Merge tag 'efi-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi into x86/efi

Pull EFI virtual mapping changes from Matt Fleming:

  * New static EFI runtime services virtual mapping layout which is
    groundwork for kexec support on EFI. (Borislav Petkov)

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 444 insertions, 17 deletions

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480c2d71..b3b19f46c016 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -30,6 +30,7 @@
  */
 struct cpa_data {
         unsigned long   *vaddr;
+        pgd_t           *pgd;
         pgprot_t        mask_set;
         pgprot_t        mask_clr;
         int             numpages;
@@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
         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.
- */
-pte_t *lookup_address(unsigned long address, unsigned int *level)
+static 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;
 
@@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
         return pte_offset_kernel(pmd, address);
 }
+
+/*
+ * 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()
@@ -437,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
          * 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;
 
@@ -543,7 +559,8 @@ out_unlock:
 }
 
 static int
-__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+                   struct page *base)
 {
         pte_t *pbase = (pte_t *)page_address(base);
         unsigned long pfn, pfninc = 1;
@@ -556,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
          * Check for races, another CPU might have split this page
          * up for us already:
          */
-        tmp = lookup_address(address, &level);
+        tmp = _lookup_address_cpa(cpa, address, &level);
         if (tmp != kpte) {
                 spin_unlock(&pgd_lock);
                 return 1;
@@ -632,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
         return 0;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+                            unsigned long address)
 {
         struct page *base;
 
@@ -644,15 +662,390 @@ static int split_large_page(pte_t *kpte, unsigned long address)
         if (!base)
                 return -ENOMEM;
 
-        if (__split_large_page(kpte, address, base))
+        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 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++;
+        }
+
+        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)
+{
+        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);
+
+        /*
+         * Not on a 2MB page boundary?
+         */
+        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++;
+        }
+
+        /*
+         * 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 void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+        pud_t *pud = pud_offset(pgd, start);
+
+        /*
+         * Not on a GB page boundary?
+         */
+        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);
+
+                start = pre_end;
+                pud++;
+        }
+
+        /*
+         * Try to unmap in 1G chunks?
+         */
+        while (end - start >= PUD_SIZE) {
+
+                if (pud_large(*pud))
+                        pud_clear(pud);
+                else
+                        unmap_pmd_range(pud, start, start + PUD_SIZE);
+
+                start += PUD_SIZE;
+                pud++;
+        }
+
+        /*
+         * 2M leftovers?
+         */
+        if (start < end)
+                unmap_pmd_range(pud, start, end);
+
+        /*
+         * No need to try to free the PUD page because we'll free it in
+         * populate_pgd's error path
+         */
+}
+
+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;
+
+        /*
+         * Not on a 2M boundary?
+         */
+        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);
+        bool allocd_pgd = false;
+        pgd_t *pgd_entry;
+        pud_t *pud = NULL;      /* shut up gcc */
+        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));
+                allocd_pgd = true;
+        }
+
+        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_pud_range(pgd_entry, addr,
+                                addr + (cpa->numpages << PAGE_SHIFT));
+
+                if (allocd_pgd) {
+                        /*
+                         * If I allocated this PUD page, I can just as well
+                         * free it in this error path.
+                         */
+                        pgd_clear(pgd_entry);
+                        free_page((unsigned long)pud);
+                }
+                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.
          */
@@ -697,7 +1090,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
         else
                 address = *cpa->vaddr;
 repeat:
-        kpte = lookup_address(address, &level);
+        kpte = _lookup_address_cpa(cpa, address, &level);
         if (!kpte)
                 return __cpa_process_fault(cpa, address, primary);
 
@@ -761,7 +1154,7 @@ repeat:
         /*
          * We have to split the large page:
          */
-        err = split_large_page(kpte, address);
+        err = split_large_page(cpa, kpte, address);
         if (!err) {
                 /*
                  * Do a global flush tlb after splitting the large page
@@ -910,6 +1303,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
         int ret, cache, checkalias;
         unsigned long baddr = 0;
 
+        memset(&cpa, 0, sizeof(cpa));
+
         /*
          * Check, if we are requested to change a not supported
          * feature:
@@ -1356,6 +1751,7 @@ static int __set_pages_p(struct page *page, int numpages)
 {
         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),
@@ -1374,6 +1770,7 @@ static int __set_pages_np(struct page *page, int numpages)
 {
         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),
@@ -1434,6 +1831,36 @@ 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;
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.