sparc64: Support transparent huge pages.

This is relatively easy since PMD's now cover exactly 4MB of memory.

Our PMD entries are 32-bits each, so we use a special encoding.  The
lowest bit, PMD_ISHUGE, determines the interpretation.  This is possible
because sparc64's page tables are purely software entities so we can use
whatever encoding scheme we want.  We just have to make the TLB miss
assembler page table walkers aware of the layout.

set_pmd_at() works much like set_pte_at() but it has to operate in two
page from a table of non-huge PTEs, so we have to queue up TLB flushes
based upon what mappings are valid in the PTE table.  In the second regime
we are going from huge-page to non-huge-page, and in that case we need
only queue up a single TLB flush to push out the huge page mapping.

We still have 5 bits remaining in the huge PMD encoding so we can very
likely support any new pieces of THP state tracking that might get added
in the future.

With lots of help from Johannes Weiner.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 87 insertions, 7 deletions

diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index ef8cd1a174f..b4c258de444 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -157,10 +157,86 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	add		REG1, REG2, REG1;
 
-	/* Do a user page table walk in MMU globals.  Leaves physical PTE
-	 * pointer in REG1.  Jumps to FAIL_LABEL on early page table walk
-	 * termination.  Physical base of page tables is in PHYS_PGD which
-	 * will not be modified.
+	/* This macro exists only to make the PMD translator below easier
+	 * to read.  It hides the ELF section switch for the sun4v code
+	 * patching.
+	 */
+#define OR_PTE_BIT(REG, NAME)				\
+661:	or		REG, _PAGE_##NAME##_4U, REG;	\
+	.section	.sun4v_1insn_patch, "ax";	\
+	.word		661b;				\
+	or		REG, _PAGE_##NAME##_4V, REG;	\
+	.previous;
+
+	/* Load into REG the PTE value for VALID, CACHE, and SZHUGE.  */
+#define BUILD_PTE_VALID_SZHUGE_CACHE(REG)				   \
+661:	sethi		%uhi(_PAGE_VALID|_PAGE_SZHUGE_4U), REG;		   \
+	.section	.sun4v_1insn_patch, "ax";			   \
+	.word		661b;						   \
+	sethi		%uhi(_PAGE_VALID), REG;				   \
+	.previous;							   \
+	sllx		REG, 32, REG;					   \
+661:	or		REG, _PAGE_CP_4U|_PAGE_CV_4U, REG;		   \
+	.section	.sun4v_1insn_patch, "ax";			   \
+	.word		661b;						   \
+	or		REG, _PAGE_CP_4V|_PAGE_CV_4V|_PAGE_SZHUGE_4V, REG; \
+	.previous;
+
+	/* PMD has been loaded into REG1, interpret the value, seeing
+	 * if it is a HUGE PMD or a normal one.  If it is not valid
+	 * then jump to FAIL_LABEL.  If it is a HUGE PMD, and it
+	 * translates to a valid PTE, branch to PTE_LABEL.
+	 *
+	 * We translate the PMD by hand, one bit at a time,
+	 * constructing the huge PTE.
+	 *
+	 * So we construct the PTE in REG2 as follows:
+	 *
+	 * 1) Extract the PMD PFN from REG1 and place it into REG2.
+	 *
+	 * 2) Translate PMD protection bits in REG1 into REG2, one bit
+	 *    at a time using andcc tests on REG1 and OR's into REG2.
+	 *
+	 *    Only two bits to be concerned with here, EXEC and WRITE.
+	 *    Now REG1 is freed up and we can use it as a temporary.
+	 *
+	 * 3) Construct the VALID, CACHE, and page size PTE bits in
+	 *    REG1, OR with REG2 to form final PTE.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+	brz,pn		REG1, FAIL_LABEL;				      \
+	 andcc		REG1, PMD_ISHUGE, %g0;				      \
+	be,pt		%xcc, 700f;					      \
+	 and		REG1, PMD_HUGE_PRESENT|PMD_HUGE_ACCESSED, REG2;	      \
+	cmp		REG2, PMD_HUGE_PRESENT|PMD_HUGE_ACCESSED;	      \
+	bne,pn		%xcc, FAIL_LABEL;				      \
+	 andn		REG1, PMD_HUGE_PROTBITS, REG2;			      \
+	sllx		REG2, PMD_PADDR_SHIFT, REG2;			      \
+	/* REG2 now holds PFN << PAGE_SHIFT */				      \
+	andcc		REG1, PMD_HUGE_EXEC, %g0;			      \
+	bne,a,pt	%xcc, 1f;					      \
+	 OR_PTE_BIT(REG2, EXEC);					      \
+1:	andcc		REG1, PMD_HUGE_WRITE, %g0;			      \
+	bne,a,pt	%xcc, 1f;					      \
+	 OR_PTE_BIT(REG2, W);						      \
+	/* REG1 can now be clobbered, build final PTE */		      \
+1:	BUILD_PTE_VALID_SZHUGE_CACHE(REG1);				      \
+	ba,pt		%xcc, PTE_LABEL;				      \
+	 or		REG1, REG2, REG1;				      \
+700:
+#else
+#define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+	brz,pn		REG1, FAIL_LABEL; \
+	 nop;
+#endif
+
+	/* Do a user page table walk in MMU globals.  Leaves final,
+	 * valid, PTE value in REG1.  Jumps to FAIL_LABEL on early
+	 * page table walk termination or if the PTE is not valid.
+	 *
+	 * Physical base of page tables is in PHYS_PGD which will not
+	 * be modified.
 	 *
 	 * VADDR will not be clobbered, but REG1 and REG2 will.
 	 */
@@ -175,12 +251,16 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sllx		REG1, PGD_PADDR_SHIFT, REG1; \
 	andn		REG2, 0x3, REG2; \
 	lduwa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
-	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, 800f) \
+	sllx		VADDR, 64 - PMD_SHIFT, REG2; \
 	srlx		REG2, 64 - (PAGE_SHIFT - 1), REG2; \
 	sllx		REG1, PMD_PADDR_SHIFT, REG1; \
 	andn		REG2, 0x7, REG2; \
-	add		REG1, REG2, REG1;
+	add		REG1, REG2, REG1; \
+	ldxa		[REG1] ASI_PHYS_USE_EC, REG1; \
+	brgez,pn	REG1, FAIL_LABEL; \
+	 nop; \
+800:
 
 /* Lookup a OBP mapping on VADDR in the prom_trans[] table at TL>0.
  * If no entry is found, FAIL_LABEL will be branched to.  On success