mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in vmalloc_to_page

vmalloc_to_page returns NULL for addresses mapped by larger pages[*].
Whether or not a vmap is huge depends on the architecture details,
alignments, boot options, etc., which the caller can not be expected to
know.  Therefore HUGE_VMAP is a regression for vmalloc_to_page.

This change teaches vmalloc_to_page about larger pages, and returns the
struct page that corresponds to the offset within the large page.  This
makes the API agnostic to mapping implementation details.

[*] As explained by commit 029c54b095995 ("mm/vmalloc.c: huge-vmap:
    fail gracefully on unexpected huge vmap mappings")

[npiggin@gmail.com: sparc32: add stub pud_page define for walking huge vmalloc page tables]
Link: https://lkml.kernel.org/r/20210324232825.1157363-1-npiggin@gmail.com
Link: https://lkml.kernel.org/r/20210317062402.533919-3-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 632cdb9..a5cf79c 100644 (file)
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -321,6 +321,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
                pgprot_val(newprot));
 }
 
+/* only used by the huge vmap code, should never be called */
+#define pud_page(pud)                  NULL
+
 struct seq_file;
 void mmu_info(struct seq_file *m);
 

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 8c20670..ee865b6 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,7 +34,7 @@
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
 #include <linux/overflow.h>
-
+#include <linux/pgtable.h>
 #include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
@@ -343,7 +343,9 @@ int is_vmalloc_or_module_addr(const void *x)
 }
 
 /*
- * Walk a vmap address to the struct page it maps.
+ * Walk a vmap address to the struct page it maps. Huge vmap mappings will
+ * return the tail page that corresponds to the base page address, which
+ * matches small vmap mappings.
  */
 struct page *vmalloc_to_page(const void *vmalloc_addr)
 {
@@ -363,25 +365,33 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 
        if (pgd_none(*pgd))
                return NULL;
+       if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+               return NULL; /* XXX: no allowance for huge pgd */
+       if (WARN_ON_ONCE(pgd_bad(*pgd)))
+               return NULL;
+
        p4d = p4d_offset(pgd, addr);
        if (p4d_none(*p4d))
                return NULL;
-       pud = pud_offset(p4d, addr);
+       if (p4d_leaf(*p4d))
+               return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
+       if (WARN_ON_ONCE(p4d_bad(*p4d)))
+               return NULL;
 
-       /*
-        * Don't dereference bad PUD or PMD (below) entries. This will also
-        * identify huge mappings, which we may encounter on architectures
-        * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
-        * identified as vmalloc addresses by is_vmalloc_addr(), but are
-        * not [unambiguously] associated with a struct page, so there is
-        * no correct value to return for them.
-        */
-       WARN_ON_ONCE(pud_bad(*pud));
-       if (pud_none(*pud) || pud_bad(*pud))
+       pud = pud_offset(p4d, addr);
+       if (pud_none(*pud))
+               return NULL;
+       if (pud_leaf(*pud))
+               return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+       if (WARN_ON_ONCE(pud_bad(*pud)))
                return NULL;
+
        pmd = pmd_offset(pud, addr);
-       WARN_ON_ONCE(pmd_bad(*pmd));
-       if (pmd_none(*pmd) || pmd_bad(*pmd))
+       if (pmd_none(*pmd))
+               return NULL;
+       if (pmd_leaf(*pmd))
+               return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+       if (WARN_ON_ONCE(pmd_bad(*pmd)))
                return NULL;
 
        ptep = pte_offset_map(pmd, addr);
@@ -389,6 +399,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
        if (pte_present(pte))
                page = pte_page(pte);
        pte_unmap(ptep);
+
        return page;
 }
 EXPORT_SYMBOL(vmalloc_to_page);