From patchwork Sat Oct 5 15:25:38 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 13823321 Received: from mail-pl1-f176.google.com (mail-pl1-f176.google.com [209.85.214.176]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 50FF51EB36 for ; Sat, 5 Oct 2024 15:26:00 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.176 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728141961; cv=none; b=eiz7sg+1ZOehCz2FOoMWw1a2kCPP+h3xd6Tw01c/ESnG5Gd2Ov6F66TOYcTDBYjAXmCbKtJGGL1YNjWTOUqQel2uhuO2SAtcPvoxzJXnOgJbhI6TCIwrixKBqY86VuxvYOJcQnzaEQt8l5jcCX6Chmk0OQyjtgQETI+Kr/urdfI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728141961; c=relaxed/simple; bh=4NVUV6YGGVu0dfDzUFRQNyxQmIfvN5ZZlTdwZgCxg+I=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=akBi9OfLgOM6wjrtedpFzMXtIPxCLUZM6WXsH/8glomIKZY1KAg4+ni7tpByz5PFatbAzi5UGy6KSlK+A/repeJ1TNDq0TyAnAds2snNGmwMCII4FMRM1FUEedGwi6ia9210hm/9QqfoDJ4DHfHocyPEcZG8FnUgUlJxTjjAXaI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linaro.org; spf=pass smtp.mailfrom=linaro.org; dkim=pass (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b=fyZ29mI1; arc=none smtp.client-ip=209.85.214.176 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linaro.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linaro.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="fyZ29mI1" Received: by mail-pl1-f176.google.com with SMTP id d9443c01a7336-20aff65aa37so26630875ad.1 for ; Sat, 05 Oct 2024 08:26:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1728141960; x=1728746760; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=aSpIks7wgvzrdGiSzq/HYW4dr1jFM7gjMRozlRGemJM=; b=fyZ29mI1dsfMmVaZaAFerE5PYV2FowGSw5vZ6oj7tSXk+fgz2FUlAL++16xPaMQzqk Mn8iv8WUduQNaIM6WVS2cXAXWV84MV9+YQp1Qr+U4819XVPDmrxbblh0O4p0Chc1PrVr qWwbHVr/liVN2LLLLJdWec68brY7lL0E+xDhRCZYQkUHlPmsrRT06kZX/WoE6r4I6W5i Z/QSUnfpQgGrUMF+d5caj9cCqmeMR7rVZlrLaUvg9WaFxMlIDgn6FGlEJlYqBBs8aKLi Upm7fOcX2FqpkKWXnI6BjAEhEm8wa5KoiQJCKdXnvojsLC/tyh6HAsJJbMiNNx9Yop12 id7g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1728141960; x=1728746760; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=aSpIks7wgvzrdGiSzq/HYW4dr1jFM7gjMRozlRGemJM=; b=mdoBLP6wfj96/WgJwoK/ssDBfKf8TdWONEozVm780XfNK9w4ZcBaOeWVcS+9mKhQXM vBKY/iSfgDff6GMqaaq7mJymMmms8l567wNgIcMUagnx6wG84FCIh6Q19BJM7FNVG8H4 jKgJzw7bYK9HAfaVjth+UVGAiNWI5h2Czy5brsu2OkNJgDLDHLIdwwQGI4mG+I5Y3kqy yUkrbhMJ9gKzw1cLHsZKgmfeg07uKxPGRfTZNaIIsO6f0GWarNSMuQgQRVpbDHZGhSdM 6jflm5cdyfG1b1sN4YiFTGuOZww1U8od4jvIOQTRqimJfaHd59ssTv8MFVVn2Ni8ltCU E+6Q== X-Forwarded-Encrypted: i=1; AJvYcCV+zjhoPQ3tCHVBxe8LEXIR7bKPwkpZfdmNZXPs1sIEERq83BGSn1OJBNRRUsdVaX6vcOOAlh1uJWArUos=@vger.kernel.org X-Gm-Message-State: AOJu0Yyp42l++cMcEZdaDoU6G8MI9RXO0y0n9X0tnW1w12kDLs8VMu5Y amNkiGa0gvImumsY0V7hP4xIvc2t8n33/foseFyqJenkNPfCQPX7Q6kP3Eu6fSocqm6fYQvs1gq L X-Google-Smtp-Source: AGHT+IHHBcTpm+lN7YnCUB3+U4K5he75In85ERBx3pFwVufluTULuz7p5KPxpM3Bc//CGD+sBFjKUg== X-Received: by 2002:a17:902:ec89:b0:20b:982e:73d6 with SMTP id d9443c01a7336-20bff043851mr82009865ad.49.1728141959618; Sat, 05 Oct 2024 08:25:59 -0700 (PDT) Received: from stoup.. (174-21-81-121.tukw.qwest.net. [174.21.81.121]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-20c1396948dsm14351765ad.225.2024.10.05.08.25.58 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 05 Oct 2024 08:25:59 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Cc: deller@kernel.org, peter.maydell@linaro.org, alex.bennee@linaro.org, linux-parisc@vger.kernel.org, qemu-arm@nongnu.org Subject: [PATCH 07/20] accel/tcg: Use the tlb_fill_align hook Date: Sat, 5 Oct 2024 08:25:38 -0700 Message-ID: <20241005152551.307923-8-richard.henderson@linaro.org> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20241005152551.307923-1-richard.henderson@linaro.org> References: <20241005152551.307923-1-richard.henderson@linaro.org> Precedence: bulk X-Mailing-List: linux-parisc@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 When we have a tlb miss, defer the alignment check to the new tlb_fill_align hook. Move the existing alignment check so that we only perform it with a tlb hit. Signed-off-by: Richard Henderson --- accel/tcg/cputlb.c | 89 +++++++++++++++++++++++++--------------------- 1 file changed, 49 insertions(+), 40 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 4bc34c8a37..0e6ae65a39 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -1616,14 +1616,14 @@ typedef struct MMULookupLocals { * tlb_fill will longjmp out. Return true if the softmmu tlb for * @mmu_idx may have resized. */ -static bool mmu_lookup1(CPUState *cpu, MMULookupPageData *data, +static bool mmu_lookup1(CPUState *cpu, MMULookupPageData *data, MemOp memop, int mmu_idx, MMUAccessType access_type, uintptr_t ra) { vaddr addr = data->addr; uintptr_t index = tlb_index(cpu, mmu_idx, addr); CPUTLBEntry *entry = tlb_entry(cpu, mmu_idx, addr); uint64_t tlb_addr = tlb_read_idx(entry, access_type); - bool maybe_resized = false; + bool did_tlb_fill = false; CPUTLBEntryFull *full; int flags; @@ -1631,17 +1631,26 @@ static bool mmu_lookup1(CPUState *cpu, MMULookupPageData *data, if (!tlb_hit(tlb_addr, addr)) { if (!victim_tlb_hit(cpu, mmu_idx, index, access_type, addr & TARGET_PAGE_MASK)) { - bool ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, data->size, - access_type, mmu_idx, - false, ra); + bool ok = cpu->cc->tcg_ops->tlb_fill_align(cpu, addr, memop, + data->size, access_type, + mmu_idx, false, ra); assert(ok); - maybe_resized = true; + did_tlb_fill = true; index = tlb_index(cpu, mmu_idx, addr); entry = tlb_entry(cpu, mmu_idx, addr); } tlb_addr = tlb_read_idx(entry, access_type) & ~TLB_INVALID_MASK; } + if (!did_tlb_fill) { + /* We didn't use tlb_fill_align, so alignment not yet checked. */ + unsigned a_bits = memop_alignment_bits(memop); + + if (unlikely(addr & ((1 << a_bits) - 1))) { + cpu_unaligned_access(cpu, addr, access_type, mmu_idx, ra); + } + } + full = &cpu->neg.tlb.d[mmu_idx].fulltlb[index]; flags = tlb_addr & (TLB_FLAGS_MASK & ~TLB_FORCE_SLOW); flags |= full->slow_flags[access_type]; @@ -1651,7 +1660,7 @@ static bool mmu_lookup1(CPUState *cpu, MMULookupPageData *data, /* Compute haddr speculatively; depending on flags it might be invalid. */ data->haddr = (void *)((uintptr_t)addr + entry->addend); - return maybe_resized; + return did_tlb_fill; } /** @@ -1702,7 +1711,6 @@ static void mmu_watch_or_dirty(CPUState *cpu, MMULookupPageData *data, static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, uintptr_t ra, MMUAccessType type, MMULookupLocals *l) { - unsigned a_bits; bool crosspage; int flags; @@ -1711,12 +1719,6 @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, tcg_debug_assert(l->mmu_idx < NB_MMU_MODES); - /* Handle CPU specific unaligned behaviour */ - a_bits = memop_alignment_bits(l->memop); - if (addr & ((1 << a_bits) - 1)) { - cpu_unaligned_access(cpu, addr, type, l->mmu_idx, ra); - } - l->page[0].addr = addr; l->page[0].size = memop_size(l->memop); l->page[1].addr = (addr + l->page[0].size - 1) & TARGET_PAGE_MASK; @@ -1724,7 +1726,7 @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, crosspage = (addr ^ l->page[1].addr) & TARGET_PAGE_MASK; if (likely(!crosspage)) { - mmu_lookup1(cpu, &l->page[0], l->mmu_idx, type, ra); + mmu_lookup1(cpu, &l->page[0], l->memop, l->mmu_idx, type, ra); flags = l->page[0].flags; if (unlikely(flags & (TLB_WATCHPOINT | TLB_NOTDIRTY))) { @@ -1743,8 +1745,8 @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, * Lookup both pages, recognizing exceptions from either. If the * second lookup potentially resized, refresh first CPUTLBEntryFull. */ - mmu_lookup1(cpu, &l->page[0], l->mmu_idx, type, ra); - if (mmu_lookup1(cpu, &l->page[1], l->mmu_idx, type, ra)) { + mmu_lookup1(cpu, &l->page[0], l->memop, l->mmu_idx, type, ra); + if (mmu_lookup1(cpu, &l->page[1], 0, l->mmu_idx, type, ra)) { uintptr_t index = tlb_index(cpu, l->mmu_idx, addr); l->page[0].full = &cpu->neg.tlb.d[l->mmu_idx].fulltlb[index]; } @@ -1770,7 +1772,7 @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, * Device memory type require alignment. */ if (unlikely(flags & TLB_CHECK_ALIGNED)) { - a_bits = memop_atomicity_bits(l->memop); + unsigned a_bits = memop_atomicity_bits(l->memop); if (addr & ((1 << a_bits) - 1)) { cpu_unaligned_access(cpu, addr, type, l->mmu_idx, ra); } @@ -1788,34 +1790,18 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, { uintptr_t mmu_idx = get_mmuidx(oi); MemOp mop = get_memop(oi); - int a_bits = memop_alignment_bits(mop); uintptr_t index; CPUTLBEntry *tlbe; vaddr tlb_addr; void *hostaddr; CPUTLBEntryFull *full; + bool did_tlb_fill = false; tcg_debug_assert(mmu_idx < NB_MMU_MODES); /* Adjust the given return address. */ retaddr -= GETPC_ADJ; - /* Enforce guest required alignment. */ - if (unlikely(a_bits > 0 && (addr & ((1 << a_bits) - 1)))) { - /* ??? Maybe indicate atomic op to cpu_unaligned_access */ - cpu_unaligned_access(cpu, addr, MMU_DATA_STORE, - mmu_idx, retaddr); - } - - /* Enforce qemu required alignment. */ - if (unlikely(addr & (size - 1))) { - /* We get here if guest alignment was not requested, - or was not enforced by cpu_unaligned_access above. - We might widen the access and emulate, but for now - mark an exception and exit the cpu loop. */ - goto stop_the_world; - } - index = tlb_index(cpu, mmu_idx, addr); tlbe = tlb_entry(cpu, mmu_idx, addr); @@ -1824,10 +1810,11 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, if (!tlb_hit(tlb_addr, addr)) { if (!victim_tlb_hit(cpu, mmu_idx, index, MMU_DATA_STORE, addr & TARGET_PAGE_MASK)) { - bool ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, size, - MMU_DATA_STORE, mmu_idx, - false, retaddr); + bool ok = cpu->cc->tcg_ops->tlb_fill_align(cpu, addr, mop, size, + MMU_DATA_STORE, mmu_idx, + false, retaddr); assert(ok); + did_tlb_fill = true; index = tlb_index(cpu, mmu_idx, addr); tlbe = tlb_entry(cpu, mmu_idx, addr); } @@ -1841,8 +1828,8 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, * but addr_read will only be -1 if PAGE_READ was unset. */ if (unlikely(tlbe->addr_read == -1)) { - cpu->cc->tcg_ops->tlb_fill(cpu, addr, size, MMU_DATA_LOAD, - mmu_idx, false, retaddr); + cpu->cc->tcg_ops->tlb_fill_align(cpu, addr, mop, size, MMU_DATA_LOAD, + mmu_idx, false, retaddr); /* * Since we don't support reads and writes to different * addresses, and we do have the proper page loaded for @@ -1850,6 +1837,28 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, */ g_assert_not_reached(); } + + /* Enforce guest required alignment, if not handled by tlb_fill_align. */ + if (!did_tlb_fill) { + int a_bits = memop_alignment_bits(mop); + if (unlikely(a_bits > 0 && (addr & ((1 << a_bits) - 1)))) { + /* ??? Maybe indicate atomic op to cpu_unaligned_access */ + cpu_unaligned_access(cpu, addr, MMU_DATA_STORE, + mmu_idx, retaddr); + } + } + + /* Enforce qemu required alignment. */ + if (unlikely(addr & (size - 1))) { + /* + * We get here if guest alignment was not requested, + * or was not enforced by cpu_unaligned_access above. + * We might widen the access and emulate, but for now + * mark an exception and exit the cpu loop. + */ + goto stop_the_world; + } + /* Collect tlb flags for read. */ tlb_addr |= tlbe->addr_read;