mm: introduce pte_special pte bit

s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory
model (which is more dynamic than most).  Instead, they had proposed to
implement it with an additional path through vm_normal_page(), using a bit in
the pte to determine whether or not the page should be refcounted:

vm_normal_page()
{
	...
        if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
                if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
			if (!mixedmap_refcount_pte(pte))
				return NULL;
#else
                        if (!pfn_valid(pfn))
                                return NULL;
#endif
                        goto out;
                }
	...
}

This is fine, however if we are allowed to use a bit in the pte to determine
refcountedness, we can use that to _completely_ replace all the vma based
schemes.  So instead of adding more cases to the already complex vma-based
scheme, we can have a clearly seperate and simple pte-based scheme (and get
slightly better code generation in the process):

vm_normal_page()
{
#ifdef s390
	if (!mixedmap_refcount_pte(pte))
		return NULL;
	return pte_page(pte);
#else
	...
#endif
}

And finally, we may rather make this concept usable by any architecture rather
than making it s390 only, so implement a new type of pte state for this.
Unfortunately the old vma based code must stay, because some architectures may
not be able to spare pte bits.  This makes vm_normal_page a little bit more
ugly than we would like, but the 2 cases are clearly seperate.

So introduce a pte_special pte state, and use it in mm/memory.c.  It is
currently a noop for all architectures, so this doesn't actually result in any
compiled code changes to mm/memory.o.

BTW:
I haven't put vm_normal_page() into arch code as-per an earlier suggestion.
The reason is that, regardless of where vm_normal_page is actually
implemented, the *abstraction* is still exactly the same. Also, while it
depends on whether the architecture has pte_special or not, that is the
only two possible cases, and it really isn't an arch specific function --
the role of the arch code should be to provide primitive functions and
accessors with which to build the core code; pte_special does that. We do
not want architectures to know or care about vm_normal_page itself, and
we definitely don't want them being able to invent something new there
out of sight of mm/ code. If we made vm_normal_page an arch function, then
we have to make vm_insert_mixed (next patch) an arch function too. So I
don't think moving it to arch code fundamentally improves any abstractions,
while it does practically make the code more difficult to follow, for both
mm and arch developers, and easier to misuse.

[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 9 insertions, 4 deletions

diff --git a/include/asm-sh/pgtable_32.h b/include/asm-sh/pgtable_32.h
index 3e3557c53c55..cbc731d35c25 100644
--- a/include/asm-sh/pgtable_32.h
+++ b/include/asm-sh/pgtable_32.h
@@ -326,6 +326,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 #define pte_dirty(pte)		((pte).pte_low & _PAGE_DIRTY)
 #define pte_young(pte)		((pte).pte_low & _PAGE_ACCESSED)
 #define pte_file(pte)		((pte).pte_low & _PAGE_FILE)
+#define pte_special(pte)	(0)
 
 #ifdef CONFIG_X2TLB
 #define pte_write(pte)		((pte).pte_high & _PAGE_EXT_USER_WRITE)
@@ -356,6 +357,8 @@ PTE_BIT_FUNC(low, mkdirty, |= _PAGE_DIRTY);
 PTE_BIT_FUNC(low, mkold, &= ~_PAGE_ACCESSED);
 PTE_BIT_FUNC(low, mkyoung, |= _PAGE_ACCESSED);
 
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
 /*
  * Macro and implementation to make a page protection as uncachable.
  */
diff --git a/include/asm-sh/pgtable_64.h b/include/asm-sh/pgtable_64.h
index f9dd9d311441..c78990cda557 100644
--- a/include/asm-sh/pgtable_64.h
+++ b/include/asm-sh/pgtable_64.h
@@ -254,10 +254,11 @@ extern void __handle_bad_pmd_kernel(pmd_t * pmd);
 /*
  * The following have defined behavior only work if pte_present() is true.
  */
-static inline int pte_dirty(pte_t pte){ return pte_val(pte) & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte){ return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_write(pte_t pte){ return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_dirty(pte_t pte)  { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)  { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_file(pte_t pte)   { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_write(pte_t pte)  { return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_special(pte_t pte){ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_WRITE)); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
@@ -266,6 +267,7 @@ static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) |
 static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 
 /*