diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-17 12:58:52 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-17 12:58:52 -0800 |
| commit | 0cbeafb245ca568bc0765645aa64f0451b716657 (patch) | |
| tree | 663c09ff5a62a1b2b66a17c4dfe0413603530a36 /arch | |
| parent | 58cf279acac3080ce03eeea5ca268210b3165fe1 (diff) | |
| parent | 06b031de22d28ae76b2e5bfaf22c56a265a1e106 (diff) | |
| download | op-kernel-dev-0cbeafb245ca568bc0765645aa64f0451b716657.zip op-kernel-dev-0cbeafb245ca568bc0765645aa64f0451b716657.tar.gz | |
Merge branch 'akpm' (patches from Andrew)
Merge second patch-bomb from Andrew Morton:
- more MM stuff:
- Kirill's page-flags rework
- Kirill's now-allegedly-fixed THP rework
- MADV_FREE implementation
- DAX feature work (msync/fsync). This isn't quite complete but DAX
is new and it's good enough and the guys have a handle on what
needs to be done - I expect this to be wrapped in the next week or
two.
- some vsprintf maintenance work
- various other misc bits
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (145 commits)
printk: change recursion_bug type to bool
lib/vsprintf: factor out %pN[F] handler as netdev_bits()
lib/vsprintf: refactor duplicate code to special_hex_number()
printk-formats.txt: remove unimplemented %pT
printk: help pr_debug and pr_devel to optimize out arguments
lib/test_printf.c: test dentry printing
lib/test_printf.c: add test for large bitmaps
lib/test_printf.c: account for kvasprintf tests
lib/test_printf.c: add a few number() tests
lib/test_printf.c: test precision quirks
lib/test_printf.c: check for out-of-bound writes
lib/test_printf.c: don't BUG
lib/kasprintf.c: add sanity check to kvasprintf
lib/vsprintf.c: warn about too large precisions and field widths
lib/vsprintf.c: help gcc make number() smaller
lib/vsprintf.c: expand field_width to 24 bits
lib/vsprintf.c: eliminate potential race in string()
lib/vsprintf.c: move string() below widen_string()
lib/vsprintf.c: pull out padding code from dentry_name()
printk: do cond_resched() between lines while outputting to consoles
...
Diffstat (limited to 'arch')
82 files changed, 286 insertions, 485 deletions
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index f2f9496..ab336c0 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -47,8 +47,10 @@ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_SPACEAVAIL 5 /* ensure resources are available */ #define MADV_DONTNEED 6 /* don't need these pages */ +#define MADV_FREE 7 /* free pages only if memory pressure */ /* common/generic parameters */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6312f60..76dde9d 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -73,9 +73,6 @@ config STACKTRACE_SUPPORT def_bool y select STACKTRACE -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y depends on ARC_MMU_V4 diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index ff7ff6c..b65f797 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -617,7 +617,7 @@ void flush_dcache_page(struct page *page) */ if (!mapping_mapped(mapping)) { clear_bit(PG_dc_clean, &page->flags); - } else if (page_mapped(page)) { + } else if (page_mapcount(page)) { /* kernel reading from page with U-mapping */ phys_addr_t paddr = (unsigned long)page_address(page); @@ -857,7 +857,7 @@ void copy_user_highpage(struct page *to, struct page *from, * For !VIPT cache, all of this gets compiled out as * addr_not_cache_congruent() is 0 */ - if (page_mapped(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { + if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { __flush_dcache_page((unsigned long)kfrom, u_vaddr); clean_src_k_mappings = 1; } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4e489cc..6a889af 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -168,11 +168,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - bool - depends on !SMP - default y - config LOCKDEP_SUPPORT bool default y diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 9203c21..a520b79 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { @@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte) static inline void __kvm_flush_dcache_pmd(pmd_t pmd) { unsigned long size = PMD_SIZE; - pfn_t pfn = pmd_pfn(pmd); + kvm_pfn_t pfn = pmd_pfn(pmd); while (size) { void *va = kmap_atomic_pfn(pfn); diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a..dc46398 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -88,7 +88,6 @@ #define L_PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) #define L_PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) -#define L_PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) #define L_PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) #define L_PMD_SECT_RDONLY (_AT(pteval_t, 1) << 58) @@ -232,13 +231,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) -#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING)) - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); -#endif #endif #define PMD_BIT_FUNC(fn,op) \ @@ -246,9 +238,9 @@ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } PMD_BIT_FUNC(wrprotect, |= L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); -PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING); PMD_BIT_FUNC(mkwrite, &= ~L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkdirty, |= L_PMD_SECT_DIRTY); +PMD_BIT_FUNC(mkclean, &= ~L_PMD_SECT_DIRTY); PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 22f7fa0..aba61fd 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -992,9 +992,9 @@ out: return ret; } -static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) +static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; if (PageTransCompound(pfn_to_page(pfn))) { @@ -1201,7 +1201,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, unsigned long size, bool uncached) { __coherent_cache_guest_page(vcpu, pfn, size, uncached); @@ -1218,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; - pfn_t pfn; + kvm_pfn_t pfn; pgprot_t mem_type = PAGE_S2; bool fault_ipa_uncached; bool logging_active = memslot_is_logging(memslot); @@ -1346,7 +1346,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { pmd_t *pmd; pte_t *pte; - pfn_t pfn; + kvm_pfn_t pfn; bool pfn_valid = false; trace_kvm_access_fault(fault_ipa); diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 588bbc2..6bd1089 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -52,14 +52,13 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) * * Lock the page table for the destination and check * to see that it's still huge and whether or not we will - * need to fault on write, or if we have a splitting THP. + * need to fault on write. */ if (unlikely(pmd_thp_or_huge(*pmd))) { ptl = ¤t->mm->page_table_lock; spin_lock(ptl); if (unlikely(!pmd_thp_or_huge(*pmd) - || pmd_hugewillfault(*pmd) - || pmd_trans_splitting(*pmd))) { + || pmd_hugewillfault(*pmd))) { spin_unlock(ptl); return 0; } diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1ec8e75..d0ba3551 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -330,7 +330,7 @@ void flush_dcache_page(struct page *page) mapping = page_mapping(page); if (!cache_ops_need_broadcast() && - mapping && !page_mapped(page)) + mapping && !page_mapcount(page)) clear_bit(PG_dcache_clean, &page->flags); else { __flush_dcache_page(mapping, page); @@ -415,18 +415,3 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l */ __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); } - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - pmd_t pmd = pmd_mksplitting(*pmdp); - VM_BUG_ON(address & ~PMD_MASK); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - - /* dummy IPI to serialise against fast_gup */ - kick_all_cpus_sync(); -} -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 0bf8b43..7364339 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -230,7 +230,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 69d2e2f..2d545d7a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -353,21 +353,14 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) -#define pmd_trans_splitting(pmd) pte_special(pmd_pte(pmd)) -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -struct vm_area_struct; -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) -#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK)) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 46649d6..60585bd 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -102,19 +102,3 @@ EXPORT_SYMBOL(flush_dcache_page); * Additional functions defined in assembly. */ EXPORT_SYMBOL(flush_icache_range); - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - pmd_t pmd = pmd_mksplitting(*pmdp); - - VM_BUG_ON(address & ~PMD_MASK); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - - /* dummy IPI to serialise against fast_gup */ - kick_all_cpus_sync(); -} -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/avr32/include/asm/page.h b/arch/avr32/include/asm/page.h index f805d1c..c5d2a3e 100644 --- a/arch/avr32/include/asm/page.h +++ b/arch/avr32/include/asm/page.h @@ -83,11 +83,9 @@ static inline int get_order(unsigned long size) #ifndef CONFIG_NEED_MULTIPLE_NODES -#define PHYS_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT) +#define ARCH_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT) -#define pfn_to_page(pfn) (mem_map + ((pfn) - PHYS_PFN_OFFSET)) -#define page_to_pfn(page) ((unsigned long)((page) - mem_map) + PHYS_PFN_OFFSET) -#define pfn_valid(pfn) ((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr)) +#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr)) #endif /* CONFIG_NEED_MULTIPLE_NODES */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) @@ -101,4 +99,6 @@ static inline int get_order(unsigned long size) */ #define HIGHMEM_START 0x20000000UL +#include <asm-generic/memory_model.h> + #endif /* __ASM_AVR32_PAGE_H */ diff --git a/arch/frv/include/asm/page.h b/arch/frv/include/asm/page.h index 8c97068..688d807 100644 --- a/arch/frv/include/asm/page.h +++ b/arch/frv/include/asm/page.h @@ -34,7 +34,7 @@ typedef struct page *pgtable_t; #define pgprot_val(x) ((x).pgprot) #define __pte(x) ((pte_t) { (x) } ) -#define __pmd(x) ((pmd_t) { (x) } ) +#define __pmd(x) ((pmd_t) { { (x) } } ) #define __pud(x) ((pud_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h index ec48bb9..e8c486e 100644 --- a/arch/ia64/include/asm/page.h +++ b/arch/ia64/include/asm/page.h @@ -105,6 +105,7 @@ extern struct page *vmem_map; #ifdef CONFIG_DISCONTIGMEM # define page_to_pfn(page) ((unsigned long) (page - vmem_map)) # define pfn_to_page(pfn) (vmem_map + (pfn)) +# define __pfn_to_phys(pfn) PFN_PHYS(pfn) #else # include <asm-generic/memory_model.h> #endif diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 0b389a8..a0fa88d 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -36,9 +36,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 0bce820..5ecd028 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -67,9 +67,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6ded8d3..7c19144 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -101,9 +101,9 @@ #define CAUSEF_DC (_ULCAST_(1) << 27) extern atomic_t kvm_mips_instance; -extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn); -extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn); -extern bool(*kvm_mips_is_error_pfn) (pfn_t pfn); +extern kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +extern void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); +extern bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); struct kvm_vm_stat { u32 remote_tlb_flush; diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index ff7ad91..97b3138 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -131,14 +131,12 @@ /* Huge TLB page */ #define _PAGE_HUGE_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #define _PAGE_HUGE (1 << _PAGE_HUGE_SHIFT) -#define _PAGE_SPLITTING_SHIFT (_PAGE_HUGE_SHIFT + 1) -#define _PAGE_SPLITTING (1 << _PAGE_SPLITTING_SHIFT) #endif /* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */ #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) /* XI - page cannot be executed */ -#ifdef _PAGE_SPLITTING_SHIFT -#define _PAGE_NO_EXEC_SHIFT (_PAGE_SPLITTING_SHIFT + 1) +#ifdef _PAGE_HUGE_SHIFT +#define _PAGE_NO_EXEC_SHIFT (_PAGE_HUGE_SHIFT + 1) #else #define _PAGE_NO_EXEC_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #endif @@ -153,8 +151,8 @@ #if defined(_PAGE_NO_READ_SHIFT) #define _PAGE_GLOBAL_SHIFT (_PAGE_NO_READ_SHIFT + 1) -#elif defined(_PAGE_SPLITTING_SHIFT) -#define _PAGE_GLOBAL_SHIFT (_PAGE_SPLITTING_SHIFT + 1) +#elif defined(_PAGE_HUGE_SHIFT) +#define _PAGE_GLOBAL_SHIFT (_PAGE_HUGE_SHIFT + 1) #else #define _PAGE_GLOBAL_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #endif diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 8957f15..6995b4a 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -482,27 +482,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) return pmd; } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return !!(pmd_val(pmd) & _PAGE_SPLITTING); -} - -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_SPLITTING; - - return pmd; -} - extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -/* Extern to avoid header file madness */ -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 97c03f4..b0ebe59 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -73,8 +73,10 @@ #define MADV_SEQUENTIAL 2 /* expect sequential page references */ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_DONTNEED 4 /* don't need these pages */ +#define MADV_FREE 5 /* free pages only if memory pressure */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 41b1b09..1b675c7 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1525,7 +1525,7 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; unsigned long pa; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; gfn = va >> PAGE_SHIFT; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index aed0ac2..570479c 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -38,13 +38,13 @@ atomic_t kvm_mips_instance; EXPORT_SYMBOL(kvm_mips_instance); /* These function pointers are initialized once the KVM module is loaded */ -pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); EXPORT_SYMBOL(kvm_mips_gfn_to_pfn); -void (*kvm_mips_release_pfn_clean)(pfn_t pfn); +void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_release_pfn_clean); -bool (*kvm_mips_is_error_pfn)(pfn_t pfn); +bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_is_error_pfn); uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) @@ -144,7 +144,7 @@ EXPORT_SYMBOL(kvm_mips_dump_guest_tlbs); static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) { int srcu_idx, err = 0; - pfn_t pfn; + kvm_pfn_t pfn; if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE) return 0; @@ -262,7 +262,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { gfn_t gfn; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long vaddr = 0; unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; int even; @@ -313,7 +313,7 @@ EXPORT_SYMBOL(kvm_mips_handle_kseg0_tlb_fault); int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long flags, old_entryhi = 0, vaddr = 0; unsigned long entrylo0 = 0, entrylo1 = 0; @@ -360,7 +360,7 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, { unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; if ((tlb->tlb_hi & VPN2_MASK) == 0) { pfn0 = 0; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5d3a25e..caac3d7 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -587,7 +587,8 @@ static inline void local_r4k_flush_cache_page(void *args) * another ASID than the current one. */ map_coherent = (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)); + page_mapcount(page) && + !Page_dcache_dirty(page)); if (map_coherent) vaddr = kmap_coherent(page, addr); else diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index aab218c..3f159ca 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -106,7 +106,7 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) unsigned long addr = (unsigned long) page_address(page); if (pages_do_alias(addr, vmaddr)) { - if (page_mapped(page) && !Page_dcache_dirty(page)) { + if (page_mapcount(page) && !Page_dcache_dirty(page)) { void *kaddr; kaddr = kmap_coherent(page, vmaddr); diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c index 349995d..1afd87c 100644 --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -87,8 +87,6 @@ static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -109,18 +107,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_huge(pmd))) { if (!gup_huge_pmd(pmd, addr, next, write, pages,nr)) @@ -153,8 +140,6 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 8770e61..7e5fa09 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -165,7 +165,7 @@ void copy_user_highpage(struct page *to, struct page *from, vto = kmap_atomic(to); if (cpu_has_dc_aliases && - page_mapped(from) && !Page_dcache_dirty(from)) { + page_mapcount(from) && !Page_dcache_dirty(from)) { vfrom = kmap_coherent(from, vaddr); copy_page(vto, vfrom); kunmap_coherent(); @@ -187,7 +187,7 @@ void copy_to_user_page(struct vm_area_struct *vma, unsigned long len) { if (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)) { + page_mapcount(page) && !Page_dcache_dirty(page)) { void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(vto, src, len); kunmap_coherent(); @@ -205,7 +205,7 @@ void copy_from_user_page(struct vm_area_struct *vma, unsigned long len) { if (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)) { + page_mapcount(page) && !Page_dcache_dirty(page)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); kunmap_coherent(); diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c index e8adc00..ce4473e 100644 --- a/arch/mips/mm/pgtable-64.c +++ b/arch/mips/mm/pgtable-64.c @@ -62,20 +62,6 @@ void pmd_init(unsigned long addr, unsigned long pagetable) } #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp) -{ - if (!pmd_trans_splitting(*pmdp)) { - pmd_t pmd = pmd_mksplitting(*pmdp); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - } -} - -#endif - pmd_t mk_pmd(struct page *page, pgprot_t prot) { pmd_t pmd; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 32e0be2..482192c 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -240,7 +240,6 @@ static void output_pgtable_bits_defines(void) pr_define("_PAGE_MODIFIED_SHIFT %d\n", _PAGE_MODIFIED_SHIFT); #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT); - pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT); #endif #ifdef CONFIG_CPU_MIPSR2 if (cpu_has_rixi) { diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h index 8288e12..3810a6f 100644 --- a/arch/mn10300/include/asm/page.h +++ b/arch/mn10300/include/asm/page.h @@ -107,6 +107,7 @@ static inline int get_order(unsigned long size) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) #define pfn_to_page(pfn) (mem_map + ((pfn) - __pfn_disp)) #define page_to_pfn(page) ((unsigned long)((page) - mem_map) + __pfn_disp) +#define __pfn_to_phys(pfn) PFN_PHYS(pfn) #define pfn_valid(pfn) \ ({ \ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 729f891..7c34caf 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -79,9 +79,6 @@ config TIME_LOW_RES depends on SMP default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - # unless you want to implement ACPI on PA-RISC ... ;-) config PM bool diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index dd4d187..cf830d4 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -43,8 +43,10 @@ #define MADV_SPACEAVAIL 5 /* insure that resources are reserved */ #define MADV_VPS_PURGE 6 /* Purge pages from VM page cache */ #define MADV_VPS_INHERIT 7 /* Inherit parents page size */ +#define MADV_FREE 8 /* free pages only if memory pressure */ /* common/generic parameters */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7d5a835..94f6c50 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -47,9 +47,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config TRACE_IRQFLAGS_SUPPORT bool default y diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 9e55e3b..849bbec 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -256,13 +256,6 @@ static inline int pmd_trans_huge(pmd_t pmd) (_PAGE_PTE | _PAGE_THP_HUGE)); } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - if (pmd_trans_huge(pmd)) - return pmd_val(pmd) & _PAGE_SPLITTING; - return 0; -} - static inline int pmd_large(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_PTE); @@ -273,11 +266,6 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT); } -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - return __pmd(pmd_val(pmd) | _PAGE_SPLITTING); -} - #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 2ff8b3d..06f17e7 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -41,11 +41,6 @@ #endif /* - * THP pages can't be special. So use the _PAGE_SPECIAL - */ -#define _PAGE_SPLITTING _PAGE_SPECIAL - -/* * We need to differentiate between explicit huge page and THP huge * page, since THP huge page also need to track real subpage details */ @@ -54,9 +49,8 @@ /* * set of bits not changed in pmd_modify. */ -#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ - _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ - _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY) +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_THP_HUGE) #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index b3a5bad..8204b0c 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -223,9 +223,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) @@ -266,10 +268,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); - extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmdp_collapse_flush pmdp_collapse_flush diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 9fac01c..8f39796 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -154,8 +154,8 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); -extern pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, - bool *writable); +extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, + bool writing, bool *writable); extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, unsigned long *rmap, long pte_index, int realmode); extern void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c6ef05b..2241d53 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -515,7 +515,7 @@ void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); -static inline void kvmppc_mmu_flush_icache(pfn_t pfn) +static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) { struct page *page; /* diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 099c79d..638c6d9 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -366,7 +366,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter); -pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, +kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, bool *writable) { ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM; @@ -379,9 +379,9 @@ pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, gpa &= ~0xFFFULL; if (unlikely(mp_pa) && unlikely((gpa & KVM_PAM) == mp_pa)) { ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); if (writable) *writable = true; diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index d5c9bfe..55c4d51 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -142,7 +142,7 @@ extern char etext[]; int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { - pfn_t hpaddr; + kvm_pfn_t hpaddr; u64 vpn; u64 vsid; struct kvmppc_sid_map *map; diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 79ad35a..913cd21 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -83,7 +83,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { unsigned long vpn; - pfn_t hpaddr; + kvm_pfn_t hpaddr; ulong hash, hpteg; u64 vsid; int ret; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 72920be..94f04fc 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -41,7 +41,7 @@ enum vcpu_ftr { #define E500_TLB_MAS2_ATTR (0x7f) struct tlbe_ref { - pfn_t pfn; /* valid only for TLB0, except briefly */ + kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 34c43ff..b0333cc 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -163,9 +163,9 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu) struct kvm_book3e_206_tlb_entry magic; ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; unsigned int stid; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); preempt_disable(); @@ -246,7 +246,7 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; @@ -309,7 +309,7 @@ static void kvmppc_e500_setup_stlbe( int tsize, struct tlbe_ref *ref, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; BUG_ON(!(ref->flags & E500_TLB_VALID)); diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h index 810507c..d44f324 100644 --- a/arch/powerpc/kvm/trace_pr.h +++ b/arch/powerpc/kvm/trace_pr.h @@ -30,7 +30,7 @@ TRACE_EVENT(kvm_book3s_reenter, #ifdef CONFIG_PPC_BOOK3S_64 TRACE_EVENT(kvm_book3s_64_mmu_map, - TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr, + TP_PROTO(int rflags, ulong hpteg, ulong va, kvm_pfn_t hpaddr, struct kvmppc_pte *orig_pte), TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte), diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index baf1301..49b152b 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -39,9 +39,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, /* If PMD busy, retry the access */ if (unlikely(old_pmd & _PAGE_BUSY)) return 0; - /* If PMD is trans splitting retry the access */ - if (unlikely(old_pmd & _PAGE_SPLITTING)) - return 0; /* If PMD permissions don't match, take page fault */ if (unlikely(access & ~old_pmd)) return 1; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 61b8b7c..744e24b 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -958,10 +958,6 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, /* * A hugepage collapse is captured by pmd_none, because * it mark the pmd none and do a hpte invalidate. - * - * We don't worry about pmd_trans_splitting here, The - * caller if it needs to handle the splitting case - * should check for that. */ if (pmd_none(pmd)) return NULL; @@ -999,7 +995,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, { unsigned long mask; unsigned long pte_end; - struct page *head, *page, *tail; + struct page *head, *page; pte_t pte; int refs; @@ -1022,7 +1018,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, head = pte_page(pte); page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -1044,15 +1039,5 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index ea6bc31..3124a20 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -604,55 +604,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, } /* - * We mark the pmd splitting and invalidate all the hpte - * entries for this hugepage. - */ -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - unsigned long old, tmp; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - -#ifdef CONFIG_DEBUG_VM - WARN_ON(!pmd_trans_huge(*pmdp)); - assert_spin_locked(&vma->vm_mm->page_table_lock); -#endif - -#ifdef PTE_ATOMIC_UPDATES - - __asm__ __volatile__( - "1: ldarx %0,0,%3\n\ - andi. %1,%0,%6\n\ - bne- 1b \n\ - oris %1,%0,%4@h \n\ - stdcx. %1,0,%3 \n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "i" (_PAGE_SPLITTING), "m" (*pmdp), "i" (_PAGE_BUSY) - : "cc" ); -#else - old = pmd_val(*pmdp); - *pmdp = __pmd(old | _PAGE_SPLITTING); -#endif - /* - * If we didn't had the splitting flag set, go and flush the - * HPTE entries. - */ - trace_hugepage_splitting(address, old); - if (!(old & _PAGE_SPLITTING)) { - /* We need to flush the hpte */ - if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old); - } - /* - * This ensures that generic code that rely on IRQ disabling - * to prevent a parallel THP split work as expected. - */ - kick_all_cpus_sync(); -} - -/* * We want to put the pgtable in pmd and use pgtable for tracking * the base page size hptes */ diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index fa9fb5b..d554351 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -135,7 +135,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); return 0; } diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index c713b34..0d112b9 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -43,6 +43,7 @@ #include <linux/types.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/pfn_t.h> #include <asm/page.h> #include <asm/prom.h> @@ -142,15 +143,13 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) */ static long axon_ram_direct_access(struct block_device *device, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct axon_ram_bank *bank = device->bd_disk->private_data; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; - void *addr = (void *)(bank->ph_addr + offset); - - *kaddr = (void __pmem *)addr; - *pfn = virt_to_phys(addr) >> PAGE_SHIFT; + *kaddr = (void __pmem __force *) bank->io_addr + offset; + *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV); return bank->size - offset; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2449034..dbeeb3a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -10,9 +10,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK bool diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 024f85f..64ead80 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -286,7 +286,6 @@ static inline int is_module_addr(void *addr) #define _SEGMENT_ENTRY_DIRTY 0x2000 /* SW segment dirty bit */ #define _SEGMENT_ENTRY_YOUNG 0x1000 /* SW segment young bit */ -#define _SEGMENT_ENTRY_SPLIT 0x0800 /* THP splitting bit */ #define _SEGMENT_ENTRY_LARGE 0x0400 /* STE-format control, large page */ #define _SEGMENT_ENTRY_READ 0x0002 /* SW segment read bit */ #define _SEGMENT_ENTRY_WRITE 0x0001 /* SW segment write bit */ @@ -318,8 +317,6 @@ static inline int is_module_addr(void *addr) * SW-bits: y young, d dirty, r read, w write */ -#define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */ - /* Page status table bits for virtualization */ #define PGSTE_ACC_BITS 0xf000000000000000UL #define PGSTE_FP_BIT 0x0800000000000000UL @@ -523,10 +520,6 @@ static inline int pmd_bad(pmd_t pmd) return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, @@ -1424,8 +1417,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) if (pmd_large(pmd)) { pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | - _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SPLIT | - _SEGMENT_ENTRY_SOFT_DIRTY; + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; pmd_val(pmd) |= massage_pgprot_pmd(newprot); if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; @@ -1533,12 +1525,6 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, #define __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) && - (pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT); -} - static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 21c74a7..13dab0c 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -55,7 +55,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask, result; - struct page *head, *page, *tail; + struct page *head, *page; int refs; result = write ? 0 : _SEGMENT_ENTRY_PROTECT; @@ -67,7 +67,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -88,16 +87,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -116,16 +105,7 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, pmd = *pmdp; barrier(); next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush() has to serialize with - * smp_call_function() against our disabled IRQs, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd))) { /* diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index aa34af0..a809fa8 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -578,17 +578,29 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr, { unsigned long vmaddr; int rc; + bool unlocked; down_read(&gmap->mm->mmap_sem); + +retry: + unlocked = false; vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) { rc = vmaddr; goto out_up; } - if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags)) { + if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, + &unlocked)) { rc = -EFAULT; goto out_up; } + /* + * In the case that fixup_user_fault unlocked the mmap_sem during + * faultin redo __gmap_translate to not race with a map/unmap_segment. + */ + if (unlocked) + goto retry; + rc = __gmap_link(gmap, gaddr, vmaddr); out_up: up_read(&gmap->mm->mmap_sem); @@ -714,12 +726,14 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len) spinlock_t *ptl; pte_t *ptep, entry; pgste_t pgste; + bool unlocked; int rc = 0; if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK)) return -EINVAL; down_read(&gmap->mm->mmap_sem); while (len) { + unlocked = false; /* Convert gmap address and connect the page tables */ addr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(addr)) { @@ -727,10 +741,14 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len) break; } /* Get the page mapped */ - if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) { + if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE, + &unlocked)) { rc = -EFAULT; break; } + /* While trying to map mmap_sem got unlocked. Let us retry */ + if (unlocked) + continue; rc = __gmap_link(gmap, gaddr, addr); if (rc) break; @@ -791,9 +809,11 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, spinlock_t *ptl; pgste_t old, new; pte_t *ptep; + bool unlocked; down_read(&mm->mmap_sem); retry: + unlocked = false; ptep = get_locked_pte(mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); @@ -802,7 +822,12 @@ retry: if (!(pte_val(*ptep) & _PAGE_INVALID) && (pte_val(*ptep) & _PAGE_PROTECT)) { pte_unmap_unlock(ptep, ptl); - if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + /* + * We do not really care about unlocked. We will retry either + * way. But this allows fixup_user_fault to enable userfaultfd. + */ + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE, + &unlocked)) { up_read(&mm->mmap_sem); return -EFAULT; } @@ -1305,22 +1330,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, return 1; } -static void pmdp_splitting_flush_sync(void *arg) -{ - /* Simply deliver the interrupt */ -} - -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT, - (unsigned long *) pmdp)) { - /* need to serialize against gup-fast (IRQ disabled) */ - smp_call_function(pmdp_splitting_flush_sync, NULL, 1); - } -} - void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d514df7e..6c391a5 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -130,9 +130,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 51d8f7f..58aaa4f 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -241,7 +241,7 @@ static void sh4_flush_cache_page(void *args) */ map_coherent = (current_cpu_data.dcache.n_aliases && test_bit(PG_dcache_clean, &page->flags) && - page_mapped(page)); + page_mapcount(page)); if (map_coherent) vaddr = kmap_coherent(page, address); else diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index f770e39..e58cfbf 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -59,7 +59,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(vto, src, len); @@ -78,7 +78,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); @@ -97,7 +97,7 @@ void copy_user_highpage(struct page *to, struct page *from, vto = kmap_atomic(to); - if (boot_cpu_data.dcache.n_aliases && page_mapped(from) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(from) && test_bit(PG_dcache_clean, &from->flags)) { vfrom = kmap_coherent(from, vaddr); copy_page(vto, vfrom); @@ -153,7 +153,7 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) unsigned long addr = (unsigned long) page_address(page); if (pages_do_alias(addr, vmaddr)) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *kaddr; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 56442d2..3203e42 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -101,10 +101,6 @@ config LOCKDEP_SUPPORT bool default y if SPARC64 -config HAVE_LATENCYTOP_SUPPORT - bool - default y if SPARC64 - config ARCH_HIBERNATION_POSSIBLE def_bool y if SPARC64 diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 131d36f..7a38d6a 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -681,13 +681,6 @@ static inline unsigned long pmd_trans_huge(pmd_t pmd) return pte_val(pte) & _PAGE_PMD_HUGE; } -static inline unsigned long pmd_trans_splitting(pmd_t pmd) -{ - pte_t pte = __pte(pmd_val(pmd)); - - return pmd_trans_huge(pmd) && pte_special(pte); -} - #define has_transparent_hugepage() 1 static inline pmd_t pmd_mkold(pmd_t pmd) @@ -717,29 +710,29 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mkyoung(pmd_t pmd) +static inline pmd_t pmd_mkclean(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkyoung(pte); + pte = pte_mkclean(pte); return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +static inline pmd_t pmd_mkyoung(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkwrite(pte); + pte = pte_mkyoung(pte); return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mksplitting(pmd_t pmd) +static inline pmd_t pmd_mkwrite(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkspecial(pte); + pte = pte_mkwrite(pte); return __pmd(pte_val(pte)); } diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index dbabe57..cb841a3 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -113,9 +113,6 @@ static unsigned int get_user_insn(unsigned long tpc) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmdp)) { - if (pmd_trans_splitting(*pmdp)) - goto out_irq_enable; - pa = pmd_pfn(*pmdp) << PAGE_SHIFT; pa += tpc & ~HPAGE_MASK; diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 2e5c4fc..eb3d8e8 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -56,8 +56,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, put_page(head); return 0; } - if (head != page) - get_huge_page_tail(page); pages[*nr] = page; (*nr)++; @@ -70,7 +68,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (!(pmd_val(pmd) & _PAGE_VALID)) @@ -82,7 +80,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -103,15 +100,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -126,7 +114,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd))) { if (!gup_huge_pmd(pmdp, pmd, addr, next, diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h index 2b05ccb..96cecf5 100644 --- a/arch/tile/include/asm/pgtable.h +++ b/arch/tile/include/asm/pgtable.h @@ -489,16 +489,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 #define pmd_trans_huge pmd_huge_page - -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - return pte_pmd(hv_pte_set_client2(pmd_pte(pmd))); -} - -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return hv_pte_get_client2(pmd_pte(pmd)); -} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h index 71c5d13..e13d41c 100644 --- a/arch/um/include/asm/page.h +++ b/arch/um/include/asm/page.h @@ -18,6 +18,7 @@ struct page; +#include <linux/pfn.h> #include <linux/types.h> #include <asm/vm-flags.h> @@ -52,7 +53,6 @@ typedef struct { unsigned long pgd; } pgd_t; #define pmd_val(x) ((x).pmd) #define __pmd(x) ((pmd_t) { (x) } ) -typedef unsigned long long pfn_t; typedef unsigned long long phys_t; #else @@ -76,7 +76,6 @@ typedef struct { unsigned long pmd; } pmd_t; #define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE)) #define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot)) -typedef unsigned long pfn_t; typedef unsigned long phys_t; #endif @@ -109,8 +108,8 @@ extern unsigned long uml_physmem; #define __pa(virt) to_phys((void *) (unsigned long) (virt)) #define __va(phys) to_virt((unsigned long) (phys)) -#define phys_to_pfn(p) ((pfn_t) ((p) >> PAGE_SHIFT)) -#define pfn_to_phys(pfn) ((phys_t) ((pfn) << PAGE_SHIFT)) +#define phys_to_pfn(p) ((p) >> PAGE_SHIFT) +#define pfn_to_phys(pfn) PFN_PHYS(pfn) #define pfn_valid(pfn) ((pfn) < max_mapnr) #define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v))) diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 2b4274e..bae8523 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -98,7 +98,7 @@ static inline unsigned long pte_pfn(pte_t pte) return phys_to_pfn(pte_val(pte)); } -static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot) +static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { pte_t pte; phys_t phys = pfn_to_phys(page_nr); @@ -107,7 +107,7 @@ static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot) return pte; } -static inline pmd_t pfn_pmd(pfn_t page_nr, pgprot_t pgprot) +static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); } diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 18eb992..7485398 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -271,7 +271,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) #define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys)) #define __virt_to_page(virt) phys_to_page(__pa(virt)) -#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page)) +#define page_to_phys(page) pfn_to_phys(page_to_pfn(page)) #define virt_to_page(addr) __virt_to_page((const unsigned long) addr) #define mk_pte(page, pgprot) \ diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 5dc4c0a..8773426 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -34,9 +34,6 @@ config NO_IOPORT_MAP config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config LOCKDEP_SUPPORT def_bool y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 24f362b..4a10ba9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -180,9 +180,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config MMU def_bool y diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d3eee66..0687c47 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -162,20 +162,22 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _PAGE_SPLITTING; -} - static inline int pmd_trans_huge(pmd_t pmd) { - return pmd_val(pmd) & _PAGE_PSE; + return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } static inline int has_transparent_hugepage(void) { return cpu_has_pse; } + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} +#endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) @@ -252,6 +254,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); +} + static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); @@ -271,6 +278,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_ACCESSED); } +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); @@ -281,6 +293,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DEVMAP); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); @@ -462,6 +479,13 @@ static inline int pte_present(pte_t a) return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t a) +{ + return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; +} +#endif + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -808,10 +832,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cad..04c27a0 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,10 +22,11 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ @@ -46,7 +47,6 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) -#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK @@ -85,8 +85,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define __HAVE_ARCH_PTE_DEVMAP #else #define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec..1544fab 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -132,12 +132,7 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size) { void *vaddr = (void __force *)addr; - /* TODO: implement the zeroing via non-temporal writes */ - if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - clear_page(vaddr); - else - memset(vaddr, 0, size); - + memset(vaddr, 0, size); __arch_wb_cache_pmem(vaddr, size); } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 483231e..e574b85 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -175,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 5c520eb..a22a488 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, +static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, unsigned long npages) { gfn_t end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + npages; @@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long npages) { unsigned long i; @@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; int r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; int flags; @@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm, { struct iommu_domain *domain; gfn_t end_gfn, gfn; - pfn_t pfn; + kvm_pfn_t pfn; u64 phys; domain = kvm->arch.iommu_domain; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 420a5ca..95a955d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -320,7 +320,7 @@ static int is_last_spte(u64 pte, int level) return 0; } -static pfn_t spte_to_pfn(u64 pte) +static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } @@ -582,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static int mmu_spte_clear_track_bits(u64 *sptep) { - pfn_t pfn; + kvm_pfn_t pfn; u64 old_spte = *sptep; if (!spte_has_volatile_bits(old_spte)) @@ -1372,7 +1372,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, int need_flush = 0; u64 new_spte; pte_t *ptep = (pte_t *)data; - pfn_t new_pfn; + kvm_pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); @@ -2450,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static bool kvm_is_mmio_pfn(pfn_t pfn) +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); @@ -2460,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, - gfn_t gfn, pfn_t pfn, bool speculative, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { u64 spte; @@ -2539,7 +2539,7 @@ done: } static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, pfn_t pfn, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool host_writable) { int was_rmapped = 0; @@ -2602,7 +2602,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, return emulate; } -static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, +static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -2684,7 +2684,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) } static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, pfn_t pfn, bool prefault) + int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2732,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_info(SIGBUS, &info, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) +static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { /* * Do not cache the mmio info caused by writing the readonly gfn @@ -2752,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, pfn_t *pfnp, int *levelp) + gfn_t *gfnp, kvm_pfn_t *pfnp, + int *levelp) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *gfnp; int level = *levelp; @@ -2793,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; @@ -2947,7 +2948,7 @@ exit: } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable); + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, @@ -2956,7 +2957,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, int r; int level; bool force_pt_level = false; - pfn_t pfn; + kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; @@ -3410,7 +3411,7 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable) + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -3448,7 +3449,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { - pfn_t pfn; + kvm_pfn_t pfn; int r; int level; bool force_pt_level; @@ -4601,7 +4602,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; - pfn_t pfn; + kvm_pfn_t pfn; struct kvm_mmu_page *sp; restart: diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 1cee3ec..dcce533 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) { struct kvm_mmu_page *sp; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; hpa_t hpa; sp = page_header(__pa(sptep)); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 91e939b..6c9fed9 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -456,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { unsigned pte_access; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; @@ -551,7 +551,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; @@ -694,7 +694,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - pfn_t pfn; + kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; bool force_pt_level = false; unsigned long mmu_seq; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 04d61d4..e2951b6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4251,7 +4251,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { int i, idx, r = 0; - pfn_t identity_map_pfn; + kvm_pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f53f5b1..4244c2b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5148,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, int emulation_type) { gpa_t gpa = cr2; - pfn_t pfn; + kvm_pfn_t pfn; if (emulation_type & EMULTYPE_NO_REEXECUTE) return false; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index ae9a37b..6d5eb59 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -9,6 +9,7 @@ #include <linux/vmstat.h> #include <linux/highmem.h> #include <linux/swap.h> +#include <linux/memremap.h> #include <asm/pgtable.h> @@ -63,6 +64,16 @@ retry: #endif } +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -71,7 +82,9 @@ retry: static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; unsigned long mask; + int nr_start = *nr; pte_t *ptep; mask = _PAGE_PRESENT|_PAGE_USER; @@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { + page = pte_page(pte); + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + pte_unmap(ptep); + return 0; + } + } else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); get_page(page); + put_dev_pagemap(pgmap); SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + unsigned long pfn = pmd_pfn(pmd); + struct dev_pagemap *pgmap = NULL; + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, mask |= _PAGE_RW; if ((pmd_flags(pmd) & mask) != mask) return 0; + + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); + if (pmd_devmap(pmd)) + return __gup_device_huge_pmd(pmd, addr, end, pages, nr); + /* hugepages are never "special" */ VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; head = pmd_page(pmd); @@ -136,8 +187,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -158,18 +207,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* @@ -212,8 +250,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 8829482..5488d21 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> @@ -714,6 +715,12 @@ static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; + struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); + + if (altmap) { + vmem_altmap_free(altmap, nr_pages); + return; + } /* bootmem page has reserved flag */ if (PageReserved(page)) { @@ -1017,13 +1024,19 @@ int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + struct page *page = pfn_to_page(start_pfn); + struct vmem_altmap *altmap; struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - kernel_physical_mapping_remove(start, start + size); + /* With altmap the first mapped page is offset from @start */ + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + page += vmem_altmap_offset(altmap); + zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); return ret; } @@ -1235,7 +1248,7 @@ static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node) + unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; @@ -1258,7 +1271,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1279,7 +1292,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; - } + } else if (altmap) + return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; @@ -1293,11 +1307,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { + struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (cpu_has_pse) - err = vmemmap_populate_hugepages(start, end, node); - else + err = vmemmap_populate_hugepages(start, end, node, altmap); + else if (altmap) { + pr_err_once("%s: no cpu support for altmap allocations\n", + __func__); + err = -ENOMEM; + } else err = vmemmap_populate_basepages(start, end, node); if (!err) sync_global_pgds(start, end - 1, 0); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 031782e..f4ae536 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/fs.h> @@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, } int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { enum page_cache_mode pcm; @@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, return 0; /* Set prot based on lookup */ - pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype(pfn_t_to_phys(pfn)); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ee9c2e3..4eb287e 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -505,19 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - int set; - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set = !test_and_set_bit(_PAGE_BIT_SPLITTING, - (unsigned long *)pmdp); - if (set) { - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 360944e..d030594 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -86,8 +86,10 @@ #define MADV_SEQUENTIAL 2 /* expect sequential page references */ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_DONTNEED 4 /* don't need these pages */ +#define MADV_FREE 5 /* free pages only if memory pressure */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 5ece856..35c8222 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -245,7 +245,7 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) page_mapcount(p)); if (!page_count(p)) rc |= TLB_INSANE; - else if (page_mapped(p)) + else if (page_mapcount(p)) rc |= TLB_SUSPICIOUS; } else { rc |= TLB_INSANE; |
