Merge commit 'v3.0-rc5' into perf/core

Merge reason: Pick up the latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

16 files changed, 77 insertions, 40 deletions

diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
index 19ae14b..0cd3800 100644
--- a/arch/x86/include/asm/memblock.h
+++ b/arch/x86/include/asm/memblock.h
@@ -4,7 +4,6 @@
 #define ARCH_DISCARD_MEMBLOCK
 
 u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_to_bootmem(u64 start, u64 end);
 
 void memblock_x86_reserve_range(u64 start, u64 end, char *name);
 void memblock_x86_free_range(u64 start, u64 end);
@@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end);
 u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
 
 #endif
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 5e83a41..224e8c5 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 static inline int pfn_valid(int pfn)
 {
 	int nid = pfn_to_nid(pfn);
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index b3f88d7..129d9aa 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -13,8 +13,5 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
-				 NODE_DATA(nid)->node_spanned_pages)
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 31d84ac..a518c0a 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 	u64 product;
 #ifdef __i386__
 	u32 tmp1, tmp2;
+#else
+	ulong tmp;
 #endif
 
 	if (shift < 0)
@@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
 #elif defined(__x86_64__)
 	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+		"mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		: [lo]"=a"(product),
+		  [hi]"=d"(tmp)
+		: "0"(delta),
+		  [mul_frac]"rm"((u64)mul_frac));
 #else
 #error implement me!
 #endif
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index b511a01..adc66c3 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat);
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
 int uv_set_vga_state(struct pci_dev *pdev, bool decode,
-		      unsigned int command_bits, bool change_bridge)
+		      unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
-	PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n",
-			pdev->devfn, decode, command_bits, change_bridge);
+	PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
+			pdev->devfn, decode, command_bits, flags);
 
-	if (!change_bridge)
+	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
 		return 0;
 
 	if ((command_bits & PCI_COMMAND_IO) == 0)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 2e4928d..e1ba8cb2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(pm_idle);
 #endif
 
@@ -399,7 +399,7 @@ void default_idle(void)
 		cpu_relax();
 	}
 }
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(default_idle);
 #endif
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index bd14bb4..aee3862 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 
 static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 {
-	return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
+	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
 }
 
 static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6c4dc010..9d03ad4 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    gva_t addr, u32 access)
 {
 	pt_element_t pte;
-	pt_element_t __user *ptep_user;
+	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
 	unsigned index, pt_access, uninitialized_var(pte_access);
 	gpa_t pte_gpa;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4c3fa0f..d48ec60 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 					unsigned long cr0,
 					struct kvm_vcpu *vcpu)
 {
-	vmx_decache_cr3(vcpu);
+	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		vmx_decache_cr3(vcpu);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index aa11693..992da5e 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -8,7 +8,7 @@
 #include <linux/range.h>
 
 /* Check for already reserved areas */
-static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
 {
 	struct memblock_region *r;
 	u64 addr = *addrp, last;
@@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
 		if (addr >= ei_last)
 			continue;
 		*sizep = ei_last - addr;
-		while (check_with_memblock_reserved_size(&addr, sizep, align))
+		while (memblock_x86_check_reserved_size(&addr, sizep, align))
 			;
 
 		if (*sizep)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 0972315..68c3c13 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point)
 	return false;
 }
 
-static void coalesce_windows(struct pci_root_info *info, int type)
+static void coalesce_windows(struct pci_root_info *info, unsigned long type)
 {
 	int i, j;
 	struct resource *res1, *res2;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0d3a4fa..474356b 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
-
-		memblock_x86_reserve_range(start, start + size, "EFI Boot");
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start+size >= virt_to_phys(_text)
+				&& start <= virt_to_phys(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_x86_check_reserved_size(&start, &size,
+							1<<EFI_PAGE_SHIFT)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg(PFX "Could not reserve boot range "
+					"[0x%010llx-0x%010llx]\n",
+						start, start+size-1);
+		} else
+			memblock_x86_reserve_range(start, start+size,
+							"EFI Boot");
 	}
 }
 
@@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
 		free_bootmem_late(start, size);
 	}
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index dd7b88f..5525163 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1033,6 +1033,13 @@ static void xen_machine_halt(void)
 	xen_reboot(SHUTDOWN_poweroff);
 }
 
+static void xen_machine_power_off(void)
+{
+	if (pm_power_off)
+		pm_power_off();
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
 static void xen_crash_shutdown(struct pt_regs *regs)
 {
 	xen_reboot(SHUTDOWN_crash);
@@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void)
 static const struct machine_ops xen_machine_ops __initconst = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,
-	.power_off = xen_machine_halt,
+	.power_off = xen_machine_power_off,
 	.shutdown = xen_machine_halt,
 	.crash_shutdown = xen_crash_shutdown,
 	.emergency_restart = xen_emergency_restart,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dc708dc..673e968 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -59,6 +59,7 @@
 #include <asm/page.h>
 #include <asm/init.h>
 #include <asm/pat.h>
+#include <asm/smp.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -1231,7 +1232,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 {
 	struct {
 		struct mmuext_op op;
-		DECLARE_BITMAP(mask, NR_CPUS);
+		DECLARE_BITMAP(mask, num_processors);
 	} *args;
 	struct multicall_space mcs;
 
@@ -1599,6 +1600,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
+#ifdef CONFIG_X86_32
+			if (pfn > max_pfn_mapped)
+				max_pfn_mapped = pfn;
+#endif
+
 			if (!pte_none(pte_page[pteidx]))
 				continue;
 
@@ -1766,7 +1772,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
+				  xen_start_info->nr_pt_frames * PAGE_SIZE +
+				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index be1a464..60aeeb5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,11 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-#ifdef CONFIG_X86_32
 	xen_extra_mem_start = mem_end;
-#else
-	xen_extra_mem_start = max((1ULL << 32), mem_end);
-#endif
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;
 
@@ -266,6 +262,12 @@ char * __init xen_memory_setup(void)
 		if (map[i].size > 0)
 			e820_add_region(map[i].addr, map[i].size, map[i].type);
 	}
+	/* Align the balloon area so that max_low_pfn does not get set
+	 * to be at the _end_ of the PCI gap at the far end (fee01000).
+	 * Note that xen_extra_mem_start gets set in the loop above to be
+	 * past the last E820 region. */
+	if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
+		xen_extra_mem_start = (1ULL<<32);
 
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 41038c0..b4533a8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void)
 static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned cpu;
+	unsigned int i;
 
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
 	cpu_data(0).x86_max_cores = 1;
+
+	for_each_possible_cpu(i) {
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+	}
 	set_cpu_sibling_map(0);
 
 	if (xen_smp_intr_init(0))