_of(dcl, VirtualConsole, gfx.dcl); + if (vc->gfx.guest_fb.dmabuf) { + graphic_hw_gl_block(vc->gfx.dcl.con, true); + } gtk_gl_area_queue_render(GTK_GL_AREA(vc->gfx.drawing_area)); } @@ -231,6 +253,10 @@ void gd_gl_area_scanout_dmabuf(DisplayChangeListener *dcl, gd_gl_area_scanout_texture(dcl, dmabuf->texture, false, dmabuf->width, dmabuf->height, 0, 0, dmabuf->width, dmabuf->height); + + if (dmabuf->allow_fences) { + vc->gfx.guest_fb.dmabuf = dmabuf; + } #endif } @@ -36,6 +36,7 @@ #include "qapi/qapi-commands-machine.h" #include "qapi/qapi-commands-misc.h" #include "qemu/cutils.h" +#include "qemu/main-loop.h" #include "ui/console.h" #include "ui/gtk.h" @@ -575,6 +576,26 @@ static bool gd_has_dmabuf(DisplayChangeListener *dcl) return vc->gfx.has_dmabuf; } +static void gd_gl_release_dmabuf(DisplayChangeListener *dcl, + QemuDmaBuf *dmabuf) +{ +#ifdef CONFIG_GBM + egl_dmabuf_release_texture(dmabuf); +#endif +} + +void gd_hw_gl_flushed(void *vcon) +{ + VirtualConsole *vc = vcon; + QemuDmaBuf *dmabuf = vc->gfx.guest_fb.dmabuf; + + graphic_hw_gl_block(vc->gfx.dcl.con, false); + graphic_hw_gl_flushed(vc->gfx.dcl.con); + qemu_set_fd_handler(dmabuf->fence_fd, NULL, NULL, NULL); + close(dmabuf->fence_fd); + dmabuf->fence_fd = -1; +} + /** DisplayState Callbacks (opengl version) **/ static const DisplayChangeListenerOps dcl_gl_area_ops = { @@ -593,6 +614,7 @@ static const DisplayChangeListenerOps dcl_gl_area_ops = { .dpy_gl_scanout_disable = gd_gl_area_scanout_disable, .dpy_gl_update = gd_gl_area_scanout_flush, .dpy_gl_scanout_dmabuf = gd_gl_area_scanout_dmabuf, + .dpy_gl_release_dmabuf = gd_gl_release_dmabuf, .dpy_has_dmabuf = gd_has_dmabuf, }; @@ -615,8 +637,8 @@ static const DisplayChangeListenerOps dcl_egl_ops = { .dpy_gl_scanout_dmabuf = gd_egl_scanout_dmabuf, .dpy_gl_cursor_dmabuf = gd_egl_cursor_dmabuf, .dpy_gl_cursor_position = gd_egl_cursor_position, - .dpy_gl_release_dmabuf = gd_egl_release_dmabuf, - .dpy_gl_update = gd_egl_scanout_flush, + .dpy_gl_update = gd_egl_flush, + .dpy_gl_release_dmabuf = gd_gl_release_dmabuf, .dpy_has_dmabuf = gd_has_dmabuf, }; diff --git a/util/qemu-openpty.c b/util/qemu-openpty.c index eb17f5b0bc..427f43a769 100644 --- a/util/qemu-openpty.c +++ b/util/qemu-openpty.c @@ -80,10 +80,9 @@ static int openpty(int *amaster, int *aslave, char *name, (termp != NULL && tcgetattr(sfd, termp) < 0)) goto err; - if (amaster) - *amaster = mfd; - if (aslave) - *aslave = sfd; + *amaster = mfd; + *aslave = sfd; + if (winp) ioctl(sfd, TIOCSWINSZ, winp); |