[PATCH 3/3] powerpc/64s/radix: Enable HAVE_ARCH_HUGE_VMAP

[Nicholas Piggin]

This sets the HAVE_ARCH_HUGE_VMAP option, and defines the required
page table functions.

This enables huge (2MB and 1GB) ioremap mappings. I don't have a
benchmark for this change, but huge vmap will be used by a later core
kernel change to enable huge vmalloc memory mappings. This improves
cached `git diff` performance by about 5% on a 2-node POWER9 with 32MB
size dentry cache hash.

  Profiling git diff dTLB misses with a vanilla kernel:

  81.75%  git      [kernel.vmlinux]    [k] __d_lookup_rcu
   7.21%  git      [kernel.vmlinux]    [k] strncpy_from_user
   1.77%  git      [kernel.vmlinux]    [k] find_get_entry
   1.59%  git      [kernel.vmlinux]    [k] kmem_cache_free

            40,168      dTLB-miss
       0.100342754 seconds time elapsed

  With powerpc huge vmalloc:

             2,987      dTLB-miss
       0.095933138 seconds time elapsed

Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 .../admin-guide/kernel-parameters.txt         |   2 +-
 arch/powerpc/Kconfig                          |   1 +
 arch/powerpc/include/asm/book3s/64/pgtable.h  |   8 ++
 arch/powerpc/mm/book3s64/radix_pgtable.c      | 100 ++++++++++++++++++
 4 files changed, 110 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 138f6664b2e2..a4c3538857e9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2927,7 +2927,7 @@
 			register save and restore. The kernel will only save
 			legacy floating-point registers on task switch.
 
-	nohugeiomap	[KNL,x86] Disable kernel huge I/O mappings.
+	nohugeiomap	[KNL,x86,PPC] Disable kernel huge I/O mappings.
 
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8c1c636308c8..f0e5b38d52e8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -167,6 +167,7 @@ config PPC
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32
 	select HAVE_ARCH_KGDB
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index ccf00a8b98c6..5faceeefd9f9 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -274,6 +274,14 @@ extern unsigned long __vmalloc_end;
 #define VMALLOC_START	__vmalloc_start
 #define VMALLOC_END	__vmalloc_end
 
+static inline unsigned int ioremap_max_order(void)
+{
+	if (radix_enabled())
+		return PUD_SHIFT;
+	return 7 + PAGE_SHIFT; /* default from linux/vmalloc.h */
+}
+#define IOREMAP_MAX_ORDER ioremap_max_order()
+
 extern unsigned long __kernel_virt_start;
 extern unsigned long __kernel_virt_size;
 extern unsigned long __kernel_io_start;
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index db993bc1aef3..35cf04bbd50b 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1124,6 +1124,106 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
 	set_pte_at(mm, addr, ptep, pte);
 }
 
+int __init arch_ioremap_pud_supported(void)
+{
+	/* HPT does not cope with large pages in the vmalloc area */
+	return radix_enabled();
+}
+
+int __init arch_ioremap_pmd_supported(void)
+{
+	return radix_enabled();
+}
+
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+	return 0;
+}
+
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	pte_t *ptep = (pte_t *)pud;
+	pte_t new_pud = pfn_pte(__phys_to_pfn(addr), prot);
+
+	if (!radix_enabled())
+		return 0;
+
+	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud);
+
+	return 1;
+}
+
+int pud_clear_huge(pud_t *pud)
+{
+	if (pud_huge(*pud)) {
+		pud_clear(pud);
+		return 1;
+	}
+
+	return 0;
+}
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	pmd_t *pmd;
+	int i;
+
+	pmd = (pmd_t *)pud_page_vaddr(*pud);
+	pud_clear(pud);
+
+	flush_tlb_kernel_range(addr, addr + PUD_SIZE);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd[i])) {
+			pte_t *pte;
+			pte = (pte_t *)pmd_page_vaddr(pmd[i]);
+
+			pte_free_kernel(&init_mm, pte);
+		}
+	}
+
+	pmd_free(&init_mm, pmd);
+
+	return 1;
+}
+
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	pte_t *ptep = (pte_t *)pmd;
+	pte_t new_pmd = pfn_pte(__phys_to_pfn(addr), prot);
+
+	if (!radix_enabled())
+		return 0;
+
+	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd);
+
+	return 1;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (pmd_huge(*pmd)) {
+		pmd_clear(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte;
+
+	pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pmd_clear(pmd);
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+
+	pte_free_kernel(&init_mm, pte);
+
+	return 1;
+}
+
 int radix__ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
 			pgprot_t prot, int nid)
 {
-- 
2.20.1