From: Nicholas Piggin <npiggin@xxxxxxxxx> Subject: mm/vmalloc: remove unmap_kernel_range This is a shim around vunmap_range, get rid of it. Move the main API comment from the _noflush variant to the normal variant, and make _noflush internal to mm/. [npiggin@xxxxxxxxx: fix nommu builds and a comment bug per sfr] Link: https://lkml.kernel.org/r/1617292598.m6g0knx24s.astroid@xxxxxxxxx [akpm@xxxxxxxxxxxxxxxxxxxx: move vunmap_range_noflush() stub inside !CONFIG_MMU, not !CONFIG_NUMA] [npiggin@xxxxxxxxx: fix nommu builds] Link: https://lkml.kernel.org/r/1617292497.o1uhq5ipxp.astroid@xxxxxxxxx Link: https://lkml.kernel.org/r/20210322021806.892164-5-npiggin@xxxxxxxxx Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx> Reviewed-by: Christoph Hellwig <hch@xxxxxx> Cc: Cédric Le Goater <clg@xxxxxxxx> Cc: Uladzislau Rezki <urezki@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/core-api/cachetlb.rst | 2 arch/arm64/mm/init.c | 2 arch/powerpc/kernel/isa-bridge.c | 4 - arch/powerpc/kernel/pci_64.c | 2 arch/powerpc/mm/ioremap.c | 2 drivers/pci/pci.c | 2 include/linux/vmalloc.h | 8 --- mm/internal.h | 15 ++++++ mm/percpu-vm.c | 2 mm/vmalloc.c | 59 ++++++++++++-------------- 10 files changed, 51 insertions(+), 47 deletions(-) --- a/arch/arm64/mm/init.c~mm-vmalloc-remove-unmap_kernel_range +++ a/arch/arm64/mm/init.c @@ -521,7 +521,7 @@ void free_initmem(void) * prevents the region from being reused for kernel modules, which * is not supported by kallsyms. */ - unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); + vunmap_range((u64)__init_begin, (u64)__init_end); } void dump_mem_limit(void) --- a/arch/powerpc/kernel/isa-bridge.c~mm-vmalloc-remove-unmap_kernel_range +++ a/arch/powerpc/kernel/isa-bridge.c @@ -48,7 +48,7 @@ static void remap_isa_base(phys_addr_t p if (slab_is_available()) { if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa, pgprot_noncached(PAGE_KERNEL))) - unmap_kernel_range(ISA_IO_BASE, size); + vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size); } else { early_ioremap_range(ISA_IO_BASE, pa, size, pgprot_noncached(PAGE_KERNEL)); @@ -311,7 +311,7 @@ static void isa_bridge_remove(void) isa_bridge_pcidev = NULL; /* Unmap the ISA area */ - unmap_kernel_range(ISA_IO_BASE, 0x10000); + vunmap_range(ISA_IO_BASE, ISA_IO_BASE + 0x10000); } /** --- a/arch/powerpc/kernel/pci_64.c~mm-vmalloc-remove-unmap_kernel_range +++ a/arch/powerpc/kernel/pci_64.c @@ -140,7 +140,7 @@ void __iomem *ioremap_phb(phys_addr_t pa addr = (unsigned long)area->addr; if (ioremap_page_range(addr, addr + size, paddr, pgprot_noncached(PAGE_KERNEL))) { - unmap_kernel_range(addr, size); + vunmap_range(addr, addr + size); return NULL; } --- a/arch/powerpc/mm/ioremap.c~mm-vmalloc-remove-unmap_kernel_range +++ a/arch/powerpc/mm/ioremap.c @@ -93,7 +93,7 @@ void __iomem *do_ioremap(phys_addr_t pa, if (!ret) return (void __iomem *)area->addr + offset; - unmap_kernel_range(va, size); + vunmap_range(va, va + size); free_vm_area(area); return NULL; --- a/Documentation/core-api/cachetlb.rst~mm-vmalloc-remove-unmap_kernel_range +++ a/Documentation/core-api/cachetlb.rst @@ -215,7 +215,7 @@ Here are the routines, one by one: The first of these two routines is invoked after vmap_range() has installed the page table entries. The second is invoked - before unmap_kernel_range() deletes the page table entries. + before vunmap_range() deletes the page table entries. There exists another whole class of cpu cache issues which currently require a whole different set of interfaces to handle properly. --- a/drivers/pci/pci.c~mm-vmalloc-remove-unmap_kernel_range +++ a/drivers/pci/pci.c @@ -4102,7 +4102,7 @@ void pci_unmap_iospace(struct resource * #if defined(PCI_IOBASE) && defined(CONFIG_MMU) unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start; - unmap_kernel_range(vaddr, resource_size(res)); + vunmap_range(vaddr, vaddr + resource_size(res)); #endif } EXPORT_SYMBOL(pci_unmap_iospace); --- a/include/linux/vmalloc.h~mm-vmalloc-remove-unmap_kernel_range +++ a/include/linux/vmalloc.h @@ -212,8 +212,7 @@ static inline bool is_vm_area_hugepages( int vmap_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift); -extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); -extern void unmap_kernel_range(unsigned long addr, unsigned long size); +void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); @@ -223,11 +222,6 @@ static inline void set_vm_flush_reset_pe } #else -static inline void -unmap_kernel_range_noflush(unsigned long addr, unsigned long size) -{ -} -#define unmap_kernel_range unmap_kernel_range_noflush static inline void set_vm_flush_reset_perms(void *addr) { } --- a/mm/internal.h~mm-vmalloc-remove-unmap_kernel_range +++ a/mm/internal.h @@ -446,7 +446,9 @@ static inline struct file *maybe_unlock_ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } - +static inline void vunmap_range_noflush(unsigned long start, unsigned long end) +{ +} #endif /* !CONFIG_MMU */ /* @@ -640,7 +642,18 @@ struct migration_target_control { /* * mm/vmalloc.c */ +#ifdef CONFIG_MMU int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); +#else +static inline +int vmap_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift) +{ + return -EINVAL; +} +#endif + +void vunmap_range_noflush(unsigned long start, unsigned long end); #endif /* __MM_INTERNAL_H */ --- a/mm/percpu-vm.c~mm-vmalloc-remove-unmap_kernel_range +++ a/mm/percpu-vm.c @@ -134,7 +134,7 @@ static void pcpu_pre_unmap_flush(struct static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { - unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); + vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** --- a/mm/vmalloc.c~mm-vmalloc-remove-unmap_kernel_range +++ a/mm/vmalloc.c @@ -378,22 +378,20 @@ static void vunmap_p4d_range(pgd_t *pgd, } while (p4d++, addr = next, addr != end); } -/** - * unmap_kernel_range_noflush - unmap kernel VM area - * @start: start of the VM area to unmap - * @size: size of the VM area to unmap +/* + * vunmap_range_noflush is similar to vunmap_range, but does not + * flush caches or TLBs. * - * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify - * should have been allocated using get_vm_area() and its friends. + * The caller is responsible for calling flush_cache_vmap() before calling + * this function, and flush_tlb_kernel_range after it has returned + * successfully (and before the addresses are expected to cause a page fault + * or be re-mapped for something else, if TLB flushes are being delayed or + * coalesced). * - * NOTE: - * This function does NOT do any cache flushing. The caller is responsible - * for calling flush_cache_vunmap() on to-be-mapped areas before calling this - * function and flush_tlb_kernel_range() after. + * This is an internal function only. Do not use outside mm/. */ -void unmap_kernel_range_noflush(unsigned long start, unsigned long size) +void vunmap_range_noflush(unsigned long start, unsigned long end) { - unsigned long end = start + size; unsigned long next; pgd_t *pgd; unsigned long addr = start; @@ -414,6 +412,22 @@ void unmap_kernel_range_noflush(unsigned arch_sync_kernel_mappings(start, end); } +/** + * vunmap_range - unmap kernel virtual addresses + * @addr: start of the VM area to unmap + * @end: end of the VM area to unmap (non-inclusive) + * + * Clears any present PTEs in the virtual address range, flushes TLBs and + * caches. Any subsequent access to the address before it has been re-mapped + * is a kernel bug. + */ +void vunmap_range(unsigned long addr, unsigned long end) +{ + flush_cache_vunmap(addr, end); + vunmap_range_noflush(addr, end); + flush_tlb_kernel_range(addr, end); +} + static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) @@ -1712,7 +1726,7 @@ static void free_vmap_area_noflush(struc static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); - unmap_kernel_range_noflush(va->va_start, va->va_end - va->va_start); + vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); @@ -1990,7 +2004,7 @@ static void vb_free(unsigned long addr, offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; vb = xa_load(&vmap_blocks, addr_to_vb_idx(addr)); - unmap_kernel_range_noflush(addr, size); + vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); @@ -2307,23 +2321,6 @@ void __init vmalloc_init(void) vmap_initialized = true; } -/** - * unmap_kernel_range - unmap kernel VM area and flush cache and TLB - * @addr: start of the VM area to unmap - * @size: size of the VM area to unmap - * - * Similar to unmap_kernel_range_noflush() but flushes vcache before - * the unmapping and tlb after. - */ -void unmap_kernel_range(unsigned long addr, unsigned long size) -{ - unsigned long end = addr + size; - - flush_cache_vunmap(addr, end); - unmap_kernel_range_noflush(addr, size); - flush_tlb_kernel_range(addr, end); -} - static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { _
