diff options
Diffstat (limited to 'arch/x86/mm/pageattr.c')
-rw-r--r-- | arch/x86/mm/pageattr.c | 810 |
1 files changed, 544 insertions, 266 deletions
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 85cf12219dea..db7a10082238 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -3,7 +3,7 @@ * Thanks to Ben LaHaise for precious feedback. */ #include <linux/highmem.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/interrupt.h> @@ -37,11 +37,20 @@ struct cpa_data { unsigned long numpages; int flags; unsigned long pfn; - unsigned force_split : 1; + unsigned force_split : 1, + force_static_prot : 1; int curpage; struct page **pages; }; +enum cpa_warn { + CPA_CONFLICT, + CPA_PROTECT, + CPA_DETECT, +}; + +static const int cpa_warn_level = CPA_PROTECT; + /* * 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 @@ -53,6 +62,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 +#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; @@ -93,21 +103,87 @@ void arch_report_meminfo(struct seq_file *m) static inline void split_page_count(int level) { } #endif -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_CPA_STATISTICS -static inline unsigned long highmap_start_pfn(void) +static unsigned long cpa_1g_checked; +static unsigned long cpa_1g_sameprot; +static unsigned long cpa_1g_preserved; +static unsigned long cpa_2m_checked; +static unsigned long cpa_2m_sameprot; +static unsigned long cpa_2m_preserved; +static unsigned long cpa_4k_install; + +static inline void cpa_inc_1g_checked(void) { - return __pa_symbol(_text) >> PAGE_SHIFT; + cpa_1g_checked++; } -static inline unsigned long highmap_end_pfn(void) +static inline void cpa_inc_2m_checked(void) { - /* Do not reference physical address outside the kernel. */ - return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; + cpa_2m_checked++; } +static inline void cpa_inc_4k_install(void) +{ + cpa_4k_install++; +} + +static inline void cpa_inc_lp_sameprot(int level) +{ + if (level == PG_LEVEL_1G) + cpa_1g_sameprot++; + else + cpa_2m_sameprot++; +} + +static inline void cpa_inc_lp_preserved(int level) +{ + if (level == PG_LEVEL_1G) + cpa_1g_preserved++; + else + cpa_2m_preserved++; +} + +static int cpastats_show(struct seq_file *m, void *p) +{ + seq_printf(m, "1G pages checked: %16lu\n", cpa_1g_checked); + seq_printf(m, "1G pages sameprot: %16lu\n", cpa_1g_sameprot); + seq_printf(m, "1G pages preserved: %16lu\n", cpa_1g_preserved); + seq_printf(m, "2M pages checked: %16lu\n", cpa_2m_checked); + seq_printf(m, "2M pages sameprot: %16lu\n", cpa_2m_sameprot); + seq_printf(m, "2M pages preserved: %16lu\n", cpa_2m_preserved); + seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install); + return 0; +} + +static int cpastats_open(struct inode *inode, struct file *file) +{ + return single_open(file, cpastats_show, NULL); +} + +static const struct file_operations cpastats_fops = { + .open = cpastats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init cpa_stats_init(void) +{ + debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL, + &cpastats_fops); + return 0; +} +late_initcall(cpa_stats_init); +#else +static inline void cpa_inc_1g_checked(void) { } +static inline void cpa_inc_2m_checked(void) { } +static inline void cpa_inc_4k_install(void) { } +static inline void cpa_inc_lp_sameprot(int level) { } +static inline void cpa_inc_lp_preserved(int level) { } #endif + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -120,6 +196,38 @@ within_inclusive(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr <= end; } +#ifdef CONFIG_X86_64 + +static inline unsigned long highmap_start_pfn(void) +{ + return __pa_symbol(_text) >> PAGE_SHIFT; +} + +static inline unsigned long highmap_end_pfn(void) +{ + /* Do not reference physical address outside the kernel. */ + return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; +} + +static bool __cpa_pfn_in_highmap(unsigned long pfn) +{ + /* + * Kernel text has an alias mapping at a high address, known + * here as "highmap". + */ + return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn()); +} + +#else + +static bool __cpa_pfn_in_highmap(unsigned long pfn) +{ + /* There is no highmap on 32-bit */ + return false; +} + +#endif + /* * Flushing functions */ @@ -172,19 +280,25 @@ static void __cpa_flush_all(void *arg) static void cpa_flush_all(unsigned long cache) { - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) cache, 1); } -static void __cpa_flush_range(void *arg) +static bool __cpa_flush_range(unsigned long start, int numpages, int cache) { - /* - * We could optimize that further and do individual per page - * tlb invalidates for a low number of pages. Caveat: we must - * flush the high aliases on 64bit as well. - */ - __flush_tlb_all(); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); + + WARN_ON(PAGE_ALIGN(start) != start); + + if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) { + cpa_flush_all(cache); + return true; + } + + flush_tlb_kernel_range(start, start + PAGE_SIZE * numpages); + + return !cache; } static void cpa_flush_range(unsigned long start, int numpages, int cache) @@ -192,12 +306,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) unsigned int i, level; unsigned long addr; - BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); - WARN_ON(PAGE_ALIGN(start) != start); - - on_each_cpu(__cpa_flush_range, NULL, 1); - - if (!cache) + if (__cpa_flush_range(start, numpages, cache)) return; /* @@ -217,30 +326,13 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) } } -static void cpa_flush_array(unsigned long *start, int numpages, int cache, +static void cpa_flush_array(unsigned long baddr, unsigned long *start, + int numpages, int cache, int in_flags, struct page **pages) { unsigned int i, level; -#ifdef CONFIG_PREEMPT - /* - * Avoid wbinvd() because it causes latencies on all CPUs, - * regardless of any CPU isolation that may be in effect. - * - * This should be extended for CAT enabled systems independent of - * PREEMPT because wbinvd() does not respect the CAT partitions and - * this is exposed to unpriviledged users through the graphics - * subsystem. - */ - unsigned long do_wbinvd = 0; -#else - unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ -#endif - - BUG_ON(irqs_disabled()); - on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); - - if (!cache || do_wbinvd) + if (__cpa_flush_range(baddr, numpages, cache)) return; /* @@ -268,82 +360,179 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, } } -/* - * 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 - * right (again, ioremap() on BIOS memory is not uncommon) so this function - * checks and fixes these known static required protection bits. - */ -static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, - unsigned long pfn) +static bool overlaps(unsigned long r1_start, unsigned long r1_end, + unsigned long r2_start, unsigned long r2_end) { - pgprot_t forbidden = __pgprot(0); + return (r1_start <= r2_end && r1_end >= r2_start) || + (r2_start <= r1_end && r2_end >= r1_start); +} - /* - * The BIOS area between 640k and 1Mb needs to be executable for - * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support. - */ #ifdef CONFIG_PCI_BIOS - if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) - pgprot_val(forbidden) |= _PAGE_NX; +/* + * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS + * based config access (CONFIG_PCI_GOBIOS) support. + */ +#define BIOS_PFN PFN_DOWN(BIOS_BEGIN) +#define BIOS_PFN_END PFN_DOWN(BIOS_END - 1) + +static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) +{ + if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END)) + return _PAGE_NX; + return 0; +} +#else +static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) +{ + return 0; +} #endif - /* - * The kernel text needs to be executable for obvious reasons - * Does not cover __inittext since that is gone later on. On - * 64bit we do not enforce !NX on the low mapping - */ - if (within(address, (unsigned long)_text, (unsigned long)_etext)) - pgprot_val(forbidden) |= _PAGE_NX; +/* + * The .rodata section needs to be read-only. Using the pfn catches all + * aliases. This also includes __ro_after_init, so do not enforce until + * kernel_set_to_readonly is true. + */ +static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn) +{ + unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata)); /* - * The .rodata section needs to be read-only. Using the pfn - * catches all aliases. + * Note: __end_rodata is at page aligned and not inclusive, so + * subtract 1 to get the last enforced PFN in the rodata area. */ - if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT, - __pa_symbol(__end_rodata) >> PAGE_SHIFT)) - pgprot_val(forbidden) |= _PAGE_RW; + epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1; + + if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro)) + return _PAGE_RW; + return 0; +} + +/* + * Protect kernel text against becoming non executable by forbidding + * _PAGE_NX. This protects only the high kernel mapping (_text -> _etext) + * out of which the kernel actually executes. Do not protect the low + * mapping. + * + * This does not cover __inittext since that is gone after boot. + */ +static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end) +{ + unsigned long t_end = (unsigned long)_etext - 1; + unsigned long t_start = (unsigned long)_text; + + if (overlaps(start, end, t_start, t_end)) + return _PAGE_NX; + return 0; +} #if defined(CONFIG_X86_64) +/* + * 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. + */ +static pgprotval_t protect_kernel_text_ro(unsigned long start, + unsigned long end) +{ + unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1; + unsigned long t_start = (unsigned long)_text; + unsigned int level; + + if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end)) + return 0; /* - * 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. + * 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 will preserve the large page mappings for kernel text/data - * at no extra cost. + * This also fixes the Linux Xen paravirt guest boot failure caused + * by 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, + * so the protections for kernel text and identity mappings have to + * be the same. */ - 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; - } + if (lookup_address(start, &level) && (level != PG_LEVEL_4K)) + return _PAGE_RW; + return 0; +} +#else +static pgprotval_t protect_kernel_text_ro(unsigned long start, + unsigned long end) +{ + return 0; +} #endif - prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); +static inline bool conflicts(pgprot_t prot, pgprotval_t val) +{ + return (pgprot_val(prot) & ~val) != pgprot_val(prot); +} - return prot; +static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val, + unsigned long start, unsigned long end, + unsigned long pfn, const char *txt) +{ + static const char *lvltxt[] = { + [CPA_CONFLICT] = "conflict", + [CPA_PROTECT] = "protect", + [CPA_DETECT] = "detect", + }; + + if (warnlvl > cpa_warn_level || !conflicts(prot, val)) + return; + + pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n", + lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot), + (unsigned long long)val); +} + +/* + * 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 + * right (again, ioremap() on BIOS memory is not uncommon) so this function + * checks and fixes these known static required protection bits. + */ +static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, + unsigned long pfn, unsigned long npg, + int warnlvl) +{ + pgprotval_t forbidden, res; + unsigned long end; + + /* + * There is no point in checking RW/NX conflicts when the requested + * mapping is setting the page !PRESENT. + */ + if (!(pgprot_val(prot) & _PAGE_PRESENT)) + return prot; + + /* Operate on the virtual address */ + end = start + npg * PAGE_SIZE - 1; + + res = protect_kernel_text(start, end); + check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX"); + forbidden = res; + + res = protect_kernel_text_ro(start, end); + check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO"); + forbidden |= res; + + /* Check the PFN directly */ + res = protect_pci_bios(pfn, pfn + npg - 1); + check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX"); + forbidden |= res; + + res = protect_rodata(pfn, pfn + npg - 1); + check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO"); + forbidden |= res; + + return __pgprot(pgprot_val(prot) & ~forbidden); } /* @@ -401,18 +590,18 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, */ pte_t *lookup_address(unsigned long address, unsigned int *level) { - return lookup_address_in_pgd(pgd_offset_k(address), address, 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) + if (cpa->pgd) return lookup_address_in_pgd(cpa->pgd + pgd_index(address), address, level); - return lookup_address(address, level); + return lookup_address(address, level); } /* @@ -512,40 +701,52 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) #endif } -static int -try_preserve_large_page(pte_t *kpte, unsigned long address, - struct cpa_data *cpa) +static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot) { - unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn; + /* + * _PAGE_GLOBAL means "global page" for present PTEs. + * But, it is also used to indicate _PAGE_PROTNONE + * for non-present PTEs. + * + * This ensures that a _PAGE_GLOBAL PTE going from + * present to non-present is not confused as + * _PAGE_PROTNONE. + */ + if (!(pgprot_val(prot) & _PAGE_PRESENT)) + pgprot_val(prot) &= ~_PAGE_GLOBAL; + + return prot; +} + +static int __should_split_large_page(pte_t *kpte, unsigned long address, + struct cpa_data *cpa) +{ + unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn; + pgprot_t old_prot, new_prot, req_prot, chk_prot; pte_t new_pte, old_pte, *tmp; - pgprot_t old_prot, new_prot, req_prot; - int i, do_split = 1; enum pg_level level; - 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_cpa(cpa, address, &level); if (tmp != kpte) - goto out_unlock; + return 1; switch (level) { case PG_LEVEL_2M: old_prot = pmd_pgprot(*(pmd_t *)kpte); old_pfn = pmd_pfn(*(pmd_t *)kpte); + cpa_inc_2m_checked(); break; case PG_LEVEL_1G: old_prot = pud_pgprot(*(pud_t *)kpte); old_pfn = pud_pfn(*(pud_t *)kpte); + cpa_inc_1g_checked(); break; default: - do_split = -EINVAL; - goto out_unlock; + return -EINVAL; } psize = page_level_size(level); @@ -555,8 +756,8 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * Calculate the number of pages, which fit into this large * page starting at address: */ - nextpage_addr = (address + psize) & pmask; - numpages = (nextpage_addr - address) >> PAGE_SHIFT; + lpaddr = (address + psize) & pmask; + numpages = (lpaddr - address) >> PAGE_SHIFT; if (numpages < cpa->numpages) cpa->numpages = numpages; @@ -566,6 +767,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * up accordingly. */ old_pte = *kpte; + /* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */ req_prot = pgprot_large_2_4k(old_prot); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); @@ -577,86 +779,147 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * different bit positions in the two formats. */ req_prot = pgprot_4k_2_large(req_prot); - - /* - * 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. - */ + req_prot = pgprot_clear_protnone_bits(req_prot); 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); + pgprot_val(req_prot) |= _PAGE_PSE; /* - * old_pfn points to the large page base pfn. So we need - * to add the offset of the virtual address: + * old_pfn points to the large page base pfn. So we need to add the + * offset of the virtual address: */ pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; - new_prot = static_protections(req_prot, address, pfn); + /* + * Calculate the large page base address and the number of 4K pages + * in the large page + */ + lpaddr = address & pmask; + numpages = psize >> PAGE_SHIFT; /* - * 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: + * Sanity check that the existing mapping is correct versus the static + * protections. static_protections() guards against !PRESENT, so no + * extra conditional required here. */ - addr = address & pmask; - pfn = old_pfn; - for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { - pgprot_t chk_prot = static_protections(req_prot, addr, pfn); + chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages, + CPA_CONFLICT); - if (pgprot_val(chk_prot) != pgprot_val(new_prot)) - goto out_unlock; + if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) { + /* + * Split the large page and tell the split code to + * enforce static protections. + */ + cpa->force_static_prot = 1; + return 1; } /* - * If there are no changes, return. maxpages has been updated - * above: + * Optimization: If the requested pgprot is the same as the current + * pgprot, then the large page can be preserved and no updates are + * required independent of alignment and length of the requested + * range. The above already established that the current pgprot is + * correct, which in consequence makes the requested pgprot correct + * as well if it is the same. The static protection scan below will + * not come to a different conclusion. */ - if (pgprot_val(new_prot) == pgprot_val(old_prot)) { - do_split = 0; - goto out_unlock; + if (pgprot_val(req_prot) == pgprot_val(old_prot)) { + cpa_inc_lp_sameprot(level); + return 0; } /* - * We need to change the attributes. Check, whether we can - * change the large page in one go. We request a split, when - * the address is not aligned and the number of pages is - * smaller than the number of pages in the large page. Note - * that we limited the number of possible pages already to - * the number of pages in the large page. + * If the requested range does not cover the full page, split it up */ - 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(old_pfn, new_prot); - __set_pmd_pte(kpte, address, new_pte); - cpa->flags |= CPA_FLUSHTLB; - do_split = 0; - } + if (address != lpaddr || cpa->numpages != numpages) + return 1; + + /* + * Check whether the requested pgprot is conflicting with a static + * protection requirement in the large page. + */ + new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, + CPA_DETECT); + + /* + * If there is a conflict, split the large page. + * + * There used to be a 4k wise evaluation trying really hard to + * preserve the large pages, but experimentation has shown, that this + * does not help at all. There might be corner cases which would + * preserve one large page occasionally, but it's really not worth the + * extra code and cycles for the common case. + */ + if (pgprot_val(req_prot) != pgprot_val(new_prot)) + return 1; + + /* All checks passed. Update the large page mapping. */ + new_pte = pfn_pte(old_pfn, new_prot); + __set_pmd_pte(kpte, address, new_pte); + cpa->flags |= CPA_FLUSHTLB; + cpa_inc_lp_preserved(level); + return 0; +} + +static int should_split_large_page(pte_t *kpte, unsigned long address, + struct cpa_data *cpa) +{ + int do_split; -out_unlock: + if (cpa->force_split) + return 1; + + spin_lock(&pgd_lock); + do_split = __should_split_large_page(kpte, address, cpa); spin_unlock(&pgd_lock); return do_split; } +static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn, + pgprot_t ref_prot, unsigned long address, + unsigned long size) +{ + unsigned int npg = PFN_DOWN(size); + pgprot_t prot; + + /* + * If should_split_large_page() discovered an inconsistent mapping, + * remove the invalid protection in the split mapping. + */ + if (!cpa->force_static_prot) + goto set; + + prot = static_protections(ref_prot, address, pfn, npg, CPA_PROTECT); + + if (pgprot_val(prot) == pgprot_val(ref_prot)) + goto set; + + /* + * If this is splitting a PMD, fix it up. PUD splits cannot be + * fixed trivially as that would require to rescan the newly + * installed PMD mappings after returning from split_large_page() + * so an eventual further split can allocate the necessary PTE + * pages. Warn for now and revisit it in case this actually + * happens. + */ + if (size == PAGE_SIZE) + ref_prot = prot; + else + pr_warn_once("CPA: Cannot fixup static protections for PUD split\n"); +set: + set_pte(pte, pfn_pte(pfn, ref_prot)); +} + static int __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, struct page *base) { + unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; pte_t *pbase = (pte_t *)page_address(base); - unsigned long ref_pfn, pfn, pfninc = 1; unsigned int i, level; - pte_t *tmp; pgprot_t ref_prot; + pte_t *tmp; spin_lock(&pgd_lock); /* @@ -674,16 +937,22 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, switch (level) { case PG_LEVEL_2M: ref_prot = pmd_pgprot(*(pmd_t *)kpte); - /* clear PSE and promote PAT bit to correct position */ + /* + * Clear PSE (aka _PAGE_PAT) and move + * PAT bit to correct position. + */ ref_prot = pgprot_large_2_4k(ref_prot); ref_pfn = pmd_pfn(*(pmd_t *)kpte); + lpaddr = address & PMD_MASK; + lpinc = PAGE_SIZE; break; case PG_LEVEL_1G: ref_prot = pud_pgprot(*(pud_t *)kpte); ref_pfn = pud_pfn(*(pud_t *)kpte); pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; - + lpaddr = address & PUD_MASK; + lpinc = PMD_SIZE; /* * Clear the PSE flags if the PRESENT flag is not set * otherwise pmd_present/pmd_huge will return true @@ -698,23 +967,14 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, return 1; } - /* - * 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; + ref_prot = pgprot_clear_protnone_bits(ref_prot); /* * Get the target pfn from the original entry: */ pfn = ref_pfn; - for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) - set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); + for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc) + split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc); if (virt_addr_valid(address)) { unsigned long pfn = PFN_DOWN(__pa(address)); @@ -733,14 +993,24 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); /* - * Intel Atom errata AAH41 workaround. + * Do a global flush tlb after splitting the large page + * and before we do the actual change page attribute in the PTE. * - * 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. + * Without 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(); + flush_tlb_all(); spin_unlock(&pgd_lock); return 0; @@ -930,19 +1200,7 @@ static void populate_pte(struct cpa_data *cpa, pte = pte_offset_kernel(pmd, start); - /* - * 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(pgprot) & _PAGE_PRESENT) - pgprot_val(pgprot) |= _PAGE_GLOBAL; - else - pgprot_val(pgprot) &= ~_PAGE_GLOBAL; - - pgprot = canon_pgprot(pgprot); + pgprot = pgprot_clear_protnone_bits(pgprot); while (num_pages-- && start < end) { set_pte(pte, pfn_pte(cpa->pfn, pgprot)); @@ -1004,8 +1262,8 @@ static long populate_pmd(struct cpa_data *cpa, pmd = pmd_offset(pud, start); - set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pmd_pgprot))); + set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn, + canon_pgprot(pmd_pgprot)))); start += PMD_SIZE; cpa->pfn += PMD_SIZE >> PAGE_SHIFT; @@ -1077,8 +1335,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, * Map everything starting from the Gb boundary, possibly with 1G pages */ while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { - set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pud_pgprot))); + set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, + canon_pgprot(pud_pgprot)))); start += PUD_SIZE; cpa->pfn += PUD_SIZE >> PAGE_SHIFT; @@ -1190,6 +1448,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, cpa->numpages = 1; cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; return 0; + + } else if (__cpa_pfn_in_highmap(cpa->pfn)) { + /* Faults in the highmap are OK, so do not warn: */ + return -EFAULT; } else { WARN(1, KERN_WARNING "CPA: called for zero pte. " "vaddr = %lx cpa->vaddr = %lx\n", vaddr, @@ -1232,26 +1494,18 @@ repeat: pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); - new_prot = static_protections(new_prot, address, pfn); + cpa_inc_4k_install(); + new_prot = static_protections(new_prot, address, pfn, 1, + CPA_PROTECT); - /* - * 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; + new_prot = pgprot_clear_protnone_bits(new_prot); /* * 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 */ - new_pte = pfn_pte(pfn, canon_pgprot(new_prot)); + new_pte = pfn_pte(pfn, new_prot); cpa->pfn = pfn; /* * Do we really change anything ? @@ -1268,7 +1522,7 @@ repeat: * Check, whether we can keep the large page intact * and just change the pte: */ - do_split = try_preserve_large_page(kpte, address, cpa); + do_split = should_split_large_page(kpte, address, cpa); /* * When the range fits into the existing large page, * return. cp->numpages and cpa->tlbflush have been updated in @@ -1281,28 +1535,8 @@ repeat: * We have to split the large page: */ err = split_large_page(cpa, kpte, address); - if (!err) { - /* - * 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(); + if (!err) goto repeat; - } return err; } @@ -1352,8 +1586,7 @@ static int cpa_process_alias(struct cpa_data *cpa) * to touch the high mapped kernel as well: */ if (!within(vaddr, (unsigned long)_text, _brk_end) && - within_inclusive(cpa->pfn, highmap_start_pfn(), - highmap_end_pfn())) { + __cpa_pfn_in_highmap(cpa->pfn)) { unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa = *cpa; @@ -1416,6 +1649,29 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) return 0; } +/* + * Machine check recovery code needs to change cache mode of poisoned + * pages to UC to avoid speculative access logging another error. But + * passing the address of the 1:1 mapping to set_memory_uc() is a fine + * way to encourage a speculative access. So we cheat and flip the top + * bit of the address. This works fine for the code that updates the + * page tables. But at the end of the process we need to flush the cache + * and the non-canonical address causes a #GP fault when used by the + * CLFLUSH instruction. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long make_addr_canonical_again(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + + 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, @@ -1428,11 +1684,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, memset(&cpa, 0, sizeof(cpa)); /* - * Check, if we are requested to change a not supported - * feature: + * Check, if we are requested to set a not supported + * feature. Clearing non-supported features is OK. */ mask_set = canon_pgprot(mask_set); - mask_clr = canon_pgprot(mask_clr); + if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split) return 0; @@ -1461,7 +1717,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * Save address for cache flush. *addr is modified in the call * to __change_page_attr_set_clr() below. */ - baddr = *addr; + baddr = make_addr_canonical_again(*addr); } /* Must avoid aliasing mappings in the highmem code */ @@ -1483,6 +1739,9 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* No alias checking for _NX bit modifications */ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; + /* Has caller explicitly disabled alias checking? */ + if (in_flag & CPA_NO_CHECK_ALIAS) + checkalias = 0; ret = __change_page_attr_set_clr(&cpa, checkalias); @@ -1499,19 +1758,19 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cache = !!pgprot2cachemode(mask_set); /* - * 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 - * WBINVD): + * On error; flush everything to be sure. */ - if (!ret && boot_cpu_has(X86_FEATURE_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 + if (ret) { cpa_flush_all(cache); + goto out; + } + + if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { + cpa_flush_array(baddr, addr, numpages, cache, + cpa.flags, pages); + } else { + cpa_flush_range(baddr, numpages, cache); + } out: return ret; @@ -1769,12 +2028,33 @@ int set_memory_np(unsigned long addr, int numpages) return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); } +int set_memory_np_noalias(unsigned long addr, int numpages) +{ + int cpa_flags = CPA_NO_CHECK_ALIAS; + + return change_page_attr_set_clr(&addr, numpages, __pgprot(0), + __pgprot(_PAGE_PRESENT), 0, + cpa_flags, NULL); +} + 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_memory_nonglobal(unsigned long addr, int numpages) +{ + return change_page_attr_clear(&addr, numpages, + __pgprot(_PAGE_GLOBAL), 0); +} + +int set_memory_global(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_GLOBAL), 0); +} + static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) { struct cpa_data cpa; @@ -1805,10 +2085,7 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) /* * Before changing the encryption attribute, we need to flush caches. */ - if (static_cpu_has(X86_FEATURE_CLFLUSH)) - cpa_flush_range(start, numpages, 1); - else - cpa_flush_all(1); + cpa_flush_range(start, numpages, 1); ret = __change_page_attr_set_clr(&cpa, 1); @@ -1819,10 +2096,7 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) * in case TLB flushing gets optimized in the cpa_flush_range() * path use the same logic as above. */ - if (static_cpu_has(X86_FEATURE_CLFLUSH)) - cpa_flush_range(start, numpages, 0); - else - cpa_flush_all(0); + cpa_flush_range(start, numpages, 0); return ret; } @@ -2035,9 +2309,13 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) /* * We should perform an IPI and flush all tlbs, - * but that can deadlock->flush only current cpu: + * but that can deadlock->flush only current cpu. + * Preemption needs to be disabled around __flush_tlb_all() due to + * CR3 reload in __native_flush_tlb(). */ + preempt_disable(); __flush_tlb_all(); + preempt_enable(); arch_flush_lazy_mmu_mode(); } |