x86: pat cpu feature bit setting for known cpus

PATCH In review Yinghai Lu 7 participants 17 messages Mar 25, 2008 – Mar 30, 2008

Subsystems (2)

x86 x86 MM

lore

Share & tools

lore

Yinghai Lu

author

2008-03-25 06:22 UTC #0 lore raw

PATCH 1/1 x86: pat cpu feature bit setting for known cpus

[PATCH] x86: pat cpu feature bit setting for known cpus

Signed-off-by Yinghai Lu <[email protected]>

arch/x86/kernel/cpu/common.c +25 -0

index eb94460..b186047 100644
@@ -309,6 +309,19 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 
 	}
 
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	case X86_VENDOR_INTEL:
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	}
+
 }
 
 /*

@@ -397,6 +410,18 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 		init_scattered_cpuid_features(c);
 	}
 
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	case X86_VENDOR_INTEL:
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	}
 }
 
 static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)

arch/x86/kernel/setup_64.c +7 -0

index 3f1dc97..ddaaaaa 100644
@@ -979,12 +979,19 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
 	switch (c->x86_vendor) {
 	case X86_VENDOR_AMD:
 		early_init_amd(c);
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
 		break;
 	case X86_VENDOR_INTEL:
 		early_init_intel(c);
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
 		break;
 	}

arch/x86/mm/pat.c +2 ~~-13~~

@@ -42,19 +42,8 @@
 	if (!pat_wc_enabled)
 		return 0;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    (boot_cpu_data.x86 == 0xF ||
-	     (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model >= 15))) {
-		if (cpu_has_pat) {
-			return 1;
-		}
-	}
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
-	     boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x11) {
-		if (cpu_has_pat) {
-			return 1;
-		}
-	}
+	if (cpu_has_pat)
+		return 1;
 
 	pat_wc_enabled = 0;
 	printk(KERN_INFO "CPU and/or kernel does not support PAT.\n");

Ingo Molnar

2008-03-25 10:59 UTC #1 lore raw

Quoted 1 line · Yinghai Lu

[PATCH] x86: pat cpu feature bit setting for known cpus

thanks, applied - we need this to widen the testing scope of the PAT changes.

Ingo

H. Peter Anvin

reviewer

2008-03-25 13:39 UTC #2 lore raw

In reply to Yinghai Lu

Quoted 3 lines · Yinghai Lu

[PATCH] x86: pat cpu feature bit setting for known cpus
Signed-off-by Yinghai Lu <[email protected]>

OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?

-hpa

Yinghai Lu

2008-03-25 18:03 UTC #3 lore raw

Quoted 7 lines · H. Peter Anvin

Quoted 3 lines · Yinghai Lu
[PATCH] x86: pat cpu feature bit setting for known cpus
Signed-off-by Yinghai Lu <[email protected]>
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?

Venkatesh could tell?

Venki Pallipadi

2008-03-25 19:17 UTC #4 lore raw

Quoted 10 lines · Yinghai Lu

Quoted 7 lines · H. Peter Anvin
Quoted 3 lines · Yinghai Lu
[PATCH] x86: pat cpu feature bit setting for known cpus
Signed-off-by Yinghai Lu <[email protected]>
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?
Venkatesh could tell?

Main reason for white-list at this point is not to be side-tracked by real or potential erratas on older CPUs. Focussing on getting the support for this feature on current and future CPUs. If older CPUs have survived all these days without this feature, they should be doing OK.

Other reason being the amount of testing we get on those older systems. I mean, any regression on some specific CPU is hard to find unless it is being tested or someone audits all the errata documents to prepare the blacklist (Unless we want to have big blacklist which is just !current_whitelist). We do not have any self test that can detect and report any problematic CPUs that we can add to the blacklist.

Having said that, if there is a need for this on older CPUs, I am OK with having this as a blacklist.

Thanks,
Venki

Ingo Molnar

2008-03-25 20:08 UTC #5 lore raw

Quoted 10 lines · Venki Pallipadi

Quoted 4 lines
Quoted 2 lines
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?
Venkatesh could tell?
Main reason for white-list at this point is not to be side-tracked by real or potential erratas on older CPUs. Focussing on getting the support for this feature on current and future CPUs. If older CPUs have survived all these days without this feature, they should be doing OK.

well, the upside would be that since most testing of Linux kernels is done on _old_ hardware (people tend to risk their old hw first ;-), we'd get faster convergence of the codebase, even though we have the risk of erratas (known and unknown ones alike). Code that artificially limits its utility is almost always slow to stabilize.

Ingo

H. Peter Anvin

reviewer

2008-03-25 20:38 UTC #6 lore raw

Quoted 9 lines · Ingo Molnar

Quoted 4 lines · Venki Pallipadi
Quoted 3 lines
Quoted 2 lines
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?
Venkatesh could tell?
Main reason for white-list at this point is not to be side-tracked by real or potential erratas on older CPUs. Focussing on getting the support for this feature on current and future CPUs. If older CPUs have survived all these days without this feature, they should be doing OK.
well, the upside would be that since most testing of Linux kernels is done on _old_ hardware (people tend to risk their old hw first ;-), we'd get faster convergence of the codebase, even though we have the risk of erratas (known and unknown ones alike). Code that artificially limits its utility is almost always slow to stabilize.

Yes, using a whitelist of this type is wrong, IMO, and smells faintly of vendor-lockin.

-hpa

H. Peter Anvin

reviewer

2008-03-25 23:02 UTC #7 lore raw

Quoted 5 lines · H. Peter Anvin

Quoted 4 lines · Ingo Molnar
Quoted 2 lines · Venki Pallipadi
Quoted 2 lines
Quoted 2 lines
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?

Quoted 8 lines

Quoted 5 lines
Quoted 2 lines
Quoted 1 line
Venkatesh could tell?
Main reason for white-list at this point is not to be side-tracked by real or potential erratas on older CPUs. Focussing on getting the support for this feature on current and future CPUs. If older CPUs have survived all these days without this feature, they should be doing OK.
well, the upside would be that since most testing of Linux kernels is done on _old_ hardware (people tend to risk their old hw first ;-), we'd get faster convergence of the codebase, even though we have the risk of erratas (known and unknown ones alike). Code that artificially limits its utility is almost always slow to stabilize.
Yes, using a whitelist of this type is wrong, IMO, and smells faintly of vendor-lockin.

By the way, I want to clarify: I didn't mean it was *intended* as vendor-lockin, just that it's an undesirable effect of this.

-hpa

Yinghai Lu

2008-03-25 23:05 UTC #8 lore raw

Quoted 21 lines · H. Peter Anvin

Quoted 19 lines · H. Peter Anvin
Quoted 17 lines · Ingo Molnar
Quoted 8 lines · Venki Pallipadi
Quoted 3 lines
Quoted 2 lines
OK, note previous question: what is the motivation for having this as a whitelist (as opposed to a blacklist)?
Venkatesh could tell?
Main reason for white-list at this point is not to be side-tracked by real or potential erratas on older CPUs. Focussing on getting the support for this feature on current and future CPUs. If older CPUs have survived all these days without this feature, they should be doing OK.
well, the upside would be that since most testing of Linux kernels is done on _old_ hardware (people tend to risk their old hw first ;-), we'd get faster convergence of the codebase, even though we have the risk of erratas (known and unknown ones alike). Code that artificially limits its utility is almost always slow to stabilize.

Quoted 6 lines

Quoted 3 lines
Yes, using a whitelist of this type is wrong, IMO, and smells faintly of vendor-lockin.
By the way, I want to clarify: I didn't mean it was *intended* as vendor-lockin, just that it's an undesirable effect of this.

if the PAT works, we may need to trim the memory according to MTRR, right?

H. Peter Anvin

reviewer

2008-03-25 23:07 UTC #9 lore raw

Quoted 6 lines · Yinghai Lu

Quoted 3 lines
By the way, I want to clarify: I didn't mean it was *intended* as vendor-lockin, just that it's an undesirable effect of this.
if the PAT works, we may need to trim the memory according to MTRR, right?

That doesn't seem like it's specific to PAT?

-hpa

Yinghai Lu

2008-03-25 23:08 UTC #10 lore raw

Quoted 9 lines · H. Peter Anvin

Quoted 6 lines · Yinghai Lu
Quoted 3 lines
By the way, I want to clarify: I didn't mean it was *intended* as vendor-lockin, just that it's an undesirable effect of this.
if the PAT works, we may need to trim the memory according to MTRR, right?
That doesn't seem like it's specific to PAT?

could page table to set WRBACK the range that is not covered by MTRR in e820..

Pallipadi, Venkatesh

2008-03-25 23:39 UTC #11 lore raw

Quoted 17 lines

-----Original Message-----
From: Yinghai Lu [mailto:[email protected]]
Sent: Tuesday, March 25, 2008 4:09 PM
To: H. Peter Anvin
Cc: Ingo Molnar; Pallipadi, Venkatesh; Thomas Gleixner; Andrew Morton; kernel list; Siddha, Suresh B
Subject: Re: [PATCH] x86: pat cpu feature bit setting for known cpus
Quoted 3 lines · H. Peter Anvin
Quoted 2 lines · Yinghai Lu
Quoted 2 lines
By the way, I want to clarify: I didn't mean it was
*intended* as
Quoted 2 lines
Quoted 2 lines
Quoted 1 line
vendor-lockin, just that it's an undesirable effect of this.

Quoted 9 lines

Quoted 1 line
Quoted 1 line
if the PAT works, we may need to trim the memory
according to MTRR, right?
Quoted 3 lines
Quoted 1 line
That doesn't seem like it's specific to PAT?
could page table to set WRBACK the range that is not covered by MTRR in e820..

Trimming of e820 memory is already done by Jesse's patch here commit 99fc8d424bc5d80
Are you referring to similar thing?

Thanks,
Venki

Yinghai Lu

2008-03-26 00:01 UTC #12 lore raw

Quoted 24 lines · Venkatesh

Quoted 24 lines
-----Original Message-----
From: Yinghai Lu [mailto:[email protected]]
Sent: Tuesday, March 25, 2008 4:09 PM
To: H. Peter Anvin
Cc: Ingo Molnar; Pallipadi, Venkatesh; Thomas Gleixner; Andrew Morton; kernel list; Siddha, Suresh B
Subject: Re: [PATCH] x86: pat cpu feature bit setting for known cpus
Quoted 3 lines · H. Peter Anvin
Quoted 2 lines · Yinghai Lu
Quoted 2 lines
By the way, I want to clarify: I didn't mean it was
*intended* as
Quoted 3 lines
Quoted 3 lines
Quoted 1 line
vendor-lockin, just that it's an undesirable effect of this.
if the PAT works, we may need to trim the memory
according to MTRR, right?
Quoted 3 lines
Quoted 1 line
That doesn't seem like it's specific to PAT?

Quoted 8 lines

Quoted 3 lines
could page table to set WRBACK the range that is not covered by MTRR in e820..
Trimming of e820 memory is already done by Jesse's patch here commit 99fc8d424bc5d80
Are you referring to similar thing?

Yes.

H. Peter Anvin

reviewer

2008-03-26 00:12 UTC #13 lore raw

In reply to Yinghai Lu

Quoted 6 lines · Yinghai Lu

Quoted 5 lines · H. Peter Anvin
Quoted 4 lines · Yinghai Lu
Quoted 3 lines
By the way, I want to clarify: I didn't mean it was *intended* as vendor-lockin, just that it's an undesirable effect of this.

Quoted 7 lines

Quoted 4 lines
Quoted 2 lines
if the PAT works, we may need to trim the memory according to MTRR, right?
That doesn't seem like it's specific to PAT?
could page table to set WRBACK the range that is not covered by MTRR in e820..

We have to trim anyway... lest we end up using uncached memory and then we're in a world of hurt.

-hpa

Pavel Machek

2008-03-28 13:41 UTC #14 lore raw

In reply to Yinghai Lu

Quoted 36 lines · Yinghai Lu

[PATCH] x86: pat cpu feature bit setting for known cpus

Signed-off-by Yinghai Lu <[email protected]>

arch/x86/kernel/cpu/common.c +17 -0

index eb94460..b186047 100644
@@ -309,6 +309,19 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 
 	}
 
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	case X86_VENDOR_INTEL:
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	}
+
 }
 
 /*

@@ -397,6 +410,18 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 		init_scattered_cpuid_features(c);
 	}
 
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:

arch/x86/kernel/cpu/common.c static void __cpuinit generic_identify(struct cpuinfo_x86 *c) · line 426

Quoted 10 lines

arch/x86/kernel/cpu/common.c +8 -0

+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	case X86_VENDOR_INTEL:
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
+		break;
+	}
 }

Cut&paste programming? Can you make it a function?

Quoted 15 lines

arch/x86/kernel/setup_64.c +2 -0

index 3f1dc97..ddaaaaa 100644
@@ -979,12 +979,19 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+
+	clear_cpu_cap(c, X86_FEATURE_PAT);
 
 
 
 	switch (c->x86_vendor) {
 	case X86_VENDOR_AMD:

arch/x86/kernel/setup_64.c static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) · line 996

Quoted 10 lines

arch/x86/kernel/setup_64.c +4 -0

 		early_init_amd(c);
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);
 		break;
 	case X86_VENDOR_INTEL:
 		early_init_intel(c);
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+			set_cpu_cap(c, X86_FEATURE_PAT);
 		break;
 	}

one more copy...
Pavel

Signature · 2 lines

(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

Yinghai Lu

2008-03-28 15:01 UTC #15 lore raw

Quoted 35 lines · Pavel Machek

Quoted 32 lines · Yinghai Lu

[PATCH] x86: pat cpu feature bit setting for known cpus

Signed-off-by Yinghai Lu <[email protected]>

arch/x86/kernel/cpu/common.c +13 -0

index eb94460..b186047 100644
@@ -309,6 +309,19 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 
      }
 
+     clear_cpu_cap(c, X86_FEATURE_PAT);
+
+     switch (c->x86_vendor) {
+     case X86_VENDOR_AMD:
+             if (c->x86 >= 0xf && c->x86 <= 0x11)
+                     set_cpu_cap(c, X86_FEATURE_PAT);
+             break;
+     case X86_VENDOR_INTEL:
+             if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+                     set_cpu_cap(c, X86_FEATURE_PAT);
+             break;
+     }
+
 }
 
 /*

@@ -397,6 +410,18 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
              init_scattered_cpuid_features(c);
      }

Quoted 16 lines

Quoted 4 lines

arch/x86/kernel/cpu/common.c +4 -0

+     clear_cpu_cap(c, X86_FEATURE_PAT);
+
+     switch (c->x86_vendor) {
+     case X86_VENDOR_AMD:

arch/x86/kernel/cpu/common.c static void __cpuinit early_get_cap(struct cpuinfo_x86 *c) · line 326

Quoted 10 lines

arch/x86/kernel/cpu/common.c +8 -0

+             if (c->x86 >= 0xf && c->x86 <= 0x11)
+                     set_cpu_cap(c, X86_FEATURE_PAT);
+             break;
+     case X86_VENDOR_INTEL:
+             if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+                     set_cpu_cap(c, X86_FEATURE_PAT);
+             break;
+     }
 }

Cut&paste programming? Can you make it a function?

yes. just want to leave one stub, so could add other cap setting if needed later in early or late identify_cpu.

Quoted 28 lines

Quoted 17 lines

arch/x86/kernel/setup_64.c +2 -0

index 3f1dc97..ddaaaaa 100644
@@ -979,12 +979,19 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
      if (c->extended_cpuid_level >= 0x80000007)
              c->x86_power = cpuid_edx(0x80000007);
 
+
+     clear_cpu_cap(c, X86_FEATURE_PAT);
 
 
 
      switch (c->x86_vendor) {
      case X86_VENDOR_AMD:

arch/x86/kernel/setup_64.c static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) · line 996

Quoted 10 lines

arch/x86/kernel/setup_64.c +4 -0

              early_init_amd(c);
+             if (c->x86 >= 0xf && c->x86 <= 0x11)
+                     set_cpu_cap(c, X86_FEATURE_PAT);
              break;
      case X86_VENDOR_INTEL:
              early_init_intel(c);
+             if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
+                     set_cpu_cap(c, X86_FEATURE_PAT);
              break;
      }

Quoted 1 line

one more copy...

for 64 bit.

dean gaudet

2008-03-30 11:43 UTC #16 lore raw

In reply to Yinghai Lu

Quoted 9 lines · Yinghai Lu

[PATCH] x86: pat cpu feature bit setting for known cpus
Signed-off-by Yinghai Lu <[email protected]>
arch/x86/kernel/cpu/common.c +0 -0
index eb94460..b186047 100644

arch/x86/kernel/cpu/common.c static void __cpuinit early_get_cap(struct cpuinfo_x86 *c) · line 317

Quoted 9 lines

arch/x86/kernel/cpu/common.c +6 -0

@@ -309,6 +309,19 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 
 	}
 
+	clear_cpu_cap(c, X86_FEATURE_PAT);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (c->x86 >= 0xf && c->x86 <= 0x11)
+			set_cpu_cap(c, X86_FEATURE_PAT);

just a general comment on things like this... "x->x86 <= 0x11" ensures this file will have to be updated every time a new AMD CPU is released.

arch/x86/kernel/cpu/common.c static void __cpuinit early_get_cap(struct cpuinfo_x86 *c) · line 320

Quoted 3 lines

arch/x86/kernel/cpu/common.c +3 -0

+		break;
+	case X86_VENDOR_INTEL:
+		if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))

note that you didn't limit intel the same way... at least for the numerous core2 processor models.

-dean