mm, dax: introduce pfn_t_special()

BugLink: http://bugs.launchpad.net/bugs/1751724
In support of removing the VM_MIXEDMAP indication from DAX VMAs,
introduce pfn_t_special() for drivers to indicate that _PAGE_SPECIAL
should be used for DAX ptes. This also helps identify drivers like
dccssblk that only want to use DAX in a read-only fashion without
get_user_pages() support.

Ideally we could delete axonram and dcssblk DAX support, but if we need
to keep it better make it explicit that axonram and dcssblk only support
a sub-set of DAX due to missing _PAGE_DEVMAP support.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
(cherry picked from commit 785a3fab4adbf91b2189c928a59ae219c54ba95e)
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>

diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 1b307c80b401083f50637daf1597f43ccabe70b9..cdbb0e59b3d31d287d9666369f2044d7b75cb3d5 100644 (file)
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -151,7 +151,7 @@ __axon_ram_direct_access(struct axon_ram_bank *bank, pgoff_t pgoff, long nr_page
        resource_size_t offset = pgoff * PAGE_SIZE;
 
        *kaddr = (void *) bank->io_addr + offset;
-       *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV);
+       *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV|PFN_SPECIAL);
        return (bank->size - offset) / PAGE_SIZE;
 }
 

diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 6aaefb78043696e658e36b6637b4e6dde59b5c83..9cae08b36b8022b590bdb550113212d102d94043 100644 (file)
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -916,7 +916,8 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 
        dev_sz = dev_info->end - dev_info->start + 1;
        *kaddr = (void *) dev_info->start + offset;
-       *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV);
+       *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset),
+                       PFN_DEV|PFN_SPECIAL);
 
        return (dev_sz - offset) / PAGE_SIZE;
 }

diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 43b1d7648e826260e193cdb0a49cb038e4896958..a03c2642a87c259c23e1157dfaf21d46080eec91 100644 (file)
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -15,8 +15,10 @@
 #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
 #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
 #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
+#define PFN_SPECIAL (1ULL << (BITS_PER_LONG_LONG - 5))
 
 #define PFN_FLAGS_TRACE \
+       { PFN_SPECIAL,  "SPECIAL" }, \
        { PFN_SG_CHAIN, "SG_CHAIN" }, \
        { PFN_SG_LAST,  "SG_LAST" }, \
        { PFN_DEV,      "DEV" }, \
@@ -120,4 +122,15 @@ pud_t pud_mkdevmap(pud_t pud);
 #endif
 #endif /* __HAVE_ARCH_PTE_DEVMAP */
 
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+static inline bool pfn_t_special(pfn_t pfn)
+{
+       return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL;
+}
+#else
+static inline bool pfn_t_special(pfn_t pfn)
+{
+       return false;
+}
+#endif /* __HAVE_ARCH_PTE_SPECIAL */
 #endif /* _LINUX_PFN_T_H_ */

diff --git a/mm/memory.c b/mm/memory.c
index 93e51ad41ba3f6f798c4dd844bd178da90f3bbfa..54f6aab212c4a2dd96efdfe2afca08dd6d58f598 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1897,12 +1897,26 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_pfn_prot);
 
+static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
+{
+       /* these checks mirror the abort conditions in vm_normal_page */
+       if (vma->vm_flags & VM_MIXEDMAP)
+               return true;
+       if (pfn_t_devmap(pfn))
+               return true;
+       if (pfn_t_special(pfn))
+               return true;
+       if (is_zero_pfn(pfn_t_to_pfn(pfn)))
+               return true;
+       return false;
+}
+
 static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
                        pfn_t pfn, bool mkwrite)
 {
        pgprot_t pgprot = vma->vm_page_prot;
 
-       BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
+       BUG_ON(!vm_mixed_ok(vma, pfn));
 
        if (addr < vma->vm_start || addr >= vma->vm_end)
                return -EFAULT;