| Message ID | 1460182444-2468-19-git-send-email-aneesh.kumar@linux.vnet.ibm.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
On 09/04/16 16:13, Aneesh Kumar K.V wrote: > This patch reduce #ifdef in C code and also help in adding radix changes > later. Only code movement in this patch. > > Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> > --- > arch/powerpc/mm/Makefile | 3 +- > arch/powerpc/mm/init_64.c | 74 ++-------------------- > arch/powerpc/mm/pgtable-book3e.c | 128 +++++++++++++++++++++++++++++++++++++++ > arch/powerpc/mm/pgtable-hash64.c | 100 ++++++++++++++++++++++++++++++ > arch/powerpc/mm/pgtable_64.c | 83 ------------------------- > 5 files changed, 235 insertions(+), 153 deletions(-) > create mode 100644 arch/powerpc/mm/pgtable-book3e.c > create mode 100644 arch/powerpc/mm/pgtable-hash64.c > > diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile > index adfee3f1aeb9..ef778997daa9 100644 > --- a/arch/powerpc/mm/Makefile > +++ b/arch/powerpc/mm/Makefile > @@ -13,7 +13,8 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ > tlb_nohash_low.o > obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o > hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o > -obj-$(CONFIG_PPC_STD_MMU_64) += hash_utils_64.o slb_low.o slb.o $(hash64-y) > +obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o > +obj-$(CONFIG_PPC_STD_MMU_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) > obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o > obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o \ > mmu_context_hash$(CONFIG_WORD_SIZE).o > diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c > index ba655666186d..8d1daf7d9785 100644 > --- a/arch/powerpc/mm/init_64.c > +++ b/arch/powerpc/mm/init_64.c > @@ -189,75 +189,6 @@ static int __meminit vmemmap_populated(unsigned long start, int page_size) > return 0; > } > > -/* On hash-based CPUs, the vmemmap is bolted in the hash table. > - * > - * On Book3E CPUs, the vmemmap is currently mapped in the top half of > - * the vmalloc space using normal page tables, though the size of > - * pages encoded in the PTEs can be different > - */ > - > -#ifdef CONFIG_PPC_BOOK3E > -static int __meminit vmemmap_create_mapping(unsigned long start, > - unsigned long page_size, > - unsigned long phys) > -{ > - /* Create a PTE encoding without page size */ > - unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED | > - _PAGE_KERNEL_RW; > - > - /* PTEs only contain page size encodings up to 32M */ > - BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf); > - > - /* Encode the size in the PTE */ > - flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8; > - > - /* For each PTE for that area, map things. Note that we don't > - * increment phys because all PTEs are of the large size and > - * thus must have the low bits clear > - */ > - for (i = 0; i < page_size; i += PAGE_SIZE) > - BUG_ON(map_kernel_page(start + i, phys, flags)); > - > - return 0; > -} > - > -#ifdef CONFIG_MEMORY_HOTPLUG > -static void vmemmap_remove_mapping(unsigned long start, > - unsigned long page_size) > -{ > -} > -#endif > -#else /* CONFIG_PPC_BOOK3E */ > -static int __meminit vmemmap_create_mapping(unsigned long start, > - unsigned long page_size, > - unsigned long phys) > -{ > - int rc = htab_bolt_mapping(start, start + page_size, phys, > - pgprot_val(PAGE_KERNEL), > - mmu_vmemmap_psize, mmu_kernel_ssize); > - if (rc < 0) { > - int rc2 = htab_remove_mapping(start, start + page_size, > - mmu_vmemmap_psize, > - mmu_kernel_ssize); > - BUG_ON(rc2 && (rc2 != -ENOENT)); > - } > - return rc; > -} > - > -#ifdef CONFIG_MEMORY_HOTPLUG > -static void vmemmap_remove_mapping(unsigned long start, > - unsigned long page_size) > -{ > - int rc = htab_remove_mapping(start, start + page_size, > - mmu_vmemmap_psize, > - mmu_kernel_ssize); > - BUG_ON((rc < 0) && (rc != -ENOENT)); > - WARN_ON(rc == -ENOENT); > -} > -#endif > - > -#endif /* CONFIG_PPC_BOOK3E */ > - > struct vmemmap_backing *vmemmap_list; > static struct vmemmap_backing *next; > static int num_left; > @@ -309,6 +240,9 @@ static __meminit void vmemmap_list_populate(unsigned long phys, > vmemmap_list = vmem_back; > } > > +extern int __meminit vmemmap_create_mapping(unsigned long start, > + unsigned long page_size, > + unsigned long phys); > int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) > { > unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; > @@ -347,6 +281,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) > } > > #ifdef CONFIG_MEMORY_HOTPLUG > +extern void vmemmap_remove_mapping(unsigned long start, > + unsigned long page_size); > static unsigned long vmemmap_list_free(unsigned long start) > { > struct vmemmap_backing *vmem_back, *vmem_back_prev; > diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/pgtable-book3e.c > new file mode 100644 > index 000000000000..f75ba4142875 > --- /dev/null > +++ b/arch/powerpc/mm/pgtable-book3e.c > @@ -0,0 +1,128 @@ > + > +/* > + * Copyright IBM Corporation, 2015 > + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> > + * You may want to retain the copyrights from the original file as well > + * This program is free software; you can redistribute it and/or modify it > + * under the terms of version 2 of the GNU Lesser General Public License > + * as published by the Free Software Foundation. > + * > + * This program is distributed in the hope that it would be useful, but > + * WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. > + * > + */ > + > +/* > + * PPC64 THP Support for hash based MMUs > + */ > +#include <linux/sched.h> > +#include <linux/memblock.h> > +#include <asm/pgalloc.h> > +#include <asm/tlb.h> > +#include <asm/dma.h> > + > +#include "mmu_decl.h" > + > +#ifdef CONFIG_SPARSEMEM_VMEMMAP > +/* > + * On Book3E CPUs, the vmemmap is currently mapped in the top half of > + * the vmalloc space using normal page tables, though the size of > + * pages encoded in the PTEs can be different > + */ > +int __meminit vmemmap_create_mapping(unsigned long start, > + unsigned long page_size, > + unsigned long phys) > +{ > + /* Create a PTE encoding without page size */ > + unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED | > + _PAGE_KERNEL_RW; > + > + /* PTEs only contain page size encodings up to 32M */ > + BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf); > + > + /* Encode the size in the PTE */ > + flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8; > + > + /* For each PTE for that area, map things. Note that we don't > + * increment phys because all PTEs are of the large size and > + * thus must have the low bits clear > + */ > + for (i = 0; i < page_size; i += PAGE_SIZE) > + BUG_ON(map_kernel_page(start + i, phys, flags)); > + > + return 0; > +} > + > +#ifdef CONFIG_MEMORY_HOTPLUG > +void vmemmap_remove_mapping(unsigned long start, > + unsigned long page_size) > +{ > +} > +#endif > +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ > + > +static __ref void *early_alloc_pgtable(unsigned long size) > +{ > + void *pt; > + > + pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); > + memset(pt, 0, size); > + > + return pt; > +} > + > +/* > + * map_kernel_page currently only called by __ioremap > + * map_kernel_page adds an entry to the ioremap page table > + * and adds an entry to the HPT, possibly bolting it > + */ > +int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) > +{ > + pgd_t *pgdp; > + pud_t *pudp; > + pmd_t *pmdp; > + pte_t *ptep; > + > + if (slab_is_available()) { > + pgdp = pgd_offset_k(ea); > + pudp = pud_alloc(&init_mm, pgdp, ea); > + if (!pudp) > + return -ENOMEM; > + pmdp = pmd_alloc(&init_mm, pudp, ea); > + if (!pmdp) > + return -ENOMEM; > + ptep = pte_alloc_kernel(pmdp, ea); > + if (!ptep) > + return -ENOMEM; > + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, > + __pgprot(flags))); > + } else { > + pgdp = pgd_offset_k(ea); > +#ifndef __PAGETABLE_PUD_FOLDED > + if (pgd_none(*pgdp)) { > + pudp = early_alloc_pgtable(PUD_TABLE_SIZE); > + BUG_ON(pudp == NULL); > + pgd_populate(&init_mm, pgdp, pudp); > + } > +#endif /* !__PAGETABLE_PUD_FOLDED */ > + pudp = pud_offset(pgdp, ea); > + if (pud_none(*pudp)) { > + pmdp = early_alloc_pgtable(PMD_TABLE_SIZE); > + BUG_ON(pmdp == NULL); > + pud_populate(&init_mm, pudp, pmdp); > + } > + pmdp = pmd_offset(pudp, ea); > + if (!pmd_present(*pmdp)) { > + ptep = early_alloc_pgtable(PAGE_SIZE); > + BUG_ON(ptep == NULL); > + pmd_populate_kernel(&init_mm, pmdp, ptep); > + } > + ptep = pte_offset_kernel(pmdp, ea); > + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, > + __pgprot(flags))); > + } > + > + smp_wmb(); > + return 0; > +} > diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c > new file mode 100644 > index 000000000000..04d6fa12789e > --- /dev/null > +++ b/arch/powerpc/mm/pgtable-hash64.c > @@ -0,0 +1,100 @@ > +/* > + * Copyright IBM Corporation, 2015 > + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> > + * Same as before > + * This program is free software; you can redistribute it and/or modify it > + * under the terms of version 2 of the GNU Lesser General Public License > + * as published by the Free Software Foundation. > + * > + * This program is distributed in the hope that it would be useful, but > + * WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. > + * > + */ > + > +/* > + * PPC64 THP Support for hash based MMUs > + */ > +#include <linux/sched.h> > +#include <asm/pgalloc.h> > +#include <asm/tlb.h> > + > +#include "mmu_decl.h" > + > +#ifdef CONFIG_SPARSEMEM_VMEMMAP > +/* > + * On hash-based CPUs, the vmemmap is bolted in the hash table. > + * > + */ > +int __meminit vmemmap_create_mapping(unsigned long start, > + unsigned long page_size, > + unsigned long phys) > +{ > + int rc = htab_bolt_mapping(start, start + page_size, phys, > + pgprot_val(PAGE_KERNEL), > + mmu_vmemmap_psize, mmu_kernel_ssize); > + if (rc < 0) { > + int rc2 = htab_remove_mapping(start, start + page_size, > + mmu_vmemmap_psize, > + mmu_kernel_ssize); > + BUG_ON(rc2 && (rc2 != -ENOENT)); > + } > + return rc; > +} > + > +#ifdef CONFIG_MEMORY_HOTPLUG > +void vmemmap_remove_mapping(unsigned long start, > + unsigned long page_size) > +{ > + int rc = htab_remove_mapping(start, start + page_size, > + mmu_vmemmap_psize, > + mmu_kernel_ssize); > + BUG_ON((rc < 0) && (rc != -ENOENT)); > + WARN_ON(rc == -ENOENT); > +} > +#endif > +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ > + > +/* > + * map_kernel_page currently only called by __ioremap > + * map_kernel_page adds an entry to the ioremap page table > + * and adds an entry to the HPT, possibly bolting it > + */ > +int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) > +{ > + pgd_t *pgdp; > + pud_t *pudp; > + pmd_t *pmdp; > + pte_t *ptep; > + > + if (slab_is_available()) { > + pgdp = pgd_offset_k(ea); > + pudp = pud_alloc(&init_mm, pgdp, ea); > + if (!pudp) > + return -ENOMEM; > + pmdp = pmd_alloc(&init_mm, pudp, ea); > + if (!pmdp) > + return -ENOMEM; > + ptep = pte_alloc_kernel(pmdp, ea); > + if (!ptep) > + return -ENOMEM; > + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, > + __pgprot(flags))); > + } else { > + /* > + * If the mm subsystem is not fully up, we cannot create a > + * linux page table entry for this mapping. Simply bolt an > + * entry in the hardware page table. > + * > + */ > + if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, > + mmu_io_psize, mmu_kernel_ssize)) { > + printk(KERN_ERR "Failed to do bolted mapping IO " > + "memory at %016lx !\n", pa); > + return -ENOMEM; What happens when we do unmap this? I know this code has been around for a while so its not new > + } > + } > + > + smp_wmb(); > + return 0; > +} > diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c > index 5fff787da17a..d493f62d12eb 100644 > --- a/arch/powerpc/mm/pgtable_64.c > +++ b/arch/powerpc/mm/pgtable_64.c > @@ -78,89 +78,6 @@ struct patb_entry *partition_tb; > #endif > unsigned long ioremap_bot = IOREMAP_BASE; > > -#ifdef CONFIG_PPC_MMU_NOHASH > -static __ref void *early_alloc_pgtable(unsigned long size) > -{ > - void *pt; > - > - pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); > - memset(pt, 0, size); > - > - return pt; > -} > -#endif /* CONFIG_PPC_MMU_NOHASH */ > - > -/* > - * map_kernel_page currently only called by __ioremap > - * map_kernel_page adds an entry to the ioremap page table > - * and adds an entry to the HPT, possibly bolting it > - */ > -int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) > -{ > - pgd_t *pgdp; > - pud_t *pudp; > - pmd_t *pmdp; > - pte_t *ptep; > - > - if (slab_is_available()) { > - pgdp = pgd_offset_k(ea); > - pudp = pud_alloc(&init_mm, pgdp, ea); > - if (!pudp) > - return -ENOMEM; > - pmdp = pmd_alloc(&init_mm, pudp, ea); > - if (!pmdp) > - return -ENOMEM; > - ptep = pte_alloc_kernel(pmdp, ea); > - if (!ptep) > - return -ENOMEM; > - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, > - __pgprot(flags))); > - } else { > -#ifdef CONFIG_PPC_MMU_NOHASH > - pgdp = pgd_offset_k(ea); > -#ifdef PUD_TABLE_SIZE > - if (pgd_none(*pgdp)) { > - pudp = early_alloc_pgtable(PUD_TABLE_SIZE); > - BUG_ON(pudp == NULL); > - pgd_populate(&init_mm, pgdp, pudp); > - } > -#endif /* PUD_TABLE_SIZE */ > - pudp = pud_offset(pgdp, ea); > - if (pud_none(*pudp)) { > - pmdp = early_alloc_pgtable(PMD_TABLE_SIZE); > - BUG_ON(pmdp == NULL); > - pud_populate(&init_mm, pudp, pmdp); > - } > - pmdp = pmd_offset(pudp, ea); > - if (!pmd_present(*pmdp)) { > - ptep = early_alloc_pgtable(PAGE_SIZE); > - BUG_ON(ptep == NULL); > - pmd_populate_kernel(&init_mm, pmdp, ptep); > - } > - ptep = pte_offset_kernel(pmdp, ea); > - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, > - __pgprot(flags))); > -#else /* CONFIG_PPC_MMU_NOHASH */ > - /* > - * If the mm subsystem is not fully up, we cannot create a > - * linux page table entry for this mapping. Simply bolt an > - * entry in the hardware page table. > - * > - */ > - if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, > - mmu_io_psize, mmu_kernel_ssize)) { > - printk(KERN_ERR "Failed to do bolted mapping IO " > - "memory at %016lx !\n", pa); > - return -ENOMEM; > - } > -#endif /* !CONFIG_PPC_MMU_NOHASH */ > - } > - > - smp_wmb(); > - return 0; > -} > - > - > /** > * __ioremap_at - Low level function to establish the page tables > * for an IO mapping > Otherwise looks good! Balbir Singh
Balbir Singh <bsingharora@gmail.com> writes: >> + ....... >> +/* >> + * map_kernel_page currently only called by __ioremap >> + * map_kernel_page adds an entry to the ioremap page table >> + * and adds an entry to the HPT, possibly bolting it >> + */ >> +int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) >> +{ >> + pgd_t *pgdp; >> + pud_t *pudp; >> + pmd_t *pmdp; >> + pte_t *ptep; >> + >> + if (slab_is_available()) { >> + pgdp = pgd_offset_k(ea); >> + pudp = pud_alloc(&init_mm, pgdp, ea); >> + if (!pudp) >> + return -ENOMEM; >> + pmdp = pmd_alloc(&init_mm, pudp, ea); >> + if (!pmdp) >> + return -ENOMEM; >> + ptep = pte_alloc_kernel(pmdp, ea); >> + if (!ptep) >> + return -ENOMEM; >> + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, >> + __pgprot(flags))); >> + } else { >> + /* >> + * If the mm subsystem is not fully up, we cannot create a >> + * linux page table entry for this mapping. Simply bolt an >> + * entry in the hardware page table. >> + * >> + */ >> + if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, >> + mmu_io_psize, mmu_kernel_ssize)) { >> + printk(KERN_ERR "Failed to do bolted mapping IO " >> + "memory at %016lx !\n", pa); >> + return -ENOMEM; > > What happens when we do unmap this? I know this code has been around for a while > so its not new you mean iounmap ? it do call vunmap, which look for a linux page table entry. If it is a bolt_mapping entry as above, we will not have a linux page table entry and that unmap will not relaly remove the mapping. > >> + } >> + } >> + >> + smp_wmb(); >> + return 0; >> +} -aneesh
>>> + if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, >>> + mmu_io_psize, mmu_kernel_ssize)) { >>> + printk(KERN_ERR "Failed to do bolted mapping IO " >>> + "memory at %016lx !\n", pa); >>> + return -ENOMEM; >> >> What happens when we do unmap this? I know this code has been around for a while >> so its not new > > you mean iounmap ? it do call vunmap, which look for a linux page table > entry. If it is a bolt_mapping entry as above, we will not have a linux > page table entry and that unmap will not relaly remove the mapping. Make sense, thanks! Balbir
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index adfee3f1aeb9..ef778997daa9 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -13,7 +13,8 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ tlb_nohash_low.o obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o -obj-$(CONFIG_PPC_STD_MMU_64) += hash_utils_64.o slb_low.o slb.o $(hash64-y) +obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o +obj-$(CONFIG_PPC_STD_MMU_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o \ mmu_context_hash$(CONFIG_WORD_SIZE).o diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index ba655666186d..8d1daf7d9785 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -189,75 +189,6 @@ static int __meminit vmemmap_populated(unsigned long start, int page_size) return 0; } -/* On hash-based CPUs, the vmemmap is bolted in the hash table. - * - * On Book3E CPUs, the vmemmap is currently mapped in the top half of - * the vmalloc space using normal page tables, though the size of - * pages encoded in the PTEs can be different - */ - -#ifdef CONFIG_PPC_BOOK3E -static int __meminit vmemmap_create_mapping(unsigned long start, - unsigned long page_size, - unsigned long phys) -{ - /* Create a PTE encoding without page size */ - unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED | - _PAGE_KERNEL_RW; - - /* PTEs only contain page size encodings up to 32M */ - BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf); - - /* Encode the size in the PTE */ - flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8; - - /* For each PTE for that area, map things. Note that we don't - * increment phys because all PTEs are of the large size and - * thus must have the low bits clear - */ - for (i = 0; i < page_size; i += PAGE_SIZE) - BUG_ON(map_kernel_page(start + i, phys, flags)); - - return 0; -} - -#ifdef CONFIG_MEMORY_HOTPLUG -static void vmemmap_remove_mapping(unsigned long start, - unsigned long page_size) -{ -} -#endif -#else /* CONFIG_PPC_BOOK3E */ -static int __meminit vmemmap_create_mapping(unsigned long start, - unsigned long page_size, - unsigned long phys) -{ - int rc = htab_bolt_mapping(start, start + page_size, phys, - pgprot_val(PAGE_KERNEL), - mmu_vmemmap_psize, mmu_kernel_ssize); - if (rc < 0) { - int rc2 = htab_remove_mapping(start, start + page_size, - mmu_vmemmap_psize, - mmu_kernel_ssize); - BUG_ON(rc2 && (rc2 != -ENOENT)); - } - return rc; -} - -#ifdef CONFIG_MEMORY_HOTPLUG -static void vmemmap_remove_mapping(unsigned long start, - unsigned long page_size) -{ - int rc = htab_remove_mapping(start, start + page_size, - mmu_vmemmap_psize, - mmu_kernel_ssize); - BUG_ON((rc < 0) && (rc != -ENOENT)); - WARN_ON(rc == -ENOENT); -} -#endif - -#endif /* CONFIG_PPC_BOOK3E */ - struct vmemmap_backing *vmemmap_list; static struct vmemmap_backing *next; static int num_left; @@ -309,6 +240,9 @@ static __meminit void vmemmap_list_populate(unsigned long phys, vmemmap_list = vmem_back; } +extern int __meminit vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys); int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; @@ -347,6 +281,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) } #ifdef CONFIG_MEMORY_HOTPLUG +extern void vmemmap_remove_mapping(unsigned long start, + unsigned long page_size); static unsigned long vmemmap_list_free(unsigned long start) { struct vmemmap_backing *vmem_back, *vmem_back_prev; diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/pgtable-book3e.c new file mode 100644 index 000000000000..f75ba4142875 --- /dev/null +++ b/arch/powerpc/mm/pgtable-book3e.c @@ -0,0 +1,128 @@ + +/* + * Copyright IBM Corporation, 2015 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +/* + * PPC64 THP Support for hash based MMUs + */ +#include <linux/sched.h> +#include <linux/memblock.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> +#include <asm/dma.h> + +#include "mmu_decl.h" + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* + * On Book3E CPUs, the vmemmap is currently mapped in the top half of + * the vmalloc space using normal page tables, though the size of + * pages encoded in the PTEs can be different + */ +int __meminit vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys) +{ + /* Create a PTE encoding without page size */ + unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED | + _PAGE_KERNEL_RW; + + /* PTEs only contain page size encodings up to 32M */ + BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf); + + /* Encode the size in the PTE */ + flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8; + + /* For each PTE for that area, map things. Note that we don't + * increment phys because all PTEs are of the large size and + * thus must have the low bits clear + */ + for (i = 0; i < page_size; i += PAGE_SIZE) + BUG_ON(map_kernel_page(start + i, phys, flags)); + + return 0; +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_remove_mapping(unsigned long start, + unsigned long page_size) +{ +} +#endif +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ + +static __ref void *early_alloc_pgtable(unsigned long size) +{ + void *pt; + + pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); + memset(pt, 0, size); + + return pt; +} + +/* + * map_kernel_page currently only called by __ioremap + * map_kernel_page adds an entry to the ioremap page table + * and adds an entry to the HPT, possibly bolting it + */ +int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) +{ + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + if (slab_is_available()) { + pgdp = pgd_offset_k(ea); + pudp = pud_alloc(&init_mm, pgdp, ea); + if (!pudp) + return -ENOMEM; + pmdp = pmd_alloc(&init_mm, pudp, ea); + if (!pmdp) + return -ENOMEM; + ptep = pte_alloc_kernel(pmdp, ea); + if (!ptep) + return -ENOMEM; + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, + __pgprot(flags))); + } else { + pgdp = pgd_offset_k(ea); +#ifndef __PAGETABLE_PUD_FOLDED + if (pgd_none(*pgdp)) { + pudp = early_alloc_pgtable(PUD_TABLE_SIZE); + BUG_ON(pudp == NULL); + pgd_populate(&init_mm, pgdp, pudp); + } +#endif /* !__PAGETABLE_PUD_FOLDED */ + pudp = pud_offset(pgdp, ea); + if (pud_none(*pudp)) { + pmdp = early_alloc_pgtable(PMD_TABLE_SIZE); + BUG_ON(pmdp == NULL); + pud_populate(&init_mm, pudp, pmdp); + } + pmdp = pmd_offset(pudp, ea); + if (!pmd_present(*pmdp)) { + ptep = early_alloc_pgtable(PAGE_SIZE); + BUG_ON(ptep == NULL); + pmd_populate_kernel(&init_mm, pmdp, ptep); + } + ptep = pte_offset_kernel(pmdp, ea); + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, + __pgprot(flags))); + } + + smp_wmb(); + return 0; +} diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c new file mode 100644 index 000000000000..04d6fa12789e --- /dev/null +++ b/arch/powerpc/mm/pgtable-hash64.c @@ -0,0 +1,100 @@ +/* + * Copyright IBM Corporation, 2015 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +/* + * PPC64 THP Support for hash based MMUs + */ +#include <linux/sched.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> + +#include "mmu_decl.h" + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* + * On hash-based CPUs, the vmemmap is bolted in the hash table. + * + */ +int __meminit vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys) +{ + int rc = htab_bolt_mapping(start, start + page_size, phys, + pgprot_val(PAGE_KERNEL), + mmu_vmemmap_psize, mmu_kernel_ssize); + if (rc < 0) { + int rc2 = htab_remove_mapping(start, start + page_size, + mmu_vmemmap_psize, + mmu_kernel_ssize); + BUG_ON(rc2 && (rc2 != -ENOENT)); + } + return rc; +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_remove_mapping(unsigned long start, + unsigned long page_size) +{ + int rc = htab_remove_mapping(start, start + page_size, + mmu_vmemmap_psize, + mmu_kernel_ssize); + BUG_ON((rc < 0) && (rc != -ENOENT)); + WARN_ON(rc == -ENOENT); +} +#endif +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ + +/* + * map_kernel_page currently only called by __ioremap + * map_kernel_page adds an entry to the ioremap page table + * and adds an entry to the HPT, possibly bolting it + */ +int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) +{ + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + if (slab_is_available()) { + pgdp = pgd_offset_k(ea); + pudp = pud_alloc(&init_mm, pgdp, ea); + if (!pudp) + return -ENOMEM; + pmdp = pmd_alloc(&init_mm, pudp, ea); + if (!pmdp) + return -ENOMEM; + ptep = pte_alloc_kernel(pmdp, ea); + if (!ptep) + return -ENOMEM; + set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, + __pgprot(flags))); + } else { + /* + * If the mm subsystem is not fully up, we cannot create a + * linux page table entry for this mapping. Simply bolt an + * entry in the hardware page table. + * + */ + if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, + mmu_io_psize, mmu_kernel_ssize)) { + printk(KERN_ERR "Failed to do bolted mapping IO " + "memory at %016lx !\n", pa); + return -ENOMEM; + } + } + + smp_wmb(); + return 0; +} diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 5fff787da17a..d493f62d12eb 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -78,89 +78,6 @@ struct patb_entry *partition_tb; #endif unsigned long ioremap_bot = IOREMAP_BASE; -#ifdef CONFIG_PPC_MMU_NOHASH -static __ref void *early_alloc_pgtable(unsigned long size) -{ - void *pt; - - pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); - memset(pt, 0, size); - - return pt; -} -#endif /* CONFIG_PPC_MMU_NOHASH */ - -/* - * map_kernel_page currently only called by __ioremap - * map_kernel_page adds an entry to the ioremap page table - * and adds an entry to the HPT, possibly bolting it - */ -int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags) -{ - pgd_t *pgdp; - pud_t *pudp; - pmd_t *pmdp; - pte_t *ptep; - - if (slab_is_available()) { - pgdp = pgd_offset_k(ea); - pudp = pud_alloc(&init_mm, pgdp, ea); - if (!pudp) - return -ENOMEM; - pmdp = pmd_alloc(&init_mm, pudp, ea); - if (!pmdp) - return -ENOMEM; - ptep = pte_alloc_kernel(pmdp, ea); - if (!ptep) - return -ENOMEM; - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, - __pgprot(flags))); - } else { -#ifdef CONFIG_PPC_MMU_NOHASH - pgdp = pgd_offset_k(ea); -#ifdef PUD_TABLE_SIZE - if (pgd_none(*pgdp)) { - pudp = early_alloc_pgtable(PUD_TABLE_SIZE); - BUG_ON(pudp == NULL); - pgd_populate(&init_mm, pgdp, pudp); - } -#endif /* PUD_TABLE_SIZE */ - pudp = pud_offset(pgdp, ea); - if (pud_none(*pudp)) { - pmdp = early_alloc_pgtable(PMD_TABLE_SIZE); - BUG_ON(pmdp == NULL); - pud_populate(&init_mm, pudp, pmdp); - } - pmdp = pmd_offset(pudp, ea); - if (!pmd_present(*pmdp)) { - ptep = early_alloc_pgtable(PAGE_SIZE); - BUG_ON(ptep == NULL); - pmd_populate_kernel(&init_mm, pmdp, ptep); - } - ptep = pte_offset_kernel(pmdp, ea); - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, - __pgprot(flags))); -#else /* CONFIG_PPC_MMU_NOHASH */ - /* - * If the mm subsystem is not fully up, we cannot create a - * linux page table entry for this mapping. Simply bolt an - * entry in the hardware page table. - * - */ - if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, - mmu_io_psize, mmu_kernel_ssize)) { - printk(KERN_ERR "Failed to do bolted mapping IO " - "memory at %016lx !\n", pa); - return -ENOMEM; - } -#endif /* !CONFIG_PPC_MMU_NOHASH */ - } - - smp_wmb(); - return 0; -} - - /** * __ioremap_at - Low level function to establish the page tables * for an IO mapping
This patch reduce #ifdef in C code and also help in adding radix changes later. Only code movement in this patch. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> --- arch/powerpc/mm/Makefile | 3 +- arch/powerpc/mm/init_64.c | 74 ++-------------------- arch/powerpc/mm/pgtable-book3e.c | 128 +++++++++++++++++++++++++++++++++++++++ arch/powerpc/mm/pgtable-hash64.c | 100 ++++++++++++++++++++++++++++++ arch/powerpc/mm/pgtable_64.c | 83 ------------------------- 5 files changed, 235 insertions(+), 153 deletions(-) create mode 100644 arch/powerpc/mm/pgtable-book3e.c create mode 100644 arch/powerpc/mm/pgtable-hash64.c