sparc: Access kernel TSB using physical addressing when possible.

On sun4v this is basically required since we point the hypervisor and
the TSB walking hardware at these tables using physical addressing
too.

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 85 insertions, 40 deletions

diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 83c571d8c8a7..1a8afd1ad04f 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
         sub     TSB, 0x8, TSB;   \
         TSB_STORE(TSB, TAG);
 
-#define KTSB_LOAD_QUAD(TSB, REG) \
-        ldda            [TSB] ASI_NUCLEUS_QUAD_LDD, REG;
-
-#define KTSB_STORE(ADDR, VAL) \
-        stxa            VAL, [ADDR] ASI_N;
-
-#define KTSB_LOCK_TAG(TSB, REG1, REG2)  \
-99:     lduwa   [TSB] ASI_N, REG1;      \
-        sethi   %hi(TSB_TAG_LOCK_HIGH), REG2;\
-        andcc   REG1, REG2, %g0;        \
-        bne,pn  %icc, 99b;              \
-         nop;                           \
-        casa    [TSB] ASI_N, REG1, REG2;\
-        cmp     REG1, REG2;             \
-        bne,pn  %icc, 99b;              \
-         nop;                           \
-
-#define KTSB_WRITE(TSB, TTE, TAG) \
-        add     TSB, 0x8, TSB;   \
-        stxa    TTE, [TSB] ASI_N;     \
-        sub     TSB, 0x8, TSB;   \
-        stxa    TAG, [TSB] ASI_N;
-
         /* Do a kernel page table walk.  Leaves physical PTE pointer in
          * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
          * VADDR will not be clobbered, but REG2 will.
@@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
         (KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES   4096
 
+#define KTSB_PHYS_SHIFT         15
+
         /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
          * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
          * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
          * VADDR and TAG will be preserved and not clobbered by this macro.
          */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-        sethi           %hi(swapper_tsb), REG1; \
+661:    sethi           %hi(swapper_tsb), REG1;                 \
         or              REG1, %lo(swapper_tsb), REG1; \
+        .section        .swapper_tsb_phys_patch, "ax"; \
+        .word           661b; \
+        .previous; \
+661:    nop; \
+        .section        .tsb_ldquad_phys_patch, "ax"; \
+        .word           661b; \
+        sllx            REG1, KTSB_PHYS_SHIFT, REG1; \
+        sllx            REG1, KTSB_PHYS_SHIFT, REG1; \
+        .previous; \
         srlx            VADDR, PAGE_SHIFT, REG2; \
         and             REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
         sllx            REG2, 4, REG2; \
         add             REG1, REG2, REG2; \
-        KTSB_LOAD_QUAD(REG2, REG3); \
+        TSB_LOAD_QUAD(REG2, REG3); \
         cmp             REG3, TAG; \
         be,a,pt         %xcc, OK_LABEL; \
          mov            REG4, REG1;
@@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
          * we can make use of that for the index computation.
          */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-        sethi           %hi(swapper_4m_tsb), REG1; \
+661:    sethi           %hi(swapper_4m_tsb), REG1;           \
         or              REG1, %lo(swapper_4m_tsb), REG1; \
+        .section        .swapper_4m_tsb_phys_patch, "ax"; \
+        .word           661b; \
+        .previous; \
+661:    nop; \
+        .section        .tsb_ldquad_phys_patch, "ax"; \
+        .word           661b; \
+        sllx            REG1, KTSB_PHYS_SHIFT, REG1; \
+        sllx            REG1, KTSB_PHYS_SHIFT, REG1; \
+        .previous; \
         and             TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
         sllx            REG2, 4, REG2; \
         add             REG1, REG2, REG2; \
-        KTSB_LOAD_QUAD(REG2, REG3); \
+        TSB_LOAD_QUAD(REG2, REG3); \
         cmp             REG3, TAG; \
         be,a,pt         %xcc, OK_LABEL; \
          mov            REG4, REG1;
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 1d361477d7d6..79f310364849 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss:
 kvmap_itlb_vmalloc_addr:
         KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
-        KTSB_LOCK_TAG(%g1, %g2, %g7)
+        TSB_LOCK_TAG(%g1, %g2, %g7)
 
         /* Load and check PTE.  */
         ldxa            [%g5] ASI_PHYS_USE_EC, %g5
         mov             1, %g7
         sllx            %g7, TSB_TAG_INVALID_BIT, %g7
         brgez,a,pn      %g5, kvmap_itlb_longpath
-         KTSB_STORE(%g1, %g7)
+         TSB_STORE(%g1, %g7)
 
-        KTSB_WRITE(%g1, %g5, %g6)
+        TSB_WRITE(%g1, %g5, %g6)
 
         /* fallthrough to TLB load */
 
@@ -102,9 +102,9 @@ kvmap_itlb_longpath:
 kvmap_itlb_obp:
         OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath)
 
-        KTSB_LOCK_TAG(%g1, %g2, %g7)
+        TSB_LOCK_TAG(%g1, %g2, %g7)
 
-        KTSB_WRITE(%g1, %g5, %g6)
+        TSB_WRITE(%g1, %g5, %g6)
 
         ba,pt           %xcc, kvmap_itlb_load
          nop
@@ -112,17 +112,17 @@ kvmap_itlb_obp:
 kvmap_dtlb_obp:
         OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath)
 
-        KTSB_LOCK_TAG(%g1, %g2, %g7)
+        TSB_LOCK_TAG(%g1, %g2, %g7)
 
-        KTSB_WRITE(%g1, %g5, %g6)
+        TSB_WRITE(%g1, %g5, %g6)
 
         ba,pt           %xcc, kvmap_dtlb_load
          nop
 
         .align          32
 kvmap_dtlb_tsb4m_load:
-        KTSB_LOCK_TAG(%g1, %g2, %g7)
-        KTSB_WRITE(%g1, %g5, %g6)
+        TSB_LOCK_TAG(%g1, %g2, %g7)
+        TSB_WRITE(%g1, %g5, %g6)
         ba,pt           %xcc, kvmap_dtlb_load
          nop
 
@@ -222,16 +222,16 @@ kvmap_linear_patch:
 kvmap_dtlb_vmalloc_addr:
         KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
-        KTSB_LOCK_TAG(%g1, %g2, %g7)
+        TSB_LOCK_TAG(%g1, %g2, %g7)
 
         /* Load and check PTE.  */
         ldxa            [%g5] ASI_PHYS_USE_EC, %g5
         mov             1, %g7
         sllx            %g7, TSB_TAG_INVALID_BIT, %g7
         brgez,a,pn      %g5, kvmap_dtlb_longpath
-         KTSB_STORE(%g1, %g7)
+         TSB_STORE(%g1, %g7)
 
-        KTSB_WRITE(%g1, %g5, %g6)
+        TSB_WRITE(%g1, %g5, %g6)
 
         /* fallthrough to TLB load */
 
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 94a954892d3f..0e1605697b49 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -107,6 +107,16 @@ SECTIONS
                 *(.sun4v_2insn_patch)
                 __sun4v_2insn_patch_end = .;
         }
+        .swapper_tsb_phys_patch : {
+                __swapper_tsb_phys_patch = .;
+                *(.swapper_tsb_phys_patch)
+                __swapper_tsb_phys_patch_end = .;
+        }
+        .swapper_4m_tsb_phys_patch : {
+                __swapper_4m_tsb_phys_patch = .;
+                *(.swapper_4m_tsb_phys_patch)
+                __swapper_4m_tsb_phys_patch_end = .;
+        }
         .popc_3insn_patch : {
                 __popc_3insn_patch = .;
                 *(.popc_3insn_patch)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3fd8e18bed80..adfac23d976a 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1597,6 +1597,42 @@ static void __init tsb_phys_patch(void)
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
+static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
+{
+        pa >>= KTSB_PHYS_SHIFT;
+
+        while (start < end) {
+                unsigned int *ia = (unsigned int *)(unsigned long)*start;
+
+                ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+                __asm__ __volatile__("flush     %0" : : "r" (ia));
+
+                ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+                __asm__ __volatile__("flush     %0" : : "r" (ia + 1));
+
+                start++;
+        }
+}
+
+static void ktsb_phys_patch(void)
+{
+        extern unsigned int __swapper_tsb_phys_patch;
+        extern unsigned int __swapper_tsb_phys_patch_end;
+        extern unsigned int __swapper_4m_tsb_phys_patch;
+        extern unsigned int __swapper_4m_tsb_phys_patch_end;
+        unsigned long ktsb_pa;
+
+        ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+        patch_one_ktsb_phys(&__swapper_tsb_phys_patch,
+                            &__swapper_tsb_phys_patch_end, ktsb_pa);
+#ifndef CONFIG_DEBUG_PAGEALLOC
+        ktsb_pa = (kern_base +
+                   ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+        patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch,
+                            &__swapper_4m_tsb_phys_patch_end, ktsb_pa);
+#endif
+}
+
 static void __init sun4v_ktsb_init(void)
 {
         unsigned long ktsb_pa;
@@ -1716,8 +1752,10 @@ void __init paging_init(void)
                 sun4u_pgprot_init();
 
         if (tlb_type == cheetah_plus ||
-            tlb_type == hypervisor)
+            tlb_type == hypervisor) {
                 tsb_phys_patch();
+                ktsb_phys_patch();
+        }
 
         if (tlb_type == hypervisor) {
                 sun4v_patch_tlb_handlers();