17 files changed, 216 insertions, 54 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index c1870dd..26af1e3 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -208,7 +208,7 @@ sysexit_from_sys_call:
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
 	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%esi		/* second arg, syscall return value */
 	cmpl $0,%eax		/* is it < 0? */
 	setl %al		/* 1 if so, 0 if not */
@@ -218,7 +218,7 @@ sysexit_from_sys_call:
 	GET_THREAD_INFO(%r10)
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall return value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags(%r10)
 	jz \exit
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index ffa037f..a6a6414 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -14,12 +14,6 @@ extern struct pglist_data *node_data[];
 
 #include <asm/numaq.h>
 
-extern void resume_map_numa_kva(pgd_t *pgd);
-
-#else /* !CONFIG_NUMA */
-
-static inline void resume_map_numa_kva(pgd_t *pgd) {}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 884507e..6be9909 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -142,6 +142,11 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 static inline int pmd_large(pmd_t pte)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0310da6..1d44903 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_TRAPS_H
 #define _ASM_X86_TRAPS_H
 
+#include <linux/kprobes.h>
 #include <asm/debugreg.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
@@ -87,4 +88,29 @@ asmlinkage void smp_thermal_interrupt(void);
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+/* Interrupts/Exceptions */
+enum {
+	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
+	X86_TRAP_DB,		/*  1, Debug */
+	X86_TRAP_NMI,		/*  2, Non-maskable Interrupt */
+	X86_TRAP_BP,		/*  3, Breakpoint */
+	X86_TRAP_OF,		/*  4, Overflow */
+	X86_TRAP_BR,		/*  5, Bound Range Exceeded */
+	X86_TRAP_UD,		/*  6, Invalid Opcode */
+	X86_TRAP_NM,		/*  7, Device Not Available */
+	X86_TRAP_DF,		/*  8, Double Fault */
+	X86_TRAP_OLD_MF,	/*  9, Coprocessor Segment Overrun */
+	X86_TRAP_TS,		/* 10, Invalid TSS */
+	X86_TRAP_NP,		/* 11, Segment Not Present */
+	X86_TRAP_SS,		/* 12, Stack Segment Fault */
+	X86_TRAP_GP,		/* 13, General Protection Fault */
+	X86_TRAP_PF,		/* 14, Page Fault */
+	X86_TRAP_SPURIOUS,	/* 15, Spurious Interrupt */
+	X86_TRAP_MF,		/* 16, x87 Floating-Point Exception */
+	X86_TRAP_AC,		/* 17, Alignment Check */
+	X86_TRAP_MC,		/* 18, Machine Check */
+	X86_TRAP_XF,		/* 19, SIMD Floating-Point Exception */
+	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
+};
+
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 33df6e8..d86aa3f 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1363,6 +1363,7 @@ static struct syscore_ops amd_iommu_syscore_ops = {
  */
 static int __init amd_iommu_init(void)
 {
+	struct amd_iommu *iommu;
 	int i, ret = 0;
 
 	/*
@@ -1411,9 +1412,6 @@ static int __init amd_iommu_init(void)
 	if (amd_iommu_pd_alloc_bitmap == NULL)
 		goto free;
 
-	/* init the device table */
-	init_device_table();
-
 	/*
 	 * let all alias entries point to itself
 	 */
@@ -1463,6 +1461,12 @@ static int __init amd_iommu_init(void)
 	if (ret)
 		goto free_disable;
 
+	/* init the device table */
+	init_device_table();
+
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
+
 	amd_iommu_init_api();
 
 	amd_iommu_init_notifier();
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index f5373df..db4f704 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -20,12 +20,19 @@ static int set_x2apic_phys_mode(char *arg)
 }
 early_param("x2apic_phys", set_x2apic_phys_mode);
 
+static bool x2apic_fadt_phys(void)
+{
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return true;
+	}
+	return false;
+}
+
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	if (x2apic_phys)
-		return x2apic_enabled();
-	else
-		return 0;
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
 static void
@@ -108,7 +115,7 @@ static void init_x2apic_ldr(void)
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && x2apic_phys)
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
 		return 1;
 
 	return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3f4b6da..a93741d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -568,6 +568,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 268b40d..2df1252 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1078,7 +1078,6 @@ ENTRY(xen_failsafe_callback)
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
-	addl $16,%esp
 	jmp iret_exc
 5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index af0699b..f6c4674 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -5,8 +5,6 @@
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
 /*
  * The BIOS places the EBDA/XBDA at the top of conventional
  * memory, and usually decreases the reported amount of
@@ -16,17 +14,30 @@
  * chipset: reserve a page before VGA to prevent PCI prefetch
  * into it (errata #56). Usually the page is reserved anyways,
  * unless you have no PS/2 mouse plugged in.
+ *
+ * This functions is deliberately very conservative.  Losing
+ * memory in the bottom megabyte is rarely a problem, as long
+ * as we have enough memory to install the trampoline.  Using
+ * memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem.
  */
+
+#define BIOS_LOWMEM_KILOBYTES	0x413
+#define LOWMEM_CAP		0x9f000U	/* Absolute maximum */
+#define INSANE_CUTOFF		0x20000U	/* Less than this = insane */
+
 void __init reserve_ebda_region(void)
 {
 	unsigned int lowmem, ebda_addr;
 
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
+	/*
+	 * To determine the position of the EBDA and the
+	 * end of conventional memory, we need to look at
+	 * the BIOS data area. In a paravirtual environment
+	 * that area is absent. We'll just have to assume
+	 * that the paravirt case can handle memory setup
+	 * correctly, without our help.
+	 */
 	if (paravirt_enabled())
 		return;
 
@@ -37,19 +48,23 @@ void __init reserve_ebda_region(void)
 	/* start of EBDA area */
 	ebda_addr = get_bios_ebda();
 
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
+	/*
+	 * Note: some old Dells seem to need 4k EBDA without
+	 * reporting so, so just consider the memory above 0x9f000
+	 * to be off limits (bugzilla 2990).
+	 */
+
+	/* If the EBDA address is below 128K, assume it is bogus */
+	if (ebda_addr < INSANE_CUTOFF)
+		ebda_addr = LOWMEM_CAP;
 
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
+	/* If lowmem is less than 128K, assume it is bogus */
+	if (lowmem < INSANE_CUTOFF)
+		lowmem = LOWMEM_CAP;
 
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
+	/* Use the lower of the lowmem and EBDA markers as the cutoff */
+	lowmem = min(lowmem, ebda_addr);
+	lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
 
 	/* reserve all memory between lowmem and the 1MB mark */
 	memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 12fcbe2..f7d1a64 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -175,6 +175,9 @@ static int msr_open(struct inode *inode, struct file *file)
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index af19a61..6c4e9ff 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -631,6 +631,83 @@ static __init void reserve_ibft_region(void)
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
+static bool __init snb_gfx_workaround_needed(void)
+{
+#ifdef CONFIG_PCI
+	int i;
+	u16 vendor, devid;
+	static const u16 snb_ids[] = {
+		0x0102,
+		0x0112,
+		0x0122,
+		0x0106,
+		0x0116,
+		0x0126,
+		0x010a,
+	};
+
+	/* Assume no if something weird is going on with PCI */
+	if (!early_pci_allowed())
+		return false;
+
+	vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+	if (vendor != 0x8086)
+		return false;
+
+	devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+	for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+		if (devid == snb_ids[i])
+			return true;
+#endif
+
+	return false;
+}
+
+/*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+static void __init trim_snb_memory(void)
+{
+	static const unsigned long bad_pages[] = {
+		0x20050000,
+		0x20110000,
+		0x20130000,
+		0x20138000,
+		0x40004000,
+	};
+	int i;
+
+	if (!snb_gfx_workaround_needed())
+		return;
+
+	printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+	/*
+	 * Reserve all memory below the 1 MB mark that has not
+	 * already been reserved.
+	 */
+	memblock_reserve(0, 1<<20);
+
+	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+			printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+			       bad_pages[i]);
+	}
+}
+
+/*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+static void __init trim_platform_memory_ranges(void)
+{
+	trim_snb_memory();
+}
+
 static void __init trim_bios_range(void)
 {
 	/*
@@ -651,6 +728,7 @@ static void __init trim_bios_range(void)
 	 * take them out.
 	 */
 	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
@@ -929,6 +1007,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_trampolines();
 
+	trim_platform_memory_ranges();
+
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2dbf6bf..3b2ad91 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -720,12 +720,15 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		if (is_errata100(regs, address))
 			return;
 
-		if (unlikely(show_unhandled_signals))
+		/* Kernel addresses are always protection faults: */
+		if (address >= TASK_SIZE)
+			error_code |= PF_PROT;
+
+		if (likely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 
-		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
-		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
+		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_no	= 14;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bbaaa00..44b93da 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -831,6 +831,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pud_none(*pud))
 		return 0;
 
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return 0;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac3aa54..0fba86d 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -38,7 +38,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 
-static pgd_t save_pgd __initdata;
+static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
 static void __init early_code_mapping_set_exec(int executable)
@@ -61,12 +61,20 @@ static void __init early_code_mapping_set_exec(int executable)
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
 
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
-	vaddress = (unsigned long)__va(0x0UL);
-	save_pgd = *pgd_offset_k(0x0UL);
-	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
 	__flush_tlb_all();
 }
 
@@ -75,7 +83,11 @@ void __init efi_call_phys_epilog(void)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 3769079..a09ecb9 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -130,8 +130,6 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
 		}
 	}
 
-	resume_map_numa_kva(pgd_base);
-
 	return 0;
 }
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cc9b1e1..d99537f 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -313,7 +313,6 @@ static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
 		if (per_cpu(lock_spinners, cpu) == xl) {
 			ADD_STATS(released_slow_kicked, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
-			break;
 		}
 	}
 }
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index b040b0e..7328f71 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -88,11 +88,11 @@ ENTRY(xen_iret)
 	 */
 #ifdef CONFIG_SMP
 	GET_THREAD_INFO(%eax)
-	movl TI_cpu(%eax), %eax
-	movl __per_cpu_offset(,%eax,4), %eax
-	mov xen_vcpu(%eax), %eax
+	movl %ss:TI_cpu(%eax), %eax
+	movl %ss:__per_cpu_offset(,%eax,4), %eax
+	mov %ss:xen_vcpu(%eax), %eax
 #else
-	movl xen_vcpu, %eax
+	movl %ss:xen_vcpu, %eax
 #endif
 
 	/* check IF state we're restoring */
@@ -105,11 +105,11 @@ ENTRY(xen_iret)
 	 * resuming the code, so we don't have to be worried about
 	 * being preempted to another CPU.
 	 */
-	setz XEN_vcpu_info_mask(%eax)
+	setz %ss:XEN_vcpu_info_mask(%eax)
 xen_iret_start_crit:
 
 	/* check for unmasked and pending */
-	cmpw $0x0001, XEN_vcpu_info_pending(%eax)
+	cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
 
 	/*
 	 * If there's something pending, mask events again so we can
@@ -117,7 +117,7 @@ xen_iret_start_crit:
 	 * touch XEN_vcpu_info_mask.
 	 */
 	jne 1f
-	movb $1, XEN_vcpu_info_mask(%eax)
+	movb $1, %ss:XEN_vcpu_info_mask(%eax)
 
 1:	popl %eax