powerpc/mm/hash64: Map all the kernel regions in the same 0xc range

This patch maps vmalloc, IO and vmemap regions in the 0xc address range
instead of the current 0xd and 0xf range. This brings the mapping closer
to radix translation mode.

With hash 64K page size each of this region is 512TB whereas with 4K config
we are limited by the max page table range of 64TB and hence there regions
are of 16TB size.

The kernel mapping is now:

 On 4K hash

     kernel_region_map_size = 16TB
     kernel vmalloc start   = 0xc000100000000000
     kernel IO start        = 0xc000200000000000
     kernel vmemmap start   = 0xc000300000000000

64K hash, 64K radix and 4k radix:

     kernel_region_map_size = 512TB
     kernel vmalloc start   = 0xc008000000000000
     kernel IO start        = 0xc00a000000000000
     kernel vmemmap start   = 0xc00c000000000000

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

7 files changed, 46 insertions, 30 deletions

diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index c8da352e8686..9b0321061bc8 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -105,7 +105,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	u64 vsid, vsidkey;
 	int psize, ssize;
 
-	switch (REGION_ID(ea)) {
+	switch (get_region_id(ea)) {
 	case USER_REGION_ID:
 		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
 		if (mm == NULL)
@@ -117,10 +117,14 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 		break;
 	case VMALLOC_REGION_ID:
 		pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
-		if (ea < VMALLOC_END)
-			psize = mmu_vmalloc_psize;
-		else
-			psize = mmu_io_psize;
+		psize = mmu_vmalloc_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		vsidkey = SLB_VSID_KERNEL;
+		break;
+	case IO_REGION_ID:
+		pr_devel("%s: 0x%llx -- IO_REGION_ID\n", __func__, ea);
+		psize = mmu_io_psize;
 		ssize = mmu_kernel_ssize;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		vsidkey = SLB_VSID_KERNEL;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index f6ffe8545717..9c4ae4aa133e 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1009,12 +1009,11 @@ void __init hash__early_init_mmu(void)
 	__pgd_val_bits = HASH_PGD_VAL_BITS;
 
 	__kernel_virt_start = H_KERN_VIRT_START;
-	__kernel_virt_size = H_KERN_VIRT_SIZE;
 	__vmalloc_start = H_VMALLOC_START;
 	__vmalloc_end = H_VMALLOC_END;
 	__kernel_io_start = H_KERN_IO_START;
 	__kernel_io_end = H_KERN_IO_END;
-	vmemmap = (struct page *)H_VMEMMAP_BASE;
+	vmemmap = (struct page *)H_VMEMMAP_START;
 	ioremap_bot = IOREMAP_BASE;
 
 #ifdef CONFIG_PCI
@@ -1241,7 +1240,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 	trace_hash_fault(ea, access, trap);
 
 	/* Get region & vsid */
- 	switch (REGION_ID(ea)) {
+	switch (get_region_id(ea)) {
 	case USER_REGION_ID:
 		user_region = 1;
 		if (! mm) {
@@ -1255,10 +1254,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		break;
 	case VMALLOC_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
-		if (ea < VMALLOC_END)
-			psize = mmu_vmalloc_psize;
-		else
-			psize = mmu_io_psize;
+		psize = mmu_vmalloc_psize;
+		ssize = mmu_kernel_ssize;
+		break;
+
+	case IO_REGION_ID:
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		psize = mmu_io_psize;
 		ssize = mmu_kernel_ssize;
 		break;
 	default:
@@ -1424,7 +1426,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
 
-	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+	if ((get_region_id(ea) == VMALLOC_REGION_ID) ||
+	    (get_region_id(ea) == IO_REGION_ID))
 		mm = &init_mm;
 
 	if (dsisr & DSISR_NOHPTE)
@@ -1440,8 +1443,9 @@ int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
 	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
+	unsigned int region_id = get_region_id(ea);
 
-	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+	if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
 		mm = &init_mm;
 
 	if (dsisr & DSISR_NOHPTE)
@@ -1458,7 +1462,7 @@ int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
 	 * 2) user space access kernel space.
 	 */
 	access |= _PAGE_PRIVILEGED;
-	if ((msr & MSR_PR) || (REGION_ID(ea) == USER_REGION_ID))
+	if ((msr & MSR_PR) || (region_id == USER_REGION_ID))
 		access &= ~_PAGE_PRIVILEGED;
 
 	if (trap == 0x400)
@@ -1502,7 +1506,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	int rc, ssize, update_flags = 0;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0);
 
-	BUG_ON(REGION_ID(ea) != USER_REGION_ID);
+	BUG_ON(get_region_id(ea) != USER_REGION_ID);
 
 	if (!should_hash_preload(mm, ea))
 		return;
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 4c1a9843d0f2..4d9fa9e900d5 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -136,6 +136,10 @@ static int __map_kernel_page(unsigned long ea, unsigned long pa,
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
 
+#ifdef CONFIG_PPC_64K_PAGES
+	BUILD_BUG_ON(RADIX_KERN_MAP_SIZE != (1UL << MAX_EA_BITS_PER_CONTEXT));
+#endif
+
 	if (unlikely(!slab_is_available()))
 		return early_map_kernel_page(ea, pa, flags, map_page_size,
 						nid, region_start, region_end);
@@ -601,12 +605,11 @@ void __init radix__early_init_mmu(void)
 	__pgd_val_bits = RADIX_PGD_VAL_BITS;
 
 	__kernel_virt_start = RADIX_KERN_VIRT_START;
-	__kernel_virt_size = RADIX_KERN_VIRT_SIZE;
 	__vmalloc_start = RADIX_VMALLOC_START;
 	__vmalloc_end = RADIX_VMALLOC_END;
 	__kernel_io_start = RADIX_KERN_IO_START;
 	__kernel_io_end = RADIX_KERN_IO_END;
-	vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
+	vmemmap = (struct page *)RADIX_VMEMMAP_START;
 	ioremap_bot = IOREMAP_BASE;
 
 #ifdef CONFIG_PCI
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 7cea39bdf05f..56068cac2a3c 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -90,8 +90,6 @@ unsigned long __pgd_val_bits;
 EXPORT_SYMBOL(__pgd_val_bits);
 unsigned long __kernel_virt_start;
 EXPORT_SYMBOL(__kernel_virt_start);
-unsigned long __kernel_virt_size;
-EXPORT_SYMBOL(__kernel_virt_size);
 unsigned long __vmalloc_start;
 EXPORT_SYMBOL(__vmalloc_start);
 unsigned long __vmalloc_end;
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index b430e4e08af6..b9bda0105841 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -500,7 +500,7 @@ static void populate_markers(void)
 	address_markers[7].start_address = IOREMAP_BASE;
 	address_markers[8].start_address = IOREMAP_END;
 #ifdef CONFIG_PPC_BOOK3S_64
-	address_markers[9].start_address =  H_VMEMMAP_BASE;
+	address_markers[9].start_address =  H_VMEMMAP_START;
 #else
 	address_markers[9].start_address =  VMEMMAP_BASE;
 #endif
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 37138428ab55..63fc56feea15 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -303,8 +303,9 @@ static void populate_markers(void)
 	address_markers[i++].start_address = PHB_IO_END;
 	address_markers[i++].start_address = IOREMAP_BASE;
 	address_markers[i++].start_address = IOREMAP_END;
+	/* What is the ifdef about? */
 #ifdef CONFIG_PPC_BOOK3S_64
-	address_markers[i++].start_address =  H_VMEMMAP_BASE;
+	address_markers[i++].start_address =  H_VMEMMAP_START;
 #else
 	address_markers[i++].start_address =  VMEMMAP_BASE;
 #endif
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 78c0c0a0e355..721cb09c9044 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -694,7 +694,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
 	if (id == KERNEL_REGION_ID) {
 
 		/* We only support upto MAX_PHYSMEM_BITS */
-		if ((ea & ~REGION_MASK) > (1UL << MAX_PHYSMEM_BITS))
+		if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS))
 			return -EFAULT;
 
 		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
@@ -702,20 +702,25 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	} else if (id == VMEMMAP_REGION_ID) {
 
-		if ((ea & ~REGION_MASK) >= (1ULL << MAX_EA_BITS_PER_CONTEXT))
+		if (ea >= H_VMEMMAP_END)
 			return -EFAULT;
 
 		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp;
 #endif
 	} else if (id == VMALLOC_REGION_ID) {
 
-		if ((ea & ~REGION_MASK) >= (1ULL << MAX_EA_BITS_PER_CONTEXT))
+		if (ea >= H_VMALLOC_END)
 			return -EFAULT;
 
-		if (ea < H_VMALLOC_END)
-			flags = local_paca->vmalloc_sllp;
-		else
-			flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+		flags = local_paca->vmalloc_sllp;
+
+	} else if (id == IO_REGION_ID) {
+
+		if (ea >= H_KERN_IO_END)
+			return -EFAULT;
+
+		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+
 	} else {
 		return -EFAULT;
 	}
@@ -725,6 +730,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
 		ssize = MMU_SEGSIZE_256M;
 
 	context = get_kernel_context(ea);
+
 	return slb_insert_entry(ea, context, flags, ssize, true);
 }
 
@@ -761,7 +767,7 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
 
 long do_slb_fault(struct pt_regs *regs, unsigned long ea)
 {
-	unsigned long id = REGION_ID(ea);
+	unsigned long id = get_region_id(ea);
 
 	/* IRQs are not reconciled here, so can't check irqs_disabled */
 	VM_WARN_ON(mfmsr() & MSR_EE);