ARC: Code cosmetics (Nothing semantical)

* reduce editor lines taken by pt_regs
* ARCompact ISA specific part of TLB Miss handlers clubbed together
* cleanup some comments

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

4 files changed, 77 insertions, 104 deletions

diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index c9938e7a7dbd..1bfeec2c0558 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,27 +20,17 @@ struct pt_regs {
 
         /* Real registers */
         long bta;       /* bta_l1, bta_l2, erbta */
-        long lp_start;
-        long lp_end;
-        long lp_count;
+
+        long lp_start, lp_end, lp_count;
+
         long status32;  /* status32_l1, status32_l2, erstatus */
         long ret;       /* ilink1, ilink2 or eret */
         long blink;
         long fp;
         long r26;       /* gp */
-        long r12;
-        long r11;
-        long r10;
-        long r9;
-        long r8;
-        long r7;
-        long r6;
-        long r5;
-        long r4;
-        long r3;
-        long r2;
-        long r1;
-        long r0;
+
+        long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+
         long sp;        /* user/kernel sp depending on where we came from  */
         long orig_r0;
 
@@ -70,19 +60,7 @@ struct pt_regs {
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-        long r25;
-        long r24;
-        long r23;
-        long r22;
-        long r21;
-        long r20;
-        long r19;
-        long r18;
-        long r17;
-        long r16;
-        long r15;
-        long r14;
-        long r13;
+        long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
 #define instruction_pointer(regs)       ((regs)->ret)
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 8276bfd61704..662627ced4f2 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -20,9 +20,9 @@ typedef struct {
 #define __ARCH_SPIN_LOCK_LOCKED         { __ARCH_SPIN_LOCK_LOCKED__ }
 
 /*
- * Unlocked:     0x01_00_00_00
- * Read lock(s): 0x00_FF_00_00 to say 0x01
- * Write lock:   0x0, but only possible if prior value "unlocked" 0x0100_0000
+ * Unlocked     : 0x0100_0000
+ * Read lock(s) : 0x00FF_FFFF to 0x01  (Multiple Readers decrement it)
+ * Write lock   : 0x0, but only if prior value is "unlocked" 0x0100_0000
  */
 typedef struct {
         volatile unsigned int   counter;
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index f415d851b765..5a1259cd948c 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -622,12 +622,12 @@ void flush_icache_range(unsigned long kstart, unsigned long kend)
 /*
  * General purpose helper to make I and D cache lines consistent.
  * @paddr is phy addr of region
- * @vaddr is typically user or kernel vaddr (vmalloc)
- *    Howver in one instance, flush_icache_range() by kprobe (for a breakpt in
+ * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc)
+ *    However in one instance, when called by kprobe (for a breakpt in
  *    builtin kernel code) @vaddr will be paddr only, meaning CDU operation will
  *    use a paddr to index the cache (despite VIPT). This is fine since since a
- *    built-in kernel page will not have any virtual mappings (not even kernel)
- *    kprobe on loadable module is different as it will have kvaddr.
+ *    builtin kernel page will not have any virtual mappings.
+ *    kprobe on loadable module will be kernel vaddr.
  */
 void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len)
 {
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index fc34ebc103bc..9cce00e94b43 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -44,17 +44,36 @@
 #include <asm/arcregs.h>
 #include <asm/cache.h>
 #include <asm/processor.h>
-#if (CONFIG_ARC_MMU_VER == 1)
 #include <asm/tlb-mmu1.h>
-#endif
 
-;--------------------------------------------------------------------------
-; scratch memory to save the registers (r0-r3) used to code TLB refill Handler
-; For details refer to comments before TLBMISS_FREEUP_REGS below
+;-----------------------------------------------------------------
+; ARC700 Exception Handling doesn't auto-switch stack and it only provides
+; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
+;
+; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a
+; "global" is used to free-up FIRST core reg to be able to code the rest of
+; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe).
+; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3
+; need to be saved as well by extending the "global" to be 4 words. Hence
+;       ".size   ex_saved_reg1, 16"
+; [All of this dance is to avoid stack switching for each TLB Miss, since we
+; only need to save only a handful of regs, as opposed to complete reg file]
+;
+; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST
+; core reg as it will not be SMP safe.
+; Thus scratch AUX reg is used (and no longer used to cache task PGD).
+; To save the rest of 3 regs - per cpu, the global is made "per-cpu".
+; Epilogue thus has to locate the "per-cpu" storage for regs.
+; To avoid cache line bouncing the per-cpu global is aligned/sized per
+; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence
+;       ".size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)"
+
+; As simple as that....
 ;--------------------------------------------------------------------------
 
+; scratch memory to save [r0-r3] used to code TLB refill Handler
 ARCFP_DATA ex_saved_reg1
-        .align 1 << L1_CACHE_SHIFT      ; IMP: Must be Cache Line aligned
+        .align 1 << L1_CACHE_SHIFT
         .type   ex_saved_reg1, @object
 #ifdef CONFIG_SMP
         .size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)
@@ -66,6 +85,44 @@ ex_saved_reg1:
         .zero 16
 #endif
 
+.macro TLBMISS_FREEUP_REGS
+#ifdef CONFIG_SMP
+        sr  r0, [ARC_REG_SCRATCH_DATA0] ; freeup r0 to code with
+        GET_CPU_ID  r0                  ; get to per cpu scratch mem,
+        lsl r0, r0, L1_CACHE_SHIFT      ; cache line wide per cpu
+        add r0, @ex_saved_reg1, r0
+#else
+        st    r0, [@ex_saved_reg1]
+        mov_s r0, @ex_saved_reg1
+#endif
+        st_s  r1, [r0, 4]
+        st_s  r2, [r0, 8]
+        st_s  r3, [r0, 12]
+
+        ; VERIFY if the ASID in MMU-PID Reg is same as
+        ; one in Linux data structures
+
+        DBG_ASID_MISMATCH
+.endm
+
+.macro TLBMISS_RESTORE_REGS
+#ifdef CONFIG_SMP
+        GET_CPU_ID  r0                  ; get to per cpu scratch mem
+        lsl r0, r0, L1_CACHE_SHIFT      ; each is cache line wide
+        add r0, @ex_saved_reg1, r0
+        ld_s  r3, [r0,12]
+        ld_s  r2, [r0, 8]
+        ld_s  r1, [r0, 4]
+        lr    r0, [ARC_REG_SCRATCH_DATA0]
+#else
+        mov_s r0, @ex_saved_reg1
+        ld_s  r3, [r0,12]
+        ld_s  r2, [r0, 8]
+        ld_s  r1, [r0, 4]
+        ld_s  r0, [r0]
+#endif
+.endm
+
 ;============================================================================
 ;  Troubleshooting Stuff
 ;============================================================================
@@ -191,68 +248,6 @@ ex_saved_reg1:
 #endif
 .endm
 
-;-----------------------------------------------------------------
-; ARC700 Exception Handling doesn't auto-switch stack and it only provides
-; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
-;
-; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a
-; "global" is used to free-up FIRST core reg to be able to code the rest of
-; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe).
-; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3
-; need to be saved as well by extending the "global" to be 4 words. Hence
-;       ".size   ex_saved_reg1, 16"
-; [All of this dance is to avoid stack switching for each TLB Miss, since we
-; only need to save only a handful of regs, as opposed to complete reg file]
-;
-; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST
-; core reg as it will not be SMP safe.
-; Thus scratch AUX reg is used (and no longer used to cache task PGD).
-; To save the rest of 3 regs - per cpu, the global is made "per-cpu".
-; Epilogue thus has to locate the "per-cpu" storage for regs.
-; To avoid cache line bouncing the per-cpu global is aligned/sized per
-; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence
-;       ".size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)"
-
-; As simple as that....
-
-.macro TLBMISS_FREEUP_REGS
-#ifdef CONFIG_SMP
-        sr  r0, [ARC_REG_SCRATCH_DATA0] ; freeup r0 to code with
-        GET_CPU_ID  r0                  ; get to per cpu scratch mem,
-        lsl r0, r0, L1_CACHE_SHIFT      ; cache line wide per cpu
-        add r0, @ex_saved_reg1, r0
-#else
-        st    r0, [@ex_saved_reg1]
-        mov_s r0, @ex_saved_reg1
-#endif
-        st_s  r1, [r0, 4]
-        st_s  r2, [r0, 8]
-        st_s  r3, [r0, 12]
-
-        ; VERIFY if the ASID in MMU-PID Reg is same as
-        ; one in Linux data structures
-
-        DBG_ASID_MISMATCH
-.endm
-
-;-----------------------------------------------------------------
-.macro TLBMISS_RESTORE_REGS
-#ifdef CONFIG_SMP
-        GET_CPU_ID  r0                  ; get to per cpu scratch mem
-        lsl r0, r0, L1_CACHE_SHIFT      ; each is cache line wide
-        add r0, @ex_saved_reg1, r0
-        ld_s  r3, [r0,12]
-        ld_s  r2, [r0, 8]
-        ld_s  r1, [r0, 4]
-        lr    r0, [ARC_REG_SCRATCH_DATA0]
-#else
-        mov_s r0, @ex_saved_reg1
-        ld_s  r3, [r0,12]
-        ld_s  r2, [r0, 8]
-        ld_s  r1, [r0, 4]
-        ld_s  r0, [r0]
-#endif
-.endm
 
 ARCFP_CODE      ;Fast Path Code, candidate for ICCM