MIPS: Implement Read Inhibit/eXecute Inhibit

The SmartMIPS ASE specifies how Read Inhibit (RI) and eXecute Inhibit
(XI) bits in the page tables work.  The upper two bits of EntryLo{0,1}
are RI and XI when the feature is enabled in the PageGrain register.
SmartMIPS only covers 32-bit systems.  Cavium Octeon+ extends this to
64-bit systems by continuing to place the RI and XI bits in the top of
EntryLo even when EntryLo is 64-bits wide.

Because we need to carry the RI and XI bits in the PTE, the layout of
the PTE is changed.  There is a two instruction overhead in the TLB
refill hot path to get the EntryLo bits into the proper position.
Also the TLB load exception has to probe the TLB to check if RI or XI
caused the exception.

Also of note is that the layout of the PTE bits is done at compile and
runtime rather than statically.  In the 32-bit case this allows for
the same number of PFN bits as before the patch as the _PAGE_HUGE is
not supported in 32-bit kernels (we have _PAGE_NO_EXEC and
_PAGE_NO_READ instead of _PAGE_READ and _PAGE_HUGE).

The patch is tested on Cavium Octeon+, but should also work on 32-bit
systems with the Smart-MIPS ASE.

Signed-off-by: David Daney <ddaney@caviumnetworks.com>
To: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/952/
Patchwork: http://patchwork.linux-mips.org/patch/956/
Patchwork: http://patchwork.linux-mips.org/patch/962/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

5 files changed, 128 insertions, 29 deletions

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 272c5ef35bbb..ac73cede3a0a 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -95,6 +95,9 @@
 #ifndef cpu_has_smartmips
 #define cpu_has_smartmips      (cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
 #endif
+#ifndef kernel_uses_smartmips_rixi
+#define kernel_uses_smartmips_rixi 0
+#endif
 #ifndef cpu_has_vtag_icache
 #define cpu_has_vtag_icache	(cpu_data[0].icache.flags & MIPS_CACHE_VTAG)
 #endif
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index 55813d6150c7..ae90412556d0 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -127,8 +127,8 @@ pfn_pte(unsigned long pfn, pgprot_t prot)
 #define pte_pfn(x)		((unsigned long)((x).pte >> (PAGE_SHIFT + 2)))
 #define pfn_pte(pfn, prot)	__pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot))
 #else
-#define pte_pfn(x)		((unsigned long)((x).pte >> PAGE_SHIFT))
-#define pfn_pte(pfn, prot)	__pte(((unsigned long long)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pte_pfn(x)		((unsigned long)((x).pte >> _PFN_SHIFT))
+#define pfn_pte(pfn, prot)	__pte(((unsigned long long)(pfn) << _PFN_SHIFT) | pgprot_val(prot))
 #endif
 #endif /* defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32) */
 
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 24314d21a708..26dc69d792a6 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -211,8 +211,8 @@ static inline void pud_clear(pud_t *pudp)
 #define pte_pfn(x)		((unsigned long)((x).pte >> (PAGE_SHIFT + 2)))
 #define pfn_pte(pfn, prot)	__pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot))
 #else
-#define pte_pfn(x)		((unsigned long)((x).pte >> PAGE_SHIFT))
-#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pte_pfn(x)		((unsigned long)((x).pte >> _PFN_SHIFT))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
 #endif
 
 #define __pgd_offset(address)	pgd_index(address)
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 1073e6df8621..e9fe7e97ce4c 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -50,7 +50,7 @@
 #define _CACHE_SHIFT                3
 #define _CACHE_MASK                 (7<<3)
 
-#else
+#elif defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
 #define _PAGE_PRESENT               (1<<0)  /* implemented in software */
 #define _PAGE_READ                  (1<<1)  /* implemented in software */
@@ -59,8 +59,6 @@
 #define _PAGE_MODIFIED              (1<<4)  /* implemented in software */
 #define _PAGE_FILE                  (1<<4)  /* set:pagecache unset:swap */
 
-#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
-
 #define _PAGE_GLOBAL                (1<<8)
 #define _PAGE_VALID                 (1<<9)
 #define _PAGE_SILENT_READ           (1<<9)  /* synonym                 */
@@ -69,21 +67,113 @@
 #define _CACHE_UNCACHED             (1<<11)
 #define _CACHE_MASK                 (1<<11)
 
+#else /* 'Normal' r4K case */
+/*
+ * When using the RI/XI bit support, we have 13 bits of flags below
+ * the physical address. The RI/XI bits are placed such that a SRL 5
+ * can strip off the software bits, then a ROTR 2 can move the RI/XI
+ * into bits [63:62]. This also limits physical address to 56 bits,
+ * which is more than we need right now.
+ */
+
+/* implemented in software */
+#define _PAGE_PRESENT_SHIFT	(0)
+#define _PAGE_PRESENT		(1 << _PAGE_PRESENT_SHIFT)
+/* implemented in software, should be unused if kernel_uses_smartmips_rixi. */
+#define _PAGE_READ_SHIFT	(kernel_uses_smartmips_rixi ? _PAGE_PRESENT_SHIFT : _PAGE_PRESENT_SHIFT + 1)
+#define _PAGE_READ ({if (kernel_uses_smartmips_rixi) BUG(); 1 << _PAGE_READ_SHIFT; })
+/* implemented in software */
+#define _PAGE_WRITE_SHIFT	(_PAGE_READ_SHIFT + 1)
+#define _PAGE_WRITE		(1 << _PAGE_WRITE_SHIFT)
+/* implemented in software */
+#define _PAGE_ACCESSED_SHIFT	(_PAGE_WRITE_SHIFT + 1)
+#define _PAGE_ACCESSED		(1 << _PAGE_ACCESSED_SHIFT)
+/* implemented in software */
+#define _PAGE_MODIFIED_SHIFT	(_PAGE_ACCESSED_SHIFT + 1)
+#define _PAGE_MODIFIED		(1 << _PAGE_MODIFIED_SHIFT)
+/* set:pagecache unset:swap */
+#define _PAGE_FILE		(_PAGE_MODIFIED)
+
+#ifdef CONFIG_HUGETLB_PAGE
+/* huge tlb page */
+#define _PAGE_HUGE_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
+#define _PAGE_HUGE		(1 << _PAGE_HUGE_SHIFT)
 #else
+#define _PAGE_HUGE_SHIFT	(_PAGE_MODIFIED_SHIFT)
+#define _PAGE_HUGE		({BUG(); 1; })  /* Dummy value */
+#endif
 
-#define _PAGE_R4KBUG                (1<<5)  /* workaround for r4k bug  */
-#define _PAGE_HUGE                  (1<<5)  /* huge tlb page */
-#define _PAGE_GLOBAL                (1<<6)
-#define _PAGE_VALID                 (1<<7)
-#define _PAGE_SILENT_READ           (1<<7)  /* synonym                 */
-#define _PAGE_DIRTY                 (1<<8)  /* The MIPS dirty bit      */
-#define _PAGE_SILENT_WRITE          (1<<8)
-#define _CACHE_SHIFT		    9
-#define _CACHE_MASK                 (7<<9)
+/* Page cannot be executed */
+#define _PAGE_NO_EXEC_SHIFT	(kernel_uses_smartmips_rixi ? _PAGE_HUGE_SHIFT + 1 : _PAGE_HUGE_SHIFT)
+#define _PAGE_NO_EXEC		({if (!kernel_uses_smartmips_rixi) BUG(); 1 << _PAGE_NO_EXEC_SHIFT; })
+
+/* Page cannot be read */
+#define _PAGE_NO_READ_SHIFT	(kernel_uses_smartmips_rixi ? _PAGE_NO_EXEC_SHIFT + 1 : _PAGE_NO_EXEC_SHIFT)
+#define _PAGE_NO_READ		({if (!kernel_uses_smartmips_rixi) BUG(); 1 << _PAGE_NO_READ_SHIFT; })
+
+#define _PAGE_GLOBAL_SHIFT	(_PAGE_NO_READ_SHIFT + 1)
+#define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
+
+#define _PAGE_VALID_SHIFT	(_PAGE_GLOBAL_SHIFT + 1)
+#define _PAGE_VALID		(1 << _PAGE_VALID_SHIFT)
+/* synonym                 */
+#define _PAGE_SILENT_READ	(_PAGE_VALID)
+
+/* The MIPS dirty bit      */
+#define _PAGE_DIRTY_SHIFT	(_PAGE_VALID_SHIFT + 1)
+#define _PAGE_DIRTY		(1 << _PAGE_DIRTY_SHIFT)
+#define _PAGE_SILENT_WRITE	(_PAGE_DIRTY)
+
+#define _CACHE_SHIFT		(_PAGE_DIRTY_SHIFT + 1)
+#define _CACHE_MASK		(7 << _CACHE_SHIFT)
+
+#define _PFN_SHIFT		(PAGE_SHIFT - 12 + _CACHE_SHIFT + 3)
 
-#endif
 #endif /* defined(CONFIG_64BIT_PHYS_ADDR && defined(CONFIG_CPU_MIPS32) */
 
+#ifndef _PFN_SHIFT
+#define _PFN_SHIFT                  PAGE_SHIFT
+#endif
+#define _PFN_MASK		(~((1 << (_PFN_SHIFT)) - 1))
+
+#ifndef _PAGE_NO_READ
+#define _PAGE_NO_READ ({BUG(); 0; })
+#define _PAGE_NO_READ_SHIFT ({BUG(); 0; })
+#endif
+#ifndef _PAGE_NO_EXEC
+#define _PAGE_NO_EXEC ({BUG(); 0; })
+#endif
+#ifndef _PAGE_GLOBAL_SHIFT
+#define _PAGE_GLOBAL_SHIFT ilog2(_PAGE_GLOBAL)
+#endif
+
+
+#ifndef __ASSEMBLY__
+/*
+ * pte_to_entrylo converts a page table entry (PTE) into a Mips
+ * entrylo0/1 value.
+ */
+static inline uint64_t pte_to_entrylo(unsigned long pte_val)
+{
+	if (kernel_uses_smartmips_rixi) {
+		int sa;
+#ifdef CONFIG_32BIT
+		sa = 31 - _PAGE_NO_READ_SHIFT;
+#else
+		sa = 63 - _PAGE_NO_READ_SHIFT;
+#endif
+		/*
+		 * C has no way to express that this is a DSRL
+		 * _PAGE_NO_EXEC_SHIFT followed by a ROTR 2.  Luckily
+		 * in the fast path this is done in assembly
+		 */
+		return (pte_val >> _PAGE_GLOBAL_SHIFT) |
+			((pte_val & (_PAGE_NO_EXEC | _PAGE_NO_READ)) << sa);
+	}
+
+	return pte_val >> _PAGE_GLOBAL_SHIFT;
+}
+#endif
 
 /*
  * Cache attributes
@@ -130,9 +220,9 @@
 
 #endif
 
-#define __READABLE	(_PAGE_READ | _PAGE_SILENT_READ | _PAGE_ACCESSED)
+#define __READABLE	(_PAGE_SILENT_READ | _PAGE_ACCESSED | (kernel_uses_smartmips_rixi ? 0 : _PAGE_READ))
 #define __WRITEABLE	(_PAGE_WRITE | _PAGE_SILENT_WRITE | _PAGE_MODIFIED)
 
-#define _PAGE_CHG_MASK  (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED | _CACHE_MASK)
+#define _PAGE_CHG_MASK  (_PFN_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED | _CACHE_MASK)
 
 #endif /* _ASM_PGTABLE_BITS_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 02335fda9e77..93598ba01355 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -22,23 +22,24 @@ struct mm_struct;
 struct vm_area_struct;
 
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _CACHE_CACHABLE_NONCOHERENT)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_WRITE | (kernel_uses_smartmips_rixi ? 0 : _PAGE_READ) | \
 				 _page_cachable_default)
-#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
-				 _page_cachable_default)
-#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+#define PAGE_COPY	__pgprot(_PAGE_PRESENT | (kernel_uses_smartmips_rixi ? 0 : _PAGE_READ) | \
+				 (kernel_uses_smartmips_rixi ?  _PAGE_NO_EXEC : 0) | _page_cachable_default)
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | (kernel_uses_smartmips_rixi ? 0 : _PAGE_READ) | \
 				 _page_cachable_default)
 #define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _page_cachable_default)
-#define PAGE_USERIO	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+#define PAGE_USERIO	__pgprot(_PAGE_PRESENT | (kernel_uses_smartmips_rixi ? 0 : _PAGE_READ) | _PAGE_WRITE | \
 				 _page_cachable_default)
 #define PAGE_KERNEL_UNCACHED __pgprot(_PAGE_PRESENT | __READABLE | \
 			__WRITEABLE | _PAGE_GLOBAL | _CACHE_UNCACHED)
 
 /*
- * MIPS can't do page protection for execute, and considers that the same like
- * read. Also, write permissions imply read permissions. This is the closest
- * we can get by reasonable means..
+ * If _PAGE_NO_EXEC is not defined, we can't do page protection for
+ * execute, and consider it to be the same as read. Also, write
+ * permissions imply read permissions. This is the closest we can get
+ * by reasonable means..
  */
 
 /*
@@ -298,8 +299,13 @@ static inline pte_t pte_mkdirty(pte_t pte)
 static inline pte_t pte_mkyoung(pte_t pte)
 {
 	pte_val(pte) |= _PAGE_ACCESSED;
-	if (pte_val(pte) & _PAGE_READ)
-		pte_val(pte) |= _PAGE_SILENT_READ;
+	if (kernel_uses_smartmips_rixi) {
+		if (!(pte_val(pte) & _PAGE_NO_READ))
+			pte_val(pte) |= _PAGE_SILENT_READ;
+	} else {
+		if (pte_val(pte) & _PAGE_READ)
+			pte_val(pte) |= _PAGE_SILENT_READ;
+	}
 	return pte;
 }