Merge commit 'v2.6.38' into release

18 files changed, 75 insertions, 55 deletions

diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index 646aa78ba5fd..46a823882437 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -62,7 +62,12 @@ int main(int argc, char *argv[])
         if (fseek(f, -4L, SEEK_END)) {
                 perror(argv[1]);
         }
-        fread(&olen, sizeof olen, 1, f);
+
+        if (fread(&olen, sizeof(olen), 1, f) != 1) {
+                perror(argv[1]);
+                return 1;
+        }
+
         ilen = ftell(f);
         olen = getle32(&olen);
         fclose(f);
diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h
new file mode 100644
index 000000000000..e656ad8c0a2e
--- /dev/null
+++ b/arch/x86/include/asm/ce4100.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_CE4100_H_
+#define _ASM_CE4100_H_
+
+int ce4100_pci_init(void);
+
+#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4d0dfa0d998e..43a18c77676d 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -36,6 +36,11 @@
 #define MSR_IA32_PERFCTR1               0x000000c2
 #define MSR_FSB_FREQ                    0x000000cd
 
+#define MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
+#define NHM_C3_AUTO_DEMOTE              (1UL << 25)
+#define NHM_C1_AUTO_DEMOTE              (1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE          (1UL << 25)
+
 #define MSR_MTRRcap                     0x000000fe
 #define MSR_IA32_BBL_CR_CTL             0x00000119
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index ce1d54c8a433..3e094af443c3 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -176,7 +176,7 @@ struct bau_msg_payload {
 struct bau_msg_header {
         unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
         /* bits 5:0 */
-        unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */
+        unsigned int base_dest_nodeid:15; /* nasid of the */
         /* bits 20:6 */                   /* first bit in uvhub map */
         unsigned int command:8; /* message type */
         /* bits 28:21 */
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 13a389179514..452932d34730 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -106,8 +106,8 @@ void __init setup_bios_corruption_check(void)
                 addr += size;
         }
 
-        printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
-               num_scan_areas);
+        if (num_scan_areas)
+                printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas);
 }
 
 
@@ -143,12 +143,12 @@ static void check_corruption(struct work_struct *dummy)
 {
         check_for_bios_corruption();
         schedule_delayed_work(&bios_check_work,
-                round_jiffies_relative(corruption_check_period*HZ)); 
+                round_jiffies_relative(corruption_check_period*HZ));
 }
 
 static int start_periodic_check_for_corruption(void)
 {
-        if (!memory_corruption_check || corruption_check_period == 0)
+        if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0)
                 return 0;
 
         printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index bd1cac747f67..52c93648e492 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -158,9 +158,9 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 {
         if (c->x86 == 0x06) {
                 if (cpu_has(c, X86_FEATURE_EST))
-                        printk(KERN_WARNING PFX "Warning: EST-capable CPU "
-                               "detected. The acpi-cpufreq module offers "
-                               "voltage scaling in addition of frequency "
+                        printk_once(KERN_WARNING PFX "Warning: EST-capable "
+                               "CPU detected. The acpi-cpufreq module offers "
+                               "voltage scaling in addition to frequency "
                                "scaling. You should use that instead of "
                                "p4-clockmod, if possible.\n");
                 switch (c->x86_model) {
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index 4f6f679f2799..4a5a42b842ad 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -195,7 +195,7 @@ static unsigned int pcc_get_freq(unsigned int cpu)
 cmd_incomplete:
         iowrite16(0, &pcch_hdr->status);
         spin_unlock(&pcc_lock);
-        return -EINVAL;
+        return 0;
 }
 
 static int pcc_cpufreq_target(struct cpufreq_policy *policy,
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 35c7e65e59be..c567dec854f6 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1537,6 +1537,7 @@ static struct notifier_block cpb_nb = {
 static int __cpuinit powernowk8_init(void)
 {
         unsigned int i, supported_cpus = 0, cpu;
+        int rv;
 
         for_each_online_cpu(i) {
                 int rc;
@@ -1555,14 +1556,14 @@ static int __cpuinit powernowk8_init(void)
 
                 cpb_capable = true;
 
-                register_cpu_notifier(&cpb_nb);
-
                 msrs = msrs_alloc();
                 if (!msrs) {
                         printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
                         return -ENOMEM;
                 }
 
+                register_cpu_notifier(&cpb_nb);
+
                 rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
 
                 for_each_cpu(cpu, cpu_online_mask) {
@@ -1574,7 +1575,13 @@ static int __cpuinit powernowk8_init(void)
                         (cpb_enabled ? "on" : "off"));
         }
 
-        return cpufreq_register_driver(&cpufreq_amd64_driver);
+        rv = cpufreq_register_driver(&cpufreq_amd64_driver);
+        if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) {
+                unregister_cpu_notifier(&cpb_nb);
+                msrs_free(msrs);
+                msrs = NULL;
+        }
+        return rv;
 }
 
 /* driver entry point for term */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 7d90ceb882a4..20e3f8702d1e 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -229,15 +229,14 @@ void vmalloc_sync_all(void)
         for (address = VMALLOC_START & PMD_MASK;
              address >= TASK_SIZE && address < FIXADDR_TOP;
              address += PMD_SIZE) {
-
-                unsigned long flags;
                 struct page *page;
 
-                spin_lock_irqsave(&pgd_lock, flags);
+                spin_lock(&pgd_lock);
                 list_for_each_entry(page, &pgd_list, lru) {
                         spinlock_t *pgt_lock;
                         pmd_t *ret;
 
+                        /* the pgt_lock only for Xen */
                         pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 
                         spin_lock(pgt_lock);
@@ -247,7 +246,7 @@ void vmalloc_sync_all(void)
                         if (!ret)
                                 break;
                 }
-                spin_unlock_irqrestore(&pgd_lock, flags);
+                spin_unlock(&pgd_lock);
         }
 }
 
@@ -828,6 +827,13 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                unsigned long address, unsigned int fault)
 {
         if (fault & VM_FAULT_OOM) {
+                /* Kernel mode? Handle exceptions or die: */
+                if (!(error_code & PF_USER)) {
+                        up_read(&current->mm->mmap_sem);
+                        no_context(regs, error_code, address);
+                        return;
+                }
+
                 out_of_memory(regs, error_code, address);
         } else {
                 if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 71a59296af80..c14a5422e152 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -105,18 +105,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 
         for (address = start; address <= end; address += PGDIR_SIZE) {
                 const pgd_t *pgd_ref = pgd_offset_k(address);
-                unsigned long flags;
                 struct page *page;
 
                 if (pgd_none(*pgd_ref))
                         continue;
 
-                spin_lock_irqsave(&pgd_lock, flags);
+                spin_lock(&pgd_lock);
                 list_for_each_entry(page, &pgd_list, lru) {
                         pgd_t *pgd;
                         spinlock_t *pgt_lock;
 
                         pgd = (pgd_t *)page_address(page) + pgd_index(address);
+                        /* the pgt_lock only for Xen */
                         pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
                         spin_lock(pgt_lock);
 
@@ -128,7 +128,7 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 
                         spin_unlock(pgt_lock);
                 }
-                spin_unlock_irqrestore(&pgd_lock, flags);
+                spin_unlock(&pgd_lock);
         }
 }
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 95ea1551eebc..1337c51b07d7 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -780,11 +780,7 @@ void __cpuinit numa_add_cpu(int cpu)
         int physnid;
         int nid = NUMA_NO_NODE;
 
-        apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-        if (apicid != BAD_APICID)
-                nid = apicid_to_node[apicid];
-        if (nid == NUMA_NO_NODE)
-                nid = early_cpu_to_node(cpu);
+        nid = early_cpu_to_node(cpu);
         BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
 
         /*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index d343b3c81f3c..90825f2eb0f4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -57,12 +57,10 @@ static unsigned long direct_pages_count[PG_LEVEL_NUM];
 
 void update_page_count(int level, unsigned long pages)
 {
-        unsigned long flags;
-
         /* Protect against CPA */
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
         direct_pages_count[level] += pages;
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 }
 
 static void split_page_count(int level)
@@ -394,7 +392,7 @@ static int
 try_preserve_large_page(pte_t *kpte, unsigned long address,
                         struct cpa_data *cpa)
 {
-        unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
+        unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn;
         pte_t new_pte, old_pte, *tmp;
         pgprot_t old_prot, new_prot, req_prot;
         int i, do_split = 1;
@@ -403,7 +401,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
         if (cpa->force_split)
                 return 1;
 
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
         /*
          * Check for races, another CPU might have split this page
          * up already:
@@ -498,14 +496,14 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
         }
 
 out_unlock:
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 
         return do_split;
 }
 
 static int split_large_page(pte_t *kpte, unsigned long address)
 {
-        unsigned long flags, pfn, pfninc = 1;
+        unsigned long pfn, pfninc = 1;
         unsigned int i, level;
         pte_t *pbase, *tmp;
         pgprot_t ref_prot;
@@ -519,7 +517,7 @@ static int split_large_page(pte_t *kpte, unsigned long address)
         if (!base)
                 return -ENOMEM;
 
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
         /*
          * Check for races, another CPU might have split this page
          * up for us already:
@@ -591,7 +589,7 @@ out_unlock:
          */
         if (base)
                 __free_page(base);
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 
         return 0;
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 500242d3c96d..0113d19c8aa6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -121,14 +121,12 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 
 static void pgd_dtor(pgd_t *pgd)
 {
-        unsigned long flags; /* can be called from interrupt context */
-
         if (SHARED_KERNEL_PMD)
                 return;
 
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
         pgd_list_del(pgd);
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 }
 
 /*
@@ -260,7 +258,6 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 {
         pgd_t *pgd;
         pmd_t *pmds[PREALLOCATED_PMDS];
-        unsigned long flags;
 
         pgd = (pgd_t *)__get_free_page(PGALLOC_GFP);
 
@@ -280,12 +277,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
          * respect to anything walking the pgd_list, so that they
          * never see a partially populated pgd.
          */
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
 
         pgd_ctor(mm, pgd);
         pgd_prepopulate_pmd(mm, pgd, pmds);
 
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 
         return pgd;
 
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 85b68ef5e809..9260b3eb18d4 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -34,6 +34,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 
+#include <asm/ce4100.h>
 #include <asm/pci_x86.h>
 
 struct sim_reg {
@@ -306,10 +307,10 @@ struct pci_raw_ops ce4100_pci_conf = {
         .write = ce4100_conf_write,
 };
 
-static int __init ce4100_pci_init(void)
+int __init ce4100_pci_init(void)
 {
         init_sim_regs();
         raw_pci_ops = &ce4100_pci_conf;
-        return 0;
+        /* Indicate caller that it should invoke pci_legacy_init() */
+        return 1;
 }
-subsys_initcall(ce4100_pci_init);
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index d2c0d51a7178..cd6f184c3b3f 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -15,6 +15,7 @@
 #include <linux/serial_reg.h>
 #include <linux/serial_8250.h>
 
+#include <asm/ce4100.h>
 #include <asm/setup.h>
 #include <asm/io.h>
 
@@ -129,4 +130,5 @@ void __init x86_ce4100_early_setup(void)
         x86_init.resources.probe_roms = x86_init_noop;
         x86_init.mpparse.get_smp_config = x86_init_uint_noop;
         x86_init.mpparse.find_smp_config = sdv_find_smp_config;
+        x86_init.pci.init = ce4100_pci_init;
 }
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index dab874647530..044bda5b3174 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -140,8 +140,7 @@ void * __init prom_early_alloc(unsigned long size)
                  * wasted bootmem) and hand off chunks of it to callers.
                  */
                 res = alloc_bootmem(chunk_size);
-                if (!res)
-                        return NULL;
+                BUG_ON(!res);
                 prom_early_allocated += chunk_size;
                 memset(res, 0, chunk_size);
                 free_mem = chunk_size;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index df58e9cad96a..a7b38d35c29a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1364,11 +1364,11 @@ uv_activation_descriptor_init(int node, int pnode)
                 memset(bd2, 0, sizeof(struct bau_desc));
                 bd2->header.sw_ack_flag = 1;
                 /*
-                 * base_dest_nodeid is the nasid (pnode<<1) of the first uvhub
+                 * base_dest_nodeid is the nasid of the first uvhub
                  * in the partition. The bit map will indicate uvhub numbers,
                  * which are 0-N in a partition. Pnodes are unique system-wide.
                  */
-                bd2->header.base_dest_nodeid = uv_partition_base_pnode << 1;
+                bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode);
                 bd2->header.dest_subnodeid = 0x10; /* the LB */
                 bd2->header.command = UV_NET_ENDPOINT_INTD;
                 bd2->header.int_both = 1;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5e92b61ad574..f6089421147a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -986,10 +986,9 @@ static void xen_pgd_pin(struct mm_struct *mm)
  */
 void xen_mm_pin_all(void)
 {
-        unsigned long flags;
         struct page *page;
 
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
 
         list_for_each_entry(page, &pgd_list, lru) {
                 if (!PagePinned(page)) {
@@ -998,7 +997,7 @@ void xen_mm_pin_all(void)
                 }
         }
 
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 }
 
 /*
@@ -1099,10 +1098,9 @@ static void xen_pgd_unpin(struct mm_struct *mm)
  */
 void xen_mm_unpin_all(void)
 {
-        unsigned long flags;
         struct page *page;
 
-        spin_lock_irqsave(&pgd_lock, flags);
+        spin_lock(&pgd_lock);
 
         list_for_each_entry(page, &pgd_list, lru) {
                 if (PageSavePinned(page)) {
@@ -1112,7 +1110,7 @@ void xen_mm_unpin_all(void)
                 }
         }
 
-        spin_unlock_irqrestore(&pgd_lock, flags);
+        spin_unlock(&pgd_lock);
 }
 
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)