From: Paolo Bonzini <pbonzini@redhat.com> To: "Barret Rhoden" <brho@google.com>, "Dan Williams" <dan.j.williams@intel.com>, "Dave Jiang" <dave.jiang@intel.com>, "Ross Zwisler" <zwisler@kernel.org>, "Vishal Verma" <vishal.l.verma@intel.com>, "Radim Krčmář" <rkrcmar@redhat.com>, "Thomas Gleixner" <tglx@linutronix.de>, "Ingo Molnar" <mingo@redhat.com>, "Borislav Petkov" <bp@alien8.de> Cc: kvm@vger.kernel.org, yu.c.zhang@intel.com, linux-nvdimm@lists.01.org, x86@kernel.org, linux-kernel@vger.kernel.org, "H. Peter Anvin" <hpa@zytor.com>, yi.z.zhang@intel.com Subject: Re: [RFC PATCH] kvm: Use huge pages for DAX-backed files Date: Tue, 6 Nov 2018 22:16:30 +0100 [thread overview] Message-ID: <13b9a5a5-6773-131e-8014-f1b1bc975794@redhat.com> (raw) In-Reply-To: <20181106160553.5a8025ed@gnomeregan.cam.corp.google.com> On 06/11/2018 22:05, Barret Rhoden wrote: > On 2018-10-29 at 17:07 Barret Rhoden <brho@google.com> wrote: >> Another issue is that kvm_mmu_zap_collapsible_spte() also uses >> PageTransCompoundMap() to detect huge pages, but we don't have a way to >> get the HVA easily. Can we just aggressively zap DAX pages there? > > Any thoughts about this? Is there a way to determine the HVA or GFN in > this function: Yes, iter.gfn is the gfn inside the loop and iter.level is the level (1=PTE, 2=PDE, ...). iter.level of course is unusable here, similar to *levelp in transparent_hugepage_adjust, but you can use iter.gfn and gfn_to_hva. Paolo > static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, > struct kvm_rmap_head *rmap_head) > { > u64 *sptep; > struct rmap_iterator iter; > int need_tlb_flush = 0; > kvm_pfn_t pfn; > struct kvm_mmu_page *sp; > > restart: > for_each_rmap_spte(rmap_head, &iter, sptep) { > sp = page_header(__pa(sptep)); > pfn = spte_to_pfn(*sptep); > > /* > * We cannot do huge page mapping for indirect shadow pages, > * which are found on the last rmap (level = 1) when not using > * tdp; such shadow pages are synced with the page table in > * the guest, and the guest page table is using 4K page size > * mapping if the indirect sp has level = 1. > */ > if (sp->role.direct && > !kvm_is_reserved_pfn(pfn) && > PageTransCompoundMap(pfn_to_page(pfn))) { > pte_list_remove(rmap_head, sptep); > need_tlb_flush = 1; > goto restart; > } > } > > return need_tlb_flush; > } > > If not, I was thinking of changing that loop to always remove PTEs for > DAX mappings, with the understanding that they'll get faulted back in > later. Ideally, we'd like to check if the page is huge, but DAX can't > use the PageTransCompoundMap check. > > Thanks, > > Barret > > > _______________________________________________ Linux-nvdimm mailing list Linux-nvdimm@lists.01.org https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com> To: "Barret Rhoden" <brho@google.com>, "Dan Williams" <dan.j.williams@intel.com>, "Dave Jiang" <dave.jiang@intel.com>, "Ross Zwisler" <zwisler@kernel.org>, "Vishal Verma" <vishal.l.verma@intel.com>, "Radim Krčmář" <rkrcmar@redhat.com>, "Thomas Gleixner" <tglx@linutronix.de>, "Ingo Molnar" <mingo@redhat.com>, "Borislav Petkov" <bp@alien8.de> Cc: linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org, "H. Peter Anvin" <hpa@zytor.com>, x86@kernel.org, kvm@vger.kernel.org, yu.c.zhang@intel.com, yi.z.zhang@intel.com Subject: Re: [RFC PATCH] kvm: Use huge pages for DAX-backed files Date: Tue, 6 Nov 2018 22:16:30 +0100 [thread overview] Message-ID: <13b9a5a5-6773-131e-8014-f1b1bc975794@redhat.com> (raw) In-Reply-To: <20181106160553.5a8025ed@gnomeregan.cam.corp.google.com> On 06/11/2018 22:05, Barret Rhoden wrote: > On 2018-10-29 at 17:07 Barret Rhoden <brho@google.com> wrote: >> Another issue is that kvm_mmu_zap_collapsible_spte() also uses >> PageTransCompoundMap() to detect huge pages, but we don't have a way to >> get the HVA easily. Can we just aggressively zap DAX pages there? > > Any thoughts about this? Is there a way to determine the HVA or GFN in > this function: Yes, iter.gfn is the gfn inside the loop and iter.level is the level (1=PTE, 2=PDE, ...). iter.level of course is unusable here, similar to *levelp in transparent_hugepage_adjust, but you can use iter.gfn and gfn_to_hva. Paolo > static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, > struct kvm_rmap_head *rmap_head) > { > u64 *sptep; > struct rmap_iterator iter; > int need_tlb_flush = 0; > kvm_pfn_t pfn; > struct kvm_mmu_page *sp; > > restart: > for_each_rmap_spte(rmap_head, &iter, sptep) { > sp = page_header(__pa(sptep)); > pfn = spte_to_pfn(*sptep); > > /* > * We cannot do huge page mapping for indirect shadow pages, > * which are found on the last rmap (level = 1) when not using > * tdp; such shadow pages are synced with the page table in > * the guest, and the guest page table is using 4K page size > * mapping if the indirect sp has level = 1. > */ > if (sp->role.direct && > !kvm_is_reserved_pfn(pfn) && > PageTransCompoundMap(pfn_to_page(pfn))) { > pte_list_remove(rmap_head, sptep); > need_tlb_flush = 1; > goto restart; > } > } > > return need_tlb_flush; > } > > If not, I was thinking of changing that loop to always remove PTEs for > DAX mappings, with the understanding that they'll get faulted back in > later. Ideally, we'd like to check if the page is huge, but DAX can't > use the PageTransCompoundMap check. > > Thanks, > > Barret > > >
next prev parent reply other threads:[~2018-11-06 21:16 UTC|newest] Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-10-29 21:07 [RFC PATCH] kvm: Use huge pages for DAX-backed files Barret Rhoden 2018-10-29 21:07 ` Barret Rhoden 2018-10-29 22:25 ` Dan Williams 2018-10-29 22:25 ` Dan Williams 2018-10-29 22:25 ` Dan Williams [not found] ` <CAPcyv4gJUjuSKwy7i2wuKR=Vz-AkDrxnGya5qkg7XTFxuXbtzw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2018-10-30 0:28 ` Barret Rhoden 2018-10-30 0:28 ` Barret Rhoden 2018-10-30 3:10 ` Dan Williams 2018-10-30 3:10 ` Dan Williams [not found] ` <CAPcyv4gQztHrJ3--rhU4ZpaZyyqdqE0=gx50CRArHKiXwfYC+A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2018-10-30 19:45 ` Barret Rhoden 2018-10-30 19:45 ` Barret Rhoden 2018-10-31 8:49 ` Paolo Bonzini 2018-10-31 8:49 ` Paolo Bonzini 2018-11-02 20:32 ` Barret Rhoden 2018-11-06 10:19 ` Paolo Bonzini [not found] ` <876d5a71-8dda-4728-5329-4e169777ba4a-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> 2018-11-06 16:22 ` Barret Rhoden 2018-11-06 16:22 ` Barret Rhoden 2018-10-31 3:05 ` Yu Zhang 2018-10-31 3:05 ` Yu Zhang 2018-10-31 3:05 ` Yu Zhang 2018-10-31 8:52 ` Paolo Bonzini 2018-10-31 8:52 ` Paolo Bonzini 2018-10-31 8:52 ` Paolo Bonzini 2018-10-31 21:16 ` Dan Williams 2018-10-31 21:16 ` Dan Williams 2018-10-31 21:16 ` Dan Williams 2018-11-06 10:22 ` Paolo Bonzini [not found] ` <20181029210716.212159-1-brho-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org> 2018-11-06 21:05 ` Barret Rhoden 2018-11-06 21:05 ` Barret Rhoden 2018-11-06 21:16 ` Paolo Bonzini [this message] 2018-11-06 21:16 ` Paolo Bonzini 2018-11-06 21:17 ` Barret Rhoden
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=13b9a5a5-6773-131e-8014-f1b1bc975794@redhat.com \ --to=pbonzini@redhat.com \ --cc=bp@alien8.de \ --cc=brho@google.com \ --cc=dan.j.williams@intel.com \ --cc=dave.jiang@intel.com \ --cc=hpa@zytor.com \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-nvdimm@lists.01.org \ --cc=mingo@redhat.com \ --cc=rkrcmar@redhat.com \ --cc=tglx@linutronix.de \ --cc=vishal.l.verma@intel.com \ --cc=x86@kernel.org \ --cc=yi.z.zhang@intel.com \ --cc=yu.c.zhang@intel.com \ --cc=zwisler@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.