[PATCH v3 3/3] powerpc/fsl-book3e-64: Use paca for hugetlb TLB1 entry selection

[Scott Wood]

This keeps usage coordinated for hugetlb and indirect entries, which
should make entry selection more predictable and probably improve overall
performance when mixing the two.

Signed-off-by: Scott Wood <scottwood at freescale.com>
---
v3: no changes

v2: new patch
---
 arch/powerpc/mm/hugetlbpage-book3e.c | 51 +++++++++++++++++++++++++++++-------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
index 3bc7006..ee57ac2 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -8,6 +8,44 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC64
+static inline int tlb1_next(void)
+{
+	struct paca_struct *paca = get_paca();
+	struct tlb_core_data *tcd;
+	int this, next;
+
+	tcd = paca->tcd_ptr;
+	this = tcd->esel_next;
+
+	next = this + 1;
+	if (next >= tcd->esel_max)
+		next = tcd->esel_first;
+
+	tcd->esel_next = next;
+	return this;
+}
+#else
+static inline int tlb1_next(void)
+{
+	int index, ncams;
+
+	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	index = __get_cpu_var(next_tlbcam_idx);
+
+	/* Just round-robin the entries and wrap when we hit the end */
+	if (unlikely(index == ncams - 1))
+		__get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+	else
+		__get_cpu_var(next_tlbcam_idx)++;
+
+	return index;
+}
+#endif /* !PPC64 */
+#endif /* FSL */
+
 static inline int mmu_get_tsize(int psize)
 {
 	return mmu_psize_defs[psize].enc;
@@ -47,7 +85,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
 	struct mm_struct *mm;
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
-	int index, ncams;
+	int index;
 #endif
 
 	if (unlikely(is_kernel_addr(ea)))
@@ -77,18 +115,11 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
 	}
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
-	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
-
 	/* We have to use the CAM(TLB1) on FSL parts for hugepages */
-	index = __get_cpu_var(next_tlbcam_idx);
+	index = tlb1_next();
 	mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
-
-	/* Just round-robin the entries and wrap when we hit the end */
-	if (unlikely(index == ncams - 1))
-		__get_cpu_var(next_tlbcam_idx) = tlbcam_index;
-	else
-		__get_cpu_var(next_tlbcam_idx)++;
 #endif
+
 	mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
 	mas2 = ea & ~((1UL << shift) - 1);
 	mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
-- 
1.8.1.2