From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:42781) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g9c8x-0003rs-9H for qemu-devel@nongnu.org; Mon, 08 Oct 2018 16:28:47 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1g9c3T-0002Or-8t for qemu-devel@nongnu.org; Mon, 08 Oct 2018 16:23:07 -0400 Received: from out3-smtp.messagingengine.com ([66.111.4.27]:41343) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1g9c3T-0002OP-19 for qemu-devel@nongnu.org; Mon, 08 Oct 2018 16:23:03 -0400 Date: Mon, 8 Oct 2018 16:23:01 -0400 From: "Emilio G. Cota" Message-ID: <20181008202301.GA24543@flamenco> References: <20181006214508.5331-1-cota@braap.org> <20181006214508.5331-3-cota@braap.org> <4dc1591e-adc9-eaaa-deea-07fd7f3470a4@linaro.org> <20181008144242.GC19899@flamenco> <498f3a82-0852-df46-d905-9e752f2c6ec1@linaro.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <498f3a82-0852-df46-d905-9e752f2c6ec1@linaro.org> Subject: Re: [Qemu-devel] [RFC 2/6] cputlb: do not evict invalid entries to the vtlb List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Richard Henderson Cc: qemu-devel@nongnu.org, Pranith Kumar , Alex =?iso-8859-1?Q?Benn=E9e?= On Mon, Oct 08, 2018 at 12:46:26 -0700, Richard Henderson wrote: > On 10/8/18 7:42 AM, Emilio G. Cota wrote: > > On Sun, Oct 07, 2018 at 19:09:01 -0700, Richard Henderson wrote: > >> On 10/6/18 2:45 PM, Emilio G. Cota wrote: > >>> Currently we evict an entry to the victim TLB when it doesn't match > >>> the current address. But it could be that there's no match because > >>> the current entry is invalid. Do not evict the entry to the vtlb > >>> in that case. > >>> > >>> This change will help us keep track of the TLB's use rate. > >>> > >>> Signed-off-by: Emilio G. Cota > >>> --- > >>> include/exec/cpu-all.h | 14 ++++++++++++++ > >>> accel/tcg/cputlb.c | 2 +- > >>> 2 files changed, 15 insertions(+), 1 deletion(-) > >>> > >>> diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h > >>> index 117d2fbbca..d938dedafc 100644 > >>> --- a/include/exec/cpu-all.h > >>> +++ b/include/exec/cpu-all.h > >>> @@ -362,6 +362,20 @@ static inline bool tlb_hit(target_ulong tlb_addr, target_ulong addr) > >>> return tlb_hit_page(tlb_addr, addr & TARGET_PAGE_MASK); > >>> } > >>> > >>> +/** > >>> + * tlb_is_valid - return true if at least one of the addresses is valid > >>> + * @te: pointer to CPUTLBEntry > >>> + * > >>> + * This is useful when we don't have a particular address to compare against, > >>> + * and we just want to know whether any entry holds valid data. > >>> + */ > >>> +static inline bool tlb_is_valid(const CPUTLBEntry *te) > >>> +{ > >>> + return !(te->addr_read & TLB_INVALID_MASK) || > >>> + !(te->addr_write & TLB_INVALID_MASK) || > >>> + !(te->addr_code & TLB_INVALID_MASK); > >>> +} > >> > >> No, I think you misunderstand. > >> > >> First, TLB_INVALID_MASK is only ever set for addr_write, in response to > >> PAGE_WRITE_INV. Second, an entry that is invalid for write is still valid for > >> read+exec. So there is benefit to swapping it out to the victim cache. > >> > >> This is used by the s390x target to make the "lowpage" read-only, which is a > >> special architected 512 byte range within pages 0 and 1. This is done by > >> forcing writes, but not reads, back through tlb_fill. > > > > Aah I see. The point is to avoid pushing to the victim cache > > an entry that is all invalid, not just partially invalid. > > I've slightly misspoken here. It is (ab)used for the s390 thing, but that bit > is also set by memset -1. Perhaps you might check > > static inline bool tlb_is_invalid(const CPUTLBEntry *te) > { > return te->addr_read & te->addr_write & te->addr_code & TLB_INVALID_MASK; > } > > That is, all forms of access have the INVALID bit set. I see. I just ran a few tests and the below gives the best performance, so I'll go with it: static inline bool tlb_is_empty(const CPUTLBEntry *te) { return te->addr_read == -1 && te->addr_write == -1 && te->addr_code == -1; } I renamed it from "invalid" to "empty" to avoid even thinking about the invalid flag. Thanks, Emilio