5 files changed, 161 insertions, 116 deletions

diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index b75b872ec154..3a63707a698b 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -308,18 +308,6 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
         unsigned long flags;
         siginfo_t info;
 
-#ifdef CONFIG_CHECKING
-        { 
-                unsigned long gs; 
-                struct x8664_pda *pda = cpu_pda + stack_smp_processor_id(); 
-                rdmsrl(MSR_GS_BASE, gs); 
-                if (gs != (unsigned long)pda) { 
-                        wrmsrl(MSR_GS_BASE, pda); 
-                        printk("page_fault: wrong gs %lx expected %p\n", gs, pda);
-                }
-        }
-#endif
-
         /* get the address */
         __asm__("movq %%cr2,%0":"=r" (address));
         if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
@@ -571,3 +559,10 @@ do_sigbus:
         force_sig_info(SIGBUS, &info, tsk);
         return;
 }
+
+static int __init enable_pagefaulttrace(char *str)
+{
+        page_fault_trace = 1;
+        return 0;
+}
+__setup("pagefaulttrace", enable_pagefaulttrace);
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index e60a1a848de8..286f6a624c3a 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -22,6 +22,7 @@
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
+#include <linux/pci.h>
 
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -36,16 +37,13 @@
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/smp.h>
+#include <asm/sections.h>
 
 #ifndef Dprintk
 #define Dprintk(x...)
 #endif
 
-#ifdef CONFIG_GART_IOMMU
-extern int swiotlb;
-#endif
-
-extern char _stext[];
+static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
@@ -86,9 +84,6 @@ void show_mem(void)
 
 /* References to section boundaries */
 
-extern char _text, _etext, _edata, __bss_start, _end[];
-extern char __init_begin, __init_end;
-
 int after_bootmem;
 
 static void *spp_getpage(void)
@@ -308,42 +303,81 @@ void __init init_memory_mapping(unsigned long start, unsigned long end)
                table_end<<PAGE_SHIFT);
 }
 
-extern struct x8664_pda cpu_pda[NR_CPUS];
+void __cpuinit zap_low_mappings(int cpu)
+{
+        if (cpu == 0) {
+                pgd_t *pgd = pgd_offset_k(0UL);
+                pgd_clear(pgd);
+        } else {
+                /*
+                 * For AP's, zap the low identity mappings by changing the cr3
+                 * to init_level4_pgt and doing local flush tlb all
+                 */
+                asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
+        }
+        __flush_tlb_all();
+}
 
-/* Assumes all CPUs still execute in init_mm */
-void zap_low_mappings(void)
+/* Compute zone sizes for the DMA and DMA32 zones in a node. */
+__init void
+size_zones(unsigned long *z, unsigned long *h,
+           unsigned long start_pfn, unsigned long end_pfn)
 {
-        pgd_t *pgd = pgd_offset_k(0UL);
-        pgd_clear(pgd);
-        flush_tlb_all();
+        int i;
+        unsigned long w;
+
+        for (i = 0; i < MAX_NR_ZONES; i++)
+                z[i] = 0;
+
+        if (start_pfn < MAX_DMA_PFN)
+                z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
+        if (start_pfn < MAX_DMA32_PFN) {
+                unsigned long dma32_pfn = MAX_DMA32_PFN;
+                if (dma32_pfn > end_pfn)
+                        dma32_pfn = end_pfn;
+                z[ZONE_DMA32] = dma32_pfn - start_pfn;
+        }
+        z[ZONE_NORMAL] = end_pfn - start_pfn;
+
+        /* Remove lower zones from higher ones. */
+        w = 0;
+        for (i = 0; i < MAX_NR_ZONES; i++) {
+                if (z[i])
+                        z[i] -= w;
+                w += z[i];
+        }
+
+        /* Compute holes */
+        w = 0;
+        for (i = 0; i < MAX_NR_ZONES; i++) {
+                unsigned long s = w;
+                w += z[i];
+                h[i] = e820_hole_size(s, w);
+        }
+
+        /* Add the space pace needed for mem_map to the holes too. */
+        for (i = 0; i < MAX_NR_ZONES; i++)
+                h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
+
+        /* The 16MB DMA zone has the kernel and other misc mappings.
+           Account them too */
+        if (h[ZONE_DMA]) {
+                h[ZONE_DMA] += dma_reserve;
+                if (h[ZONE_DMA] >= z[ZONE_DMA]) {
+                        printk(KERN_WARNING
+                                "Kernel too large and filling up ZONE_DMA?\n");
+                        h[ZONE_DMA] = z[ZONE_DMA];
+                }
+        }
 }
 
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
-        {
-                unsigned long zones_size[MAX_NR_ZONES];
-                unsigned long holes[MAX_NR_ZONES];
-                unsigned int max_dma;
-
-                memset(zones_size, 0, sizeof(zones_size));
-                memset(holes, 0, sizeof(holes));
-
-                max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-
-                if (end_pfn < max_dma) {
-                        zones_size[ZONE_DMA] = end_pfn;
-                        holes[ZONE_DMA] = e820_hole_size(0, end_pfn);
-                } else {
-                        zones_size[ZONE_DMA] = max_dma;
-                        holes[ZONE_DMA] = e820_hole_size(0, max_dma);
-                        zones_size[ZONE_NORMAL] = end_pfn - max_dma;
-                        holes[ZONE_NORMAL] = e820_hole_size(max_dma, end_pfn);
-                }
-                free_area_init_node(0, NODE_DATA(0), zones_size,
-                        __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
-        }
-        return;
+        unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
+        size_zones(zones, holes, 0, end_pfn);
+        free_area_init_node(0, NODE_DATA(0), zones,
+                            __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
 }
 #endif
 
@@ -438,19 +472,16 @@ void __init mem_init(void)
                 datasize >> 10,
                 initsize >> 10);
 
+#ifdef CONFIG_SMP
         /*
-         * Subtle. SMP is doing its boot stuff late (because it has to
-         * fork idle threads) - but it also needs low mappings for the
-         * protected-mode entry to work. We zap these entries only after
-         * the WP-bit has been tested.
+         * Sync boot_level4_pgt mappings with the init_level4_pgt
+         * except for the low identity mappings which are already zapped
+         * in init_level4_pgt. This sync-up is essential for AP's bringup
          */
-#ifndef CONFIG_SMP
-        zap_low_mappings();
+        memcpy(boot_level4_pgt+1, init_level4_pgt+1, (PTRS_PER_PGD-1)*sizeof(pgd_t));
 #endif
 }
 
-extern char __initdata_begin[], __initdata_end[];
-
 void free_initmem(void)
 {
         unsigned long addr;
@@ -464,7 +495,7 @@ void free_initmem(void)
                 totalram_pages++;
         }
         memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
-        printk ("Freeing unused kernel memory: %luk freed\n", (&__init_end - &__init_begin) >> 10);
+        printk ("Freeing unused kernel memory: %luk freed\n", (__init_end - __init_begin) >> 10);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -491,6 +522,8 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 #else                   
         reserve_bootmem(phys, len);    
 #endif
+        if (phys+len <= MAX_DMA_PFN*PAGE_SIZE)
+                dma_reserve += len / PAGE_SIZE;
 }
 
 int kern_addr_valid(unsigned long addr) 
@@ -532,10 +565,6 @@ extern int exception_trace, page_fault_trace;
 static ctl_table debug_table2[] = {
         { 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL,
           proc_dointvec },
-#ifdef CONFIG_CHECKING
-        { 100, "page-fault-trace", &page_fault_trace, sizeof(int), 0644, NULL,
-          proc_dointvec },
-#endif
         { 0, }
 }; 
 
diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c
index 65417b040c1b..a5663e0bb01c 100644
--- a/arch/x86_64/mm/k8topology.c
+++ b/arch/x86_64/mm/k8topology.c
@@ -108,6 +108,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
                 limit >>= 16; 
                 limit <<= 24; 
                 limit |= (1<<24)-1;
+                limit++;
 
                 if (limit > end_pfn << PAGE_SHIFT)
                         limit = end_pfn << PAGE_SHIFT;
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 214803821001..a828a01739cc 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -38,38 +38,57 @@ cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly;
 
 int numa_off __initdata;
 
-int __init compute_hash_shift(struct node *nodes, int numnodes)
+
+/*
+ * Given a shift value, try to populate memnodemap[]
+ * Returns :
+ * 1 if OK
+ * 0 if memnodmap[] too small (of shift too small)
+ * -1 if node overlap or lost ram (shift too big)
+ */
+static int __init populate_memnodemap(
+        const struct node *nodes, int numnodes, int shift)
 {
         int i; 
-        int shift = 20;
-        unsigned long addr,maxend=0;
-        
-        for (i = 0; i < numnodes; i++)
-                if ((nodes[i].start != nodes[i].end) && (nodes[i].end > maxend))
-                                maxend = nodes[i].end;
+        int res = -1;
+        unsigned long addr, end;
 
-        while ((1UL << shift) <  (maxend / NODEMAPSIZE))
-                shift++;
-
-        printk (KERN_DEBUG"Using %d for the hash shift. Max adder is %lx \n",
-                        shift,maxend);
-        memset(memnodemap,0xff,sizeof(*memnodemap) * NODEMAPSIZE);
+        memset(memnodemap, 0xff, sizeof(memnodemap));
         for (i = 0; i < numnodes; i++) {
-                if (nodes[i].start == nodes[i].end)
+                addr = nodes[i].start;
+                end = nodes[i].end;
+                if (addr >= end)
                         continue;
-                for (addr = nodes[i].start;
-                     addr < nodes[i].end;
-                     addr += (1UL << shift)) {
-                        if (memnodemap[addr >> shift] != 0xff) {
-                                printk(KERN_INFO
-        "Your memory is not aligned you need to rebuild your kernel "
-        "with a bigger NODEMAPSIZE shift=%d adder=%lu\n",
-                                        shift,addr);
+                if ((end >> shift) >= NODEMAPSIZE)
+                        return 0;
+                do {
+                        if (memnodemap[addr >> shift] != 0xff)
                                 return -1;
-                        } 
                         memnodemap[addr >> shift] = i;
-                } 
+                        addr += (1 << shift);
+                } while (addr < end);
+                res = 1;
         } 
+        return res;
+}
+
+int __init compute_hash_shift(struct node *nodes, int numnodes)
+{
+        int shift = 20;
+
+        while (populate_memnodemap(nodes, numnodes, shift + 1) >= 0)
+                shift++;
+
+        printk(KERN_DEBUG "Using %d for the hash shift.\n",
+                shift);
+
+        if (populate_memnodemap(nodes, numnodes, shift) != 1) {
+                printk(KERN_INFO
+        "Your memory is not aligned you need to rebuild your kernel "
+        "with a bigger NODEMAPSIZE shift=%d\n",
+                        shift);
+                return -1;
+        }
         return shift;
 }
 
@@ -94,7 +113,6 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
         start_pfn = start >> PAGE_SHIFT;
         end_pfn = end >> PAGE_SHIFT;
 
-        memory_present(nodeid, start_pfn, end_pfn);
         nodedata_phys = find_e820_area(start, end, pgdat_size); 
         if (nodedata_phys == -1L) 
                 panic("Cannot find memory pgdat in node %d\n", nodeid);
@@ -132,29 +150,14 @@ void __init setup_node_zones(int nodeid)
         unsigned long start_pfn, end_pfn; 
         unsigned long zones[MAX_NR_ZONES];
         unsigned long holes[MAX_NR_ZONES];
-        unsigned long dma_end_pfn;
 
-        memset(zones, 0, sizeof(unsigned long) * MAX_NR_ZONES); 
-        memset(holes, 0, sizeof(unsigned long) * MAX_NR_ZONES);
+        start_pfn = node_start_pfn(nodeid);
+        end_pfn = node_end_pfn(nodeid);
 
-        start_pfn = node_start_pfn(nodeid);
-        end_pfn = node_end_pfn(nodeid);
+        Dprintk(KERN_INFO "setting up node %d %lx-%lx\n",
+                nodeid, start_pfn, end_pfn);
 
-        Dprintk(KERN_INFO "setting up node %d %lx-%lx\n", nodeid, start_pfn, end_pfn);
-        
-        /* All nodes > 0 have a zero length zone DMA */ 
-        dma_end_pfn = __pa(MAX_DMA_ADDRESS) >> PAGE_SHIFT; 
-        if (start_pfn < dma_end_pfn) { 
-                zones[ZONE_DMA] = dma_end_pfn - start_pfn;
-                holes[ZONE_DMA] = e820_hole_size(start_pfn, dma_end_pfn);
-                zones[ZONE_NORMAL] = end_pfn - dma_end_pfn; 
-                holes[ZONE_NORMAL] = e820_hole_size(dma_end_pfn, end_pfn);
-
-        } else { 
-                zones[ZONE_NORMAL] = end_pfn - start_pfn; 
-                holes[ZONE_NORMAL] = e820_hole_size(start_pfn, end_pfn);
-        } 
-    
+        size_zones(zones, holes, start_pfn, end_pfn);
         free_area_init_node(nodeid, NODE_DATA(nodeid), zones,
                             start_pfn, holes);
 } 
@@ -171,7 +174,7 @@ void __init numa_init_array(void)
         for (i = 0; i < NR_CPUS; i++) {
                 if (cpu_to_node[i] != NUMA_NO_NODE)
                         continue;
-                cpu_to_node[i] = rr;
+                numa_set_node(i, rr);
                 rr = next_node(rr, node_online_map);
                 if (rr == MAX_NUMNODES)
                         rr = first_node(node_online_map);
@@ -205,8 +208,6 @@ static int numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
                 if (i == numa_fake-1)
                         sz = (end_pfn<<PAGE_SHIFT) - nodes[i].start;
                 nodes[i].end = nodes[i].start + sz;
-                if (i != numa_fake-1)
-                        nodes[i].end--;
                 printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n",
                        i,
                        nodes[i].start, nodes[i].end,
@@ -257,7 +258,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
         nodes_clear(node_online_map);
         node_set_online(0);
         for (i = 0; i < NR_CPUS; i++)
-                cpu_to_node[i] = 0;
+                numa_set_node(i, 0);
         node_to_cpumask[0] = cpumask_of_cpu(0);
         setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
 }
@@ -267,6 +268,12 @@ __cpuinit void numa_add_cpu(int cpu)
         set_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]);
 } 
 
+void __cpuinit numa_set_node(int cpu, int node)
+{
+        cpu_pda[cpu].nodenumber = node;
+        cpu_to_node[cpu] = node;
+}
+
 unsigned long __init numa_free_all_bootmem(void) 
 { 
         int i;
@@ -277,9 +284,26 @@ unsigned long __init numa_free_all_bootmem(void)
         return pages;
 } 
 
+#ifdef CONFIG_SPARSEMEM
+static void __init arch_sparse_init(void)
+{
+        int i;
+
+        for_each_online_node(i)
+                memory_present(i, node_start_pfn(i), node_end_pfn(i));
+
+        sparse_init();
+}
+#else
+#define arch_sparse_init() do {} while (0)
+#endif
+
 void __init paging_init(void)
 { 
         int i;
+
+        arch_sparse_init();
+
         for_each_online_node(i) {
                 setup_node_zones(i); 
         }
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index 4b2e844c15a7..33340bd1e328 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -71,8 +71,6 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end)
                         nd->start = nd->end;
         }
         if (nd->end > end) {
-                if (!(end & 0xfff))
-                        end--;
                 nd->end = end;
                 if (nd->start > nd->end)
                         nd->start = nd->end;
@@ -166,8 +164,6 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
                 if (nd->end < end)
                         nd->end = end;
         }
-        if (!(nd->end & 0xfff))
-                nd->end--;
         printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
                nd->start, nd->end);
 }
@@ -203,7 +199,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                 if (cpu_to_node[i] == NUMA_NO_NODE)
                         continue;
                 if (!node_isset(cpu_to_node[i], nodes_parsed))
-                        cpu_to_node[i] = NUMA_NO_NODE; 
+                        numa_set_node(i, NUMA_NO_NODE);
         }
         numa_init_array();
         return 0;