diff for duplicates of <20130725010438.GE10517@redhat.com> diff --git a/a/1.txt b/N1/1.txt index e32a2bc..2e78ef7 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -112,8 +112,8 @@ refcounting and doesn't require in turn the driver to mark the page PageReserved). The above explains why KVM needs to skip the refcounting on -PageReserved = true && pfn_valid() = true, and it must skip the -refcounting for pfn_valid = false without trying to call pfn_to_page +PageReserved == true && pfn_valid() == true, and it must skip the +refcounting for pfn_valid == false without trying to call pfn_to_page (or it'll crash). Now the code doing the THP check with smp_rmb is very safe, possibly @@ -147,8 +147,8 @@ on a head page anymore. Untested RFC patch follows. -= -From 76927680df7034a575bed5da754f7ebe94481fb3 Mon Sep 17 00:00:00 2001 +== +>From 76927680df7034a575bed5da754f7ebe94481fb3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli <aarcange@redhat.com> Date: Thu, 25 Jul 2013 02:56:08 +0200 Subject: [PATCH] kvm: optimize away THP checks in kvm_is_mmio_pfn() diff --git a/a/content_digest b/N1/content_digest index 91c8de0..632f3db 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -10,7 +10,7 @@ "ref\020130724103012.GA14667@redhat.com\0" "From\0Andrea Arcangeli <aarcange@redhat.com>\0" "Subject\0Re: [PATCH 2/2] kvm: powerpc: set cache coherency only for kernel managed pages\0" - "Date\0Thu, 25 Jul 2013 01:04:38 +0000\0" + "Date\0Thu, 25 Jul 2013 03:04:38 +0200\0" "To\0Gleb Natapov <gleb@redhat.com>\0" "Cc\0Alexander Graf <agraf@suse.de>" " \\\342\200\234tiejun.chen\342\200\235\\ <tiejun.chen@windriver.com>" @@ -135,8 +135,8 @@ "PageReserved).\n" "\n" "The above explains why KVM needs to skip the refcounting on\n" - "PageReserved = true && pfn_valid() = true, and it must skip the\n" - "refcounting for pfn_valid = false without trying to call pfn_to_page\n" + "PageReserved == true && pfn_valid() == true, and it must skip the\n" + "refcounting for pfn_valid == false without trying to call pfn_to_page\n" "(or it'll crash).\n" "\n" "Now the code doing the THP check with smp_rmb is very safe, possibly\n" @@ -170,8 +170,8 @@ "\n" "Untested RFC patch follows.\n" "\n" - "=\n" - "From 76927680df7034a575bed5da754f7ebe94481fb3 Mon Sep 17 00:00:00 2001\n" + "==\n" + ">From 76927680df7034a575bed5da754f7ebe94481fb3 Mon Sep 17 00:00:00 2001\n" "From: Andrea Arcangeli <aarcange@redhat.com>\n" "Date: Thu, 25 Jul 2013 02:56:08 +0200\n" "Subject: [PATCH] kvm: optimize away THP checks in kvm_is_mmio_pfn()\n" @@ -237,4 +237,4 @@ " \treturn true;\n" } -4414669ee66c9f85aebc3d2d1f32ff4294c370cc85517f595b164057ca30d9cd +63aecaa15619045f14c810e32cdcf30283c87cf5146e91b8bd5a95ca94531282
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.