Merge branch 'x86/debug' into x86/irq

We merge this branch because x86/debug touches code that we started
cleaning up in x86/irq. The two branches started out independent,
but as unexpected amount of activity went into x86/irq, they became
dependent. Resolve that by this cross-merge.

16 files changed, 93 insertions, 22 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3cf457f90e8e..d4d4cb7629ea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -952,7 +952,7 @@ config ARCH_PHYS_ADDR_T_64BIT
 config NUMA
         bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
         depends on SMP
-        depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && BROKEN)
+        depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
         default n if X86_PC
         default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
         help
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 485bdf059ffb..07f1af494ca5 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -34,10 +34,14 @@ static inline void get_memcfg_numa(void)
 
 extern int early_pfn_to_nid(unsigned long pfn);
 
+extern void resume_map_numa_kva(pgd_t *pgd);
+
 #else /* !CONFIG_NUMA */
 
 #define get_memcfg_numa get_memcfg_numa_flat
 
+static inline void resume_map_numa_kva(pgd_t *pgd) {}
+
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f15280f14..f8cfd00db450 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,7 +46,7 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
                 return ret;
         case 10:
                 __get_user_asm(*(u64 *)dst, (u64 __user *)src,
-                               ret, "q", "", "=r", 16);
+                               ret, "q", "", "=r", 10);
                 if (unlikely(ret))
                         return ret;
                 __get_user_asm(*(u16 *)(8 + (char *)dst),
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 834b2c1d89fb..d2e415e6666f 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -639,8 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate)
 __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
 #define __NR_timerfd_gettime                    287
 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
-#define __NR_paccept                            288
-__SYSCALL(__NR_paccept, sys_paccept)
+#define __NR_accept4                            288
+__SYSCALL(__NR_accept4, sys_accept4)
 #define __NR_signalfd4                          289
 __SYSCALL(__NR_signalfd4, sys_signalfd4)
 #define __NR_eventfd2                           290
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e489ff9cb3e2..943fe6026c64 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -12,6 +12,7 @@ CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
 #
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 331b318304eb..e4899e0e8787 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -537,7 +537,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
         address >>= PAGE_SHIFT;
         iommu_area_free(dom->bitmap, address, pages);
 
-        if (address + pages >= dom->next_bit)
+        if (address >= dom->next_bit)
                 dom->need_flush = true;
 }
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 0cdcda35a05f..30ae2701b3df 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -121,7 +121,7 @@ u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 LIST_HEAD(amd_iommu_unity_map);         /* a list of required unity mappings
                                            we find in ACPI */
 unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
-int amd_iommu_isolate;                  /* if 1, device isolation is enabled */
+int amd_iommu_isolate = 1;              /* if 1, device isolation is enabled */
 bool amd_iommu_unmap_flush;             /* if true, flush on every unmap */
 
 LIST_HEAD(amd_iommu_list);              /* list of all AMD IOMMUs in the
@@ -1213,7 +1213,9 @@ static int __init parse_amd_iommu_options(char *str)
         for (; *str; ++str) {
                 if (strncmp(str, "isolate", 7) == 0)
                         amd_iommu_isolate = 1;
-                if (strncmp(str, "fullflush", 11) == 0)
+                if (strncmp(str, "share", 5) == 0)
+                        amd_iommu_isolate = 0;
+                if (strncmp(str, "fullflush", 9) == 0)
                         amd_iommu_unmap_flush = true;
         }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 6e96028d1a9c..fe7014176eb0 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -847,6 +847,7 @@ ENTRY(kernel_thread_helper)
         push %eax
         CFI_ADJUST_CFA_OFFSET 4
         call do_exit
+        ud2                     # padding for call trace
         CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 08c0c9777a09..e41734a537bd 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -373,6 +373,7 @@ ENTRY(ret_from_fork)
         call schedule_tail
         GET_THREAD_INFO(%rcx)
         testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
+        CFI_REMEMBER_STATE
         jnz rff_trace
 rff_action:
         RESTORE_REST
@@ -382,6 +383,7 @@ rff_action:
         jnz  int_ret_from_sys_call
         RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
         jmp ret_from_sys_call
+        CFI_RESTORE_STATE
 rff_trace:
         movq %rsp,%rdi
         call syscall_trace_leave
@@ -1173,6 +1175,7 @@ ENTRY(child_rip)
         # exit
         mov %eax, %edi
         call do_exit
+        ud2                     # padding for call trace
         CFI_ENDPROC
 END(child_rip)
 
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 7a3f2028e2eb..c9513e1ff28d 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq)
 
         cfg->vector = 0;
         cpus_clear(cfg->domain);
+
+        if (likely(!cfg->move_in_progress))
+                return;
+        cpus_and(mask, cfg->old_domain, cpu_online_map);
+        for_each_cpu_mask_nr(cpu, mask) {
+                for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+                                                                vector++) {
+                        if (per_cpu(vector_irq, cpu)[vector] != irq)
+                                continue;
+                        per_cpu(vector_irq, cpu)[vector] = -1;
+                        break;
+                }
+        }
+        cfg->move_in_progress = 0;
 }
 
 void __setup_vector_irq(int cpu)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 60eb84eb77a0..1d3d0e71b044 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,7 +18,6 @@
 #include <asm/idle.h>
 #include <asm/smp.h>
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 /*
  * Probabilistic stack overflow check:
  *
@@ -28,19 +27,18 @@
  */
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
         u64 curbase = (u64)task_stack_page(current);
-        static unsigned long warned = -60*HZ;
-
-        if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE &&
-            regs->sp <  curbase + sizeof(struct thread_info) + 128 &&
-            time_after(jiffies, warned + 60*HZ)) {
-                printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-                       current->comm, curbase, regs->sp);
-                show_stack(NULL,NULL);
-                warned = jiffies;
-        }
-}
+
+        WARN_ONCE(regs->sp >= curbase &&
+                  regs->sp <= curbase + THREAD_SIZE &&
+                  regs->sp <  curbase + sizeof(struct thread_info) +
+                                        sizeof(struct pt_regs) + 128,
+
+                  "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
+                        current->comm, curbase, regs->sp);
 #endif
+}
 
 /*
  * do_IRQ handles all normal device IRQ's (the special
@@ -60,9 +58,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
         irq_enter();
         irq = __get_cpu_var(vector_irq)[vector];
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
         stack_overflow_check(regs);
-#endif
 
         desc = irq_to_desc(irq);
         if (likely(desc))
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc63cb9..cc5a2545dd41 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -169,6 +169,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                         DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
                 },
         },
+        {   /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+                .callback = set_bios_reboot,
+                .ident = "Dell OptiPlex 330",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+                        DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+                },
+        },
         {       /* Handle problems with rebooting on Dell 2400's */
                 .callback = set_bios_reboot,
                 .ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0fa6790c1dd3..9d5674f7b6cc 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -764,7 +764,7 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
                 .callback = dmi_low_memory_corruption,
                 .ident = "Phoenix BIOS",
                 .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
                 },
         },
 #endif
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index cb19d650c216..418a095c5796 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -80,6 +80,8 @@ unsigned long __init calibrate_cpu(void)
                         break;
         no_ctr_free = (i == 4);
         if (no_ctr_free) {
+                WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
+                     "cpu_khz value may be incorrect.\n");
                 i = 3;
                 rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
                 wrmsrl(MSR_K7_EVNTSEL3, 0);
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 847c164725f4..8518c678d83f 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
         }
 }
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ *                       during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+        int node;
+
+        for_each_online_node(node) {
+                unsigned long start_va, start_pfn, size, pfn;
+
+                start_va = (unsigned long)node_remap_start_vaddr[node];
+                start_pfn = node_remap_start_pfn[node];
+                size = node_remap_size[node];
+
+                printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+                for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+                        unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+                        pgd_t *pgd = pgd_base + pgd_index(vaddr);
+                        pud_t *pud = pud_offset(pgd, vaddr);
+                        pmd_t *pmd = pmd_offset(pud, vaddr);
+
+                        set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+                                                PAGE_KERNEL_LARGE_EXEC));
+
+                        printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+                                __FUNCTION__, vaddr, start_pfn + pfn);
+                }
+        }
+}
+#endif
+
 static unsigned long calculate_numa_remap_pages(void)
 {
         int nid;
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index f2b6e3f11bfc..81197c62d5b3 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -12,6 +12,7 @@
 #include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/mmzone.h>
 
 /* Defined in hibernate_asm_32.S */
 extern int restore_image(void);
@@ -127,6 +128,9 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
                         }
                 }
         }
+
+        resume_map_numa_kva(pgd_base);
+
         return 0;
 }