diff options
Diffstat (limited to 'mm/vmalloc.c')
-rw-r--r-- | mm/vmalloc.c | 145 |
1 files changed, 113 insertions, 32 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e86ba6e74b50..67bbb8d2a0a8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -18,6 +18,7 @@ #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> @@ -632,7 +633,7 @@ static unsigned long lazy_max_pages(void) return log * (32UL * 1024 * 1024 / PAGE_SIZE); } -static atomic_t vmap_lazy_nr = ATOMIC_INIT(0); +static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual criticial section protected @@ -650,7 +651,7 @@ static void purge_fragmented_blocks_allcpus(void); */ void set_iounmap_nonlazy(void) { - atomic_set(&vmap_lazy_nr, lazy_max_pages()+1); + atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); } /* @@ -658,34 +659,40 @@ void set_iounmap_nonlazy(void) */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) { + unsigned long resched_threshold; struct llist_node *valist; struct vmap_area *va; struct vmap_area *n_va; - bool do_free = false; lockdep_assert_held(&vmap_purge_lock); valist = llist_del_all(&vmap_purge_list); + if (unlikely(valist == NULL)) + return false; + + /* + * TODO: to calculate a flush range without looping. + * The list can be up to lazy_max_pages() elements. + */ llist_for_each_entry(va, valist, purge_list) { if (va->va_start < start) start = va->va_start; if (va->va_end > end) end = va->va_end; - do_free = true; } - if (!do_free) - return false; - flush_tlb_kernel_range(start, end); + resched_threshold = lazy_max_pages() << 1; spin_lock(&vmap_area_lock); llist_for_each_entry_safe(va, n_va, valist, purge_list) { - int nr = (va->va_end - va->va_start) >> PAGE_SHIFT; + unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; __free_vmap_area(va); - atomic_sub(nr, &vmap_lazy_nr); - cond_resched_lock(&vmap_area_lock); + atomic_long_sub(nr, &vmap_lazy_nr); + + if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) + cond_resched_lock(&vmap_area_lock); } spin_unlock(&vmap_area_lock); return true; @@ -721,10 +728,10 @@ static void purge_vmap_area_lazy(void) */ static void free_vmap_area_noflush(struct vmap_area *va) { - int nr_lazy; + unsigned long nr_lazy; - nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT, - &vmap_lazy_nr); + nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> + PAGE_SHIFT, &vmap_lazy_nr); /* After this point, we may free va at any time */ llist_add(&va->purge_list, &vmap_purge_list); @@ -1059,24 +1066,9 @@ static void vb_free(const void *addr, unsigned long size) spin_unlock(&vb->lock); } -/** - * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer - * - * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily - * to amortize TLB flushing overheads. What this means is that any page you - * have now, may, in a former life, have been mapped into kernel virtual - * address by the vmap layer and so there might be some CPUs with TLB entries - * still referencing that page (additional to the regular 1:1 kernel mapping). - * - * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can - * be sure that none of the pages we have control over will have any aliases - * from the vmap layer. - */ -void vm_unmap_aliases(void) +static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { - unsigned long start = ULONG_MAX, end = 0; int cpu; - int flush = 0; if (unlikely(!vmap_initialized)) return; @@ -1113,6 +1105,27 @@ void vm_unmap_aliases(void) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } + +/** + * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer + * + * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily + * to amortize TLB flushing overheads. What this means is that any page you + * have now, may, in a former life, have been mapped into kernel virtual + * address by the vmap layer and so there might be some CPUs with TLB entries + * still referencing that page (additional to the regular 1:1 kernel mapping). + * + * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can + * be sure that none of the pages we have control over will have any aliases + * from the vmap layer. + */ +void vm_unmap_aliases(void) +{ + unsigned long start = ULONG_MAX, end = 0; + int flush = 0; + + _vm_unmap_aliases(start, end, flush); +} EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** @@ -1505,6 +1518,72 @@ struct vm_struct *remove_vm_area(const void *addr) return NULL; } +static inline void set_area_direct_map(const struct vm_struct *area, + int (*set_direct_map)(struct page *page)) +{ + int i; + + for (i = 0; i < area->nr_pages; i++) + if (page_address(area->pages[i])) + set_direct_map(area->pages[i]); +} + +/* Handle removing and resetting vm mappings related to the vm_struct. */ +static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) +{ + unsigned long addr = (unsigned long)area->addr; + unsigned long start = ULONG_MAX, end = 0; + int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; + int i; + + /* + * The below block can be removed when all architectures that have + * direct map permissions also have set_direct_map_() implementations. + * This is concerned with resetting the direct map any an vm alias with + * execute permissions, without leaving a RW+X window. + */ + if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { + set_memory_nx(addr, area->nr_pages); + set_memory_rw(addr, area->nr_pages); + } + + remove_vm_area(area->addr); + + /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */ + if (!flush_reset) + return; + + /* + * If not deallocating pages, just do the flush of the VM area and + * return. + */ + if (!deallocate_pages) { + vm_unmap_aliases(); + return; + } + + /* + * If execution gets here, flush the vm mapping and reset the direct + * map. Find the start and end range of the direct mappings to make sure + * the vm_unmap_aliases() flush includes the direct map. + */ + for (i = 0; i < area->nr_pages; i++) { + if (page_address(area->pages[i])) { + start = min(addr, start); + end = max(addr, end); + } + } + + /* + * Set direct map to something invalid so that it won't be cached if + * there are any accesses after the TLB flush, then flush the TLB and + * reset the direct map permissions to the default. + */ + set_area_direct_map(area, set_direct_map_invalid_noflush); + _vm_unmap_aliases(start, end, 1); + set_area_direct_map(area, set_direct_map_default_noflush); +} + static void __vunmap(const void *addr, int deallocate_pages) { struct vm_struct *area; @@ -1526,7 +1605,8 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); - remove_vm_area(addr); + vm_remove_mappings(area, deallocate_pages); + if (deallocate_pages) { int i; @@ -1961,8 +2041,9 @@ EXPORT_SYMBOL(vzalloc_node); */ void *vmalloc_exec(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC, - NUMA_NO_NODE, __builtin_return_address(0)); + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) |