makedumpfile/arm64: Add support for ARMv8.2 extensions
Subsystems (2)
v3 cover makedumpfile/arm64: Add support for ARMv8.2 extensions
Changes since v2:
----------------
- v2 can be seen here:
http://lists.infradead.org/pipermail/kexec/2019-February/022456.html
- I missed some comments from Kazu sent on the LVA v1 patch when I sent out the v2. So, addressing them now in v3.
- Also added a patch that adds a tree-wide feature to read 'MAX_PHYSMEM_BITS' from vmcoreinfo (if available).
Changes since v1:
----------------
- v1 was sent as two separate patches:
http://lists.infradead.org/pipermail/kexec/2019-February/022424.html
(ARMv8.2-LPA)
http://lists.infradead.org/pipermail/kexec/2019-February/022425.html
(ARMv8.2-LVA)
- v2 combined the two in a single patchset and also addresses Kazu's review comments.
This patchset adds support for ARMv8.2 extensions in makedumpfile code. I cover the following two cases with this patchset:
- 48-bit VA + 52-bit PA (LPA)
- 48-bit kernel VA + 52-bit virtual VA (LVA)
This has been tested for the following user-cases:
1. Calculating --mem-usage on the primary kernel,
2. Creating a dumpfile using /proc/vmcore, and
3. Post-processing a vmcore.
I have tested this patchset on the following platforms, with kernels which support/do-not-support ARMv8.2 features:
1. CPUs which don't support ARMv8.2 features, e.g. qualcomm-amberwing, ampere-osprey.
2. Prototype models which support ARMv8.2 extensions (e.g. ARMv8 FVP simulation model).
Also a preparation patch has been added in this patchset which adds a common feature for archs (except arm64, for which similar support is added via subsequent patch) to retrieve 'MAX_PHYSMEM_BITS' from vmcoreinfo (if available).
I recently posted two kernel patches (see [0] and [1]) which append 'PTRS_PER_PGD' and 'MAX_PHYSMEM_BITS' to vmcoreinfo in the kernel code, so that user-space code can benefit from the same.
This patchset ensures backward compatibility for kernel versions in which 'PTRS_PER_PGD' and 'MAX_PHYSMEM_BITS' are not available in vmcoreinfo.
[0]. http://lists.infradead.org/pipermail/kexec/2019-March/022532.html
[1]. http://lists.infradead.org/pipermail/kexec/2019-March/022533.html
Bhupesh Sharma (3):
tree-wide: Retrieve 'MAX_PHYSMEM_BITS' from vmcoreinfo (if available) makedumpfile/arm64: Add support for ARMv8.2-LPA (52-bit PA support) makedumpfile/arm64: Add support for ARMv8.2-LVA (52-bit user-space VA
support)
arch/arm.c | 8 +- arch/arm64.c | 394 ++++++++++++++++++++++++++++++++++++++++----------------- arch/ia64.c | 7 +- arch/ppc.c | 8 +- arch/ppc64.c | 49 ++++--- arch/s390x.c | 29 +++-- arch/sparc64.c | 9 +- arch/x86.c | 34 +++-- arch/x86_64.c | 27 ++-- makedumpfile.c | 2 + makedumpfile.h | 1 + 11 files changed, 390 insertions(+), 178 deletions(-)
Signature · 7 lines
2.7.4 _______________________________________________ kexec mailing list [email protected] http://lists.infradead.org/mailman/listinfo/kexec
PATCH v3 1/3 tree-wide: Retrieve 'MAX_PHYSMEM_BITS' from vmcoreinfo (if available)
This patch adds a common feature for archs (except arm64, for which similar support is added via subsequent patch) to retrieve 'MAX_PHYSMEM_BITS' from vmcoreinfo (if available).
I recently posted a kernel patch (see [0]) which appends 'MAX_PHYSMEM_BITS' to vmcoreinfo in the core code itself rather than in arch-specific code, so that user-space code can also benefit from this addition to the vmcoreinfo and use it as a standard way of determining 'SECTIONS_SHIFT' value in 'makedumpfile' utility.
This patch ensures backward compatibility for kernel versions in which 'MAX_PHYSMEM_BITS' is not available in vmcoreinfo.
[0]. http://lists.infradead.org/pipermail/kexec/2019-March/022531.html
--- arch/arm.c | 8 +++++++- arch/ia64.c | 7 ++++++- arch/ppc.c | 8 +++++++- arch/ppc64.c | 49 ++++++++++++++++++++++++++++--------------------- arch/s390x.c | 29 ++++++++++++++++++----------- arch/sparc64.c | 9 +++++++-- arch/x86.c | 34 ++++++++++++++++++++-------------- arch/x86_64.c | 27 ++++++++++++++++----------- 8 files changed, 109 insertions(+), 62 deletions(-)
arch/arm.c +7 -1
@@ -81,7 +81,13 @@ intget_machdep_info_arm (void) { info->page_offset =SYMBOL (_stext) &0xffff0000UL ; - info->max_physmem_bits = _MAX_PHYSMEM_BITS; + +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +else + info->max_physmem_bits = _MAX_PHYSMEM_BITS; + info->kernel_start =SYMBOL (_stext); info->section_size_bits = _SECTION_SIZE_BITS;
arch/ia64.c +6 -1
@@ -85,7 +85,12 @@ get_machdep_info_ia64(void) } info->section_size_bits = _SECTION_SIZE_BITS; - info->max_physmem_bits = _MAX_PHYSMEM_BITS; + +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +else + info->max_physmem_bits = _MAX_PHYSMEM_BITS;return TRUE; }
arch/ppc.c +7 -1
@@ -31,7 +31,13 @@ get_machdep_info_ppc(void)unsigned long vmlist, vmap_area_list, vmalloc_start; info->section_size_bits = _SECTION_SIZE_BITS; - info->max_physmem_bits = _MAX_PHYSMEM_BITS; + +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +else + info->max_physmem_bits = _MAX_PHYSMEM_BITS; + info->page_offset = __PAGE_OFFSET;if (SYMBOL (_stext) !=NOT_FOUND_SYMBOL )
arch/ppc64.c +28 -21
58 lines not on this page · raw message
arch/s390x.c +18 -11
@@ -63,20 +63,27 @@ intset_s390x_max_physmem_bits (void) {long array_len =ARRAY_LENGTH (mem_section); -/* -* The older s390x kernels uses _MAX_PHYSMEM_BITS as 42 and the -* newer kernels uses 46 bits. -*/ - info->max_physmem_bits = _MAX_PHYSMEM_BITS_ORIG ; -if ((array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT_EXTREME ())) - || (array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT ()))) +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) { + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS );return TRUE; + }else { +/* +* The older s390x kernels uses _MAX_PHYSMEM_BITS as 42 and the +* newer kernels uses 46 bits. +*/ - info->max_physmem_bits = _MAX_PHYSMEM_BITS_3_3; -if ((array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT_EXTREME ())) - || (array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT ()))) -return TRUE; + info->max_physmem_bits = _MAX_PHYSMEM_BITS_ORIG ; +if ((array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT_EXTREME ())) + || (array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT ()))) +return TRUE; + + info->max_physmem_bits = _MAX_PHYSMEM_BITS_3_3; +if ((array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT_EXTREME ())) + || (array_len == (NR_MEM_SECTIONS () /_SECTIONS_PER_ROOT ()))) +return TRUE; + }return FALSE; }
arch/sparc64.c +7 -2
@@ -25,10 +25,15 @@ int get_versiondep_info_sparc64(void) { info->section_size_bits = _SECTION_SIZE_BITS; -if (info->kernel_version >=KERNEL_VERSION (3 ,8 ,13 )) +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +else if (info->kernel_version >=KERNEL_VERSION (3 ,8 ,13 )) info->max_physmem_bits = _MAX_PHYSMEM_BITS_L4; -else { +else info->max_physmem_bits = _MAX_PHYSMEM_BITS_L3; + +if (info->kernel_version <KERNEL_VERSION (3 ,8 ,13 )) { info->flag_vmemmap = TRUE; info->vmemmap_start =VMEMMAP_BASE_SPARC64 ; info->vmemmap_end = VMEMMAP_BASE_SPARC64 +
arch/x86.c +20 -14
@@ -72,21 +72,27 @@ get_machdep_info_x86(void) {unsigned long vmlist, vmap_area_list, vmalloc_start; -/* PAE */ -if ((vt.mem_flags &MEMORY_X86_PAE ) - || ((SYMBOL (pkmap_count) !=NOT_FOUND_SYMBOL ) - && (SYMBOL (pkmap_count_next) !=NOT_FOUND_SYMBOL ) - && ((SYMBOL (pkmap_count_next)-SYMBOL (pkmap_count))/sizeof (int )) - ==512 )) { -DEBUG_MSG ("\n" ); -DEBUG_MSG ("PAE : ON\n" ); - vt.mem_flags |=MEMORY_X86_PAE ; - info->max_physmem_bits = _MAX_PHYSMEM_BITS_PAE; - }else { -DEBUG_MSG ("\n" ); -DEBUG_MSG ("PAE : OFF\n" ); - info->max_physmem_bits = _MAX_PHYSMEM_BITS; +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +else { +/* PAE */ +if ((vt.mem_flags &MEMORY_X86_PAE ) + || ((SYMBOL (pkmap_count) !=NOT_FOUND_SYMBOL ) + && (SYMBOL (pkmap_count_next) !=NOT_FOUND_SYMBOL ) + && ((SYMBOL (pkmap_count_next)-SYMBOL (pkmap_count))/sizeof (int )) + ==512 )) { +DEBUG_MSG ("\n" ); +DEBUG_MSG ("PAE : ON\n" ); + vt.mem_flags |=MEMORY_X86_PAE ; + info->max_physmem_bits = _MAX_PHYSMEM_BITS_PAE; + }else { +DEBUG_MSG ("\n" ); +DEBUG_MSG ("PAE : OFF\n" ); + info->max_physmem_bits = _MAX_PHYSMEM_BITS; + } } + info->page_offset = __PAGE_OFFSET;if (SYMBOL (_stext) ==NOT_FOUND_SYMBOL ) {
arch/x86_64.c +16 -11
@@ -259,17 +259,22 @@ get_machdep_info_x86_64(void)int get_versiondep_info_x86_64 (void ) { -/* -* On linux-2.6.26, MAX_PHYSMEM_BITS is changed to 44 from 40. -*/ -if (info->kernel_version <KERNEL_VERSION (2 ,6 ,26 )) - info->max_physmem_bits = _MAX_PHYSMEM_BITS_ORIG; -else if (info->kernel_version <KERNEL_VERSION (2 ,6 ,31 )) - info->max_physmem_bits = _MAX_PHYSMEM_BITS_2_6_26; -else if (check_5level_paging ()) - info->max_physmem_bits = _MAX_PHYSMEM_BITS_5LEVEL; -else - info->max_physmem_bits = _MAX_PHYSMEM_BITS_2_6_31; +/* Check if we can get MAX_PHYSMEM_BITS from vmcoreinfo */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) { + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); + }else { +/* +* On linux-2.6.26, MAX_PHYSMEM_BITS is changed to 44 from 40. +*/ +if (info->kernel_version <KERNEL_VERSION (2 ,6 ,26 )) + info->max_physmem_bits = _MAX_PHYSMEM_BITS_ORIG; +else if (info->kernel_version <KERNEL_VERSION (2 ,6 ,31 )) + info->max_physmem_bits = _MAX_PHYSMEM_BITS_2_6_26; +else if (check_5level_paging ()) + info->max_physmem_bits = _MAX_PHYSMEM_BITS_5LEVEL; +else + info->max_physmem_bits = _MAX_PHYSMEM_BITS_2_6_31; + }if (!get_page_offset_x86_64 ())return FALSE;
Signature · 7 lines
2.7.4 _______________________________________________ kexec mailing list [email protected] http://lists.infradead.org/mailman/listinfo/kexec
PATCH v3 2/3 makedumpfile/arm64: Add support for ARMv8.2-LPA (52-bit PA support)
In reply to Bhupesh SharmaARMv8.2-LPA architecture extension (if available on underlying hardware) can support 52-bit physical addresses, while the kernel virtual addresses remain 48-bit.
This patch is in accordance with ARMv8 Architecture Reference Manual version D.a
Make sure that we read the 52-bit PA address capability from 'MAX_PHYSMEM_BITS' variable (if available in vmcoreinfo) and accordingly change the pte_to_phy() mask values and also traverse the page-table walk accordingly.
Also make sure that it works well for the existing 48-bit PA address platforms and also on environments which use newer kernels with 52-bit PA support but hardware which is not ARM8.2-LPA compliant.
I have sent a kernel patch upstream to add 'MAX_PHYSMEM_BITS' to vmcoreinfo for arm64 (see [0]).
[0]. http://lists.infradead.org/pipermail/kexec/2019-February/022411.html
--- arch/arm64.c | 292 +++++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 204 insertions(+), 88 deletions(-)
arch/arm64.c +204 -88
@@ -39,72 +39,184 @@ typedef struct {unsigned long pte; } pte_t; +#define __pte (x) ((pte_t) { (x) } ) +#define __pmd (x) ((pmd_t) { (x) } ) +#define __pud (x) ((pud_t) { (x) } ) +#define __pgd (x) ((pgd_t) { (x) } ) + +static int lpa_52_bit_support_available;static int pgtable_level;static int va_bits;static unsigned long kimage_voffset; -#define SZ_4K (4 * 1024) -#define SZ_16K (16 * 1024) -#define SZ_64K (64 * 1024) -#define SZ_128M (128 * 1024 * 1024) +#define SZ_4K 4096 +#define SZ_16K 16384 +#define SZ_64K 65536 -#define PAGE_OFFSET_36 ((0xffffffffffffffffUL) << 36) -#define PAGE_OFFSET_39 ((0xffffffffffffffffUL) << 39) -#define PAGE_OFFSET_42 ((0xffffffffffffffffUL) << 42) -#define PAGE_OFFSET_47 ((0xffffffffffffffffUL) << 47) -#define PAGE_OFFSET_48 ((0xffffffffffffffffUL) << 48) +#define PAGE_OFFSET_36 ((0xffffffffffffffffUL) << 36) +#define PAGE_OFFSET_39 ((0xffffffffffffffffUL) << 39) +#define PAGE_OFFSET_42 ((0xffffffffffffffffUL) << 42) +#define PAGE_OFFSET_47 ((0xffffffffffffffffUL) << 47) +#define PAGE_OFFSET_48 ((0xffffffffffffffffUL) << 48) +#define PAGE_OFFSET_52 ((0xffffffffffffffffUL) << 52)#define pgd_val (x) ((x).pgd)#define pud_val (x) (pgd_val((x).pgd))#define pmd_val (x) (pud_val((x).pud))#define pte_val (x) ((x).pte) -#define PAGE_MASK (~(PAGESIZE() - 1)) -#define PGDIR_SHIFT ((PAGESHIFT() - 3) * pgtable_level + 3) -#define PTRS_PER_PGD (1 << (va_bits - PGDIR_SHIFT)) -#define PUD_SHIFT get_pud_shift_arm64() -#define PUD_SIZE (1UL << PUD_SHIFT) -#define PUD_MASK (~(PUD_SIZE - 1)) -#define PTRS_PER_PTE (1 << (PAGESHIFT() - 3)) -#define PTRS_PER_PUD PTRS_PER_PTE -#define PMD_SHIFT ((PAGESHIFT() - 3) * 2 + 3) -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE - 1)) +/* See 'include/uapi/linux/const.h' for definitions below */ +#define __AC (X ,Y ) (X##Y) +#define _AC (X ,Y ) __AC(X,Y) +#define _AT (T ,X ) ((T)(X)) + +/* See 'include/asm/pgtable-types.h' for definitions below */ +typedef unsigned long pteval_t ; +typedef unsigned long pmdval_t ; +typedef unsigned long pudval_t ; +typedef unsigned long pgdval_t ; + +#define PAGE_SHIFT PAGESHIFT() + +/* See 'arch/arm64/include/asm/pgtable-hwdef.h' for definitions below */ + +#define ARM64_HW_PGTABLE_LEVEL_SHIFT (n) ((PAGE_SHIFT - 3) * (4 - (n)) + 3) + +#define PTRS_PER_PTE (1 << (PAGE_SHIFT - 3)) + +/* +* PMD_SHIFT determines the size a level 2 page table entry can map. +*/ +#define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2) +#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1))#define PTRS_PER_PMD PTRS_PER_PTE -#define PAGE_PRESENT (1 << 0) +/* +* PUD_SHIFT determines the size a level 1 page table entry can map. +*/ +#define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1) +#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) +#define PTRS_PER_PUD PTRS_PER_PTE + +/* +* PGDIR_SHIFT determines the size a top-level page table entry can map +* (depending on the configuration, this level can be 0, 1 or 2). +*/ +#define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (pgtable_level)) +#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) +#define PTRS_PER_PGD (1 << ((va_bits) - PGDIR_SHIFT)) + +/* +* Section address mask and size definitions. +*/ #define SECTIONS_SIZE_BITS 30 -/* Highest possible physical address supported */ -#define PHYS_MASK_SHIFT 48 -#define PHYS_MASK ((1UL << PHYS_MASK_SHIFT) - 1) +/* -* Remove the highest order bits that are not a part of the -* physical address in a section +* Hardware page table definitions. +* +* Level 1 descriptor (PUD). */ -#define PMD_SECTION_MASK ((1UL << 40) - 1) +#define PUD_TYPE_TABLE (_AT(pudval_t, 3) << 0) +#define PUD_TABLE_BIT (_AT(pudval_t, 1) << 1) +#define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0) +#define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0) -#define PMD_TYPE_MASK 3 -#define PMD_TYPE_SECT 1 -#define PMD_TYPE_TABLE 3 +/* +* Level 2 descriptor (PMD). +*/ +#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) +#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) +#define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) +#define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0) +#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1) + +/* +* Level 3 descriptor (PTE). +*/ +#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) +#define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12) + +static inline unsigned long +get_pte_addr_mask_arm64 (void ) +{ +if (lpa_52_bit_support_available) +return (PTE_ADDR_LOW |PTE_ADDR_HIGH ); +else +return PTE_ADDR_LOW ; +} + +#define PTE_ADDR_MASK get_pte_addr_mask_arm64() -#define PUD_TYPE_MASK 3 -#define PUD_TYPE_SECT 1 -#define PUD_TYPE_TABLE 3 +#define PAGE_MASK (~(PAGESIZE() - 1)) +#define PAGE_PRESENT (1 << 0) +/* Helper API to convert between a physical address and its placement +* in a page table entry, taking care of 52-bit addresses. +*/ +static inline unsigned long +__pte_to_phys (pte_t pte) +{ +if (lpa_52_bit_support_available) +return ((pte_val (pte) &PTE_ADDR_LOW ) | ((pte_val (pte) &PTE_ADDR_HIGH ) <<36 )); +else +return (pte_val (pte) &PTE_ADDR_MASK ); +} + +/* Find an entry in a page-table-directory */ #define pgd_index (vaddr) (((vaddr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) -#define pgd_offset (pgdir, vaddr) ((pgd_t *)(pgdir) + pgd_index(vaddr)) -#define pte_index (vaddr) (((vaddr) >> PAGESHIFT()) & (PTRS_PER_PTE - 1)) -#define pmd_page_paddr (pmd) (pmd_val(pmd) & PHYS_MASK & (int32_t)PAGE_MASK) -#define pte_offset (dir, vaddr) ((pte_t*)pmd_page_paddr((*dir)) + pte_index(vaddr)) +static inline pte_t +pgd_pte (pgd_t pgd) +{ +return __pte (pgd_val (pgd)); +} -#define pmd_index (vaddr) (((vaddr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -#define pud_page_paddr (pud) (pud_val(pud) & PHYS_MASK & (int32_t)PAGE_MASK) -#define pmd_offset_pgtbl_lvl_2 (pud, vaddr) ((pmd_t *)pud) -#define pmd_offset_pgtbl_lvl_3 (pud, vaddr) ((pmd_t *)pud_page_paddr((*pud)) + pmd_index(vaddr)) +#define __pgd_to_phys (pgd) __pte_to_phys(pgd_pte(pgd)) +#define pgd_offset (pgd, vaddr) ((pgd_t *)(pgd) + pgd_index(vaddr)) + +static inline pte_t pud_pte (pud_t pud) +{ +return __pte (pud_val (pud)); +} +static inline unsigned long +pgd_page_paddr (pgd_t pgd) +{ +return __pgd_to_phys (pgd); +} + +/* Find an entry in the first-level page table. */ #define pud_index (vaddr) (((vaddr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -#define pgd_page_paddr (pgd) (pgd_val(pgd) & PHYS_MASK & (int32_t)PAGE_MASK) +#define __pud_to_phys (pud) __pte_to_phys(pud_pte(pud)) + +static inline unsigned long +pud_page_paddr (pud_t pud) +{ +return __pud_to_phys (pud); +} + +/* Find an entry in the second-level page table. */ +#define pmd_index (vaddr) (((vaddr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) + +static inline pte_t pmd_pte (pmd_t pmd) +{ +return __pte (pmd_val (pmd)); +} + +#define __pmd_to_phys (pmd) __pte_to_phys(pmd_pte(pmd)) + +static inline unsigned long +pmd_page_paddr (pmd_t pmd) +{ +return __pmd_to_phys (pmd); +} + +/* Find an entry in the third-level page table. */ +#define pte_index (vaddr) (((vaddr) >> PAGESHIFT()) & (PTRS_PER_PTE - 1)) +#define pte_offset (dir, vaddr) (pmd_page_paddr((*dir)) + pte_index(vaddr) * sizeof(pte_t))static unsigned long long __pa (unsigned long vaddr)
@@ -116,32 +228,22 @@ __pa(unsigned long vaddr)return (vaddr - kimage_voffset); } -static int -get_pud_shift_arm64 (void ) +static pud_t * +pud_offset (pgd_t *pgda,pgd_t *pgdv,unsigned long vaddr) { -if (pgtable_level ==4 ) -return ((PAGESHIFT () -3 ) *3 +3 ); +if (pgtable_level >3 ) +return (pud_t *)(pgd_page_paddr (*pgdv) +pud_index (vaddr) *sizeof (pud_t));else -return PGDIR_SHIFT ; +return (pud_t *)(pgda); }static pmd_t *pmd_offset (pud_t *puda,pud_t *pudv,unsigned long vaddr) { -if (pgtable_level ==2 ) { -return pmd_offset_pgtbl_lvl_2 (puda, vaddr); - }else { -return pmd_offset_pgtbl_lvl_3 (pudv, vaddr); - } -} - -static pud_t * -pud_offset (pgd_t *pgda,pgd_t *pgdv,unsigned long vaddr) -{ -if (pgtable_level ==4 ) -return ((pud_t *)pgd_page_paddr ((*pgdv)) +pud_index (vaddr)); +if (pgtable_level >2 ) +return (pmd_t *)(pud_page_paddr (*pudv) +pmd_index (vaddr) *sizeof (pmd_t));else -return (pud_t *)(pgda); +return (pmd_t *)(puda); }static int calculate_plat_config (void )
@@ -287,6 +389,14 @@ get_stext_symbol(void)int get_machdep_info_arm64 (void ) { +/* Determine if the PA address range is 52-bits: ARMv8.2-LPA */ +if (NUMBER (MAX_PHYSMEM_BITS ) !=NOT_FOUND_NUMBER ) { + info->max_physmem_bits =NUMBER (MAX_PHYSMEM_BITS ); +if (info->max_physmem_bits ==52 ) + lpa_52_bit_support_available =1 ; + }else + info->max_physmem_bits =48 ; +/* Check if va_bits is still not initialized. If still 0, call * get_versiondep_info() to initialize the same. */
@@ -299,12 +409,11 @@ get_machdep_info_arm64(void) } kimage_voffset =NUMBER (kimage_voffset); - info->max_physmem_bits =PHYS_MASK_SHIFT ; info->section_size_bits =SECTIONS_SIZE_BITS ;DEBUG_MSG ("kimage_voffset : %lx\n" , kimage_voffset); -DEBUG_MSG ("max_physmem_bits : %lx\n" , info->max_physmem_bits); -DEBUG_MSG ("section_size_bits: %lx\n" , info->section_size_bits); +DEBUG_MSG ("max_physmem_bits : %ld\n" , info->max_physmem_bits); +DEBUG_MSG ("section_size_bits: %ld\n" , info->section_size_bits);return TRUE; }
@@ -362,6 +471,19 @@ get_versiondep_info_arm64(void)return TRUE; } +/* 1GB section for Page Table level = 4 and Page Size = 4KB */ +static int +is_pud_sect (pud_t pud) +{ +return ((pud_val (pud) &PUD_TYPE_MASK ) ==PUD_TYPE_SECT ); +} + +static int +is_pmd_sect (pmd_t pmd) +{ +return ((pmd_val (pmd) &PMD_TYPE_MASK ) ==PMD_TYPE_SECT ); +} +/* * vaddr_to_paddr_arm64() - translate arbitrary virtual address to physical * @vaddr: virtual address to translate
@@ -399,10 +521,9 @@ vaddr_to_paddr_arm64(unsigned long vaddr)return NOT_PADDR ; } -if ((pud_val (pudv) &PUD_TYPE_MASK ) ==PUD_TYPE_SECT ) { -/* 1GB section for Page Table level = 4 and Page Size = 4KB */ - paddr = (pud_val (pudv) & (PUD_MASK &PMD_SECTION_MASK )) - + (vaddr & (PUD_SIZE -1 )); +if (is_pud_sect (pudv)) { + paddr = (pud_page_paddr (pudv) &PUD_MASK ) + + (vaddr & (PUD_SIZE -1 ));return paddr; }
@@ -412,29 +533,24 @@ vaddr_to_paddr_arm64(unsigned long vaddr)return NOT_PADDR ; } -switch (pmd_val (pmdv) &PMD_TYPE_MASK ) { -case PMD_TYPE_TABLE : - ptea =pte_offset (&pmdv, vaddr); -/* 64k page */ -if (!readmem (PADDR , (unsigned long long )ptea, &ptev,sizeof (ptev))) { -ERRMSG ("Can't read pte\n" ); -return NOT_PADDR ; - } +if (is_pmd_sect (pmdv)) { + paddr = (pmd_page_paddr (pmdv) &PMD_MASK ) + + (vaddr & (PMD_SIZE -1 )); +return paddr; + } -if (!(pte_val (ptev) &PAGE_PRESENT )) { -ERRMSG ("Can't get a valid pte.\n" ); -return NOT_PADDR ; - }else { + ptea = (pte_t *)pte_offset (&pmdv, vaddr); +if (!readmem (PADDR , (unsigned long long )ptea, &ptev,sizeof (ptev))) { +ERRMSG ("Can't read pte\n" ); +return NOT_PADDR ; + } - paddr = (PAGEBASE (pte_val (ptev)) &PHYS_MASK ) - + (vaddr & (PAGESIZE () -1 )); - } -break ; -case PMD_TYPE_SECT : -/* 512MB section for Page Table level = 3 and Page Size = 64KB*/ - paddr = (pmd_val (pmdv) & (PMD_MASK &PMD_SECTION_MASK )) - + (vaddr & (PMD_SIZE -1 )); -break ; +if (!(pte_val (ptev) &PAGE_PRESENT )) { +ERRMSG ("Can't get a valid pte.\n" ); +return NOT_PADDR ; + }else { + paddr =__pte_to_phys (ptev) + + (vaddr & (PAGESIZE () -1 )); }return paddr;
Signature · 7 lines
2.7.4 _______________________________________________ kexec mailing list [email protected] http://lists.infradead.org/mailman/listinfo/kexec
PATCH v3 3/3 makedumpfile/arm64: Add support for ARMv8.2-LVA (52-bit user-space VA support)
In reply to Bhupesh SharmaWith ARMv8.2-LVA architecture extension availability, arm64 hardware which supports this extension can support upto 52-bit virtual addresses. It is specially useful for having a 52-bit user-space virtual address space while the kernel can still retain 48-bit virtual addresses.
Since at the moment we enable the support of this extension in the kernel via a CONFIG flag (CONFIG_ARM64_USER_VA_BITS_52), so there are no clear mechanisms in user-space to determine this CONFIG flag value and use it to determine the user-space VA address range values.
'makedumpfile' can instead use 'MAX_USER_VA_BITS' value to determine the maximum virtual physical address supported by user-space. If 'MAX_USER_VA_BITS' value is greater than 'VA_BITS' than we are running a use-case where user-space is 52-bit and underlying kernel is still 48-bit. The increased 'PTRS_PER_PGD' value for such cases can then be calculated as is done by the underlying kernel (see kernel file 'arch/arm64/include/asm/pgtable-hwdef.h' for details):
#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT))
I have sent a kernel patch upstream to add 'MAX_USER_VA_BITS' to vmcoreinfo for arm64 (see [0]).
This patch is in accordance with ARMv8 Architecture Reference Manual version D.a
[0].
http://lists.infradead.org/pipermail/kexec/2019-February/022411.html
--- arch/arm64.c | 106 +++++++++++++++++++++++++++++++++++++++++---------------- makedumpfile.c | 2 ++ makedumpfile.h | 1 + 3 files changed, 79 insertions(+), 30 deletions(-)
arch/arm64.c +76 -30
@@ -47,6 +47,7 @@ typedef struct {static int lpa_52_bit_support_available;static int pgtable_level;static int va_bits; +static int ptrs_per_pgd;static unsigned long kimage_voffset;#define SZ_4K 4096
@@ -107,7 +108,6 @@ typedef unsigned long pgdval_t;#define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (pgtable_level))#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)#define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << ((va_bits) - PGDIR_SHIFT))/* * Section address mask and size definitions.
@@ -166,7 +166,7 @@ __pte_to_phys(pte_t pte) }/* Find an entry in a page-table-directory */ -#define pgd_index (vaddr) (((vaddr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) +#define pgd_index (vaddr) (((vaddr) >> PGDIR_SHIFT) & (ptrs_per_pgd - 1))static inline pte_t pgd_pte (pgd_t pgd)
@@ -386,6 +386,46 @@ get_stext_symbol(void)return (found ? kallsym : FALSE); } +static int +get_va_bits_from_stext_arm64 (void ) +{ +ulong _stext; + + _stext =get_stext_symbol (); +if (!_stext) { +ERRMSG ("Can't get the symbol of _stext.\n" ); +return FALSE; + } + +/* Derive va_bits as per arch/arm64/Kconfig */ +if ((_stext &PAGE_OFFSET_36 ) ==PAGE_OFFSET_36 ) { + va_bits =36 ; + }else if ((_stext &PAGE_OFFSET_39 ) ==PAGE_OFFSET_39 ) { + va_bits =39 ; + }else if ((_stext &PAGE_OFFSET_42 ) ==PAGE_OFFSET_42 ) { + va_bits =42 ; + }else if ((_stext &PAGE_OFFSET_47 ) ==PAGE_OFFSET_47 ) { + va_bits =47 ; + }else if ((_stext &PAGE_OFFSET_48 ) ==PAGE_OFFSET_48 ) { + va_bits =48 ; + }else { +ERRMSG ("Cannot find a proper _stext for calculating VA_BITS\n" ); +return FALSE; + } + +DEBUG_MSG ("va_bits : %d (_stext)\n" , va_bits); + +return TRUE; +} + +static void +get_page_offset_arm64 (void ) +{ + info->page_offset = (0xffffffffffffffffUL ) << (va_bits -1 ); + +DEBUG_MSG ("page_offset : %lx\n" , info->page_offset); +} +int get_machdep_info_arm64 (void ) {
@@ -400,8 +440,37 @@ get_machdep_info_arm64(void)/* Check if va_bits is still not initialized. If still 0, call * get_versiondep_info() to initialize the same. */ +if (NUMBER (VA_BITS ) !=NOT_FOUND_NUMBER ) { + va_bits =NUMBER (VA_BITS ); +DEBUG_MSG ("va_bits : %d (vmcoreinfo)\n" , + va_bits); + } + +/* Check if va_bits is still not initialized. If still 0, call +* get_versiondep_info() to initialize the same from _stext +* symbol. +*/ if (!va_bits) -get_versiondep_info_arm64 (); +if (get_va_bits_from_stext_arm64 () == FALSE) +return FALSE; + +get_page_offset_arm64 (); + +if (NUMBER (PTRS_PER_PGD ) !=NOT_FOUND_NUMBER ) { + ptrs_per_pgd =NUMBER (PTRS_PER_PGD ); +DEBUG_MSG ("ptrs_per_pgd : %d (vmcoreinfo)\n" , + ptrs_per_pgd); + } + +/* Check if ptrs_per_pgd is still not initialized. +* If still 0, its not available in vmcoreinfo and its +* safe to initialize it with va_bits. +*/ +if (!ptrs_per_pgd) { + ptrs_per_pgd = (1 << ((va_bits) -PGDIR_SHIFT )); +DEBUG_MSG ("ptrs_per_pgd : %d (default)\n" , + ptrs_per_pgd); + }if (!calculate_plat_config ()) {ERRMSG ("Can't determine platform config values\n" );
@@ -439,34 +508,11 @@ get_xen_info_arm64(void)int get_versiondep_info_arm64 (void ) { -ulong _stext; - - _stext =get_stext_symbol (); -if (!_stext) { -ERRMSG ("Can't get the symbol of _stext.\n" ); -return FALSE; - } - -/* Derive va_bits as per arch/arm64/Kconfig */ -if ((_stext &PAGE_OFFSET_36 ) ==PAGE_OFFSET_36 ) { - va_bits =36 ; - }else if ((_stext &PAGE_OFFSET_39 ) ==PAGE_OFFSET_39 ) { - va_bits =39 ; - }else if ((_stext &PAGE_OFFSET_42 ) ==PAGE_OFFSET_42 ) { - va_bits =42 ; - }else if ((_stext &PAGE_OFFSET_47 ) ==PAGE_OFFSET_47 ) { - va_bits =47 ; - }else if ((_stext &PAGE_OFFSET_48 ) ==PAGE_OFFSET_48 ) { - va_bits =48 ; - }else { -ERRMSG ("Cannot find a proper _stext for calculating VA_BITS\n" ); -return FALSE; - } - - info->page_offset = (0xffffffffffffffffUL ) << (va_bits -1 ); +if (!va_bits) +if (get_va_bits_from_stext_arm64 () == FALSE) +return FALSE; -DEBUG_MSG ("va_bits : %d\n" , va_bits); -DEBUG_MSG ("page_offset : %lx\n" , info->page_offset); +get_page_offset_arm64 ();return TRUE; }
makedumpfile.c +2 -0
@@ -2291,6 +2291,7 @@ write_vmcoreinfo_data(void)WRITE_NUMBER ("HUGETLB_PAGE_DTOR" ,HUGETLB_PAGE_DTOR );#ifdef __aarch64__ +WRITE_NUMBER ("PTRS_PER_PGD" ,PTRS_PER_PGD );WRITE_NUMBER ("VA_BITS" ,VA_BITS );WRITE_NUMBER_UNSIGNED ("PHYS_OFFSET" ,PHYS_OFFSET );WRITE_NUMBER_UNSIGNED ("kimage_voffset" , kimage_voffset);
@@ -2694,6 +2695,7 @@ read_vmcoreinfo(void)READ_NUMBER ("PAGE_BUDDY_MAPCOUNT_VALUE" ,PAGE_BUDDY_MAPCOUNT_VALUE );READ_NUMBER ("phys_base" , phys_base);#ifdef __aarch64__ +READ_NUMBER ("PTRS_PER_PGD" ,PTRS_PER_PGD );READ_NUMBER ("VA_BITS" ,VA_BITS );READ_NUMBER_UNSIGNED ("PHYS_OFFSET" ,PHYS_OFFSET );READ_NUMBER_UNSIGNED ("kimage_voffset" , kimage_voffset);
makedumpfile.h +1 -0
@@ -1933,6 +1933,7 @@ struct number_table {long HUGETLB_PAGE_DTOR ;long phys_base;#ifdef __aarch64__ +long PTRS_PER_PGD ;long VA_BITS ;unsigned long PHYS_OFFSET ;unsigned long kimage_voffset;
Signature · 7 lines
2.7.4 _______________________________________________ kexec mailing list [email protected] http://lists.infradead.org/mailman/listinfo/kexec