Patchwork [v2] powerpc/4xx: work around CHIP11 errata in a more PAGE_SIZE-friendly way

login
register
mail settings
Submitter Hollis Blanchard
Date Nov. 10, 2008, 11:24 p.m.
Message ID <a861cad705fe7ebccef3.1226359474@localhost.localdomain>
Download mbox | patch
Permalink /patch/8067/
State Superseded, archived
Delegated to: Josh Boyer
Headers show

Comments

Hollis Blanchard - Nov. 10, 2008, 11:24 p.m.
The current CHIP11 errata truncates the device tree memory node, and subtracts
(hardcoded) 4096 bytes. This breaks kernels with larger PAGE_SIZE, since the
bootmem allocator assumes that total memory is a multiple of PAGE_SIZE.

Instead, use a device tree memory reservation to reserve only the 256 bytes
actually affected by the errata, leaving the total memory size unaltered.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>

---

Using large pages results in a huge performance improvement for KVM, and this
patch is required to make Ilya's large page patch work. David and/or Josh,
please apply.
Josh Boyer - Nov. 11, 2008, 12:52 p.m.
On Mon, Nov 10, 2008 at 05:24:34PM -0600, Hollis Blanchard wrote:
>The current CHIP11 errata truncates the device tree memory node, and subtracts
>(hardcoded) 4096 bytes. This breaks kernels with larger PAGE_SIZE, since the
>bootmem allocator assumes that total memory is a multiple of PAGE_SIZE.
>
>Instead, use a device tree memory reservation to reserve only the 256 bytes
>actually affected by the errata, leaving the total memory size unaltered.
>
>Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
>
>---
>
>Using large pages results in a huge performance improvement for KVM, and this
>patch is required to make Ilya's large page patch work. David and/or Josh,
>please apply.

The patch looks fine to me, and once David acks the fdt parts I'll apply
for -next.  I'll try to do some testing later today as well, since I have
one of the boards with the Errata.

josh

>
>diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
>--- a/arch/powerpc/boot/4xx.c
>+++ b/arch/powerpc/boot/4xx.c
>@@ -21,7 +21,7 @@
> #include "reg.h"
> #include "dcr.h"
> 
>-static unsigned long chip_11_errata(unsigned long memsize)
>+static void chip_11_errata(unsigned long memsize)
> {
> 	unsigned long pvr;
> 
>@@ -31,13 +31,11 @@ static unsigned long chip_11_errata(unsi
> 		case 0x40000850:
> 		case 0x400008d0:
> 		case 0x200008d0:
>-			memsize -= 4096;
>+			fdt_add_mem_rsv(fdt, memsize - 256, 256);
> 			break;
> 		default:
> 			break;
> 	}
>-
>-	return memsize;
> }
> 
> /* Read the 4xx SDRAM controller to get size of system memory. */
>@@ -53,7 +51,7 @@ void ibm4xx_sdram_fixup_memsize(void)
> 			memsize += SDRAM_CONFIG_BANK_SIZE(bank_config);
> 	}
> 
>-	memsize = chip_11_errata(memsize);
>+	chip_11_errata(memsize);
> 	dt_fixup_memory(0, memsize);
> }
> 
>@@ -219,7 +217,7 @@ void ibm4xx_denali_fixup_memsize(void)
> 		bank = 4; /* 4 banks */
> 
> 	memsize = cs * (1 << (col+row)) * bank * dpath;
>-	memsize = chip_11_errata(memsize);
>+	chip_11_errata(memsize);
> 	dt_fixup_memory(0, memsize);
> }
> 
>diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c
>--- a/arch/powerpc/boot/libfdt-wrapper.c
>+++ b/arch/powerpc/boot/libfdt-wrapper.c
>@@ -51,7 +51,7 @@
> #define devp_offset_find(devp)	(((int)(devp))-1)
> #define devp_offset(devp)	(devp ? ((int)(devp))-1 : 0)
> 
>-static void *fdt;
>+void *fdt;
> static void *buf; /* = NULL */
> 
> #define EXPAND_GRANULARITY	1024
>diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
>--- a/arch/powerpc/boot/ops.h
>+++ b/arch/powerpc/boot/ops.h
>@@ -14,6 +14,7 @@
> #include <stddef.h>
> #include "types.h"
> #include "string.h"
>+#include "libfdt_env.h"
> 
> #define	COMMAND_LINE_SIZE	512
> #define	MAX_PATH_LEN		256
>@@ -32,6 +33,9 @@ struct platform_ops {
> 	void *	(*vmlinux_alloc)(unsigned long size);
> };
> extern struct platform_ops platform_ops;
>+
>+/* The device tree itself. Should almost always be accessed via dt_ops. */
>+extern void *fdt;
> 
> /* Device Tree operations */
> struct dt_ops {
>@@ -98,6 +102,8 @@ void dt_get_reg_format(void *node, u32 *
> void dt_get_reg_format(void *node, u32 *naddr, u32 *nsize);
> int dt_get_virtual_reg(void *node, void **addr, int nres);
> 
>+int fdt_add_mem_rsv(void *fdt, uint64_t address, uint64_t size);
>+
> static inline void *finddevice(const char *name)
> {
> 	return (dt_ops.finddevice) ? dt_ops.finddevice(name) : NULL;
>_______________________________________________
>Linuxppc-dev mailing list
>Linuxppc-dev@ozlabs.org
>https://ozlabs.org/mailman/listinfo/linuxppc-dev
David Gibson - Nov. 11, 2008, 11:20 p.m.
On Tue, Nov 11, 2008 at 07:52:18AM -0500, Josh Boyer wrote:
> On Mon, Nov 10, 2008 at 05:24:34PM -0600, Hollis Blanchard wrote:
> >The current CHIP11 errata truncates the device tree memory node, and subtracts
> >(hardcoded) 4096 bytes. This breaks kernels with larger PAGE_SIZE, since the
> >bootmem allocator assumes that total memory is a multiple of PAGE_SIZE.
> >
> >Instead, use a device tree memory reservation to reserve only the 256 bytes
> >actually affected by the errata, leaving the total memory size unaltered.
> >
> >Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
> >
> >---
> >
> >Using large pages results in a huge performance improvement for KVM, and this
> >patch is required to make Ilya's large page patch work. David and/or Josh,
> >please apply.
> 
> The patch looks fine to me, and once David acks the fdt parts I'll apply
> for -next.  I'll try to do some testing later today as well, since I have
> one of the boards with the Errata.

Um.. I sent something the fdt stuff a while back, but didn't get a
response.

Patch

diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -21,7 +21,7 @@ 
 #include "reg.h"
 #include "dcr.h"
 
-static unsigned long chip_11_errata(unsigned long memsize)
+static void chip_11_errata(unsigned long memsize)
 {
 	unsigned long pvr;
 
@@ -31,13 +31,11 @@  static unsigned long chip_11_errata(unsi
 		case 0x40000850:
 		case 0x400008d0:
 		case 0x200008d0:
-			memsize -= 4096;
+			fdt_add_mem_rsv(fdt, memsize - 256, 256);
 			break;
 		default:
 			break;
 	}
-
-	return memsize;
 }
 
 /* Read the 4xx SDRAM controller to get size of system memory. */
@@ -53,7 +51,7 @@  void ibm4xx_sdram_fixup_memsize(void)
 			memsize += SDRAM_CONFIG_BANK_SIZE(bank_config);
 	}
 
-	memsize = chip_11_errata(memsize);
+	chip_11_errata(memsize);
 	dt_fixup_memory(0, memsize);
 }
 
@@ -219,7 +217,7 @@  void ibm4xx_denali_fixup_memsize(void)
 		bank = 4; /* 4 banks */
 
 	memsize = cs * (1 << (col+row)) * bank * dpath;
-	memsize = chip_11_errata(memsize);
+	chip_11_errata(memsize);
 	dt_fixup_memory(0, memsize);
 }
 
diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c
--- a/arch/powerpc/boot/libfdt-wrapper.c
+++ b/arch/powerpc/boot/libfdt-wrapper.c
@@ -51,7 +51,7 @@ 
 #define devp_offset_find(devp)	(((int)(devp))-1)
 #define devp_offset(devp)	(devp ? ((int)(devp))-1 : 0)
 
-static void *fdt;
+void *fdt;
 static void *buf; /* = NULL */
 
 #define EXPAND_GRANULARITY	1024
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -14,6 +14,7 @@ 
 #include <stddef.h>
 #include "types.h"
 #include "string.h"
+#include "libfdt_env.h"
 
 #define	COMMAND_LINE_SIZE	512
 #define	MAX_PATH_LEN		256
@@ -32,6 +33,9 @@  struct platform_ops {
 	void *	(*vmlinux_alloc)(unsigned long size);
 };
 extern struct platform_ops platform_ops;
+
+/* The device tree itself. Should almost always be accessed via dt_ops. */
+extern void *fdt;
 
 /* Device Tree operations */
 struct dt_ops {
@@ -98,6 +102,8 @@  void dt_get_reg_format(void *node, u32 *
 void dt_get_reg_format(void *node, u32 *naddr, u32 *nsize);
 int dt_get_virtual_reg(void *node, void **addr, int nres);
 
+int fdt_add_mem_rsv(void *fdt, uint64_t address, uint64_t size);
+
 static inline void *finddevice(const char *name)
 {
 	return (dt_ops.finddevice) ? dt_ops.finddevice(name) : NULL;