powerpc ioremap_prot

This adds ioremap_prot and pte_pgprot() so that one can extract protection
bits from a PTE and use them to ioremap_prot() (in order to support ptrace
of VM_IO | VM_PFNMAP as per Rik's patch).

This moves a couple of flag checks around in the ioremap implementations
of arch/powerpc.  There's a side effect of allowing non-cacheable and
non-guarded mappings on ppc32 which before would always have _PAGE_GUARDED
set whenever _PAGE_NO_CACHE is.

(standard ioremap will still set _PAGE_GUARDED, but ioremap_prot will be
capable of setting such a non guarded mapping).

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Dave Airlie <airlied@linux.ie>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 64 insertions, 7 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4d7e2ba10bae..a487671c282f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -111,6 +111,7 @@ config PPC
         select HAVE_DYNAMIC_FTRACE
         select HAVE_FTRACE
         select HAVE_IDE
+        select HAVE_IOREMAP_PROT
         select HAVE_KPROBES
         select HAVE_ARCH_KGDB
         select HAVE_KRETPROBES
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index c7584072dfcc..2001abdb1912 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -145,13 +145,20 @@ void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 void __iomem *
 ioremap(phys_addr_t addr, unsigned long size)
 {
-        return __ioremap(addr, size, _PAGE_NO_CACHE);
+        return __ioremap(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED);
 }
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *
 ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
+        /* writeable implies dirty for kernel addresses */
+        if (flags & _PAGE_RW)
+                flags |= _PAGE_DIRTY | _PAGE_HWWRITE;
+
+        /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
+        flags &= ~(_PAGE_USER | _PAGE_EXEC | _PAGE_HWEXEC);
+
         return __ioremap(addr, size, flags);
 }
 EXPORT_SYMBOL(ioremap_flags);
@@ -163,6 +170,14 @@ __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
         phys_addr_t p;
         int err;
 
+        /* Make sure we have the base flags */
+        if ((flags & _PAGE_PRESENT) == 0)
+                flags |= _PAGE_KERNEL;
+
+        /* Non-cacheable page cannot be coherent */
+        if (flags & _PAGE_NO_CACHE)
+                flags &= ~_PAGE_COHERENT;
+
         /*
          * Choose an address to map it to.
          * Once the vmalloc system is running, we use it.
@@ -219,11 +234,6 @@ __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
                 v = (ioremap_bot -= size);
         }
 
-        if ((flags & _PAGE_PRESENT) == 0)
-                flags |= _PAGE_KERNEL;
-        if (flags & _PAGE_NO_CACHE)
-                flags |= _PAGE_GUARDED;
-
         /*
          * Should check if it is a candidate for a BAT mapping
          */
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 3ef0ad2f9ca0..365e61ae5dbc 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -107,9 +107,18 @@ void __iomem * __ioremap_at(phys_addr_t pa, void *ea, unsigned long size,
 {
         unsigned long i;
 
+        /* Make sure we have the base flags */
         if ((flags & _PAGE_PRESENT) == 0)
                 flags |= pgprot_val(PAGE_KERNEL);
 
+        /* Non-cacheable page cannot be coherent */
+        if (flags & _PAGE_NO_CACHE)
+                flags &= ~_PAGE_COHERENT;
+
+        /* We don't support the 4K PFN hack with ioremap */
+        if (flags & _PAGE_4K_PFN)
+                return NULL;
+
         WARN_ON(pa & ~PAGE_MASK);
         WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
         WARN_ON(size & ~PAGE_MASK);
@@ -190,6 +199,13 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size)
 void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
                              unsigned long flags)
 {
+        /* writeable implies dirty for kernel addresses */
+        if (flags & _PAGE_RW)
+                flags |= _PAGE_DIRTY;
+
+        /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
+        flags &= ~(_PAGE_USER | _PAGE_EXEC);
+
         if (ppc_md.ioremap)
                 return ppc_md.ioremap(addr, size, flags);
         return __ioremap(addr, size, flags);
diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h
index 8b627823f5f9..77c7fa025e65 100644
--- a/include/asm-powerpc/io.h
+++ b/include/asm-powerpc/io.h
@@ -617,7 +617,8 @@ static inline void iosync(void)
  *   and can be hooked by the platform via ppc_md
  *
  * * ioremap_flags allows to specify the page flags as an argument and can
- *   also be hooked by the platform via ppc_md
+ *   also be hooked by the platform via ppc_md. ioremap_prot is the exact
+ *   same thing as ioremap_flags.
  *
  * * ioremap_nocache is identical to ioremap
  *
@@ -639,6 +640,8 @@ extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
 extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size,
                                    unsigned long flags);
 #define ioremap_nocache(addr, size)     ioremap((addr), (size))
+#define ioremap_prot(addr, size, prot)  ioremap_flags((addr), (size), (prot))
+
 extern void iounmap(volatile void __iomem *addr);
 
 extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
diff --git a/include/asm-powerpc/pgtable-4k.h b/include/asm-powerpc/pgtable-4k.h
index fd2090dc1dce..c9601dfb4a1e 100644
--- a/include/asm-powerpc/pgtable-4k.h
+++ b/include/asm-powerpc/pgtable-4k.h
@@ -51,6 +51,9 @@
 #define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \
                          _PAGE_SECONDARY | _PAGE_GROUP_IX)
 
+/* There is no 4K PFN hack on 4K pages */
+#define _PAGE_4K_PFN    0
+
 /* PAGE_MASK gives the right answer below, but only by accident */
 /* It should be preserving the high 48 bits and then specifically */
 /* preserving _PAGE_SECONDARY | _PAGE_GROUP_IX */
diff --git a/include/asm-powerpc/pgtable-ppc32.h b/include/asm-powerpc/pgtable-ppc32.h
index 3a96d001cb75..bdbab72f3ebc 100644
--- a/include/asm-powerpc/pgtable-ppc32.h
+++ b/include/asm-powerpc/pgtable-ppc32.h
@@ -395,6 +395,12 @@ extern int icache_44x_need_flush;
 #ifndef _PAGE_EXEC
 #define _PAGE_EXEC      0
 #endif
+#ifndef _PAGE_ENDIAN
+#define _PAGE_ENDIAN    0
+#endif
+#ifndef _PAGE_COHERENT
+#define _PAGE_COHERENT  0
+#endif
 #ifndef _PMD_PRESENT_MASK
 #define _PMD_PRESENT_MASK       _PMD_PRESENT
 #endif
@@ -405,6 +411,12 @@ extern int icache_44x_need_flush;
 
 #define _PAGE_CHG_MASK  (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
 
+
+#define PAGE_PROT_BITS  __pgprot(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
+                                 _PAGE_WRITETHRU | _PAGE_ENDIAN | \
+                                 _PAGE_USER | _PAGE_ACCESSED | \
+                                 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \
+                                 _PAGE_EXEC | _PAGE_HWEXEC)
 /*
  * Note: the _PAGE_COHERENT bit automatically gets set in the hardware
  * PTE if CONFIG_SMP is defined (hash_page does this); there is no need
@@ -538,6 +550,10 @@ static inline pte_t pte_mkyoung(pte_t pte) {
         pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkspecial(pte_t pte) {
         return pte; }
+static inline unsigned long pte_pgprot(pte_t pte)
+{
+        return __pgprot(pte_val(pte)) & PAGE_PROT_BITS;
+}
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/include/asm-powerpc/pgtable-ppc64.h b/include/asm-powerpc/pgtable-ppc64.h
index ab98a9c80b28..ba8000352b9a 100644
--- a/include/asm-powerpc/pgtable-ppc64.h
+++ b/include/asm-powerpc/pgtable-ppc64.h
@@ -117,6 +117,10 @@
 #define PAGE_AGP        __pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_NO_CACHE)
 #define HAVE_PAGE_AGP
 
+#define PAGE_PROT_BITS  __pgprot(_PAGE_GUARDED | _PAGE_COHERENT | \
+                                 _PAGE_NO_CACHE | _PAGE_WRITETHRU | \
+                                 _PAGE_4K_PFN | _PAGE_RW | _PAGE_USER | \
+                                 _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_EXEC)
 /* PTEIDX nibble */
 #define _PTEIDX_SECONDARY       0x8
 #define _PTEIDX_GROUP_IX        0x7
@@ -262,6 +266,10 @@ static inline pte_t pte_mkhuge(pte_t pte) {
         return pte; }
 static inline pte_t pte_mkspecial(pte_t pte) {
         return pte; }
+static inline unsigned long pte_pgprot(pte_t pte)
+{
+        return __pgprot(pte_val(pte)) & PAGE_PROT_BITS;
+}
 
 /* Atomic PTE updates */
 static inline unsigned long pte_update(struct mm_struct *mm,