From patchwork Thu Feb 9 17:08:58 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?Alex_Benn=C3=A9e?= X-Patchwork-Id: 93763 Delivered-To: patch@linaro.org Received: by 10.140.20.99 with SMTP id 90csp116162qgi; Thu, 9 Feb 2017 09:41:59 -0800 (PST) X-Received: by 10.237.35.231 with SMTP id k36mr4009235qtc.192.1486662119179; Thu, 09 Feb 2017 09:41:59 -0800 (PST) Return-Path: Received: from lists.gnu.org (lists.gnu.org. [2001:4830:134:3::11]) by mx.google.com with ESMTPS id m26si8513422qtm.22.2017.02.09.09.41.58 for (version=TLS1 cipher=AES128-SHA bits=128/128); Thu, 09 Feb 2017 09:41:59 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) client-ip=2001:4830:134:3::11; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:39378 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cbsjE-0002Fy-LN for patch@linaro.org; Thu, 09 Feb 2017 12:41:56 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:56991) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cbsDb-0006Tp-Ho for qemu-devel@nongnu.org; Thu, 09 Feb 2017 12:09:17 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cbsDZ-0002ZK-SK for qemu-devel@nongnu.org; Thu, 09 Feb 2017 12:09:15 -0500 Received: from mail-wr0-x231.google.com ([2a00:1450:400c:c0c::231]:34375) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1cbsDZ-0002Yi-HU for qemu-devel@nongnu.org; Thu, 09 Feb 2017 12:09:13 -0500 Received: by mail-wr0-x231.google.com with SMTP id o16so88307214wra.1 for ; Thu, 09 Feb 2017 09:09:13 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=0tVFYz/nzL0By9w3sLfPvjvA6MQu3IYvxpDN14+1TYM=; b=gsxNtqNb8M6OVz6LD1oh7DGSUktP42XMG880VnC/KwuzMBG7Z1lWaiDmzI2lxO1a/O hLqlB/Kx0P+LCSh0G502or7ZwwriF34NLdcdwFLqng/qEnfyYY4v33r8gPBTHxbPQ/hU QZ1Pq1+lWHTCx5GGt0ojsaFmg2muodlHjwV9c= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=0tVFYz/nzL0By9w3sLfPvjvA6MQu3IYvxpDN14+1TYM=; b=UcjbAQ2NTHhjgr7rrd6M423As0UyGrFvI4VCg+lLzXVd5t21QIe2kip5GxfacRXU26 Y2frH9Ai84V6M++VniAMz72Xdr4h0Y8PEIG1LMCj9AoS9E21qSq6Zsncz8d4a7gUeR17 dSmTrPJK1iVdPfYEzJm6F5+h1Fatsf6vU8N32FvyoOE2Ayf3OdKASiT4g95CIuqe6STw smB7PgwkOZaFVHEKdBnLXIXNgPpR8U0kKSiKAJlc7c/F8BomvH3wVteBxTPIjeNI+dg/ w3+BWvEPaFbnuSgaiIr6JJXPXyONo+66aIFAtSKzmJqIp5BOOfnj2D44utH/kZsO4A4l Ysew== X-Gm-Message-State: AMke39nL1uE2nWTMS/l7hrVp/P4iA9dj9Itand8Xx08ReBrAGhR4TZKgkkbGEMsHSx6nn3Cv X-Received: by 10.223.136.152 with SMTP id f24mr3726389wrf.187.1486660152382; Thu, 09 Feb 2017 09:09:12 -0800 (PST) Received: from zen.linaro.local ([81.128.185.34]) by smtp.gmail.com with ESMTPSA id z67sm19451449wrb.49.2017.02.09.09.09.02 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 09 Feb 2017 09:09:04 -0800 (PST) Received: from zen.linaroharston (localhost [127.0.0.1]) by zen.linaro.local (Postfix) with ESMTP id 316E23E2D77; Thu, 9 Feb 2017 17:09:06 +0000 (GMT) From: =?utf-8?q?Alex_Benn=C3=A9e?= To: peter.maydell@linaro.org, rth@twiddle.net Date: Thu, 9 Feb 2017 17:08:58 +0000 Message-Id: <20170209170904.5713-19-alex.bennee@linaro.org> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170209170904.5713-1-alex.bennee@linaro.org> References: <20170209170904.5713-1-alex.bennee@linaro.org> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 2a00:1450:400c:c0c::231 Subject: [Qemu-devel] [PATCH v11 18/24] cputlb: atomically update tlb fields used by tlb_reset_dirty X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: mttcg@listserver.greensocs.com, nikunj@linux.vnet.ibm.com, Peter Crosthwaite , jan.kiszka@siemens.com, mark.burton@greensocs.com, a.rigo@virtualopensystems.com, qemu-devel@nongnu.org, cota@braap.org, serge.fdrv@gmail.com, pbonzini@redhat.com, bobby.prani@gmail.com, =?utf-8?q?Alex_Benn=C3=A9e?= , bamvor.zhangjian@linaro.org, fred.konrad@greensocs.com Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" The main use case for tlb_reset_dirty is to set the TLB_NOTDIRTY flags in TLB entries to force the slow-path on writes. This is used to mark page ranges containing code which has been translated so it can be invalidated if written to. To do this safely we need to ensure the TLB entries in question for all vCPUs are updated before we attempt to run the code otherwise a race could be introduced. To achieve this we atomically set the flag in tlb_reset_dirty_range and take care when setting it when the TLB entry is filled. On 32 bit systems attempting to emulate 64 bit guests we don't even bother as we might not have the atomic primitives available. MTTCG is disabled in this case and can't be forced on. The copy_tlb_helper function helps keep the atomic semantics in one place to avoid confusion. The dirty helper function is made static as it isn't used outside of cputlb. Signed-off-by: Alex Bennée Reviewed-by: Richard Henderson --- v6 - use TARGET_PAGE_BITS_MIN - use run_on_cpu helpers v7 - fix tlb_debug fmt for 32bit build - un-merged the mmuidx async work which got mashed in last round - introduced copy_tlb_helper function and made TCG_OVERSIZED_GUEST aware --- cputlb.c | 120 +++++++++++++++++++++++++++++++++++++++----------- include/exec/cputlb.h | 2 - 2 files changed, 95 insertions(+), 27 deletions(-) -- 2.11.0 diff --git a/cputlb.c b/cputlb.c index c50254be26..65003350e3 100644 --- a/cputlb.c +++ b/cputlb.c @@ -342,32 +342,90 @@ void tlb_unprotect_code(ram_addr_t ram_addr) cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_CODE); } -static bool tlb_is_dirty_ram(CPUTLBEntry *tlbe) -{ - return (tlbe->addr_write & (TLB_INVALID_MASK|TLB_MMIO|TLB_NOTDIRTY)) == 0; -} -void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start, +/* + * Dirty write flag handling + * + * When the TCG code writes to a location it looks up the address in + * the TLB and uses that data to compute the final address. If any of + * the lower bits of the address are set then the slow path is forced. + * There are a number of reasons to do this but for normal RAM the + * most usual is detecting writes to code regions which may invalidate + * generated code. + * + * Because we want other vCPUs to respond to changes straight away we + * update the te->addr_write field atomically. If the TLB entry has + * been changed by the vCPU in the mean time we skip the update. + * + * As this function uses atomic accesses we also need to ensure + * updates to tlb_entries follow the same access rules. We don't need + * to worry about this for oversized guests as MTTCG is disabled for + * them. + */ + +static void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start, uintptr_t length) { - uintptr_t addr; +#if TCG_OVERSIZED_GUEST + uintptr_t addr = tlb_entry->addr_write; - if (tlb_is_dirty_ram(tlb_entry)) { - addr = (tlb_entry->addr_write & TARGET_PAGE_MASK) + tlb_entry->addend; + if ((addr & (TLB_INVALID_MASK | TLB_MMIO | TLB_NOTDIRTY)) == 0) { + addr &= TARGET_PAGE_MASK; + addr += tlb_entry->addend; if ((addr - start) < length) { tlb_entry->addr_write |= TLB_NOTDIRTY; } } +#else + /* paired with atomic_mb_set in tlb_set_page_with_attrs */ + uintptr_t orig_addr = atomic_mb_read(&tlb_entry->addr_write); + uintptr_t addr = orig_addr; + + if ((addr & (TLB_INVALID_MASK | TLB_MMIO | TLB_NOTDIRTY)) == 0) { + addr &= TARGET_PAGE_MASK; + addr += atomic_read(&tlb_entry->addend); + if ((addr - start) < length) { + uintptr_t notdirty_addr = orig_addr | TLB_NOTDIRTY; + atomic_cmpxchg(&tlb_entry->addr_write, orig_addr, notdirty_addr); + } + } +#endif +} + +/* For atomic correctness when running MTTCG we need to use the right + * primitives when copying entries */ +static inline void copy_tlb_helper(CPUTLBEntry *d, CPUTLBEntry *s, + bool atomic_set) +{ +#if TCG_OVERSIZED_GUEST + *d = *s; +#else + if (atomic_set) { + d->addr_read = s->addr_read; + d->addr_code = s->addr_code; + atomic_set(&d->addend, atomic_read(&s->addend)); + /* Pairs with flag setting in tlb_reset_dirty_range */ + atomic_mb_set(&d->addr_write, atomic_read(&s->addr_write)); + } else { + d->addr_read = s->addr_read; + d->addr_write = atomic_read(&s->addr_write); + d->addr_code = s->addr_code; + d->addend = atomic_read(&s->addend); + } +#endif } +/* This is a cross vCPU call (i.e. another vCPU resetting the flags of + * the target vCPU). As such care needs to be taken that we don't + * dangerously race with another vCPU update. The only thing actually + * updated is the target TLB entry ->addr_write flags. + */ void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length) { CPUArchState *env; int mmu_idx; - assert_cpu_is_self(cpu); - env = cpu->env_ptr; for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) { unsigned int i; @@ -455,7 +513,7 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, target_ulong address; target_ulong code_address; uintptr_t addend; - CPUTLBEntry *te; + CPUTLBEntry *te, *tv, tn; hwaddr iotlb, xlat, sz; unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE; int asidx = cpu_asidx_from_attrs(cpu, attrs); @@ -490,41 +548,50 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, index = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); te = &env->tlb_table[mmu_idx][index]; - /* do not discard the translation in te, evict it into a victim tlb */ - env->tlb_v_table[mmu_idx][vidx] = *te; + tv = &env->tlb_v_table[mmu_idx][vidx]; + + /* addr_write can race with tlb_reset_dirty_range */ + copy_tlb_helper(tv, te, true); + env->iotlb_v[mmu_idx][vidx] = env->iotlb[mmu_idx][index]; /* refill the tlb */ env->iotlb[mmu_idx][index].addr = iotlb - vaddr; env->iotlb[mmu_idx][index].attrs = attrs; - te->addend = addend - vaddr; + + /* Now calculate the new entry */ + tn.addend = addend - vaddr; if (prot & PAGE_READ) { - te->addr_read = address; + tn.addr_read = address; } else { - te->addr_read = -1; + tn.addr_read = -1; } if (prot & PAGE_EXEC) { - te->addr_code = code_address; + tn.addr_code = code_address; } else { - te->addr_code = -1; + tn.addr_code = -1; } + + tn.addr_write = -1; if (prot & PAGE_WRITE) { if ((memory_region_is_ram(section->mr) && section->readonly) || memory_region_is_romd(section->mr)) { /* Write access calls the I/O callback. */ - te->addr_write = address | TLB_MMIO; + tn.addr_write = address | TLB_MMIO; } else if (memory_region_is_ram(section->mr) && cpu_physical_memory_is_clean( memory_region_get_ram_addr(section->mr) + xlat)) { - te->addr_write = address | TLB_NOTDIRTY; + tn.addr_write = address | TLB_NOTDIRTY; } else { - te->addr_write = address; + tn.addr_write = address; } - } else { - te->addr_write = -1; } + + /* Pairs with flag setting in tlb_reset_dirty_range */ + copy_tlb_helper(te, &tn, true); + /* atomic_mb_set(&te->addr_write, write_address); */ } /* Add a new TLB entry, but without specifying the memory @@ -687,10 +754,13 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index, if (cmp == page) { /* Found entry in victim tlb, swap tlb and iotlb. */ CPUTLBEntry tmptlb, *tlb = &env->tlb_table[mmu_idx][index]; + + copy_tlb_helper(&tmptlb, tlb, false); + copy_tlb_helper(tlb, vtlb, true); + copy_tlb_helper(vtlb, &tmptlb, true); + CPUIOTLBEntry tmpio, *io = &env->iotlb[mmu_idx][index]; CPUIOTLBEntry *vio = &env->iotlb_v[mmu_idx][vidx]; - - tmptlb = *tlb; *tlb = *vtlb; *vtlb = tmptlb; tmpio = *io; *io = *vio; *vio = tmpio; return true; } diff --git a/include/exec/cputlb.h b/include/exec/cputlb.h index d454c005b7..3f941783c5 100644 --- a/include/exec/cputlb.h +++ b/include/exec/cputlb.h @@ -23,8 +23,6 @@ /* cputlb.c */ void tlb_protect_code(ram_addr_t ram_addr); void tlb_unprotect_code(ram_addr_t ram_addr); -void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start, - uintptr_t length); extern int tlb_flush_count; #endif