14 files changed, 95 insertions, 68 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 82e508677b91..f9961034e557 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,6 +162,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
                 if (strncmp(str, "old_ordering", 12) == 0)
                         acpi_old_suspend_ordering();
+                if (strncmp(str, "sci_force_enable", 16) == 0)
+                        acpi_set_sci_en_on_resume();
                 str = strchr(str, ',');
                 if (str != NULL)
                         str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 1dca9c34eaeb..fb490ce7dd55 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -138,6 +138,11 @@ int amd_iommus_present;
 bool amd_iommu_np_cache __read_mostly;
 
 /*
+ * Set to true if ACPI table parsing and hardware intialization went properly
+ */
+static bool amd_iommu_initialized;
+
+/*
  * List of protection domains - used during resume
  */
 LIST_HEAD(amd_iommu_pd_list);
@@ -929,6 +934,8 @@ static int __init init_iommu_all(struct acpi_table_header *table)
         }
         WARN_ON(p != end);
 
+        amd_iommu_initialized = true;
+
         return 0;
 }
 
@@ -1263,6 +1270,9 @@ static int __init amd_iommu_init(void)
         if (acpi_table_parse("IVRS", init_iommu_all) != 0)
                 goto free;
 
+        if (!amd_iommu_initialized)
+                goto free;
+
         if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
                 goto free;
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3704997e8b25..f147a95fd84a 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -31,6 +31,7 @@
 #include <asm/x86_init.h>
 
 int gart_iommu_aperture;
+EXPORT_SYMBOL_GPL(gart_iommu_aperture);
 int gart_iommu_aperture_disabled __initdata;
 int gart_iommu_aperture_allowed __initdata;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index aa57c079c98f..3987e4408f75 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -61,12 +61,6 @@ unsigned int boot_cpu_physical_apicid = -1U;
 
 /*
  * The highest APIC ID seen during enumeration.
- *
- * On AMD, this determines the messaging protocol we can use: if all APIC IDs
- * are in the 0 ... 7 range, then we can use logical addressing which
- * has some performance advantages (better broadcasting).
- *
- * If there's an APIC ID above 8, we use physical addressing.
  */
 unsigned int max_physical_apicid;
 
@@ -1898,14 +1892,17 @@ void __cpuinit generic_processor_info(int apicid, int version)
                 max_physical_apicid = apicid;
 
 #ifdef CONFIG_X86_32
-        switch (boot_cpu_data.x86_vendor) {
-        case X86_VENDOR_INTEL:
-                if (num_processors > 8)
-                        def_to_bigsmp = 1;
-                break;
-        case X86_VENDOR_AMD:
-                if (max_physical_apicid >= 8)
+        if (num_processors > 8) {
+                switch (boot_cpu_data.x86_vendor) {
+                case X86_VENDOR_INTEL:
+                        if (!APIC_XAPIC(version)) {
+                                def_to_bigsmp = 0;
+                                break;
+                        }
+                        /* If P4 and above fall through */
+                case X86_VENDOR_AMD:
                         def_to_bigsmp = 1;
+                }
         }
 #endif
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index eacbd2b31d27..e3c3d820c325 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -240,6 +240,11 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                 printk(KERN_DEBUG "system APIC only can use physical flat");
                 return 1;
         }
+
+        if (!strncmp(oem_id, "IBM", 3) && !strncmp(oem_table_id, "EXA", 3)) {
+                printk(KERN_DEBUG "IBM Summit detected, will use apic physical");
+                return 1;
+        }
 #endif
 
         return 0;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index de00c4619a55..53243ca7816d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2434,6 +2434,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
                 cfg = irq_cfg(irq);
                 raw_spin_lock(&desc->lock);
 
+                /*
+                 * Check if the irq migration is in progress. If so, we
+                 * haven't received the cleanup request yet for this irq.
+                 */
+                if (cfg->move_in_progress)
+                        goto unlock;
+
                 if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
                         goto unlock;
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index c4cbd3080c1c..450fe2064a14 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -67,17 +67,8 @@ void __init default_setup_apic_routing(void)
         }
 #endif
 
-        if (apic == &apic_flat) {
-                switch (boot_cpu_data.x86_vendor) {
-                case X86_VENDOR_INTEL:
-                        if (num_processors > 8)
-                                apic = &apic_physflat;
-                        break;
-                case X86_VENDOR_AMD:
-                        if (max_physical_apicid >= 8)
-                                apic = &apic_physflat;
-                }
-        }
+        if (apic == &apic_flat && num_processors > 8)
+                        apic = &apic_physflat;
 
         printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d56b0efb2057..21db3cbea7dc 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -36,6 +36,8 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
 static u64 gru_start_paddr, gru_end_paddr;
+int uv_min_hub_revision_id;
+EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
 
 static inline bool is_GRU_range(u64 start, u64 end)
 {
@@ -55,12 +57,19 @@ static int early_get_nodeid(void)
         mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
         node_id.v = *mmr;
         early_iounmap(mmr, sizeof(*mmr));
+
+        /* Currently, all blades have same revision number */
+        uv_min_hub_revision_id = node_id.s.revision;
+
         return node_id.s.node_id;
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
+        int nodeid;
+
         if (!strcmp(oem_id, "SGI")) {
+                nodeid = early_get_nodeid();
                 x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
                 if (!strcmp(oem_table_id, "UVL"))
                         uv_system_type = UV_LEGACY_APIC;
@@ -68,7 +77,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                         uv_system_type = UV_X2APIC;
                 else if (!strcmp(oem_table_id, "UVH")) {
                         __get_cpu_var(x2apic_extra_bits) =
-                                early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1);
+                                nodeid << (UV_APIC_PNODE_SHIFT - 1);
                         uv_system_type = UV_NON_UNIQUE_APIC;
                         return 1;
                 }
@@ -374,13 +383,13 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 
 enum map_type {map_wb, map_uc};
 
-static __init void map_high(char *id, unsigned long base, int shift,
-                            int max_pnode, enum map_type map_type)
+static __init void map_high(char *id, unsigned long base, int pshift,
+                        int bshift, int max_pnode, enum map_type map_type)
 {
         unsigned long bytes, paddr;
 
-        paddr = base << shift;
-        bytes = (1UL << shift) * (max_pnode + 1);
+        paddr = base << pshift;
+        bytes = (1UL << bshift) * (max_pnode + 1);
         printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr,
                                                 paddr + bytes);
         if (map_type == map_uc)
@@ -396,7 +405,7 @@ static __init void map_gru_high(int max_pnode)
 
         gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
         if (gru.s.enable) {
-                map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
+                map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb);
                 gru_start_paddr = ((u64)gru.s.base << shift);
                 gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
 
@@ -410,7 +419,7 @@ static __init void map_mmr_high(int max_pnode)
 
         mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR);
         if (mmr.s.enable)
-                map_high("MMR", mmr.s.base, shift, max_pnode, map_uc);
+                map_high("MMR", mmr.s.base, shift, shift, max_pnode, map_uc);
 }
 
 static __init void map_mmioh_high(int max_pnode)
@@ -420,7 +429,8 @@ static __init void map_mmioh_high(int max_pnode)
 
         mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
         if (mmioh.s.enable)
-                map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc);
+                map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io,
+                        max_pnode, map_uc);
 }
 
 static __init void map_low_mmrs(void)
@@ -629,8 +639,10 @@ void __init uv_system_init(void)
         uv_rtc_init();
 
         for_each_present_cpu(cpu) {
+                int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+
                 nid = cpu_to_node(cpu);
-                pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu));
+                pnode = uv_apicid_to_pnode(apicid);
                 blade = boot_pnode_to_blade(pnode);
                 lcpu = uv_blade_info[blade].nr_possible_cpus;
                 uv_blade_info[blade].nr_possible_cpus++;
@@ -651,15 +663,13 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
                 uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
                 uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
-                uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
+                uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
                 uv_node_to_blade[nid] = blade;
                 uv_cpu_to_blade[cpu] = blade;
                 max_pnode = max(pnode, max_pnode);
 
-                printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, "
-                        "lcpu %d, blade %d\n",
-                        cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid,
-                        lcpu, blade);
+                printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n",
+                        cpu, apicid, pnode, nid, lcpu, blade);
         }
 
         /* Add blade/pnode info for nodes without cpus */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c223b7e895d9..d616c06e99b4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2347,7 +2347,7 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
         callchain_store(entry, PERF_CONTEXT_KERNEL);
         callchain_store(entry, regs->ip);
 
-        dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+        dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
 
 /*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c56bc2873030..6d817554780a 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -123,13 +123,15 @@ print_context_stack_bp(struct thread_info *tinfo,
         while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
                 unsigned long addr = *ret_addr;
 
-                if (__kernel_text_address(addr)) {
-                        ops->address(data, addr, 1);
-                        frame = frame->next_frame;
-                        ret_addr = &frame->return_address;
-                        print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
-                }
+                if (!__kernel_text_address(addr))
+                        break;
+
+                ops->address(data, addr, 1);
+                frame = frame->next_frame;
+                ret_addr = &frame->return_address;
+                print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
         }
+
         return (unsigned long)frame;
 }
 EXPORT_SYMBOL_GPL(print_context_stack_bp);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 05ed7ab2ca48..a1a7876cadcb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -733,13 +733,13 @@ struct early_res {
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
         { 0, PAGE_SIZE, "BIOS data page", 1 },  /* BIOS data page */
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
         /*
          * But first pinch a few for the stack/trampoline stuff
          * FIXME: Don't need the extra page at 4K, but need to fix
          * trampoline before removing it. (see the GDT stuff)
          */
-        { PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 },
+        { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
 #endif
 
         {}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 98c2cdeb599e..02c3ee013ccd 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -103,8 +103,8 @@ void show_regs_common(void)
         if (!product)
                 product = "";
 
-        printk("\n");
-        printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+        printk(KERN_CONT "\n");
+        printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
                 current->pid, current->comm, print_tainted(),
                 init_utsname()->release,
                 (int)strcspn(init_utsname()->version, " "),
@@ -288,6 +288,8 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
         regs.es = __USER_DS;
         regs.fs = __KERNEL_PERCPU;
         regs.gs = __KERNEL_STACK_CANARY;
+#else
+        regs.ss = __KERNEL_DS;
 #endif
 
         regs.orig_ax = -1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9c517b5858f0..37ad1e046aae 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -139,16 +139,16 @@ void __show_regs(struct pt_regs *regs, int all)
 
         show_regs_common();
 
-        printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
+        printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
                         (u16)regs->cs, regs->ip, regs->flags,
                         smp_processor_id());
         print_symbol("EIP is at %s\n", regs->ip);
 
-        printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
+        printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
                 regs->ax, regs->bx, regs->cx, regs->dx);
-        printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
+        printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
                 regs->si, regs->di, regs->bp, sp);
-        printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
+        printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
                (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
 
         if (!all)
@@ -158,19 +158,19 @@ void __show_regs(struct pt_regs *regs, int all)
         cr2 = read_cr2();
         cr3 = read_cr3();
         cr4 = read_cr4_safe();
-        printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
+        printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
                         cr0, cr2, cr3, cr4);
 
         get_debugreg(d0, 0);
         get_debugreg(d1, 1);
         get_debugreg(d2, 2);
         get_debugreg(d3, 3);
-        printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
+        printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
                         d0, d1, d2, d3);
 
         get_debugreg(d6, 6);
         get_debugreg(d7, 7);
-        printk("DR6: %08lx DR7: %08lx\n",
+        printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n",
                         d6, d7);
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 52fbd0c60198..f9e033150cdf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -161,19 +161,19 @@ void __show_regs(struct pt_regs *regs, int all)
         unsigned int ds, cs, es;
 
         show_regs_common();
-        printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
+        printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
         printk_address(regs->ip, 1);
-        printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
+        printk(KERN_DEFAULT "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
                         regs->sp, regs->flags);
-        printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
+        printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
                regs->ax, regs->bx, regs->cx);
-        printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
+        printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",
                regs->dx, regs->si, regs->di);
-        printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
+        printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n",
                regs->bp, regs->r8, regs->r9);
-        printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
+        printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n",
                regs->r10, regs->r11, regs->r12);
-        printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n",
+        printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
                regs->r13, regs->r14, regs->r15);
 
         asm("movl %%ds,%0" : "=r" (ds));
@@ -194,21 +194,21 @@ void __show_regs(struct pt_regs *regs, int all)
         cr3 = read_cr3();
         cr4 = read_cr4();
 
-        printk(KERN_INFO "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
+        printk(KERN_DEFAULT "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
                fs, fsindex, gs, gsindex, shadowgs);
-        printk(KERN_INFO "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+        printk(KERN_DEFAULT "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
                         es, cr0);
-        printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
+        printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
                         cr4);
 
         get_debugreg(d0, 0);
         get_debugreg(d1, 1);
         get_debugreg(d2, 2);
-        printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
+        printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
         get_debugreg(d3, 3);
         get_debugreg(d6, 6);
         get_debugreg(d7, 7);
-        printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
+        printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
 void show_regs(struct pt_regs *regs)