diff options
| -rw-r--r-- | accel/tcg/cputlb.c | 103 | ||||
| -rw-r--r-- | docs/devel/multi-thread-tcg.rst | 13 | ||||
| -rw-r--r-- | include/exec/exec-all.h | 97 |
3 files changed, 19 insertions, 194 deletions
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index cdb3e12dfb..45799869eb 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -431,21 +431,6 @@ void tlb_flush(CPUState *cpu) tlb_flush_by_mmuidx(cpu, ALL_MMUIDX_BITS); } -void tlb_flush_by_mmuidx_all_cpus(CPUState *src_cpu, uint16_t idxmap) -{ - const run_on_cpu_func fn = tlb_flush_by_mmuidx_async_work; - - tlb_debug("mmu_idx: 0x%"PRIx16"\n", idxmap); - - flush_all_helper(src_cpu, fn, RUN_ON_CPU_HOST_INT(idxmap)); - fn(src_cpu, RUN_ON_CPU_HOST_INT(idxmap)); -} - -void tlb_flush_all_cpus(CPUState *src_cpu) -{ - tlb_flush_by_mmuidx_all_cpus(src_cpu, ALL_MMUIDX_BITS); -} - void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *src_cpu, uint16_t idxmap) { const run_on_cpu_func fn = tlb_flush_by_mmuidx_async_work; @@ -656,46 +641,6 @@ void tlb_flush_page(CPUState *cpu, vaddr addr) tlb_flush_page_by_mmuidx(cpu, addr, ALL_MMUIDX_BITS); } -void tlb_flush_page_by_mmuidx_all_cpus(CPUState *src_cpu, vaddr addr, - uint16_t idxmap) -{ - tlb_debug("addr: %016" VADDR_PRIx " mmu_idx:%"PRIx16"\n", addr, idxmap); - - /* This should already be page aligned */ - addr &= TARGET_PAGE_MASK; - - /* - * Allocate memory to hold addr+idxmap only when needed. - * See tlb_flush_page_by_mmuidx for details. - */ - if (idxmap < TARGET_PAGE_SIZE) { - flush_all_helper(src_cpu, tlb_flush_page_by_mmuidx_async_1, - RUN_ON_CPU_TARGET_PTR(addr | idxmap)); - } else { - CPUState *dst_cpu; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - TLBFlushPageByMMUIdxData *d - = g_new(TLBFlushPageByMMUIdxData, 1); - - d->addr = addr; - d->idxmap = idxmap; - async_run_on_cpu(dst_cpu, tlb_flush_page_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(d)); - } - } - } - - tlb_flush_page_by_mmuidx_async_0(src_cpu, addr, idxmap); -} - -void tlb_flush_page_all_cpus(CPUState *src, vaddr addr) -{ - tlb_flush_page_by_mmuidx_all_cpus(src, addr, ALL_MMUIDX_BITS); -} - void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *src_cpu, vaddr addr, uint16_t idxmap) @@ -887,54 +832,6 @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, vaddr addr, tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits); } -void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, - vaddr addr, vaddr len, - uint16_t idxmap, unsigned bits) -{ - TLBFlushRangeData d; - CPUState *dst_cpu; - - /* - * If all bits are significant, and len is small, - * this devolves to tlb_flush_page. - */ - if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { - tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap); - return; - } - /* If no page bits are significant, this devolves to tlb_flush. */ - if (bits < TARGET_PAGE_BITS) { - tlb_flush_by_mmuidx_all_cpus(src_cpu, idxmap); - return; - } - - /* This should already be page aligned */ - d.addr = addr & TARGET_PAGE_MASK; - d.len = len; - d.idxmap = idxmap; - d.bits = bits; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); - async_run_on_cpu(dst_cpu, - tlb_flush_range_by_mmuidx_async_1, - RUN_ON_CPU_HOST_PTR(p)); - } - } - - tlb_flush_range_by_mmuidx_async_0(src_cpu, d); -} - -void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, - vaddr addr, uint16_t idxmap, - unsigned bits) -{ - tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE, - idxmap, bits); -} - void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu, vaddr addr, vaddr len, diff --git a/docs/devel/multi-thread-tcg.rst b/docs/devel/multi-thread-tcg.rst index 1420789fff..d706c27ea7 100644 --- a/docs/devel/multi-thread-tcg.rst +++ b/docs/devel/multi-thread-tcg.rst @@ -205,15 +205,10 @@ DESIGN REQUIREMENTS: (Current solution) -We have updated cputlb.c to defer operations when a cross-vCPU -operation with async_run_on_cpu() which ensures each vCPU sees a -coherent state when it next runs its work (in a few instructions -time). - -A new set up operations (tlb_flush_*_all_cpus) take an additional flag -which when set will force synchronisation by setting the source vCPUs -work as "safe work" and exiting the cpu run loop. This ensure by the -time execution restarts all flush operations have completed. +A new set of tlb flush operations (tlb_flush_*_all_cpus_synced) force +synchronisation by setting the source vCPUs work as "safe work" and +exiting the cpu run loop. This ensures that by the time execution +restarts all flush operations have completed. TLB flag updates are all done atomically and are also protected by the corresponding page lock. diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 2cd7b8f61b..b6b46ad13c 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -68,24 +68,15 @@ void tlb_destroy(CPUState *cpu); */ void tlb_flush_page(CPUState *cpu, vaddr addr); /** - * tlb_flush_page_all_cpus: + * tlb_flush_page_all_cpus_synced: * @cpu: src CPU of the flush * @addr: virtual address of page to be flushed * - * Flush one page from the TLB of the specified CPU, for all + * Flush one page from the TLB of all CPUs, for all * MMU indexes. - */ -void tlb_flush_page_all_cpus(CPUState *src, vaddr addr); -/** - * tlb_flush_page_all_cpus_synced: - * @cpu: src CPU of the flush - * @addr: virtual address of page to be flushed * - * Flush one page from the TLB of the specified CPU, for all MMU - * indexes like tlb_flush_page_all_cpus except the source vCPUs work - * is scheduled as safe work meaning all flushes will be complete once - * the source vCPUs safe work is complete. This will depend on when - * the guests translation ends the TB. + * When this function returns, no CPUs will subsequently perform + * translations using the flushed TLBs. */ void tlb_flush_page_all_cpus_synced(CPUState *src, vaddr addr); /** @@ -99,18 +90,13 @@ void tlb_flush_page_all_cpus_synced(CPUState *src, vaddr addr); */ void tlb_flush(CPUState *cpu); /** - * tlb_flush_all_cpus: - * @cpu: src CPU of the flush - */ -void tlb_flush_all_cpus(CPUState *src_cpu); -/** * tlb_flush_all_cpus_synced: * @cpu: src CPU of the flush * - * Like tlb_flush_all_cpus except this except the source vCPUs work is - * scheduled as safe work meaning all flushes will be complete once - * the source vCPUs safe work is complete. This will depend on when - * the guests translation ends the TB. + * Flush the entire TLB for all CPUs, for all MMU indexes. + * + * When this function returns, no CPUs will subsequently perform + * translations using the flushed TLBs. */ void tlb_flush_all_cpus_synced(CPUState *src_cpu); /** @@ -125,27 +111,16 @@ void tlb_flush_all_cpus_synced(CPUState *src_cpu); void tlb_flush_page_by_mmuidx(CPUState *cpu, vaddr addr, uint16_t idxmap); /** - * tlb_flush_page_by_mmuidx_all_cpus: + * tlb_flush_page_by_mmuidx_all_cpus_synced: * @cpu: Originating CPU of the flush * @addr: virtual address of page to be flushed * @idxmap: bitmap of MMU indexes to flush * * Flush one page from the TLB of all CPUs, for the specified * MMU indexes. - */ -void tlb_flush_page_by_mmuidx_all_cpus(CPUState *cpu, vaddr addr, - uint16_t idxmap); -/** - * tlb_flush_page_by_mmuidx_all_cpus_synced: - * @cpu: Originating CPU of the flush - * @addr: virtual address of page to be flushed - * @idxmap: bitmap of MMU indexes to flush * - * Flush one page from the TLB of all CPUs, for the specified MMU - * indexes like tlb_flush_page_by_mmuidx_all_cpus except the source - * vCPUs work is scheduled as safe work meaning all flushes will be - * complete once the source vCPUs safe work is complete. This will - * depend on when the guests translation ends the TB. + * When this function returns, no CPUs will subsequently perform + * translations using the flushed TLBs. */ void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, uint16_t idxmap); @@ -160,24 +135,15 @@ void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, */ void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap); /** - * tlb_flush_by_mmuidx_all_cpus: + * tlb_flush_by_mmuidx_all_cpus_synced: * @cpu: Originating CPU of the flush * @idxmap: bitmap of MMU indexes to flush * - * Flush all entries from all TLBs of all CPUs, for the specified + * Flush all entries from the TLB of all CPUs, for the specified * MMU indexes. - */ -void tlb_flush_by_mmuidx_all_cpus(CPUState *cpu, uint16_t idxmap); -/** - * tlb_flush_by_mmuidx_all_cpus_synced: - * @cpu: Originating CPU of the flush - * @idxmap: bitmap of MMU indexes to flush * - * Flush all entries from all TLBs of all CPUs, for the specified - * MMU indexes like tlb_flush_by_mmuidx_all_cpus except except the source - * vCPUs work is scheduled as safe work meaning all flushes will be - * complete once the source vCPUs safe work is complete. This will - * depend on when the guests translation ends the TB. + * When this function returns, no CPUs will subsequently perform + * translations using the flushed TLBs. */ void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap); @@ -194,8 +160,6 @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, vaddr addr, uint16_t idxmap, unsigned bits); /* Similarly, with broadcast and syncing. */ -void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, vaddr addr, - uint16_t idxmap, unsigned bits); void tlb_flush_page_bits_by_mmuidx_all_cpus_synced (CPUState *cpu, vaddr addr, uint16_t idxmap, unsigned bits); @@ -215,9 +179,6 @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, vaddr addr, unsigned bits); /* Similarly, with broadcast and syncing. */ -void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, vaddr addr, - vaddr len, uint16_t idxmap, - unsigned bits); void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, vaddr len, @@ -290,18 +251,12 @@ static inline void tlb_destroy(CPUState *cpu) static inline void tlb_flush_page(CPUState *cpu, vaddr addr) { } -static inline void tlb_flush_page_all_cpus(CPUState *src, vaddr addr) -{ -} static inline void tlb_flush_page_all_cpus_synced(CPUState *src, vaddr addr) { } static inline void tlb_flush(CPUState *cpu) { } -static inline void tlb_flush_all_cpus(CPUState *src_cpu) -{ -} static inline void tlb_flush_all_cpus_synced(CPUState *src_cpu) { } @@ -313,20 +268,11 @@ static inline void tlb_flush_page_by_mmuidx(CPUState *cpu, static inline void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap) { } -static inline void tlb_flush_page_by_mmuidx_all_cpus(CPUState *cpu, - vaddr addr, - uint16_t idxmap) -{ -} static inline void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, uint16_t idxmap) { } -static inline void tlb_flush_by_mmuidx_all_cpus(CPUState *cpu, uint16_t idxmap) -{ -} - static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap) { @@ -337,12 +283,6 @@ static inline void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, unsigned bits) { } -static inline void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, - vaddr addr, - uint16_t idxmap, - unsigned bits) -{ -} static inline void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, uint16_t idxmap, unsigned bits) @@ -353,13 +293,6 @@ static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, vaddr addr, unsigned bits) { } -static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, - vaddr addr, - vaddr len, - uint16_t idxmap, - unsigned bits) -{ -} static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, vaddr len, |