From ca5a45c06cd4764fb8510740f7fc550d9a0208d4 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 31 Jul 2013 12:44:41 -0400 Subject: ARM: mm: use phys_addr_t appropriately in p2v and v2p conversions Fix remainder types used when converting back and forth between physical and virtual addresses. Cc: Russell King Acked-by: Nicolas Pitre Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/memory.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index e750a938fd3c..c133bd915f48 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -185,22 +185,32 @@ extern unsigned long __pv_phys_offset; : "=r" (to) \ : "r" (from), "I" (type)) -static inline unsigned long __virt_to_phys(unsigned long x) +static inline phys_addr_t __virt_to_phys(unsigned long x) { unsigned long t; __pv_stub(x, t, "add", __PV_BITS_31_24); 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__ */ @@ -238,14 +248,14 @@ 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) /* -- cgit v1.2.3 From 4dc9a81715973cb137a14399420bb35b0ed7d6ef Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 31 Jul 2013 12:44:42 -0400 Subject: ARM: mm: Introduce virt_to_idmap() with an arch hook On some PAE systems (e.g. TI Keystone), memory is above the 32-bit addressable limit, and the interconnect provides an aliased view of parts of physical memory in the 32-bit addressable space. This alias is strictly for boot time usage, and is not otherwise usable because of coherency limitations. On such systems, the idmap mechanism needs to take this aliased mapping into account. This patch introduces virt_to_idmap() and a arch function pointer which can be populated by platform which needs it. Also populate necessary idmap spots with now available virt_to_idmap(). Avoided #ifdef approach to be compatible with multi-platform builds. Most architecture won't touch it and in that case virt_to_idmap() fall-back to existing virt_to_phys() macro. Cc: Russell King Acked-by: Nicolas Pitre Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/memory.h | 16 ++++++++++++++++ arch/arm/kernel/smp.c | 2 +- arch/arm/mm/idmap.c | 5 +++-- 3 files changed, 20 insertions(+), 3 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index c133bd915f48..d9b96c65e594 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -173,6 +173,7 @@ */ #define __PV_BITS_31_24 0x81000000 +extern phys_addr_t (*arch_virt_to_idmap) (unsigned long x); extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset @@ -258,6 +259,21 @@ static inline void *phys_to_virt(phys_addr_t 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 diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 72024ea8a3a6..a0eb830c3daf 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -80,7 +80,7 @@ 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; } diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 83cb3ac27095..c0a1e48f6733 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -10,6 +10,7 @@ #include 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 +68,8 @@ 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); prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; -- cgit v1.2.3 From f52bb722547f43caeaecbcc62db9f3c3b80ead9b Mon Sep 17 00:00:00 2001 From: Sricharan R Date: Mon, 29 Jul 2013 20:26:22 +0530 Subject: ARM: mm: Correct virt_to_phys patching for 64 bit physical addresses The current phys_to_virt patching mechanism works only for 32 bit physical addresses and this patch extends the idea for 64bit physical addresses. The 64bit v2p patching mechanism patches the higher 8 bits of physical address with a constant using 'mov' instruction and lower 32bits are patched using 'add'. While this is correct, in those platforms where the lowmem addressable physical memory spawns across 4GB boundary, a carry bit can be produced as a result of addition of lower 32bits. This has to be taken in to account and added in to the upper. The patched __pv_offset and va are added in lower 32bits, where __pv_offset can be in two's complement form when PA_START < VA_START and that can result in a false carry bit. e.g 1) PA = 0x80000000; VA = 0xC0000000 __pv_offset = PA - VA = 0xC0000000 (2's complement) 2) PA = 0x2 80000000; VA = 0xC000000 __pv_offset = PA - VA = 0x1 C0000000 So adding __pv_offset + VA should never result in a true overflow for (1). So in order to differentiate between a true carry, a __pv_offset is extended to 64bit and the upper 32bits will have 0xffffffff if __pv_offset is 2's complement. So 'mvn #0' is inserted instead of 'mov' while patching for the same reason. Since mov, add, sub instruction are to patched with different constants inside the same stub, the rotation field of the opcode is using to differentiate between them. So the above examples for v2p translation becomes for VA=0xC0000000, 1) PA[63:32] = 0xffffffff PA[31:0] = VA + 0xC0000000 --> results in a carry PA[63:32] = PA[63:32] + carry PA[63:0] = 0x0 80000000 2) PA[63:32] = 0x1 PA[31:0] = VA + 0xC0000000 --> results in a carry PA[63:32] = PA[63:32] + carry PA[63:0] = 0x2 80000000 The above ideas were suggested by Nicolas Pitre as part of the review of first and second versions of the subject patch. There is no corresponding change on the phys_to_virt() side, because computations on the upper 32-bits would be discarded anyway. Cc: Russell King Reviewed-by: Nicolas Pitre Signed-off-by: Sricharan R Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/memory.h | 37 ++++++++++++++++++++++--- arch/arm/kernel/armksyms.c | 1 + arch/arm/kernel/head.S | 63 ++++++++++++++++++++++++++++++++----------- 3 files changed, 82 insertions(+), 19 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index d9b96c65e594..6748d6295a1a 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -172,9 +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 unsigned long __pv_phys_offset; +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; + #define PHYS_OFFSET __pv_phys_offset #define __pv_stub(from,to,instr,type) \ @@ -186,10 +191,36 @@ extern unsigned long __pv_phys_offset; : "=r" (to) \ : "r" (from), "I" (type)) +#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; - __pv_stub(x, t, "add", __PV_BITS_31_24); + 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; } diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index 60d3b738d420..1f031ddd0667 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -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 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 2c7cc1e03473..54547947a4e9 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -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" -- cgit v1.2.3 From a77e0c7b2774fd52ce6bf25c2c3ffdccb7b110ff Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 31 Jul 2013 12:44:46 -0400 Subject: ARM: mm: Recreate kernel mappings in early_paging_init() This patch adds a step in the init sequence, in order to recreate the kernel code/data page table mappings prior to full paging initialization. This is necessary on LPAE systems that run out of a physical address space outside the 4G limit. On these systems, this implementation provides a machine descriptor hook that allows the PHYS_OFFSET to be overridden in a machine specific fashion. Cc: Russell King Acked-by: Nicolas Pitre Signed-off-by: R Sricharan Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/mach/arch.h | 1 + arch/arm/kernel/setup.c | 4 ++ arch/arm/mm/mmu.c | 82 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 87 insertions(+) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 402a2bc6aa68..17a3fa2979e8 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -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); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 0e1e2b3afa45..af7b7db4699e 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -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); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b1d17eeb59b8..78eeeca78f5a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include #include #include @@ -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. -- cgit v1.2.3