powerpc/mm/4k: Limit 4k page size config to 64TB virtual address space

Supporting 512TB requires us to do a order 3 allocation for level 1 page
table (pgd). This results in page allocation failures with certain workloads.
For now limit 4k linux page size config to 64TB.

Fixes: f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB")
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 15 insertions, 16 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b4b5e6b..0c4e470 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -8,7 +8,7 @@
 #define H_PTE_INDEX_SIZE  9
 #define H_PMD_INDEX_SIZE  7
 #define H_PUD_INDEX_SIZE  9
-#define H_PGD_INDEX_SIZE  12
+#define H_PGD_INDEX_SIZE  9
 
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index a2123f2..bb99b65 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -110,13 +110,18 @@ void release_thread(struct task_struct *);
 #define TASK_SIZE_128TB (0x0000800000000000UL)
 #define TASK_SIZE_512TB (0x0002000000000000UL)
 
-#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
 /*
  * Max value currently used:
  */
-#define TASK_SIZE_USER64	TASK_SIZE_512TB
+#define TASK_SIZE_USER64		TASK_SIZE_512TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
 #else
-#define TASK_SIZE_USER64	TASK_SIZE_64TB
+#define TASK_SIZE_USER64		TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
 #endif
 
 /*
@@ -132,7 +137,7 @@ void release_thread(struct task_struct *);
  * space during mmap's.
  */
 #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
 
 #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
@@ -143,21 +148,15 @@ void release_thread(struct task_struct *);
  * with 128TB and conditionally enable upto 512TB
  */
 #ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ? \
-				 TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ?			\
+				 TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
 #else
 #define DEFAULT_MAP_WINDOW	TASK_SIZE
 #endif
 
 #ifdef __powerpc64__
 
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Limit stack to 128TB */
-#define STACK_TOP_USER64 TASK_SIZE_128TB
-#else
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#endif
-
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
 #define STACK_TOP_USER32 TASK_SIZE_USER32
 
 #define STACK_TOP (is_32bit_task() ? \
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 71dcda9..857129a 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_PPC_MM_SLICES
 #ifdef CONFIG_PPC64
-	init_mm.context.addr_limit = TASK_SIZE_128TB;
+	init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 #else
 #error	"context.addr_limit not initialized."
 #endif
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index c6dca2a..a3edf81 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm)
 	 * mm->context.addr_limit. Default to max task size so that we copy the
 	 * default values to paca which will help us to handle slb miss early.
 	 */
-	mm->context.addr_limit = TASK_SIZE_128TB;
+	mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 
 	/*
 	 * The old code would re-promote on fork, we don't do that when using