[PATCH v2 4/4] powerpc/mm/book3s: Split radix and hash MAX_PHYSMEM limit
Aneesh Kumar K.V
aneesh.kumar at linux.ibm.com
Mon Jun 8 17:09:04 AEST 2020
MAX_PHYSMEM #define is used along with sparsemem to determine the SECTION_SHIFT
value. Powerpc also uses the same value to limit the max memory enabled on the
system. With 4K PAGE_SIZE and hash translation mode, we want to limit the max
memory enabled to 64TB due to page table size restrictions. However, with
radix translation, we don't have these restrictions. Hence split the radix
and hash MA_PHYSMEM limit and use different limit for each of them.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/hash-4k.h | 5 +++++
arch/powerpc/include/asm/book3s/64/hash-64k.h | 13 +++++++++++++
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 4 ++--
arch/powerpc/include/asm/book3s/64/mmu.h | 15 ---------------
arch/powerpc/include/asm/book3s/64/pgtable.h | 7 +++++++
arch/powerpc/include/asm/book3s/64/radix.h | 16 ++++++++++++++++
arch/powerpc/kernel/prom.c | 5 +++++
arch/powerpc/mm/book3s64/slb.c | 4 ++--
8 files changed, 50 insertions(+), 19 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 80c953414882..2e86d9b35766 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -22,6 +22,11 @@
#define REGION_SHIFT (40)
#define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT)
+/*
+ * Limits the linear mapping range
+ */
+#define H_MAX_PHYSMEM_BITS 46
+
/*
* Define the address range of the kernel non-linear virtual area (61TB)
*/
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 0729c034e56f..16c040d19a2b 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -7,6 +7,19 @@
#define H_PUD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB
#define H_PGD_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 16TB = 4PB
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME)
+#define H_MAX_PHYSMEM_BITS 51
+#else
+#define H_MAX_PHYSMEM_BITS 46
+#endif
/*
* Each context is 512TB size. SLB miss for first context/default context
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 3fa1b962dc27..84817466a3dd 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -577,8 +577,8 @@ extern void slb_set_size(u16 size);
* For vmalloc and memmap, we use just one context with 512TB. With 64 byte
* struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)).
*/
-#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT)
-#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT))
+#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT)
+#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT))
#else
#define MAX_KERNEL_CTX_CNT 1
#endif
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 5393a535240c..6202649e3e11 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -27,21 +27,6 @@ struct mmu_psize_def {
extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
#endif /* __ASSEMBLY__ */
-/*
- * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
- * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
- * page_to_nid does a page->section->node lookup
- * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
- * memory requirements with large number of sections.
- * 51 bits is the max physical real address on POWER9
- */
-#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \
- defined(CONFIG_PPC_64K_PAGES)
-#define MAX_PHYSMEM_BITS 51
-#else
-#define MAX_PHYSMEM_BITS 46
-#endif
-
/* 64-bit classic hash table MMU */
#include <asm/book3s/64/mmu-hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index f17442c3a092..4a6a0c51a733 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -295,6 +295,13 @@ extern unsigned long pci_io_base;
#include <asm/book3s/64/hash.h>
#include <asm/book3s/64/radix.h>
+#if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS
+#define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS
+#else
+#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS
+#endif
+
+
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/pgtable-64k.h>
#else
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 0cba794c4fb8..c7813dc628fc 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -91,6 +91,22 @@
* +------------------------------+ Kernel linear (0xc.....)
*/
+
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME)
+#define R_MAX_PHYSMEM_BITS 51
+#else
+#define R_MAX_PHYSMEM_BITS 46
+#endif
+
#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000)
/*
* 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6a3bac357e24..238349dd101a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -771,6 +771,11 @@ void __init early_init_devtree(void *params)
limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
memblock_enforce_memory_limit(limit);
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES)
+ if (!early_radix_enabled())
+ memblock_cap_memory_range(0, 1UL << (H_MAX_PHYSMEM_BITS));
+#endif
+
memblock_allow_resize();
memblock_dump_all();
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 8141e8b40ee5..11d65de400e1 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -765,8 +765,8 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
if (id == LINEAR_MAP_REGION_ID) {
- /* We only support upto MAX_PHYSMEM_BITS */
- if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS))
+ /* We only support upto H_MAX_PHYSMEM_BITS */
+ if ((ea & EA_MASK) > (1UL << H_MAX_PHYSMEM_BITS))
return -EFAULT;
flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
--
2.26.2
More information about the Linuxppc-dev
mailing list