diff options
Diffstat (limited to 'arch')
109 files changed, 1647 insertions, 1007 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 96cf8720bb93..6f4995ad9873 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -26,6 +26,7 @@ config ARC select GENERIC_PENDING_IRQ if SMP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD + select GENERIC_IOREMAP select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARC_MMU_V4 diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 80347382a380..4fdb7350636c 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -21,8 +21,9 @@ #endif extern void __iomem *ioremap(phys_addr_t paddr, unsigned long size); -extern void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, - unsigned long flags); +#define ioremap ioremap +#define ioremap_prot ioremap_prot +#define iounmap iounmap static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { return (void __iomem *)port; @@ -32,8 +33,6 @@ static inline void ioport_unmap(void __iomem *addr) { } -extern void iounmap(const volatile void __iomem *addr); - /* * io{read,write}{16,32}be() macros */ diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index 712c2311daef..b07004d53267 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -8,7 +8,6 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/mm.h> -#include <linux/slab.h> #include <linux/cache.h> static inline bool arc_uncached_addr_space(phys_addr_t paddr) @@ -25,13 +24,6 @@ static inline bool arc_uncached_addr_space(phys_addr_t paddr) void __iomem *ioremap(phys_addr_t paddr, unsigned long size) { - phys_addr_t end; - - /* Don't allow wraparound or zero size */ - end = paddr + size - 1; - if (!size || (end < paddr)) - return NULL; - /* * If the region is h/w uncached, MMU mapping can be elided as optim * The cast to u32 is fine as this region can only be inside 4GB @@ -51,55 +43,22 @@ EXPORT_SYMBOL(ioremap); * ARC hardware uncached region, this one still goes thru the MMU as caller * might need finer access control (R/W/X) */ -void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, +void __iomem *ioremap_prot(phys_addr_t paddr, size_t size, unsigned long flags) { - unsigned int off; - unsigned long vaddr; - struct vm_struct *area; - phys_addr_t end; pgprot_t prot = __pgprot(flags); - /* Don't allow wraparound, zero size */ - end = paddr + size - 1; - if ((!size) || (end < paddr)) - return NULL; - - /* An early platform driver might end up here */ - if (!slab_is_available()) - return NULL; - /* force uncached */ - prot = pgprot_noncached(prot); - - /* Mappings have to be page-aligned */ - off = paddr & ~PAGE_MASK; - paddr &= PAGE_MASK_PHYS; - size = PAGE_ALIGN(end + 1) - paddr; - - /* - * Ok, go for it.. - */ - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - area->phys_addr = paddr; - vaddr = (unsigned long)area->addr; - if (ioremap_page_range(vaddr, vaddr + size, paddr, prot)) { - vunmap((void __force *)vaddr); - return NULL; - } - return (void __iomem *)(off + (char __iomem *)vaddr); + return generic_ioremap_prot(paddr, size, pgprot_noncached(prot)); } EXPORT_SYMBOL(ioremap_prot); - -void iounmap(const volatile void __iomem *addr) +void iounmap(volatile void __iomem *addr) { /* weird double cast to handle phys_addr_t > 32 bits */ if (arc_uncached_addr_space((phys_addr_t)(u32)addr)) return; - vfree((void *)(PAGE_MASK & (unsigned long __force)addr)); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index d02d6ca88e92..a3a82b7158d4 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -10,6 +10,7 @@ #ifndef _ASM_ARM_HUGETLB_H #define _ASM_ARM_HUGETLB_H +#include <asm/cacheflush.h> #include <asm/page.h> #include <asm/hugetlb-3level.h> #include <asm-generic/hugetlb.h> diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index b8cbe03ad260..f40d06ad5d2a 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -39,7 +39,9 @@ static inline void __tlb_remove_table(void *_table) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_pte_page_dtor(pte); + struct ptdesc *ptdesc = page_ptdesc(pte); + + pagetable_pte_dtor(ptdesc); #ifndef CONFIG_ARM_LPAE /* @@ -50,17 +52,17 @@ __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) __tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE); #endif - tlb_remove_table(tlb, pte); + tlb_remove_ptdesc(tlb, ptdesc); } static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { #ifdef CONFIG_ARM_LPAE - struct page *page = virt_to_page(pmdp); + struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); - pgtable_pmd_page_dtor(page); - tlb_remove_table(tlb, page); + pagetable_pmd_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); #endif } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index ca5302b0b7ee..7cb125497976 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -117,11 +117,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, * must use the nested version. This also means we need to * open-code the spin-locking. */ - pte = pte_offset_map(pmd, address); + pte = pte_offset_map_nolock(vma->vm_mm, pmd, address, &ptl); if (!pte) return 0; - ptl = pte_lockptr(vma->vm_mm, pmd); do_pte_lock(ptl); ret = do_adjust_pte(vma, address, pfn, pte); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 13fc4bb5f792..fdeaee30d167 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -737,11 +737,12 @@ static void __init *early_alloc(unsigned long sz) static void *__init late_alloc(unsigned long sz) { - void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz)); + void *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, + get_order(sz)); - if (!ptr || !pgtable_pte_page_ctor(virt_to_page(ptr))) + if (!ptdesc || !pagetable_pte_ctor(ptdesc)) BUG(); - return ptr; + return ptdesc_to_virt(ptdesc); } static pte_t * __init arm_pte_alloc(pmd_t *pmd, unsigned long addr, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2511b30d0f6..a7a88322bf46 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -78,6 +78,7 @@ config ARM64 select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION select ARCH_KEEP_MEMBLOCK + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_GNU_PROPERTY select ARCH_USE_MEMTEST @@ -96,6 +97,7 @@ config ARM64 select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_SUPPORTS_PAGE_TABLE_CHECK select ARCH_SUPPORTS_PER_VMA_LOCK + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT @@ -348,9 +350,6 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y -config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE - def_bool y - config SMP def_bool y diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 6a4a1ab8eb23..f43a38ac1779 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -10,6 +10,7 @@ #ifndef __ASM_HUGETLB_H #define __ASM_HUGETLB_H +#include <asm/cacheflush.h> #include <asm/page.h> #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION @@ -60,4 +61,19 @@ extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #include <asm-generic/hugetlb.h> +#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + unsigned long stride = huge_page_size(hstate_vma(vma)); + + if (stride == PMD_SIZE) + __flush_tlb_range(vma, start, end, stride, false, 2); + else if (stride == PUD_SIZE) + __flush_tlb_range(vma, start, end, stride, false, 1); + else + __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0); +} + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 51d92abf945e..3b694511b98f 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -139,8 +139,7 @@ extern void __memset_io(volatile void __iomem *, int, size_t); * I/O memory mapping functions. */ -bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot); -#define ioremap_allowed ioremap_allowed +#define ioremap_prot ioremap_prot #define _PAGE_IOREMAP PROT_DEVICE_nGnRE diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index c028afb1cd0b..4cedbaa16f41 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -90,7 +90,7 @@ static inline bool try_page_mte_tagging(struct page *page) } void mte_zero_clear_page_tags(void *addr); -void mte_sync_tags(pte_t old_pte, pte_t pte); +void mte_sync_tags(pte_t pte); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); @@ -122,7 +122,7 @@ static inline bool try_page_mte_tagging(struct page *page) static inline void mte_zero_clear_page_tags(void *addr) { } -static inline void mte_sync_tags(pte_t old_pte, pte_t pte) +static inline void mte_sync_tags(pte_t pte) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 0bd18de9fd97..fe4b913589ee 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -337,18 +337,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, * don't expose tags (instruction fetches don't check tags). */ if (system_supports_mte() && pte_access_permitted(pte, false) && - !pte_special(pte)) { - pte_t old_pte = READ_ONCE(*ptep); - /* - * We only need to synchronise if the new PTE has tags enabled - * or if swapping in (in which case another mapping may have - * set tags in the past even if this PTE isn't tagged). - * (!pte_none() && !pte_present()) is an open coded version of - * is_swap_pte() - */ - if (pte_tagged(pte) || (!pte_none(old_pte) && !pte_present(old_pte))) - mte_sync_tags(old_pte, pte); - } + !pte_special(pte) && pte_tagged(pte)) + mte_sync_tags(pte); __check_safe_pte_update(mm, ptep, pte); @@ -358,7 +348,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - page_table_check_pte_set(mm, addr, ptep, pte); + page_table_check_pte_set(mm, ptep, pte); return __set_pte_at(mm, addr, ptep, pte); } @@ -534,14 +524,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); + page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); + page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); } @@ -938,7 +928,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } @@ -950,7 +940,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -986,7 +976,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index c995d1f4594f..2c29239d05c3 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -75,18 +75,20 @@ static inline void tlb_flush(struct mmu_gather *tlb) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_pte_page_dtor(pte); - tlb_remove_table(tlb, pte); + struct ptdesc *ptdesc = page_ptdesc(pte); + + pagetable_pte_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { - struct page *page = virt_to_page(pmdp); + struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); - pgtable_pmd_page_dtor(page); - tlb_remove_table(tlb, page); + pagetable_pmd_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); } #endif @@ -94,7 +96,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { - tlb_remove_table(tlb, virt_to_page(pudp)); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pudp)); } #endif diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h new file mode 100644 index 000000000000..fedb0b87b8db --- /dev/null +++ b/arch/arm64/include/asm/tlbbatch.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_ARM64_TLBBATCH_H +#define _ARCH_ARM64_TLBBATCH_H + +struct arch_tlbflush_unmap_batch { + /* + * For arm64, HW can do tlb shootdown, so we don't + * need to record cpumask for sending IPI + */ +}; + +#endif /* _ARCH_ARM64_TLBBATCH_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 412a3b9a3c25..55b50e1d4a84 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -13,6 +13,7 @@ #include <linux/bitfield.h> #include <linux/mm_types.h> #include <linux/sched.h> +#include <linux/mmu_notifier.h> #include <asm/cputype.h> #include <asm/mmu.h> @@ -252,17 +253,26 @@ static inline void flush_tlb_mm(struct mm_struct *mm) __tlbi(aside1is, asid); __tlbi_user(aside1is, asid); dsb(ish); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } -static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, - unsigned long uaddr) +static inline void __flush_tlb_page_nosync(struct mm_struct *mm, + unsigned long uaddr) { unsigned long addr; dsb(ishst); - addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); + addr = __TLBI_VADDR(uaddr, ASID(mm)); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, uaddr & PAGE_MASK, + (uaddr & PAGE_MASK) + PAGE_SIZE); +} + +static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, + unsigned long uaddr) +{ + return __flush_tlb_page_nosync(vma->vm_mm, uaddr); } static inline void flush_tlb_page(struct vm_area_struct *vma, @@ -272,6 +282,53 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, dsb(ish); } +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ +#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI + /* + * TLB flush deferral is not required on systems which are affected by + * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation + * will have two consecutive TLBI instructions with a dsb(ish) in between + * defeating the purpose (i.e save overall 'dsb ish' cost). + */ + if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI))) + return false; +#endif + return true; +} + +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, + unsigned long uaddr) +{ + __flush_tlb_page_nosync(mm, uaddr); +} + +/* + * If mprotect/munmap/etc occurs during TLB batched flushing, we need to + * synchronise all the TLBI issued with a DSB to avoid the race mentioned in + * flush_tlb_batched_pending(). + */ +static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) +{ + dsb(ish); +} + +/* + * To support TLB batched flush for multiple pages unmapping, we only send + * the TLBI for each page in arch_tlbbatch_add_pending() and wait for the + * completion at the end in arch_tlbbatch_flush(). Since we've already issued + * TLBI for each page so only a DSB is needed to synchronise its effect on the + * other CPUs. + * + * This will save the time waiting on DSB comparing issuing a TLBI;DSB sequence + * for each page. + */ +static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + dsb(ish); +} + /* * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. @@ -358,6 +415,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, scale++; } dsb(ish); + mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } static inline void flush_tlb_range(struct vm_area_struct *vma, diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 4c5ef9b20065..4edecaac8f91 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -35,41 +35,18 @@ DEFINE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode); #endif -static void mte_sync_page_tags(struct page *page, pte_t old_pte, - bool check_swap, bool pte_is_tagged) -{ - if (check_swap && is_swap_pte(old_pte)) { - swp_entry_t entry = pte_to_swp_entry(old_pte); - - if (!non_swap_entry(entry)) - mte_restore_tags(entry, page); - } - - if (!pte_is_tagged) - return; - - if (try_page_mte_tagging(page)) { - mte_clear_page_tags(page_address(page)); - set_page_mte_tagged(page); - } -} - -void mte_sync_tags(pte_t old_pte, pte_t pte) +void mte_sync_tags(pte_t pte) { struct page *page = pte_page(pte); long i, nr_pages = compound_nr(page); - bool check_swap = nr_pages == 1; - bool pte_is_tagged = pte_tagged(pte); - - /* Early out if there's nothing to do */ - if (!check_swap && !pte_is_tagged) - return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) - if (!page_mte_tagged(page)) - mte_sync_page_tags(page, old_pte, check_swap, - pte_is_tagged); + for (i = 0; i < nr_pages; i++, page++) { + if (try_page_mte_tagging(page)) { + mte_clear_page_tags(page_address(page)); + set_page_mte_tagged(page); + } + } /* ensure the tags are visible before the PTE is set */ smp_wmb(); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3fe516b32577..103fcbdc6552 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -587,7 +587,6 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); -#ifdef CONFIG_PER_VMA_LOCK if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -615,7 +614,6 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, return 0; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ retry: vma = lock_mm_and_find_vma(mm, addr, regs); diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index c5af103d4ad4..269f2f63ab7d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -3,20 +3,22 @@ #include <linux/mm.h> #include <linux/io.h> -bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { unsigned long last_addr = phys_addr + size - 1; /* Don't allow outside PHYS_MASK */ if (last_addr & ~PHYS_MASK) - return false; + return NULL; /* Don't allow RAM to be mapped. */ if (WARN_ON(pfn_is_map_memory(__phys_to_pfn(phys_addr)))) - return false; + return NULL; - return true; + return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); } +EXPORT_SYMBOL(ioremap_prot); /* * Must be called after early_fixmap_init diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 95d360805f8a..47781bec6171 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -426,6 +426,7 @@ static phys_addr_t __pgd_pgtable_alloc(int shift) static phys_addr_t pgd_pgtable_alloc(int shift) { phys_addr_t pa = __pgd_pgtable_alloc(shift); + struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa)); /* * Call proper page table ctor in case later we need to @@ -433,12 +434,12 @@ static phys_addr_t pgd_pgtable_alloc(int shift) * this pre-allocated page table. * * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is - * folded, and if so pgtable_pmd_page_ctor() becomes nop. + * folded, and if so pagetable_pte_ctor() becomes nop. */ if (shift == PAGE_SHIFT) - BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa))); + BUG_ON(!pagetable_pte_ctor(ptdesc)); else if (shift == PMD_SHIFT) - BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa))); + BUG_ON(!pagetable_pmd_ctor(ptdesc)); return pa; } diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index 7d57e5da0914..9c84c9012e53 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -63,8 +63,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #define __pte_free_tlb(tlb, pte, address) \ do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page(tlb, pte); \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc(tlb, page_ptdesc(pte)); \ } while (0) extern void pagetable_init(void); diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 6726f4941015..a880ee067d2e 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -25,6 +25,7 @@ config HEXAGON select NEED_SG_DMA_LENGTH select NO_IOPORT_MAP select GENERIC_IOMAP + select GENERIC_IOREMAP select GENERIC_SMP_IDLE_THREAD select STACKTRACE_SUPPORT select GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h index 46a099de85b7..e2b308e32a37 100644 --- a/arch/hexagon/include/asm/io.h +++ b/arch/hexagon/include/asm/io.h @@ -27,8 +27,6 @@ extern int remap_area_pages(unsigned long start, unsigned long phys_addr, unsigned long end, unsigned long flags); -extern void iounmap(const volatile void __iomem *addr); - /* Defined in lib/io.c, needed for smc91x driver. */ extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen); extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen); @@ -170,8 +168,13 @@ static inline void writel(u32 data, volatile void __iomem *addr) #define writew_relaxed __raw_writew #define writel_relaxed __raw_writel -void __iomem *ioremap(unsigned long phys_addr, unsigned long size); -#define ioremap_uc(X, Y) ioremap((X), (Y)) +/* + * I/O memory mapping functions. + */ +#define _PAGE_IOREMAP (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + (__HEXAGON_C_DEV << 6)) + +#define ioremap_uc(addr, size) ioremap((addr), (size)) #define __raw_writel writel diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index f0c47e6a7427..55988625e6fb 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -87,10 +87,10 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, max_kernel_seg = pmdindex; } -#define __pte_free_tlb(tlb, pte, addr) \ -do { \ - pgtable_pte_page_dtor((pte)); \ - tlb_remove_page((tlb), (pte)); \ +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pagetable_pte_dtor((page_ptdesc(pte))); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #endif diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c index ec56ce2d92a2..36a80e31d187 100644 --- a/arch/hexagon/kernel/hexagon_ksyms.c +++ b/arch/hexagon/kernel/hexagon_ksyms.c @@ -14,12 +14,10 @@ EXPORT_SYMBOL(__clear_user_hexagon); EXPORT_SYMBOL(raw_copy_from_user); EXPORT_SYMBOL(raw_copy_to_user); -EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(__vmgetie); EXPORT_SYMBOL(__vmsetie); EXPORT_SYMBOL(__vmyield); EXPORT_SYMBOL(empty_zero_page); -EXPORT_SYMBOL(ioremap); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/hexagon/mm/Makefile b/arch/hexagon/mm/Makefile index 49911a906fd0..ba4b04d962d6 100644 --- a/arch/hexagon/mm/Makefile +++ b/arch/hexagon/mm/Makefile @@ -3,5 +3,5 @@ # Makefile for Hexagon memory management subsystem # -obj-y := init.o ioremap.o uaccess.o vm_fault.o cache.o +obj-y := init.o uaccess.o vm_fault.o cache.o obj-y += copy_to_user.o copy_from_user.o vm_tlb.o diff --git a/arch/hexagon/mm/ioremap.c b/arch/hexagon/mm/ioremap.c deleted file mode 100644 index 255c5b1ee1a7..000000000000 --- a/arch/hexagon/mm/ioremap.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * I/O remap functions for Hexagon - * - * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. - */ - -#include <linux/io.h> -#include <linux/vmalloc.h> -#include <linux/mm.h> - -void __iomem *ioremap(unsigned long phys_addr, unsigned long size) -{ - unsigned long last_addr, addr; - unsigned long offset = phys_addr & ~PAGE_MASK; - struct vm_struct *area; - - pgprot_t prot = __pgprot(_PAGE_PRESENT|_PAGE_READ|_PAGE_WRITE - |(__HEXAGON_C_DEV << 6)); - - last_addr = phys_addr + size - 1; - - /* Wrapping not allowed */ - if (!size || (last_addr < phys_addr)) - return NULL; - - /* Rounds up to next page size, including whole-page offset */ - size = PAGE_ALIGN(offset + size); - - area = get_vm_area(size, VM_IOREMAP); - addr = (unsigned long)area->addr; - - if (ioremap_page_range(addr, addr+size, phys_addr, prot)) { - vunmap((void *)addr); - return NULL; - } - - return (void __iomem *) (offset + addr); -} - -void iounmap(const volatile void __iomem *addr) -{ - vunmap((void *) ((unsigned long) addr & PAGE_MASK)); -} diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 2cd93e6bf0fe..3ab75f36c037 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -47,6 +47,7 @@ config IA64 select GENERIC_IRQ_LEGACY select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP + select GENERIC_IOREMAP select GENERIC_SMP_IDLE_THREAD select ARCH_TASK_STRUCT_ON_STACK select ARCH_TASK_STRUCT_ALLOCATOR diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 83a492c8d298..eedc0afa8cad 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -243,15 +243,12 @@ static inline void outsl(unsigned long port, const void *src, # ifdef __KERNEL__ -extern void __iomem * ioremap(unsigned long offset, unsigned long size); +#define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL) + extern void __iomem * ioremap_uc(unsigned long offset, unsigned long size); -extern void iounmap (volatile void __iomem *addr); -static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned long size) -{ - return ioremap(phys_addr, size); -} -#define ioremap ioremap -#define ioremap_cache ioremap_cache + +#define ioremap_prot ioremap_prot +#define ioremap_cache ioremap #define ioremap_uc ioremap_uc #define iounmap iounmap diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c index 92b81bc91397..711b6abc822e 100644 --- a/arch/ia64/mm/ioremap.c +++ b/arch/ia64/mm/ioremap.c @@ -29,13 +29,9 @@ early_ioremap (unsigned long phys_addr, unsigned long size) return __ioremap_uc(phys_addr); } -void __iomem * -ioremap (unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long flags) { - void __iomem *addr; - struct vm_struct *area; - unsigned long offset; - pgprot_t prot; u64 attr; unsigned long gran_base, gran_size; unsigned long page_base; @@ -68,36 +64,12 @@ ioremap (unsigned long phys_addr, unsigned long size) */ page_base = phys_addr & PAGE_MASK; size = PAGE_ALIGN(phys_addr + size) - page_base; - if (efi_mem_attribute(page_base, size) & EFI_MEMORY_WB) { - prot = PAGE_KERNEL; - - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - - /* - * Ok, go for it.. - */ - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - - area->phys_addr = phys_addr; - addr = (void __iomem *) area->addr; - if (ioremap_page_range((unsigned long) addr, - (unsigned long) addr + size, phys_addr, prot)) { - vunmap((void __force *) addr); - return NULL; - } - - return (void __iomem *) (offset + (char __iomem *)addr); - } + if (efi_mem_attribute(page_base, size) & EFI_MEMORY_WB) + return generic_ioremap_prot(phys_addr, size, __pgprot(flags)); return __ioremap_uc(phys_addr); } -EXPORT_SYMBOL(ioremap); +EXPORT_SYMBOL(ioremap_prot); void __iomem * ioremap_uc(unsigned long phys_addr, unsigned long size) @@ -114,8 +86,7 @@ early_iounmap (volatile void __iomem *addr, unsigned long size) { } -void -iounmap (volatile void __iomem *addr) +void iounmap(volatile void __iomem *addr) { if (REGION_NUMBER(addr) == RGN_GATE) vunmap((void *) ((unsigned long) addr & PAGE_MASK)); diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e71d5bf2cee0..dc56ddf9ba03 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -60,7 +60,7 @@ config LOONGARCH select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANT_OPTIMIZE_VMEMMAP + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_NO_INSTR select BUILDTIME_TABLE_SORT select COMMON_CLK diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 1c9410220040..0dcb36b32cb2 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -5,8 +5,6 @@ #ifndef _ASM_IO_H #define _ASM_IO_H -#define ARCH_HAS_IOREMAP_WC - #include <linux/kernel.h> #include <linux/types.h> diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index af1d1e4a6965..23f5b1107246 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -45,9 +45,9 @@ extern void pagetable_init(void); extern pgd_t *pgd_alloc(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, address) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), pte); \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) #ifndef __PAGETABLE_PMD_FOLDED @@ -55,18 +55,18 @@ do { \ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { pmd_t *pmd; - struct page *pg; + struct ptdesc *ptdesc; - pg = alloc_page(GFP_KERNEL_ACCOUNT); - if (!pg) + ptdesc = pagetable_alloc(GFP_KERNEL_ACCOUNT, 0); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(pg)) { - __free_page(pg); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - pmd = (pmd_t *)page_address(pg); + pmd = ptdesc_address(ptdesc); pmd_init(pmd); return pmd; } @@ -80,10 +80,13 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - pud = (pud_t *) __get_free_page(GFP_KERNEL); - if (pud) - pud_init(pud); + if (!ptdesc) + return NULL; + pud = ptdesc_address(ptdesc); + + pud_init(pud); return pud; } diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 36a6dc0148ae..5bd102b51f7c 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -11,10 +11,11 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *ret, *init; + pgd_t *init, *ret = NULL; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - ret = (pgd_t *) __get_free_page(GFP_KERNEL); - if (ret) { + if (ptdesc) { + ret = (pgd_t *)ptdesc_address(ptdesc); init = pgd_offset(&init_mm, 0UL); pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h index d41fa488453b..6a0abd4846c6 100644 --- a/arch/m68k/include/asm/io_mm.h +++ b/arch/m68k/include/asm/io_mm.h @@ -26,8 +26,6 @@ #include <asm/virtconvert.h> #include <asm/kmap.h> -#include <asm-generic/iomap.h> - #ifdef CONFIG_ATARI #define atari_readb raw_inb #define atari_writeb raw_outb diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h index dec05743d426..4efb3efa593a 100644 --- a/arch/m68k/include/asm/kmap.h +++ b/arch/m68k/include/asm/kmap.h @@ -4,8 +4,6 @@ #ifdef CONFIG_MMU -#define ARCH_HAS_IOREMAP_WT - /* Values for nocacheflag and cmode */ #define IOMAP_FULL_CACHING 0 #define IOMAP_NOCACHE_SER 1 diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 5c2c0a864524..302c5bf67179 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -5,22 +5,22 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> -extern inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long) pte); + pagetable_free(virt_to_ptdesc(pte)); } extern const char bad_pmd_string[]; -extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { - unsigned long page = __get_free_page(GFP_DMA); + struct ptdesc *ptdesc = pagetable_alloc((GFP_DMA | __GFP_ZERO) & + ~__GFP_HIGHMEM, 0); - if (!page) + if (!ptdesc) return NULL; - memset((void *)page, 0, PAGE_SIZE); - return (pte_t *) (page); + return ptdesc_address(ptdesc); } extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) @@ -35,36 +35,34 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, unsigned long address) { - struct page *page = virt_to_page(pgtable); + struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); - pgtable_pte_page_dtor(page); - __free_page(page); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *page = alloc_pages(GFP_DMA, 0); + struct ptdesc *ptdesc = pagetable_alloc(GFP_DMA | __GFP_ZERO, 0); pte_t *pte; - if (!page) + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - pte = page_address(page); - clear_page(pte); - + pte = ptdesc_address(ptdesc); return pte; } static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) { - struct page *page = virt_to_page(pgtable); + struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); - pgtable_pte_page_dtor(page); - __free_page(page); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } /* @@ -75,16 +73,19 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_page((unsigned long) pgd); + pagetable_free(virt_to_ptdesc(pgd)); } static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *new_pgd; + struct ptdesc *ptdesc = pagetable_alloc((GFP_DMA | __GFP_NOWARN) & + ~__GFP_HIGHMEM, 0); - new_pgd = (pgd_t *)__get_free_page(GFP_DMA | __GFP_NOWARN); - if (!new_pgd) + if (!ptdesc) return NULL; + new_pgd = ptdesc_address(ptdesc); + memcpy(new_pgd, swapper_pg_dir, PTRS_PER_PGD * sizeof(pgd_t)); memset(new_pgd, 0, PAGE_OFFSET >> PGDIR_SHIFT); return new_pgd; diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 198036aff519..ff48573db2c0 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -17,10 +17,10 @@ extern const char bad_pmd_string[]; -#define __pte_free_tlb(tlb,pte,addr) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), pte); \ +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index c75984e2d86b..594575a0780c 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -161,7 +161,7 @@ void *get_pointer_table(int type) * m68k doesn't have SPLIT_PTE_PTLOCKS for not having * SMP. */ - pgtable_pte_page_ctor(virt_to_page(page)); + pagetable_pte_ctor(virt_to_ptdesc(page)); } mmu_page_ctor(page); @@ -201,7 +201,7 @@ int free_pointer_table(void *table, int type) list_del(dp); mmu_page_dtor((void *)page); if (type == TABLE_PTE) - pgtable_pte_page_dtor(virt_to_page((void *)page)); + pagetable_pte_dtor(virt_to_ptdesc((void *)page)); free_page (page); return 1; } else if (ptable_list[type].next != dp) { diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index affd21e9c20b..062dd4e6b954 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -12,8 +12,6 @@ #ifndef _ASM_IO_H #define _ASM_IO_H -#define ARCH_HAS_IOREMAP_WC - #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/types.h> @@ -25,7 +23,6 @@ #include <asm/byteorder.h> #include <asm/cpu.h> #include <asm/cpu-features.h> -#include <asm-generic/iomap.h> #include <asm/page.h> #include <asm/pgtable-bits.h> #include <asm/processor.h> @@ -210,6 +207,8 @@ void iounmap(const volatile void __iomem *addr); #define ioremap_wc(offset, size) \ ioremap_prot((offset), (size), boot_cpu_data.writecombine) +#include <asm-generic/iomap.h> + #if defined(CONFIG_CPU_CAVIUM_OCTEON) #define war_io_reorder_wmb() wmb() #else diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index f72e737dda21..40e40a7eb94a 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -51,13 +51,13 @@ extern pgd_t *pgd_alloc(struct mm_struct *mm); static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGD_TABLE_ORDER); + pagetable_free(virt_to_ptdesc(pgd)); } -#define __pte_free_tlb(tlb,pte,address) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), pte); \ +#define __pte_free_tlb(tlb, pte, address) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), page_ptdesc(pte)); \ } while (0) #ifndef __PAGETABLE_PMD_FOLDED @@ -65,18 +65,18 @@ do { \ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { pmd_t *pmd; - struct page *pg; + struct ptdesc *ptdesc; - pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_TABLE_ORDER); - if (!pg) + ptdesc = pagetable_alloc(GFP_KERNEL_ACCOUNT, PMD_TABLE_ORDER); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(pg)) { - __free_pages(pg, PMD_TABLE_ORDER); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - pmd = (pmd_t *)page_address(pg); + pmd = ptdesc_address(ptdesc); pmd_init(pmd); return pmd; } @@ -90,10 +90,14 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, + PUD_TABLE_ORDER); - pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_TABLE_ORDER); - if (pud) - pud_init(pud); + if (!ptdesc) + return NULL; + pud = ptdesc_address(ptdesc); + + pud_init(pud); return pud; } diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c index b13314be5d0e..1506e458040d 100644 --- a/arch/mips/mm/pgtable.c +++ b/arch/mips/mm/pgtable.c @@ -10,10 +10,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *ret, *init; + pgd_t *init, *ret = NULL; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, + PGD_TABLE_ORDER); - ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); - if (ret) { + if (ptdesc) { + ret = ptdesc_address(ptdesc); init = pgd_offset(&init_mm, 0UL); pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index ecd1657bb2ce..ce6bb8e74271 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -28,10 +28,10 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, extern pgd_t *pgd_alloc(struct mm_struct *mm); -#define __pte_free_tlb(tlb, pte, addr) \ - do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), (pte)); \ +#define __pte_free_tlb(tlb, pte, addr) \ + do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #endif /* _ASM_NIOS2_PGALLOC_H */ diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index c7f282f60f64..fd9bb76a610b 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -21,6 +21,7 @@ config OPENRISC select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP + select GENERIC_IOREMAP select GENERIC_CPU_DEVICES select HAVE_PCI select HAVE_UID16 diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index ee6043a03173..5a6f0f16a5ce 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -15,6 +15,8 @@ #define __ASM_OPENRISC_IO_H #include <linux/types.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> /* * PCI: We do not use IO ports in OpenRISC @@ -27,11 +29,10 @@ #define PIO_OFFSET 0 #define PIO_MASK 0 -#define ioremap ioremap -void __iomem *ioremap(phys_addr_t offset, unsigned long size); - -#define iounmap iounmap -extern void iounmap(volatile void __iomem *addr); +/* + * I/O memory mapping functions. + */ +#define _PAGE_IOREMAP (pgprot_val(PAGE_KERNEL) | _PAGE_CI) #include <asm-generic/io.h> diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index b7b2b8d16fad..c6a73772a546 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -66,10 +66,10 @@ extern inline pgd_t *pgd_alloc(struct mm_struct *mm) extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm); -#define __pte_free_tlb(tlb, pte, addr) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), (pte)); \ +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #endif diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 8ec0dafecf25..91c8259d4b7e 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -22,88 +22,6 @@ extern int mem_init_done; -static unsigned int fixmaps_used __initdata; - -/* - * Remap an arbitrary physical address space into the kernel virtual - * address space. Needed when the kernel wants to access high addresses - * directly. - * - * NOTE! We need to allow non-page-aligned mappings too: we will obviously - * have to convert them into an offset in a page-aligned mapping, but the - * caller shouldn't need to know that small detail. - */ -void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) -{ - phys_addr_t p; - unsigned long v; - unsigned long offset, last_addr; - struct vm_struct *area = NULL; - - /* Don't allow wraparound or zero size */ - last_addr = addr + size - 1; - if (!size || last_addr < addr) - return NULL; - - /* - * Mappings have to be page-aligned - */ - offset = addr & ~PAGE_MASK; - p = addr & PAGE_MASK; - size = PAGE_ALIGN(last_addr + 1) - p; - - if (likely(mem_init_done)) { - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - v = (unsigned long)area->addr; - } else { - if ((fixmaps_used + (size >> PAGE_SHIFT)) > FIX_N_IOREMAPS) - return NULL; - v = fix_to_virt(FIX_IOREMAP_BEGIN + fixmaps_used); - fixmaps_used += (size >> PAGE_SHIFT); - } - - if (ioremap_page_range(v, v + size, p, - __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_CI))) { - if (likely(mem_init_done)) - vfree(area->addr); - else - fixmaps_used -= (size >> PAGE_SHIFT); - return NULL; - } - - return (void __iomem *)(offset + (char *)v); -} -EXPORT_SYMBOL(ioremap); - -void iounmap(volatile void __iomem *addr) -{ - /* If the page is from the fixmap pool then we just clear out - * the fixmap mapping. - */ - if (unlikely((unsigned long)addr > FIXADDR_START)) { - /* This is a bit broken... we don't really know - * how big the area is so it's difficult to know - * how many fixed pages to invalidate... - * just flush tlb and hope for the best... - * consider this a FIXME - * - * Really we should be clearing out one or more page - * table entries for these virtual addresses so that - * future references cause a page fault... for now, we - * rely on two things: - * i) this code never gets called on known boards - * ii) invalid accesses to the freed areas aren't made - */ - flush_tlb_all(); - return; - } - - return vfree((void *)(PAGE_MASK & (unsigned long)addr)); -} -EXPORT_SYMBOL(iounmap); - /** * OK, this one's a bit tricky... ioremap can get called before memory is * initialized (early serial console does this) and will want to alloc a page diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 4cb46d5c64a2..4cda9f0a3277 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -36,6 +36,7 @@ config PARISC select GENERIC_ATOMIC64 if !64BIT select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP + select GENERIC_IOREMAP select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_ARCH_TOPOLOGY if SMP diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index c05e781be2f5..366537042465 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -125,12 +125,17 @@ static inline void gsc_writeq(unsigned long long val, unsigned long addr) /* * The standard PCI ioremap interfaces */ -void __iomem *ioremap(unsigned long offset, unsigned long size); -#define ioremap_wc ioremap -#define ioremap_uc ioremap -#define pci_iounmap pci_iounmap +#define ioremap_prot ioremap_prot + +#define _PAGE_IOREMAP (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_NO_CACHE) -extern void iounmap(const volatile void __iomem *addr); +#define ioremap_wc(addr, size) \ + ioremap_prot((addr), (size), _PAGE_IOREMAP) +#define ioremap_uc(addr, size) \ + ioremap_prot((addr), (size), _PAGE_IOREMAP) + +#define pci_iounmap pci_iounmap void memset_io(volatile void __iomem *addr, unsigned char val, int count); void memcpy_fromio(void *dst, const volatile void __iomem *src, int count); diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 345ff0b66499..fd996472dfe7 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -13,25 +13,9 @@ #include <linux/io.h> #include <linux/mm.h> -/* - * Generic mapping function (not visible outside): - */ - -/* - * Remap an arbitrary physical address space into the kernel virtual - * address space. - * - * NOTE! We need to allow non-page-aligned mappings too: we will obviously - * have to convert them into an offset in a page-aligned mapping, but the - * caller shouldn't need to know that small detail. - */ -void __iomem *ioremap(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { - void __iomem *addr; - struct vm_struct *area; - unsigned long offset, last_addr; - pgprot_t pgprot; - #ifdef CONFIG_EISA unsigned long end = phys_addr + size - 1; /* Support EISA addresses */ @@ -40,11 +24,6 @@ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) phys_addr |= F_EXTEND(0xfc000000); #endif - /* Don't allow wraparound or zero size */ - last_addr = phys_addr + size - 1; - if (!size || last_addr < phys_addr) - return NULL; - /* * Don't allow anybody to remap normal RAM that we're using.. */ @@ -62,39 +41,6 @@ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) } } - pgprot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | - _PAGE_ACCESSED | _PAGE_NO_CACHE); - - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr + 1) - phys_addr; - - /* - * Ok, go for it.. - */ - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - - addr = (void __iomem *) area->addr; - if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, - phys_addr, pgprot)) { - vunmap(addr); - return NULL; - } - - return (void __iomem *) (offset + (char __iomem *)addr); -} -EXPORT_SYMBOL(ioremap); - -void iounmap(const volatile void __iomem *io_addr) -{ - unsigned long addr = (unsigned long)io_addr & PAGE_MASK; - - if (is_vmalloc_addr((void *)addr)) - vunmap((void *)addr); + return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); } -EXPORT_SYMBOL(iounmap); +EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 0b1172cbeccb..938294c996dc 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -157,6 +157,7 @@ config PPC select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if PPC_RADIX_MMU select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX @@ -174,6 +175,7 @@ config PPC select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if PPC_RADIX_MMU select ARCH_WANTS_MODULES_DATA_IN_VMALLOC if PPC_BOOK3S_32 || PPC_8xx select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF @@ -193,6 +195,7 @@ config PPC select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC select GENERIC_EARLY_IOREMAP select GENERIC_GETTIMEOFDAY + select GENERIC_IOREMAP select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP if PCI diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index d4a19e6547ac..6e70ae511631 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -138,7 +138,16 @@ static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) } #define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) + +/* + * pud comparison that will work with both pte and page table pointer. + */ +static inline int hash__pud_same(pud_t pud_a, pud_t pud_b) +{ + return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} #define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) + static inline int hash__p4d_bad(p4d_t p4d) { return (p4d_val(p4d) == 0); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 4acc9690f599..a8204566cfd0 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -921,8 +921,29 @@ static inline pud_t pte_pud(pte_t pte) { return __pud_raw(pte_raw(pte)); } + +static inline pte_t *pudp_ptep(pud_t *pud) +{ + return (pte_t *)pud; +} + +#define pud_pfn(pud) pte_pfn(pud_pte(pud)) +#define pud_dirty(pud) pte_dirty(pud_pte(pud)) +#define pud_young(pud) pte_young(pud_pte(pud)) +#define pud_mkold(pud) pte_pud(pte_mkold(pud_pte(pud))) +#define pud_wrprotect(pud) pte_pud(pte_wrprotect(pud_pte(pud))) +#define pud_mkdirty(pud) pte_pud(pte_mkdirty(pud_pte(pud))) +#define pud_mkclean(pud) pte_pud(pte_mkclean(pud_pte(pud))) +#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) +#define pud_mkwrite(pud) pte_pud(pte_mkwrite(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pud_soft_dirty(pmd) pte_soft_dirty(pud_pte(pud)) +#define pud_mksoft_dirty(pmd) pte_pud(pte_mksoft_dirty(pud_pte(pud))) +#define pud_clear_soft_dirty(pmd) pte_pud(pte_clear_soft_dirty(pud_pte(pud))) +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + static inline int pud_bad(pud_t pud) { if (radix_enabled()) @@ -1115,15 +1136,24 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); +extern void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} + extern int hash__has_transparent_hugepage(void); static inline int has_transparent_hugepage(void) { @@ -1133,6 +1163,14 @@ static inline int has_transparent_hugepage(void) } #define has_transparent_hugepage has_transparent_hugepage +static inline int has_transparent_pud_hugepage(void) +{ + if (radix_enabled()) + return radix__has_transparent_pud_hugepage(); + return 0; +} +#define has_transparent_pud_hugepage has_transparent_pud_hugepage + static inline unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set) @@ -1142,6 +1180,16 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } +static inline unsigned long +pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp, + unsigned long clr, unsigned long set) +{ + if (radix_enabled()) + return radix__pud_hugepage_update(mm, addr, pudp, clr, set); + BUG(); + return pud_val(*pudp); +} + /* * returns true for pmd migration entries, THP, devmap, hugetlb * But compile time dependent on THP config @@ -1151,6 +1199,11 @@ static inline int pmd_large(pmd_t pmd) return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } +static inline int pud_large(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} + /* * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too @@ -1166,6 +1219,17 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, return ((old & _PAGE_ACCESSED) != 0); } +static inline int __pudp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + unsigned long old; + + if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -1174,6 +1238,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); } +#define __HAVE_ARCH_PUDP_SET_WRPROTECT +static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pud_t *pudp) +{ + if (pud_write(*pudp)) + pud_hugepage_update(mm, addr, pudp, _PAGE_WRITE, 0); +} + /* * Only returns true for a THP. False for pmd migration entry. * We also need to return true when we come across a pte that @@ -1195,6 +1267,17 @@ static inline int pmd_trans_huge(pmd_t pmd) return hash__pmd_trans_huge(pmd); } +static inline int pud_trans_huge(pud_t pud) +{ + if (!pud_present(pud)) + return false; + + if (radix_enabled()) + return radix__pud_trans_huge(pud); + return 0; +} + + #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { @@ -1203,6 +1286,15 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) return hash__pmd_same(pmd_a, pmd_b); } +#define pud_same pud_same +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + if (radix_enabled()) + return radix__pud_same(pud_a, pud_b); + return hash__pud_same(pud_a, pud_b); +} + + static inline pmd_t __pmd_mkhuge(pmd_t pmd) { if (radix_enabled()) @@ -1210,6 +1302,14 @@ static inline pmd_t __pmd_mkhuge(pmd_t pmd) return hash__pmd_mkhuge(pmd); } +static inline pud_t __pud_mkhuge(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkhuge(pud); + BUG(); + return pud; +} + /* * pfn_pmd return a pmd_t that can be used as pmd pte entry. */ @@ -1225,14 +1325,34 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) return pmd; } +static inline pud_t pud_mkhuge(pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pud_raw(pud) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON(1); +#endif + return pud; +} + + #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); +#define __HAVE_ARCH_PUDP_SET_ACCESS_FLAGS +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp); + #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, @@ -1243,6 +1363,16 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + if (radix_enabled()) + return radix__pudp_huge_get_and_clear(mm, addr, pudp); + BUG(); + return *pudp; +} + static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -1257,6 +1387,11 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, int full); +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pud_t *pudp, int full); + #define __HAVE_ARCH_PGTABLE_DEPOSIT static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) @@ -1305,6 +1440,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) return hash__pmd_mkdevmap(pmd); } +static inline pud_t pud_mkdevmap(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkdevmap(pud); + BUG(); + return pud; +} + static inline int pmd_devmap(pmd_t pmd) { return pte_devmap(pmd_pte(pmd)); @@ -1312,7 +1455,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) @@ -1321,16 +1464,6 @@ static inline int pgd_devmap(pgd_t pgd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int pud_pfn(pud_t pud) -{ - /* - * Currently all calls to pud_pfn() are gated around a pud_devmap() - * check so this should never be used. If it grows another user we - * want to know about it. - */ - BUILD_BUG(); - return 0; -} #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 686001eda936..357e23a403d3 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -250,6 +250,10 @@ static inline int radix__pud_bad(pud_t pud) return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); } +static inline int radix__pud_same(pud_t pud_a, pud_t pud_b) +{ + return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0); +} static inline int radix__p4d_bad(p4d_t p4d) { @@ -268,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE); } +static inline int radix__pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; +} + +static inline pud_t radix__pud_mkhuge(pud_t pud) +{ + return __pud(pud_val(pud) | _PAGE_PTE); +} + extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set); +extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set); extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, @@ -278,6 +295,9 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp); + static inline int radix__has_transparent_hugepage(void) { /* For radix 2M at PMD level means thp */ @@ -285,6 +305,14 @@ static inline int radix__has_transparent_hugepage(void) return 1; return 0; } + +static inline int radix__has_transparent_pud_hugepage(void) +{ + /* For radix 1G at PUD level means pud hugepage support */ + if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT) + return 1; + return 0; +} #endif static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) @@ -292,9 +320,20 @@ static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); } +static inline pud_t radix__pud_mkdevmap(pud_t pud) +{ + return __pud(pud_val(pud) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +struct vmem_altmap; +struct dev_pagemap; extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); @@ -325,5 +364,15 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end); void radix__kernel_map_pages(struct page *page, int numpages, int enable); +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +#define vmemmap_can_optimize vmemmap_can_optimize +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +#endif + +#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 77797a2a82eb..a38542259fab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -68,6 +68,8 @@ void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, unsigned long end, int psize); extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +extern void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 0d0c1447ecf0..1950c1b825b4 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -5,6 +5,7 @@ #define MMU_NO_CONTEXT ~0UL #include <linux/mm_types.h> +#include <linux/mmu_notifier.h> #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> @@ -50,6 +51,14 @@ static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, radix__flush_pmd_tlb_range(vma, start, end); } +#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE +static inline void flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + radix__flush_pud_tlb_range(vma, start, end); +} + #define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index f1e657c9bbe8..0732b743e099 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -3,11 +3,6 @@ #define _ASM_POWERPC_IO_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WC -#ifdef CONFIG_PPC32 -#define ARCH_HAS_IOREMAP_WT -#endif - /* */ @@ -732,9 +727,7 @@ static inline void name at \ #define writel_relaxed(v, addr) writel(v, addr) #define writeq_relaxed(v, addr) writeq(v, addr) -#ifdef CONFIG_GENERIC_IOMAP -#include <asm-generic/iomap.h> -#else +#ifndef CONFIG_GENERIC_IOMAP /* * Here comes the implementation of the IOMAP interfaces. */ @@ -896,8 +889,8 @@ static inline void iosync(void) * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); -extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, - unsigned long flags); +#define ioremap ioremap +#define ioremap_prot ioremap_prot extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); #define ioremap_wc ioremap_wc @@ -911,14 +904,12 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); #define ioremap_cache(addr, size) \ ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) -extern void iounmap(volatile void __iomem *addr); +#define iounmap iounmap void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size); int early_ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot); -void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller); extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, pgprot_t prot, void *caller); diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index 3360cad78ace..3a971e2a8c73 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -45,6 +45,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) pte_fragment_free((unsigned long *)ptepage, 0); } +/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */ +#define pte_free_defer pte_free_defer +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + /* * Functions that deal with pagetables that could be at any level of * the table need to be passed an "index_size" so they know how to diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 6a88bfdaa69b..33464e6d6431 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -158,13 +158,30 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd) } #ifdef CONFIG_PPC64 -#define is_ioremap_addr is_ioremap_addr -static inline bool is_ioremap_addr(const void *x) +int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size); +bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, + unsigned long page_size); +/* + * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details + * some of the restrictions. We don't check for PMD_SIZE because our + * vmemmap allocation code can fallback correctly. The pageblock + * alignment requirement is met using altmap->reserve blocks. + */ +#define arch_supports_memmap_on_memory arch_supports_memmap_on_memory +static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size) { - unsigned long addr = (unsigned long)x; - - return addr >= IOREMAP_BASE && addr < IOREMAP_END; + if (!radix_enabled()) + return false; + /* + * With 4K page size and 2M PMD_SIZE, we can align + * things better with memory block size value + * starting from 128MB. Hence align things with PMD_SIZE. + */ + if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) + return IS_ALIGNED(vmemmap_size, PMD_SIZE); + return true; } + #endif /* CONFIG_PPC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 709ebd578394..e2d6f9327f77 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -410,6 +410,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm, ret = H_STATE; break; } + vma_start_write(vma); /* Copy vm_flags to avoid partial modifications in ksm_madvise */ vm_flags = vma->vm_flags; ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 51f48984abca..988948d69bc1 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -214,7 +214,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr old = be64_to_cpu(old_be); - trace_hugepage_update(addr, old, clr, set); + trace_hugepage_update_pmd(addr, old, clr, set); if (old & H_PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index c766e4c26e42..1715b07c630c 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -246,15 +246,15 @@ static void destroy_contexts(mm_context_t *ctx) static void pmd_frag_destroy(void *pmd_frag) { int count; - struct page *page; + struct ptdesc *ptdesc; - page = virt_to_page(pmd_frag); + ptdesc = virt_to_ptdesc(pmd_frag); /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 85c84e89e3ea..1498ccd08367 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -64,11 +64,39 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, return changed; } +int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp, pud_t entry, int dirty) +{ + int changed; +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(vma->vm_mm, pudp)); +#endif + changed = !pud_same(*(pudp), entry); + if (changed) { + /* + * We can use MMU_PAGE_1G here, because only radix + * path look at the psize. + */ + __ptep_set_access_flags(vma, pudp_ptep(pudp), + pud_pte(entry), address, MMU_PAGE_1G); + } + return changed; +} + + int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); } + +int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return __pudp_test_and_clear_young(vma->vm_mm, address, pudp); +} + /* * set a new huge pmd. We should not be called for updating * an existing pmd entry. That should go via pmd_hugepage_update. @@ -90,6 +118,23 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } +void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + /* + * Make sure hardware valid bit is not set. We don't do + * tlb flush for this update. + */ + + WARN_ON(pte_hw_valid(pud_pte(*pudp))); + assert_spin_locked(pud_lockptr(mm, pudp)); + WARN_ON(!(pud_large(pud))); +#endif + trace_hugepage_set_pud(addr, pud_val(pud)); + return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); +} + static void do_serialize(void *arg) { /* We've taken the IPI, so try to trim the mask while here */ @@ -147,11 +192,35 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, return pmd; } +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, int full) +{ + pud_t pud; + + VM_BUG_ON(addr & ~HPAGE_PMD_MASK); + VM_BUG_ON((pud_present(*pudp) && !pud_devmap(*pudp)) || + !pud_present(*pudp)); + pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp); + /* + * if it not a fullmm flush, then we can possibly end up converting + * this PMD pte entry to a regular level 0 PTE by a parallel page fault. + * Make sure we flush the tlb in this case. + */ + if (!full) + flush_pud_tlb_range(vma, addr, addr + HPAGE_PUD_SIZE); + return pud; +} + static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) { return __pmd(pmd_val(pmd) | pgprot_val(pgprot)); } +static pud_t pud_set_protbits(pud_t pud, pgprot_t pgprot) +{ + return __pud(pud_val(pud) | pgprot_val(pgprot)); +} + /* * At some point we should be able to get rid of * pmd_mkhuge() and mk_huge_pmd() when we update all the @@ -166,6 +235,15 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot) return __pmd_mkhuge(pmd_set_protbits(__pmd(pmdv), pgprot)); } +pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot) +{ + unsigned long pudv; + + pudv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK; + + return __pud_mkhuge(pud_set_protbits(__pud(pudv), pgprot)); +} + pmd_t mk_pmd(struct page *page, pgprot_t pgprot) { return pfn_pmd(page_to_pfn(page), pgprot); @@ -306,22 +384,22 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) { void *ret = NULL; - struct page *page; + struct ptdesc *ptdesc; gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; - page = alloc_page(gfp); - if (!page) + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_pages(page, 0); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - atomic_set(&page->pt_frag_refcount, 1); + atomic_set(&ptdesc->pt_frag_refcount, 1); - ret = page_address(page); + ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page. @@ -331,12 +409,12 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) spin_lock(&mm->page_table_lock); /* - * If we find pgtable_page set, we return + * If we find ptdesc_page set, we return * the allocated page with single fragment * count. */ if (likely(!mm->context.pmd_frag)) { - atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); + atomic_set(&ptdesc->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -357,15 +435,15 @@ pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr) void pmd_fragment_free(unsigned long *pmd) { - struct page *page = virt_to_page(pmd); + struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - if (PageReserved(page)) - return free_reserved_page(page); + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index 5e3195568525..17075c78d4bc 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -39,6 +39,7 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st radix__flush_tlb_pwc_range_psize(vma->vm_mm, start, end, psize); else radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize); + mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index e7ea492ac510..96679018e7fb 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -601,17 +601,6 @@ void __init radix__early_init_mmu(void) #else mmu_virtual_psize = MMU_PAGE_4K; #endif - -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* vmemmap mapping */ - if (mmu_psize_defs[MMU_PAGE_2M].shift) { - /* - * map vmemmap using 2M if available - */ - mmu_vmemmap_psize = MMU_PAGE_2M; - } else - mmu_vmemmap_psize = mmu_virtual_psize; -#endif #endif /* * initialize page table size @@ -744,8 +733,58 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d) p4d_clear(p4d); } -static void remove_pte_table(pte_t *pte_start, unsigned long addr, - unsigned long end, bool direct) +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PMD_SIZE); + + return !vmemmap_populated(start, PMD_SIZE); +} + +static bool __meminit vmemmap_page_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE); + + return !vmemmap_populated(start, PAGE_SIZE); + +} +#endif + +static void __meminit free_vmemmap_pages(struct page *page, + struct vmem_altmap *altmap, + int order) +{ + unsigned int nr_pages = 1 << order; + + if (altmap) { + unsigned long alt_start, alt_end; + unsigned long base_pfn = page_to_pfn(page); + + /* + * with 2M vmemmap mmaping we can have things setup + * such that even though atlmap is specified we never + * used altmap. + */ + alt_start = altmap->base_pfn; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; + + if (base_pfn >= alt_start && base_pfn < alt_end) { + vmem_altmap_free(altmap, nr_pages); + return; + } + } + + if (PageReserved(page)) { + /* allocated from memblock */ + while (nr_pages--) + free_reserved_page(page++); + } else + free_pages((unsigned long)page_address(page), order); +} + +static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte; @@ -759,24 +798,26 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, if (!pte_present(*pte)) continue; - if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) { - /* - * The vmemmap_free() and remove_section_mapping() - * codepaths call us with aligned addresses. - */ - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { + if (!direct) + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + pages++; } - - pte_clear(&init_mm, addr, pte); - pages++; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_page_is_unused(addr, next)) { + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + } +#endif } if (direct) update_page_count(mmu_virtual_psize, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, - unsigned long end, bool direct) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte_base; @@ -790,18 +831,24 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_is_leaf(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + if (!direct) + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + pages++; } - pte_clear(&init_mm, addr, (pte_t *)pmd); - pages++; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_pmd_is_unused(addr, next)) { + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + } +#endif continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next, direct); + remove_pte_table(pte_base, addr, next, direct, altmap); free_pte_table(pte_base, pmd); } if (direct) @@ -809,7 +856,8 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, - unsigned long end, bool direct) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pmd_t *pmd_base; @@ -834,15 +882,16 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, } pmd_base = pud_pgtable(*pud); - remove_pmd_table(pmd_base, addr, next, direct); + remove_pmd_table(pmd_base, addr, next, direct, altmap); free_pmd_table(pmd_base, pud); } if (direct) update_page_count(MMU_PAGE_1G, -pages); } -static void __meminit remove_pagetable(unsigned long start, unsigned long end, - bool direct) +static void __meminit +remove_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long addr, next; pud_t *pud_base; @@ -871,7 +920,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end, } pud_base = p4d_pgtable(*p4d); - remove_pud_table(pud_base, addr, next, direct); + remove_pud_table(pud_base, addr, next, direct, altmap); free_pud_table(pud_base, p4d); } @@ -894,7 +943,7 @@ int __meminit radix__create_section_mapping(unsigned long start, int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) { - remove_pagetable(start, end, true); + remove_pagetable(start, end, true, NULL); return 0; } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -926,10 +975,429 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, return 0; } + +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) +{ + if (radix_enabled()) + return __vmemmap_can_optimize(altmap, pgmap); + + return false; +} + +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_large(*pmdp); + + if (large) + vmemmap_verify(pmdp_ptep(pmdp), node, addr, next); + + return large; +} + +void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, + unsigned long addr, unsigned long next) +{ + pte_t entry; + pte_t *ptep = pmdp_ptep(pmdp); + + VM_BUG_ON(!IS_ALIGNED(addr, PMD_SIZE)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, ptep, entry); + asm volatile("ptesync": : :"memory"); + + vmemmap_verify(ptep, node, addr, next); +} + +static pte_t * __meminit radix__vmemmap_pte_populate(pmd_t *pmdp, unsigned long addr, + int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pte_t *pte = pte_offset_kernel(pmdp, addr); + + if (pte_none(*pte)) { + pte_t entry; + void *p; + + if (!reuse) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + if (altmap && altmap_cross_boundary(altmap, addr, PAGE_SIZE)) + altmap = NULL; + + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); + if (!p && altmap) + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, NULL); + if (!p) + return NULL; + pr_debug("PAGE_SIZE vmemmap mapping\n"); + } else { + /* + * When a PTE/PMD entry is freed from the init_mm + * there's a free_pages() call to this page allocated + * above. Thus this get_page() is paired with the + * put_page_testzero() on the freeing path. + * This can only called by certain ZONE_DEVICE path, + * and through vmemmap_populate_compound_pages() when + * slab is available. + */ + get_page(reuse); + p = page_to_virt(reuse); + pr_debug("Tail page reuse vmemmap mapping\n"); + } + + VM_BUG_ON(!PAGE_ALIGNED(addr)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + asm volatile("ptesync": : :"memory"); + } + return pte; +} + +static inline pud_t *vmemmap_pud_alloc(p4d_t *p4dp, int node, + unsigned long address) +{ + pud_t *pud; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(p4d_none(*p4dp))) { + if (unlikely(!slab_is_available())) { + pud = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + p4d_populate(&init_mm, p4dp, pud); + /* go to the pud_offset */ + } else + return pud_alloc(&init_mm, p4dp, address); + } + return pud_offset(p4dp, address); +} + +static inline pmd_t *vmemmap_pmd_alloc(pud_t *pudp, int node, + unsigned long address) +{ + pmd_t *pmd; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pud_none(*pudp))) { + if (unlikely(!slab_is_available())) { + pmd = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pud_populate(&init_mm, pudp, pmd); + } else + return pmd_alloc(&init_mm, pudp, address); + } + return pmd_offset(pudp, address); +} + +static inline pte_t *vmemmap_pte_alloc(pmd_t *pmdp, int node, + unsigned long address) +{ + pte_t *pte; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pmd_none(*pmdp))) { + if (unlikely(!slab_is_available())) { + pte = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pmd_populate(&init_mm, pmdp, pte); + } else + return pte_alloc_kernel(pmdp, address); + } + return pte_offset_kernel(pmdp, address); +} + + + +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + unsigned long addr; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_none(READ_ONCE(*pmd))) { + void *p; + + /* + * keep it simple by checking addr PMD_SIZE alignment + * and verifying the device boundary condition. + * For us to use a pmd mapping, both addr and pfn should + * be aligned. We skip if addr is not aligned and for + * pfn we hope we have extra area in the altmap that + * can help to find an aligned block. This can result + * in altmap block allocation failures, in which case + * we fallback to RAM for vmemmap allocation. + */ + if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) || + altmap_cross_boundary(altmap, addr, PMD_SIZE))) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + goto base_mapping; + } + + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); + if (p) { + vmemmap_set_pmd(pmd, p, node, addr, next); + pr_debug("PMD_SIZE vmemmap mapping\n"); + continue; + } else if (altmap) { + /* + * A vmemmap block allocation can fail due to + * alignment requirements and we trying to align + * things aggressively there by running out of + * space. Try base mapping on failure. + */ + goto base_mapping; + } + } else if (vmemmap_check_pmd(pmd, node, addr, next)) { + /* + * If a huge mapping exist due to early call to + * vmemmap_populate, let's try to use that. + */ + continue; + } +base_mapping: + /* + * Not able allocate higher order memory to back memmap + * or we found a pointer to pte page. Allocate base page + * size vmemmap + */ + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + + pte = radix__vmemmap_pte_populate(pmd, addr, node, altmap, NULL); + if (!pte) + return -ENOMEM; + + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + next = addr + PAGE_SIZE; + } + return 0; +} + +static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return NULL; + radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + return pte; +} + +static pte_t * __meminit vmemmap_compound_tail_page(unsigned long addr, + unsigned long pfn_offset, int node) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long map_addr; + + /* the second vmemmap page which we use for duplication */ + map_addr = addr - pfn_offset * sizeof(struct page) + PAGE_SIZE; + pgd = pgd_offset_k(map_addr); + p4d = p4d_offset(pgd, map_addr); + pud = vmemmap_pud_alloc(p4d, node, map_addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, map_addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, map_addr); + if (!pte) + return NULL; + /* + * Check if there exist a mapping to the left + */ + if (pte_none(*pte)) { + /* + * Populate the head page vmemmap page. + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(map_addr - PAGE_SIZE, node, NULL, NULL); + if (!pte) + return NULL; + /* + * Populate the tail pages vmemmap page + */ + pte = radix__vmemmap_pte_populate(pmd, map_addr, node, NULL, NULL); + if (!pte) + return NULL; + vmemmap_verify(pte, node, map_addr, map_addr + PAGE_SIZE); + return pte; + } + return pte; +} + +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap) +{ + /* + * we want to map things as base page size mapping so that + * we can save space in vmemmap. We could have huge mapping + * covering out both edges. + */ + unsigned long addr; + unsigned long addr_pfn = start_pfn; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_leaf(READ_ONCE(*pmd))) { + /* existing huge mapping. Skip the range */ + addr_pfn += (PMD_SIZE >> PAGE_SHIFT); + next = pmd_addr_end(addr, end); + continue; + } + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + if (!pte_none(*pte)) { + /* + * This could be because we already have a compound + * page whose VMEMMAP_RESERVE_NR pages were mapped and + * this request fall in those pages. + */ + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } else { + unsigned long nr_pages = pgmap_vmemmap_nr(pgmap); + unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages); + pte_t *tail_page_pte; + + /* + * if the address is aligned to huge page size it is the + * head mapping. + */ + if (pfn_offset == 0) { + /* Populate the head page vmemmap page */ + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + /* + * Populate the tail pages vmemmap page + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL); + if (!pte) + return -ENOMEM; + + addr_pfn += 2; + next = addr + 2 * PAGE_SIZE; + continue; + } + /* + * get the 2nd mapping details + * Also create it if that doesn't exist + */ + tail_page_pte = vmemmap_compound_tail_page(addr, pfn_offset, node); + if (!tail_page_pte) { + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, pte_page(*tail_page_pte)); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + } + return 0; +} + + #ifdef CONFIG_MEMORY_HOTPLUG void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { - remove_pagetable(start, start + page_size, false); + remove_pagetable(start, start + page_size, true, NULL); +} + +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) +{ + remove_pagetable(start, end, false, altmap); } #endif #endif @@ -962,7 +1430,24 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add #endif old = radix__pte_update(mm, addr, pmdp_ptep(pmdp), clr, set, 1); - trace_hugepage_update(addr, old, clr, set); + trace_hugepage_update_pmd(addr, old, clr, set); + + return old; +} + +unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set) +{ + unsigned long old; + +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(mm, pudp)); +#endif + + old = radix__pte_update(mm, addr, pudp_ptep(pudp), clr, set, 1); + trace_hugepage_update_pud(addr, old, clr, set); return old; } @@ -1043,6 +1528,17 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, return old_pmd; } +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + pud_t old_pud; + unsigned long old; + + old = radix__pud_hugepage_update(mm, addr, pudp, ~0UL, 0); + old_pud = __pud(old); + return old_pud; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 0bd4866d9824..3020a8b38572 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -987,6 +987,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm) } } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } EXPORT_SYMBOL(radix__flush_tlb_mm); @@ -1020,6 +1021,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL); } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } void radix__flush_all_mm(struct mm_struct *mm) @@ -1228,6 +1230,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, @@ -1392,6 +1395,7 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, @@ -1461,6 +1465,13 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, } EXPORT_SYMBOL(radix__flush_pmd_tlb_range); +void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_1G); +} +EXPORT_SYMBOL(radix__flush_pud_tlb_range); + void radix__flush_tlb_all(void) { unsigned long rb,prs,r,rs; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5bfdf6ecfa96..fafce6bdeff0 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -469,7 +469,6 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (is_exec) flags |= FAULT_FLAG_INSTRUCTION; -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -501,7 +500,6 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, return user_mode(regs) ? 0 : SIGBUS; lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -551,9 +549,7 @@ retry: mmap_read_unlock(current->mm); -#ifdef CONFIG_PER_VMA_LOCK done: -#endif if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index fe1b83020e0d..f7930360406e 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -92,7 +92,7 @@ static struct page * __meminit vmemmap_subsection_start(unsigned long vmemmap_ad * a page table lookup here because with the hash translation we don't keep * vmemmap details in linux page table. */ -static int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size) +int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size) { struct page *start; unsigned long vmemmap_end = vmemmap_addr + vmemmap_map_size; @@ -183,8 +183,8 @@ static __meminit int vmemmap_list_populate(unsigned long phys, return 0; } -static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, - unsigned long page_size) +bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, + unsigned long page_size) { unsigned long nr_pfn = page_size / sizeof(struct page); unsigned long start_pfn = page_to_pfn((struct page *)start); @@ -198,8 +198,8 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star return false; } -int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) +static int __meminit __vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) { bool altmap_alloc; unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; @@ -272,6 +272,18 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return 0; } +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + +#ifdef CONFIG_PPC_BOOK3S_64 + if (radix_enabled()) + return radix__vmemmap_populate(start, end, node, altmap); +#endif + + return __vmemmap_populate(start, end, node, altmap); +} + #ifdef CONFIG_MEMORY_HOTPLUG static unsigned long vmemmap_list_free(unsigned long start) { @@ -303,8 +315,8 @@ static unsigned long vmemmap_list_free(unsigned long start) return vmem_back->phys; } -void __ref vmemmap_free(unsigned long start, unsigned long end, - struct vmem_altmap *altmap) +static void __ref __vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) { unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; unsigned long page_order = get_order(page_size); @@ -362,6 +374,17 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, vmemmap_remove_mapping(start, page_size); } } + +void __ref vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (radix_enabled()) + return radix__vmemmap_free(start, end, altmap); +#endif + return __vmemmap_free(start, end, altmap); +} + #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index 4f12504fb405..705e8e8ffde4 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -41,7 +41,7 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, prot, caller); } -void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long flags) { pte_t pte = __pte(flags); void *caller = __builtin_return_address(0); @@ -74,27 +74,3 @@ int early_ioremap_range(unsigned long ea, phys_addr_t pa, return 0; } - -void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller) -{ - struct vm_struct *area; - int ret; - unsigned long va; - - area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller); - if (area == NULL) - return NULL; - - area->phys_addr = pa; - va = (unsigned long)area->addr; - - ret = ioremap_page_range(va, va + size, pa, prot); - if (!ret) - return (void __iomem *)area->addr + offset; - - vunmap_range(va, va + size); - free_vm_area(area); - - return NULL; -} diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c index 9d13143b8be4..ca5bc6be3e6f 100644 --- a/arch/powerpc/mm/ioremap_32.c +++ b/arch/powerpc/mm/ioremap_32.c @@ -22,6 +22,13 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call int err; /* + * If the address lies within the first 16 MB, assume it's in ISA + * memory space + */ + if (addr < SZ_16M) + addr += _ISA_MEM_BASE; + + /* * Choose an address to map it to. * Once the vmalloc system is running, we use it. * Before then, we use space going down from IOREMAP_TOP @@ -31,13 +38,6 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call offset = addr & ~PAGE_MASK; size = PAGE_ALIGN(addr + size) - p; - /* - * If the address lies within the first 16 MB, assume it's in ISA - * memory space - */ - if (p < 16 * 1024 * 1024) - p += _ISA_MEM_BASE; - #ifndef CONFIG_CRASH_DUMP /* * Don't allow anybody to remap normal RAM that we're using. @@ -63,7 +63,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call return (void __iomem *)v + offset; if (slab_is_available()) - return do_ioremap(p, offset, size, prot, caller); + return generic_ioremap_prot(addr, size, prot); /* * Should check if it is a candidate for a BAT mapping @@ -87,7 +87,6 @@ void iounmap(volatile void __iomem *addr) if (v_block_mapped((unsigned long)addr)) return; - if (addr > high_memory && (unsigned long)addr < ioremap_bot) - vunmap((void *)(PAGE_MASK & (unsigned long)addr)); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c index 3acece00b33e..d24e5f166723 100644 --- a/arch/powerpc/mm/ioremap_64.c +++ b/arch/powerpc/mm/ioremap_64.c @@ -29,7 +29,7 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, return NULL; if (slab_is_available()) - return do_ioremap(paligned, offset, size, prot, caller); + return generic_ioremap_prot(addr, size, prot); pr_warn("ioremap() called early from %pS. Use early_ioremap() instead\n", caller); @@ -49,17 +49,9 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, */ void iounmap(volatile void __iomem *token) { - void *addr; - if (!slab_is_available()) return; - addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK); - - if ((unsigned long)addr < ioremap_bot) { - pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr); - return; - } - vunmap(addr); + generic_iounmap(PCI_FIX_ADDR(token)); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index 20652daa1d7e..8c31802f97e8 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -18,15 +18,15 @@ void pte_frag_destroy(void *pte_frag) { int count; - struct page *page; + struct ptdesc *ptdesc; - page = virt_to_page(pte_frag); + ptdesc = virt_to_ptdesc(pte_frag); /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_pte_page_dtor(page); - __free_page(page); + if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } } @@ -55,25 +55,25 @@ static pte_t *get_pte_from_cache(struct mm_struct *mm) static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) { void *ret = NULL; - struct page *page; + struct ptdesc *ptdesc; if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) + ptdesc = pagetable_alloc(PGALLOC_GFP | __GFP_ACCOUNT, 0); + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } } else { - page = alloc_page(PGALLOC_GFP); - if (!page) + ptdesc = pagetable_alloc(PGALLOC_GFP, 0); + if (!ptdesc) return NULL; } - atomic_set(&page->pt_frag_refcount, 1); + atomic_set(&ptdesc->pt_frag_refcount, 1); - ret = page_address(page); + ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page. @@ -82,12 +82,12 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return ret; spin_lock(&mm->page_table_lock); /* - * If we find pgtable_page set, we return + * If we find ptdesc_page set, we return * the allocated page with single fragment * count. */ if (likely(!pte_frag_get(&mm->context))) { - atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); + atomic_set(&ptdesc->pt_frag_refcount, PTE_FRAG_NR); pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE); } spin_unlock(&mm->page_table_lock); @@ -106,17 +106,40 @@ pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel) return __alloc_for_ptecache(mm, kernel); } -void pte_fragment_free(unsigned long *table, int kernel) +static void pte_free_now(struct rcu_head *head) { - struct page *page = virt_to_page(table); + struct ptdesc *ptdesc; - if (PageReserved(page)) - return free_reserved_page(page); + ptdesc = container_of(head, struct ptdesc, pt_rcu_head); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); +} - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - if (!kernel) - pgtable_pte_page_dtor(page); - __free_page(page); +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct ptdesc *ptdesc = virt_to_ptdesc(table); + + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); + + BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { + if (kernel) + pagetable_free(ptdesc); + else if (folio_test_clear_active(ptdesc_folio(ptdesc))) + call_rcu(&ptdesc->pt_rcu_head, pte_free_now); + else + pte_free_now(&ptdesc->pt_rcu_head); } } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) +{ + struct page *page; + + page = virt_to_page(pgtable); + SetPageActive(page); + pte_fragment_free((unsigned long *)pgtable, 0); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index cb2dcdb18f8e..a3dcdb2d5b4b 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -311,6 +311,8 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) p4d_t *p4d; pud_t *pud; pmd_t *pmd; + pte_t *pte; + spinlock_t *ptl; if (mm == &init_mm) return; @@ -329,8 +331,10 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) */ if (pmd_none(*pmd)) return; - BUG_ON(!pmd_present(*pmd)); - assert_spin_locked(pte_lockptr(mm, pmd)); + pte = pte_offset_map_nolock(mm, pmd, addr, &ptl); + BUG_ON(!pte); + assert_spin_locked(ptl); + pte_unmap(pte); } #endif /* CONFIG_DEBUG_VM */ diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 45fd975ef521..340b86ef7284 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -94,6 +94,7 @@ config PPC_BOOK3S_64 select PPC_FPU select PPC_HAVE_PMU_SUPPORT select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_SPLIT_PMD_PTLOCK select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9c62c2c3b3d0..4f3d6a2f9065 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -637,7 +637,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) nid = first_online_node; /* Add the memory */ - rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE); + rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index fae747cc57d2..ee17270d35d0 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1084,7 +1084,7 @@ cmds(struct pt_regs *excp) memzcan(); break; case 'i': - show_mem(0, NULL); + show_mem(); break; default: termch = cmd; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 4c07b9189c86..6943d34c1ec1 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -53,7 +53,7 @@ config RISCV select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL - select ARCH_WANT_OPTIMIZE_VMEMMAP + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index ce1ebda1a49a..34e24f078cc1 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -2,6 +2,7 @@ #ifndef _ASM_RISCV_HUGETLB_H #define _ASM_RISCV_HUGETLB_H +#include <asm/cacheflush.h> #include <asm/page.h> static inline void arch_clear_hugepage_flags(struct page *page) diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 59dc12b5b7e8..d169a4f41a2e 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -153,10 +153,10 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #endif /* __PAGETABLE_PMD_FOLDED */ -#define __pte_free_tlb(tlb, pte, buf) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), pte); \ +#define __pte_free_tlb(tlb, pte, buf) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\ } while (0) #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 75970ee2bda2..44377f0d7c35 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -499,7 +499,7 @@ static inline void __set_pte_at(struct mm_struct *mm, static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { - page_table_check_pte_set(mm, addr, ptep, pteval); + page_table_check_pte_set(mm, ptep, pteval); __set_pte_at(mm, addr, ptep, pteval); } @@ -529,7 +529,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } @@ -687,14 +687,14 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); + page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); + page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); } @@ -742,7 +742,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, { pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0)); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -758,7 +758,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd))); } diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 6ea2cce4cc17..046732fcb48c 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -283,7 +283,6 @@ void handle_page_fault(struct pt_regs *regs) flags |= FAULT_FLAG_WRITE; else if (cause == EXC_INST_PAGE_FAULT) flags |= FAULT_FLAG_INSTRUCTION; -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -311,7 +310,6 @@ void handle_page_fault(struct pt_regs *regs) return; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ retry: vma = lock_mm_and_find_vma(mm, addr, regs); @@ -368,9 +366,7 @@ retry: mmap_read_unlock(mm); -#ifdef CONFIG_PER_VMA_LOCK done: -#endif if (unlikely(fault & VM_FAULT_ERROR)) { tsk->thread.bad_cause = cause; mm_fault_error(regs, addr, fault); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9ce504737d18..430a3d05a841 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -353,12 +353,10 @@ static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va) static phys_addr_t __init alloc_pte_late(uintptr_t va) { - unsigned long vaddr; - - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr || !pgtable_pte_page_ctor(virt_to_page((void *)vaddr))); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - return __pa(vaddr); + BUG_ON(!ptdesc || !pagetable_pte_ctor(ptdesc)); + return __pa((pte_t *)ptdesc_address(ptdesc)); } static void __init create_pte_mapping(pte_t *ptep, @@ -436,12 +434,10 @@ static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) static phys_addr_t __init alloc_pmd_late(uintptr_t va) { - unsigned long vaddr; - - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr || !pgtable_pmd_page_ctor(virt_to_page((void *)vaddr))); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - return __pa(vaddr); + BUG_ON(!ptdesc || !pagetable_pmd_ctor(ptdesc)); + return __pa((pmd_t *)ptdesc_address(ptdesc)); } static void __init create_pmd_mapping(pmd_t *pmdp, diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 5b39918b7042..8ff6d1c21e38 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -127,7 +127,7 @@ config S390 select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_IPC_PARSE_VERSION - select ARCH_WANT_OPTIMIZE_VMEMMAP + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 select DMA_OPS if PCI @@ -143,6 +143,7 @@ config S390 select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_VDSO_TIME_NS + select GENERIC_IOREMAP if PCI select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index e3882b012bfa..4453ad7c11ac 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -22,11 +22,18 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 -void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot); -void __iomem *ioremap(phys_addr_t addr, size_t size); -void __iomem *ioremap_wc(phys_addr_t addr, size_t size); -void __iomem *ioremap_wt(phys_addr_t addr, size_t size); -void iounmap(volatile void __iomem *addr); +/* + * I/O memory mapping functions. + */ +#define ioremap_prot ioremap_prot +#define iounmap iounmap + +#define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL) + +#define ioremap_wc(addr, size) \ + ioremap_prot((addr), (size), pgprot_val(pgprot_writecombine(PAGE_KERNEL))) +#define ioremap_wt(addr, size) \ + ioremap_prot((addr), (size), pgprot_val(pgprot_writethrough(PAGE_KERNEL))) static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { @@ -51,10 +58,6 @@ static inline void ioport_unmap(void __iomem *p) #define pci_iomap_wc pci_iomap_wc #define pci_iomap_wc_range pci_iomap_wc_range -#define ioremap ioremap -#define ioremap_wt ioremap_wt -#define ioremap_wc ioremap_wc - #define memcpy_fromio(dst, src, count) zpci_memcpy_fromio(dst, src, count) #define memcpy_toio(dst, src, count) zpci_memcpy_toio(dst, src, count) #define memset_io(dst, val, count) zpci_memset_io(dst, val, count) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 17eb618f1348..376b4b23bdaa 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -86,7 +86,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) if (!table) return NULL; crst_table_init(table, _SEGMENT_ENTRY_EMPTY); - if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) { crst_table_free(mm, table); return NULL; } @@ -97,7 +97,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { if (mm_pmd_folded(mm)) return; - pgtable_pmd_page_dtor(virt_to_page(pmd)); + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); crst_table_free(mm, (unsigned long *) pmd); } @@ -143,6 +143,10 @@ static inline void pmd_populate(struct mm_struct *mm, #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte) #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte) +/* arch use pte_free_defer() implementation in arch/s390/mm/pgalloc.c */ +#define pte_free_defer pte_free_defer +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + void vmem_map_init(void); void *vmem_crst_alloc(unsigned long val); pte_t *vmem_pte_alloc(void); diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index b91f4a9b044c..383b1f91442c 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -89,12 +89,12 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, { if (mm_pmd_folded(tlb->mm)) return; - pgtable_pmd_page_dtor(virt_to_page(pmd)); + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_puds = 1; - tlb_remove_table(tlb, pmd); + tlb_remove_ptdesc(tlb, pmd); } /* diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2f123429a291..6f6b9881e55e 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -407,7 +407,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) access = VM_WRITE; if (access == VM_WRITE) flags |= FAULT_FLAG_WRITE; -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, address); @@ -432,7 +431,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) goto out; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ mmap_read_lock(mm); gmap = NULL; diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 66ab68db9842..07fc660a24aa 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -43,17 +43,17 @@ __initcall(page_table_register_sysctl); unsigned long *crst_table_alloc(struct mm_struct *mm) { - struct page *page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER); - if (!page) + if (!ptdesc) return NULL; - arch_set_page_dat(page, CRST_ALLOC_ORDER); - return (unsigned long *) page_to_virt(page); + arch_set_page_dat(ptdesc_page(ptdesc), CRST_ALLOC_ORDER); + return (unsigned long *) ptdesc_to_virt(ptdesc); } void crst_table_free(struct mm_struct *mm, unsigned long *table) { - free_pages((unsigned long)table, CRST_ALLOC_ORDER); + pagetable_free(virt_to_ptdesc(table)); } static void __crst_table_upgrade(void *arg) @@ -140,21 +140,21 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) struct page *page_table_alloc_pgste(struct mm_struct *mm) { - struct page *page; + struct ptdesc *ptdesc; u64 *table; - page = alloc_page(GFP_KERNEL); - if (page) { - table = (u64 *)page_to_virt(page); + ptdesc = pagetable_alloc(GFP_KERNEL, 0); + if (ptdesc) { + table = (u64 *)ptdesc_to_virt(ptdesc); memset64(table, _PAGE_INVALID, PTRS_PER_PTE); memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE); } - return page; + return ptdesc_page(ptdesc); } void page_table_free_pgste(struct page *page) { - __free_page(page); + pagetable_free(page_ptdesc(page)); } #endif /* CONFIG_PGSTE */ @@ -229,11 +229,20 @@ void page_table_free_pgste(struct page *page) * logic described above. Both AA bits are set to 1 to denote a 4KB-pgtable * while the PP bits are never used, nor such a page is added to or removed * from mm_context_t::pgtable_list. + * + * pte_free_defer() overrides those rules: it takes the page off pgtable_list, + * and prevents both 2K fragments from being reused. pte_free_defer() has to + * guarantee that its pgtable cannot be reused before the RCU grace period + * has elapsed (which page_table_free_rcu() does not actually guarantee). + * But for simplicity, because page->rcu_head overlays page->lru, and because + * the RCU callback might not be called before the mm_context_t has been freed, + * pte_free_defer() in this implementation prevents both fragments from being + * reused, and delays making the call to RCU until both fragments are freed. */ unsigned long *page_table_alloc(struct mm_struct *mm) { unsigned long *table; - struct page *page; + struct ptdesc *ptdesc; unsigned int mask, bit; /* Try to get a fragment of a 4K page as a 2K page table */ @@ -241,9 +250,9 @@ unsigned long *page_table_alloc(struct mm_struct *mm) table = NULL; spin_lock_bh(&mm->context.lock); if (!list_empty(&mm->context.pgtable_list)) { - page = list_first_entry(&mm->context.pgtable_list, - struct page, lru); - mask = atomic_read(&page->_refcount) >> 24; + ptdesc = list_first_entry(&mm->context.pgtable_list, + struct ptdesc, pt_list); + mask = atomic_read(&ptdesc->_refcount) >> 24; /* * The pending removal bits must also be checked. * Failure to do so might lead to an impossible @@ -255,13 +264,13 @@ unsigned long *page_table_alloc(struct mm_struct *mm) */ mask = (mask | (mask >> 4)) & 0x03U; if (mask != 0x03U) { - table = (unsigned long *) page_to_virt(page); + table = (unsigned long *) ptdesc_to_virt(ptdesc); bit = mask & 1; /* =1 -> second 2K */ if (bit) table += PTRS_PER_PTE; - atomic_xor_bits(&page->_refcount, + atomic_xor_bits(&ptdesc->_refcount, 0x01U << (bit + 24)); - list_del(&page->lru); + list_del_init(&ptdesc->pt_list); } } spin_unlock_bh(&mm->context.lock); @@ -269,27 +278,28 @@ unsigned long *page_table_alloc(struct mm_struct *mm) return table; } /* Allocate a fresh page */ - page = alloc_page(GFP_KERNEL); - if (!page) + ptdesc = pagetable_alloc(GFP_KERNEL, 0); + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - arch_set_page_dat(page, 0); + arch_set_page_dat(ptdesc_page(ptdesc), 0); /* Initialize page table */ - table = (unsigned long *) page_to_virt(page); + table = (unsigned long *) ptdesc_to_virt(ptdesc); if (mm_alloc_pgste(mm)) { /* Return 4K page table with PGSTEs */ - atomic_xor_bits(&page->_refcount, 0x03U << 24); + INIT_LIST_HEAD(&ptdesc->pt_list); + atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); } else { /* Return the first 2K fragment of the page */ - atomic_xor_bits(&page->_refcount, 0x01U << 24); + atomic_xor_bits(&ptdesc->_refcount, 0x01U << 24); memset64((u64 *)table, _PAGE_INVALID, 2 * PTRS_PER_PTE); spin_lock_bh(&mm->context.lock); - list_add(&page->lru, &mm->context.pgtable_list); + list_add(&ptdesc->pt_list, &mm->context.pgtable_list); spin_unlock_bh(&mm->context.lock); } return table; @@ -300,7 +310,9 @@ static void page_table_release_check(struct page *page, void *table, { char msg[128]; - if (!IS_ENABLED(CONFIG_DEBUG_VM) || !mask) + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return; + if (!mask && list_empty(&page->lru)) return; snprintf(msg, sizeof(msg), "Invalid pgtable %p release half 0x%02x mask 0x%02x", @@ -308,12 +320,20 @@ static void page_table_release_check(struct page *page, void *table, dump_page(page, msg); } +static void pte_free_now(struct rcu_head *head) +{ + struct ptdesc *ptdesc; + + ptdesc = container_of(head, struct ptdesc, pt_rcu_head); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); +} + void page_table_free(struct mm_struct *mm, unsigned long *table) { unsigned int mask, bit, half; - struct page *page; + struct ptdesc *ptdesc = virt_to_ptdesc(table); - page = virt_to_page(table); if (!mm_alloc_pgste(mm)) { /* Free 2K page table fragment of a 4K page */ bit = ((unsigned long) table & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)); @@ -323,42 +343,50 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) * will happen outside of the critical section from this * function or from __tlb_remove_table() */ - mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24)); + mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24)); mask >>= 24; - if (mask & 0x03U) - list_add(&page->lru, &mm->context.pgtable_list); - else - list_del(&page->lru); + if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) { + /* + * Other half is allocated, and neither half has had + * its free deferred: add page to head of list, to make + * this freed half available for immediate reuse. + */ + list_add(&ptdesc->pt_list, &mm->context.pgtable_list); + } else { + /* If page is on list, now remove it. */ + list_del_init(&ptdesc->pt_list); + } spin_unlock_bh(&mm->context.lock); - mask = atomic_xor_bits(&page->_refcount, 0x10U << (bit + 24)); + mask = atomic_xor_bits(&ptdesc->_refcount, 0x10U << (bit + 24)); mask >>= 24; if (mask != 0x00U) return; half = 0x01U << bit; } else { half = 0x03U; - mask = atomic_xor_bits(&page->_refcount, 0x03U << 24); + mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); mask >>= 24; } - page_table_release_check(page, table, half, mask); - pgtable_pte_page_dtor(page); - __free_page(page); + page_table_release_check(ptdesc_page(ptdesc), table, half, mask); + if (folio_test_clear_active(ptdesc_folio(ptdesc))) + call_rcu(&ptdesc->pt_rcu_head, pte_free_now); + else + pte_free_now(&ptdesc->pt_rcu_head); } void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table, unsigned long vmaddr) { struct mm_struct *mm; - struct page *page; unsigned int bit, mask; + struct ptdesc *ptdesc = virt_to_ptdesc(table); mm = tlb->mm; - page = virt_to_page(table); if (mm_alloc_pgste(mm)) { gmap_unlink(mm, table, vmaddr); table = (unsigned long *) ((unsigned long)table | 0x03U); - tlb_remove_table(tlb, table); + tlb_remove_ptdesc(tlb, table); return; } bit = ((unsigned long) table & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)); @@ -368,12 +396,20 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table, * outside of the critical section from __tlb_remove_table() or from * page_table_free() */ - mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24)); + mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24)); mask >>= 24; - if (mask & 0x03U) - list_add_tail(&page->lru, &mm->context.pgtable_list); - else - list_del(&page->lru); + if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) { + /* + * Other half is allocated, and neither half has had + * its free deferred: add page to end of list, to make + * this freed half available for reuse once its pending + * bit has been cleared by __tlb_remove_table(). + */ + list_add_tail(&ptdesc->pt_list, &mm->context.pgtable_list); + } else { + /* If page is on list, now remove it. */ + list_del_init(&ptdesc->pt_list); + } spin_unlock_bh(&mm->context.lock); table = (unsigned long *) ((unsigned long) table | (0x01U << bit)); tlb_remove_table(tlb, table); @@ -383,30 +419,48 @@ void __tlb_remove_table(void *_table) { unsigned int mask = (unsigned long) _table & 0x03U, half = mask; void *table = (void *)((unsigned long) _table ^ mask); - struct page *page = virt_to_page(table); + struct ptdesc *ptdesc = virt_to_ptdesc(table); switch (half) { case 0x00U: /* pmd, pud, or p4d */ - free_pages((unsigned long)table, CRST_ALLOC_ORDER); + pagetable_free(ptdesc); return; case 0x01U: /* lower 2K of a 4K page table */ case 0x02U: /* higher 2K of a 4K page table */ - mask = atomic_xor_bits(&page->_refcount, mask << (4 + 24)); + mask = atomic_xor_bits(&ptdesc->_refcount, mask << (4 + 24)); mask >>= 24; if (mask != 0x00U) return; break; case 0x03U: /* 4K page table with pgstes */ - mask = atomic_xor_bits(&page->_refcount, 0x03U << 24); + mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); mask >>= 24; break; } - page_table_release_check(page, table, half, mask); - pgtable_pte_page_dtor(page); - __free_page(page); + page_table_release_check(ptdesc_page(ptdesc), table, half, mask); + if (folio_test_clear_active(ptdesc_folio(ptdesc))) + call_rcu(&ptdesc->pt_rcu_head, pte_free_now); + else + pte_free_now(&ptdesc->pt_rcu_head); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) +{ + struct page *page; + + page = virt_to_page(pgtable); + SetPageActive(page); + page_table_free(mm, (unsigned long *)pgtable); + /* + * page_table_free() does not do the pgste gmap_unlink() which + * page_table_free_rcu() does: warn us if pgste ever reaches here. + */ + WARN_ON_ONCE(mm_has_pgste(mm)); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + /* * Base infrastructure required to generate basic asces, region, segment, * and page tables that do not make use of enhanced features like EDAT1. @@ -432,16 +486,20 @@ static void base_pgt_free(unsigned long *table) static unsigned long *base_crst_alloc(unsigned long val) { unsigned long *table; + struct ptdesc *ptdesc; - table = (unsigned long *)__get_free_pages(GFP_KERNEL, CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, CRST_ALLOC_ORDER); + if (!ptdesc) + return NULL; + table = ptdesc_address(ptdesc); + + crst_table_init(table, val); return table; } static void base_crst_free(unsigned long *table) { - free_pages((unsigned long)table, CRST_ALLOC_ORDER); + pagetable_free(virt_to_ptdesc(table)); } #define BASE_ADDR_END_FUNC(NAME, SIZE) \ diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index afc3f33788da..d34d5813d006 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -244,62 +244,25 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) zpci_memcpy_toio(to, from, count); } -static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { - unsigned long offset, vaddr; - struct vm_struct *area; - phys_addr_t last_addr; - - last_addr = addr + size - 1; - if (!size || last_addr < addr) - return NULL; - + /* + * When PCI MIO instructions are unavailable the "physical" address + * encodes a hint for accessing the PCI memory space it represents. + * Just pass it unchanged such that ioread/iowrite can decode it. + */ if (!static_branch_unlikely(&have_mio)) - return (void __iomem *) addr; + return (void __iomem *)phys_addr; - offset = addr & ~PAGE_MASK; - addr &= PAGE_MASK; - size = PAGE_ALIGN(size + offset); - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - - vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) { - free_vm_area(area); - return NULL; - } - return (void __iomem *) ((unsigned long) area->addr + offset); -} - -void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) -{ - return __ioremap(addr, size, __pgprot(prot)); + return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); } EXPORT_SYMBOL(ioremap_prot); -void __iomem *ioremap(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, PAGE_KERNEL); -} -EXPORT_SYMBOL(ioremap); - -void __iomem *ioremap_wc(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL)); -} -EXPORT_SYMBOL(ioremap_wc); - -void __iomem *ioremap_wt(phys_addr_t addr, size_t size) -{ - return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL)); -} -EXPORT_SYMBOL(ioremap_wt); - void iounmap(volatile void __iomem *addr) { if (static_branch_likely(&have_mio)) - vunmap((__force void *) ((unsigned long) addr & PAGE_MASK)); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 2b3ce4fd3956..6be32254211c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -29,6 +29,7 @@ config SUPERH select GENERIC_SMP_IDLE_THREAD select GUP_GET_PXX_LOW_HIGH if X2TLB select HAS_IOPORT if HAS_IOPORT_MAP + select GENERIC_IOREMAP if MMU select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index d8f3537ef57f..f2f38e9d489a 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -119,6 +119,30 @@ void __raw_readsl(const void __iomem *addr, void *data, int longlen); __BUILD_MEMORY_STRING(__raw_, q, u64) +#define ioport_map ioport_map +#define ioport_unmap ioport_unmap +#define pci_iounmap pci_iounmap + +#define ioread8 ioread8 +#define ioread16 ioread16 +#define ioread16be ioread16be +#define ioread32 ioread32 +#define ioread32be ioread32be + +#define iowrite8 iowrite8 +#define iowrite16 iowrite16 +#define iowrite16be iowrite16be +#define iowrite32 iowrite32 +#define iowrite32be iowrite32be + +#define ioread8_rep ioread8_rep +#define ioread16_rep ioread16_rep +#define ioread32_rep ioread32_rep + +#define iowrite8_rep iowrite8_rep +#define iowrite16_rep iowrite16_rep +#define iowrite32_rep iowrite32_rep + #ifdef CONFIG_HAS_IOPORT_MAP /* @@ -221,10 +245,33 @@ __BUILD_IOPORT_STRING(q, u64) #endif +#define inb(addr) inb(addr) +#define inw(addr) inw(addr) +#define inl(addr) inl(addr) +#define outb(x, addr) outb((x), (addr)) +#define outw(x, addr) outw((x), (addr)) +#define outl(x, addr) outl((x), (addr)) + +#define inb_p(addr) inb(addr) +#define inw_p(addr) inw(addr) +#define inl_p(addr) inl(addr) +#define outb_p(x, addr) outb((x), (addr)) +#define outw_p(x, addr) outw((x), (addr)) +#define outl_p(x, addr) outl((x), (addr)) + +#define insb insb +#define insw insw +#define insl insl +#define outsb outsb +#define outsw outsw +#define outsl outsl #define IO_SPACE_LIMIT 0xffffffff /* We really want to try and get these to memcpy etc */ +#define memset_io memset_io +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio void memcpy_fromio(void *, const volatile void __iomem *, unsigned long); void memcpy_toio(volatile void __iomem *, const void *, unsigned long); void memset_io(volatile void __iomem *, int, unsigned long); @@ -243,40 +290,16 @@ unsigned long long poke_real_address_q(unsigned long long addr, #endif #ifdef CONFIG_MMU -void iounmap(void __iomem *addr); -void __iomem *__ioremap_caller(phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller); - -static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size) -{ - return __ioremap_caller(offset, size, PAGE_KERNEL_NOCACHE, - __builtin_return_address(0)); -} - -static inline void __iomem * -ioremap_cache(phys_addr_t offset, unsigned long size) -{ - return __ioremap_caller(offset, size, PAGE_KERNEL, - __builtin_return_address(0)); -} -#define ioremap_cache ioremap_cache - -#ifdef CONFIG_HAVE_IOREMAP_PROT -static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, - unsigned long flags) -{ - return __ioremap_caller(offset, size, __pgprot(flags), - __builtin_return_address(0)); -} -#endif /* CONFIG_HAVE_IOREMAP_PROT */ +/* + * I/O memory mapping functions. + */ +#define ioremap_prot ioremap_prot +#define iounmap iounmap -#else /* CONFIG_MMU */ -static inline void __iomem *ioremap(phys_addr_t offset, size_t size) -{ - return (void __iomem *)(unsigned long)offset; -} +#define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_NOCACHE) -static inline void iounmap(volatile void __iomem *addr) { } +#define ioremap_cache(addr, size) \ + ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) #endif /* CONFIG_MMU */ #define ioremap_uc ioremap @@ -288,6 +311,8 @@ static inline void iounmap(volatile void __iomem *addr) { } #define xlate_dev_mem_ptr(p) __va(p) #define unxlate_dev_mem_ptr(p, v) do { } while (0) +#include <asm-generic/io.h> + #define ARCH_HAS_VALID_PHYS_ADDR_RANGE int valid_phys_addr_range(phys_addr_t addr, size_t size); int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); diff --git a/arch/sh/include/asm/io_noioport.h b/arch/sh/include/asm/io_noioport.h index f7938fe0f911..12dad91f41c1 100644 --- a/arch/sh/include/asm/io_noioport.h +++ b/arch/sh/include/asm/io_noioport.h @@ -46,13 +46,6 @@ static inline void ioport_unmap(void __iomem *addr) BUG(); } -#define inb_p(addr) inb(addr) -#define inw_p(addr) inw(addr) -#define inl_p(addr) inl(addr) -#define outb_p(x, addr) outb((x), (addr)) -#define outw_p(x, addr) outw((x), (addr)) -#define outl_p(x, addr) outl((x), (addr)) - static inline void insb(unsigned long port, void *dst, unsigned long count) { BUG(); diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index a9e98233c4d4..5d8577ab1591 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -2,6 +2,7 @@ #ifndef __ASM_SH_PGALLOC_H #define __ASM_SH_PGALLOC_H +#include <linux/mm.h> #include <asm/page.h> #define __HAVE_ARCH_PMD_ALLOC_ONE @@ -31,10 +32,10 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, set_pmd(pmd, __pmd((unsigned long)page_address(pte))); } -#define __pte_free_tlb(tlb,pte,addr) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), (pte)); \ +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #endif /* __ASM_SH_PGALLOC_H */ diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index 21342581144d..c33b3daa4ad1 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -72,22 +72,11 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) #define __ioremap_29bit(offset, size, prot) NULL #endif /* CONFIG_29BIT */ -/* - * Remap an arbitrary physical address space into the kernel virtual - * address space. Needed when the kernel wants to access high addresses - * directly. - * - * NOTE! We need to allow non-page-aligned mappings too: we will obviously - * have to convert them into an offset in a page-aligned mapping, but the - * caller shouldn't need to know that small detail. - */ -void __iomem * __ref -__ioremap_caller(phys_addr_t phys_addr, unsigned long size, - pgprot_t pgprot, void *caller) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { - struct vm_struct *area; - unsigned long offset, last_addr, addr, orig_addr; void __iomem *mapped; + pgprot_t pgprot = __pgprot(prot); mapped = __ioremap_trapped(phys_addr, size); if (mapped) @@ -97,11 +86,6 @@ __ioremap_caller(phys_addr_t phys_addr, unsigned long size, if (mapped) return mapped; - /* Don't allow wraparound or zero size */ - last_addr = phys_addr + size - 1; - if (!size || last_addr < phys_addr) - return NULL; - /* * If we can't yet use the regular approach, go the fixmap route. */ @@ -112,34 +96,14 @@ __ioremap_caller(phys_addr_t phys_addr, unsigned long size, * First try to remap through the PMB. * PMB entries are all pre-faulted. */ - mapped = pmb_remap_caller(phys_addr, size, pgprot, caller); + mapped = pmb_remap_caller(phys_addr, size, pgprot, + __builtin_return_address(0)); if (mapped && !IS_ERR(mapped)) return mapped; - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr+1) - phys_addr; - - /* - * Ok, go for it.. - */ - area = get_vm_area_caller(size, VM_IOREMAP, caller); - if (!area) - return NULL; - area->phys_addr = phys_addr; - orig_addr = addr = (unsigned long)area->addr; - - if (ioremap_page_range(addr, addr + size, phys_addr, pgprot)) { - vunmap((void *)orig_addr); - return NULL; - } - - return (void __iomem *)(offset + (char *)orig_addr); + return generic_ioremap_prot(phys_addr, size, pgprot); } -EXPORT_SYMBOL(__ioremap_caller); +EXPORT_SYMBOL(ioremap_prot); /* * Simple checks for non-translatable mappings. @@ -158,10 +122,9 @@ static inline int iomapping_nontranslatable(unsigned long offset) return 0; } -void iounmap(void __iomem *addr) +void iounmap(volatile void __iomem *addr) { unsigned long vaddr = (unsigned long __force)addr; - struct vm_struct *p; /* * Nothing to do if there is no translatable mapping. @@ -172,21 +135,15 @@ void iounmap(void __iomem *addr) /* * There's no VMA if it's from an early fixed mapping. */ - if (iounmap_fixed(addr) == 0) + if (iounmap_fixed((void __iomem *)addr) == 0) return; /* * If the PMB handled it, there's nothing else to do. */ - if (pmb_unmap(addr) == 0) + if (pmb_unmap((void __iomem *)addr) == 0) return; - p = remove_vm_area((void *)(vaddr & PAGE_MASK)); - if (!p) { - printk(KERN_ERR "%s: bad address %p\n", __func__, addr); - return; - } - - kfree(p); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index 7b5561d17ab1..caa7632be4c2 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -65,6 +65,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm); void pte_free_kernel(struct mm_struct *mm, pte_t *pte); void pte_free(struct mm_struct *mm, pgtable_t ptepage); +/* arch use pte_free_defer() implementation in arch/sparc/mm/init_64.c */ +#define pte_free_defer pte_free_defer +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + #define pmd_populate_kernel(MM, PMD, PTE) pmd_set(MM, PMD, PTE) #define pmd_populate(MM, PMD, PTE) pmd_set(MM, PMD, PTE) diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index 1adf5c1c16b8..34ef7febf0d5 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -83,7 +83,7 @@ static void prom_sync_me(void) "nop\n\t" : : "r" (&trapbase)); prom_printf("PROM SYNC COMMAND...\n"); - show_free_areas(0, NULL); + show_mem(); if (!is_idle_task(current)) { local_irq_enable(); ksys_sync(); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 04f9db0c3111..9a63a3e08e40 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2893,14 +2893,15 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm) pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL | __GFP_ZERO, 0); + + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - return (pte_t *) page_address(page); + return ptdesc_address(ptdesc); } void pte_free_kernel(struct mm_struct *mm, pte_t *pte) @@ -2910,10 +2911,10 @@ void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static void __pte_free(pgtable_t pte) { - struct page *page = virt_to_page(pte); + struct ptdesc *ptdesc = virt_to_ptdesc(pte); - pgtable_pte_page_dtor(page); - __free_page(page); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -2930,6 +2931,22 @@ void pgtable_free(void *table, bool is_page) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pte_free_now(struct rcu_head *head) +{ + struct page *page; + + page = container_of(head, struct page, rcu_head); + __pte_free((pgtable_t)page_address(page)); +} + +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) +{ + struct page *page; + + page = virt_to_page(pgtable); + call_rcu(&page->rcu_head, pte_free_now); +} + void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 13f027afc875..8393faa3e596 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -355,7 +355,8 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) return NULL; page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); - if (page_ref_inc_return(page) == 2 && !pgtable_pte_page_ctor(page)) { + if (page_ref_inc_return(page) == 2 && + !pagetable_pte_ctor(page_ptdesc(page))) { page_ref_dec(page); ptep = NULL; } @@ -371,7 +372,7 @@ void pte_free(struct mm_struct *mm, pgtable_t ptep) page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); if (page_ref_dec_return(page) == 1) - pgtable_pte_page_dtor(page); + pagetable_pte_dtor(page_ptdesc(page)); spin_unlock(&mm->page_table_lock); srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE); diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 8ec7cd46dd96..de5e31c64793 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -25,19 +25,19 @@ */ extern pgd_t *pgd_alloc(struct mm_struct *); -#define __pte_free_tlb(tlb,pte, address) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb),(pte)); \ +#define __pte_free_tlb(tlb, pte, address) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES -#define __pmd_free_tlb(tlb, pmd, address) \ -do { \ - pgtable_pmd_page_dtor(virt_to_page(pmd)); \ - tlb_remove_page((tlb),virt_to_page(pmd)); \ -} while (0) \ +#define __pmd_free_tlb(tlb, pmd, address) \ +do { \ + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \ +} while (0) #endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7422db409770..d0258e92a8af 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -102,6 +102,7 @@ config X86 select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO @@ -128,7 +129,8 @@ config X86 select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANT_OPTIMIZE_VMEMMAP if X86_64 + select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 select ARCH_WANTS_THP_SWAP if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT @@ -2609,9 +2611,6 @@ config ARCH_HAS_ADD_PAGES def_bool y depends on ARCH_ENABLE_MEMORY_HOTPLUG -config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE - def_bool y - menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e9025640f634..76238842406a 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -35,9 +35,6 @@ * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ -#define ARCH_HAS_IOREMAP_WC -#define ARCH_HAS_IOREMAP_WT - #include <linux/string.h> #include <linux/compiler.h> #include <linux/cc_platform.h> @@ -212,8 +209,6 @@ void memset_io(volatile void __iomem *, int, size_t); #define memcpy_toio memcpy_toio #define memset_io memset_io -#include <asm-generic/iomap.h> - /* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5700bb337987..ada1bbf12961 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1023,21 +1023,21 @@ static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - page_table_check_pte_set(mm, addr, ptep, pte); + page_table_check_pte_set(mm, ptep, pte); set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); + page_table_check_pmd_set(mm, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); + page_table_check_pud_set(mm, pudp, pud); native_set_pud(pudp, pud); } @@ -1068,7 +1068,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); - page_table_check_pte_clear(mm, addr, pte); + page_table_check_pte_clear(mm, pte); return pte; } @@ -1084,7 +1084,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); - page_table_check_pte_clear(mm, addr, pte); + page_table_check_pte_clear(mm, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } @@ -1133,7 +1133,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long { pmd_t pmd = native_pmdp_get_and_clear(pmdp); - page_table_check_pmd_clear(mm, addr, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -1144,7 +1144,7 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, { pud_t pud = native_pudp_get_and_clear(pudp); - page_table_check_pud_clear(mm, addr, pud); + page_table_check_pud_clear(mm, pud); return pud; } @@ -1167,7 +1167,7 @@ static inline int pud_write(pud_t pud) static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 80450e1d5385..6ab42caaa67a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -3,6 +3,7 @@ #define _ASM_X86_TLBFLUSH_H #include <linux/mm_types.h> +#include <linux/mmu_notifier.h> #include <linux/sched.h> #include <asm/processor.h> @@ -253,6 +254,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false); } +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ + bool should_defer = false; + + /* If remote CPUs need to be flushed then defer batch the flush */ + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) + should_defer = true; + put_cpu(); + + return should_defer; +} + static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) { /* @@ -264,11 +277,18 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) return atomic64_inc_return(&mm->context.tlb_gen); } -static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm) +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, + unsigned long uaddr) { inc_mm_tlb_gen(mm); cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); +} + +static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) +{ + flush_tlb_mm(mm); } extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e8711b2cafaf..787da09d24f3 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1328,7 +1328,6 @@ void do_user_addr_fault(struct pt_regs *regs, } #endif -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -1358,7 +1357,6 @@ void do_user_addr_fault(struct pt_regs *regs, return; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ retry: vma = lock_mm_and_find_vma(mm, address, regs); @@ -1418,9 +1416,7 @@ retry: } mmap_read_unlock(mm); -#ifdef CONFIG_PER_VMA_LOCK done: -#endif if (likely(!(fault & VM_FAULT_ERROR))) return; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 15a8009a4480..d3a93e8766ee 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -52,7 +52,7 @@ early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { - pgtable_pte_page_dtor(pte); + pagetable_pte_dtor(page_ptdesc(pte)); paravirt_release_pte(page_to_pfn(pte)); paravirt_tlb_remove_table(tlb, pte); } @@ -60,7 +60,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { - struct page *page = virt_to_page(pmd); + struct ptdesc *ptdesc = virt_to_ptdesc(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table @@ -69,8 +69,8 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif - pgtable_pmd_page_dtor(page); - paravirt_tlb_remove_table(tlb, page); + pagetable_pmd_dtor(ptdesc); + paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc)); } #if CONFIG_PGTABLE_LEVELS > 3 @@ -92,16 +92,16 @@ void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) static inline void pgd_list_add(pgd_t *pgd) { - struct page *page = virt_to_page(pgd); + struct ptdesc *ptdesc = virt_to_ptdesc(pgd); - list_add(&page->lru, &pgd_list); + list_add(&ptdesc->pt_list, &pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { - struct page *page = virt_to_page(pgd); + struct ptdesc *ptdesc = virt_to_ptdesc(pgd); - list_del(&page->lru); + list_del(&ptdesc->pt_list); } #define UNSHARED_PTRS_PER_PGD \ @@ -112,12 +112,12 @@ static inline void pgd_list_del(pgd_t *pgd) static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { - virt_to_page(pgd)->pt_mm = mm; + virt_to_ptdesc(pgd)->pt_mm = mm; } struct mm_struct *pgd_page_get_mm(struct page *page) { - return page->pt_mm; + return page_ptdesc(page)->pt_mm; } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) @@ -213,11 +213,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; + struct ptdesc *ptdesc; for (i = 0; i < count; i++) if (pmds[i]) { - pgtable_pmd_page_dtor(virt_to_page(pmds[i])); - free_page((unsigned long)pmds[i]); + ptdesc = virt_to_ptdesc(pmds[i]); + + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } } @@ -230,18 +233,24 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; + gfp &= ~__GFP_HIGHMEM; for (i = 0; i < count; i++) { - pmd_t *pmd = (pmd_t *)__get_free_page(gfp); - if (!pmd) + pmd_t *pmd = NULL; + struct ptdesc *ptdesc = pagetable_alloc(gfp, 0); + + if (!ptdesc) failed = true; - if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { - free_page((unsigned long)pmd); - pmd = NULL; + if (ptdesc && !pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); + ptdesc = NULL; failed = true; } - if (pmd) + if (ptdesc) { mm_inc_nr_pmds(mm); + pmd = ptdesc_address(ptdesc); + } + pmds[i] = pmd; } @@ -830,7 +839,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) free_page((unsigned long)pmd_sv); - pgtable_pmd_page_dtor(virt_to_page(pmd)); + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 267acf27480a..2d253919b3e8 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -10,6 +10,7 @@ #include <linux/debugfs.h> #include <linux/sched/smt.h> #include <linux/task_work.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -1036,6 +1037,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, put_flush_tlb_info(); put_cpu(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index e0a975165de7..8796ec310483 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -667,7 +667,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) spinlock_t *ptl = NULL; #if USE_SPLIT_PTE_PTLOCKS - ptl = ptlock_ptr(page); + ptl = ptlock_ptr(page_ptdesc(page)); spin_lock_nest_lock(ptl, &mm->page_table_lock); #endif diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 2a51a466779f..a5488cc40f58 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -28,6 +28,7 @@ config XTENSA select GENERIC_LIB_UCMPDI2 select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK + select GENERIC_IOREMAP if MMU select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index a5b707e1c0f4..934e58399c8c 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -16,6 +16,7 @@ #include <asm/vectors.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/pgtable.h> #include <linux/types.h> @@ -24,22 +25,24 @@ #define PCI_IOBASE ((void __iomem *)XCHAL_KIO_BYPASS_VADDR) #ifdef CONFIG_MMU - -void __iomem *xtensa_ioremap_nocache(unsigned long addr, unsigned long size); -void __iomem *xtensa_ioremap_cache(unsigned long addr, unsigned long size); -void xtensa_iounmap(volatile void __iomem *addr); - /* - * Return the virtual address for the specified bus memory. + * I/O memory mapping functions. */ +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot); +#define ioremap_prot ioremap_prot +#define iounmap iounmap + static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { if (offset >= XCHAL_KIO_PADDR && offset - XCHAL_KIO_PADDR < XCHAL_KIO_SIZE) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_BYPASS_VADDR); else - return xtensa_ioremap_nocache(offset, size); + return ioremap_prot(offset, size, + pgprot_val(pgprot_noncached(PAGE_KERNEL))); } +#define ioremap ioremap static inline void __iomem *ioremap_cache(unsigned long offset, unsigned long size) @@ -48,21 +51,10 @@ static inline void __iomem *ioremap_cache(unsigned long offset, && offset - XCHAL_KIO_PADDR < XCHAL_KIO_SIZE) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_CACHED_VADDR); else - return xtensa_ioremap_cache(offset, size); -} -#define ioremap_cache ioremap_cache + return ioremap_prot(offset, size, pgprot_val(PAGE_KERNEL)); -static inline void iounmap(volatile void __iomem *addr) -{ - unsigned long va = (unsigned long) addr; - - if (!(va >= XCHAL_KIO_CACHED_VADDR && - va - XCHAL_KIO_CACHED_VADDR < XCHAL_KIO_SIZE) && - !(va >= XCHAL_KIO_BYPASS_VADDR && - va - XCHAL_KIO_BYPASS_VADDR < XCHAL_KIO_SIZE)) - xtensa_iounmap(addr); } - +#define ioremap_cache ioremap_cache #endif /* CONFIG_MMU */ #include <asm-generic/io.h> diff --git a/arch/xtensa/mm/ioremap.c b/arch/xtensa/mm/ioremap.c index a400188c16b9..8ca660b7ab49 100644 --- a/arch/xtensa/mm/ioremap.c +++ b/arch/xtensa/mm/ioremap.c @@ -6,60 +6,30 @@ */ #include <linux/io.h> -#include <linux/vmalloc.h> #include <linux/pgtable.h> #include <asm/cacheflush.h> #include <asm/io.h> -static void __iomem *xtensa_ioremap(unsigned long paddr, unsigned long size, - pgprot_t prot) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { - unsigned long offset = paddr & ~PAGE_MASK; - unsigned long pfn = __phys_to_pfn(paddr); - struct vm_struct *area; - unsigned long vaddr; - int err; - - paddr &= PAGE_MASK; - + unsigned long pfn = __phys_to_pfn((phys_addr)); WARN_ON(pfn_valid(pfn)); - size = PAGE_ALIGN(offset + size); - - area = get_vm_area(size, VM_IOREMAP); - if (!area) - return NULL; - - vaddr = (unsigned long)area->addr; - area->phys_addr = paddr; - - err = ioremap_page_range(vaddr, vaddr + size, paddr, prot); - - if (err) { - vunmap((void *)vaddr); - return NULL; - } - - flush_cache_vmap(vaddr, vaddr + size); - return (void __iomem *)(offset + vaddr); -} - -void __iomem *xtensa_ioremap_nocache(unsigned long addr, unsigned long size) -{ - return xtensa_ioremap(addr, size, pgprot_noncached(PAGE_KERNEL)); + return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); } -EXPORT_SYMBOL(xtensa_ioremap_nocache); +EXPORT_SYMBOL(ioremap_prot); -void __iomem *xtensa_ioremap_cache(unsigned long addr, unsigned long size) +void iounmap(volatile void __iomem *addr) { - return xtensa_ioremap(addr, size, PAGE_KERNEL); -} -EXPORT_SYMBOL(xtensa_ioremap_cache); + unsigned long va = (unsigned long) addr; -void xtensa_iounmap(volatile void __iomem *io_addr) -{ - void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); + if ((va >= XCHAL_KIO_CACHED_VADDR && + va - XCHAL_KIO_CACHED_VADDR < XCHAL_KIO_SIZE) || + (va >= XCHAL_KIO_BYPASS_VADDR && + va - XCHAL_KIO_BYPASS_VADDR < XCHAL_KIO_SIZE)) + return; - vunmap(addr); + generic_iounmap(addr); } -EXPORT_SYMBOL(xtensa_iounmap); +EXPORT_SYMBOL(iounmap); |