s390/mm: change swap pte encoding and pgtable cleanup

After the file ptes have been removed the bit combination used to
encode non-linear mappings can be reused for the swap ptes. This
frees up a precious pte software bit. Reflect the change in the
swap encoding in the comments and do some cleanup while we are
at it.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

2 files changed, 97 insertions, 123 deletions

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1fba63997d50..fc642399b489 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -12,12 +12,9 @@
 #define _ASM_S390_PGTABLE_H
 
 /*
- * The Linux memory management assumes a three-level page table setup. For
- * s390 31 bit we "fold" the mid level into the top-level page table, so
- * that we physically have the same two-level page table as the s390 mmu
- * expects in 31 bit mode. For s390 64 bit we use three of the five levels
- * the hardware provides (region first and region second tables are not
- * used).
+ * The Linux memory management assumes a three-level page table setup.
+ * For s390 64 bit we use up to four of the five levels the hardware
+ * provides (region first tables are not used).
  *
  * The "pgd_xxx()" functions are trivial for a folded two-level
  * setup: the pgd is never bad, and a pmd always exists (as it's folded
@@ -101,8 +98,8 @@ extern unsigned long zero_page_mask;
 
 #ifndef __ASSEMBLY__
 /*
- * The vmalloc and module area will always be on the topmost area of the kernel
- * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules.
+ * The vmalloc and module area will always be on the topmost area of the
+ * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules.
  * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where
  * modules will reside. That makes sure that inter module branches always
  * happen without trampolines and in addition the placement within a 2GB frame
@@ -131,38 +128,6 @@ static inline int is_module_addr(void *addr)
 }
 
 /*
- * A 31 bit pagetable entry of S390 has following format:
- *  |   PFRA          |    |  OS  |
- * 0                   0IP0
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * I Page-Invalid Bit:    Page is not available for address-translation
- * P Page-Protection Bit: Store access not possible for page
- *
- * A 31 bit segmenttable entry of S390 has following format:
- *  |   P-table origin      |  |PTL
- * 0                         IC
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * I Segment-Invalid Bit:    Segment is not available for address-translation
- * C Common-Segment Bit:     Segment is not private (PoP 3-30)
- * PTL Page-Table-Length:    Page-table length (PTL+1*16 entries -> up to 256)
- *
- * The 31 bit segmenttable origin of S390 has following format:
- *
- *  |S-table origin   |     | STL |
- * X                   **GPS
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * X Space-Switch event:
- * G Segment-Invalid Bit:     *
- * P Private-Space Bit:       Segment is not private (PoP 3-30)
- * S Storage-Alteration:
- * STL Segment-Table-Length:  Segment-table length (STL+1*16 entries -> up to 2048)
- *
  * A 64 bit pagetable entry of S390 has following format:
  * |			 PFRA			      |0IPC|  OS  |
  * 0000000000111111111122222222223333333333444444444455555555556666
@@ -220,7 +185,6 @@ static inline int is_module_addr(void *addr)
 
 /* Software bits in the page table entry */
 #define _PAGE_PRESENT	0x001		/* SW pte present bit */
-#define _PAGE_TYPE	0x002		/* SW pte type bit */
 #define _PAGE_YOUNG	0x004		/* SW pte young bit */
 #define _PAGE_DIRTY	0x008		/* SW pte dirty bit */
 #define _PAGE_READ	0x010		/* SW pte read bit */
@@ -240,31 +204,34 @@ static inline int is_module_addr(void *addr)
  * table lock held.
  *
  * The following table gives the different possible bit combinations for
- * the pte hardware and software bits in the last 12 bits of a pte:
+ * the pte hardware and software bits in the last 12 bits of a pte
+ * (. unassigned bit, x don't care, t swap type):
  *
  *				842100000000
  *				000084210000
  *				000000008421
- *				.IR...wrdytp
- * empty			.10...000000
- * swap				.10...xxxx10
- * file				.11...xxxxx0
- * prot-none, clean, old	.11...000001
- * prot-none, clean, young	.11...000101
- * prot-none, dirty, old	.10...001001
- * prot-none, dirty, young	.10...001101
- * read-only, clean, old	.11...010001
- * read-only, clean, young	.01...010101
- * read-only, dirty, old	.11...011001
- * read-only, dirty, young	.01...011101
- * read-write, clean, old	.11...110001
- * read-write, clean, young	.01...110101
- * read-write, dirty, old	.10...111001
- * read-write, dirty, young	.00...111101
+ *				.IR.uswrdy.p
+ * empty			.10.00000000
+ * swap				.11..ttttt.0
+ * prot-none, clean, old	.11.xx0000.1
+ * prot-none, clean, young	.11.xx0001.1
+ * prot-none, dirty, old	.10.xx0010.1
+ * prot-none, dirty, young	.10.xx0011.1
+ * read-only, clean, old	.11.xx0100.1
+ * read-only, clean, young	.01.xx0101.1
+ * read-only, dirty, old	.11.xx0110.1
+ * read-only, dirty, young	.01.xx0111.1
+ * read-write, clean, old	.11.xx1100.1
+ * read-write, clean, young	.01.xx1101.1
+ * read-write, dirty, old	.10.xx1110.1
+ * read-write, dirty, young	.00.xx1111.1
+ * HW-bits: R read-only, I invalid
+ * SW-bits: p present, y young, d dirty, r read, w write, s special,
+ *	    u unused, l large
  *
- * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001
- * pte_none    is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400
- * pte_swap    is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402
+ * pte_none    is true for the bit pattern .10.00000000, pte == 0x400
+ * pte_swap    is true for the bit pattern .11..ooooo.0, (pte & 0x201) == 0x200
+ * pte_present is true for the bit pattern .xx.xxxxxx.1, (pte & 0x001) == 0x001
  */
 
 /* Bits in the segment/region table address-space-control-element */
@@ -335,6 +302,8 @@ static inline int is_module_addr(void *addr)
  * read-write, dirty, young	11..0...0...11
  * The segment table origin is used to distinguish empty (origin==0) from
  * read-write, old segment table entries (origin!=0)
+ * HW-bits: R read-only, I invalid
+ * SW-bits: y young, d dirty, r read, w write
  */
 
 #define _SEGMENT_ENTRY_SPLIT_BIT 11	/* THP splitting bit number */
@@ -591,10 +560,9 @@ static inline int pte_none(pte_t pte)
 
 static inline int pte_swap(pte_t pte)
 {
-	/* Bit pattern: (pte & 0x603) == 0x402 */
-	return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT |
-				_PAGE_TYPE | _PAGE_PRESENT))
-		== (_PAGE_INVALID | _PAGE_TYPE);
+	/* Bit pattern: (pte & 0x201) == 0x200 */
+	return (pte_val(pte) & (_PAGE_PROTECT | _PAGE_PRESENT))
+		== _PAGE_PROTECT;
 }
 
 static inline int pte_special(pte_t pte)
@@ -1595,51 +1563,51 @@ static inline int has_transparent_hugepage(void)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * 31 bit swap entry format:
- * A page-table entry has some bits we have to treat in a special way.
- * Bits 0, 20 and bit 23 have to be zero, otherwise an specification
- * exception will occur instead of a page translation exception. The
- * specifiation exception has the bad habit not to store necessary
- * information in the lowcore.
- * Bits 21, 22, 30 and 31 are used to indicate the page type.
- * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
- * This leaves the bits 1-19 and bits 24-29 to store type and offset.
- * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19
- * plus 24 for the offset.
- * 0|     offset        |0110|o|type |00|
- * 0 0000000001111111111 2222 2 22222 33
- * 0 1234567890123456789 0123 4 56789 01
- *
  * 64 bit swap entry format:
  * A page-table entry has some bits we have to treat in a special way.
  * Bits 52 and bit 55 have to be zero, otherwise an specification
  * exception will occur instead of a page translation exception. The
  * specifiation exception has the bad habit not to store necessary
  * information in the lowcore.
- * Bits 53, 54, 62 and 63 are used to indicate the page type.
- * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
- * This leaves the bits 0-51 and bits 56-61 to store type and offset.
- * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51
- * plus 56 for the offset.
- * |                      offset                        |0110|o|type |00|
- *  0000000000111111111122222222223333333333444444444455 5555 5 55566 66
- *  0123456789012345678901234567890123456789012345678901 2345 6 78901 23
+ * Bits 54 and 63 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200
+ * This leaves the bits 0-51 and bits 56-62 to store type and offset.
+ * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51
+ * for the offset.
+ * |			  offset			|01100|type |00|
+ * |0000000000111111111122222222223333333333444444444455|55555|55566|66|
+ * |0123456789012345678901234567890123456789012345678901|23456|78901|23|
  */
 
-#define __SWP_OFFSET_MASK (~0UL >> 11)
+#define __SWP_OFFSET_MASK	((1UL << 52) - 1)
+#define __SWP_OFFSET_SHIFT	12
+#define __SWP_TYPE_MASK		((1UL << 5) - 1)
+#define __SWP_TYPE_SHIFT	2
 
 static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 {
 	pte_t pte;
-	offset &= __SWP_OFFSET_MASK;
-	pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) |
-		((offset & 1UL) << 7) | ((offset & ~1UL) << 11);
+
+	pte_val(pte) = _PAGE_INVALID | _PAGE_PROTECT;
+	pte_val(pte) |= (offset & __SWP_OFFSET_MASK) << __SWP_OFFSET_SHIFT;
+	pte_val(pte) |= (type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT;
 	return pte;
 }
 
-#define __swp_type(entry)	(((entry).val >> 2) & 0x1f)
-#define __swp_offset(entry)	(((entry).val >> 11) | (((entry).val >> 7) & 1))
-#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) })
+static inline unsigned long __swp_type(swp_entry_t entry)
+{
+	return (entry.val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK;
+}
+
+static inline unsigned long __swp_offset(swp_entry_t entry)
+{
+	return (entry.val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK;
+}
+
+static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset)
+{
+	return (swp_entry_t) { pte_val(mk_swap_pte(type, offset)) };
+}
 
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index c67e8bf012b6..e617e74b7be2 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -14,20 +14,23 @@ static inline pmd_t __pte_to_pmd(pte_t pte)
 
 	/*
 	 * Convert encoding		  pte bits	   pmd bits
-	 *				.IR...wrdytp	dy..R...I...wr
-	 * empty			.10...000000 -> 00..0...1...00
-	 * prot-none, clean, old	.11...000001 -> 00..1...1...00
-	 * prot-none, clean, young	.11...000101 -> 01..1...1...00
-	 * prot-none, dirty, old	.10...001001 -> 10..1...1...00
-	 * prot-none, dirty, young	.10...001101 -> 11..1...1...00
-	 * read-only, clean, old	.11...010001 -> 00..1...1...01
-	 * read-only, clean, young	.01...010101 -> 01..1...0...01
-	 * read-only, dirty, old	.11...011001 -> 10..1...1...01
-	 * read-only, dirty, young	.01...011101 -> 11..1...0...01
-	 * read-write, clean, old	.11...110001 -> 00..0...1...11
-	 * read-write, clean, young	.01...110101 -> 01..0...0...11
-	 * read-write, dirty, old	.10...111001 -> 10..0...1...11
-	 * read-write, dirty, young	.00...111101 -> 11..0...0...11
+	 *				lIR.uswrdy.p	dy..R...I...wr
+	 * empty			010.000000.0 -> 00..0...1...00
+	 * prot-none, clean, old	111.000000.1 -> 00..1...1...00
+	 * prot-none, clean, young	111.000001.1 -> 01..1...1...00
+	 * prot-none, dirty, old	111.000010.1 -> 10..1...1...00
+	 * prot-none, dirty, young	111.000011.1 -> 11..1...1...00
+	 * read-only, clean, old	111.000100.1 -> 00..1...1...01
+	 * read-only, clean, young	101.000101.1 -> 01..1...0...01
+	 * read-only, dirty, old	111.000110.1 -> 10..1...1...01
+	 * read-only, dirty, young	101.000111.1 -> 11..1...0...01
+	 * read-write, clean, old	111.001100.1 -> 00..1...1...11
+	 * read-write, clean, young	101.001101.1 -> 01..1...0...11
+	 * read-write, dirty, old	110.001110.1 -> 10..0...1...11
+	 * read-write, dirty, young	100.001111.1 -> 11..0...0...11
+	 * HW-bits: R read-only, I invalid
+	 * SW-bits: p present, y young, d dirty, r read, w write, s special,
+	 *	    u unused, l large
 	 */
 	if (pte_present(pte)) {
 		pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
@@ -48,20 +51,23 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
 
 	/*
 	 * Convert encoding		   pmd bits	    pte bits
-	 *				dy..R...I...wr	  .IR...wrdytp
-	 * empty			00..0...1...00 -> .10...001100
-	 * prot-none, clean, old	00..0...1...00 -> .10...000001
-	 * prot-none, clean, young	01..0...1...00 -> .10...000101
-	 * prot-none, dirty, old	10..0...1...00 -> .10...001001
-	 * prot-none, dirty, young	11..0...1...00 -> .10...001101
-	 * read-only, clean, old	00..1...1...01 -> .11...010001
-	 * read-only, clean, young	01..1...1...01 -> .11...010101
-	 * read-only, dirty, old	10..1...1...01 -> .11...011001
-	 * read-only, dirty, young	11..1...1...01 -> .11...011101
-	 * read-write, clean, old	00..0...1...11 -> .10...110001
-	 * read-write, clean, young	01..0...1...11 -> .10...110101
-	 * read-write, dirty, old	10..0...1...11 -> .10...111001
-	 * read-write, dirty, young	11..0...1...11 -> .10...111101
+	 *				dy..R...I...wr	  lIR.uswrdy.p
+	 * empty			00..0...1...00 -> 010.000000.0
+	 * prot-none, clean, old	00..1...1...00 -> 111.000000.1
+	 * prot-none, clean, young	01..1...1...00 -> 111.000001.1
+	 * prot-none, dirty, old	10..1...1...00 -> 111.000010.1
+	 * prot-none, dirty, young	11..1...1...00 -> 111.000011.1
+	 * read-only, clean, old	00..1...1...01 -> 111.000100.1
+	 * read-only, clean, young	01..1...0...01 -> 101.000101.1
+	 * read-only, dirty, old	10..1...1...01 -> 111.000110.1
+	 * read-only, dirty, young	11..1...0...01 -> 101.000111.1
+	 * read-write, clean, old	00..1...1...11 -> 111.001100.1
+	 * read-write, clean, young	01..1...0...11 -> 101.001101.1
+	 * read-write, dirty, old	10..0...1...11 -> 110.001110.1
+	 * read-write, dirty, young	11..0...0...11 -> 100.001111.1
+	 * HW-bits: R read-only, I invalid
+	 * SW-bits: p present, y young, d dirty, r read, w write, s special,
+	 *	    u unused, l large
 	 */
 	if (pmd_present(pmd)) {
 		pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE;