[RFC 16/23] ARM: LPAE: accomodate >32-bit addresses for page table base

From: Cyril Chemparathy
Date: Mon Jul 23 2012 - 21:13:38 EST

Next message: Cyril Chemparathy: "[RFC 01/23] ARM: LPAE: disable phys-to-virt patching on PAE systems"
Previous message: Cyril Chemparathy: "[RFC 12/23] ARM: mm: clean up membank size limit checks"
In reply to: Cyril Chemparathy: "[RFC 12/23] ARM: mm: clean up membank size limit checks"
Next in thread: Cyril Chemparathy: "[RFC 01/23] ARM: LPAE: disable phys-to-virt patching on PAE systems"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This patch redefines the early boot time use of the R4 register to steal a few
low order bits (ARCH_PGD_SHIFT bits), allowing for up to 38-bit physical
addresses.

This is probably not the best means to the end, and a better alternative may
be to modify the head.S register allocations to fit in full register pairs for
pgdir and swapper_pg_dir. However, squeezing out these extra registers seemed
to be a far greater pain than squeezing out a few low order bits from the page
table addresses.

Signed-off-by: Cyril Chemparathy <cyril@xxxxxx>
Signed-off-by: Vitaly Andrianov <vitalya@xxxxxx>
---
arch/arm/include/asm/cache.h | 9 +++++++++
arch/arm/kernel/head.S | 7 +++++--
arch/arm/kernel/smp.c | 11 +++++++++--
arch/arm/mm/proc-arm1026.S | 2 ++
arch/arm/mm/proc-mohawk.S | 2 ++
arch/arm/mm/proc-v6.S | 2 ++
arch/arm/mm/proc-v7-2level.S | 2 ++
arch/arm/mm/proc-v7-3level.S | 7 +++++++
arch/arm/mm/proc-v7.S | 1 +
arch/arm/mm/proc-xsc3.S | 2 ++
10 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 75fe66b..986480c 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -17,6 +17,15 @@
#define ARCH_DMA_MINALIGN L1_CACHE_BYTES

/*
+ * Minimum guaranted alignment in pgd_alloc(). The page table pointers passed
+ * around in head.S and proc-*.S are shifted by this amount, in order to
+ * leave spare high bits for systems with physical address extension. This
+ * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
+ * gives us about 38-bits or so.
+ */
+#define ARCH_PGD_SHIFT L1_CACHE_SHIFT
+
+/*
* With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
*/
#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 692e57f..6fe1c40 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -22,6 +22,7 @@
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/pgtable.h>
+#include <asm/cache.h>

#ifdef CONFIG_DEBUG_LL
#include <mach/debug-macro.S>
@@ -160,7 +161,7 @@ ENDPROC(stext)
*
* Returns:
* r0, r3, r5-r7 corrupted
- * r4 = physical page table address
+ * r4 = page table (see ARCH_PGD_SHIFT in asm/cache.h)
*/
__create_page_tables:
pgtbl r4, r8 @ page table address
@@ -320,6 +321,7 @@ __create_page_tables:
#ifdef CONFIG_ARM_LPAE
sub r4, r4, #0x1000 @ point to the PGD table
#endif
+ mov r4, r4, lsr #ARCH_PGD_SHIFT
mov pc, lr
ENDPROC(__create_page_tables)
.ltorg
@@ -392,7 +394,7 @@ __secondary_data:
* r0 = cp#15 control register
* r1 = machine ID
* r2 = atags or dtb pointer
- * r4 = page table pointer
+ * r4 = page table (see ARCH_PGD_SHIFT in asm/cache.h)
* r9 = processor ID
* r13 = *virtual* address to jump to upon completion
*/
@@ -422,6 +424,7 @@ __enable_mmu:
@ has the processor setup already programmed the page table pointer?
adds r5, r4, #1
beq __turn_mmu_on @ yes!
+ mov r4, r4, lsl #ARCH_PGD_SHIFT
mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
b __turn_mmu_on
ENDPROC(__enable_mmu)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2c7217d..e41e1be 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -42,6 +42,7 @@
#include <asm/ptrace.h>
#include <asm/localtimer.h>
#include <asm/smp_plat.h>
+#include <asm/cache.h>

/*
* as from 2.5, kernels no longer have an init_tasks structure
@@ -62,6 +63,7 @@ static DECLARE_COMPLETION(cpu_running);

int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
{
+ phys_addr_t pgdir;
int ret;

/*
@@ -69,8 +71,13 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
* its stack and the page tables.
*/
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
- secondary_data.pgdir = virt_to_phys(idmap_pgd);
- secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
+
+ pgdir = virt_to_phys(idmap_pgd);
+ secondary_data.pgdir = pgdir >> ARCH_PGD_SHIFT;
+
+ pgdir = virt_to_phys(swapper_pg_dir);
+ secondary_data.swapper_pg_dir = pgdir >> ARCH_PGD_SHIFT;
+
__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));

diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index c28070e..4556f77 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -22,6 +22,7 @@
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/ptrace.h>
+#include <asm/cache.h>

#include "proc-macros.S"

@@ -403,6 +404,7 @@ __arm1026_setup:
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer on v4
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7 @ invalidate I,D TLBs on v4
+ mov r4, r4, lsl #ARCH_PGD_SHIFT
mcr p15, 0, r4, c2, c0 @ load page table pointer
mvn r4, #0 @ do not set page table pointer
#endif
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index a26303c..13fcc67 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -28,6 +28,7 @@
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/ptrace.h>
+#include <asm/cache.h>
#include "proc-macros.S"

/*
@@ -388,6 +389,7 @@ __mohawk_setup:
mcr p15, 0, r0, c7, c7 @ invalidate I,D caches
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c8, c7 @ invalidate I,D TLBs
+ mov r4, r4, lsl #ARCH_PGD_SHIFT
orr r4, r4, #0x18 @ cache the page table in L2
mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
mvn r4, #0 @ do not set page table pointer
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 872156e..4751be7 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -17,6 +17,7 @@
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
+#include <asm/cache.h>

#include "proc-macros.S"

@@ -206,6 +207,7 @@ __v6_setup:
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs
mcr p15, 0, r0, c2, c0, 2 @ TTB control register
+ mov r4, r4, lsl #ARCH_PGD_SHIFT
ALT_SMP(orr r4, r4, #TTB_FLAGS_SMP)
ALT_UP(orr r4, r4, #TTB_FLAGS_UP)
ALT_SMP(orr r8, r8, #TTB_FLAGS_SMP)
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index cc78c0c..f4bc63b 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -143,8 +143,10 @@ ENDPROC(cpu_v7_set_pte_ext)
*/
.macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp
mcr p15, 0, \zero, c2, c0, 2 @ TTB control register
+ mov \ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT
ALT_SMP(orr \ttbr0, \ttbr0, #TTB_FLAGS_SMP)
ALT_UP(orr \ttbr0, \ttbr0, #TTB_FLAGS_UP)
+ mov \ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT
ALT_SMP(orr \ttbr1, \ttbr1, #TTB_FLAGS_SMP)
ALT_UP(orr \ttbr1, \ttbr1, #TTB_FLAGS_UP)
mcr p15, 0, \ttbr0, c2, c0, 0 @ load TTB0
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 5e3bed1..33f322a 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -103,6 +103,7 @@ ENDPROC(cpu_v7_set_pte_ext)
*/
.macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp
ldr \tmp, =swapper_pg_dir @ swapper_pg_dir virtual address
+ mov \tmp, \tmp, lsr #ARCH_PGD_SHIFT
cmp \ttbr1, \tmp @ PHYS_OFFSET > PAGE_OFFSET? (branch below)
mrc p15, 0, \tmp, c2, c0, 2 @ TTB control register
orr \tmp, \tmp, #TTB_EAE
@@ -122,8 +123,14 @@ ENDPROC(cpu_v7_set_pte_ext)
*/
orrls \tmp, \tmp, #TTBR1_SIZE @ TTBCR.T1SZ
mcr p15, 0, \tmp, c2, c0, 2 @ TTBCR
+ mov \tmp, \ttbr1, lsr #(32 - ARCH_PGD_SHIFT) @ upper bits
+ mov \ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT @ lower bits
addls \ttbr1, \ttbr1, #TTBR1_OFFSET
mcrr p15, 1, \ttbr1, \zero, c2 @ load TTBR1
+ mov \tmp, \ttbr0, lsr #(32 - ARCH_PGD_SHIFT) @ upper bits
+ mov \ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT @ lower bits
+ mcrr p15, 0, \ttbr0, \zero, c2 @ load TTBR0
+ mcrr p15, 1, \ttbr1, \zero, c2 @ load TTBR1
mcrr p15, 0, \ttbr0, \zero, c2 @ load TTBR0
.endm

diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 8850194..443f602 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -16,6 +16,7 @@
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
+#include <asm/cache.h>

#include "proc-macros.S"

diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index db3836b..a43a07d 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -32,6 +32,7 @@
#include <asm/pgtable-hwdef.h>
#include <asm/page.h>
#include <asm/ptrace.h>
+#include <asm/cache.h>
#include "proc-macros.S"

/*
@@ -453,6 +454,7 @@ __xsc3_setup:
mcr p15, 0, ip, c7, c10, 4 @ data write barrier
mcr p15, 0, ip, c7, c5, 4 @ prefetch flush
mcr p15, 0, ip, c8, c7, 0 @ invalidate I and D TLBs
+ mov r4, r4, lsl #ARCH_PGD_SHIFT
orr r4, r4, #0x18 @ cache the page table in L2
mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
mvn r4, #0 @ do not set page table pointer
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Cyril Chemparathy: "[RFC 01/23] ARM: LPAE: disable phys-to-virt patching on PAE systems"
Previous message: Cyril Chemparathy: "[RFC 12/23] ARM: mm: clean up membank size limit checks"
In reply to: Cyril Chemparathy: "[RFC 12/23] ARM: mm: clean up membank size limit checks"
Next in thread: Cyril Chemparathy: "[RFC 01/23] ARM: LPAE: disable phys-to-virt patching on PAE systems"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]