From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:48957) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gHpVh-0000qw-Gy for qemu-devel@nongnu.org; Wed, 31 Oct 2018 08:22:13 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gHpVg-0001vn-GL for qemu-devel@nongnu.org; Wed, 31 Oct 2018 08:22:09 -0400 Received: from mail-wr1-x434.google.com ([2a00:1450:4864:20::434]:42585) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1gHpVe-0001BG-E7 for qemu-devel@nongnu.org; Wed, 31 Oct 2018 08:22:08 -0400 Received: by mail-wr1-x434.google.com with SMTP id y15-v6so16247675wru.9 for ; Wed, 31 Oct 2018 05:21:26 -0700 (PDT) From: Richard Henderson Date: Wed, 31 Oct 2018 12:21:14 +0000 Message-Id: <20181031122119.1669-6-richard.henderson@linaro.org> In-Reply-To: <20181031122119.1669-1-richard.henderson@linaro.org> References: <20181031122119.1669-1-richard.henderson@linaro.org> Subject: [Qemu-devel] [PULL 05/10] cputlb: Move env->vtlb_index to env->tlb_d.vindex List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: peter.maydell@linaro.org The rest of the tlb victim cache is per-tlb, the next use index should be as well. Tested-by: Emilio G. Cota Reviewed-by: Emilio G. Cota Signed-off-by: Richard Henderson --- include/exec/cpu-defs.h | 5 +++-- accel/tcg/cputlb.c | 5 ++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index df8ae18d9d..181c0dbfa4 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -150,6 +150,8 @@ typedef struct CPUTLBDesc { */ target_ulong large_page_addr; target_ulong large_page_mask; + /* The next index to use in the tlb victim table. */ + size_t vindex; } CPUTLBDesc; /* @@ -178,8 +180,7 @@ typedef struct CPUTLBCommon { CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE]; \ CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE]; \ CPUIOTLBEntry iotlb_v[NB_MMU_MODES][CPU_VTLB_SIZE]; \ - size_t tlb_flush_count; \ - target_ulong vtlb_index; \ + size_t tlb_flush_count; #else diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 8060ec99d7..2cd3886fd6 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -119,6 +119,7 @@ static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx) memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0])); env->tlb_d[mmu_idx].large_page_addr = -1; env->tlb_d[mmu_idx].large_page_mask = -1; + env->tlb_d[mmu_idx].vindex = 0; } /* This is OK because CPU architectures generally permit an @@ -149,8 +150,6 @@ static void tlb_flush_nocheck(CPUState *cpu) qemu_spin_unlock(&env->tlb_c.lock); cpu_tb_jmp_cache_clear(cpu); - - env->vtlb_index = 0; } static void tlb_flush_global_async_work(CPUState *cpu, run_on_cpu_data data) @@ -667,7 +666,7 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * different page; otherwise just overwrite the stale data. */ if (!tlb_hit_page_anyprot(te, vaddr_page)) { - unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE; + unsigned vidx = env->tlb_d[mmu_idx].vindex++ % CPU_VTLB_SIZE; CPUTLBEntry *tv = &env->tlb_v_table[mmu_idx][vidx]; /* Evict the old entry into the victim tlb. */ -- 2.17.2