Merge branch 'for-rmk/arm-mm-lpae' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone into devel-stable

This series extends the existing ARM v2p runtime patching for 64 bit.
Needed for LPAE machines which have physical memory beyond 4GB.
This commit is contained in:
Russell King 2013-10-15 14:12:24 +01:00
commit 8754c4bf2a
8 changed files with 206 additions and 30 deletions

View File

@ -49,6 +49,7 @@ struct machine_desc {
bool (*smp_init)(void);
void (*fixup)(struct tag *, char **,
struct meminfo *);
void (*init_meminfo)(void);
void (*reserve)(void);/* reserve mem blocks */
void (*map_io)(void);/* IO mapping function */
void (*init_early)(void);

View File

@ -172,8 +172,14 @@
* so that all we need to do is modify the 8-bit constant field.
*/
#define __PV_BITS_31_24 0x81000000
#define __PV_BITS_7_0 0x81
extern phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
extern u64 __pv_phys_offset;
extern u64 __pv_offset;
extern void fixup_pv_table(const void *, unsigned long);
extern const void *__pv_table_begin, *__pv_table_end;
extern unsigned long __pv_phys_offset;
#define PHYS_OFFSET __pv_phys_offset
#define __pv_stub(from,to,instr,type) \
@ -185,22 +191,58 @@ extern unsigned long __pv_phys_offset;
: "=r" (to) \
: "r" (from), "I" (type))
static inline unsigned long __virt_to_phys(unsigned long x)
#define __pv_stub_mov_hi(t) \
__asm__ volatile("@ __pv_stub_mov\n" \
"1: mov %R0, %1\n" \
" .pushsection .pv_table,\"a\"\n" \
" .long 1b\n" \
" .popsection\n" \
: "=r" (t) \
: "I" (__PV_BITS_7_0))
#define __pv_add_carry_stub(x, y) \
__asm__ volatile("@ __pv_add_carry_stub\n" \
"1: adds %Q0, %1, %2\n" \
" adc %R0, %R0, #0\n" \
" .pushsection .pv_table,\"a\"\n" \
" .long 1b\n" \
" .popsection\n" \
: "+r" (y) \
: "r" (x), "I" (__PV_BITS_31_24) \
: "cc")
static inline phys_addr_t __virt_to_phys(unsigned long x)
{
unsigned long t;
phys_addr_t t;
if (sizeof(phys_addr_t) == 4) {
__pv_stub(x, t, "add", __PV_BITS_31_24);
} else {
__pv_stub_mov_hi(t);
__pv_add_carry_stub(x, t);
}
return t;
}
static inline unsigned long __phys_to_virt(unsigned long x)
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
unsigned long t;
__pv_stub(x, t, "sub", __PV_BITS_31_24);
return t;
}
#else
#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET)
#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET)
static inline phys_addr_t __virt_to_phys(unsigned long x)
{
return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
}
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
return x - PHYS_OFFSET + PAGE_OFFSET;
}
#endif
#endif
#endif /* __ASSEMBLY__ */
@ -238,16 +280,31 @@ static inline phys_addr_t virt_to_phys(const volatile void *x)
static inline void *phys_to_virt(phys_addr_t x)
{
return (void *)(__phys_to_virt((unsigned long)(x)));
return (void *)__phys_to_virt(x);
}
/*
* Drivers should NOT use these either.
*/
#define __pa(x) __virt_to_phys((unsigned long)(x))
#define __va(x) ((void *)__phys_to_virt((unsigned long)(x)))
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
/*
* These are for systems that have a hardware interconnect supported alias of
* physical memory for idmap purposes. Most cases should leave these
* untouched.
*/
static inline phys_addr_t __virt_to_idmap(unsigned long x)
{
if (arch_virt_to_idmap)
return arch_virt_to_idmap(x);
else
return __virt_to_phys(x);
}
#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x))
/*
* Virtual <-> DMA view memory address translations
* Again, these are *only* valid on the kernel direct mapped RAM

View File

@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
EXPORT_SYMBOL(__pv_phys_offset);
EXPORT_SYMBOL(__pv_offset);
#endif

View File

@ -536,6 +536,14 @@ ENTRY(fixup_smp)
ldmfd sp!, {r4 - r6, pc}
ENDPROC(fixup_smp)
#ifdef __ARMEB_
#define LOW_OFFSET 0x4
#define HIGH_OFFSET 0x0
#else
#define LOW_OFFSET 0x0
#define HIGH_OFFSET 0x4
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
/* __fixup_pv_table - patch the stub instructions with the delta between
@ -546,17 +554,20 @@ ENDPROC(fixup_smp)
__HEAD
__fixup_pv_table:
adr r0, 1f
ldmia r0, {r3-r5, r7}
sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
ldmia r0, {r3-r7}
mvn ip, #0
subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
add r4, r4, r3 @ adjust table start address
add r5, r5, r3 @ adjust table end address
add r7, r7, r3 @ adjust __pv_phys_offset address
str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset
add r6, r6, r3 @ adjust __pv_phys_offset address
add r7, r7, r3 @ adjust __pv_offset address
str r8, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_offset
strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits
mov r6, r3, lsr #24 @ constant for add/sub instructions
teq r3, r6, lsl #24 @ must be 16MiB aligned
THUMB( it ne @ cross section branch )
bne __error
str r6, [r7, #4] @ save to __pv_offset
str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits
b __fixup_a_pv_table
ENDPROC(__fixup_pv_table)
@ -565,10 +576,19 @@ ENDPROC(__fixup_pv_table)
.long __pv_table_begin
.long __pv_table_end
2: .long __pv_phys_offset
.long __pv_offset
.text
__fixup_a_pv_table:
adr r0, 3f
ldr r6, [r0]
add r6, r6, r3
ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word
ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word
mov r6, r6, lsr #24
cmn r0, #1
#ifdef CONFIG_THUMB2_KERNEL
moveq r0, #0x200000 @ set bit 21, mov to mvn instruction
lsls r6, #24
beq 2f
clz r7, r6
@ -582,18 +602,28 @@ __fixup_a_pv_table:
b 2f
1: add r7, r3
ldrh ip, [r7, #2]
and ip, 0x8f00
orr ip, r6 @ mask in offset bits 31-24
tst ip, #0x4000
and ip, #0x8f00
orrne ip, r6 @ mask in offset bits 31-24
orreq ip, r0 @ mask in offset bits 7-0
strh ip, [r7, #2]
ldrheq ip, [r7]
biceq ip, #0x20
orreq ip, ip, r0, lsr #16
strheq ip, [r7]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
bcc 1b
bx lr
#else
moveq r0, #0x400000 @ set bit 22, mov to mvn instruction
b 2f
1: ldr ip, [r7, r3]
bic ip, ip, #0x000000ff
orr ip, ip, r6 @ mask in offset bits 31-24
tst ip, #0xf00 @ check the rotation field
orrne ip, ip, r6 @ mask in offset bits 31-24
biceq ip, ip, #0x400000 @ clear bit 22
orreq ip, ip, r0 @ mask in offset bits 7-0
str ip, [r7, r3]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
@ -602,28 +632,29 @@ __fixup_a_pv_table:
#endif
ENDPROC(__fixup_a_pv_table)
3: .long __pv_offset
ENTRY(fixup_pv_table)
stmfd sp!, {r4 - r7, lr}
ldr r2, 2f @ get address of __pv_phys_offset
mov r3, #0 @ no offset
mov r4, r0 @ r0 = table start
add r5, r0, r1 @ r1 = table size
ldr r6, [r2, #4] @ get __pv_offset
bl __fixup_a_pv_table
ldmfd sp!, {r4 - r7, pc}
ENDPROC(fixup_pv_table)
.align
2: .long __pv_phys_offset
.data
.globl __pv_phys_offset
.type __pv_phys_offset, %object
__pv_phys_offset:
.long 0
.size __pv_phys_offset, . - __pv_phys_offset
.quad 0
.size __pv_phys_offset, . -__pv_phys_offset
.globl __pv_offset
.type __pv_offset, %object
__pv_offset:
.long 0
.quad 0
.size __pv_offset, . -__pv_offset
#endif
#include "head-common.S"

View File

@ -73,6 +73,8 @@ __setup("fpe=", fpe_setup);
#endif
extern void paging_init(const struct machine_desc *desc);
extern void early_paging_init(const struct machine_desc *,
struct proc_info_list *);
extern void sanity_check_meminfo(void);
extern enum reboot_mode reboot_mode;
extern void setup_dma_zone(const struct machine_desc *desc);
@ -878,6 +880,8 @@ void __init setup_arch(char **cmdline_p)
parse_early_param();
sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
sanity_check_meminfo();
arm_memblock_init(&meminfo, mdesc);

View File

@ -81,7 +81,7 @@ void __init smp_set_ops(struct smp_operations *ops)
static unsigned long get_arch_pgd(pgd_t *pgd)
{
phys_addr_t pgdir = virt_to_phys(pgd);
phys_addr_t pgdir = virt_to_idmap(pgd);
BUG_ON(pgdir & ARCH_PGD_MASK);
return pgdir >> ARCH_PGD_SHIFT;
}

View File

@ -10,6 +10,7 @@
#include <asm/system_info.h>
pgd_t *idmap_pgd;
phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
#ifdef CONFIG_ARM_LPAE
static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
@ -67,8 +68,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
unsigned long addr, end;
unsigned long next;
addr = virt_to_phys(text_start);
end = virt_to_phys(text_end);
addr = virt_to_idmap(text_start);
end = virt_to_idmap(text_end);
pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end);
prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
@ -90,8 +92,6 @@ static int __init init_static_idmap(void)
if (!idmap_pgd)
return -ENOMEM;
pr_info("Setting up static identity map for 0x%p - 0x%p\n",
__idmap_text_start, __idmap_text_end);
identity_mapping_add(idmap_pgd, __idmap_text_start,
__idmap_text_end, 0);

View File

@ -28,6 +28,8 @@
#include <asm/highmem.h>
#include <asm/system_info.h>
#include <asm/traps.h>
#include <asm/procinfo.h>
#include <asm/memory.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
@ -1315,6 +1317,86 @@ static void __init map_lowmem(void)
}
}
#ifdef CONFIG_ARM_LPAE
/*
* early_paging_init() recreates boot time page table setup, allowing machines
* to switch over to a high (>4G) address space on LPAE systems
*/
void __init early_paging_init(const struct machine_desc *mdesc,
struct proc_info_list *procinfo)
{
pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags;
unsigned long map_start, map_end;
pgd_t *pgd0, *pgdk;
pud_t *pud0, *pudk, *pud_start;
pmd_t *pmd0, *pmdk;
phys_addr_t phys;
int i;
if (!(mdesc->init_meminfo))
return;
/* remap kernel code and data */
map_start = init_mm.start_code;
map_end = init_mm.brk;
/* get a handle on things... */
pgd0 = pgd_offset_k(0);
pud_start = pud0 = pud_offset(pgd0, 0);
pmd0 = pmd_offset(pud0, 0);
pgdk = pgd_offset_k(map_start);
pudk = pud_offset(pgdk, map_start);
pmdk = pmd_offset(pudk, map_start);
mdesc->init_meminfo();
/* Run the patch stub to update the constants */
fixup_pv_table(&__pv_table_begin,
(&__pv_table_end - &__pv_table_begin) << 2);
/*
* Cache cleaning operations for self-modifying code
* We should clean the entries by MVA but running a
* for loop over every pv_table entry pointer would
* just complicate the code.
*/
flush_cache_louis();
dsb();
isb();
/* remap level 1 table */
for (i = 0; i < PTRS_PER_PGD; pud0++, i++) {
set_pud(pud0,
__pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
pmd0 += PTRS_PER_PMD;
}
/* remap pmds for kernel mapping */
phys = __pa(map_start) & PMD_MASK;
do {
*pmdk++ = __pmd(phys | pmdprot);
phys += PMD_SIZE;
} while (phys < map_end);
flush_cache_all();
cpu_switch_mm(pgd0, &init_mm);
cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
local_flush_bp_all();
local_flush_tlb_all();
}
#else
void __init early_paging_init(const struct machine_desc *mdesc,
struct proc_info_list *procinfo)
{
if (mdesc->init_meminfo)
mdesc->init_meminfo();
}
#endif
/*
* paging_init() sets up the page tables, initialises the zone memory
* maps, and sets up the zero page, bad page and bad page tables.