[PATCHv5 0/4] apic: core part for eoi optimization support

[PATCHv5 0/4] apic: core part for eoi optimization support

[Michael S. Tsirkin]

Hi Ingo, please cosider the following patches for tip.git and for
3.5.

This patchset includes just the core bits for the eoi optimization.
Please note that even though I numbered it PATCHv5 to stress this is the
latest version, in fact there are absolutely no changes in the patches
included here since v1.  the only change is that I split out kvm bits
out to a separate patch.

Avi indicated the preferred merging path is to merge core bits throug
tip.git and the kvm bits through kvm. So I'd like it for it to be merged
in tip and merged for 3.5: this will make sure APIs for kvm are in
place, minor fixes included here will also be helpful.  Also in my
testing this gives a tiny speedup on some benchmarks, these will get
wider testing this way.  The kvm parts, posted separately, will be
subsequently merged through kvm.git: they reduce the # of exits by about
half, details are in the kvm patchset which was posted separately.

---

I'm looking at reducing the interrupt overhead for virtualized guests:
some workloads spend a large part of their time processing interrupts.
This patchset supplies infrastructure to reduce the IRQ ack overhead on
x86: the idea is to add an eoi_write callback that we can then optimize
without touching other apic functionality.

The main user weill be kvm: on kvm, an EOI write from the guest causes an
expensive exit to host; we can avoid this using shared memory as the
last patches in the series demonstrate.

But I also wrote a micro-optimized version for the regular x2apic: this
shaves off a branch and about 9 instructions from EOI when x2apic is
used, and a comment in ack_APIC_irq implies that someone counted
instructions there, at some point.

That's patch 4 in the series - if someone's unhappy with
this patch specifically this patch can be dropped
as nothing else in the series depends on it.

Also included in the patchset are a couple of trivial macro fixes.

The patches work fine on my boxes. See individual patches
for perf tests. You need to patch qemu to whitelist the kvm feature.
qemu patch will be sent as a reply to this mail.

The patches are against 3.4-rc7 - let me know if
I need to rebase.

Please review, and consider for linux 3.5.

Thanks,
MST


Michael S. Tsirkin (4):
  apic: fix typo EIO_ACK -> EOI_ACK and document
  apic: use symbolic APIC_EOI_ACK
  x86: add apic->eoi_write callback
  x86: eoi micro-optimization

 arch/x86/include/asm/apic.h            |   22 +++++++++++++++++++---
 arch/x86/include/asm/apicdef.h         |    2 +-
 arch/x86/kernel/apic/apic_flat_64.c    |    2 ++
 arch/x86/kernel/apic/apic_noop.c       |    1 +
 arch/x86/kernel/apic/apic_numachip.c   |    1 +
 arch/x86/kernel/apic/bigsmp_32.c       |    1 +
 arch/x86/kernel/apic/es7000_32.c       |    2 ++
 arch/x86/kernel/apic/numaq_32.c        |    1 +
 arch/x86/kernel/apic/probe_32.c        |    1 +
 arch/x86/kernel/apic/summit_32.c       |    1 +
 arch/x86/kernel/apic/x2apic_cluster.c  |    1 +
 arch/x86/kernel/apic/x2apic_phys.c     |    1 +
 arch/x86/kernel/apic/x2apic_uv_x.c     |    1 +
 arch/x86/platform/visws/visws_quirks.c |    2 +-
 14 files changed, 34 insertions(+), 5 deletions(-)

-- 
MST

[PATCHv5 1/4] apic: fix typo EIO_ACK -> EOI_ACK and document

[Michael S. Tsirkin]

Fix typo in the macro name and document the
reason it has this value. Update users.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/x86/include/asm/apicdef.h         |    2 +-
 arch/x86/platform/visws/visws_quirks.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 134bba0..c46bb99 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -37,7 +37,7 @@
 #define		APIC_ARBPRI_MASK	0xFFu
 #define	APIC_PROCPRI	0xA0
 #define	APIC_EOI	0xB0
-#define		APIC_EIO_ACK		0x0
+#define		APIC_EOI_ACK		0x0 /* Docs say 0 for future compat. */
 #define	APIC_RRR	0xC0
 #define	APIC_LDR	0xD0
 #define		APIC_LDR_MASK		(0xFFu << 24)
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index c7abf13..94d8a39 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -445,7 +445,7 @@ static void ack_cobalt_irq(struct irq_data *data)
 
 	spin_lock_irqsave(&cobalt_lock, flags);
 	disable_cobalt_irq(data);
-	apic_write(APIC_EOI, APIC_EIO_ACK);
+	apic_write(APIC_EOI, APIC_EOI_ACK);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
-- 
MST

[tip:x86/apic] x86/apic: Fix typo EIO_ACK -> EOI_ACK and document it

[tip-bot for Michael S. Tsirkin]

Commit-ID:  c8f64bf7df9e4858c051b6c1c09582359b97677d
Gitweb:     http://git.kernel.org/tip/c8f64bf7df9e4858c051b6c1c09582359b97677d
Author:     Michael S. Tsirkin <mst@redhat.com>
AuthorDate: Wed, 16 May 2012 19:03:25 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 18 May 2012 09:46:07 +0200

x86/apic: Fix typo EIO_ACK -> EOI_ACK and document it

Fix typo in the macro name and document the
reason it has this value. Update users.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: gleb@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/37867b31b9330690af2e60a2a7c4cb4b1b070caf.1337184153.git.mst@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apicdef.h         |    2 +-
 arch/x86/platform/visws/visws_quirks.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 134bba0..c46bb99 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -37,7 +37,7 @@
 #define		APIC_ARBPRI_MASK	0xFFu
 #define	APIC_PROCPRI	0xA0
 #define	APIC_EOI	0xB0
-#define		APIC_EIO_ACK		0x0
+#define		APIC_EOI_ACK		0x0 /* Docs say 0 for future compat. */
 #define	APIC_RRR	0xC0
 #define	APIC_LDR	0xD0
 #define		APIC_LDR_MASK		(0xFFu << 24)
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index c7abf13..94d8a39 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -445,7 +445,7 @@ static void ack_cobalt_irq(struct irq_data *data)
 
 	spin_lock_irqsave(&cobalt_lock, flags);
 	disable_cobalt_irq(data);
-	apic_write(APIC_EOI, APIC_EIO_ACK);
+	apic_write(APIC_EOI, APIC_EOI_ACK);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 

[PATCHv5 2/4] apic: use symbolic APIC_EOI_ACK

[Michael S. Tsirkin]

Use the symbol instead of hard-coded numbers,
now that the reason for the value is documented
where the constant is defined we don't need to
duplicate this explanation in code.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/x86/include/asm/apic.h |    4 +---
 1 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index d854101..a09e9ab 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -463,9 +463,7 @@ static inline void ack_APIC_irq(void)
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
 	 */
-
-	/* Docs say use 0 for future compatibility */
-	apic_write(APIC_EOI, 0);
+	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)
-- 
MST

[tip:x86/apic] x86/apic: Use symbolic APIC_EOI_ACK

[tip-bot for Michael S. Tsirkin]

Commit-ID:  4ebcc243901c48ee3baba6bdf179c7315fa8806f
Gitweb:     http://git.kernel.org/tip/4ebcc243901c48ee3baba6bdf179c7315fa8806f
Author:     Michael S. Tsirkin <mst@redhat.com>
AuthorDate: Wed, 16 May 2012 19:03:44 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 18 May 2012 09:46:08 +0200

x86/apic: Use symbolic APIC_EOI_ACK

Use the symbol instead of hard-coded numbers,
now that the reason for the value is documented
where the constant is defined we don't need to
duplicate this explanation in code.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: gleb@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/ecbe4c79d69c172378e47e5a587ff5cd10293c9f.1337184153.git.mst@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h |    4 +---
 1 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index d854101..a09e9ab 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -463,9 +463,7 @@ static inline void ack_APIC_irq(void)
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
 	 */
-
-	/* Docs say use 0 for future compatibility */
-	apic_write(APIC_EOI, 0);
+	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)

[PATCHv5 3/4] x86: add apic->eoi_write callback

[Michael S. Tsirkin]

Add eoi_write callback so that kvm can override
eoi accesses without touching the rest of the apic.
As a side-effect, this will enable a micro-optimization
for apics using msr.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/x86/include/asm/apic.h           |   15 ++++++++++++++-
 arch/x86/kernel/apic/apic_flat_64.c   |    2 ++
 arch/x86/kernel/apic/apic_noop.c      |    1 +
 arch/x86/kernel/apic/apic_numachip.c  |    1 +
 arch/x86/kernel/apic/bigsmp_32.c      |    1 +
 arch/x86/kernel/apic/es7000_32.c      |    2 ++
 arch/x86/kernel/apic/numaq_32.c       |    1 +
 arch/x86/kernel/apic/probe_32.c       |    1 +
 arch/x86/kernel/apic/summit_32.c      |    1 +
 arch/x86/kernel/apic/x2apic_cluster.c |    1 +
 arch/x86/kernel/apic/x2apic_phys.c    |    1 +
 arch/x86/kernel/apic/x2apic_uv_x.c    |    1 +
 12 files changed, 27 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a09e9ab..74efb8d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -351,6 +351,13 @@ struct apic {
 	/* apic ops */
 	u32 (*read)(u32 reg);
 	void (*write)(u32 reg, u32 v);
+        /*
+	 * eoi_write has the same signature as write.
+	 * Drivers can support both eoi_write and write by passing the same
+	 * callback value. Kernel can override eoi_write and fall back
+	 * on write for EOI.
+	 */
+	void (*eoi_write)(u32 reg, u32 v);
 	u64 (*icr_read)(void);
 	void (*icr_write)(u32 low, u32 high);
 	void (*wait_icr_idle)(void);
@@ -426,6 +433,11 @@ static inline void apic_write(u32 reg, u32 val)
 	apic->write(reg, val);
 }
 
+static inline void apic_eoi(void)
+{
+	apic->eoi_write(APIC_EOI, APIC_EOI_ACK);
+}
+
 static inline u64 apic_icr_read(void)
 {
 	return apic->icr_read();
@@ -450,6 +462,7 @@ static inline u32 safe_apic_wait_icr_idle(void)
 
 static inline u32 apic_read(u32 reg) { return 0; }
 static inline void apic_write(u32 reg, u32 val) { }
+static inline void apic_eoi(void) { }
 static inline u64 apic_icr_read(void) { return 0; }
 static inline void apic_icr_write(u32 low, u32 high) { }
 static inline void apic_wait_icr_idle(void) { }
@@ -463,7 +476,7 @@ static inline void ack_APIC_irq(void)
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
 	 */
-	apic_write(APIC_EOI, APIC_EOI_ACK);
+	apic_eoi();
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 359b689..0e881c4 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -227,6 +227,7 @@ static struct apic apic_flat =  {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
@@ -386,6 +387,7 @@ static struct apic apic_physflat =  {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 634ae6c..a6e4c6e 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -181,6 +181,7 @@ struct apic apic_noop = {
 
 	.read				= noop_apic_read,
 	.write				= noop_apic_write,
+	.eoi_write			= noop_apic_write,
 	.icr_read			= noop_apic_icr_read,
 	.icr_write			= noop_apic_icr_write,
 	.wait_icr_idle			= noop_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 23e7542..6ec6d5d 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -295,6 +295,7 @@ static struct apic apic_numachip __refconst = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 0cdec70..31fbdbf 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -248,6 +248,7 @@ static struct apic apic_bigsmp = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index e42d1d3b9..db4ab1b 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -678,6 +678,7 @@ static struct apic __refdata apic_es7000_cluster = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
@@ -742,6 +743,7 @@ static struct apic __refdata apic_es7000 = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 00d2422..f00a68c 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -530,6 +530,7 @@ static struct apic __refdata apic_numaq = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index ff2c1b9..1b291da 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -142,6 +142,7 @@ static struct apic apic_default = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index fea000b..659897c 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -546,6 +546,7 @@ static struct apic apic_summit = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 48f3103..a5baa78 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -260,6 +260,7 @@ static struct apic apic_x2apic_cluster = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 991e315..8340356 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -172,6 +172,7 @@ static struct apic apic_x2apic_phys = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 87bfa69..5b0e3d0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -404,6 +404,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
-- 
MST

[tip:x86/apic] x86/apic: Add apic->eoi_write() callback

[tip-bot for Michael S. Tsirkin]

Commit-ID:  2a43195d831997551da93e6b3c22c965e93fe9cc
Gitweb:     http://git.kernel.org/tip/2a43195d831997551da93e6b3c22c965e93fe9cc
Author:     Michael S. Tsirkin <mst@redhat.com>
AuthorDate: Wed, 16 May 2012 19:03:52 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 18 May 2012 09:46:08 +0200

x86/apic: Add apic->eoi_write() callback

Add eoi_write callback so that kvm can override
eoi accesses without touching the rest of the apic.
As a side-effect, this will enable a micro-optimization
for apics using msr.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: gleb@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/0df425d746c49ac2ecc405174df87752869629d2.1337184153.git.mst@redhat.com
[ tidied it up a bit ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h           |   16 +++++++++++++++-
 arch/x86/kernel/apic/apic_flat_64.c   |    2 ++
 arch/x86/kernel/apic/apic_noop.c      |    1 +
 arch/x86/kernel/apic/apic_numachip.c  |    1 +
 arch/x86/kernel/apic/bigsmp_32.c      |    1 +
 arch/x86/kernel/apic/es7000_32.c      |    2 ++
 arch/x86/kernel/apic/numaq_32.c       |    1 +
 arch/x86/kernel/apic/probe_32.c       |    1 +
 arch/x86/kernel/apic/summit_32.c      |    1 +
 arch/x86/kernel/apic/x2apic_cluster.c |    1 +
 arch/x86/kernel/apic/x2apic_phys.c    |    1 +
 arch/x86/kernel/apic/x2apic_uv_x.c    |    1 +
 12 files changed, 28 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a09e9ab..bf8d065 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -351,6 +351,14 @@ struct apic {
 	/* apic ops */
 	u32 (*read)(u32 reg);
 	void (*write)(u32 reg, u32 v);
+	/*
+	 * ->eoi_write() has the same signature as ->write().
+	 *
+	 * Drivers can support both ->eoi_write() and ->write() by passing the same
+	 * callback value. Kernel can override ->eoi_write() and fall back
+	 * on write for EOI.
+	 */
+	void (*eoi_write)(u32 reg, u32 v);
 	u64 (*icr_read)(void);
 	void (*icr_write)(u32 low, u32 high);
 	void (*wait_icr_idle)(void);
@@ -426,6 +434,11 @@ static inline void apic_write(u32 reg, u32 val)
 	apic->write(reg, val);
 }
 
+static inline void apic_eoi(void)
+{
+	apic->eoi_write(APIC_EOI, APIC_EOI_ACK);
+}
+
 static inline u64 apic_icr_read(void)
 {
 	return apic->icr_read();
@@ -450,6 +463,7 @@ static inline u32 safe_apic_wait_icr_idle(void)
 
 static inline u32 apic_read(u32 reg) { return 0; }
 static inline void apic_write(u32 reg, u32 val) { }
+static inline void apic_eoi(void) { }
 static inline u64 apic_icr_read(void) { return 0; }
 static inline void apic_icr_write(u32 low, u32 high) { }
 static inline void apic_wait_icr_idle(void) { }
@@ -463,7 +477,7 @@ static inline void ack_APIC_irq(void)
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
 	 */
-	apic_write(APIC_EOI, APIC_EOI_ACK);
+	apic_eoi();
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 359b689..0e881c4 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -227,6 +227,7 @@ static struct apic apic_flat =  {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
@@ -386,6 +387,7 @@ static struct apic apic_physflat =  {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 634ae6c..a6e4c6e 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -181,6 +181,7 @@ struct apic apic_noop = {
 
 	.read				= noop_apic_read,
 	.write				= noop_apic_write,
+	.eoi_write			= noop_apic_write,
 	.icr_read			= noop_apic_icr_read,
 	.icr_write			= noop_apic_icr_write,
 	.wait_icr_idle			= noop_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 23e7542..6ec6d5d 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -295,6 +295,7 @@ static struct apic apic_numachip __refconst = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 0cdec70..31fbdbf 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -248,6 +248,7 @@ static struct apic apic_bigsmp = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index e42d1d3b9..db4ab1b 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -678,6 +678,7 @@ static struct apic __refdata apic_es7000_cluster = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
@@ -742,6 +743,7 @@ static struct apic __refdata apic_es7000 = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 00d2422..f00a68c 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -530,6 +530,7 @@ static struct apic __refdata apic_numaq = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index ff2c1b9..1b291da 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -142,6 +142,7 @@ static struct apic apic_default = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index fea000b..659897c 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -546,6 +546,7 @@ static struct apic apic_summit = {
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
+	.eoi_write			= native_apic_mem_write,
 	.icr_read			= native_apic_icr_read,
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 48f3103..a5baa78 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -260,6 +260,7 @@ static struct apic apic_x2apic_cluster = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 991e315..8340356 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -172,6 +172,7 @@ static struct apic apic_x2apic_phys = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 87bfa69..5b0e3d0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -404,6 +404,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,

[PATCHv5 4/4] x86: eoi micro-optimization

[Michael S. Tsirkin]

We know both register and value for eoi beforehand,
so there's no need to check it and no need to do math
to calculate the msr. Saves instructions/branches
on each EOI when using x2apic.

I'm not sure what kind of tests should one run
to check whether this patch is good for performance.

Some data below - in case it's insufficient,
this patch can be dropped from the series for now:

I looked at the objdump output to verify that the generated code
looks right and actually is shorter.

Some benchmark results below show a tiny
but measureable improvement. The tests were run on
an AMD box with 24 cpus.

- A clean kernel build after reboot shows
a tiny but measureable improvement in system time
which means lower CPU overhead (though not measureable
in total time - that is dominated by user time and fluctuates
too much):
linux# reboot -f
...
linux# make clean
linux# time make -j 64 LOCALVERSION= 2>&1 > /dev/null

Before:

real    2m52.244s
user    35m53.833s
sys     6m7.194s

After:

real    2m52.827s
user    35m48.916s
sys     6m2.305s

- perf micro-benchmarks seem to consistently show
  a tiny improvement in total time as well but it's below
  the confidence level of 3 std deviations:

...
       0.414666797 seconds time elapsed ( +-  1.29% )

Performance counter stats for 'perf bench sched messaging' (100 runs):

       0.395370891 seconds time elapsed ( +-  1.04% )

       0.307019664 seconds time elapsed ( +-  0.10% )

       0.304738024 seconds time elapsed ( +-  0.08% )

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/x86/include/asm/apic.h           |    5 +++++
 arch/x86/kernel/apic/x2apic_cluster.c |    2 +-
 arch/x86/kernel/apic/x2apic_phys.c    |    2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c    |    2 +-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 74efb8d..5eb6d56 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -138,6 +138,11 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
 }
 
+static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
+{
+	wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+}
+
 static inline u32 native_apic_msr_read(u32 reg)
 {
 	u64 msr;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a5baa78..ff35cff 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -260,7 +260,7 @@ static struct apic apic_x2apic_cluster = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8340356..c17e982 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -172,7 +172,7 @@ static struct apic apic_x2apic_phys = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 5b0e3d0..c6d03f7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -404,7 +404,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
-- 
MST

[tip:x86/apic] x86/apic: Implement EIO micro-optimization

[tip-bot for Michael S. Tsirkin]

Commit-ID:  0ab711ae6ab0db7696b43c74f9ba9de4d7fc1deb
Gitweb:     http://git.kernel.org/tip/0ab711ae6ab0db7696b43c74f9ba9de4d7fc1deb
Author:     Michael S. Tsirkin <mst@redhat.com>
AuthorDate: Wed, 16 May 2012 19:03:58 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 18 May 2012 09:46:09 +0200

x86/apic: Implement EIO micro-optimization

We know both register and value for eoi beforehand,
so there's no need to check it and no need to do math
to calculate the msr. Saves instructions/branches
on each EOI when using x2apic.

I looked at the objdump output to verify that the
generated code looks right and actually is shorter.

The real improvemements will be on the KVM guest side
though, those come in a later patch.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: gleb@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/e019d1a125316f10d3e3a4b2f6bda41473f4fb72.1337184153.git.mst@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h           |    5 +++++
 arch/x86/kernel/apic/x2apic_cluster.c |    2 +-
 arch/x86/kernel/apic/x2apic_phys.c    |    2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c    |    2 +-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index bf8d065..eaff479 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -138,6 +138,11 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
 }
 
+static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
+{
+	wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+}
+
 static inline u32 native_apic_msr_read(u32 reg)
 {
 	u64 msr;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a5baa78..ff35cff 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -260,7 +260,7 @@ static struct apic apic_x2apic_cluster = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8340356..c17e982 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -172,7 +172,7 @@ static struct apic apic_x2apic_phys = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 5b0e3d0..c6d03f7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -404,7 +404,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,