diff options
Diffstat (limited to 'arch/powerpc/include/asm')
| -rw-r--r-- | arch/powerpc/include/asm/eeh.h | 13 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/kvm_book3s.h | 2 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/machdep.h | 9 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/mmu-hash64.h | 169 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/mmu.h | 9 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/paca.h | 2 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/page_64.h | 10 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pci-bridge.h | 9 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pgtable-ppc64-4k.h | 4 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pgtable-ppc64-64k.h | 2 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pgtable-ppc64.h | 19 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pgtable.h | 10 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/ppc-opcode.h | 3 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/processor.h | 4 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/pte-hash64-64k.h | 18 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/reg.h | 1 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/sparsemem.h | 4 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/thread_info.h | 3 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/tlbflush.h | 7 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/uaccess.h | 11 |
20 files changed, 193 insertions, 116 deletions
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 58c5ee61e700..b0ef73882b38 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -45,9 +45,10 @@ struct device_node; * in the corresponding PHB. Therefore, the root PEs should be created * against existing PHBs in on-to-one fashion. */ -#define EEH_PE_PHB 1 /* PHB PE */ -#define EEH_PE_DEVICE 2 /* Device PE */ -#define EEH_PE_BUS 3 /* Bus PE */ +#define EEH_PE_INVALID (1 << 0) /* Invalid */ +#define EEH_PE_PHB (1 << 1) /* PHB PE */ +#define EEH_PE_DEVICE (1 << 2) /* Device PE */ +#define EEH_PE_BUS (1 << 3) /* Bus PE */ #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ @@ -184,7 +185,7 @@ static inline void eeh_unlock(void) typedef void *(*eeh_traverse_func)(void *data, void *flag); int __devinit eeh_phb_pe_create(struct pci_controller *phb); int eeh_add_to_parent_pe(struct eeh_dev *edev); -int eeh_rmv_from_parent_pe(struct eeh_dev *edev); +int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe); void *eeh_pe_dev_traverse(struct eeh_pe *root, eeh_traverse_func fn, void *flag); void eeh_pe_restore_bars(struct eeh_pe *pe); @@ -200,7 +201,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev); void __init eeh_addr_cache_build(void); void eeh_add_device_tree_early(struct device_node *); void eeh_add_device_tree_late(struct pci_bus *); -void eeh_remove_bus_device(struct pci_dev *); +void eeh_remove_bus_device(struct pci_dev *, int); /** * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure. @@ -239,7 +240,7 @@ static inline void eeh_add_device_tree_early(struct device_node *dn) { } static inline void eeh_add_device_tree_late(struct pci_bus *bus) { } -static inline void eeh_remove_bus_device(struct pci_dev *dev) { } +static inline void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) { } static inline void eeh_lock(void) { } static inline void eeh_unlock(void) { } diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index f0e0c6a66d97..7aefdb3e1ce4 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -59,7 +59,7 @@ struct hpte_cache { struct hlist_node list_vpte; struct hlist_node list_vpte_long; struct rcu_head rcu_head; - u64 host_va; + u64 host_vpn; u64 pfn; ulong slot; struct kvmppc_pte pte; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 236b4779ec4f..c4231973edd3 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -34,19 +34,19 @@ struct machdep_calls { char *name; #ifdef CONFIG_PPC64 void (*hpte_invalidate)(unsigned long slot, - unsigned long va, + unsigned long vpn, int psize, int ssize, int local); long (*hpte_updatepp)(unsigned long slot, unsigned long newpp, - unsigned long va, + unsigned long vpn, int psize, int ssize, int local); void (*hpte_updateboltedpp)(unsigned long newpp, unsigned long ea, int psize, int ssize); long (*hpte_insert)(unsigned long hpte_group, - unsigned long va, + unsigned long vpn, unsigned long prpn, unsigned long rflags, unsigned long vflags, @@ -215,6 +215,9 @@ struct machdep_calls { /* Called after scan and before resource survey */ void (*pcibios_fixup_phb)(struct pci_controller *hose); + /* Called during PCI resource reassignment */ + resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); + /* Called to shutdown machine specific hardware not already controlled * by other drivers. */ diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 1c65a59881ea..9673f73eb8db 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -16,6 +16,13 @@ #include <asm/page.h> /* + * This is necessary to get the definition of PGTABLE_RANGE which we + * need for various slices related matters. Note that this isn't the + * complete pgtable.h but only a portion of it. + */ +#include <asm/pgtable-ppc64.h> + +/* * Segment table */ @@ -154,9 +161,25 @@ struct mmu_psize_def #define MMU_SEGSIZE_256M 0 #define MMU_SEGSIZE_1T 1 +/* + * encode page number shift. + * in order to fit the 78 bit va in a 64 bit variable we shift the va by + * 12 bits. This enable us to address upto 76 bit va. + * For hpt hash from a va we can ignore the page size bits of va and for + * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure + * we work in all cases including 4k page size. + */ +#define VPN_SHIFT 12 #ifndef __ASSEMBLY__ +static inline int segment_shift(int ssize) +{ + if (ssize == MMU_SEGSIZE_256M) + return SID_SHIFT; + return SID_SHIFT_1T; +} + /* * The current system page and segment sizes */ @@ -180,18 +203,39 @@ extern unsigned long tce_alloc_start, tce_alloc_end; extern int mmu_ci_restrictions; /* + * This computes the AVPN and B fields of the first dword of a HPTE, + * for use when we want to match an existing PTE. The bottom 7 bits + * of the returned value are zero. + */ +static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize, + int ssize) +{ + unsigned long v; + /* + * The AVA field omits the low-order 23 bits of the 78 bits VA. + * These bits are not needed in the PTE, because the + * low-order b of these bits are part of the byte offset + * into the virtual page and, if b < 23, the high-order + * 23-b of these bits are always used in selecting the + * PTEGs to be searched + */ + v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm); + v <<= HPTE_V_AVPN_SHIFT; + v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT; + return v; +} + +/* * This function sets the AVPN and L fields of the HPTE appropriately * for the page size */ -static inline unsigned long hpte_encode_v(unsigned long va, int psize, - int ssize) +static inline unsigned long hpte_encode_v(unsigned long vpn, + int psize, int ssize) { unsigned long v; - v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm); - v <<= HPTE_V_AVPN_SHIFT; + v = hpte_encode_avpn(vpn, psize, ssize); if (psize != MMU_PAGE_4K) v |= HPTE_V_LARGE; - v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT; return v; } @@ -216,30 +260,37 @@ static inline unsigned long hpte_encode_r(unsigned long pa, int psize) } /* - * Build a VA given VSID, EA and segment size + * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size. */ -static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid, - int ssize) +static inline unsigned long hpt_vpn(unsigned long ea, + unsigned long vsid, int ssize) { - if (ssize == MMU_SEGSIZE_256M) - return (vsid << 28) | (ea & 0xfffffffUL); - return (vsid << 40) | (ea & 0xffffffffffUL); + unsigned long mask; + int s_shift = segment_shift(ssize); + + mask = (1ul << (s_shift - VPN_SHIFT)) - 1; + return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask); } /* * This hashes a virtual address */ - -static inline unsigned long hpt_hash(unsigned long va, unsigned int shift, - int ssize) +static inline unsigned long hpt_hash(unsigned long vpn, + unsigned int shift, int ssize) { + int mask; unsigned long hash, vsid; + /* VPN_SHIFT can be atmost 12 */ if (ssize == MMU_SEGSIZE_256M) { - hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift); + mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1; + hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^ + ((vpn & mask) >> (shift - VPN_SHIFT)); } else { - vsid = va >> 40; - hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift); + mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1; + vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT); + hash = vsid ^ (vsid << 25) ^ + ((vpn & mask) >> (shift - VPN_SHIFT)) ; } return hash & 0x7fffffffffUL; } @@ -280,63 +331,61 @@ extern void slb_set_size(u16 size); #endif /* __ASSEMBLY__ */ /* - * VSID allocation + * VSID allocation (256MB segment) + * + * We first generate a 38-bit "proto-VSID". For kernel addresses this + * is equal to the ESID | 1 << 37, for user addresses it is: + * (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1) * - * We first generate a 36-bit "proto-VSID". For kernel addresses this - * is equal to the ESID, for user addresses it is: - * (context << 15) | (esid & 0x7fff) + * This splits the proto-VSID into the below range + * 0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range + * 2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range * - * The two forms are distinguishable because the top bit is 0 for user - * addresses, whereas the top two bits are 1 for kernel addresses. - * Proto-VSIDs with the top two bits equal to 0b10 are reserved for - * now. + * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1 + * That is, we assign half of the space to user processes and half + * to the kernel. * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: * * VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS - * where VSID_MULTIPLIER = 268435399 = 0xFFFFFC7 - * VSID_MODULUS = 2^36-1 = 0xFFFFFFFFF * - * This scramble is only well defined for proto-VSIDs below - * 0xFFFFFFFFF, so both proto-VSID and actual VSID 0xFFFFFFFFF are - * reserved. VSID_MULTIPLIER is prime, so in particular it is + * VSID_MULTIPLIER is prime, so in particular it is * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. * Because the modulus is 2^n-1 we can compute it efficiently without * a divide or extra multiply (see below). * * This scheme has several advantages over older methods: * - * - We have VSIDs allocated for every kernel address + * - We have VSIDs allocated for every kernel address * (i.e. everything above 0xC000000000000000), except the very top * segment, which simplifies several things. * - * - We allow for 16 significant bits of ESID and 19 bits of - * context for user addresses. i.e. 16T (44 bits) of address space for - * up to half a million contexts. + * - We allow for USER_ESID_BITS significant bits of ESID and + * CONTEXT_BITS bits of context for user addresses. + * i.e. 64T (46 bits) of address space for up to half a million contexts. * - * - The scramble function gives robust scattering in the hash + * - The scramble function gives robust scattering in the hash * table (at least based on some initial results). The previous * method was more susceptible to pathological cases giving excessive * hash collisions. */ + /* - * WARNING - If you change these you must make sure the asm - * implementations in slb_allocate (slb_low.S), do_stab_bolted - * (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly. + * This should be computed such that protovosid * vsid_mulitplier + * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus */ - -#define VSID_MULTIPLIER_256M ASM_CONST(200730139) /* 28-bit prime */ -#define VSID_BITS_256M 36 +#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ +#define VSID_BITS_256M 38 #define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1) #define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_1T 24 +#define VSID_BITS_1T 26 #define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1) #define CONTEXT_BITS 19 -#define USER_ESID_BITS 16 -#define USER_ESID_BITS_1T 4 +#define USER_ESID_BITS 18 +#define USER_ESID_BITS_1T 6 #define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT)) @@ -372,6 +421,8 @@ extern void slb_set_size(u16 size); srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \ add rt,rt,rx +/* 4 bits per slice and we have one slice per 1TB */ +#define SLICE_ARRAY_SIZE (PGTABLE_RANGE >> 41) #ifndef __ASSEMBLY__ @@ -416,7 +467,7 @@ typedef struct { #ifdef CONFIG_PPC_MM_SLICES u64 low_slices_psize; /* SLB page size encodings */ - u64 high_slices_psize; /* 4 bits per slice for now */ + unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; #else u16 sllp; /* SLB page size encoding */ #endif @@ -452,12 +503,32 @@ typedef struct { }) #endif /* 1 */ -/* This is only valid for addresses >= PAGE_OFFSET */ +/* + * This is only valid for addresses >= PAGE_OFFSET + * The proto-VSID space is divided into two class + * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1 + * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1 + * + * With KERNEL_START at 0xc000000000000000, the proto vsid for + * the kernel ends up with 0xc00000000 (36 bits). With 64TB + * support we need to have kernel proto-VSID in the + * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS. + */ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) { - if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble(ea >> SID_SHIFT, 256M); - return vsid_scramble(ea >> SID_SHIFT_1T, 1T); + unsigned long proto_vsid; + /* + * We need to make sure proto_vsid for the kernel is + * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T]) + */ + if (ssize == MMU_SEGSIZE_256M) { + proto_vsid = ea >> SID_SHIFT; + proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS)); + return vsid_scramble(proto_vsid, 256M); + } + proto_vsid = ea >> SID_SHIFT_1T; + proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T)); + return vsid_scramble(proto_vsid, 1T); } /* Returns the segment size indicator for a user address */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index e8a26db2e8f3..5e38eedea218 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -146,6 +146,15 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, extern u64 ppc64_rma_size; #endif /* CONFIG_PPC64 */ +struct mm_struct; +#ifdef CONFIG_DEBUG_VM +extern void assert_pte_locked(struct mm_struct *mm, unsigned long addr); +#else /* CONFIG_DEBUG_VM */ +static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) +{ +} +#endif /* !CONFIG_DEBUG_VM */ + #endif /* !__ASSEMBLY__ */ /* The kernel use the constants below to index in the page sizes array. diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 7796519fd238..e9e7a6999bb8 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -100,7 +100,7 @@ struct paca_struct { /* SLB related definitions */ u16 vmalloc_sllp; u16 slb_cache_ptr; - u16 slb_cache[SLB_CACHE_ENTRIES]; + u32 slb_cache[SLB_CACHE_ENTRIES]; #endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC_BOOK3E diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index fed85e6290e1..cd915d6b093d 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -78,11 +78,19 @@ extern u64 ppc64_pft_size; #define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) #define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) +/* + * 1 bit per slice and we have one slice per 1TB + * Right now we support only 64TB. + * IF we change this we will have to change the type + * of high_slices + */ +#define SLICE_MASK_SIZE 8 + #ifndef __ASSEMBLY__ struct slice_mask { u16 low_slices; - u16 high_slices; + u64 high_slices; }; struct mm_struct; diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 973df4d9d366..025a130729bc 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -182,6 +182,14 @@ static inline int pci_device_from_OF_node(struct device_node *np, #if defined(CONFIG_EEH) static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn) { + /* + * For those OF nodes whose parent isn't PCI bridge, they + * don't have PCI_DN actually. So we have to skip them for + * any EEH operations. + */ + if (!dn || !PCI_DN(dn)) + return NULL; + return PCI_DN(dn)->edev; } #else @@ -192,6 +200,7 @@ static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn) extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn); /** Remove all of the PCI devices under this bus */ +extern void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe); extern void pcibios_remove_pci_devices(struct pci_bus *bus); /** Discover new pci devices under this bus, and add them */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/pgtable-ppc64-4k.h index 6eefdcffa359..12798c9d4b4b 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-4k.h @@ -7,7 +7,7 @@ */ #define PTE_INDEX_SIZE 9 #define PMD_INDEX_SIZE 7 -#define PUD_INDEX_SIZE 7 +#define PUD_INDEX_SIZE 9 #define PGD_INDEX_SIZE 9 #ifndef __ASSEMBLY__ @@ -19,7 +19,7 @@ #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) -#define PTRS_PER_PUD (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 */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h index 90533ddcd703..be4e2878fbc0 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h @@ -7,7 +7,7 @@ #define PTE_INDEX_SIZE 12 #define PMD_INDEX_SIZE 12 #define PUD_INDEX_SIZE 0 -#define PGD_INDEX_SIZE 4 +#define PGD_INDEX_SIZE 6 #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index c4205616dfb5..0182c203e411 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -21,17 +21,6 @@ #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE) -/* Some sanity checking */ -#if TASK_SIZE_USER64 > PGTABLE_RANGE -#error TASK_SIZE_USER64 exceeds pagetable range -#endif - -#ifdef CONFIG_PPC_STD_MMU_64 -#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT)) -#error TASK_SIZE_USER64 exceeds user VSID range -#endif -#endif - /* * Define the address range of the kernel non-linear virtual area */ @@ -41,7 +30,7 @@ #else #define KERN_VIRT_START ASM_CONST(0xD000000000000000) #endif -#define KERN_VIRT_SIZE PGTABLE_RANGE +#define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) /* * The vmalloc space starts at the beginning of that region, and @@ -117,9 +106,6 @@ #ifndef __ASSEMBLY__ -#include <linux/stddef.h> -#include <asm/tlbflush.h> - /* * This is the default implementation of various PTE accessors, it's * used in all cases except Book3S with 64K pages where we have a @@ -198,7 +184,8 @@ /* 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, diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 2e0e4110f7ae..a9cbd3ba5c33 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -9,14 +9,6 @@ struct mm_struct; -#ifdef CONFIG_DEBUG_VM -extern void assert_pte_locked(struct mm_struct *mm, unsigned long addr); -#else /* CONFIG_DEBUG_VM */ -static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) -{ -} -#endif /* !CONFIG_DEBUG_VM */ - #endif /* !__ASSEMBLY__ */ #if defined(CONFIG_PPC64) @@ -27,6 +19,8 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) #ifndef __ASSEMBLY__ +#include <asm/tlbflush.h> + /* Generic accessors to PTE bits */ static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 4c25319f2fbc..5f73ce63fcae 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -126,6 +126,7 @@ #define PPC_INST_TLBIVAX 0x7c000624 #define PPC_INST_TLBSRX_DOT 0x7c0006a5 #define PPC_INST_XXLOR 0xf0000510 +#define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_NAP 0x4c000364 #define PPC_INST_SLEEP 0x4c0003a4 @@ -277,6 +278,8 @@ VSX_XX1((s), a, b)) #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ VSX_XX3((t), a, b)) +#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \ + VSX_XX3((t), (a), (b)))) #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 83efc6e81543..9dc5cd1fde1a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -97,8 +97,8 @@ extern struct task_struct *last_task_used_spe; #endif #ifdef CONFIG_PPC64 -/* 64-bit user address space is 44-bits (16TB user VM) */ -#define TASK_SIZE_USER64 (0x0000100000000000UL) +/* 64-bit user address space is 46-bits (64TB user VM) */ +#define TASK_SIZE_USER64 (0x0000400000000000UL) /* * 32-bit user address space is 4GB - 1 page diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index 59247e816ac5..eedf427c9124 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -58,14 +58,16 @@ /* Trick: we set __end to va + 64k, which happens works for * a 16M page as well as we want only one iteration */ -#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ - do { \ - unsigned long __end = va + PAGE_SIZE; \ - unsigned __split = (psize == MMU_PAGE_4K || \ - psize == MMU_PAGE_64K_AP); \ - shift = mmu_psize_defs[psize].shift; \ - for (index = 0; va < __end; index++, va += (1L << shift)) { \ - if (!__split || __rpte_sub_valid(rpte, index)) do { \ +#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift) \ + do { \ + unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT)); \ + unsigned __split = (psize == MMU_PAGE_4K || \ + psize == MMU_PAGE_64K_AP); \ + shift = mmu_psize_defs[psize].shift; \ + for (index = 0; vpn < __end; index++, \ + vpn += (1L << (shift - VPN_SHIFT))) { \ + if (!__split || __rpte_sub_valid(rpte, index)) \ + do { #define pte_iterate_hashed_end() } while(0); } } while(0) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 121a90bbf778..a1096fb62816 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -524,6 +524,7 @@ #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ +#define HSRR1_DENORM 0x00100000 /* Denorm exception */ #define SPRN_TBCTL 0x35f /* PA6T Timebase control register */ #define TBCTL_FREEZE 0x0000000000000000ull /* Freeze all tbs */ diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 0c5fa3145615..f6fc0ee813d7 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -10,8 +10,8 @@ */ #define SECTION_SIZE_BITS 24 -#define MAX_PHYSADDR_BITS 44 -#define MAX_PHYSMEM_BITS 44 +#define MAX_PHYSADDR_BITS 46 +#define MAX_PHYSMEM_BITS 46 #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index e942203cd4a8..8ceea14d6fe4 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -104,6 +104,8 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ #define TIF_UPROBE 14 /* breakpointed or single-stepping */ #define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ +#define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation + for stack store? */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -121,6 +123,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) +#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) #define _TIF_SYSCALL_T_OR_A (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 81143fcbd113..61a59271665b 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -95,7 +95,7 @@ struct ppc64_tlb_batch { unsigned long index; struct mm_struct *mm; real_pte_t pte[PPC64_TLB_BATCH_NR]; - unsigned long vaddr[PPC64_TLB_BATCH_NR]; + unsigned long vpn[PPC64_TLB_BATCH_NR]; unsigned int psize; int ssize; }; @@ -103,9 +103,6 @@ DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch); -extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, unsigned long pte, int huge); - #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) @@ -127,7 +124,7 @@ static inline void arch_leave_lazy_mmu_mode(void) #define arch_flush_lazy_mmu_mode() do {} while (0) -extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize, +extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, int local); extern void flush_hash_range(unsigned long number, int local); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 17bb40cad5bf..4db49590acf5 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -98,11 +98,6 @@ struct exception_table_entry { * PowerPC, we can just do these as direct assignments. (Of course, the * exception handling means that it's no longer "just"...) * - * The "user64" versions of the user access functions are versions that - * allow access of 64-bit data. The "get_user" functions do not - * properly handle 64-bit data because the value gets down cast to a long. - * The "put_user" functions already handle 64-bit data properly but we add - * "user64" versions for completeness */ #define get_user(x, ptr) \ __get_user_check((x), (ptr), sizeof(*(ptr))) @@ -114,12 +109,6 @@ struct exception_table_entry { #define __put_user(x, ptr) \ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -#ifndef __powerpc64__ -#define __get_user64(x, ptr) \ - __get_user64_nocheck((x), (ptr), sizeof(*(ptr))) -#define __put_user64(x, ptr) __put_user(x, ptr) -#endif - #define __get_user_inatomic(x, ptr) \ __get_user_nosleep((x), (ptr), sizeof(*(ptr))) #define __put_user_inatomic(x, ptr) \ |