ARC: [optim] Cache "current" in Register r25

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

9 files changed, 120 insertions, 1 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 7db978570fb8..03347cbde9bd 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -264,6 +264,13 @@ config LINUX_LINK_BASE
 
 endmenu # "Platform Board Configuration"
 
+config ARC_CURR_IN_REG
+        bool "Dedicate Register r25 for current_task pointer"
+        default y
+        help
+          This reserved Register R25 to point to Current Task in
+          kernel mode. This saves memory access for each such access
+
 config ARC_STACK_NONEXEC
         bool "Make stack non-executable"
         default n
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 29b5fcd9c4b6..5c98fc19d99d 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -20,6 +20,15 @@ export PLATFORM
 cflags-y        += -Iarch/arc/plat-$(PLATFORM)/include
 cflags-y        += -mA7 -fno-common -pipe -fno-builtin -D__linux__
 
+ifdef CONFIG_ARC_CURR_IN_REG
+# For a global register defintion, make sure it gets passed to every file
+# We had a customer reported bug where some code built in kernel was NOT using
+# any kernel headers, and missing the r25 global register
+# Can't do unconditionally (like above) because of recursive include issues
+# due to <linux/thread_info.h>
+LINUXINCLUDE    +=  -include ${src}/arch/arc/include/asm/current.h
+endif
+
 atleast_gcc44 :=  $(call cc-ifversion, -gt, 0402, y)
 cflags-$(atleast_gcc44)                 += -fsection-anchors
 
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 105ec1188aaf..78e982dad537 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -11,7 +11,6 @@ generic-y += bugs.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/arc/include/asm/current.h b/arch/arc/include/asm/current.h
new file mode 100644
index 000000000000..87b918585c4a
--- /dev/null
+++ b/arch/arc/include/asm/current.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Vineetg: May 16th, 2008
+ *  - Current macro is now implemented as "global register" r25
+ */
+
+#ifndef _ASM_ARC_CURRENT_H
+#define _ASM_ARC_CURRENT_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+register struct task_struct *curr_arc asm("r25");
+#define current (curr_arc)
+
+#else
+#include <asm-generic/current.h>
+#endif /* ! CONFIG_ARC_CURR_IN_REG */
+
+#endif /* ! __ASSEMBLY__ */
+
+#endif  /* __KERNEL__ */
+
+#endif /* _ASM_ARC_CURRENT_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 9eada5b28be6..716f4f7b5cd2 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -13,6 +13,8 @@
  *   was being "CLEARED" rather then "SET". Actually "SET" clears ZOL context
  *
  * Vineetg: May 5th 2008
+ *  -Modified CALLEE_REG save/restore macros to handle the fact that
+ *      r25 contains the kernel current task ptr
  *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
  *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
  *      address Write back load ld.ab instead of seperate ld/add instn
@@ -28,6 +30,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/arcregs.h>
 #include <asm/ptrace.h>
+#include <asm/processor.h>      /* For VMALLOC_START */
 #include <asm/thread_info.h>    /* For THREAD_SIZE */
 
 /* Note on the LD/ST addr modes with addr reg wback
@@ -106,7 +109,14 @@
         st.a    r22, [sp, -4]
         st.a    r23, [sp, -4]
         st.a    r24, [sp, -4]
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+        ; Retrieve orig r25 and save it on stack
+        ld      r12, [r25, TASK_THREAD + THREAD_USER_R25]
+        st.a    r12, [sp, -4]
+#else
         st.a    r25, [sp, -4]
+#endif
 
         /* move up by 1 word to "create" callee_regs->"stack_place_holder" */
         sub sp, sp, 4
@@ -131,8 +141,12 @@
         st.a    r22, [sp, -4]
         st.a    r23, [sp, -4]
         st.a    r24, [sp, -4]
+#ifdef CONFIG_ARC_CURR_IN_REG
+        sub     sp, sp, 8
+#else
         st.a    r25, [sp, -4]
         sub     sp, sp, 4
+#endif
 .endm
 
 /*--------------------------------------------------------------
@@ -148,8 +162,14 @@
  *-------------------------------------------------------------*/
 .macro RESTORE_CALLEE_SAVED_KERNEL
 
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+        add     sp, sp, 8  /* skip callee_reg gutter and user r25 placeholder */
+#else
         add     sp, sp, 4   /* skip "callee_regs->stack_place_holder" */
         ld.ab   r25, [sp, 4]
+#endif
+
         ld.ab   r24, [sp, 4]
         ld.ab   r23, [sp, 4]
         ld.ab   r22, [sp, 4]
@@ -235,6 +255,7 @@
  *
  * Entry   : r9 contains pre-IRQ/exception/trap status32
  * Exit    : SP is set to kernel mode stack pointer
+ *           If CURR_IN_REG, r25 set to "current" task pointer
  * Clobbers: r9
  *-------------------------------------------------------------*/
 
@@ -259,6 +280,16 @@
 
         GET_CURR_TASK_ON_CPU   r9
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+        /* If current task pointer cached in r25, time to
+         *  -safekeep USER r25 in task->thread_struct->user_r25
+         *  -load r25 with current task ptr
+         */
+        st.as   r25, [r9, (TASK_THREAD + THREAD_USER_R25)/4]
+        mov     r25, r9
+#endif
+
         /* With current tsk in r9, get it's kernel mode stack base */
         GET_TSK_STACK_BASE  r9, r9
 
@@ -519,17 +550,31 @@
 
 .macro  SET_CURR_TASK_ON_CPU    tsk, tmp
         st  \tsk, [@_current_task]
+#ifdef CONFIG_ARC_CURR_IN_REG
+        mov r25, \tsk
+#endif
 .endm
 
 /* ------------------------------------------------------------------
  * Get the ptr to some field of Current Task at @off in task struct
+ *  -Uses r25 for Current task ptr if that is enabled
  */
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+
+.macro GET_CURR_TASK_FIELD_PTR  off,  reg
+        add \reg, r25, \off
+.endm
+
+#else
+
 .macro GET_CURR_TASK_FIELD_PTR  off,  reg
         GET_CURR_TASK_ON_CPU  \reg
         add \reg, \reg, \off
 .endm
 
+#endif  /* CONFIG_ARC_CURR_IN_REG */
+
 #endif  /* __ASSEMBLY__ */
 
 #endif  /* __ASM_ARC_ENTRY_H */
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 860252ec3fa7..b7b155610067 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -29,6 +29,9 @@ struct thread_struct {
         unsigned long callee_reg;       /* pointer to callee regs */
         unsigned long fault_address;    /* dbls as brkpt holder as well */
         unsigned long cause_code;       /* Exception Cause Code (ECR) */
+#ifdef CONFIG_ARC_CURR_IN_REG
+        unsigned long user_r25;
+#endif
 #ifdef CONFIG_ARC_FPU_SAVE_RESTORE
         struct arc_fpu fpu;
 #endif
diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c
index d7770cc9aee3..0dc148ebce74 100644
--- a/arch/arc/kernel/asm-offsets.c
+++ b/arch/arc/kernel/asm-offsets.c
@@ -24,6 +24,9 @@ int main(void)
 
         DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
         DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg));
+#ifdef CONFIG_ARC_CURR_IN_REG
+        DEFINE(THREAD_USER_R25, offsetof(struct thread_struct, user_r25));
+#endif
         DEFINE(THREAD_FAULT_ADDR,
                offsetof(struct thread_struct, fault_address));
 
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index 647e37a5165e..fbf739cbaf7d 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -24,6 +24,9 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
         unsigned int prev = (unsigned int)prev_task;
         unsigned int next = (unsigned int)next_task;
         int num_words_to_skip = 1;
+#ifdef CONFIG_ARC_CURR_IN_REG
+        num_words_to_skip++;
+#endif
 
         __asm__ __volatile__(
                 /* FP/BLINK save generated by gcc (standard function prologue */
@@ -39,7 +42,9 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
                 "st.a    r22, [sp, -4]   \n\t"
                 "st.a    r23, [sp, -4]   \n\t"
                 "st.a    r24, [sp, -4]   \n\t"
+#ifndef CONFIG_ARC_CURR_IN_REG
                 "st.a    r25, [sp, -4]   \n\t"
+#endif
                 "sub     sp, sp, %4      \n\t"  /* create gutter at top */
 
                 /* set ksp of outgoing task in tsk->thread.ksp */
@@ -62,7 +67,9 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 
                 "add    sp, sp, %4     \n\t"    /* skip gutter at top */
 
+#ifndef CONFIG_ARC_CURR_IN_REG
                 "ld.ab   r25, [sp, 4]   \n\t"
+#endif
                 "ld.ab   r24, [sp, 4]   \n\t"
                 "ld.ab   r23, [sp, 4]   \n\t"
                 "ld.ab   r22, [sp, 4]   \n\t"
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index ce8670da8306..69d0d376e28b 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -32,6 +32,9 @@
  *   was being "CLEARED" rather then "SET". Since it is Loop INHIBIT Bit,
  *   setting it and not clearing it clears ZOL context
  *
+ * Vineetg: May 16th, 2008
+ *  - r25 now contains the Current Task when in kernel
+ *
  * Vineetg: Dec 22, 2007
  *    Minor Surgery of Low Level ISR to make it SMP safe
  *    - MMU_SCRATCH0 Reg used for freeing up r9 in Level 1 ISR
@@ -535,6 +538,17 @@ restore_regs :
         ; XXX can this be optimised out
         IRQ_DISABLE_SAVE    r9, r10     ;@r10 has prisitine (pre-disable) copy
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+        ; Restore User R25
+        ; Earlier this used to be only for returning to user mode
+        ; However with 2 levels of IRQ this can also happen even if
+        ; in kernel mode
+        ld r9, [sp, PT_sp]
+        brhs r9, VMALLOC_START, 8f
+        RESTORE_USER_R25
+8:
+#endif
+
         ; Restore REG File. In case multiple Events outstanding,
         ; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None
         ; Note that we use realtime STATUS32 (not pt_regs->status32) to