mm/vmalloc: add interfaces to free unmapped page table

On architectures with CONFIG_HAVE_ARCH_HUGE_VMAP set, ioremap() may
create pud/pmd mappings.  A kernel panic was observed on arm64 systems
with Cortex-A75 in the following steps as described by Hanjun Guo.

 1. ioremap a 4K size, valid page table will build,
 2. iounmap it, pte0 will set to 0;
 3. ioremap the same address with 2M size, pgd/pmd is unchanged,
    then set the a new value for pmd;
 4. pte0 is leaked;
 5. CPU may meet exception because the old pmd is still in TLB,
    which will lead to kernel panic.

This panic is not reproducible on x86.  INVLPG, called from iounmap,
purges all levels of entries associated with purged address on x86.  x86
still has memory leak.

The patch changes the ioremap path to free unmapped page table(s) since
doing so in the unmap path has the following issues:

 - The iounmap() path is shared with vunmap(). Since vmap() only
   supports pte mappings, making vunmap() to free a pte page is an
   overhead for regular vmap users as they do not need a pte page freed
   up.

 - Checking if all entries in a pte page are cleared in the unmap path
   is racy, and serializing this check is expensive.

 - The unmap path calls free_vmap_area_noflush() to do lazy TLB purges.
   Clearing a pud/pmd entry before the lazy TLB purges needs extra TLB
   purge.

Add two interfaces, pud_free_pmd_page() and pmd_free_pte_page(), which
clear a given pud/pmd entry and free up a page for the lower level
entries.

This patch implements their stub functions on x86 and arm64, which work
as workaround.

[[email protected]: fix typo in pmd_free_pte_page() stub]
Link: http://lkml.kernel.org/r/[email protected]
Fixes: e61ce6a ("mm: change ioremap to set up huge I/O mappings")
Reported-by: Lei Li <[email protected]>
Signed-off-by: Toshi Kani <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Wang Xuefeng <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Hanjun Guo <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Chintan Pandya <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/arm64/mm/mmu.c

@@ -972,3 +972,13 @@ int pmd_clear_huge(pmd_t *pmdp)
 	pmd_clear(pmdp);
 	return 1;
 }
+
+int pud_free_pmd_page(pud_t *pud)
+{
+	return pud_none(*pud);
+}
+
+int pmd_free_pte_page(pmd_t *pmd)
+{
+	return pmd_none(*pmd);
+}

arch/x86/mm/pgtable.c

@@ -702,4 +702,28 @@ int pmd_clear_huge(pmd_t *pmd)
 
 	return 0;
 }
+
+/**
+ * pud_free_pmd_page - Clear pud entry and free pmd page.
+ * @pud: Pointer to a PUD.
+ *
+ * Context: The pud range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pud_free_pmd_page(pud_t *pud)
+{
+	return pud_none(*pud);
+}
+
+/**
+ * pmd_free_pte_page - Clear pmd entry and free pte page.
+ * @pmd: Pointer to a PMD.
+ *
+ * Context: The pmd range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pmd_free_pte_page(pmd_t *pmd)
+{
+	return pmd_none(*pmd);
+}
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

include/asm-generic/pgtable.h

@@ -983,6 +983,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
+int pud_free_pmd_page(pud_t *pud);
+int pmd_free_pte_page(pmd_t *pmd);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -1008,6 +1010,14 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 {
 	return 0;
 }
+static inline int pud_free_pmd_page(pud_t *pud)
+{
+	return 0;
+}
+static inline int pmd_free_pte_page(pmd_t *pmd)
+{
+	return 0;
+}
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
 
 #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE

lib/ioremap.c

@@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 
 		if (ioremap_pmd_enabled() &&
 		    ((next - addr) == PMD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PMD_SIZE)) {
+		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
+		    pmd_free_pte_page(pmd)) {
 			if (pmd_set_huge(pmd, phys_addr + addr, prot))
 				continue;
 		}
@@ -117,7 +118,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 
 		if (ioremap_pud_enabled() &&
 		    ((next - addr) == PUD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PUD_SIZE)) {
+		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
+		    pud_free_pmd_page(pud)) {
 			if (pud_set_huge(pud, phys_addr + addr, prot))
 				continue;
 		}