On Mon, Jun 17, 2019 at 11:00:15AM -0700, Fenghua Yu wrote:
> @@ -832,33 +857,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
> c->x86_capability[CPUID_D_1_EAX] = eax;
> }
>
> - /* Additional Intel-defined flags: level 0x0000000F */
> - if (c->cpuid_level >= 0x0000000F) {
> -
> - /* QoS sub-leaf, EAX=0Fh, ECX=0 */
> - cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
> - c->x86_capability[CPUID_F_0_EDX] = edx;
> -
> - if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
> - /* will be overridden if occupancy monitoring exists */
> - c->x86_cache_max_rmid = ebx;
> -
> - /* QoS sub-leaf, EAX=0Fh, ECX=1 */
> - cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
> - c->x86_capability[CPUID_F_1_EDX] = edx;
> -
> - if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
> - ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
> - (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
> - c->x86_cache_max_rmid = ecx;
> - c->x86_cache_occ_scale = ebx;
> - }
> - } else {
> - c->x86_cache_max_rmid = -1;
> - c->x86_cache_occ_scale = -1;
> - }
> - }
> -
> /* AMD-defined flags: level 0x80000001 */
> eax = cpuid_eax(0x80000000);
> c->extended_cpuid_level = eax;
What I meant with having a separate patch doing the carve out is to have
a single patch doing *only* code movement - no changes, no nothing. So
that it is clear what happens. Intermixing code movement and changes is
a bad idea and hard to review.
IOW, I did this:
---
>From cef4f58a3da0465bbff33b2d669cc600b775f3ba Mon Sep 17 00:00:00 2001
From: Borislav Petkov <[email protected]>
Date: Wed, 19 Jun 2019 17:24:34 +0200
Subject: [PATCH] x86/cpufeatures: Carve out CQM features retrieval
... into a separate function for better readability. Split out from a
patch from Fenghua Yu <[email protected]> to keep the mechanical,
sole code movement separate for easy review.
No functional changes.
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: [email protected]
---
arch/x86/kernel/cpu/common.c | 60 ++++++++++++++++++++----------------
1 file changed, 33 insertions(+), 27 deletions(-)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..fe6ed9696467 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -801,6 +801,38 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
}
}
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+ u32 eax, ebx, ecx, edx;
+
+ /* Additional Intel-defined flags: level 0x0000000F */
+ if (c->cpuid_level >= 0x0000000F) {
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=0 */
+ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_F_0_EDX] = edx;
+
+ if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = ebx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_F_1_EDX] = edx;
+
+ if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
+ ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
+ (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
+ }
+ } else {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ }
+ }
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
@@ -832,33 +864,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_D_1_EAX] = eax;
}
- /* Additional Intel-defined flags: level 0x0000000F */
- if (c->cpuid_level >= 0x0000000F) {
-
- /* QoS sub-leaf, EAX=0Fh, ECX=0 */
- cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_0_EDX] = edx;
-
- if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
- /* will be overridden if occupancy monitoring exists */
- c->x86_cache_max_rmid = ebx;
-
- /* QoS sub-leaf, EAX=0Fh, ECX=1 */
- cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_1_EDX] = edx;
-
- if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
- ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
- (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
- c->x86_cache_max_rmid = ecx;
- c->x86_cache_occ_scale = ebx;
- }
- } else {
- c->x86_cache_max_rmid = -1;
- c->x86_cache_occ_scale = -1;
- }
- }
-
/* AMD-defined flags: level 0x80000001 */
eax = cpuid_eax(0x80000000);
c->extended_cpuid_level = eax;
@@ -889,6 +894,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
init_scattered_cpuid_features(c);
init_speculation_control(c);
+ init_cqm(c);
/*
* Clear/Set all flags overridden by options, after probe.
--
2.21.0
---
This way you have *pure* code movement only.
And then your second patch turns into this, which shows *exactly* what
has been changed in init_cqm().
Please have a look and send me only the now third patch with corrected
commit message.
Thx.
---
>From e33527b8cde8bef84cdc90651d1a1c7a9a5234d7 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <[email protected]>
Date: Wed, 19 Jun 2019 18:51:09 +0200
Subject: [PATCH] x86/cpufeatures: Combine word 11 and 12 into a new
scattered features word
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
It's a waste for the four X86_FEATURE_CQM_* feature bits to occupy two
whole feature bits words. To better utilize feature words, re-define
word 11 to host scattered features and move the four X86_FEATURE_CQM_*
features into Linux defined word 11. More scattered features can be
added in word 11 in the future.
Rename leaf 11 in cpuid_leafs to CPUID_LNX_4 to reflect it's a
Linux-defined leaf.
Rename leaf 12 as CPUID_DUMMY which will be replaced by a meaningful
name in the next patch when CPUID.7.1:EAX occupies world 12.
Maximum number of RMID and cache occupancy scale are retrieved from
CPUID.0xf.1 after scattered CQM features are enumerated. Carve out the
code into a separate function.
KVM doesn't support resctrl now. So it's safe to move the
X86_FEATURE_CQM_* features to scattered features word 11 for KVM.
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Aaron Lewis <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Babu Moger <[email protected]>
Cc: "Chang S. Bae" <[email protected]>
Cc: "Sean J Christopherson" <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Konrad Rzeszutek Wilk <[email protected]>
Cc: kvm ML <[email protected]>
Cc: Masahiro Yamada <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Nadav Amit <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Peter Feiner <[email protected]>
Cc: "Peter Zijlstra (Intel)" <[email protected]>
Cc: "Radim Krčmář" <[email protected]>
Cc: "Rafael J. Wysocki" <[email protected]>
Cc: Ravi V Shankar <[email protected]>
Cc: Sherry Hurwitz <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Thomas Lendacky <[email protected]>
Cc: x86 <[email protected]>
Link:
https://lkml.kernel.org/r/[email protected]
---
arch/x86/include/asm/cpufeature.h | 4 ++--
arch/x86/include/asm/cpufeatures.h | 17 +++++++------
arch/x86/kernel/cpu/common.c | 38 ++++++++++++------------------
arch/x86/kernel/cpu/cpuid-deps.c | 3 +++
arch/x86/kernel/cpu/scattered.c | 4 ++++
arch/x86/kvm/cpuid.h | 2 --
6 files changed, 34 insertions(+), 34 deletions(-)
diff --git a/arch/x86/include/asm/cpufeature.h
b/arch/x86/include/asm/cpufeature.h
index 1d337c51f7e6..403f70c2e431 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,8 +22,8 @@ enum cpuid_leafs
CPUID_LNX_3,
CPUID_7_0_EBX,
CPUID_D_1_EAX,
- CPUID_F_0_EDX,
- CPUID_F_1_EDX,
+ CPUID_LNX_4,
+ CPUID_DUMMY,
CPUID_8000_0008_EBX,
CPUID_6_EAX,
CPUID_8000_000A_EDX,
diff --git a/arch/x86/include/asm/cpufeatures.h
b/arch/x86/include/asm/cpufeatures.h
index 1017b9c7dfe0..be858b86023a 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -271,13 +271,16 @@
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1
instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS
instructions */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring
*/
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring
*/
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring
*/
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring
*/
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring
*/
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring
*/
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fe6ed9696467..efb114298cfb 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -803,33 +803,25 @@ static void init_speculation_control(struct cpuinfo_x86
*c)
static void init_cqm(struct cpuinfo_x86 *c)
{
- u32 eax, ebx, ecx, edx;
-
- /* Additional Intel-defined flags: level 0x0000000F */
- if (c->cpuid_level >= 0x0000000F) {
+ if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ return;
+ }
- /* QoS sub-leaf, EAX=0Fh, ECX=0 */
- cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_0_EDX] = edx;
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = cpuid_ebx(0xf);
- if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
- /* will be overridden if occupancy monitoring exists */
- c->x86_cache_max_rmid = ebx;
+ if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+ u32 eax, ebx, ecx, edx;
- /* QoS sub-leaf, EAX=0Fh, ECX=1 */
- cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_1_EDX] = edx;
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
- if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
- ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
- (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
- c->x86_cache_max_rmid = ecx;
- c->x86_cache_occ_scale = ebx;
- }
- } else {
- c->x86_cache_max_rmid = -1;
- c->x86_cache_occ_scale = -1;
- }
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
}
}
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..fa07a224e7b9 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -59,6 +59,9 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
{}
};
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
+ { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 9a327d5b6d1f..d78a61408243 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,8 +47,6 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
- [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
- [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
[CPUID_6_EAX] = { 6, 0, CPUID_EAX},
[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
--
2.21.0
--
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.
