summaryrefslogtreecommitdiffstats
path: root/arch/arm/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/mm')
-rw-r--r--arch/arm/mm/Kconfig24
-rw-r--r--arch/arm/mm/Makefile3
-rw-r--r--arch/arm/mm/cache-l2x0.c158
-rw-r--r--arch/arm/mm/cache-nop.S50
-rw-r--r--arch/arm/mm/cache-v7.S8
-rw-r--r--arch/arm/mm/context.c64
-rw-r--r--arch/arm/mm/dma-mapping.c22
-rw-r--r--arch/arm/mm/fault.c2
-rw-r--r--arch/arm/mm/flush.c60
-rw-r--r--arch/arm/mm/fsr-3level.c4
-rw-r--r--arch/arm/mm/hugetlbpage.c101
-rw-r--r--arch/arm/mm/init.c19
-rw-r--r--arch/arm/mm/ioremap.c10
-rw-r--r--arch/arm/mm/mmu.c59
-rw-r--r--arch/arm/mm/nommu.c276
-rw-r--r--arch/arm/mm/proc-fa526.S1
-rw-r--r--arch/arm/mm/proc-macros.S5
-rw-r--r--arch/arm/mm/proc-v6.S6
-rw-r--r--arch/arm/mm/proc-v7-3level.S53
-rw-r--r--arch/arm/mm/proc-v7.S65
-rw-r--r--arch/arm/mm/proc-v7m.S157
21 files changed, 1020 insertions, 127 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 35955b54944..6cacdc8dd65 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -392,11 +392,21 @@ config CPU_V7
select CPU_CACHE_V7
select CPU_CACHE_VIPT
select CPU_COPY_V6 if MMU
- select CPU_CP15_MMU
+ select CPU_CP15_MMU if MMU
+ select CPU_CP15_MPU if !MMU
select CPU_HAS_ASID if MMU
select CPU_PABRT_V7
select CPU_TLB_V7 if MMU
+# ARMv7M
+config CPU_V7M
+ bool
+ select CPU_32v7M
+ select CPU_ABRT_NOMMU
+ select CPU_CACHE_NOP
+ select CPU_PABRT_LEGACY
+ select CPU_THUMBONLY
+
config CPU_THUMBONLY
bool
# There are no CPUs available with MMU that don't implement an ARM ISA:
@@ -441,6 +451,9 @@ config CPU_32v6K
config CPU_32v7
bool
+config CPU_32v7M
+ bool
+
# The abort model
config CPU_ABRT_NOMMU
bool
@@ -491,6 +504,9 @@ config CPU_CACHE_V6
config CPU_CACHE_V7
bool
+config CPU_CACHE_NOP
+ bool
+
config CPU_CACHE_VIVT
bool
@@ -613,7 +629,11 @@ config ARCH_DMA_ADDR_T_64BIT
config ARM_THUMB
bool "Support Thumb user binaries" if !CPU_THUMBONLY
- depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
+ depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || \
+ CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || \
+ CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
+ CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || \
+ CPU_V7 || CPU_FEROCEON || CPU_V7M
default y
help
Say Y if you want to include kernel support for running user space
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 9e51be96f63..ecfe6e53f6e 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_MODULES) += proc-syms.o
obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o
obj-$(CONFIG_HIGHMEM) += highmem.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_CPU_ABRT_NOMMU) += abort-nommu.o
obj-$(CONFIG_CPU_ABRT_EV4) += abort-ev4.o
@@ -39,6 +40,7 @@ obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o
obj-$(CONFIG_CPU_CACHE_V6) += cache-v6.o
obj-$(CONFIG_CPU_CACHE_V7) += cache-v7.o
obj-$(CONFIG_CPU_CACHE_FA) += cache-fa.o
+obj-$(CONFIG_CPU_CACHE_NOP) += cache-nop.o
AFLAGS_cache-v6.o :=-Wa,-march=armv6
AFLAGS_cache-v7.o :=-Wa,-march=armv7-a
@@ -87,6 +89,7 @@ obj-$(CONFIG_CPU_FEROCEON) += proc-feroceon.o
obj-$(CONFIG_CPU_V6) += proc-v6.o
obj-$(CONFIG_CPU_V6K) += proc-v6.o
obj-$(CONFIG_CPU_V7) += proc-v7.o
+obj-$(CONFIG_CPU_V7M) += proc-v7m.o
AFLAGS_proc-v6.o :=-Wa,-march=armv6
AFLAGS_proc-v7.o :=-Wa,-march=armv7-a
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c465faca51b..d70e0aba0c9 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -523,6 +523,147 @@ static void aurora_flush_range(unsigned long start, unsigned long end)
}
}
+/*
+ * For certain Broadcom SoCs, depending on the address range, different offsets
+ * need to be added to the address before passing it to L2 for
+ * invalidation/clean/flush
+ *
+ * Section Address Range Offset EMI
+ * 1 0x00000000 - 0x3FFFFFFF 0x80000000 VC
+ * 2 0x40000000 - 0xBFFFFFFF 0x40000000 SYS
+ * 3 0xC0000000 - 0xFFFFFFFF 0x80000000 VC
+ *
+ * When the start and end addresses have crossed two different sections, we
+ * need to break the L2 operation into two, each within its own section.
+ * For example, if we need to invalidate addresses starts at 0xBFFF0000 and
+ * ends at 0xC0001000, we need do invalidate 1) 0xBFFF0000 - 0xBFFFFFFF and 2)
+ * 0xC0000000 - 0xC0001000
+ *
+ * Note 1:
+ * By breaking a single L2 operation into two, we may potentially suffer some
+ * performance hit, but keep in mind the cross section case is very rare
+ *
+ * Note 2:
+ * We do not need to handle the case when the start address is in
+ * Section 1 and the end address is in Section 3, since it is not a valid use
+ * case
+ *
+ * Note 3:
+ * Section 1 in practical terms can no longer be used on rev A2. Because of
+ * that the code does not need to handle section 1 at all.
+ *
+ */
+#define BCM_SYS_EMI_START_ADDR 0x40000000UL
+#define BCM_VC_EMI_SEC3_START_ADDR 0xC0000000UL
+
+#define BCM_SYS_EMI_OFFSET 0x40000000UL
+#define BCM_VC_EMI_OFFSET 0x80000000UL
+
+static inline int bcm_addr_is_sys_emi(unsigned long addr)
+{
+ return (addr >= BCM_SYS_EMI_START_ADDR) &&
+ (addr < BCM_VC_EMI_SEC3_START_ADDR);
+}
+
+static inline unsigned long bcm_l2_phys_addr(unsigned long addr)
+{
+ if (bcm_addr_is_sys_emi(addr))
+ return addr + BCM_SYS_EMI_OFFSET;
+ else
+ return addr + BCM_VC_EMI_OFFSET;
+}
+
+static void bcm_inv_range(unsigned long start, unsigned long end)
+{
+ unsigned long new_start, new_end;
+
+ BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+ if (unlikely(end <= start))
+ return;
+
+ new_start = bcm_l2_phys_addr(start);
+ new_end = bcm_l2_phys_addr(end);
+
+ /* normal case, no cross section between start and end */
+ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+ l2x0_inv_range(new_start, new_end);
+ return;
+ }
+
+ /* They cross sections, so it can only be a cross from section
+ * 2 to section 3
+ */
+ l2x0_inv_range(new_start,
+ bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+ l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+ new_end);
+}
+
+static void bcm_clean_range(unsigned long start, unsigned long end)
+{
+ unsigned long new_start, new_end;
+
+ BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+ if (unlikely(end <= start))
+ return;
+
+ if ((end - start) >= l2x0_size) {
+ l2x0_clean_all();
+ return;
+ }
+
+ new_start = bcm_l2_phys_addr(start);
+ new_end = bcm_l2_phys_addr(end);
+
+ /* normal case, no cross section between start and end */
+ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+ l2x0_clean_range(new_start, new_end);
+ return;
+ }
+
+ /* They cross sections, so it can only be a cross from section
+ * 2 to section 3
+ */
+ l2x0_clean_range(new_start,
+ bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+ l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+ new_end);
+}
+
+static void bcm_flush_range(unsigned long start, unsigned long end)
+{
+ unsigned long new_start, new_end;
+
+ BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+ if (unlikely(end <= start))
+ return;
+
+ if ((end - start) >= l2x0_size) {
+ l2x0_flush_all();
+ return;
+ }
+
+ new_start = bcm_l2_phys_addr(start);
+ new_end = bcm_l2_phys_addr(end);
+
+ /* normal case, no cross section between start and end */
+ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+ l2x0_flush_range(new_start, new_end);
+ return;
+ }
+
+ /* They cross sections, so it can only be a cross from section
+ * 2 to section 3
+ */
+ l2x0_flush_range(new_start,
+ bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+ l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+ new_end);
+}
+
static void __init l2x0_of_setup(const struct device_node *np,
u32 *aux_val, u32 *aux_mask)
{
@@ -765,6 +906,21 @@ static const struct l2x0_of_data aurora_no_outer_data = {
},
};
+static const struct l2x0_of_data bcm_l2x0_data = {
+ .setup = pl310_of_setup,
+ .save = pl310_save,
+ .outer_cache = {
+ .resume = pl310_resume,
+ .inv_range = bcm_inv_range,
+ .clean_range = bcm_clean_range,
+ .flush_range = bcm_flush_range,
+ .sync = l2x0_cache_sync,
+ .flush_all = l2x0_flush_all,
+ .inv_all = l2x0_inv_all,
+ .disable = l2x0_disable,
+ },
+};
+
static const struct of_device_id l2x0_ids[] __initconst = {
{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
@@ -773,6 +929,8 @@ static const struct of_device_id l2x0_ids[] __initconst = {
.data = (void *)&aurora_no_outer_data},
{ .compatible = "marvell,aurora-outer-cache",
.data = (void *)&aurora_with_outer_data},
+ { .compatible = "bcm,bcm11351-a2-pl310-cache",
+ .data = (void *)&bcm_l2x0_data},
{}
};
diff --git a/arch/arm/mm/cache-nop.S b/arch/arm/mm/cache-nop.S
new file mode 100644
index 00000000000..8e12ddca003
--- /dev/null
+++ b/arch/arm/mm/cache-nop.S
@@ -0,0 +1,50 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+#include "proc-macros.S"
+
+ENTRY(nop_flush_icache_all)
+ mov pc, lr
+ENDPROC(nop_flush_icache_all)
+
+ .globl nop_flush_kern_cache_all
+ .equ nop_flush_kern_cache_all, nop_flush_icache_all
+
+ .globl nop_flush_kern_cache_louis
+ .equ nop_flush_kern_cache_louis, nop_flush_icache_all
+
+ .globl nop_flush_user_cache_all
+ .equ nop_flush_user_cache_all, nop_flush_icache_all
+
+ .globl nop_flush_user_cache_range
+ .equ nop_flush_user_cache_range, nop_flush_icache_all
+
+ .globl nop_coherent_kern_range
+ .equ nop_coherent_kern_range, nop_flush_icache_all
+
+ENTRY(nop_coherent_user_range)
+ mov r0, 0
+ mov pc, lr
+ENDPROC(nop_coherent_user_range)
+
+ .globl nop_flush_kern_dcache_area
+ .equ nop_flush_kern_dcache_area, nop_flush_icache_all
+
+ .globl nop_dma_flush_range
+ .equ nop_dma_flush_range, nop_flush_icache_all
+
+ .globl nop_dma_map_area
+ .equ nop_dma_map_area, nop_flush_icache_all
+
+ .globl nop_dma_unmap_area
+ .equ nop_dma_unmap_area, nop_flush_icache_all
+
+ __INITDATA
+
+ @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
+ define_cache_functions nop
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 15451ee4acc..515b00064da 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -92,6 +92,14 @@ ENTRY(v7_flush_dcache_louis)
mrc p15, 1, r0, c0, c0, 1 @ read clidr, r0 = clidr
ALT_SMP(ands r3, r0, #(7 << 21)) @ extract LoUIS from clidr
ALT_UP(ands r3, r0, #(7 << 27)) @ extract LoUU from clidr
+#ifdef CONFIG_ARM_ERRATA_643719
+ ALT_SMP(mrceq p15, 0, r2, c0, c0, 0) @ read main ID register
+ ALT_UP(moveq pc, lr) @ LoUU is zero, so nothing to do
+ ldreq r1, =0x410fc090 @ ID of ARM Cortex A9 r0p?
+ biceq r2, r2, #0x0000000f @ clear minor revision number
+ teqeq r2, r1 @ test for errata affected core and if so...
+ orreqs r3, #(1 << 21) @ fix LoUIS value (and set flags state to 'ne')
+#endif
ALT_SMP(mov r3, r3, lsr #20) @ r3 = LoUIS * 2
ALT_UP(mov r3, r3, lsr #26) @ r3 = LoUU * 2
moveq pc, lr @ return if level == 0
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 2ac37372ef5..b55b1015724 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -20,6 +20,7 @@
#include <asm/smp_plat.h>
#include <asm/thread_notify.h>
#include <asm/tlbflush.h>
+#include <asm/proc-fns.h>
/*
* On ARMv6, we have the following structure in the Context ID:
@@ -39,33 +40,51 @@
* non 64-bit operations.
*/
#define ASID_FIRST_VERSION (1ULL << ASID_BITS)
-#define NUM_USER_ASIDS (ASID_FIRST_VERSION - 1)
-
-#define ASID_TO_IDX(asid) ((asid & ~ASID_MASK) - 1)
-#define IDX_TO_ASID(idx) ((idx + 1) & ~ASID_MASK)
+#define NUM_USER_ASIDS ASID_FIRST_VERSION
static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
static DEFINE_PER_CPU(u64, reserved_asids);
static cpumask_t tlb_flush_pending;
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+ cpumask_t *mask)
+{
+ int cpu;
+ unsigned long flags;
+ u64 context_id, asid;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+ context_id = mm->context.id.counter;
+ for_each_online_cpu(cpu) {
+ if (cpu == this_cpu)
+ continue;
+ /*
+ * We only need to send an IPI if the other CPUs are
+ * running the same ASID as the one being invalidated.
+ */
+ asid = per_cpu(active_asids, cpu).counter;
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, cpu);
+ if (context_id == asid)
+ cpumask_set_cpu(cpu, mask);
+ }
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
#ifdef CONFIG_ARM_LPAE
static void cpu_set_reserved_ttbr0(void)
{
- unsigned long ttbl = __pa(swapper_pg_dir);
- unsigned long ttbh = 0;
-
/*
* Set TTBR0 to swapper_pg_dir which contains only global entries. The
* ASID is set to 0.
*/
- asm volatile(
- " mcrr p15, 0, %0, %1, c2 @ set TTBR0\n"
- :
- : "r" (ttbl), "r" (ttbh));
+ cpu_set_ttbr(0, __pa(swapper_pg_dir));
isb();
}
#else
@@ -128,7 +147,16 @@ static void flush_context(unsigned int cpu)
asid = 0;
} else {
asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
- __set_bit(ASID_TO_IDX(asid), asid_map);
+ /*
+ * If this CPU has already been through a
+ * rollover, but hasn't run another task in
+ * the meantime, we must preserve its reserved
+ * ASID, as this is the only trace we have of
+ * the process it is still running.
+ */
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, i);
+ __set_bit(asid & ~ASID_MASK, asid_map);
}
per_cpu(reserved_asids, i) = asid;
}
@@ -167,17 +195,19 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
/*
* Allocate a free ASID. If we can't find one, take a
* note of the currently active ASIDs and mark the TLBs
- * as requiring flushes.
+ * as requiring flushes. We always count from ASID #1,
+ * as we reserve ASID #0 to switch via TTBR0 and indicate
+ * rollover events.
*/
- asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
if (asid == NUM_USER_ASIDS) {
generation = atomic64_add_return(ASID_FIRST_VERSION,
&asid_generation);
flush_context(cpu);
- asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
}
__set_bit(asid, asid_map);
- asid = generation | IDX_TO_ASID(asid);
+ asid |= generation;
cpumask_clear(mm_cpumask(mm));
}
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3aac9..7ec02961dfa 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -250,7 +250,7 @@ static void __dma_free_buffer(struct page *page, size_t size)
#ifdef CONFIG_MMU
#ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
#endif
static void *__alloc_from_contiguous(struct device *dev, size_t size,
@@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
/*
- * Mark the D-cache clean for this page to avoid extra flushing.
+ * Mark the D-cache clean for these pages to avoid extra flushing.
*/
- if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
- set_bit(PG_dcache_clean, &page->flags);
+ if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+ unsigned long pfn;
+ size_t left = size;
+
+ pfn = page_to_pfn(page) + off / PAGE_SIZE;
+ off %= PAGE_SIZE;
+ if (off) {
+ pfn++;
+ left -= PAGE_SIZE - off;
+ }
+ while (left >= PAGE_SIZE) {
+ page = pfn_to_page(pfn++);
+ set_bit(PG_dcache_clean, &page->flags);
+ left -= PAGE_SIZE;
+ }
+ }
}
/**
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5dbf13f954f..c97f7940cb9 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -491,12 +491,14 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
* Some section permission faults need to be handled gracefully.
* They can happen due to a __{get,put}_user during an oops.
*/
+#ifndef CONFIG_ARM_LPAE
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
do_bad_area(addr, fsr, regs);
return 0;
}
+#endif /* CONFIG_ARM_LPAE */
/*
* This abort handler always returns "fault".
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0d473cce501..6d5ba9afb16 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
#include <asm/highmem.h>
#include <asm/smp_plat.h>
#include <asm/tlbflush.h>
+#include <linux/hugetlb.h>
#include "mm.h"
@@ -168,19 +169,23 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
* coherent with the kernels mapping.
*/
if (!PageHighMem(page)) {
- __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+ size_t page_size = PAGE_SIZE << compound_order(page);
+ __cpuc_flush_dcache_area(page_address(page), page_size);
} else {
- void *addr;
-
+ unsigned long i;
if (cache_is_vipt_nonaliasing()) {
- addr = kmap_atomic(page);
- __cpuc_flush_dcache_area(addr, PAGE_SIZE);
- kunmap_atomic(addr);
- } else {
- addr = kmap_high_get(page);
- if (addr) {
+ for (i = 0; i < (1 << compound_order(page)); i++) {
+ void *addr = kmap_atomic(page);
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
- kunmap_high(page);
+ kunmap_atomic(addr);
+ }
+ } else {
+ for (i = 0; i < (1 << compound_order(page)); i++) {
+ void *addr = kmap_high_get(page);
+ if (addr) {
+ __cpuc_flush_dcache_area(addr, PAGE_SIZE);
+ kunmap_high(page);
+ }
}
}
}
@@ -287,7 +292,7 @@ void flush_dcache_page(struct page *page)
mapping = page_mapping(page);
if (!cache_ops_need_broadcast() &&
- mapping && !mapping_mapped(mapping))
+ mapping && !page_mapped(page))
clear_bit(PG_dcache_clean, &page->flags);
else {
__flush_dcache_page(mapping, page);
@@ -301,6 +306,39 @@ void flush_dcache_page(struct page *page)
EXPORT_SYMBOL(flush_dcache_page);
/*
+ * Ensure cache coherency for the kernel mapping of this page. We can
+ * assume that the page is pinned via kmap.
+ *
+ * If the page only exists in the page cache and there are no user
+ * space mappings, this is a no-op since the page was already marked
+ * dirty at creation. Otherwise, we need to flush the dirty kernel
+ * cache lines directly.
+ */
+void flush_kernel_dcache_page(struct page *page)
+{
+ if (cache_is_vivt() || cache_is_vipt_aliasing()) {
+ struct address_space *mapping;
+
+ mapping = page_mapping(page);
+
+ if (!mapping || mapping_mapped(mapping)) {
+ void *addr;
+
+ addr = page_address(page);
+ /*
+ * kmap_atomic() doesn't set the page virtual
+ * address for highmem pages, and
+ * kunmap_atomic() takes care of cache
+ * flushing already.
+ */
+ if (!IS_ENABLED(CONFIG_HIGHMEM) || addr)
+ __cpuc_flush_dcache_area(addr, PAGE_SIZE);
+ }
+ }
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+/*
* Flush an anonymous page so that users of get_user_pages()
* can safely access the data. The expected sequence is:
*
diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c
index 05a4e943183..ab4409a2307 100644
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@@ -9,11 +9,11 @@ static struct fsr_info fsr_info[] = {
{ do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "reserved access flag fault" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
{ do_bad, SIGBUS, 0, "reserved permission fault" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
- { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
{ do_bad, SIGBUS, 0, "synchronous external abort" },
{ do_bad, SIGBUS, 0, "asynchronous external abort" },
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
new file mode 100644
index 00000000000..3d1e4a205b0
--- /dev/null
+++ b/arch/arm/mm/hugetlbpage.c
@@ -0,0 +1,101 @@
+/*
+ * arch/arm/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+/*
+ * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot
+ * of type casting from pmd_t * to pte_t *.
+ */
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_present(*pgd)) {
+ pud = pud_offset(pgd, addr);
+ if (pud_present(*pud))
+ pmd = pmd_offset(pud, addr);
+ }
+
+ return (pte_t *)pmd;
+}
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+ int write)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+int pud_huge(pud_t pud)
+{
+ return 0;
+}
+
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+ return 0;
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pte_t *pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ pud = pud_alloc(mm, pgd, addr);
+ if (pud)
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
+ return pte;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+ pmd_t *pmd, int write)
+{
+ struct page *page;
+
+ page = pte_page(*(pte_t *)pmd);
+ if (page)
+ page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+ return page;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+ return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9a5cdc01fcd..2ffee02d1d5 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -36,12 +36,13 @@
#include "mm.h"
-static unsigned long phys_initrd_start __initdata = 0;
+static phys_addr_t phys_initrd_start __initdata = 0;
static unsigned long phys_initrd_size __initdata = 0;
static int __init early_initrd(char *p)
{
- unsigned long start, size;
+ phys_addr_t start;
+ unsigned long size;
char *endp;
start = memparse(p, &endp);
@@ -350,14 +351,14 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
#ifdef CONFIG_BLK_DEV_INITRD
if (phys_initrd_size &&
!memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
- pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n",
- phys_initrd_start, phys_initrd_size);
+ pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
+ (u64)phys_initrd_start, phys_initrd_size);
phys_initrd_start = phys_initrd_size = 0;
}
if (phys_initrd_size &&
memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
- pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
- phys_initrd_start, phys_initrd_size);
+ pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+ (u64)phys_initrd_start, phys_initrd_size);
phys_initrd_start = phys_initrd_size = 0;
}
if (phys_initrd_size) {
@@ -442,7 +443,7 @@ static inline void
free_memmap(unsigned long start_pfn, unsigned long end_pfn)
{
struct page *start_pg, *end_pg;
- unsigned long pg, pgend;
+ phys_addr_t pg, pgend;
/*
* Convert start_pfn/end_pfn to a struct page pointer.
@@ -454,8 +455,8 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
* Convert to physical addresses, and
* round start upwards and end downwards.
*/
- pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
- pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
+ pg = PAGE_ALIGN(__pa(start_pg));
+ pgend = __pa(end_pg) & PAGE_MASK;
/*
* If there are free pages between these,
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 04d9006eab1..f123d6eb074 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -331,10 +331,10 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
return (void __iomem *) (offset + addr);
}
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
- unsigned long last_addr;
+ phys_addr_t last_addr;
unsigned long offset = phys_addr & ~PAGE_MASK;
unsigned long pfn = __phys_to_pfn(phys_addr);
@@ -367,12 +367,12 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
}
EXPORT_SYMBOL(__arm_ioremap_pfn);
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
unsigned int, void *) =
__arm_ioremap_caller;
void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
{
return arch_ioremap_caller(phys_addr, size, mtype,
__builtin_return_address(0));
@@ -387,7 +387,7 @@ EXPORT_SYMBOL(__arm_ioremap);
* CONFIG_GENERIC_ALLOCATOR for allocating external memory.
*/
void __iomem *
-__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
{
unsigned int mtype;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e0d8565671a..d7229d28c7f 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -616,10 +616,12 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
} while (pte++, addr += PAGE_SIZE, addr != end);
}
-static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
unsigned long end, phys_addr_t phys,
const struct mem_type *type)
{
+ pmd_t *p = pmd;
+
#ifndef CONFIG_ARM_LPAE
/*
* In classic MMU format, puds and pmds are folded in to
@@ -638,7 +640,7 @@ static void __init map_init_section(pmd_t *pmd, unsigned long addr,
phys += SECTION_SIZE;
} while (pmd++, addr += SECTION_SIZE, addr != end);
- flush_pmd_entry(pmd);
+ flush_pmd_entry(p);
}
static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
@@ -661,7 +663,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
*/
if (type->prot_sect &&
((addr | next | phys) & ~SECTION_MASK) == 0) {
- map_init_section(pmd, addr, next, phys, type);
+ __map_init_section(pmd, addr, next, phys, type);
} else {
alloc_init_pte(pmd, addr, next,
__phys_to_pfn(phys), type);
@@ -673,7 +675,8 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
}
static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
- unsigned long end, unsigned long phys, const struct mem_type *type)
+ unsigned long end, phys_addr_t phys,
+ const struct mem_type *type)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
@@ -987,27 +990,28 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
void __init sanity_check_meminfo(void)
{
int i, j, highmem = 0;
+ phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
struct membank *bank = &meminfo.bank[j];
+ phys_addr_t size_limit;
+
*bank = meminfo.bank[i];
+ size_limit = bank->size;
- if (bank->start > ULONG_MAX)
- highmem = 1;
-
-#ifdef CONFIG_HIGHMEM
- if (__va(bank->start) >= vmalloc_min ||
- __va(bank->start) < (void *)PAGE_OFFSET)
+ if (bank->start >= vmalloc_limit)
highmem = 1;
+ else
+ size_limit = vmalloc_limit - bank->start;
bank->highmem = highmem;
+#ifdef CONFIG_HIGHMEM
/*
* Split those memory banks which are partially overlapping
* the vmalloc area greatly simplifying things later.
*/
- if (!highmem && __va(bank->start) < vmalloc_min &&
- bank->size > vmalloc_min - __va(bank->start)) {
+ if (!highmem && bank->size > size_limit) {
if (meminfo.nr_banks >= NR_BANKS) {
printk(KERN_CRIT "NR_BANKS too low, "
"ignoring high memory\n");
@@ -1016,16 +1020,14 @@ void __init sanity_check_meminfo(void)
(meminfo.nr_banks - i) * sizeof(*bank));
meminfo.nr_banks++;
i++;
- bank[1].size -= vmalloc_min - __va(bank->start);
- bank[1].start = __pa(vmalloc_min - 1) + 1;
+ bank[1].size -= size_limit;
+ bank[1].start = vmalloc_limit;
bank[1].highmem = highmem = 1;
j++;
}
- bank->size = vmalloc_min - __va(bank->start);
+ bank->size = size_limit;
}
#else
- bank->highmem = highmem;
-
/*
* Highmem banks not allowed with !CONFIG_HIGHMEM.
*/
@@ -1038,31 +1040,16 @@ void __init sanity_check_meminfo(void)
}
/*
- * Check whether this memory bank would entirely overlap
- * the vmalloc area.
- */
- if (__va(bank->start) >= vmalloc_min ||
- __va(bank->start) < (void *)PAGE_OFFSET) {
- printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
- "(vmalloc region overlap).\n",
- (unsigned long long)bank->start,
- (unsigned long long)bank->start + bank->size - 1);
- continue;
- }
-
- /*
* Check whether this memory bank would partially overlap
* the vmalloc area.
*/
- if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
- __va(bank->start + bank->size - 1) <= __va(bank->start)) {
- unsigned long newsize = vmalloc_min - __va(bank->start);
+ if (bank->size > size_limit) {
printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
"to -%.8llx (vmalloc region overlap).\n",
(unsigned long long)bank->start,
(unsigned long long)bank->start + bank->size - 1,
- (unsigned long long)bank->start + newsize - 1);
- bank->size = newsize;
+ (unsigned long long)bank->start + size_limit - 1);
+ bank->size = size_limit;
}
#endif
if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
@@ -1232,6 +1219,8 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
*/
if (mdesc->map_io)
mdesc->map_io();
+ else
+ debug_ll_io_init();
fill_pmd_gaps();
/* Reserve fixed i/o space in VMALLOC region */
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index d51225f90ae..1fa50100ab6 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -8,6 +8,7 @@
#include <linux/pagemap.h>
#include <linux/io.h>
#include <linux/memblock.h>
+#include <linux/kernel.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
@@ -15,22 +16,282 @@
#include <asm/setup.h>
#include <asm/traps.h>
#include <asm/mach/arch.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>
#include "mm.h"
+#ifdef CONFIG_ARM_MPU
+struct mpu_rgn_info mpu_rgn_info;
+
+/* Region number */
+static void rgnr_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c2, 0" : : "r" (v));
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static void dracr_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 4" : : "r" (v));
+}
+
+/* Region size register */
+static void drsr_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 2" : : "r" (v));
+}
+
+/* Region base address register */
+static void drbar_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 0" : : "r" (v));
+}
+
+static u32 drbar_read(void)
+{
+ u32 v;
+ asm("mrc p15, 0, %0, c6, c1, 0" : "=r" (v));
+ return v;
+}
+/* Optional instruction-side region attributes */
+
+/* I-side Region access control register */
+static void iracr_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 5" : : "r" (v));
+}
+
+/* I-side Region size register */
+static void irsr_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 3" : : "r" (v));
+}
+
+/* I-side Region base address register */
+static void irbar_write(u32 v)
+{
+ asm("mcr p15, 0, %0, c6, c1, 1" : : "r" (v));
+}
+
+static unsigned long irbar_read(void)
+{
+ unsigned long v;
+ asm("mrc p15, 0, %0, c6, c1, 1" : "=r" (v));
+ return v;
+}
+
+/* MPU initialisation functions */
+void __init sanity_check_meminfo_mpu(void)
+{
+ int i;
+ struct membank *bank = meminfo.bank;
+ phys_addr_t phys_offset = PHYS_OFFSET;
+ phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
+
+ /* Initially only use memory continuous from PHYS_OFFSET */
+ if (bank_phys_start(&bank[0]) != phys_offset)
+ panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+ /* Banks have already been sorted by start address */
+ for (i = 1; i < meminfo.nr_banks; i++) {
+ if (bank[i].start <= bank_phys_end(&bank[0]) &&
+ bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) {
+ bank[0].size = bank_phys_end(&bank[i]) - bank[0].start;
+ } else {
+ pr_notice("Ignoring RAM after 0x%.8lx. "
+ "First non-contiguous (ignored) bank start: 0x%.8lx\n",
+ (unsigned long)bank_phys_end(&bank[0]),
+ (unsigned long)bank_phys_start(&bank[i]));
+ break;
+ }
+ }
+ /* All contiguous banks are now merged in to the first bank */
+ meminfo.nr_banks = 1;
+ specified_mem_size = bank[0].size;
+
+ /*
+ * MPU has curious alignment requirements: Size must be power of 2, and
+ * region start must be aligned to the region size
+ */
+ if (phys_offset != 0)
+ pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
+
+ /*
+ * Maximum aligned region might overflow phys_addr_t if phys_offset is
+ * 0. Hence we keep everything below 4G until we take the smaller of
+ * the aligned_region_size and rounded_mem_size, one of which is
+ * guaranteed to be smaller than the maximum physical address.
+ */
+ aligned_region_size = (phys_offset - 1) ^ (phys_offset);
+ /* Find the max power-of-two sized region that fits inside our bank */
+ rounded_mem_size = (1 << __fls(bank[0].size)) - 1;
+
+ /* The actual region size is the smaller of the two */
+ aligned_region_size = aligned_region_size < rounded_mem_size
+ ? aligned_region_size + 1
+ : rounded_mem_size + 1;
+
+ if (aligned_region_size != specified_mem_size)
+ pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)",
+ (unsigned long)specified_mem_size,
+ (unsigned long)aligned_region_size);
+
+ meminfo.bank[0].size = aligned_region_size;
+ pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n",
+ (unsigned long)phys_offset,
+ (unsigned long)aligned_region_size,
+ (unsigned long)bank_phys_end(&bank[0]));
+
+}
+
+static int mpu_present(void)
+{
+ return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
+static int mpu_max_regions(void)
+{
+ /*
+ * We don't support a different number of I/D side regions so if we
+ * have separate instruction and data memory maps then return
+ * whichever side has a smaller number of supported regions.
+ */
+ u32 dregions, iregions, mpuir;
+ mpuir = read_cpuid(CPUID_MPUIR);
+
+ dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+ /* Check for separate d-side and i-side memory maps */
+ if (mpuir & MPUIR_nU)
+ iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
+
+ /* Use the smallest of the two maxima */
+ return min(dregions, iregions);
+}
+
+static int mpu_iside_independent(void)
+{
+ /* MPUIR.nU specifies whether there is *not* a unified memory map */
+ return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
+}
+
+static int mpu_min_region_order(void)
+{
+ u32 drbar_result, irbar_result;
+ /* We've kept a region free for this probing */
+ rgnr_write(MPU_PROBE_REGION);
+ isb();
+ /*
+ * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
+ * region order
+ */
+ drbar_write(0xFFFFFFFC);
+ drbar_result = irbar_result = drbar_read();
+ drbar_write(0x0);
+ /* If the MPU is non-unified, we use the larger of the two minima*/
+ if (mpu_iside_independent()) {
+ irbar_write(0xFFFFFFFC);
+ irbar_result = irbar_read();
+ irbar_write(0x0);
+ }
+ isb(); /* Ensure that MPU region operations have completed */
+ /* Return whichever result is larger */
+ return __ffs(max(drbar_result, irbar_result));
+}
+
+static int mpu_setup_region(unsigned int number, phys_addr_t start,
+ unsigned int size_order, unsigned int properties)
+{
+ u32 size_data;
+
+ /* We kept a region free for probing resolution of MPU regions*/
+ if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
+ return -ENOENT;
+
+ if (size_order > 32)
+ return -ENOMEM;
+
+ if (size_order < mpu_min_region_order())
+ return -ENOMEM;
+
+ /* Writing N to bits 5:1 (RSR_SZ) specifies region size 2^N+1 */
+ size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+
+ dsb(); /* Ensure all previous data accesses occur with old mappings */
+ rgnr_write(number);
+ isb();
+ drbar_write(start);
+ dracr_write(properties);
+ isb(); /* Propagate properties before enabling region */
+ drsr_write(size_data);
+
+ /* Check for independent I-side registers */
+ if (mpu_iside_independent()) {
+ irbar_write(start);
+ iracr_write(properties);
+ isb();
+ irsr_write(size_data);
+ }
+ isb();
+
+ /* Store region info (we treat i/d side the same, so only store d) */
+ mpu_rgn_info.rgns[number].dracr = properties;
+ mpu_rgn_info.rgns[number].drbar = start;
+ mpu_rgn_info.rgns[number].drsr = size_data;
+ return 0;
+}
+
+/*
+* Set up default MPU regions, doing nothing if there is no MPU
+*/
+void __init mpu_setup(void)
+{
+ int region_err;
+ if (!mpu_present())
+ return;
+
+ region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
+ ilog2(meminfo.bank[0].size),
+ MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+ if (region_err) {
+ panic("MPU region initialization failure! %d", region_err);
+ } else {
+ pr_info("Using ARMv7 PMSA Compliant MPU. "
+ "Region independence: %s, Max regions: %d\n",
+ mpu_iside_independent() ? "Yes" : "No",
+ mpu_max_regions());
+ }
+}
+#else
+static void sanity_check_meminfo_mpu(void) {}
+static void __init mpu_setup(void) {}
+#endif /* CONFIG_ARM_MPU */
+
void __init arm_mm_memblock_reserve(void)
{
+#ifndef CONFIG_CPU_V7M
/*
* Register the exception vector page.
* some architectures which the DRAM is the exception vector to trap,
* alloc_page breaks with error, although it is not NULL, but "0."
*/
memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE);
+#else /* ifndef CONFIG_CPU_V7M */
+ /*
+ * There is no dedicated vector page on V7-M. So nothing needs to be
+ * reserved here.
+ */
+#endif
}
void __init sanity_check_meminfo(void)
{
- phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+ phys_addr_t end;
+ sanity_check_meminfo_mpu();
+ end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
high_memory = __va(end - 1) + 1;
}
@@ -41,6 +302,7 @@ void __init sanity_check_meminfo(void)
void __init paging_init(struct machine_desc *mdesc)
{
early_trap_init((void *)CONFIG_VECTORS_BASE);
+ mpu_setup();
bootmem_init();
}
@@ -57,6 +319,12 @@ void flush_dcache_page(struct page *page)
}
EXPORT_SYMBOL(flush_dcache_page);
+void flush_kernel_dcache_page(struct page *page)
+{
+ __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long uaddr, void *dst, const void *src,
unsigned long len)
@@ -81,16 +349,16 @@ void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
return __arm_ioremap_pfn(pfn, offset, size, mtype);
}
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
unsigned int mtype)
{
return (void __iomem *)phys_addr;
}
EXPORT_SYMBOL(__arm_ioremap);
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
return __arm_ioremap(phys_addr, size, mtype);
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index d217e9795d7..aaeb6c127c7 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -81,7 +81,6 @@ ENDPROC(cpu_fa526_reset)
*/
.align 4
ENTRY(cpu_fa526_do_idle)
- mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt
mov pc, lr
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index f9a0aa725ea..e3c48a3fe06 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -333,3 +333,8 @@ ENTRY(\name\()_tlb_fns)
.endif
.size \name\()_tlb_fns, . - \name\()_tlb_fns
.endm
+
+.macro globl_equ x, y
+ .globl \x
+ .equ \x, \y
+.endm
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 919405e20b8..2d1ef87328a 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -140,8 +140,10 @@ ENTRY(cpu_v6_set_pte_ext)
ENTRY(cpu_v6_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID
+#ifdef CONFIG_MMU
mrc p15, 0, r5, c3, c0, 0 @ Domain ID
mrc p15, 0, r6, c2, c0, 1 @ Translation table base 1
+#endif
mrc p15, 0, r7, c1, c0, 1 @ auxiliary control register
mrc p15, 0, r8, c1, c0, 2 @ co-processor access control
mrc p15, 0, r9, c1, c0, 0 @ control register
@@ -158,14 +160,16 @@ ENTRY(cpu_v6_do_resume)
mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID
ldmia r0, {r4 - r9}
mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID
+#ifdef CONFIG_MMU
mcr p15, 0, r5, c3, c0, 0 @ Domain ID
ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP)
ALT_UP(orr r1, r1, #TTB_FLAGS_UP)
mcr p15, 0, r1, c2, c0, 0 @ Translation table base 0
mcr p15, 0, r6, c2, c0, 1 @ Translation table base 1
+ mcr p15, 0, ip, c2, c0, 2 @ TTB control register
+#endif
mcr p15, 0, r7, c1, c0, 1 @ auxiliary control register
mcr p15, 0, r8, c1, c0, 2 @ co-processor access control
- mcr p15, 0, ip, c2, c0, 2 @ TTB control register
mcr p15, 0, ip, c7, c5, 4 @ ISB
mov r0, r9 @ control register
b cpu_resume_mmu
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 363027e811d..5ffe1956c6d 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -39,6 +39,14 @@
#define TTB_FLAGS_SMP (TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
#define PMD_FLAGS_SMP (PMD_SECT_WBWA|PMD_SECT_S)
+#ifndef __ARMEB__
+# define rpgdl r0
+# define rpgdh r1
+#else
+# define rpgdl r1
+# define rpgdh r0
+#endif
+
/*
* cpu_v7_switch_mm(pgd_phys, tsk)
*
@@ -47,10 +55,10 @@
*/
ENTRY(cpu_v7_switch_mm)
#ifdef CONFIG_MMU
- mmid r1, r1 @ get mm->context.id
- asid r3, r1
- mov r3, r3, lsl #(48 - 32) @ ASID
- mcrr p15, 0, r0, r3, c2 @ set TTB 0
+ mmid r2, r2
+ asid r2, r2
+ orr rpgdh, rpgdh, r2, lsl #(48 - 32) @ upper 32-bits of pgd
+ mcrr p15, 0, rpgdl, rpgdh, c2 @ set TTB 0
isb
#endif
mov pc, lr
@@ -106,7 +114,8 @@ ENDPROC(cpu_v7_set_pte_ext)
*/
.macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp
ldr \tmp, =swapper_pg_dir @ swapper_pg_dir virtual address
- cmp \ttbr1, \tmp @ PHYS_OFFSET > PAGE_OFFSET? (branch below)
+ mov \tmp, \tmp, lsr #ARCH_PGD_SHIFT
+ cmp \ttbr1, \tmp @ PHYS_OFFSET > PAGE_OFFSET?
mrc p15, 0, \tmp, c2, c0, 2 @ TTB control register
orr \tmp, \tmp, #TTB_EAE
ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP)
@@ -114,27 +123,21 @@ ENDPROC(cpu_v7_set_pte_ext)
ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP << 16)
ALT_UP(orr \tmp, \tmp, #TTB_FLAGS_UP << 16)
/*
- * TTBR0/TTBR1 split (PAGE_OFFSET):
- * 0x40000000: T0SZ = 2, T1SZ = 0 (not used)
- * 0x80000000: T0SZ = 0, T1SZ = 1
- * 0xc0000000: T0SZ = 0, T1SZ = 2
- *
- * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
- * booting secondary CPUs would end up using TTBR1 for the identity
- * mapping set up in TTBR0.
+ * Only use split TTBRs if PHYS_OFFSET <= PAGE_OFFSET (cmp above),
+ * otherwise booting secondary CPUs would end up using TTBR1 for the
+ * identity mapping set up in TTBR0.
*/
- bhi 9001f @ PHYS_OFFSET > PAGE_OFFSET?
- orr \tmp, \tmp, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ
-#if defined CONFIG_VMSPLIT_2G
- /* PAGE_OFFSET == 0x80000000, T1SZ == 1 */
- add \ttbr1, \ttbr1, #1 << 4 @ skip two L1 entries
-#elif defined CONFIG_VMSPLIT_3G
- /* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */
- add \ttbr1, \ttbr1, #4096 * (1 + 3) @ only L2 used, skip pgd+3*pmd
-#endif
- /* CONFIG_VMSPLIT_1G does not need TTBR1 adjustment */
-9001: mcr p15, 0, \tmp, c2, c0, 2 @ TTB control register
- mcrr p15, 1, \ttbr1, \zero, c2 @ load TTBR1
+ 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
__CPUINIT
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c73a7301ff..7ef3ad05df3 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -98,9 +98,11 @@ ENTRY(cpu_v7_do_suspend)
mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID
mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID
stmia r0!, {r4 - r5}
+#ifdef CONFIG_MMU
mrc p15, 0, r6, c3, c0, 0 @ Domain ID
mrc p15, 0, r7, c2, c0, 1 @ TTB 1
mrc p15, 0, r11, c2, c0, 2 @ TTB control register
+#endif
mrc p15, 0, r8, c1, c0, 0 @ Control register
mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register
mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control
@@ -110,13 +112,14 @@ ENDPROC(cpu_v7_do_suspend)
ENTRY(cpu_v7_do_resume)
mov ip, #0
- mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs
mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache
mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID
ldmia r0!, {r4 - r5}
mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID
mcr p15, 0, r5, c13, c0, 3 @ User r/o thread ID
ldmia r0, {r6 - r11}
+#ifdef CONFIG_MMU
+ mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs
mcr p15, 0, r6, c3, c0, 0 @ Domain ID
#ifndef CONFIG_ARM_LPAE
ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP)
@@ -125,14 +128,15 @@ ENTRY(cpu_v7_do_resume)
mcr p15, 0, r1, c2, c0, 0 @ TTB 0
mcr p15, 0, r7, c2, c0, 1 @ TTB 1
mcr p15, 0, r11, c2, c0, 2 @ TTB control register
- mrc p15, 0, r4, c1, c0, 1 @ Read Auxiliary control register
- teq r4, r9 @ Is it already set?
- mcrne p15, 0, r9, c1, c0, 1 @ No, so write it
- mcr p15, 0, r10, c1, c0, 2 @ Co-processor access control
ldr r4, =PRRR @ PRRR
ldr r5, =NMRR @ NMRR
mcr p15, 0, r4, c10, c2, 0 @ write PRRR
mcr p15, 0, r5, c10, c2, 1 @ write NMRR
+#endif /* CONFIG_MMU */
+ mrc p15, 0, r4, c1, c0, 1 @ Read Auxiliary control register
+ teq r4, r9 @ Is it already set?
+ mcrne p15, 0, r9, c1, c0, 1 @ No, so write it
+ mcr p15, 0, r10, c1, c0, 2 @ Co-processor access control
isb
dsb
mov r0, r8 @ control register
@@ -140,6 +144,29 @@ ENTRY(cpu_v7_do_resume)
ENDPROC(cpu_v7_do_resume)
#endif
+#ifdef CONFIG_CPU_PJ4B
+ globl_equ cpu_pj4b_switch_mm, cpu_v7_switch_mm
+ globl_equ cpu_pj4b_set_pte_ext, cpu_v7_set_pte_ext
+ globl_equ cpu_pj4b_proc_init, cpu_v7_proc_init
+ globl_equ cpu_pj4b_proc_fin, cpu_v7_proc_fin
+ globl_equ cpu_pj4b_reset, cpu_v7_reset
+#ifdef CONFIG_PJ4B_ERRATA_4742
+ENTRY(cpu_pj4b_do_idle)
+ dsb @ WFI may enter a low-power mode
+ wfi
+ dsb @barrier
+ mov pc, lr
+ENDPROC(cpu_pj4b_do_idle)
+#else
+ globl_equ cpu_pj4b_do_idle, cpu_v7_do_idle
+#endif
+ globl_equ cpu_pj4b_dcache_clean_area, cpu_v7_dcache_clean_area
+ globl_equ cpu_pj4b_do_suspend, cpu_v7_do_suspend
+ globl_equ cpu_pj4b_do_resume, cpu_v7_do_resume
+ globl_equ cpu_pj4b_suspend_size, cpu_v7_suspend_size
+
+#endif
+
__CPUINIT
/*
@@ -155,7 +182,8 @@ ENDPROC(cpu_v7_do_resume)
*/
__v7_ca5mp_setup:
__v7_ca9mp_setup:
- mov r10, #(1 << 0) @ TLB ops broadcasting
+__v7_cr7mp_setup:
+ mov r10, #(1 << 0) @ Cache/TLB ops broadcasting
b 1f
__v7_ca7mp_setup:
__v7_ca15mp_setup:
@@ -350,6 +378,9 @@ __v7_setup_stack:
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#ifdef CONFIG_CPU_PJ4B
+ define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#endif
.section ".rodata"
@@ -362,7 +393,7 @@ __v7_setup_stack:
/*
* Standard v7 proc info content
*/
-.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0
+.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions
ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
@@ -375,7 +406,7 @@ __v7_setup_stack:
.long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \
HWCAP_EDSP | HWCAP_TLS | \hwcaps
.long cpu_v7_name
- .long v7_processor_functions
+ .long \proc_fns
.long v7wbi_tlb_fns
.long v6_user_fns
.long v7_cache_fns
@@ -407,12 +438,24 @@ __v7_ca9mp_proc_info:
/*
* Marvell PJ4B processor.
*/
+#ifdef CONFIG_CPU_PJ4B
.type __v7_pj4b_proc_info, #object
__v7_pj4b_proc_info:
- .long 0x562f5840
- .long 0xfffffff0
- __v7_proc __v7_pj4b_setup
+ .long 0x560f5800
+ .long 0xff0fff00
+ __v7_proc __v7_pj4b_setup, proc_fns = pj4b_processor_functions
.size __v7_pj4b_proc_info, . - __v7_pj4b_proc_info
+#endif
+
+ /*
+ * ARM Ltd. Cortex R7 processor.
+ */
+ .type __v7_cr7mp_proc_info, #object
+__v7_cr7mp_proc_info:
+ .long 0x410fc170
+ .long 0xff0ffff0
+ __v7_proc __v7_cr7mp_setup
+ .size __v7_cr7mp_proc_info, . - __v7_cr7mp_proc_info
/*
* ARM Ltd. Cortex A7 processor.
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
new file mode 100644
index 00000000000..0c93588fcb9
--- /dev/null
+++ b/arch/arm/mm/proc-v7m.S
@@ -0,0 +1,157 @@
+/*
+ * linux/arch/arm/mm/proc-v7m.S
+ *
+ * Copyright (C) 2008 ARM Ltd.
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This is the "shell" of the ARMv7-M processor support.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/v7m.h>
+#include "proc-macros.S"
+
+ENTRY(cpu_v7m_proc_init)
+ mov pc, lr
+ENDPROC(cpu_v7m_proc_init)
+
+ENTRY(cpu_v7m_proc_fin)
+ mov pc, lr
+ENDPROC(cpu_v7m_proc_fin)
+
+/*
+ * cpu_v7m_reset(loc)
+ *
+ * Perform a soft reset of the system. Put the CPU into the
+ * same state as it would be if it had been reset, and branch
+ * to what would be the reset vector.
+ *
+ * - loc - location to jump to for soft reset
+ */
+ .align 5
+ENTRY(cpu_v7m_reset)
+ mov pc, r0
+ENDPROC(cpu_v7m_reset)
+
+/*
+ * cpu_v7m_do_idle()
+ *
+ * Idle the processor (eg, wait for interrupt).
+ *
+ * IRQs are already disabled.
+ */
+ENTRY(cpu_v7m_do_idle)
+ wfi
+ mov pc, lr
+ENDPROC(cpu_v7m_do_idle)
+
+ENTRY(cpu_v7m_dcache_clean_area)
+ mov pc, lr
+ENDPROC(cpu_v7m_dcache_clean_area)
+
+/*
+ * There is no MMU, so here is nothing to do.
+ */
+ENTRY(cpu_v7m_switch_mm)
+ mov pc, lr
+ENDPROC(cpu_v7m_switch_mm)
+
+.globl cpu_v7m_suspend_size
+.equ cpu_v7m_suspend_size, 0
+
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_v7m_do_suspend)
+ mov pc, lr
+ENDPROC(cpu_v7m_do_suspend)
+
+ENTRY(cpu_v7m_do_resume)
+ mov pc, lr
+ENDPROC(cpu_v7m_do_resume)
+#endif
+
+ .section ".text.init", #alloc, #execinstr
+
+/*
+ * __v7m_setup
+ *
+ * This should be able to cover all ARMv7-M cores.
+ */
+__v7m_setup:
+ @ Configure the vector table base address
+ ldr r0, =BASEADDR_V7M_SCB
+ ldr r12, =vector_table
+ str r12, [r0, V7M_SCB_VTOR]
+
+ @ enable UsageFault, BusFault and MemManage fault.
+ ldr r5, [r0, #V7M_SCB_SHCSR]
+ orr r5, #(V7M_SCB_SHCSR_USGFAULTENA | V7M_SCB_SHCSR_BUSFAULTENA | V7M_SCB_SHCSR_MEMFAULTENA)
+ str r5, [r0, #V7M_SCB_SHCSR]
+
+ @ Lower the priority of the SVC and PendSV exceptions
+ mov r5, #0x80000000
+ str r5, [r0, V7M_SCB_SHPR2] @ set SVC priority
+ mov r5, #0x00800000
+ str r5, [r0, V7M_SCB_SHPR3] @ set PendSV priority
+
+ @ SVC to run the kernel in this mode
+ adr r1, BSYM(1f)
+ ldr r5, [r12, #11 * 4] @ read the SVC vector entry
+ str r1, [r12, #11 * 4] @ write the temporary SVC vector entry
+ mov r6, lr @ save LR
+ mov r7, sp @ save SP
+ ldr sp, =__v7m_setup_stack_top
+ cpsie i
+ svc #0
+1: cpsid i
+ str r5, [r12, #11 * 4] @ restore the original SVC vector entry
+ mov lr, r6 @ restore LR
+ mov sp, r7 @ restore SP
+
+ @ Special-purpose control register
+ mov r1, #1
+ msr control, r1 @ Thread mode has unpriviledged access
+
+ @ Configure the System Control Register to ensure 8-byte stack alignment
+ @ Note the STKALIGN bit is either RW or RAO.
+ ldr r12, [r0, V7M_SCB_CCR] @ system control register
+ orr r12, #V7M_SCB_CCR_STKALIGN
+ str r12, [r0, V7M_SCB_CCR]
+ mov pc, lr
+ENDPROC(__v7m_setup)
+
+ define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
+
+ .section ".rodata"
+ string cpu_arch_name, "armv7m"
+ string cpu_elf_name "v7m"
+ string cpu_v7m_name "ARMv7-M"
+
+ .section ".proc.info.init", #alloc, #execinstr
+
+ /*
+ * Match any ARMv7-M processor core.
+ */
+ .type __v7m_proc_info, #object
+__v7m_proc_info:
+ .long 0x000f0000 @ Required ID value
+ .long 0x000f0000 @ Mask for ID
+ .long 0 @ proc_info_list.__cpu_mm_mmu_flags
+ .long 0 @ proc_info_list.__cpu_io_mmu_flags
+ b __v7m_setup @ proc_info_list.__cpu_flush
+ .long cpu_arch_name
+ .long cpu_elf_name
+ .long HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT
+ .long cpu_v7m_name
+ .long v7m_processor_functions @ proc_info_list.proc
+ .long 0 @ proc_info_list.tlb
+ .long 0 @ proc_info_list.user
+ .long nop_cache_fns @ proc_info_list.cache
+ .size __v7m_proc_info, . - __v7m_proc_info
+
+__v7m_setup_stack:
+ .space 4 * 8 @ 8 registers
+__v7m_setup_stack_top: