From: Xiao Guangrong <guangrong.xiao@linux.intel.com>
To: pbonzini@redhat.com
Cc: gleb@kernel.org, mtosatti@redhat.com, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org,
Xiao Guangrong <guangrong.xiao@linux.intel.com>
Subject: [PATCH 07/15] KVM: MTRR: improve kvm_mtrr_get_guest_memory_type
Date: Sat, 30 May 2015 18:59:18 +0800 [thread overview]
Message-ID: <1432983566-15773-8-git-send-email-guangrong.xiao@linux.intel.com> (raw)
In-Reply-To: <1432983566-15773-1-git-send-email-guangrong.xiao@linux.intel.com>
- kvm_mtrr_get_guest_memory_type() only checks one page in MTRRs so that
it's unnecessary to check to see if the range is partially covered in
MTRR
- optimize the check of overlap memory type and add some comments to explain
the precedence
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
---
arch/x86/kvm/mtrr.c | 89 ++++++++++++++++++++++++++---------------------------
1 file changed, 44 insertions(+), 45 deletions(-)
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index bc9c6da..d3c06d2 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -231,24 +231,16 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return 0;
}
-/*
- * The function is based on mtrr_type_lookup() in
- * arch/x86/kernel/cpu/mtrr/generic.c
- */
-static int get_mtrr_type(struct kvm_mtrr *mtrr_state,
- u64 start, u64 end)
+u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
{
- u64 base, mask;
- u8 prev_match, curr_match;
- int i, num_var_ranges = KVM_NR_VAR_MTRR;
+ struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+ u64 base, mask, start = gfn_to_gpa(gfn);
+ int i, num_var_ranges = KVM_NR_VAR_MTRR, type_mask, type = -1;
/* MTRR is completely disabled, use UC for all of physical memory. */
if (!mtrr_state->mtrr_enabled)
return MTRR_TYPE_UNCACHABLE;
- /* Make end inclusive end, instead of exclusive */
- end--;
-
/* Look in fixed ranges. Just return the type as per start */
if (mtrr_state->fixed_mtrr_enabled && (start < 0x100000)) {
int idx;
@@ -273,9 +265,9 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state,
* Look of multiple ranges matching this address and pick type
* as per MTRR precedence
*/
- prev_match = 0xFF;
+ type_mask = (1 << MTRR_TYPE_WRBACK) | (1 << MTRR_TYPE_WRTHROUGH);
for (i = 0; i < num_var_ranges; ++i) {
- unsigned short start_state, end_state;
+ int curr_type;
if (!(mtrr_state->var_ranges[i].mask & (1 << 11)))
continue;
@@ -283,50 +275,57 @@ static int get_mtrr_type(struct kvm_mtrr *mtrr_state,
base = mtrr_state->var_ranges[i].base & PAGE_MASK;
mask = mtrr_state->var_ranges[i].mask & PAGE_MASK;
- start_state = ((start & mask) == (base & mask));
- end_state = ((end & mask) == (base & mask));
- if (start_state != end_state)
- return 0xFE;
-
if ((start & mask) != (base & mask))
continue;
- curr_match = mtrr_state->var_ranges[i].base & 0xff;
- if (prev_match == 0xFF) {
- prev_match = curr_match;
+ /*
+ * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR
+ * Precedences.
+ */
+
+ curr_type = mtrr_state->var_ranges[i].base & 0xff;
+ if (type == -1) {
+ type = curr_type;
continue;
}
- if (prev_match == MTRR_TYPE_UNCACHABLE ||
- curr_match == MTRR_TYPE_UNCACHABLE)
+ /*
+ * If two or more variable memory ranges match and the
+ * memory types are identical, then that memory type is
+ * used.
+ */
+ if (type == curr_type)
+ continue;
+
+ /*
+ * If two or more variable memory ranges match and one of
+ * the memory types is UC, the UC memory type used.
+ */
+ if (curr_type == MTRR_TYPE_UNCACHABLE)
return MTRR_TYPE_UNCACHABLE;
- if ((prev_match == MTRR_TYPE_WRBACK &&
- curr_match == MTRR_TYPE_WRTHROUGH) ||
- (prev_match == MTRR_TYPE_WRTHROUGH &&
- curr_match == MTRR_TYPE_WRBACK)) {
- prev_match = MTRR_TYPE_WRTHROUGH;
- curr_match = MTRR_TYPE_WRTHROUGH;
+ /*
+ * If two or more variable memory ranges match and the
+ * memory types are WT and WB, the WT memory type is used.
+ */
+ if (((1 << type) & type_mask) &&
+ ((1 << curr_type) & type_mask)) {
+ type = MTRR_TYPE_WRTHROUGH;
+ continue;
}
- if (prev_match != curr_match)
- return MTRR_TYPE_UNCACHABLE;
+ /*
+ * For overlaps not defined by the above rules, processor
+ * behavior is undefined.
+ */
+
+ /* We use WB for this undefined behavior. :( */
+ return MTRR_TYPE_WRBACK;
}
- if (prev_match != 0xFF)
- return prev_match;
+ if (type != -1)
+ return type;
return mtrr_state->def_type;
}
-
-u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- u8 mtrr;
-
- mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
- (gfn << PAGE_SHIFT) + PAGE_SIZE);
- if (mtrr == 0xfe || mtrr == 0xff)
- mtrr = MTRR_TYPE_WRBACK;
- return mtrr;
-}
EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
--
2.1.0
next prev parent reply other threads:[~2015-05-30 11:00 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-30 10:59 [PATCH 00/15] KVM: x86: fully implement vMTRR Xiao Guangrong
2015-05-30 10:58 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 01/15] KVM: x86: move MTRR related code to a separate file Xiao Guangrong
2015-05-30 10:59 ` [PATCH 02/15] KVM: MTRR: handle MSR_MTRRcap in kvm_mtrr_get_msr Xiao Guangrong
2015-05-30 10:59 ` [PATCH 03/15] KVM: MTRR: remove mtrr_state.have_fixed Xiao Guangrong
2015-05-30 10:59 ` [PATCH 04/15] KVM: MTRR: exactly define the size of variable MTRRs Xiao Guangrong
2015-05-30 10:59 ` [PATCH 05/15] KVM: MTRR: clean up mtrr default type Xiao Guangrong
2015-06-01 9:11 ` Paolo Bonzini
2015-06-03 1:55 ` Xiao Guangrong
2015-06-09 0:35 ` David Matlack
2015-05-30 10:59 ` [PATCH 06/15] KVM: MTRR: do not split 64 bits MSR content Xiao Guangrong
2015-05-30 10:59 ` Xiao Guangrong [this message]
2015-06-01 9:16 ` [PATCH 07/15] KVM: MTRR: improve kvm_mtrr_get_guest_memory_type Paolo Bonzini
2015-06-03 2:12 ` Xiao Guangrong
2015-06-03 7:57 ` Paolo Bonzini
2015-05-30 10:59 ` [PATCH 08/15] KVM: MTRR: introduce fixed_mtrr_segment table Xiao Guangrong
2015-06-01 9:25 ` Paolo Bonzini
2015-06-03 2:29 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 09/15] KVM: MTRR: introduce var_mtrr_range Xiao Guangrong
2015-06-09 0:36 ` David Matlack
2015-06-09 2:38 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 10/15] KVM: MTRR: sort variable MTRRs Xiao Guangrong
2015-06-01 9:27 ` Paolo Bonzini
2015-06-03 2:31 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 11/15] KVM: MTRR: introduce fixed_mtrr_addr_* functions Xiao Guangrong
2015-05-30 10:59 ` [PATCH 12/15] KVM: MTRR: introduce mtrr_for_each_mem_type Xiao Guangrong
2015-06-01 9:33 ` Paolo Bonzini
2015-06-01 14:26 ` Paolo Bonzini
2015-06-03 2:57 ` Xiao Guangrong
2015-06-03 2:40 ` Xiao Guangrong
2015-06-09 0:36 ` David Matlack
2015-06-09 2:45 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 13/15] KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type Xiao Guangrong
2015-05-30 10:59 ` [PATCH 14/15] KVM: MTRR: do not map huage page for non-consistent range Xiao Guangrong
2015-06-01 9:36 ` Paolo Bonzini
2015-06-01 9:38 ` Paolo Bonzini
2015-06-03 2:56 ` Xiao Guangrong
2015-06-03 7:55 ` Paolo Bonzini
2015-06-04 8:23 ` Xiao Guangrong
2015-06-04 8:26 ` Xiao Guangrong
2015-06-04 8:34 ` Paolo Bonzini
2015-06-04 8:36 ` Paolo Bonzini
2015-06-05 6:33 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 15/15] KVM: VMX: fully implement guest MTRR virtualization Xiao Guangrong
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=1432983566-15773-8-git-send-email-guangrong.xiao@linux.intel.com \
--to=guangrong.xiao@linux.intel.com \
--cc=gleb@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).