[PATCH v3 62/70] powerpc/mm: Add radix support for hugetlb

[Michael Ellerman <mpe@ellerman.id.au>]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hugetlb-radix.h | 14 ++++
 arch/powerpc/include/asm/hugetlb.h                 | 14 ++++
 arch/powerpc/mm/Makefile                           |  1 +
 arch/powerpc/mm/hugetlbpage-radix.c                | 87 ++++++++++++++++++++++
 arch/powerpc/mm/hugetlbpage.c                      |  8 +-
 arch/powerpc/mm/tlb-radix.c                        |  9 +++
 6 files changed, 132 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
 create mode 100644 arch/powerpc/mm/hugetlbpage-radix.c

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
new file mode 100644
index 000000000000..60f47649306f
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_RADIX_H
+#define _ASM_POWERPC_BOOK3S_64_HUGETLB_RADIX_H
+/*
+ * For radix we want generic code to handle hugetlb. But then if we want
+ * both hash and radix to be enabled together we need to workaround the
+ * limitations.
+ */
+void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern unsigned long
+radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				unsigned long len, unsigned long pgoff,
+				unsigned long flags);
+#endif
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 42814f0567cc..e2d9f4996e5c 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -8,6 +8,8 @@
 extern struct kmem_cache *hugepte_cache;
 
 #ifdef CONFIG_PPC_BOOK3S_64
+
+#include <asm/book3s/64/hugetlb-radix.h>
 /*
  * This should work for other subarchs too. But right now we use the
  * new format only for 64bit book3s
@@ -31,7 +33,19 @@ static inline unsigned int hugepd_shift(hugepd_t hpd)
 {
 	return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
 }
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+				      unsigned long vmaddr)
+{
+	if (radix_enabled())
+		return radix__flush_hugetlb_page(vma, vmaddr);
+}
 
+static inline void __local_flush_hugetlb_page(struct vm_area_struct *vma,
+					      unsigned long vmaddr)
+{
+	if (radix_enabled())
+		return radix__local_flush_hugetlb_page(vma, vmaddr);
+}
 #else
 
 static inline pte_t *hugepd_page(hugepd_t hpd)
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 48aa11ae6a6b..47511dd00599 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-y				+= hugetlbpage.o
 ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
+obj-$(CONFIG_PPC_RADIX_MMU)	+= hugetlbpage-radix.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
 endif
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
new file mode 100644
index 000000000000..1e11559e1aac
--- /dev/null
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -0,0 +1,87 @@
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/machdep.h>
+#include <asm/mman.h>
+
+void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+	unsigned long ap, shift;
+	struct hstate *hstate = hstate_file(vma->vm_file);
+
+	shift = huge_page_shift(hstate);
+	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		ap = mmu_get_ap(MMU_PAGE_2M);
+	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
+		ap = mmu_get_ap(MMU_PAGE_1G);
+	else {
+		WARN(1, "Wrong huge page shift\n");
+		return ;
+	}
+	radix___flush_tlb_page(vma->vm_mm, vmaddr, ap, 0);
+}
+
+void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+	unsigned long ap, shift;
+	struct hstate *hstate = hstate_file(vma->vm_file);
+
+	shift = huge_page_shift(hstate);
+	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		ap = mmu_get_ap(MMU_PAGE_2M);
+	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
+		ap = mmu_get_ap(MMU_PAGE_1G);
+	else {
+		WARN(1, "Wrong huge page shift\n");
+		return ;
+	}
+	radix___local_flush_tlb_page(vma->vm_mm, vmaddr, ap, 0);
+}
+
+/*
+ * A vairant of hugetlb_get_unmapped_area doing topdown search
+ * FIXME!! should we do as x86 does or non hugetlb area does ?
+ * ie, use topdown or not based on mmap_is_legacy check ?
+ */
+unsigned long
+radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				unsigned long len, unsigned long pgoff,
+				unsigned long flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (addr) {
+		addr = ALIGN(addr, huge_page_size(h));
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+	/*
+	 * We are always doing an topdown search here. Slice code
+	 * does that too.
+	 */
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = current->mm->mmap_base;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	return vm_unmapped_area(&info);
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7d677ef51033..790c5de3b183 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -711,6 +711,9 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
+	if (radix_enabled())
+		return radix__hugetlb_get_unmapped_area(file, addr, len,
+						       pgoff, flags);
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
 }
 #endif
@@ -823,7 +826,7 @@ static int __init hugetlbpage_init(void)
 {
 	int psize;
 
-	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
+	if (!radix_enabled() && !mmu_has_feature(MMU_FTR_16M_PAGE))
 		return -ENODEV;
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
@@ -863,6 +866,9 @@ static int __init hugetlbpage_init(void)
 		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
 	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
 		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
+
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index ecfa00f81f1e..0fdaf93a3e09 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -141,6 +141,11 @@ void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+	/* need the return fix for nohash.c */
+	if (vma && is_vm_hugetlb_page(vma))
+		return __local_flush_hugetlb_page(vma, vmaddr);
+#endif
 	radix___local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
 			       mmu_get_ap(mmu_virtual_psize), 0);
 }
@@ -202,6 +207,10 @@ bail:
 
 void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+	if (vma && is_vm_hugetlb_page(vma))
+		return flush_hugetlb_page(vma, vmaddr);
+#endif
 	radix___flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
 			 mmu_get_ap(mmu_virtual_psize), 0);
 }
-- 
2.5.0