diff options
Diffstat (limited to 'arch/powerpc/include/asm/nohash')
| -rw-r--r-- | arch/powerpc/include/asm/nohash/32/pgtable.h | 343 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/32/pte-40x.h | 64 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/32/pte-44x.h | 97 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/32/pte-8xx.h | 65 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h | 40 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/64/pgtable-4k.h | 92 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/64/pgtable-64k.h | 57 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/64/pgtable.h | 364 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/pgtable.h | 252 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/nohash/pte-book3e.h | 87 |
10 files changed, 1461 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h new file mode 100644 index 000000000000..c82cbf52d19e --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -0,0 +1,343 @@ +#ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H +#define _ASM_POWERPC_NOHASH_32_PGTABLE_H + +#include <asm-generic/pgtable-nopmd.h> + +#ifndef __ASSEMBLY__ +#include <linux/sched.h> +#include <linux/threads.h> +#include <asm/io.h> /* For sub-arch specific PPC_PIN_SIZE */ + +extern unsigned long ioremap_bot; + +#ifdef CONFIG_44x +extern int icache_44x_need_flush; +#endif + +#endif /* __ASSEMBLY__ */ + +/* + * The normal case is that PTEs are 32-bits and we have a 1-page + * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages. -- paulus + * + * For any >32-bit physical address platform, we can use the following + * two level page table layout where the pgdir is 8KB and the MS 13 bits + * are an index to the second level table. The combined pgdir/pmd first + * level has 2048 entries and the second level has 512 64-bit PTE entries. + * -Matt + */ +/* PGDIR_SHIFT determines what a top-level page table entry can map */ +#define PGDIR_SHIFT (PAGE_SHIFT + PTE_SHIFT) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * entries per page directory level: our page-table tree is two-level, so + * we don't really have any PMD directory. + */ +#ifndef __ASSEMBLY__ +#define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_SHIFT) +#define PGD_TABLE_SIZE (sizeof(pgd_t) << (32 - PGDIR_SHIFT)) +#endif /* __ASSEMBLY__ */ + +#define PTRS_PER_PTE (1 << PTE_SHIFT) +#define PTRS_PER_PMD 1 +#define PTRS_PER_PGD (1 << (32 - PGDIR_SHIFT)) + +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) +#define FIRST_USER_ADDRESS 0UL + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ + (unsigned long long)pte_val(e)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + +/* + * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary + * value (for now) on others, from where we can start layout kernel + * virtual space that goes below PKMAP and FIXMAP + */ +#ifdef CONFIG_HIGHMEM +#define KVIRT_TOP PKMAP_BASE +#else +#define KVIRT_TOP (0xfe000000UL) /* for now, could be FIXMAP_BASE ? */ +#endif + +/* + * ioremap_bot starts at that address. Early ioremaps move down from there, + * until mem_init() at which point this becomes the top of the vmalloc + * and ioremap space + */ +#ifdef CONFIG_NOT_COHERENT_CACHE +#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) +#else +#define IOREMAP_TOP KVIRT_TOP +#endif + +/* + * Just any arbitrary offset to the start of the vmalloc VM area: the + * current 16MB value just means that there will be a 64MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + * + * We no longer map larger than phys RAM with the BATs so we don't have + * to worry about the VMALLOC_OFFSET causing problems. We do have to worry + * about clashes between our early calls to ioremap() that start growing down + * from ioremap_base being run into the VM area allocations (growing upwards + * from VMALLOC_START). For this reason we have ioremap_bot to check when + * we actually run into our mappings setup in the early boot with the VM + * system. This really does become a problem for machines with good amounts + * of RAM. -- Cort + */ +#define VMALLOC_OFFSET (0x1000000) /* 16M */ +#ifdef PPC_PIN_SIZE +#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) +#else +#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) +#endif +#define VMALLOC_END ioremap_bot + +/* + * Bits in a linux-style PTE. These match the bits in the + * (hardware-defined) PowerPC PTE as closely as possible. + */ + +#if defined(CONFIG_40x) +#include <asm/nohash/32/pte-40x.h> +#elif defined(CONFIG_44x) +#include <asm/nohash/32/pte-44x.h> +#elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT) +#include <asm/nohash/pte-book3e.h> +#elif defined(CONFIG_FSL_BOOKE) +#include <asm/nohash/32/pte-fsl-booke.h> +#elif defined(CONFIG_8xx) +#include <asm/nohash/32/pte-8xx.h> +#endif + +/* And here we include common definitions */ +#include <asm/pte-common.h> + +#ifndef __ASSEMBLY__ + +#define pte_clear(mm, addr, ptep) \ + do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0) + +#define pmd_none(pmd) (!pmd_val(pmd)) +#define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) +#define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + + + +/* + * When flushing the tlb entry for a page, we also need to flush the hash + * table entry. flush_hash_pages is assembler (for speed) in hashtable.S. + */ +extern int flush_hash_pages(unsigned context, unsigned long va, + unsigned long pmdval, int count); + +/* Add an HPTE to the hash table */ +extern void add_hash_page(unsigned context, unsigned long va, + unsigned long pmdval); + +/* Flush an entry from the TLB/hash table */ +extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, + unsigned long address); + +/* + * PTE updates. This function is called whenever an existing + * valid PTE is updated. This does -not- include set_pte_at() + * which nowadays only sets a new PTE. + * + * Depending on the type of MMU, we may need to use atomic updates + * and the PTE may be either 32 or 64 bit wide. In the later case, + * when using atomic updates, only the low part of the PTE is + * accessed atomically. + * + * In addition, on 44x, we also maintain a global flag indicating + * that an executable user mapping was modified, which is needed + * to properly flush the virtually tagged instruction cache of + * those implementations. + */ +#ifndef CONFIG_PTE_64BIT +static inline unsigned long pte_update(pte_t *p, + unsigned long clr, + unsigned long set) +{ +#ifdef PTE_ATOMIC_UPDATES + unsigned long old, tmp; + + __asm__ __volatile__("\ +1: lwarx %0,0,%3\n\ + andc %1,%0,%4\n\ + or %1,%1,%5\n" + PPC405_ERR77(0,%3) +" stwcx. %1,0,%3\n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) + : "r" (p), "r" (clr), "r" (set), "m" (*p) + : "cc" ); +#else /* PTE_ATOMIC_UPDATES */ + unsigned long old = pte_val(*p); + *p = __pte((old & ~clr) | set); +#endif /* !PTE_ATOMIC_UPDATES */ + +#ifdef CONFIG_44x + if ((old & _PAGE_USER) && (old & _PAGE_EXEC)) + icache_44x_need_flush = 1; +#endif + return old; +} +#else /* CONFIG_PTE_64BIT */ +static inline unsigned long long pte_update(pte_t *p, + unsigned long clr, + unsigned long set) +{ +#ifdef PTE_ATOMIC_UPDATES + unsigned long long old; + unsigned long tmp; + + __asm__ __volatile__("\ +1: lwarx %L0,0,%4\n\ + lwzx %0,0,%3\n\ + andc %1,%L0,%5\n\ + or %1,%1,%6\n" + PPC405_ERR77(0,%3) +" stwcx. %1,0,%4\n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) + : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p) + : "cc" ); +#else /* PTE_ATOMIC_UPDATES */ + unsigned long long old = pte_val(*p); + *p = __pte((old & ~(unsigned long long)clr) | set); +#endif /* !PTE_ATOMIC_UPDATES */ + +#ifdef CONFIG_44x + if ((old & _PAGE_USER) && (old & _PAGE_EXEC)) + icache_44x_need_flush = 1; +#endif + return old; +} +#endif /* CONFIG_PTE_64BIT */ + +/* + * 2.6 calls this without flushing the TLB entry; this is wrong + * for our hash-based implementation, we fix that up here. + */ +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) +{ + unsigned long old; + old = pte_update(ptep, _PAGE_ACCESSED, 0); +#if _PAGE_HASHPTE != 0 + if (old & _PAGE_HASHPTE) { + unsigned long ptephys = __pa(ptep) & PAGE_MASK; + flush_hash_pages(context, addr, ptephys, 1); + } +#endif + return (old & _PAGE_ACCESSED) != 0; +} +#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ + __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0)); +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO); +} +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + + +static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +{ + unsigned long set = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); + unsigned long clr = ~pte_val(entry) & _PAGE_RO; + + pte_update(ptep, clr, set); +} + +#define __HAVE_ARCH_PTE_SAME +#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) + +/* + * Note that on Book E processors, the pmd contains the kernel virtual + * (lowmem) address of the pte page. The physical address is less useful + * because everything runs with translation enabled (even the TLB miss + * handler). On everything else the pmd contains the physical address + * of the pte page. -- paulus + */ +#ifndef CONFIG_BOOKE +#define pmd_page_vaddr(pmd) \ + ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) +#define pmd_page(pmd) \ + pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) +#else +#define pmd_page_vaddr(pmd) \ + ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) +#define pmd_page(pmd) \ + pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) +#endif + +/* to find an entry in a kernel page-table-directory */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) + +/* to find an entry in a page-table-directory */ +#define pgd_index(address) ((address) >> PGDIR_SHIFT) +#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) + +/* Find an entry in the third-level page table.. */ +#define pte_index(address) \ + (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +#define pte_offset_kernel(dir, addr) \ + ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) +#define pte_offset_map(dir, addr) \ + ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) +#define pte_unmap(pte) kunmap_atomic(pte) + +/* + * Encode and decode a swap entry. + * Note that the bits we use in a PTE for representing a swap entry + * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used). + * -- paulus + */ +#define __swp_type(entry) ((entry).val & 0x1f) +#define __swp_offset(entry) ((entry).val >> 5) +#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 5) }) +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) + +#ifndef CONFIG_PPC_4K_PAGES +void pgtable_cache_init(void); +#else +/* + * No page table caches to initialise + */ +#define pgtable_cache_init() do { } while (0) +#endif + +extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, + pmd_t **pmdp); + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h new file mode 100644 index 000000000000..9624ebdacc47 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -0,0 +1,64 @@ +#ifndef _ASM_POWERPC_NOHASH_32_PTE_40x_H +#define _ASM_POWERPC_NOHASH_32_PTE_40x_H +#ifdef __KERNEL__ + +/* + * At present, all PowerPC 400-class processors share a similar TLB + * architecture. The instruction and data sides share a unified, + * 64-entry, fully-associative TLB which is maintained totally under + * software control. In addition, the instruction side has a + * hardware-managed, 4-entry, fully-associative TLB which serves as a + * first level to the shared TLB. These two TLBs are known as the UTLB + * and ITLB, respectively (see "mmu.h" for definitions). + * + * There are several potential gotchas here. The 40x hardware TLBLO + * field looks like this: + * + * 0 1 2 3 4 ... 18 19 20 21 22 23 24 25 26 27 28 29 30 31 + * RPN..................... 0 0 EX WR ZSEL....... W I M G + * + * Where possible we make the Linux PTE bits match up with this + * + * - bits 20 and 21 must be cleared, because we use 4k pages (40x can + * support down to 1k pages), this is done in the TLBMiss exception + * handler. + * - We use only zones 0 (for kernel pages) and 1 (for user pages) + * of the 16 available. Bit 24-26 of the TLB are cleared in the TLB + * miss handler. Bit 27 is PAGE_USER, thus selecting the correct + * zone. + * - PRESENT *must* be in the bottom two bits because swap cache + * entries use the top 30 bits. Because 40x doesn't support SMP + * anyway, M is irrelevant so we borrow it for PAGE_PRESENT. Bit 30 + * is cleared in the TLB miss handler before the TLB entry is loaded. + * - All other bits of the PTE are loaded into TLBLO without + * modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for + * software PTE bits. We actually use use bits 21, 24, 25, and + * 30 respectively for the software bits: ACCESSED, DIRTY, RW, and + * PRESENT. + */ + +#define _PAGE_GUARDED 0x001 /* G: page is guarded from prefetch */ +#define _PAGE_PRESENT 0x002 /* software: PTE contains a translation */ +#define _PAGE_NO_CACHE 0x004 /* I: caching is inhibited */ +#define _PAGE_WRITETHRU 0x008 /* W: caching is write-through */ +#define _PAGE_USER 0x010 /* matches one of the zone permission bits */ +#define _PAGE_SPECIAL 0x020 /* software: Special page */ +#define _PAGE_RW 0x040 /* software: Writes permitted */ +#define _PAGE_DIRTY 0x080 /* software: dirty page */ +#define _PAGE_HWWRITE 0x100 /* hardware: Dirty & RW, set in exception */ +#define _PAGE_EXEC 0x200 /* hardware: EX permission */ +#define _PAGE_ACCESSED 0x400 /* software: R: page referenced */ + +#define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */ +#define _PMD_BAD 0x802 +#define _PMD_SIZE 0x0e0 /* size field, != 0 for large-page PMD entry */ +#define _PMD_SIZE_4M 0x0c0 +#define _PMD_SIZE_16M 0x0e0 + +#define PMD_PAGE_SIZE(pmdval) (1024 << (((pmdval) & _PMD_SIZE) >> 4)) + +/* Until my rework is finished, 40x still needs atomic PTE updates */ +#define PTE_ATOMIC_UPDATES 1 + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h new file mode 100644 index 000000000000..fdab41c654ef --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h @@ -0,0 +1,97 @@ +#ifndef _ASM_POWERPC_NOHASH_32_PTE_44x_H +#define _ASM_POWERPC_NOHASH_32_PTE_44x_H +#ifdef __KERNEL__ + +/* + * Definitions for PPC440 + * + * Because of the 3 word TLB entries to support 36-bit addressing, + * the attribute are difficult to map in such a fashion that they + * are easily loaded during exception processing. I decided to + * organize the entry so the ERPN is the only portion in the + * upper word of the PTE and the attribute bits below are packed + * in as sensibly as they can be in the area below a 4KB page size + * oriented RPN. This at least makes it easy to load the RPN and + * ERPN fields in the TLB. -Matt + * + * This isn't entirely true anymore, at least some bits are now + * easier to move into the TLB from the PTE. -BenH. + * + * Note that these bits preclude future use of a page size + * less than 4KB. + * + * + * PPC 440 core has following TLB attribute fields; + * + * TLB1: + * 0 1 2 3 4 ... 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 + * RPN................................. - - - - - - ERPN....... + * + * TLB2: + * 0 1 2 3 4 ... 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 + * - - - - - - U0 U1 U2 U3 W I M G E - UX UW UR SX SW SR + * + * Newer 440 cores (440x6 as used on AMCC 460EX/460GT) have additional + * TLB2 storage attibute fields. Those are: + * + * TLB2: + * 0...10 11 12 13 14 15 16...31 + * no change WL1 IL1I IL1D IL2I IL2D no change + * + * There are some constrains and options, to decide mapping software bits + * into TLB entry. + * + * - PRESENT *must* be in the bottom three bits because swap cache + * entries use the top 29 bits for TLB2. + * + * - CACHE COHERENT bit (M) has no effect on original PPC440 cores, + * because it doesn't support SMP. However, some later 460 variants + * have -some- form of SMP support and so I keep the bit there for + * future use + * + * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used + * for memory protection related functions (see PTE structure in + * include/asm-ppc/mmu.h). The _PAGE_XXX definitions in this file map to the + * above bits. Note that the bit values are CPU specific, not architecture + * specific. + * + * The kernel PTE entry holds an arch-dependent swp_entry structure under + * certain situations. In other words, in such situations some portion of + * the PTE bits are used as a swp_entry. In the PPC implementation, the + * 3-24th LSB are shared with swp_entry, however the 0-2nd three LSB still + * hold protection values. That means the three protection bits are + * reserved for both PTE and SWAP entry at the most significant three + * LSBs. + * + * There are three protection bits available for SWAP entry: + * _PAGE_PRESENT + * _PAGE_HASHPTE (if HW has) + * + * So those three bits have to be inside of 0-2nd LSB of PTE. + * + */ + +#define _PAGE_PRESENT 0x00000001 /* S: PTE valid */ +#define _PAGE_RW 0x00000002 /* S: Write permission */ +#define _PAGE_EXEC 0x00000004 /* H: Execute permission */ +#define _PAGE_ACCESSED 0x00000008 /* S: Page referenced */ +#define _PAGE_DIRTY 0x00000010 /* S: Page dirty */ +#define _PAGE_SPECIAL 0x00000020 /* S: Special page */ +#define _PAGE_USER 0x00000040 /* S: User page */ +#define _PAGE_ENDIAN 0x00000080 /* H: E bit */ +#define _PAGE_GUARDED 0x00000100 /* H: G bit */ +#define _PAGE_COHERENT 0x00000200 /* H: M bit */ +#define _PAGE_NO_CACHE 0x00000400 /* H: I bit */ +#define _PAGE_WRITETHRU 0x00000800 /* H: W bit */ + +/* TODO: Add large page lowmem mapping support */ +#define _PMD_PRESENT 0 +#define _PMD_PRESENT_MASK (PAGE_MASK) +#define _PMD_BAD (~PAGE_MASK) + +/* ERPN in a PTE never gets cleared, ignore it */ +#define _PTE_NONE_MASK 0xffffffff00000000ULL + + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_44x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h new file mode 100644 index 000000000000..3742b1919661 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -0,0 +1,65 @@ +#ifndef _ASM_POWERPC_NOHASH_32_PTE_8xx_H +#define _ASM_POWERPC_NOHASH_32_PTE_8xx_H +#ifdef __KERNEL__ + +/* + * The PowerPC MPC8xx uses a TLB with hardware assisted, software tablewalk. + * We also use the two level tables, but we can put the real bits in them + * needed for the TLB and tablewalk. These definitions require Mx_CTR.PPM = 0, + * Mx_CTR.PPCS = 0, and MD_CTR.TWAM = 1. The level 2 descriptor has + * additional page protection (when Mx_CTR.PPCS = 1) that allows TLB hit + * based upon user/super access. The TLB does not have accessed nor write + * protect. We assume that if the TLB get loaded with an entry it is + * accessed, and overload the changed bit for write protect. We use + * two bits in the software pte that are supposed to be set to zero in + * the TLB entry (24 and 25) for these indicators. Although the level 1 + * descriptor contains the guarded and writethrough/copyback bits, we can + * set these at the page level since they get copied from the Mx_TWC + * register when the TLB entry is loaded. We will use bit 27 for guard, since + * that is where it exists in the MD_TWC, and bit 26 for writethrough. + * These will get masked from the level 2 descriptor at TLB load time, and + * copied to the MD_TWC before it gets loaded. + * Large page sizes added. We currently support two sizes, 4K and 8M. + * This also allows a TLB hander optimization because we can directly + * load the PMD into MD_TWC. The 8M pages are only used for kernel + * mapping of well known areas. The PMD (PGD) entries contain control + * flags in addition to the address, so care must be taken that the + * software no longer assumes these are only pointers. + */ + +/* Definitions for 8xx embedded chips. */ +#define _PAGE_PRESENT 0x0001 /* Page is valid */ +#define _PAGE_NO_CACHE 0x0002 /* I: cache inhibit */ +#define _PAGE_SHARED 0x0004 /* No ASID (context) compare */ +#define _PAGE_SPECIAL 0x0008 /* SW entry, forced to 0 by the TLB miss */ +#define _PAGE_DIRTY 0x0100 /* C: page changed */ + +/* These 4 software bits must be masked out when the L2 entry is loaded + * into the TLB. + */ +#define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ +#define _PAGE_USER 0x0020 /* Copied to L1 APG lsb */ +#define _PAGE_EXEC 0x0040 /* Copied to L1 APG */ +#define _PAGE_WRITETHRU 0x0080 /* software: caching is write through */ +#define _PAGE_ACCESSED 0x0800 /* software: page referenced */ + +#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ + +#define _PMD_PRESENT 0x0001 +#define _PMD_BAD 0x0ff0 +#define _PMD_PAGE_MASK 0x000c +#define _PMD_PAGE_8M 0x000c + +/* Until my rework is finished, 8xx still needs atomic PTE updates */ +#define PTE_ATOMIC_UPDATES 1 + +/* We need to add _PAGE_SHARED to kernel pages */ +#define _PAGE_KERNEL_RO (_PAGE_SHARED | _PAGE_RO) +#define _PAGE_KERNEL_ROX (_PAGE_SHARED | _PAGE_RO | _PAGE_EXEC) +#define _PAGE_KERNEL_RW (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \ + _PAGE_HWWRITE) +#define _PAGE_KERNEL_RWX (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \ + _PAGE_HWWRITE | _PAGE_EXEC) + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_8xx_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h new file mode 100644 index 000000000000..5422d00c6145 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h @@ -0,0 +1,40 @@ +#ifndef _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H +#define _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H +#ifdef __KERNEL__ + +/* PTE bit definitions for Freescale BookE SW loaded TLB MMU based + * processors + * + MMU Assist Register 3: + + 32 33 34 35 36 ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63 + RPN...................... 0 0 U0 U1 U2 U3 UX SX UW SW UR SR + + - PRESENT *must* be in the bottom three bits because swap cache + entries use the top 29 bits. + +*/ + +/* Definitions for FSL Book-E Cores */ +#define _PAGE_PRESENT 0x00001 /* S: PTE contains a translation */ +#define _PAGE_USER 0x00002 /* S: User page (maps to UR) */ +#define _PAGE_RW 0x00004 /* S: Write permission (SW) */ +#define _PAGE_DIRTY 0x00008 /* S: Page dirty */ +#define _PAGE_EXEC 0x00010 /* H: SX permission */ +#define _PAGE_ACCESSED 0x00020 /* S: Page referenced */ + +#define _PAGE_ENDIAN 0x00040 /* H: E bit */ +#define _PAGE_GUARDED 0x00080 /* H: G bit */ +#define _PAGE_COHERENT 0x00100 /* H: M bit */ +#define _PAGE_NO_CACHE 0x00200 /* H: I bit */ +#define _PAGE_WRITETHRU 0x00400 /* H: W bit */ +#define _PAGE_SPECIAL 0x00800 /* S: Special page */ + +#define _PMD_PRESENT 0 +#define _PMD_PRESENT_MASK (PAGE_MASK) +#define _PMD_BAD (~PAGE_MASK) + +#define PTE_WIMGE_SHIFT (6) + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h new file mode 100644 index 000000000000..fc7d51753f81 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h @@ -0,0 +1,92 @@ +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H +/* + * Entries per page directory level. The PTE level must use a 64b record + * for each page table entry. The PMD and PGD level use a 32b record for + * each entry by assuming that each entry is page aligned. + */ +#define PTE_INDEX_SIZE 9 +#define PMD_INDEX_SIZE 7 +#define PUD_INDEX_SIZE 9 +#define PGD_INDEX_SIZE 9 + +#ifndef __ASSEMBLY__ +#define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) +#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) +#endif /* __ASSEMBLY__ */ + +#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) +#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) +#define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) +#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) + +/* PMD_SHIFT determines what a second-level page table entry can map */ +#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) + +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PMD_SHIFT + +/* PUD_SHIFT determines what a third-level page table entry can map */ +#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) + +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* Bits to mask out from a PMD to get to the PTE page */ +#define PMD_MASKED_BITS 0 +/* Bits to mask out from a PUD to get to the PMD page */ +#define PUD_MASKED_BITS 0 +/* Bits to mask out from a PGD to get to the PUD page */ +#define PGD_MASKED_BITS 0 + + +/* + * 4-level page tables related bits + */ + +#define pgd_none(pgd) (!pgd_val(pgd)) +#define pgd_bad(pgd) (pgd_val(pgd) == 0) +#define pgd_present(pgd) (pgd_val(pgd) != 0) +#define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) + +#ifndef __ASSEMBLY__ + +static inline void pgd_clear(pgd_t *pgdp) +{ + *pgdp = __pgd(0); +} + +static inline pte_t pgd_pte(pgd_t pgd) +{ + return __pte(pgd_val(pgd)); +} + +static inline pgd_t pte_pgd(pte_t pte) +{ + return __pgd(pte_val(pte)); +} +extern struct page *pgd_page(pgd_t pgd); + +#endif /* !__ASSEMBLY__ */ + +#define pud_offset(pgdp, addr) \ + (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))) + +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) + +/* + * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */ +#define remap_4k_pfn(vma, addr, pfn, prot) \ + remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot)) + +#endif /* _ _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h new file mode 100644 index 000000000000..570fb30be21c --- /dev/null +++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h @@ -0,0 +1,57 @@ +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H + +#include <asm-generic/pgtable-nopud.h> + + +#define PTE_INDEX_SIZE 8 +#define PMD_INDEX_SIZE 10 +#define PUD_INDEX_SIZE 0 +#define PGD_INDEX_SIZE 12 + +/* + * we support 32 fragments per PTE page of 64K size + */ +#define PTE_FRAG_NR 32 +/* + * We use a 2K PTE page fragment and another 2K for storing + * real_pte_t hash index + */ +#define PTE_FRAG_SIZE_SHIFT 11 +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + +#ifndef __ASSEMBLY__ +#define PTE_TABLE_SIZE PTE_FRAG_SIZE +#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) +#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) +#endif /* __ASSEMBLY__ */ + +#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) +#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) +#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) + +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PAGE_SHIFT + +/* PMD_SHIFT determines what a second-level page table entry can map */ +#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) + +/* PGDIR_SHIFT determines what a third-level page table entry can map */ +#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * Bits to mask out from a PMD to get to the PTE page + * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned. + */ +#define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) +/* Bits to mask out from a PGD/PUD to get to the PMD page */ +#define PUD_MASKED_BITS 0x1ff + +#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) +#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) + +#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h new file mode 100644 index 000000000000..b9f734dd5b81 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -0,0 +1,364 @@ +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_H +/* + * This file contains the functions and defines necessary to modify and use + * the ppc64 hashed page table. + */ + +#ifdef CONFIG_PPC_64K_PAGES +#include <asm/nohash/64/pgtable-64k.h> +#else +#include <asm/nohash/64/pgtable-4k.h> +#endif +#include <asm/barrier.h> + +#define FIRST_USER_ADDRESS 0UL + +/* + * Size of EA range mapped by our pagetables. + */ +#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \ + PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT) +#define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PMD_CACHE_INDEX (PMD_INDEX_SIZE + 1) +#else +#define PMD_CACHE_INDEX PMD_INDEX_SIZE +#endif +/* + * Define the address range of the kernel non-linear virtual area + */ + +#ifdef CONFIG_PPC_BOOK3E +#define KERN_VIRT_START ASM_CONST(0x8000000000000000) +#else +#define KERN_VIRT_START ASM_CONST(0xD000000000000000) +#endif +#define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) + +/* + * The vmalloc space starts at the beginning of that region, and + * occupies half of it on hash CPUs and a quarter of it on Book3E + * (we keep a quarter for the virtual memmap) + */ +#define VMALLOC_START KERN_VIRT_START +#ifdef CONFIG_PPC_BOOK3E +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 2) +#else +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#endif +#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE) + +/* + * The second half of the kernel virtual space is used for IO mappings, + * it's itself carved into the PIO region (ISA and PHB IO space) and + * the ioremap space + * + * ISA_IO_BASE = KERN_IO_START, 64K reserved area + * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces + * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE + */ +#define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1)) +#define FULL_IO_SIZE 0x80000000ul +#define ISA_IO_BASE (KERN_IO_START) +#define ISA_IO_END (KERN_IO_START + 0x10000ul) +#define PHB_IO_BASE (ISA_IO_END) +#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) +#define IOREMAP_BASE (PHB_IO_END) +#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE) + + +/* + * Region IDs + */ +#define REGION_SHIFT 60UL +#define REGION_MASK (0xfUL << REGION_SHIFT) +#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) + +#define VMALLOC_REGION_ID (REGION_ID(VMALLOC_START)) +#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET)) +#define VMEMMAP_REGION_ID (0xfUL) /* Server only */ +#define USER_REGION_ID (0UL) + +/* + * Defines the address of the vmemap area, in its own region on + * hash table CPUs and after the vmalloc space on Book3E + */ +#ifdef CONFIG_PPC_BOOK3E +#define VMEMMAP_BASE VMALLOC_END +#define VMEMMAP_END KERN_IO_START +#else +#define VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT) +#endif +#define vmemmap ((struct page *)VMEMMAP_BASE) + + +/* + * Include the PTE bits definitions + */ +#include <asm/nohash/pte-book3e.h> +#include <asm/pte-common.h> + +#ifdef CONFIG_PPC_MM_SLICES +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#endif /* CONFIG_PPC_MM_SLICES */ + +#ifndef __ASSEMBLY__ +/* pte_clear moved to later in this file */ + +#define PMD_BAD_BITS (PTE_TABLE_SIZE-1) +#define PUD_BAD_BITS (PMD_TABLE_SIZE-1) + +static inline void pmd_set(pmd_t *pmdp, unsigned long val) +{ + *pmdp = __pmd(val); +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +#define pmd_none(pmd) (!pmd_val(pmd)) +#define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ + || (pmd_val(pmd) & PMD_BAD_BITS)) +#define pmd_present(pmd) (!pmd_none(pmd)) +#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) +extern struct page *pmd_page(pmd_t pmd); + +static inline void pud_set(pud_t *pudp, unsigned long val) +{ + *pudp = __pud(val); +} + +static inline void pud_clear(pud_t *pudp) +{ + *pudp = __pud(0); +} + +#define pud_none(pud) (!pud_val(pud)) +#define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ + || (pud_val(pud) & PUD_BAD_BITS)) +#define pud_present(pud) (pud_val(pud) != 0) +#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) + +extern struct page *pud_page(pud_t pud); + +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} +#define pud_write(pud) pte_write(pud_pte(pud)) +#define pgd_write(pgd) pte_write(pgd_pte(pgd)) + +static inline void pgd_set(pgd_t *pgdp, unsigned long val) +{ + *pgdp = __pgd(val); +} + +/* + * Find an entry in a page-table-directory. We combine the address region + * (the high order N bits) and the pgd portion of the address. + */ +#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) + +#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) + +#define pmd_offset(pudp,addr) \ + (((pmd_t *) pud_page_vaddr(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))) + +#define pte_offset_kernel(dir,addr) \ + (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))) + +#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) +#define pte_unmap(pte) do { } while(0) + +/* to find an entry in a kernel page-table-directory */ +/* This now only contains the vmalloc pages */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) +extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long pte, int huge); + +/* Atomic PTE updates */ +static inline unsigned long pte_update(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, + int huge) +{ +#ifdef PTE_ATOMIC_UPDATES + unsigned long old, tmp; + + __asm__ __volatile__( + "1: ldarx %0,0,%3 # pte_update\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + andc %1,%0,%4 \n\ + or %1,%1,%7\n\ + stdcx. %1,0,%3 \n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*ptep) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) + : "cc" ); +#else + unsigned long old = pte_val(*ptep); + *ptep = __pte((old & ~clr) | set); +#endif + /* huge pages use the old page table lock */ + if (!huge) + assert_pte_locked(mm, addr); + +#ifdef CONFIG_PPC_STD_MMU_64 + if (old & _PAGE_HASHPTE) + hpte_need_flush(mm, addr, ptep, old, huge); +#endif + + return old; +} + +static inline int __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; + + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + return 0; + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + return (old & _PAGE_ACCESSED) != 0; +} +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ +({ \ + int __r; \ + __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ + __r; \ +}) + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); +} + +/* + * We currently remove entries from the hashtable regardless of whether + * the entry was young or dirty. The generic routines only flush if the + * entry was young or dirty which is not good enough. + * + * We should be more intelligent about this but for the moment we override + * these functions and force a tlb flush unconditionally + */ +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young(__vma, __address, __ptep) \ +({ \ + int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \ + __ptep); \ + __young; \ +}) + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); + return __pte(old); +} + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t * ptep) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 0); +} + + +/* Set the dirty and/or accessed bits atomically in a linux PTE, this + * function doesn't need to flush the hash entry + */ +static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +{ + unsigned long bits = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); + +#ifdef PTE_ATOMIC_UPDATES + unsigned long old, tmp; + + __asm__ __volatile__( + "1: ldarx %0,0,%4\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + or %0,%3,%0\n\ + stdcx. %0,0,%4\n\ + bne- 1b" + :"=&r" (old), "=&r" (tmp), "=m" (*ptep) + :"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY) + :"cc"); +#else + unsigned long old = pte_val(*ptep); + *ptep = __pte(old | bits); +#endif +} + +#define __HAVE_ARCH_PTE_SAME +#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + +/* Encode and de-code a swap entry */ +#define MAX_SWAPFILES_CHECK() do { \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ + /* \ + * Don't have overlapping bits with _PAGE_HPTEFLAGS \ + * We filter HPTEFLAGS on set_pte. \ + */ \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + } while (0) +/* + * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; + */ +#define SWP_TYPE_BITS 5 +#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ + & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT) +#define __swp_entry(type, offset) ((swp_entry_t) { \ + ((type) << _PAGE_BIT_SWAP_TYPE) \ + | ((offset) << PTE_RPN_SHIFT) }) + +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) +#define __swp_entry_to_pte(x) __pte((x).val) + +void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); +void pgtable_cache_init(void); +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h new file mode 100644 index 000000000000..1263c22d60d8 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -0,0 +1,252 @@ +#ifndef _ASM_POWERPC_NOHASH_PGTABLE_H +#define _ASM_POWERPC_NOHASH_PGTABLE_H + +#if defined(CONFIG_PPC64) +#include <asm/nohash/64/pgtable.h> +#else +#include <asm/nohash/32/pgtable.h> +#endif + +#ifndef __ASSEMBLY__ + +/* Generic accessors to PTE bits */ +static inline int pte_write(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; +} +static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } +static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } +static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } +static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } +static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } + +#ifdef CONFIG_NUMA_BALANCING +/* + * These work without NUMA balancing but the kernel does not care. See the + * comment in include/asm-generic/pgtable.h . On powerpc, this will only + * work for user pages and always return true for kernel pages. + */ +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & + (_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif /* CONFIG_NUMA_BALANCING */ + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + * + * Even if PTEs can be unsigned long long, a PFN is always an unsigned + * long for now. + */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { + return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | + pgprot_val(pgprot)); } +static inline unsigned long pte_pfn(pte_t pte) { + return pte_val(pte) >> PTE_RPN_SHIFT; } + +/* Generic modifiers for PTE bits */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + pte_basic_t ptev; + + ptev = pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE); + ptev |= _PAGE_RO; + return __pte(ptev); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE)); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_ACCESSED); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + pte_basic_t ptev; + + ptev = pte_val(pte) & ~_PAGE_RO; + ptev |= _PAGE_RW; + return __pte(ptev); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); +} + +/* Insert a PTE, top-level function is out of line. It uses an inline + * low level function in the respective pgtable-* files + */ +extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte); + +/* This low level function performs the actual PTE insertion + * Setting the PTE depends on the MMU type and other factors. It's + * an horrible mess that I'm not going to try to clean up now but + * I'm keeping it in one place rather than spread around + */ +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ +#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) + /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we do a simple update preserving + * the hash bits instead (ie, same as the non-SMP case) + */ + if (percpu) + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + else + pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); + +#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) + /* Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we also fallback to the simple update preserving + * the hash bits + */ + if (percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + return; + } +#if _PAGE_HASHPTE != 0 + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); +#endif + __asm__ __volatile__("\ + stw%U0%X0 %2,%0\n\ + eieio\n\ + stw%U0%X0 %L2,%1" + : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) + : "r" (pte) : "memory"); + +#elif defined(CONFIG_PPC_STD_MMU_32) + /* Third case is 32-bit hash table in UP mode, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating + */ + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + +#else + /* Anything else just stores the PTE normally. That covers all 64-bit + * cases, and 32-bit non-hash with 32-bit PTEs. + */ + *ptep = pte; + +#ifdef CONFIG_PPC_BOOK3E_64 + /* + * With hardware tablewalk, a sync is needed to ensure that + * subsequent accesses see the PTE we just wrote. Unlike userspace + * mappings, we can't tolerate spurious faults, so make sure + * the new PTE will be seen the first time. + */ + if (is_kernel_addr(addr)) + mb(); +#endif +#endif +} + + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE | _PAGE_GUARDED)) + +#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE)) + +#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT)) + +#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT | _PAGE_WRITETHRU)) + +#define pgprot_cached_noncoherent(prot) \ + (__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL)) + +#define pgprot_writecombine pgprot_noncached_wc + +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +#define __HAVE_PHYS_MEM_ACCESS_PROT + +#ifdef CONFIG_HUGETLB_PAGE +static inline int hugepd_ok(hugepd_t hpd) +{ + return (hpd.pd > 0); +} + +static inline int pmd_huge(pmd_t pmd) +{ + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + return 0; +} + +static inline int pgd_huge(pgd_t pgd) +{ + return 0; +} +#define pgd_huge pgd_huge + +#define is_hugepd(hpd) (hugepd_ok(hpd)) +#endif + +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h new file mode 100644 index 000000000000..e16807b78edf --- /dev/null +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -0,0 +1,87 @@ +#ifndef _ASM_POWERPC_NOHASH_PTE_BOOK3E_H +#define _ASM_POWERPC_NOHASH_PTE_BOOK3E_H +#ifdef __KERNEL__ + +/* PTE bit definitions for processors compliant to the Book3E + * architecture 2.06 or later. The position of the PTE bits + * matches the HW definition of the optional Embedded Page Table + * category. + */ + +/* Architected bits */ +#define _PAGE_PRESENT 0x000001 /* software: pte contains a translation */ +#define _PAGE_SW1 0x000002 +#define _PAGE_BIT_SWAP_TYPE 2 +#define _PAGE_BAP_SR 0x000004 +#define _PAGE_BAP_UR 0x000008 +#define _PAGE_BAP_SW 0x000010 +#define _PAGE_BAP_UW 0x000020 +#define _PAGE_BAP_SX 0x000040 +#define _PAGE_BAP_UX 0x000080 +#define _PAGE_PSIZE_MSK 0x000f00 +#define _PAGE_PSIZE_4K 0x000200 +#define _PAGE_PSIZE_8K 0x000300 +#define _PAGE_PSIZE_16K 0x000400 +#define _PAGE_PSIZE_32K 0x000500 +#define _PAGE_PSIZE_64K 0x000600 +#define _PAGE_PSIZE_128K 0x000700 +#define _PAGE_PSIZE_256K 0x000800 +#define _PAGE_PSIZE_512K 0x000900 +#define _PAGE_PSIZE_1M 0x000a00 +#define _PAGE_PSIZE_2M 0x000b00 +#define _PAGE_PSIZE_4M 0x000c00 +#define _PAGE_PSIZE_8M 0x000d00 +#define _PAGE_PSIZE_16M 0x000e00 +#define _PAGE_PSIZE_32M 0x000f00 +#define _PAGE_DIRTY 0x001000 /* C: page changed */ +#define _PAGE_SW0 0x002000 +#define _PAGE_U3 0x004000 +#define _PAGE_U2 0x008000 +#define _PAGE_U1 0x010000 +#define _PAGE_U0 0x020000 +#define _PAGE_ACCESSED 0x040000 +#define _PAGE_ENDIAN 0x080000 +#define _PAGE_GUARDED 0x100000 +#define _PAGE_COHERENT 0x200000 /* M: enforce memory coherence */ +#define _PAGE_NO_CACHE 0x400000 /* I: cache inhibit */ +#define _PAGE_WRITETHRU 0x800000 /* W: cache write-through */ + +/* "Higher level" linux bit combinations */ +#define _PAGE_EXEC _PAGE_BAP_UX /* .. and was cache cleaned */ +#define _PAGE_RW (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ +#define _PAGE_KERNEL_RW (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY) +#define _PAGE_KERNEL_RO (_PAGE_BAP_SR) +#define _PAGE_KERNEL_RWX (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX) +#define _PAGE_KERNEL_ROX (_PAGE_BAP_SR | _PAGE_BAP_SX) +#define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */ + +#define _PAGE_HASHPTE 0 +#define _PAGE_BUSY 0 + +#define _PAGE_SPECIAL _PAGE_SW0 + +/* Flags to be preserved on PTE modifications */ +#define _PAGE_HPTEFLAGS _PAGE_BUSY + +/* Base page size */ +#ifdef CONFIG_PPC_64K_PAGES +#define _PAGE_PSIZE _PAGE_PSIZE_64K +#define PTE_RPN_SHIFT (28) +#else +#define _PAGE_PSIZE _PAGE_PSIZE_4K +#define PTE_RPN_SHIFT (24) +#endif + +#define PTE_WIMGE_SHIFT (19) +#define PTE_BAP_SHIFT (2) + +/* On 32-bit, we never clear the top part of the PTE */ +#ifdef CONFIG_PPC32 +#define _PTE_NONE_MASK 0xffffffff00000000ULL +#define _PMD_PRESENT 0 +#define _PMD_PRESENT_MASK (PAGE_MASK) +#define _PMD_BAD (~PAGE_MASK) +#endif + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */ |