parisc: Switch from DISCONTIGMEM to SPARSEMEM

The commit 1c30844d2dfe ("mm: reclaim small amounts of memory when an
external fragmentation event occurs") breaks memory management on a
parisc c8000 workstation with this memory layout:

	0) Start 0x0000000000000000 End 0x000000003fffffff Size   1024 MB
	1) Start 0x0000000100000000 End 0x00000001bfdfffff Size   3070 MB
	2) Start 0x0000004040000000 End 0x00000040ffffffff Size   3072 MB

With the patch 1c30844d2dfe, the kernel will incorrectly reclaim the
first zone when it fills up, ignoring the fact that there are two
completely free zones. Basiscally, it limits cache size to 1GiB.

The parisc kernel is currently using the DISCONTIGMEM implementation,
but isn't NUMA. Avoid this issue or strange work-arounds by switching to
the more commonly used SPARSEMEM implementation.

Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs")
Signed-off-by: Helge Deller <deller@gmx.de>

1 files changed, 47 insertions, 55 deletions

diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index b2b52de2b82b..513f747b0d9d 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -32,6 +32,7 @@
 #include <asm/mmzone.h>
 #include <asm/sections.h>
 #include <asm/msgbuf.h>
+#include <asm/sparsemem.h>
 
 extern int  data_start;
 extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
@@ -48,11 +49,6 @@ pmd_t pmd0[PTRS_PER_PMD] __attribute__ ((__section__ (".data..vm0.pmd"), aligned
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__ ((__section__ (".data..vm0.pgd"), aligned(PAGE_SIZE)));
 pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __attribute__ ((__section__ (".data..vm0.pte"), aligned(PAGE_SIZE)));
 
-#ifdef CONFIG_DISCONTIGMEM
-struct node_map_data node_data[MAX_NUMNODES] __read_mostly;
-signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
-#endif
-
 static struct resource data_resource = {
 	.name	= "Kernel data",
 	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
@@ -76,11 +72,11 @@ static struct resource sysram_resources[MAX_PHYSMEM_RANGES] __read_mostly;
  * information retrieved in kernel/inventory.c.
  */
 
-physmem_range_t pmem_ranges[MAX_PHYSMEM_RANGES] __read_mostly;
-int npmem_ranges __read_mostly;
+physmem_range_t pmem_ranges[MAX_PHYSMEM_RANGES] __initdata;
+int npmem_ranges __initdata;
 
 #ifdef CONFIG_64BIT
-#define MAX_MEM         (~0UL)
+#define MAX_MEM         (1UL << MAX_PHYSMEM_BITS)
 #else /* !CONFIG_64BIT */
 #define MAX_MEM         (3584U*1024U*1024U)
 #endif /* !CONFIG_64BIT */
@@ -119,7 +115,7 @@ static void __init mem_limit_func(void)
 static void __init setup_bootmem(void)
 {
 	unsigned long mem_max;
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_SPARSEMEM
 	physmem_range_t pmem_holes[MAX_PHYSMEM_RANGES - 1];
 	int npmem_holes;
 #endif
@@ -137,23 +133,20 @@ static void __init setup_bootmem(void)
 		int j;
 
 		for (j = i; j > 0; j--) {
-			unsigned long tmp;
+			physmem_range_t tmp;
 
 			if (pmem_ranges[j-1].start_pfn <
 			    pmem_ranges[j].start_pfn) {
 
 				break;
 			}
-			tmp = pmem_ranges[j-1].start_pfn;
-			pmem_ranges[j-1].start_pfn = pmem_ranges[j].start_pfn;
-			pmem_ranges[j].start_pfn = tmp;
-			tmp = pmem_ranges[j-1].pages;
-			pmem_ranges[j-1].pages = pmem_ranges[j].pages;
-			pmem_ranges[j].pages = tmp;
+			tmp = pmem_ranges[j-1];
+			pmem_ranges[j-1] = pmem_ranges[j];
+			pmem_ranges[j] = tmp;
 		}
 	}
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_SPARSEMEM
 	/*
 	 * Throw out ranges that are too far apart (controlled by
 	 * MAX_GAP).
@@ -165,7 +158,7 @@ static void __init setup_bootmem(void)
 			 pmem_ranges[i-1].pages) > MAX_GAP) {
 			npmem_ranges = i;
 			printk("Large gap in memory detected (%ld pages). "
-			       "Consider turning on CONFIG_DISCONTIGMEM\n",
+			       "Consider turning on CONFIG_SPARSEMEM\n",
 			       pmem_ranges[i].start_pfn -
 			       (pmem_ranges[i-1].start_pfn +
 			        pmem_ranges[i-1].pages));
@@ -230,9 +223,8 @@ static void __init setup_bootmem(void)
 
 	printk(KERN_INFO "Total Memory: %ld MB\n",mem_max >> 20);
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_SPARSEMEM
 	/* Merge the ranges, keeping track of the holes */
-
 	{
 		unsigned long end_pfn;
 		unsigned long hole_pages;
@@ -255,18 +247,6 @@ static void __init setup_bootmem(void)
 	}
 #endif
 
-#ifdef CONFIG_DISCONTIGMEM
-	for (i = 0; i < MAX_PHYSMEM_RANGES; i++) {
-		memset(NODE_DATA(i), 0, sizeof(pg_data_t));
-	}
-	memset(pfnnid_map, 0xff, sizeof(pfnnid_map));
-
-	for (i = 0; i < npmem_ranges; i++) {
-		node_set_state(i, N_NORMAL_MEMORY);
-		node_set_online(i);
-	}
-#endif
-
 	/*
 	 * Initialize and free the full range of memory in each range.
 	 */
@@ -314,7 +294,7 @@ static void __init setup_bootmem(void)
 	memblock_reserve(__pa(KERNEL_BINARY_TEXT_START),
 			(unsigned long)(_end - KERNEL_BINARY_TEXT_START));
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_SPARSEMEM
 
 	/* reserve the holes */
 
@@ -360,6 +340,9 @@ static void __init setup_bootmem(void)
 
 	/* Initialize Page Deallocation Table (PDT) and check for bad memory. */
 	pdc_pdt_init();
+
+	memblock_allow_resize();
+	memblock_dump_all();
 }
 
 static int __init parisc_text_address(unsigned long vaddr)
@@ -713,37 +696,46 @@ static void __init gateway_init(void)
 		  PAGE_SIZE, PAGE_GATEWAY, 1);
 }
 
-void __init paging_init(void)
+static void __init parisc_bootmem_free(void)
 {
+	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
+	unsigned long holes_size[MAX_NR_ZONES] = { 0, };
+	unsigned long mem_start_pfn = ~0UL, mem_end_pfn = 0, mem_size_pfn = 0;
 	int i;
 
+	for (i = 0; i < npmem_ranges; i++) {
+		unsigned long start = pmem_ranges[i].start_pfn;
+		unsigned long size = pmem_ranges[i].pages;
+		unsigned long end = start + size;
+
+		if (mem_start_pfn > start)
+			mem_start_pfn = start;
+		if (mem_end_pfn < end)
+			mem_end_pfn = end;
+		mem_size_pfn += size;
+	}
+
+	zones_size[0] = mem_end_pfn - mem_start_pfn;
+	holes_size[0] = zones_size[0] - mem_size_pfn;
+
+	free_area_init_node(0, zones_size, mem_start_pfn, holes_size);
+}
+
+void __init paging_init(void)
+{
 	setup_bootmem();
 	pagetable_init();
 	gateway_init();
 	flush_cache_all_local(); /* start with known state */
 	flush_tlb_all_local(NULL);
 
-	for (i = 0; i < npmem_ranges; i++) {
-		unsigned long zones_size[MAX_NR_ZONES] = { 0, };
-
-		zones_size[ZONE_NORMAL] = pmem_ranges[i].pages;
-
-#ifdef CONFIG_DISCONTIGMEM
-		/* Need to initialize the pfnnid_map before we can initialize
-		   the zone */
-		{
-		    int j;
-		    for (j = (pmem_ranges[i].start_pfn >> PFNNID_SHIFT);
-			 j <= ((pmem_ranges[i].start_pfn + pmem_ranges[i].pages) >> PFNNID_SHIFT);
-			 j++) {
-			pfnnid_map[j] = i;
-		    }
-		}
-#endif
-
-		free_area_init_node(i, zones_size,
-				pmem_ranges[i].start_pfn, NULL);
-	}
+	/*
+	 * Mark all memblocks as present for sparsemem using
+	 * memory_present() and then initialize sparsemem.
+	 */
+	memblocks_present();
+	sparse_init();
+	parisc_bootmem_free();
 }
 
 #ifdef CONFIG_PA20