diff options
Diffstat (limited to 'arch/x86/mm/pageattr.c')
| -rw-r--r-- | arch/x86/mm/pageattr.c | 1465 |
1 files changed, 1206 insertions, 259 deletions
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 7b79f6be4e7..ae242a7c11c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -6,40 +6,101 @@ #include <linux/bootmem.h> #include <linux/module.h> #include <linux/sched.h> -#include <linux/slab.h> #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/pfn.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/pci.h> #include <asm/e820.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> +#include <asm/pat.h> /* * The current flushing context - we pass it instead of 5 arguments: */ struct cpa_data { - unsigned long vaddr; + unsigned long *vaddr; + pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; int numpages; - int flushtlb; + int flags; unsigned long pfn; + unsigned force_split : 1; + int curpage; + struct page **pages; }; +/* + * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings) + * using cpa_lock. So that we don't allow any other cpu, with stale large tlb + * entries change the page attribute in parallel to some other cpu + * splitting a large page entry along with changing the attribute. + */ +static DEFINE_SPINLOCK(cpa_lock); + +#define CPA_FLUSHTLB 1 +#define CPA_ARRAY 2 +#define CPA_PAGES_ARRAY 4 + +#ifdef CONFIG_PROC_FS +static unsigned long direct_pages_count[PG_LEVEL_NUM]; + +void update_page_count(int level, unsigned long pages) +{ + /* Protect against CPA */ + spin_lock(&pgd_lock); + direct_pages_count[level] += pages; + spin_unlock(&pgd_lock); +} + +static void split_page_count(int level) +{ + direct_pages_count[level]--; + direct_pages_count[level - 1] += PTRS_PER_PTE; +} + +void arch_report_meminfo(struct seq_file *m) +{ + seq_printf(m, "DirectMap4k: %8lu kB\n", + direct_pages_count[PG_LEVEL_4K] << 2); +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + seq_printf(m, "DirectMap2M: %8lu kB\n", + direct_pages_count[PG_LEVEL_2M] << 11); +#else + seq_printf(m, "DirectMap4M: %8lu kB\n", + direct_pages_count[PG_LEVEL_2M] << 12); +#endif +#ifdef CONFIG_X86_64 + if (direct_gbpages) + seq_printf(m, "DirectMap1G: %8lu kB\n", + direct_pages_count[PG_LEVEL_1G] << 20); +#endif +} +#else +static inline void split_page_count(int level) { } +#endif + #ifdef CONFIG_X86_64 static inline unsigned long highmap_start_pfn(void) { - return __pa(_text) >> PAGE_SHIFT; + return __pa_symbol(_text) >> PAGE_SHIFT; } static inline unsigned long highmap_end_pfn(void) { - return __pa(round_up((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT; + return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; } #endif @@ -62,11 +123,11 @@ within(unsigned long addr, unsigned long start, unsigned long end) /** * clflush_cache_range - flush a cache range with clflush - * @addr: virtual start address + * @vaddr: virtual start address * @size: number of bytes to flush * - * clflush is an unordered instruction which needs fencing with mfence - * to avoid ordering issues. + * clflushopt is an unordered instruction which needs fencing with mfence or + * sfence to avoid ordering issues. */ void clflush_cache_range(void *vaddr, unsigned int size) { @@ -75,14 +136,15 @@ void clflush_cache_range(void *vaddr, unsigned int size) mb(); for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size) - clflush(vaddr); + clflushopt(vaddr); /* * Flush any possible final partial cacheline: */ - clflush(vend); + clflushopt(vend); mb(); } +EXPORT_SYMBOL_GPL(clflush_cache_range); static void __cpa_flush_all(void *arg) { @@ -94,7 +156,7 @@ static void __cpa_flush_all(void *arg) */ __flush_tlb_all(); - if (cache && boot_cpu_data.x86_model >= 4) + if (cache && boot_cpu_data.x86 >= 4) wbinvd(); } @@ -102,7 +164,7 @@ static void cpa_flush_all(unsigned long cache) { BUG_ON(irqs_disabled()); - on_each_cpu(__cpa_flush_all, (void *) cache, 1, 1); + on_each_cpu(__cpa_flush_all, (void *) cache, 1); } static void __cpa_flush_range(void *arg) @@ -123,7 +185,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) BUG_ON(irqs_disabled()); WARN_ON(PAGE_ALIGN(start) != start); - on_each_cpu(__cpa_flush_range, NULL, 1, 1); + on_each_cpu(__cpa_flush_range, NULL, 1); if (!cache) return; @@ -145,6 +207,44 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) } } +static void cpa_flush_array(unsigned long *start, int numpages, int cache, + int in_flags, struct page **pages) +{ + unsigned int i, level; + unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ + + BUG_ON(irqs_disabled()); + + on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); + + if (!cache || do_wbinvd) + return; + + /* + * We only need to flush on one CPU, + * clflush is a MESI-coherent instruction that + * will cause all other CPUs to flush the same + * cachelines: + */ + for (i = 0; i < numpages; i++) { + unsigned long addr; + pte_t *pte; + + if (in_flags & CPA_PAGES_ARRAY) + addr = (unsigned long)page_address(pages[i]); + else + addr = start[i]; + + pte = lookup_address(addr, &level); + + /* + * Only flush present addresses: + */ + if (pte && (pte_val(*pte) & _PAGE_PRESENT)) + clflush_cache_range((void *)addr, PAGE_SIZE); + } +} + /* * Certain areas of memory on x86 require very specific protection flags, * for example the BIOS area or kernel text. Callers don't always get this @@ -160,8 +260,10 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, * The BIOS area between 640k and 1Mb needs to be executable for * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support. */ - if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) +#ifdef CONFIG_PCI_BIOS + if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_NX; +#endif /* * The kernel text needs to be executable for obvious reasons @@ -175,26 +277,59 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, * The .rodata section needs to be read-only. Using the pfn * catches all aliases. */ - if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, - __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) + if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT, + __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) + /* + * Once the kernel maps the text as RO (kernel_set_to_readonly is set), + * kernel text mappings for the large page aligned text, rodata sections + * will be always read-only. For the kernel identity mappings covering + * the holes caused by this alignment can be anything that user asks. + * + * This will preserve the large page mappings for kernel text/data + * at no extra cost. + */ + if (kernel_set_to_readonly && + within(address, (unsigned long)_text, + (unsigned long)__end_rodata_hpage_align)) { + unsigned int level; + + /* + * Don't enforce the !RW mapping for the kernel text mapping, + * if the current mapping is already using small page mapping. + * No need to work hard to preserve large page mappings in this + * case. + * + * This also fixes the Linux Xen paravirt guest boot failure + * (because of unexpected read-only mappings for kernel identity + * mappings). In this paravirt guest case, the kernel text + * mapping and the kernel identity mapping share the same + * page-table pages. Thus we can't really use different + * protections for the kernel text and identity mappings. Also, + * these shared mappings are made of small page mappings. + * Thus this don't enforce !RW mapping for small page kernel + * text mapping logic will help Linux Xen parvirt guest boot + * as well. + */ + if (lookup_address(address, &level) && (level != PG_LEVEL_4K)) + pgprot_val(forbidden) |= _PAGE_RW; + } +#endif + prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); return prot; } /* - * Lookup the page table entry for a virtual address. Return a pointer - * to the entry and the level of the mapping. - * - * Note: We return pud and pmd either when the entry is marked large - * or when the present bit is not set. Otherwise we would return a - * pointer to a nonexisting mapping. + * Lookup the page table entry for a virtual address in a specific pgd. + * Return a pointer to the entry and the level of the mapping. */ -pte_t *lookup_address(unsigned long address, unsigned int *level) +pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level) { - pgd_t *pgd = pgd_offset_k(address); pud_t *pud; pmd_t *pmd; @@ -225,6 +360,61 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } /* + * Lookup the page table entry for a virtual address. Return a pointer + * to the entry and the level of the mapping. + * + * Note: We return pud and pmd either when the entry is marked large + * or when the present bit is not set. Otherwise we would return a + * pointer to a nonexisting mapping. + */ +pte_t *lookup_address(unsigned long address, unsigned int *level) +{ + return lookup_address_in_pgd(pgd_offset_k(address), address, level); +} +EXPORT_SYMBOL_GPL(lookup_address); + +static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, + unsigned int *level) +{ + if (cpa->pgd) + return lookup_address_in_pgd(cpa->pgd + pgd_index(address), + address, level); + + return lookup_address(address, level); +} + +/* + * This is necessary because __pa() does not work on some + * kinds of memory, like vmalloc() or the alloc_remap() + * areas on 32-bit NUMA systems. The percpu areas can + * end up in this kind of memory, for instance. + * + * This could be optimized, but it is only intended to be + * used at inititalization time, and keeping it + * unoptimized should increase the testing coverage for + * the more obscure platforms. + */ +phys_addr_t slow_virt_to_phys(void *__virt_addr) +{ + unsigned long virt_addr = (unsigned long)__virt_addr; + phys_addr_t phys_addr; + unsigned long offset; + enum pg_level level; + unsigned long psize; + unsigned long pmask; + pte_t *pte; + + pte = lookup_address(virt_addr, &level); + BUG_ON(!pte); + psize = page_level_size(level); + pmask = page_level_mask(level); + offset = virt_addr & ~pmask; + phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + return (phys_addr | offset); +} +EXPORT_SYMBOL_GPL(slow_virt_to_phys); + +/* * Set the new pmd in all the pgds we know about: */ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) @@ -253,32 +443,32 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; pte_t new_pte, old_pte, *tmp; - pgprot_t old_prot, new_prot; + pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; - unsigned int level; + enum pg_level level; - spin_lock_irqsave(&pgd_lock, flags); + if (cpa->force_split) + return 1; + + spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up already: */ - tmp = lookup_address(address, &level); + tmp = _lookup_address_cpa(cpa, address, &level); if (tmp != kpte) goto out_unlock; switch (level) { case PG_LEVEL_2M: - psize = PMD_PAGE_SIZE; - pmask = PMD_PAGE_MASK; - break; #ifdef CONFIG_X86_64 case PG_LEVEL_1G: - psize = PUD_PAGE_SIZE; - pmask = PUD_PAGE_MASK; - break; #endif + psize = page_level_size(level); + pmask = page_level_mask(level); + break; default: do_split = -EINVAL; goto out_unlock; @@ -297,10 +487,23 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = pte_pgprot(old_pte); + old_prot = req_prot = pte_pgprot(old_pte); + + pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); + pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); - pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); - pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); + /* + * Set the PSE and GLOBAL flags only if the PRESENT flag is + * set otherwise pmd_present/pmd_huge will return true even on + * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(req_prot) & _PAGE_PRESENT) + pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + else + pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + + req_prot = canon_pgprot(req_prot); /* * old_pte points to the large page base address. So we need @@ -309,17 +512,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; - new_prot = static_protections(new_prot, address, pfn); + new_prot = static_protections(req_prot, address, pfn); /* * We need to check the full range, whether * static_protection() requires a different pgprot for one of * the pages in the range we try to preserve: */ - addr = address + PAGE_SIZE; - pfn++; - for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) { - pgprot_t chk_prot = static_protections(new_prot, addr, pfn); + addr = address & pmask; + pfn = pte_pfn(old_pte); + for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { + pgprot_t chk_prot = static_protections(req_prot, addr, pfn); if (pgprot_val(chk_prot) != pgprot_val(new_prot)) goto out_unlock; @@ -342,211 +545,574 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * that we limited the number of possible pages already to * the number of pages in the large page. */ - if (address == (nextpage_addr - psize) && cpa->numpages == numpages) { + if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) { /* * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot)); + new_pte = pfn_pte(pte_pfn(old_pte), new_prot); __set_pmd_pte(kpte, address, new_pte); - cpa->flushtlb = 1; + cpa->flags |= CPA_FLUSHTLB; do_split = 0; } out_unlock: - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return do_split; } -static LIST_HEAD(page_pool); -static unsigned long pool_size, pool_pages, pool_low; -static unsigned long pool_used, pool_failed; - -static void cpa_fill_pool(struct page **ret) +static int +__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, + struct page *base) { - gfp_t gfp = GFP_KERNEL; - unsigned long flags; - struct page *p; + pte_t *pbase = (pte_t *)page_address(base); + unsigned long pfn, pfninc = 1; + unsigned int i, level; + pte_t *tmp; + pgprot_t ref_prot; + spin_lock(&pgd_lock); /* - * Avoid recursion (on debug-pagealloc) and also signal - * our priority to get to these pagetables: + * Check for races, another CPU might have split this page + * up for us already: */ - if (current->flags & PF_MEMALLOC) - return; - current->flags |= PF_MEMALLOC; + tmp = _lookup_address_cpa(cpa, address, &level); + if (tmp != kpte) { + spin_unlock(&pgd_lock); + return 1; + } + paravirt_alloc_pte(&init_mm, page_to_pfn(base)); + ref_prot = pte_pgprot(pte_clrhuge(*kpte)); /* - * Allocate atomically from atomic contexts: + * If we ever want to utilize the PAT bit, we need to + * update this function to make sure it's converted from + * bit 12 to bit 7 when we cross from the 2MB level to + * the 4K level: */ - if (in_atomic() || irqs_disabled() || debug_pagealloc) - gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; + WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE); - while (pool_pages < pool_size || (ret && !*ret)) { - p = alloc_pages(gfp, 0); - if (!p) { - pool_failed++; - break; - } +#ifdef CONFIG_X86_64 + if (level == PG_LEVEL_1G) { + pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; /* - * If the call site needs a page right now, provide it: + * Set the PSE flags only if the PRESENT flag is set + * otherwise pmd_present/pmd_huge will return true + * even on a non present pmd. */ - if (ret && !*ret) { - *ret = p; - continue; - } - spin_lock_irqsave(&pgd_lock, flags); - list_add(&p->lru, &page_pool); - pool_pages++; - spin_unlock_irqrestore(&pgd_lock, flags); + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_PSE; + else + pgprot_val(ref_prot) &= ~_PAGE_PSE; } +#endif + + /* + * Set the GLOBAL flags only if the PRESENT flag is set + * otherwise pmd/pte_present will return true even on a non + * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_GLOBAL; + else + pgprot_val(ref_prot) &= ~_PAGE_GLOBAL; + + /* + * Get the target pfn from the original entry: + */ + pfn = pte_pfn(*kpte); + for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) + set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); - current->flags &= ~PF_MEMALLOC; + if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), + PFN_DOWN(__pa(address)) + 1)) + split_page_count(level); + + /* + * Install the new, split up pagetable. + * + * We use the standard kernel pagetable protections for the new + * pagetable protections, the actual ptes set above control the + * primary protection behavior: + */ + __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); + + /* + * Intel Atom errata AAH41 workaround. + * + * The real fix should be in hw or in a microcode update, but + * we also probabilistically try to reduce the window of having + * a large TLB mixed with 4K TLBs while instruction fetches are + * going on. + */ + __flush_tlb_all(); + spin_unlock(&pgd_lock); + + return 0; +} + +static int split_large_page(struct cpa_data *cpa, pte_t *kpte, + unsigned long address) +{ + struct page *base; + + if (!debug_pagealloc) + spin_unlock(&cpa_lock); + base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); + if (!debug_pagealloc) + spin_lock(&cpa_lock); + if (!base) + return -ENOMEM; + + if (__split_large_page(cpa, kpte, address, base)) + __free_page(base); + + return 0; +} + +static bool try_to_free_pte_page(pte_t *pte) +{ + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) + if (!pte_none(pte[i])) + return false; + + free_page((unsigned long)pte); + return true; +} + +static bool try_to_free_pmd_page(pmd_t *pmd) +{ + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) + if (!pmd_none(pmd[i])) + return false; + + free_page((unsigned long)pmd); + return true; +} + +static bool try_to_free_pud_page(pud_t *pud) +{ + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) + if (!pud_none(pud[i])) + return false; + + free_page((unsigned long)pud); + return true; } -#define SHIFT_MB (20 - PAGE_SHIFT) -#define ROUND_MB_GB ((1 << 10) - 1) -#define SHIFT_MB_GB 10 -#define POOL_PAGES_PER_GB 16 +static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) +{ + pte_t *pte = pte_offset_kernel(pmd, start); + + while (start < end) { + set_pte(pte, __pte(0)); + + start += PAGE_SIZE; + pte++; + } -void __init cpa_init(void) + if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { + pmd_clear(pmd); + return true; + } + return false; +} + +static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, + unsigned long start, unsigned long end) { - struct sysinfo si; - unsigned long gb; + if (unmap_pte_range(pmd, start, end)) + if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + pud_clear(pud); +} + +static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) +{ + pmd_t *pmd = pmd_offset(pud, start); - si_meminfo(&si); /* - * Calculate the number of pool pages: - * - * Convert totalram (nr of pages) to MiB and round to the next - * GiB. Shift MiB to Gib and multiply the result by - * POOL_PAGES_PER_GB: + * Not on a 2MB page boundary? */ - if (debug_pagealloc) { - gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; - pool_size = POOL_PAGES_PER_GB * gb; - } else { - pool_size = 1; + if (start & (PMD_SIZE - 1)) { + unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; + unsigned long pre_end = min_t(unsigned long, end, next_page); + + __unmap_pmd_range(pud, pmd, start, pre_end); + + start = pre_end; + pmd++; + } + + /* + * Try to unmap in 2M chunks. + */ + while (end - start >= PMD_SIZE) { + if (pmd_large(*pmd)) + pmd_clear(pmd); + else + __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); + + start += PMD_SIZE; + pmd++; } - pool_low = pool_size; - cpa_fill_pool(NULL); - printk(KERN_DEBUG - "CPA: page pool initialized %lu of %lu pages preallocated\n", - pool_pages, pool_size); + /* + * 4K leftovers? + */ + if (start < end) + return __unmap_pmd_range(pud, pmd, start, end); + + /* + * Try again to free the PMD page if haven't succeeded above. + */ + if (!pud_none(*pud)) + if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + pud_clear(pud); } -static int split_large_page(pte_t *kpte, unsigned long address) +static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) { - unsigned long flags, pfn, pfninc = 1; - unsigned int i, level; - pte_t *pbase, *tmp; - pgprot_t ref_prot; - struct page *base; + pud_t *pud = pud_offset(pgd, start); /* - * Get a page from the pool. The pool list is protected by the - * pgd_lock, which we have to take anyway for the split - * operation: + * Not on a GB page boundary? */ - spin_lock_irqsave(&pgd_lock, flags); - if (list_empty(&page_pool)) { - spin_unlock_irqrestore(&pgd_lock, flags); - base = NULL; - cpa_fill_pool(&base); - if (!base) - return -ENOMEM; - spin_lock_irqsave(&pgd_lock, flags); - } else { - base = list_first_entry(&page_pool, struct page, lru); - list_del(&base->lru); - pool_pages--; + if (start & (PUD_SIZE - 1)) { + unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; + unsigned long pre_end = min_t(unsigned long, end, next_page); + + unmap_pmd_range(pud, start, pre_end); - if (pool_pages < pool_low) - pool_low = pool_pages; + start = pre_end; + pud++; } /* - * Check for races, another CPU might have split this page - * up for us already: + * Try to unmap in 1G chunks? */ - tmp = lookup_address(address, &level); - if (tmp != kpte) - goto out_unlock; + while (end - start >= PUD_SIZE) { - pbase = (pte_t *)page_address(base); -#ifdef CONFIG_X86_32 - paravirt_alloc_pt(&init_mm, page_to_pfn(base)); -#endif - ref_prot = pte_pgprot(pte_clrhuge(*kpte)); + if (pud_large(*pud)) + pud_clear(pud); + else + unmap_pmd_range(pud, start, start + PUD_SIZE); -#ifdef CONFIG_X86_64 - if (level == PG_LEVEL_1G) { - pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; - pgprot_val(ref_prot) |= _PAGE_PSE; + start += PUD_SIZE; + pud++; } -#endif /* - * Get the target pfn from the original entry: + * 2M leftovers? */ - pfn = pte_pfn(*kpte); - for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) - set_pte(&pbase[i], pfn_pte(pfn, ref_prot)); + if (start < end) + unmap_pmd_range(pud, start, end); /* - * Install the new, split up pagetable. Important details here: - * - * On Intel the NX bit of all levels must be cleared to make a - * page executable. See section 4.13.2 of Intel 64 and IA-32 - * Architectures Software Developer's Manual). - * - * Mark the entry present. The current mapping might be - * set to not present, which we preserved above. + * No need to try to free the PUD page because we'll free it in + * populate_pgd's error path */ - ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte))); - pgprot_val(ref_prot) |= _PAGE_PRESENT; - __set_pmd_pte(kpte, address, mk_pte(base, ref_prot)); - base = NULL; +} + +static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) +{ + pgd_t *pgd_entry = root + pgd_index(addr); + + unmap_pud_range(pgd_entry, addr, end); + + if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry))) + pgd_clear(pgd_entry); +} + +static int alloc_pte_page(pmd_t *pmd) +{ + pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pte) + return -1; + + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); + return 0; +} + +static int alloc_pmd_page(pud_t *pud) +{ + pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pmd) + return -1; + + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + return 0; +} + +static void populate_pte(struct cpa_data *cpa, + unsigned long start, unsigned long end, + unsigned num_pages, pmd_t *pmd, pgprot_t pgprot) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, start); + + while (num_pages-- && start < end) { + + /* deal with the NX bit */ + if (!(pgprot_val(pgprot) & _PAGE_NX)) + cpa->pfn &= ~_PAGE_NX; + + set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot)); + + start += PAGE_SIZE; + cpa->pfn += PAGE_SIZE; + pte++; + } +} + +static int populate_pmd(struct cpa_data *cpa, + unsigned long start, unsigned long end, + unsigned num_pages, pud_t *pud, pgprot_t pgprot) +{ + unsigned int cur_pages = 0; + pmd_t *pmd; -out_unlock: /* - * If we dropped out via the lookup_address check under - * pgd_lock then stick the page back into the pool: + * Not on a 2M boundary? */ - if (base) { - list_add(&base->lru, &page_pool); - pool_pages++; - } else - pool_used++; - spin_unlock_irqrestore(&pgd_lock, flags); + if (start & (PMD_SIZE - 1)) { + unsigned long pre_end = start + (num_pages << PAGE_SHIFT); + unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; + + pre_end = min_t(unsigned long, pre_end, next_page); + cur_pages = (pre_end - start) >> PAGE_SHIFT; + cur_pages = min_t(unsigned int, num_pages, cur_pages); + + /* + * Need a PTE page? + */ + pmd = pmd_offset(pud, start); + if (pmd_none(*pmd)) + if (alloc_pte_page(pmd)) + return -1; + + populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot); + + start = pre_end; + } + + /* + * We mapped them all? + */ + if (num_pages == cur_pages) + return cur_pages; + + while (end - start >= PMD_SIZE) { + /* + * We cannot use a 1G page so allocate a PMD page if needed. + */ + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + pmd = pmd_offset(pud, start); + + set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + + start += PMD_SIZE; + cpa->pfn += PMD_SIZE; + cur_pages += PMD_SIZE >> PAGE_SHIFT; + } + + /* + * Map trailing 4K pages. + */ + if (start < end) { + pmd = pmd_offset(pud, start); + if (pmd_none(*pmd)) + if (alloc_pte_page(pmd)) + return -1; + + populate_pte(cpa, start, end, num_pages - cur_pages, + pmd, pgprot); + } + return num_pages; +} + +static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, + pgprot_t pgprot) +{ + pud_t *pud; + unsigned long end; + int cur_pages = 0; + + end = start + (cpa->numpages << PAGE_SHIFT); + + /* + * Not on a Gb page boundary? => map everything up to it with + * smaller pages. + */ + if (start & (PUD_SIZE - 1)) { + unsigned long pre_end; + unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; + + pre_end = min_t(unsigned long, end, next_page); + cur_pages = (pre_end - start) >> PAGE_SHIFT; + cur_pages = min_t(int, (int)cpa->numpages, cur_pages); + + pud = pud_offset(pgd, start); + + /* + * Need a PMD page? + */ + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + cur_pages = populate_pmd(cpa, start, pre_end, cur_pages, + pud, pgprot); + if (cur_pages < 0) + return cur_pages; + + start = pre_end; + } + + /* We mapped them all? */ + if (cpa->numpages == cur_pages) + return cur_pages; + + pud = pud_offset(pgd, start); + + /* + * Map everything starting from the Gb boundary, possibly with 1G pages + */ + while (end - start >= PUD_SIZE) { + set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + + start += PUD_SIZE; + cpa->pfn += PUD_SIZE; + cur_pages += PUD_SIZE >> PAGE_SHIFT; + pud++; + } + + /* Map trailing leftover */ + if (start < end) { + int tmp; + + pud = pud_offset(pgd, start); + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages, + pud, pgprot); + if (tmp < 0) + return cur_pages; + + cur_pages += tmp; + } + return cur_pages; +} + +/* + * Restrictions for kernel page table do not necessarily apply when mapping in + * an alternate PGD. + */ +static int populate_pgd(struct cpa_data *cpa, unsigned long addr) +{ + pgprot_t pgprot = __pgprot(_KERNPG_TABLE); + pud_t *pud = NULL; /* shut up gcc */ + pgd_t *pgd_entry; + int ret; + + pgd_entry = cpa->pgd + pgd_index(addr); + + /* + * Allocate a PUD page and hand it down for mapping. + */ + if (pgd_none(*pgd_entry)) { + pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pud) + return -1; + + set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); + } + + pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); + pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); + + ret = populate_pud(cpa, addr, pgd_entry, pgprot); + if (ret < 0) { + unmap_pgd_range(cpa->pgd, addr, + addr + (cpa->numpages << PAGE_SHIFT)); + return ret; + } + + cpa->numpages = ret; return 0; } +static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, + int primary) +{ + if (cpa->pgd) + return populate_pgd(cpa, vaddr); + + /* + * Ignore all non primary paths. + */ + if (!primary) + return 0; + + /* + * Ignore the NULL PTE for kernel identity mapping, as it is expected + * to have holes. + * Also set numpages to '1' indicating that we processed cpa req for + * one virtual address page and its pfn. TBD: numpages can be set based + * on the initial value and the level returned by lookup_address(). + */ + if (within(vaddr, PAGE_OFFSET, + PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) { + cpa->numpages = 1; + cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; + return 0; + } else { + WARN(1, KERN_WARNING "CPA: called for zero pte. " + "vaddr = %lx cpa->vaddr = %lx\n", vaddr, + *cpa->vaddr); + + return -EFAULT; + } +} + static int __change_page_attr(struct cpa_data *cpa, int primary) { - unsigned long address = cpa->vaddr; + unsigned long address; int do_split, err; unsigned int level; pte_t *kpte, old_pte; + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + address = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) + address = cpa->vaddr[cpa->curpage]; + else + address = *cpa->vaddr; repeat: - kpte = lookup_address(address, &level); + kpte = _lookup_address_cpa(cpa, address, &level); if (!kpte) - return primary ? -EINVAL : 0; + return __cpa_process_fault(cpa, address, primary); old_pte = *kpte; - if (!pte_val(old_pte)) { - if (!primary) - return 0; - printk(KERN_WARNING "CPA: called for zero pte. " - "vaddr = %lx cpa->vaddr = %lx\n", address, - cpa->vaddr); - WARN_ON(1); - return -EINVAL; - } + if (!pte_val(old_pte)) + return __cpa_process_fault(cpa, address, primary); if (level == PG_LEVEL_4K) { pte_t new_pte; @@ -559,6 +1125,18 @@ repeat: new_prot = static_protections(new_prot, address, pfn); /* + * Set the GLOBAL flags only if the PRESENT flag is + * set otherwise pte_present will return true even on + * a non present pte. The canon_pgprot will clear + * _PAGE_GLOBAL for the ancient hardware that doesn't + * support it. + */ + if (pgprot_val(new_prot) & _PAGE_PRESENT) + pgprot_val(new_prot) |= _PAGE_GLOBAL; + else + pgprot_val(new_prot) &= ~_PAGE_GLOBAL; + + /* * We need to keep the pfn from the existing PTE, * after all we're only going to change it's attributes * not the memory it points to @@ -570,7 +1148,7 @@ repeat: */ if (pte_val(old_pte) != pte_val(new_pte)) { set_pte_atomic(kpte, new_pte); - cpa->flushtlb = 1; + cpa->flags |= CPA_FLUSHTLB; } cpa->numpages = 1; return 0; @@ -592,9 +1170,27 @@ repeat: /* * We have to split the large page: */ - err = split_large_page(kpte, address); + err = split_large_page(cpa, kpte, address); if (!err) { - cpa->flushtlb = 1; + /* + * Do a global flush tlb after splitting the large page + * and before we do the actual change page attribute in the PTE. + * + * With out this, we violate the TLB application note, that says + * "The TLBs may contain both ordinary and large-page + * translations for a 4-KByte range of linear addresses. This + * may occur if software modifies the paging structures so that + * the page size used for the address range changes. If the two + * translations differ with respect to page frame or attributes + * (e.g., permissions), processor behavior is undefined and may + * be implementation-specific." + * + * We do this global tlb flush inside the cpa_lock, so that we + * don't allow any other cpu, with stale tlb entries change the + * page attribute in parallel, that also falls into the + * just split large page entry. + */ + flush_tlb_all(); goto repeat; } @@ -606,51 +1202,62 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias); static int cpa_process_alias(struct cpa_data *cpa) { struct cpa_data alias_cpa; - int ret = 0; + unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT); + unsigned long vaddr; + int ret; - if (cpa->pfn > max_pfn_mapped) + if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1)) return 0; /* * No need to redo, when the primary call touched the direct * mapping already: */ - if (!within(cpa->vaddr, PAGE_OFFSET, - PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) { + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + vaddr = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) + vaddr = cpa->vaddr[cpa->curpage]; + else + vaddr = *cpa->vaddr; + + if (!(within(vaddr, PAGE_OFFSET, + PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) { alias_cpa = *cpa; - alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT); + alias_cpa.vaddr = &laddr; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); ret = __change_page_attr_set_clr(&alias_cpa, 0); + if (ret) + return ret; } #ifdef CONFIG_X86_64 - if (ret) - return ret; /* - * No need to redo, when the primary call touched the high - * mapping already: - */ - if (within(cpa->vaddr, (unsigned long) _text, (unsigned long) _end)) - return 0; - - /* - * If the physical address is inside the kernel map, we need + * If the primary call didn't touch the high mapping already + * and the physical address is inside the kernel map, we need * to touch the high mapped kernel as well: */ - if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) - return 0; - - alias_cpa = *cpa; - alias_cpa.vaddr = - (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; + if (!within(vaddr, (unsigned long)_text, _brk_end) && + within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) { + unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + + __START_KERNEL_map - phys_base; + alias_cpa = *cpa; + alias_cpa.vaddr = &temp_cpa_vaddr; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); - /* - * The high mapping range is imprecise, so ignore the return value. - */ - __change_page_attr_set_clr(&alias_cpa, 0); + /* + * The high mapping range is imprecise, so ignore the + * return value. + */ + __change_page_attr_set_clr(&alias_cpa, 0); + } #endif - return ret; + + return 0; } static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) @@ -663,8 +1270,15 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * preservation check. */ cpa->numpages = numpages; + /* for array changes, we can't use large page */ + if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY)) + cpa->numpages = 1; + if (!debug_pagealloc) + spin_lock(&cpa_lock); ret = __change_page_attr(cpa, checkalias); + if (!debug_pagealloc) + spin_unlock(&cpa_lock); if (ret) return ret; @@ -681,7 +1295,11 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) */ BUG_ON(cpa->numpages > numpages); numpages -= cpa->numpages; - cpa->vaddr += cpa->numpages * PAGE_SIZE; + if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) + cpa->curpage++; + else + *cpa->vaddr += cpa->numpages * PAGE_SIZE; + } return 0; } @@ -692,11 +1310,16 @@ static inline int cache_attr(pgprot_t attr) (_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD); } -static int change_page_attr_set_clr(unsigned long addr, int numpages, - pgprot_t mask_set, pgprot_t mask_clr) +static int change_page_attr_set_clr(unsigned long *addr, int numpages, + pgprot_t mask_set, pgprot_t mask_clr, + int force_split, int in_flag, + struct page **pages) { struct cpa_data cpa; int ret, cache, checkalias; + unsigned long baddr = 0; + + memset(&cpa, 0, sizeof(cpa)); /* * Check, if we are requested to change a not supported @@ -704,23 +1327,53 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, */ mask_set = canon_pgprot(mask_set); mask_clr = canon_pgprot(mask_clr); - if (!pgprot_val(mask_set) && !pgprot_val(mask_clr)) + if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split) return 0; /* Ensure we are PAGE_SIZE aligned */ - if (addr & ~PAGE_MASK) { - addr &= PAGE_MASK; + if (in_flag & CPA_ARRAY) { + int i; + for (i = 0; i < numpages; i++) { + if (addr[i] & ~PAGE_MASK) { + addr[i] &= PAGE_MASK; + WARN_ON_ONCE(1); + } + } + } else if (!(in_flag & CPA_PAGES_ARRAY)) { + /* + * in_flag of CPA_PAGES_ARRAY implies it is aligned. + * No need to cehck in that case + */ + if (*addr & ~PAGE_MASK) { + *addr &= PAGE_MASK; + /* + * People should not be passing in unaligned addresses: + */ + WARN_ON_ONCE(1); + } /* - * People should not be passing in unaligned addresses: + * Save address for cache flush. *addr is modified in the call + * to __change_page_attr_set_clr() below. */ - WARN_ON_ONCE(1); + baddr = *addr; } + /* Must avoid aliasing mappings in the highmem code */ + kmap_flush_unused(); + + vm_unmap_aliases(); + cpa.vaddr = addr; + cpa.pages = pages; cpa.numpages = numpages; cpa.mask_set = mask_set; cpa.mask_clr = mask_clr; - cpa.flushtlb = 0; + cpa.flags = 0; + cpa.curpage = 0; + cpa.force_split = force_split; + + if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY)) + cpa.flags |= in_flag; /* No alias checking for _NX bit modifications */ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; @@ -730,7 +1383,7 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, /* * Check whether we really changed something: */ - if (!cpa.flushtlb) + if (!(cpa.flags & CPA_FLUSHTLB)) goto out; /* @@ -740,73 +1393,250 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, cache = cache_attr(mask_set); /* - * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it and in the + * On success we use CLFLUSH, when the CPU supports it to + * avoid the WBINVD. If the CPU does not support it and in the * error case we fall back to cpa_flush_all (which uses - * wbindv): + * WBINVD): */ - if (!ret && cpu_has_clflush) - cpa_flush_range(addr, numpages, cache); - else + if (!ret && cpu_has_clflush) { + if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { + cpa_flush_array(addr, numpages, cache, + cpa.flags, pages); + } else + cpa_flush_range(baddr, numpages, cache); + } else cpa_flush_all(cache); out: - cpa_fill_pool(NULL); - return ret; } -static inline int change_page_attr_set(unsigned long addr, int numpages, +static inline int change_page_attr_set(unsigned long *addr, int numpages, + pgprot_t mask, int array) +{ + return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0, + (array ? CPA_ARRAY : 0), NULL); +} + +static inline int change_page_attr_clear(unsigned long *addr, int numpages, + pgprot_t mask, int array) +{ + return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0, + (array ? CPA_ARRAY : 0), NULL); +} + +static inline int cpa_set_pages_array(struct page **pages, int numpages, pgprot_t mask) { - return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0)); + return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0, + CPA_PAGES_ARRAY, pages); } -static inline int change_page_attr_clear(unsigned long addr, int numpages, +static inline int cpa_clear_pages_array(struct page **pages, int numpages, pgprot_t mask) { - return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask); + return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0, + CPA_PAGES_ARRAY, pages); +} + +int _set_memory_uc(unsigned long addr, int numpages) +{ + /* + * for now UC MINUS. see comments in ioremap_nocache() + */ + return change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_CACHE_UC_MINUS), 0); } int set_memory_uc(unsigned long addr, int numpages) { - return change_page_attr_set(addr, numpages, - __pgprot(_PAGE_PCD)); + int ret; + + /* + * for now UC MINUS. see comments in ioremap_nocache() + */ + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_err; + + ret = _set_memory_uc(addr, numpages); + if (ret) + goto out_free; + + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_uc); +static int _set_memory_array(unsigned long *addr, int addrinarray, + unsigned long new_type) +{ + int i, j; + int ret; + + /* + * for now UC MINUS. see comments in ioremap_nocache() + */ + for (i = 0; i < addrinarray; i++) { + ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, + new_type, NULL); + if (ret) + goto out_free; + } + + ret = change_page_attr_set(addr, addrinarray, + __pgprot(_PAGE_CACHE_UC_MINUS), 1); + + if (!ret && new_type == _PAGE_CACHE_WC) + ret = change_page_attr_set_clr(addr, addrinarray, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, CPA_ARRAY, NULL); + if (ret) + goto out_free; + + return 0; + +out_free: + for (j = 0; j < i; j++) + free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE); + + return ret; +} + +int set_memory_array_uc(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS); +} +EXPORT_SYMBOL(set_memory_array_uc); + +int set_memory_array_wc(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC); +} +EXPORT_SYMBOL(set_memory_array_wc); + +int _set_memory_wc(unsigned long addr, int numpages) +{ + int ret; + unsigned long addr_copy = addr; + + ret = change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_CACHE_UC_MINUS), 0); + if (!ret) { + ret = change_page_attr_set_clr(&addr_copy, numpages, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, 0, NULL); + } + return ret; +} + +int set_memory_wc(unsigned long addr, int numpages) +{ + int ret; + + if (!pat_enabled) + return set_memory_uc(addr, numpages); + + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_WC, NULL); + if (ret) + goto out_err; + + ret = _set_memory_wc(addr, numpages); + if (ret) + goto out_free; + + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; +} +EXPORT_SYMBOL(set_memory_wc); + +int _set_memory_wb(unsigned long addr, int numpages) +{ + return change_page_attr_clear(&addr, numpages, + __pgprot(_PAGE_CACHE_MASK), 0); +} + int set_memory_wb(unsigned long addr, int numpages) { - return change_page_attr_clear(addr, numpages, - __pgprot(_PAGE_PCD | _PAGE_PWT)); + int ret; + + ret = _set_memory_wb(addr, numpages); + if (ret) + return ret; + + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + return 0; } EXPORT_SYMBOL(set_memory_wb); +int set_memory_array_wb(unsigned long *addr, int addrinarray) +{ + int i; + int ret; + + ret = change_page_attr_clear(addr, addrinarray, + __pgprot(_PAGE_CACHE_MASK), 1); + if (ret) + return ret; + + for (i = 0; i < addrinarray; i++) + free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE); + + return 0; +} +EXPORT_SYMBOL(set_memory_array_wb); + int set_memory_x(unsigned long addr, int numpages) { - return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_NX)); + if (!(__supported_pte_mask & _PAGE_NX)) + return 0; + + return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0); } EXPORT_SYMBOL(set_memory_x); int set_memory_nx(unsigned long addr, int numpages) { - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_NX)); + if (!(__supported_pte_mask & _PAGE_NX)) + return 0; + + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0); } EXPORT_SYMBOL(set_memory_nx); int set_memory_ro(unsigned long addr, int numpages) { - return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_RW)); + return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0); } +EXPORT_SYMBOL_GPL(set_memory_ro); int set_memory_rw(unsigned long addr, int numpages) { - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_RW)); + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0); } +EXPORT_SYMBOL_GPL(set_memory_rw); int set_memory_np(unsigned long addr, int numpages) { - return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT)); + return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + +int set_memory_4k(unsigned long addr, int numpages) +{ + return change_page_attr_set_clr(&addr, numpages, __pgprot(0), + __pgprot(0), 1, 0, NULL); } int set_pages_uc(struct page *page, int numpages) @@ -817,6 +1647,58 @@ int set_pages_uc(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_uc); +static int _set_pages_array(struct page **pages, int addrinarray, + unsigned long new_type) +{ + unsigned long start; + unsigned long end; + int i; + int free_idx; + int ret; + + for (i = 0; i < addrinarray; i++) { + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; + end = start + PAGE_SIZE; + if (reserve_memtype(start, end, new_type, NULL)) + goto err_out; + } + + ret = cpa_set_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_UC_MINUS)); + if (!ret && new_type == _PAGE_CACHE_WC) + ret = change_page_attr_set_clr(NULL, addrinarray, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, CPA_PAGES_ARRAY, pages); + if (ret) + goto err_out; + return 0; /* Success */ +err_out: + free_idx = i; + for (i = 0; i < free_idx; i++) { + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; + end = start + PAGE_SIZE; + free_memtype(start, end); + } + return -EINVAL; +} + +int set_pages_array_uc(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS); +} +EXPORT_SYMBOL(set_pages_array_uc); + +int set_pages_array_wc(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC); +} +EXPORT_SYMBOL(set_pages_array_wc); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -825,6 +1707,30 @@ int set_pages_wb(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_wb); +int set_pages_array_wb(struct page **pages, int addrinarray) +{ + int retval; + unsigned long start; + unsigned long end; + int i; + + retval = cpa_clear_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_MASK)); + if (retval) + return retval; + + for (i = 0; i < addrinarray; i++) { + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; + end = start + PAGE_SIZE; + free_memtype(start, end); + } + + return 0; +} +EXPORT_SYMBOL(set_pages_array_wb); + int set_pages_x(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -859,22 +1765,40 @@ int set_pages_rw(struct page *page, int numpages) static int __set_pages_p(struct page *page, int numpages) { - struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page), + unsigned long tempaddr = (unsigned long) page_address(page); + struct cpa_data cpa = { .vaddr = &tempaddr, + .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), - .mask_clr = __pgprot(0)}; + .mask_clr = __pgprot(0), + .flags = 0}; - return __change_page_attr_set_clr(&cpa, 1); + /* + * No alias checking needed for setting present flag. otherwise, + * we may need to break large pages for 64-bit kernel text + * mappings (this adds to complexity if we want to do this from + * atomic context especially). Let's keep it simple! + */ + return __change_page_attr_set_clr(&cpa, 0); } static int __set_pages_np(struct page *page, int numpages) { - struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page), + unsigned long tempaddr = (unsigned long) page_address(page); + struct cpa_data cpa = { .vaddr = &tempaddr, + .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW)}; + .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), + .flags = 0}; - return __change_page_attr_set_clr(&cpa, 1); + /* + * No alias checking needed for setting not present flag. otherwise, + * we may need to break large pages for 64-bit kernel text + * mappings (this adds to complexity if we want to do this from + * atomic context especially). Let's keep it simple! + */ + return __change_page_attr_set_clr(&cpa, 0); } void kernel_map_pages(struct page *page, int numpages, int enable) @@ -887,18 +1811,9 @@ void kernel_map_pages(struct page *page, int numpages, int enable) } /* - * If page allocator is not up yet then do not call c_p_a(): - */ - if (!debug_pagealloc_enabled) - return; - - /* * The return value is ignored as the calls cannot fail. - * Large pages are kept enabled at boot time, and are - * split up quickly with DEBUG_PAGEALLOC. If a splitup - * fails here (due to temporary memory shortage) no damage - * is done because we just keep the largepage intact up - * to the next attempt when it will likely be split up: + * Large pages for identity mappings are not used at boot time + * and hence no memory allocations during large page split. */ if (enable) __set_pages_p(page, numpages); @@ -911,11 +1826,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) */ __flush_tlb_all(); - /* - * Try to refill the page pool here. We can do this only after - * the tlb flush. - */ - cpa_fill_pool(NULL); + arch_flush_lazy_mmu_mode(); } #ifdef CONFIG_HIBERNATION @@ -936,6 +1847,42 @@ bool kernel_page_present(struct page *page) #endif /* CONFIG_DEBUG_PAGEALLOC */ +int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, + unsigned numpages, unsigned long page_flags) +{ + int retval = -EINVAL; + + struct cpa_data cpa = { + .vaddr = &address, + .pfn = pfn, + .pgd = pgd, + .numpages = numpages, + .mask_set = __pgprot(0), + .mask_clr = __pgprot(0), + .flags = 0, + }; + + if (!(__supported_pte_mask & _PAGE_NX)) + goto out; + + if (!(page_flags & _PAGE_NX)) + cpa.mask_clr = __pgprot(_PAGE_NX); + + cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); + + retval = __change_page_attr_set_clr(&cpa, 0); + __flush_tlb_all(); + +out: + return retval; +} + +void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, + unsigned numpages) +{ + unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT)); +} + /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. |