ARCv2: mm: TLB Miss optim: SMP builds can cache pgd pointer in mmu scratch reg

ARC700 exception (and intr handling) didn't have auto stack switching
thus had to rely on stashing a reg temporarily (to free it up) at a
known place in memory, allowing to code up the low level stack switching.
This however was not re-entrant in SMP which thus had to repurpose the
per-cpu MMU SCRATCH DATA register otherwise used to "cache" the task pdg
pointer (vs. reading it from mm struct)

The newer HS cores do have auto-stack switching and thus even SMP builds
can use the MMU SCRATCH reg as originally intended.

This patch fixes the restriction to ARC700 SMP builds only

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

diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 66a292335ee6770e96ecbbb3c5abb4ce4aaf898d..c3aa775878dc8709e38203d65504408b23e05067 100644 (file)
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -130,7 +130,7 @@
  * to be saved again on kernel mode stack, as part of pt_regs.
  *-------------------------------------------------------------*/
 .macro PROLOG_FREEUP_REG       reg, mem
-#ifdef CONFIG_SMP
+#ifndef ARC_USE_SCRATCH_REG
        sr  \reg, [ARC_REG_SCRATCH_DATA0]
 #else
        st  \reg, [\mem]
@@ -138,7 +138,7 @@
 .endm
 
 .macro PROLOG_RESTORE_REG      reg, mem
-#ifdef CONFIG_SMP
+#ifndef ARC_USE_SCRATCH_REG
        lr  \reg, [ARC_REG_SCRATCH_DATA0]
 #else
        ld  \reg, [\mem]

diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 98cadf1a09acfd9a6d4b0ca4900140d4054cef6a..0abacb82a72b830c060db265ee76f76e3229a641 100644 (file)
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -40,6 +40,10 @@
 #define ARC_REG_SCRATCH_DATA0  0x46c
 #endif
 
+#if defined(CONFIG_ISA_ARCV2) || !defined(CONFIG_SMP)
+#define        ARC_USE_SCRATCH_REG
+#endif
+
 /* Bits in MMU PID register */
 #define __TLB_ENABLE           (1 << 31)
 #define __PROG_ENABLE          (1 << 30)

diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 035470816be55e578e94bededfe8f544b12750f2..3a5e6a5b9ed64c819c17fdaab9a6d5095e2b6ae3 100644 (file)
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -144,7 +144,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
         */
        cpumask_set_cpu(cpu, mm_cpumask(next));
 
-#ifndef CONFIG_SMP
+#ifdef ARC_USE_SCRATCH_REG
        /* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */
        write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd);
 #endif

diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 7addd0301c51a73671197cfaa0cacc0b6cb71a64..ea14a8bfc6910ad3cf61eaf301ff9050a1aea6a3 100644 (file)
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -351,7 +351,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
  * Thus use this macro only when you are certain that "current" is current
  * e.g. when dealing with signal frame setup code etc
  */
-#ifndef CONFIG_SMP
+#ifdef ARC_USE_SCRATCH_REG
 #define pgd_offset_fast(mm, addr)      \
 ({                                     \
        pgd_t *pgd_base = (pgd_t *) read_aux_reg(ARC_REG_SCRATCH_DATA0);  \

diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 10025e199353322426d7fb7569c89a900885541d..417f05ac43977a7d28099790ebc17600498e4e04 100644 (file)
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -868,7 +868,7 @@ void arc_mmu_init(void)
        write_aux_reg(ARC_REG_PID, MMU_ENABLE);
 
        /* In smp we use this reg for interrupt 1 scratch */
-#ifndef CONFIG_SMP
+#ifdef ARC_USE_SCRATCH_REG
        /* swapper_pg_dir is the pgd for the kernel, used by vmalloc */
        write_aux_reg(ARC_REG_SCRATCH_DATA0, swapper_pg_dir);
 #endif

diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index c55d95dd2f3949f0fae10451ce8e02691ca03d9a..d6fbdeda400addfbc12e35dfc081a0c48f13bcae 100644 (file)
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -193,7 +193,7 @@ ex_saved_reg1:
 
        lr  r2, [efa]
 
-#ifndef CONFIG_SMP
+#ifdef ARC_USE_SCRATCH_REG
        lr  r1, [ARC_REG_SCRATCH_DATA0] ; current pgd
 #else
        GET_CURR_TASK_ON_CPU  r1