summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig4
-rw-r--r--arch/x86/Makefile3
-rw-r--r--arch/x86/boot/compressed/Makefile9
-rw-r--r--arch/x86/ia32/ia32_aout.c3
-rw-r--r--arch/x86/include/asm/irq_remapping.h118
-rw-r--r--arch/x86/include/asm/kvm_para.h3
-rw-r--r--arch/x86/include/asm/nmi.h22
-rw-r--r--arch/x86/include/asm/stat.h21
-rw-r--r--arch/x86/include/asm/word-at-a-time.h33
-rw-r--r--arch/x86/kernel/acpi/boot.c2
-rw-r--r--arch/x86/kernel/apic/apic.c30
-rw-r--r--arch/x86/kernel/apic/io_apic.c297
-rw-r--r--arch/x86/kernel/cpu/amd.c18
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c14
-rw-r--r--arch/x86/kernel/kvm.c9
-rw-r--r--arch/x86/kernel/microcode_intel.c14
-rw-r--r--arch/x86/kernel/nmi.c83
-rw-r--r--arch/x86/kernel/process_64.c1
-rw-r--r--arch/x86/kernel/setup_percpu.c14
-rw-r--r--arch/x86/kvm/x86.c1
-rw-r--r--arch/x86/lib/usercopy.c20
-rw-r--r--arch/x86/pci/acpi.c128
-rw-r--r--arch/x86/pci/amd_bus.c91
-rw-r--r--arch/x86/pci/broadcom_bus.c12
-rw-r--r--arch/x86/pci/bus_numa.c69
-rw-r--r--arch/x86/pci/bus_numa.h18
-rw-r--r--arch/x86/pci/common.c43
-rw-r--r--arch/x86/pci/i386.c2
-rw-r--r--arch/x86/platform/geode/net5501.c2
-rw-r--r--arch/x86/tools/.gitignore1
-rw-r--r--arch/x86/tools/Makefile4
-rw-r--r--arch/x86/tools/relocs.c (renamed from arch/x86/boot/compressed/relocs.c)244
-rw-r--r--arch/x86/xen/enlighten.c42
-rw-r--r--arch/x86/xen/mmu.c7
34 files changed, 765 insertions, 617 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 98876f55a2e..c940cb6f040 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -77,11 +77,11 @@ config X86
select GENERIC_CLOCKEVENTS_MIN_ADJUST
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
- select HAVE_BPF_JIT if (X86_64 && NET)
+ select HAVE_BPF_JIT if X86_64
select CLKEVT_I8253
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select GENERIC_IOMAP
- select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
+ select DCACHE_WORD_ACCESS
select GENERIC_SMP_IDLE_THREAD
config INSTRUCTION_DECODER
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 3e48b26f67d..277418ff8b5 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -134,6 +134,9 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
KBUILD_CFLAGS += $(mflags-y)
KBUILD_AFLAGS += $(mflags-y)
+archscripts:
+ $(Q)$(MAKE) $(build)=arch/x86/tools relocs
+
###
# Syscall table generation
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fd55a2ff3ad..e398bb5d63b 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -40,13 +40,12 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
+targets += vmlinux.bin.all vmlinux.relocs
-targets += vmlinux.bin.all vmlinux.relocs relocs
-hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs
-
+CMD_RELOCS = arch/x86/tools/relocs
quiet_cmd_relocs = RELOCS $@
- cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
-$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
+ cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux FORCE
$(call if_changed,relocs)
vmlinux.bin.all-y := $(obj)/vmlinux.bin
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 4824fb45560..07b3a68d2d2 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -294,8 +294,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
/* OK, This is the point of no return */
set_personality(PER_LINUX);
- set_thread_flag(TIF_IA32);
- current->mm->context.ia32_compat = 1;
+ set_personality_ia32(false);
setup_new_exec(bprm);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 47d99934580..5fb9bbbd2f1 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -1,45 +1,101 @@
-#ifndef _ASM_X86_IRQ_REMAPPING_H
-#define _ASM_X86_IRQ_REMAPPING_H
+/*
+ * Copyright (C) 2012 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * This header file contains the interface of the interrupt remapping code to
+ * the x86 interrupt management code.
+ */
-#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
+#ifndef __X86_IRQ_REMAPPING_H
+#define __X86_IRQ_REMAPPING_H
+
+#include <asm/io_apic.h>
#ifdef CONFIG_IRQ_REMAP
-static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
-static inline void prepare_irte(struct irte *irte, int vector,
- unsigned int dest)
+
+extern int irq_remapping_enabled;
+
+extern void setup_irq_remapping_ops(void);
+extern int irq_remapping_supported(void);
+extern int irq_remapping_prepare(void);
+extern int irq_remapping_enable(void);
+extern void irq_remapping_disable(void);
+extern int irq_remapping_reenable(int);
+extern int irq_remap_enable_fault_handling(void);
+extern int setup_ioapic_remapped_entry(int irq,
+ struct IO_APIC_route_entry *entry,
+ unsigned int destination,
+ int vector,
+ struct io_apic_irq_attr *attr);
+extern int set_remapped_irq_affinity(struct irq_data *data,
+ const struct cpumask *mask,
+ bool force);
+extern void free_remapped_irq(int irq);
+extern void compose_remapped_msi_msg(struct pci_dev *pdev,
+ unsigned int irq, unsigned int dest,
+ struct msi_msg *msg, u8 hpet_id);
+extern int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
+extern int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
+ int index, int sub_handle);
+extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
+
+#else /* CONFIG_IRQ_REMAP */
+
+#define irq_remapping_enabled 0
+
+static inline void setup_irq_remapping_ops(void) { }
+static inline int irq_remapping_supported(void) { return 0; }
+static inline int irq_remapping_prepare(void) { return -ENODEV; }
+static inline int irq_remapping_enable(void) { return -ENODEV; }
+static inline void irq_remapping_disable(void) { }
+static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
+static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
+static inline int setup_ioapic_remapped_entry(int irq,
+ struct IO_APIC_route_entry *entry,
+ unsigned int destination,
+ int vector,
+ struct io_apic_irq_attr *attr)
+{
+ return -ENODEV;
+}
+static inline int set_remapped_irq_affinity(struct irq_data *data,
+ const struct cpumask *mask,
+ bool force)
{
- memset(irte, 0, sizeof(*irte));
-
- irte->present = 1;
- irte->dst_mode = apic->irq_dest_mode;
- /*
- * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
- * actual level or edge trigger will be setup in the IO-APIC
- * RTE. This will help simplify level triggered irq migration.
- * For more details, see the comments (in io_apic.c) explainig IO-APIC
- * irq migration in the presence of interrupt-remapping.
- */
- irte->trigger_mode = 0;
- irte->dlvry_mode = apic->irq_delivery_mode;
- irte->vector = vector;
- irte->dest_id = IRTE_DEST(dest);
- irte->redir_hint = 1;
+ return 0;
}
-static inline bool irq_remapped(struct irq_cfg *cfg)
+static inline void free_remapped_irq(int irq) { }
+static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
+ unsigned int irq, unsigned int dest,
+ struct msi_msg *msg, u8 hpet_id)
{
- return cfg->irq_2_iommu.iommu != NULL;
}
-#else
-static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+static inline int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
{
+ return -ENODEV;
}
-static inline bool irq_remapped(struct irq_cfg *cfg)
+static inline int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
+ int index, int sub_handle)
{
- return false;
+ return -ENODEV;
}
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
{
+ return -ENODEV;
}
-#endif
+#endif /* CONFIG_IRQ_REMAP */
-#endif /* _ASM_X86_IRQ_REMAPPING_H */
+#endif /* __X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 734c3767cfa..183922e13de 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -170,6 +170,9 @@ static inline int kvm_para_available(void)
unsigned int eax, ebx, ecx, edx;
char signature[13];
+ if (boot_cpu_data.cpuid_level < 0)
+ return 0; /* So we don't blow up on old processors */
+
cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
memcpy(signature + 0, &ebx, 4);
memcpy(signature + 4, &ecx, 4);
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index fd3f9f18cf3..0e3793b821e 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -27,6 +27,8 @@ void arch_trigger_all_cpu_backtrace(void);
enum {
NMI_LOCAL=0,
NMI_UNKNOWN,
+ NMI_SERR,
+ NMI_IO_CHECK,
NMI_MAX
};
@@ -35,8 +37,24 @@ enum {
typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
-int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long,
- const char *);
+struct nmiaction {
+ struct list_head list;
+ nmi_handler_t handler;
+ unsigned long flags;
+ const char *name;
+};
+
+#define register_nmi_handler(t, fn, fg, n) \
+({ \
+ static struct nmiaction fn##_na = { \
+ .handler = (fn), \
+ .name = (n), \
+ .flags = (fg), \
+ }; \
+ __register_nmi_handler((t), &fn##_na); \
+})
+
+int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
diff --git a/arch/x86/include/asm/stat.h b/arch/x86/include/asm/stat.h
index e0b1d9bbcbc..7b3ddc34858 100644
--- a/arch/x86/include/asm/stat.h
+++ b/arch/x86/include/asm/stat.h
@@ -25,6 +25,12 @@ struct stat {
unsigned long __unused5;
};
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT_PADDING(st) do { \
+ st.__unused4 = 0; \
+ st.__unused5 = 0; \
+} while (0)
+
#define STAT64_HAS_BROKEN_ST_INO 1
/* This matches struct stat64 in glibc2.1, hence the absolutely
@@ -63,6 +69,12 @@ struct stat64 {
unsigned long long st_ino;
};
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT64_PADDING(st) do { \
+ memset(&st.__pad0, 0, sizeof(st.__pad0)); \
+ memset(&st.__pad3, 0, sizeof(st.__pad3)); \
+} while (0)
+
#else /* __i386__ */
struct stat {
@@ -87,6 +99,15 @@ struct stat {
unsigned long st_ctime_nsec;
long __unused[3];
};
+
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT_PADDING(st) do { \
+ st.__pad0 = 0; \
+ st.__unused[0] = 0; \
+ st.__unused[1] = 0; \
+ st.__unused[2] = 0; \
+} while (0)
+
#endif
/* for 32bit emulation and 32 bit kernels */
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 6fe6767b712..e58f03b206c 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -43,4 +43,37 @@ static inline unsigned long has_zero(unsigned long a)
return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
}
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret, dummy;
+
+ asm(
+ "1:\tmov %2,%0\n"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3:\t"
+ "lea %2,%1\n\t"
+ "and %3,%1\n\t"
+ "mov (%1),%0\n\t"
+ "leal %2,%%ecx\n\t"
+ "andl %4,%%ecx\n\t"
+ "shll $3,%%ecx\n\t"
+ "shr %%cl,%0\n\t"
+ "jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ :"=&r" (ret),"=&c" (dummy)
+ :"m" (*(unsigned long *)addr),
+ "i" (-sizeof(unsigned long)),
+ "i" (sizeof(unsigned long)-1));
+ return ret;
+}
+
#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a415b1f4436..7c439fe4941 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void)
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
-static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index edc24480469..3722179a49d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -35,6 +35,7 @@
#include <linux/smp.h>
#include <linux/mm.h>
+#include <asm/irq_remapping.h>
#include <asm/perf_event.h>
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
@@ -1441,8 +1442,8 @@ void __init bsp_end_local_APIC_setup(void)
* Now that local APIC setup is completed for BP, configure the fault
* handling for interrupt remapping.
*/
- if (intr_remapping_enabled)
- enable_drhd_fault_handling();
+ if (irq_remapping_enabled)
+ irq_remap_enable_fault_handling();
}
@@ -1517,7 +1518,7 @@ void enable_x2apic(void)
int __init enable_IR(void)
{
#ifdef CONFIG_IRQ_REMAP
- if (!intr_remapping_supported()) {
+ if (!irq_remapping_supported()) {
pr_debug("intr-remapping not supported\n");
return -1;
}
@@ -1528,7 +1529,7 @@ int __init enable_IR(void)
return -1;
}
- return enable_intr_remapping();
+ return irq_remapping_enable();
#endif
return -1;
}
@@ -1537,10 +1538,13 @@ void __init enable_IR_x2apic(void)
{
unsigned long flags;
int ret, x2apic_enabled = 0;
- int dmar_table_init_ret;
+ int hardware_init_ret;
- dmar_table_init_ret = dmar_table_init();
- if (dmar_table_init_ret && !x2apic_supported())
+ /* Make sure irq_remap_ops are initialized */
+ setup_irq_remapping_ops();
+
+ hardware_init_ret = irq_remapping_prepare();
+ if (hardware_init_ret && !x2apic_supported())
return;
ret = save_ioapic_entries();
@@ -1556,7 +1560,7 @@ void __init enable_IR_x2apic(void)
if (x2apic_preenabled && nox2apic)
disable_x2apic();
- if (dmar_table_init_ret)
+ if (hardware_init_ret)
ret = -1;
else
ret = enable_IR();
@@ -2176,8 +2180,8 @@ static int lapic_suspend(void)
local_irq_save(flags);
disable_local_APIC();
- if (intr_remapping_enabled)
- disable_intr_remapping();
+ if (irq_remapping_enabled)
+ irq_remapping_disable();
local_irq_restore(flags);
return 0;
@@ -2193,7 +2197,7 @@ static void lapic_resume(void)
return;
local_irq_save(flags);
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
/*
* IO-APIC and PIC have their own resume routines.
* We just mask them here to make sure the interrupt
@@ -2245,8 +2249,8 @@ static void lapic_resume(void)
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- if (intr_remapping_enabled)
- reenable_intr_remapping(x2apic_mode);
+ if (irq_remapping_enabled)
+ irq_remapping_reenable(x2apic_mode);
local_irq_restore(flags);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e88300d8e80..ef0648cd708 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -86,6 +86,22 @@ void __init set_io_apic_ops(const struct io_apic_ops *ops)
io_apic_ops = *ops;
}
+#ifdef CONFIG_IRQ_REMAP
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+ return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+ return false;
+}
+static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+}
+#endif
+
/*
* Is the SiS APIC rmw bug present ?
* -1 = don't know, 0 = no, 1 = yes
@@ -1361,77 +1377,13 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
fasteoi ? "fasteoi" : "edge");
}
-
-static int setup_ir_ioapic_entry(int irq,
- struct IR_IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- int index;
- struct irte irte;
- int ioapic_id = mpc_ioapic_id(attr->ioapic);
- struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id);
-
- if (!iommu) {
- pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
- return -ENODEV;
- }
-
- index = alloc_irte(iommu, irq, 1);
- if (index < 0) {
- pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id);
- return -ENOMEM;
- }
-
- prepare_irte(&irte, vector, destination);
-
- /* Set source-id of interrupt request */
- set_ioapic_sid(&irte, ioapic_id);
-
- modify_irte(irq, &irte);
-
- apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
- "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
- "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
- "Avail:%X Vector:%02X Dest:%08X "
- "SID:%04X SQ:%X SVT:%X)\n",
- attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
- irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
- irte.avail, irte.vector, irte.dest_id,
- irte.sid, irte.sq, irte.svt);
-
- memset(entry, 0, sizeof(*entry));
-
- entry->index2 = (index >> 15) & 0x1;
- entry->zero = 0;
- entry->format = 1;
- entry->index = (index & 0x7fff);
- /*
- * IO-APIC RTE will be configured with virtual vector.
- * irq handler will do the explicit EOI to the io-apic.
- */
- entry->vector = attr->ioapic_pin;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
unsigned int destination, int vector,
struct io_apic_irq_attr *attr)
{
- if (intr_remapping_enabled)
- return setup_ir_ioapic_entry(irq,
- (struct IR_IO_APIC_route_entry *)entry,
- destination, vector, attr);
+ if (irq_remapping_enabled)
+ return setup_ioapic_remapped_entry(irq, entry, destination,
+ vector, attr);
memset(entry, 0, sizeof(*entry));
@@ -1588,7 +1540,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
{
struct IO_APIC_route_entry entry;
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
return;
memset(&entry, 0, sizeof(entry));
@@ -1674,7 +1626,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
printk(KERN_DEBUG ".... IRQ redirection table:\n");
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR"
" Pol Stat Indx2 Zero Vect:\n");
} else {
@@ -1683,7 +1635,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
}
for (i = 0; i <= reg_01.bits.entries; i++) {
- if (intr_remapping_enabled) {
+ if (irq_remapping_enabled) {
struct IO_APIC_route_entry entry;
struct IR_IO_APIC_route_entry *ir_entry;
@@ -2050,7 +2002,7 @@ void disable_IO_APIC(void)
* IOAPIC RTE as well as interrupt-remapping table entry).
* As this gets called during crash dump, keep this simple for now.
*/
- if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) {
+ if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) {
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
@@ -2074,7 +2026,7 @@ void disable_IO_APIC(void)
* Use virtual wire A mode when interrupt remapping is enabled.
*/
if (cpu_has_apic || apic_from_smp_config())
- disconnect_bsp_APIC(!intr_remapping_enabled &&
+ disconnect_bsp_APIC(!irq_remapping_enabled &&
ioapic_i8259.pin != -1);
}
@@ -2390,71 +2342,6 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
return ret;
}
-#ifdef CONFIG_IRQ_REMAP
-
-/*
- * Migrate the IO-APIC irq in the presence of intr-remapping.
- *
- * For both level and edge triggered, irq migration is a simple atomic
- * update(of vector and cpu destination) of IRTE and flush the hardware cache.
- *
- * For level triggered, we eliminate the io-apic RTE modification (with the
- * updated vector information), by using a virtual vector (io-apic pin number).
- * Real vector that is used for interrupting cpu will be coming from
- * the interrupt-remapping table entry.
- *
- * As the migration is a simple atomic update of IRTE, the same mechanism
- * is used to migrate MSI irq's in the presence of interrupt-remapping.
- */
-static int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int dest, irq = data->irq;
- struct irte irte;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- if (get_irte(irq, &irte))
- return -EBUSY;
-
- if (assign_irq_vector(irq, cfg, mask))
- return -EBUSY;
-
- dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
-
- irte.vector = cfg->vector;
- irte.dest_id = IRTE_DEST(dest);
-
- /*
- * Atomically updates the IRTE with the new destination, vector
- * and flushes the interrupt entry cache.
- */
- modify_irte(irq, &irte);
-
- /*
- * After this point, all the interrupts will start arriving
- * at the new destination. So, time to cleanup the previous
- * vector allocation.
- */
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- cpumask_copy(data->affinity, mask);
- return 0;
-}
-
-#else
-static inline int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- return 0;
-}
-#endif
-
asmlinkage void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
@@ -2699,7 +2586,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
chip->irq_eoi = ir_ack_apic_level;
#ifdef CONFIG_SMP
- chip->irq_set_affinity = ir_ioapic_set_affinity;
+ chip->irq_set_affinity = set_remapped_irq_affinity;
#endif
}
#endif /* CONFIG_IRQ_REMAP */
@@ -2912,7 +2799,7 @@ static inline void __init check_timer(void)
* 8259A.
*/
if (pin1 == -1) {
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
panic("BIOS bug: timer not connected to IO-APIC");
pin1 = pin2;
apic1 = apic2;
@@ -2945,7 +2832,7 @@ static inline void __init check_timer(void)
clear_IO_APIC_pin(0, pin1);
goto out;
}
- if (intr_remapping_enabled)
+ if (irq_remapping_enabled)
panic("timer doesn't work through Interrupt-remapped IO-APIC");
local_irq_disable();
clear_IO_APIC_pin(apic1, pin1);
@@ -3169,7 +3056,7 @@ void destroy_irq(unsigned int irq)
irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
if (irq_remapped(cfg))
- free_irte(irq);
+ free_remapped_irq(irq);
raw_spin_lock_irqsave(&vector_lock, flags);
__clear_irq_vector(irq, cfg);
raw_spin_unlock_irqrestore(&vector_lock, flags);
@@ -3198,54 +3085,34 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
if (irq_remapped(cfg)) {
- struct irte irte;
- int ir_index;
- u16 sub_handle;
-
- ir_index = map_irq_to_irte_handle(irq, &sub_handle);
- BUG_ON(ir_index == -1);
-
- prepare_irte(&irte, cfg->vector, dest);
-
- /* Set source-id of interrupt request */
- if (pdev)
- set_msi_sid(&irte, pdev);
- else
- set_hpet_sid(&irte, hpet_id);
-
- modify_irte(irq, &irte);
+ compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id);
+ return err;
+ }
+ if (x2apic_enabled())
+ msg->address_hi = MSI_ADDR_BASE_HI |
+ MSI_ADDR_EXT_DEST_ID(dest);
+ else
msg->address_hi = MSI_ADDR_BASE_HI;
- msg->data = sub_handle;
- msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
- MSI_ADDR_IR_SHV |
- MSI_ADDR_IR_INDEX1(ir_index) |
- MSI_ADDR_IR_INDEX2(ir_index);
- } else {
- if (x2apic_enabled())
- msg->address_hi = MSI_ADDR_BASE_HI |
- MSI_ADDR_EXT_DEST_ID(dest);
- else
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->address_lo =
- MSI_ADDR_BASE_LO |
- ((apic->irq_dest_mode == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
- MSI_ADDR_DEST_MODE_LOGICAL) |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_ADDR_REDIRECTION_CPU:
- MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
+ msg->address_lo =
+ MSI_ADDR_BASE_LO |
+ ((apic->irq_dest_mode == 0) ?
+ MSI_ADDR_DEST_MODE_PHYSICAL:
+ MSI_ADDR_DEST_MODE_LOGICAL) |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_ADDR_REDIRECTION_CPU:
+ MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_DEST_ID(dest);
+
+ msg->data =
+ MSI_DATA_TRIGGER_EDGE |
+ MSI_DATA_LEVEL_ASSERT |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_DATA_DELIVERY_FIXED:
+ MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_VECTOR(cfg->vector);
- msg->data =
- MSI_DATA_TRIGGER_EDGE |
- MSI_DATA_LEVEL_ASSERT |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
- MSI_DATA_DELIVERY_LOWPRI) |
- MSI_DATA_VECTOR(cfg->vector);
- }
return err;
}
@@ -3288,33 +3155,6 @@ static struct irq_chip msi_chip = {
.irq_retrigger = ioapic_retrigger_irq,
};
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
-{
- struct intel_iommu *iommu;
- int index;
-
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- printk(KERN_ERR
- "Unable to map PCI %s to iommu\n", pci_name(dev));
- return -ENOENT;
- }
-
- index = alloc_irte(iommu, irq, nvec);
- if (index < 0) {
- printk(KERN_ERR
- "Unable to allocate %d IRTE for PCI %s\n", nvec,
- pci_name(dev));
- return -ENOSPC;
- }
- return index;
-}
-
static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
struct irq_chip *chip = &msi_chip;
@@ -3345,7 +3185,6 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
int node, ret, sub_handle, index = 0;
unsigned int irq, irq_want;
struct msi_desc *msidesc;
- struct intel_iommu *iommu = NULL;
/* x86 doesn't support multiple MSI yet */
if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3359,7 +3198,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
if (irq == 0)
return -1;
irq_want = irq + 1;
- if (!intr_remapping_enabled)
+ if (!irq_remapping_enabled)
goto no_ir;
if (!sub_handle) {
@@ -3367,23 +3206,16 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
* allocate the consecutive block of IRTE's
* for 'nvec'
*/
- index = msi_alloc_irte(dev, irq, nvec);
+ index = msi_alloc_remapped_irq(dev, irq, nvec);
if (index < 0) {
ret = index;
goto error;
}
} else {
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- ret = -ENOENT;
+ ret = msi_setup_remapped_irq(dev, irq, index,
+ sub_handle);
+ if (ret < 0)
goto error;
- }
- /*
- * setup the mapping between the irq and the IRTE
- * base index, the sub_handle pointing to the
- * appropriate interrupt remap table entry.
- */
- set_irte_irq(irq, iommu, index, sub_handle);
}
no_ir:
ret = setup_msi_irq(dev, msidesc, irq);
@@ -3501,15 +3333,8 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
struct msi_msg msg;
int ret;
- if (intr_remapping_enabled) {
- struct intel_iommu *iommu = map_hpet_to_ir(id);
- int index;
-
- if (!iommu)
- return -1;
-
- index = alloc_irte(iommu, irq, 1);
- if (index < 0)
+ if (irq_remapping_enabled) {
+ if (!setup_hpet_msi_remapped(irq, id))
return -1;
}
@@ -3888,8 +3713,8 @@ void __init setup_ioapic_dest(void)
else
mask = apic->target_cpus();
- if (intr_remapping_enabled)
- ir_ioapic_set_affinity(idata, mask, false);
+ if (irq_remapping_enabled)
+ set_remapped_irq_affinity(idata, mask, false);
else
ioapic_set_affinity(idata, mask, false);
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1c67ca100e4..146bb6218ee 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -580,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
+ /* re-enable TopologyExtensions if switched off by BIOS */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+ !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ u64 val;
+
+ if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+ val |= 1ULL << 54;
+ wrmsrl_amd_safe(0xc0011005, val);
+ rdmsrl(0xc0011005, val);
+ if (val & (1ULL << 54)) {
+ set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+ printk(KERN_INFO FW_INFO "CPU: Re-enabling "
+ "disabled Topology Extensions Support\n");
+ }
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09c087..11c9166c333 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
atomic_t inuse;
struct task_struct *t;
__u64 paddr;
+ int restartable;
} mce_info[MCE_INFO_MAX];
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
{
struct mce_info *mi;
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
mi->t = current;
mi->paddr = addr;
+ mi->restartable = c;
return;
}
}
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst == MCE_AR_SEVERITY) {
/* schedule action before return to userland */
- mce_save_info(m.addr);
+ mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
set_thread_flag(TIF_MCE_NOTIFY);
} else if (kill_it) {
force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
pr_err("Uncorrected hardware memory error in user-access at %llx",
mi->paddr);
- if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+ /*
+ * We must call memory_failure() here even if the current process is
+ * doomed. We still need to mark the page as poisoned and alert any
+ * other users of the page.
+ */
+ if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+ mi->restartable == 0) {
pr_err("Memory error not recovered");
force_sig(SIGBUS, current);
}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ba6e4a27e..e554e5ad2fe 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -79,7 +79,6 @@ struct kvm_task_sleep_node {
u32 token;
int cpu;
bool halted;
- struct mm_struct *mm;
};
static struct kvm_task_sleep_head {
@@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token)
n.token = token;
n.cpu = smp_processor_id();
- n.mm = current->active_mm;
n.halted = idle || preempt_count() > 1;
- atomic_inc(&n.mm->mm_count);
init_waitqueue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
spin_unlock(&b->lock);
@@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
hlist_del_init(&n->link);
- if (!n->mm)
- return;
- mmdrop(n->mm);
if (n->halted)
smp_send_reschedule(n->cpu);
else if (waitqueue_active(&n->wq))
@@ -207,7 +201,7 @@ again:
* async PF was not yet handled.
* Add dummy entry for the token.
*/
- n = kmalloc(sizeof(*n), GFP_ATOMIC);
+ n = kzalloc(sizeof(*n), GFP_ATOMIC);
if (!n) {
/*
* Allocation failed! Busy wait while other cpu
@@ -219,7 +213,6 @@ again:
}
n->token = token;
n->cpu = smp_processor_id();
- n->mm = NULL;
init_waitqueue_head(&n->wq);
hlist_add_head(&n->link, &b->list);
} else
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 3ca42d0e43a..0327e2b3c40 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -147,12 +147,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
memset(csig, 0, sizeof(*csig));
- if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
- cpu_has(c, X86_FEATURE_IA64)) {
- pr_err("CPU%d not a capable Intel processor\n", cpu_num);
- return -1;
- }
-
csig->sig = cpuid_eax(0x00000001);
if ((c->x86_model >= 5) || (c->x86 > 6)) {
@@ -463,6 +457,14 @@ static struct microcode_ops microcode_intel_ops = {
struct microcode_ops * __init init_intel_microcode(void)
{
+ struct cpuinfo_x86 *c = &cpu_data(0);
+
+ if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+ cpu_has(c, X86_FEATURE_IA64)) {
+ pr_err("Intel CPU family 0x%x not supported\n", c->x86);
+ return NULL;
+ }
+
return &microcode_intel_ops;
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 47acaf31916..585be4bd71a 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -31,14 +31,6 @@
#include <asm/nmi.h>
#include <asm/x86_init.h>
-#define NMI_MAX_NAMELEN 16
-struct nmiaction {
- struct list_head list;
- nmi_handler_t handler;
- unsigned int flags;
- char *name;
-};
-
struct nmi_desc {
spinlock_t lock;
struct list_head head;
@@ -54,6 +46,14 @@ static struct nmi_desc nmi_desc[NMI_MAX] =
.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
.head = LIST_HEAD_INIT(nmi_desc[1].head),
},
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[2].head),
+ },
+ {
+ .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock),
+ .head = LIST_HEAD_INIT(nmi_desc[3].head),
+ },
};
@@ -107,11 +107,14 @@ static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs,
return handled;
}
-static int __setup_nmi(unsigned int type, struct nmiaction *action)
+int __register_nmi_handler(unsigned int type, struct nmiaction *action)
{
struct nmi_desc *desc = nmi_to_desc(type);
unsigned long flags;
+ if (!action->handler)
+ return -EINVAL;
+
spin_lock_irqsave(&desc->lock, flags);
/*
@@ -120,6 +123,8 @@ static int __setup_nmi(unsigned int type, struct nmiaction *action)
* to manage expectations
*/
WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
+ WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
+ WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
/*
* some handlers need to be executed first otherwise a fake
@@ -133,8 +138,9 @@ static int __setup_nmi(unsigned int type, struct nmiaction *action)
spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
+EXPORT_SYMBOL(__register_nmi_handler);
-static struct nmiaction *__free_nmi(unsigned int type, const char *name)
+void unregister_nmi_handler(unsigned int type, const char *name)
{
struct nmi_desc *desc = nmi_to_desc(type);
struct nmiaction *n;
@@ -157,61 +163,16 @@ static struct nmiaction *__free_nmi(unsigned int type, const char *name)
spin_unlock_irqrestore(&desc->lock, flags);
synchronize_rcu();
- return (n);
}
-
-int register_nmi_handler(unsigned int type, nmi_handler_t handler,
- unsigned long nmiflags, const char *devname)
-{
- struct nmiaction *action;
- int retval = -ENOMEM;
-
- if (!handler)
- return -EINVAL;
-
- action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
- if (!action)
- goto fail_action;
-
- action->handler = handler;
- action->flags = nmiflags;
- action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
- if (!action->name)
- goto fail_action_name;
-
- retval = __setup_nmi(type, action);
-
- if (retval)
- goto fail_setup_nmi;
-
- return retval;
-
-fail_setup_nmi:
- kfree(action->name);
-fail_action_name:
- kfree(action);
-fail_action:
-
- return retval;
-}
-EXPORT_SYMBOL_GPL(register_nmi_handler);
-
-void unregister_nmi_handler(unsigned int type, const char *name)
-{
- struct nmiaction *a;
-
- a = __free_nmi(type, name);
- if (a) {
- kfree(a->name);
- kfree(a);
- }
-}
-
EXPORT_SYMBOL_GPL(unregister_nmi_handler);
static notrace __kprobes void
pci_serr_error(unsigned char reason, struct pt_regs *regs)
{
+ /* check to see if anyone registered against these types of errors */
+ if (nmi_handle(NMI_SERR, regs, false))
+ return;
+
pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
@@ -241,6 +202,10 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
{
unsigned long i;
+ /* check to see if anyone registered against these types of errors */
+ if (nmi_handle(NMI_IO_CHECK, regs, false))
+ return;
+
pr_emerg(
"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 733ca39f367..43d8b48b23e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -423,6 +423,7 @@ void set_personality_ia32(bool x32)
current_thread_info()->status |= TS_COMPAT;
}
}
+EXPORT_SYMBOL_GPL(set_personality_ia32);
unsigned long get_wchan(struct task_struct *p)
{
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da37..5a98aa27218 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
#endif
rc = -EINVAL;
if (pcpu_chosen_fc != PCPU_FC_PAGE) {
- const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
const size_t dyn_size = PERCPU_MODULE_RESERVE +
PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+ size_t atom_size;
+ /*
+ * On 64bit, use PMD_SIZE for atom_size so that embedded
+ * percpu areas are aligned to PMD. This, in the future,
+ * can also allow using PMD mappings in vmalloc area. Use
+ * PAGE_SIZE on 32bit as vmalloc space is highly contended
+ * and large vmalloc area allocs can easily fail.
+ */
+#ifdef CONFIG_X86_64
+ atom_size = PMD_SIZE;
+#else
+ atom_size = PAGE_SIZE;
+#endif
rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
dyn_size, atom_size,
pcpu_cpu_distance,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 91a5e989abc..185a2b823a2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6581,6 +6581,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
kvm_inject_page_fault(vcpu, &fault);
}
vcpu->arch.apf.halted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index d6ae30bbd7b..2e4e4b02c37 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -44,13 +44,6 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
}
EXPORT_SYMBOL_GPL(copy_from_user_nmi);
-static inline unsigned long count_bytes(unsigned long mask)
-{
- mask = (mask - 1) & ~mask;
- mask >>= 7;
- return count_masked_bytes(mask);
-}
-
/*
* Do a strncpy, return length of string without final '\0'.
* 'count' is the user-supplied count (return 'count' if we
@@ -69,16 +62,19 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, long
max = count;
while (max >= sizeof(unsigned long)) {
- unsigned long c;
+ unsigned long c, mask;
/* Fall back to byte-at-a-time if we get a page fault */
if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
break;
- /* This can write a few bytes past the NUL character, but that's ok */
+ mask = has_zero(c);
+ if (mask) {
+ mask = (mask - 1) & ~mask;
+ mask >>= 7;
+ *(unsigned long *)(dst+res) = c & mask;
+ return res + count_masked_bytes(mask);
+ }
*(unsigned long *)(dst+res) = c;
- c = has_zero(c);
- if (c)
- return res + count_bytes(c);
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index ed2835e148b..fc09c2754e0 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -9,11 +9,11 @@
struct pci_root_info {
struct acpi_device *bridge;
- char *name;
+ char name[16];
unsigned int res_num;
struct resource *res;
- struct list_head *resources;
int busnum;
+ struct pci_sysdata sd;
};
static bool pci_use_crs = true;
@@ -245,13 +245,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
return AE_OK;
}
-static bool resource_contains(struct resource *res, resource_size_t point)
-{
- if (res->start <= point && point <= res->end)
- return true;
- return false;
-}
-
static void coalesce_windows(struct pci_root_info *info, unsigned long type)
{
int i, j;
@@ -272,10 +265,7 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type)
* our resources no longer match the ACPI _CRS, but
* the kernel resource tree doesn't allow overlaps.
*/
- if (resource_contains(res1, res2->start) ||
- resource_contains(res1, res2->end) ||
- resource_contains(res2, res1->start) ||
- resource_contains(res2, res1->end)) {
+ if (resource_overlaps(res1, res2)) {
res1->start = min(res1->start, res2->start);
res1->end = max(res1->end, res2->end);
dev_info(&info->bridge->dev,
@@ -287,7 +277,8 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type)
}
}
-static void add_resources(struct pci_root_info *info)
+static void add_resources(struct pci_root_info *info,
+ struct list_head *resources)
{
int i;
struct resource *res, *root, *conflict;
@@ -311,53 +302,74 @@ static void add_resources(struct pci_root_info *info)
"ignoring host bridge window %pR (conflicts with %s %pR)\n",
res, conflict->name, conflict);
else
- pci_add_resource(info->resources, res);
+ pci_add_resource(resources, res);
}
}
+static void free_pci_root_info_res(struct pci_root_info *info)
+{
+ kfree(info->res);
+ info->res = NULL;
+ info->res_num = 0;
+}
+
+static void __release_pci_root_info(struct pci_root_info *info)
+{
+ int i;
+ struct resource *res;
+
+ for (i = 0; i < info->res_num; i++) {
+ res = &info->res[i];
+
+ if (!res->parent)
+ continue;
+
+ if (!(res->flags & (IORESOURCE_MEM | IORESOURCE_IO)))
+ continue;
+
+ release_resource(res);
+ }
+
+ free_pci_root_info_res(info);
+
+ kfree(info);
+}
+static void release_pci_root_info(struct pci_host_bridge *bridge)
+{
+ struct pci_root_info *info = bridge->release_data;
+
+ __release_pci_root_info(info);
+}
+
static void
-get_current_resources(struct acpi_device *device, int busnum,
- int domain, struct list_head *resources)
+probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
+ int busnum, int domain)
{
- struct pci_root_info info;
size_t size;
- info.bridge = device;
- info.res_num = 0;
- info.resources = resources;
+ info->bridge = device;
+ info->res_num = 0;
acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource,
- &info);
- if (!info.res_num)
+ info);
+ if (!info->res_num)
return;
- size = sizeof(*info.res) * info.res_num;
- info.res = kmalloc(size, GFP_KERNEL);
- if (!info.res)
+ size = sizeof(*info->res) * info->res_num;
+ info->res_num = 0;
+ info->res = kmalloc(size, GFP_KERNEL);
+ if (!info->res)
return;
- info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum);
- if (!info.name)
- goto name_alloc_fail;
+ sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
- info.res_num = 0;
acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
- &info);
-
- if (pci_use_crs) {
- add_resources(&info);
-
- return;
- }
-
- kfree(info.name);
-
-name_alloc_fail:
- kfree(info.res);
+ info);
}
struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
{
struct acpi_device *device = root->device;
+ struct pci_root_info *info = NULL;
int domain = root->segment;
int busnum = root->secondary.start;
LIST_HEAD(resources);
@@ -389,17 +401,14 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
if (node != -1 && !node_online(node))
node = -1;
- /* Allocate per-root-bus (not per bus) arch-specific data.
- * TODO: leak; this memory is never freed.
- * It's arguable whether it's worth the trouble to care.
- */
- sd = kzalloc(sizeof(*sd), GFP_KERNEL);
- if (!sd) {
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (out of memory)\n", domain, busnum);
return NULL;
}
+ sd = &info->sd;
sd->domain = domain;
sd->node = node;
/*
@@ -413,22 +422,32 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
* be replaced by sd.
*/
memcpy(bus->sysdata, sd, sizeof(*sd));
- kfree(sd);
+ kfree(info);
} else {
- get_current_resources(device, busnum, domain, &resources);
+ probe_pci_root_info(info, device, busnum, domain);
/*
* _CRS with no apertures is normal, so only fall back to
* defaults or native bridge info if we're ignoring _CRS.
*/
- if (!pci_use_crs)
+ if (pci_use_crs)
+ add_resources(info, &resources);
+ else {
+ free_pci_root_info_res(info);
x86_pci_root_bus_resources(busnum, &resources);
+ }
+
bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd,
&resources);
- if (bus)
+ if (bus) {
bus->subordinate = pci_scan_child_bus(bus);
- else
+ pci_set_host_bridge_release(
+ to_pci_host_bridge(bus->bridge),
+ release_pci_root_info, info);
+ } else {
pci_free_resource_list(&resources);
+ __release_pci_root_info(info);
+ }
}
/* After the PCI-E bus has been walked and all devices discovered,
@@ -445,9 +464,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
}
}
- if (!bus)
- kfree(sd);
-
if (bus && node != -1) {
#ifdef CONFIG_ACPI_NUMA
if (pxm >= 0)
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 0567df3890e..5aed49bff05 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -32,6 +32,27 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = {
#define RANGE_NUM 16
+static struct pci_root_info __init *find_pci_root_info(int node, int link)
+{
+ struct pci_root_info *info;
+
+ /* find the position */
+ list_for_each_entry(info, &pci_root_infos, list)
+ if (info->node == node && info->link == link)
+ return info;
+
+ return NULL;
+}
+
+static void __init set_mp_bus_range_to_node(int min_bus, int max_bus, int node)
+{
+#ifdef CONFIG_NUMA
+ int j;
+
+ for (j = min_bus; j <= max_bus; j++)
+ set_mp_bus_to_node(j, node);
+#endif
+}
/**
* early_fill_mp_bus_to_node()
* called before pcibios_scan_root and pci_scan_bus
@@ -41,7 +62,6 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = {
static int __init early_fill_mp_bus_info(void)
{
int i;
- int j;
unsigned bus;
unsigned slot;
int node;
@@ -50,7 +70,6 @@ static int __init early_fill_mp_bus_info(void)
int def_link;
struct pci_root_info *info;
u32 reg;
- struct resource *res;
u64 start;
u64 end;
struct range range[RANGE_NUM];
@@ -86,7 +105,6 @@ static int __init early_fill_mp_bus_info(void)
if (!found)
return 0;
- pci_root_num = 0;
for (i = 0; i < 4; i++) {
int min_bus;
int max_bus;
@@ -99,19 +117,11 @@ static int __init early_fill_mp_bus_info(void)
min_bus = (reg >> 16) & 0xff;
max_bus = (reg >> 24) & 0xff;
node = (reg >> 4) & 0x07;
-#ifdef CONFIG_NUMA
- for (j = min_bus; j <= max_bus; j++)
- set_mp_bus_to_node(j, node);
-#endif
+ set_mp_bus_range_to_node(min_bus, max_bus, node);
link = (reg >> 8) & 0x03;
- info = &pci_root_info[pci_root_num];
- info->bus_min = min_bus;
- info->bus_max = max_bus;
- info->node = node;
- info->link = link;
+ info = alloc_pci_root_info(min_bus, max_bus, node, link);
sprintf(info->name, "PCI Bus #%02x", min_bus);
- pci_root_num++;
}
/* get the default node and link for left over res */
@@ -134,16 +144,10 @@ static int __init early_fill_mp_bus_info(void)
link = (reg >> 4) & 0x03;
end = (reg & 0xfff000) | 0xfff;
- /* find the position */
- for (j = 0; j < pci_root_num; j++) {
- info = &pci_root_info[j];
- if (info->node == node && info->link == link)
- break;
- }
- if (j == pci_root_num)
+ info = find_pci_root_info(node, link);
+ if (!info)
continue; /* not found */
- info = &pci_root_info[j];
printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
node, link, start, end);
@@ -155,13 +159,8 @@ static int __init early_fill_mp_bus_info(void)
}
/* add left over io port range to def node/link, [0, 0xffff] */
/* find the position */
- for (j = 0; j < pci_root_num; j++) {
- info = &pci_root_info[j];
- if (info->node == def_node && info->link == def_link)
- break;
- }
- if (j < pci_root_num) {
- info = &pci_root_info[j];
+ info = find_pci_root_info(def_node, def_link);
+ if (info) {
for (i = 0; i < RANGE_NUM; i++) {
if (!range[i].end)
continue;
@@ -214,16 +213,10 @@ static int __init early_fill_mp_bus_info(void)
end <<= 8;
end |= 0xffff;
- /* find the position */
- for (j = 0; j < pci_root_num; j++) {
- info = &pci_root_info[j];
- if (info->node == node && info->link == link)
- break;
- }
- if (j == pci_root_num)
- continue; /* not found */
+ info = find_pci_root_info(node, link);
- info = &pci_root_info[j];
+ if (!info)
+ continue;
printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
node, link, start, end);
@@ -291,14 +284,8 @@ static int __init early_fill_mp_bus_info(void)
* add left over mmio range to def node/link ?
* that is tricky, just record range in from start_min to 4G
*/
- for (j = 0; j < pci_root_num; j++) {
- info = &pci_root_info[j];
- if (info->node == def_node && info->link == def_link)
- break;
- }
- if (j < pci_root_num) {
- info = &pci_root_info[j];
-
+ info = find_pci_root_info(def_node, def_link);
+ if (info) {
for (i = 0; i < RANGE_NUM; i++) {
if (!range[i].end)
continue;
@@ -309,20 +296,16 @@ static int __init early_fill_mp_bus_info(void)
}
}
- for (i = 0; i < pci_root_num; i++) {
- int res_num;
+ list_for_each_entry(info, &pci_root_infos, list) {
int busnum;
+ struct pci_root_res *root_res;
- info = &pci_root_info[i];
- res_num = info->res_num;
busnum = info->bus_min;
printk(KERN_DEBUG "bus: [%02x, %02x] on node %x link %x\n",
info->bus_min, info->bus_max, info->node, info->link);
- for (j = 0; j < res_num; j++) {
- res = &info->res[j];
- printk(KERN_DEBUG "bus: %02x index %x %pR\n",
- busnum, j, res);
- }
+ list_for_each_entry(root_res, &info->resources, list)
+ printk(KERN_DEBUG "bus: %02x %pR\n",
+ busnum, &root_res->res);
}
return 0;
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index f3a7c569a40..614392ced7d 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -22,19 +22,15 @@
static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
{
struct pci_root_info *info;
+ struct pci_root_res *root_res;
struct resource res;
u16 word1, word2;
u8 fbus, lbus;
- int i;
-
- info = &pci_root_info[pci_root_num];
- pci_root_num++;
/* read the PCI bus numbers */
fbus = read_pci_config_byte(bus, slot, func, 0x44);
lbus = read_pci_config_byte(bus, slot, func, 0x45);
- info->bus_min = fbus;
- info->bus_max = lbus;
+ info = alloc_pci_root_info(fbus, lbus, 0, 0);
/*
* Add the legacy IDE ports on bus 0
@@ -86,8 +82,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
res.flags = IORESOURCE_BUS;
printk(KERN_INFO "CNB20LE PCI Host Bridge (domain 0000 %pR)\n", &res);
- for (i = 0; i < info->res_num; i++)
- printk(KERN_INFO "host bridge window %pR\n", &info->res[i]);
+ list_for_each_entry(root_res, &info->resources, list)
+ printk(KERN_INFO "host bridge window %pR\n", &root_res->res);
}
static int __init broadcom_postcore_init(void)
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index fd3f65510e9..306579f7d0f 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -4,35 +4,38 @@
#include "bus_numa.h"
-int pci_root_num;
-struct pci_root_info pci_root_info[PCI_ROOT_NR];
+LIST_HEAD(pci_root_infos);
-void x86_pci_root_bus_resources(int bus, struct list_head *resources)
+static struct pci_root_info *x86_find_pci_root_info(int bus)
{
- int i;
- int j;
struct pci_root_info *info;
- if (!pci_root_num)
- goto default_resources;
+ if (list_empty(&pci_root_infos))
+ return NULL;
- for (i = 0; i < pci_root_num; i++) {
- if (pci_root_info[i].bus_min == bus)
- break;
- }
+ list_for_each_entry(info, &pci_root_infos, list)
+ if (info->bus_min == bus)
+ return info;
+
+ return NULL;
+}
- if (i == pci_root_num)
+void x86_pci_root_bus_resources(int bus, struct list_head *resources)
+{
+ struct pci_root_info *info = x86_find_pci_root_info(bus);
+ struct pci_root_res *root_res;
+
+ if (!info)
goto default_resources;
printk(KERN_DEBUG "PCI: root bus %02x: hardware-probed resources\n",
bus);
- info = &pci_root_info[i];
- for (j = 0; j < info->res_num; j++) {
+ list_for_each_entry(root_res, &info->resources, list) {
struct resource *res;
struct resource *root;
- res = &info->res[j];
+ res = &root_res->res;
pci_add_resource(resources, res);
if (res->flags & IORESOURCE_IO)
root = &ioport_resource;
@@ -53,11 +56,32 @@ default_resources:
pci_add_resource(resources, &iomem_resource);
}
+struct pci_root_info __init *alloc_pci_root_info(int bus_min, int bus_max,
+ int node, int link)
+{
+ struct pci_root_info *info;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+ if (!info)
+ return info;
+
+ INIT_LIST_HEAD(&info->resources);
+ info->bus_min = bus_min;
+ info->bus_max = bus_max;
+ info->node = node;
+ info->link = link;
+
+ list_add_tail(&info->list, &pci_root_infos);
+
+ return info;
+}
+
void __devinit update_res(struct pci_root_info *info, resource_size_t start,
resource_size_t end, unsigned long flags, int merge)
{
- int i;
struct resource *res;
+ struct pci_root_res *root_res;
if (start > end)
return;
@@ -69,11 +93,11 @@ void __devinit update_res(struct pci_root_info *info, resource_size_t start,
goto addit;
/* try to merge it with old one */
- for (i = 0; i < info->res_num; i++) {
+ list_for_each_entry(root_res, &info->resources, list) {
resource_size_t final_start, final_end;
resource_size_t common_start, common_end;
- res = &info->res[i];
+ res = &root_res->res;
if (res->flags != flags)
continue;
@@ -93,14 +117,15 @@ void __devinit update_res(struct pci_root_info *info, resource_size_t start,
addit:
/* need to add that */
- if (info->res_num >= RES_NUM)
+ root_res = kzalloc(sizeof(*root_res), GFP_KERNEL);
+ if (!root_res)
return;
- res = &info->res[info->res_num];
+ res = &root_res->res;
res->name = info->name;
res->flags = flags;
res->start = start;
res->end = end;
- res->child = NULL;
- info->res_num++;
+
+ list_add_tail(&root_res->list, &info->resources);
}
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index 804a4b40c31..226a466b2b2 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -4,22 +4,24 @@
* sub bus (transparent) will use entres from 3 to store extra from
* root, so need to make sure we have enough slot there.
*/
-#define RES_NUM 16
+struct pci_root_res {
+ struct list_head list;
+ struct resource res;
+};
+
struct pci_root_info {
+ struct list_head list;
char name[12];
- unsigned int res_num;
- struct resource res[RES_NUM];
+ struct list_head resources;
int bus_min;
int bus_max;
int node;
int link;
};
-/* 4 at this time, it may become to 32 */
-#define PCI_ROOT_NR 4
-extern int pci_root_num;
-extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
-
+extern struct list_head pci_root_infos;
+struct pci_root_info *alloc_pci_root_info(int bus_min, int bus_max,
+ int node, int link);
extern void update_res(struct pci_root_info *info, resource_size_t start,
resource_size_t end, unsigned long flags, int merge);
#endif
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 323481e06ef..0ad990a20d4 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -11,6 +11,7 @@
#include <linux/dmi.h>
#include <linux/slab.h>
+#include <asm-generic/pci-bridge.h>
#include <asm/acpi.h>
#include <asm/segment.h>
#include <asm/io.h>
@@ -229,6 +230,14 @@ static int __devinit assign_all_busses(const struct dmi_system_id *d)
}
#endif
+static int __devinit set_scan_all(const struct dmi_system_id *d)
+{
+ printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n",
+ d->ident);
+ pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+ return 0;
+}
+
static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = {
#ifdef __i386__
/*
@@ -420,6 +429,13 @@ static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
},
},
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ftServer"),
+ },
+ },
{}
};
@@ -430,9 +446,7 @@ void __init dmi_check_pciprobe(void)
struct pci_bus * __devinit pcibios_scan_root(int busnum)
{
- LIST_HEAD(resources);
struct pci_bus *bus = NULL;
- struct pci_sysdata *sd;
while ((bus = pci_find_next_bus(bus)) != NULL) {
if (bus->number == busnum) {
@@ -441,28 +455,10 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
}
}
- /* Allocate per-root-bus (not per bus) arch-specific data.
- * TODO: leak; this memory is never freed.
- * It's arguable whether it's worth the trouble to care.
- */
- sd = kzalloc(sizeof(*sd), GFP_KERNEL);
- if (!sd) {
- printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum);
- return NULL;
- }
-
- sd->node = get_mp_bus_to_node(busnum);
-
- printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
- x86_pci_root_bus_resources(busnum, &resources);
- bus = pci_scan_root_bus(NULL, busnum, &pci_root_ops, sd, &resources);
- if (!bus) {
- pci_free_resource_list(&resources);
- kfree(sd);
- }
-
- return bus;
+ return pci_scan_bus_on_node(busnum, &pci_root_ops,
+ get_mp_bus_to_node(busnum));
}
+
void __init pcibios_set_cache_line_size(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -656,6 +652,7 @@ struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops,
}
sd->node = node;
x86_pci_root_bus_resources(busno, &resources);
+ printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busno);
bus = pci_scan_root_bus(NULL, busno, ops, sd, &resources);
if (!bus) {
pci_free_resource_list(&resources);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 831971e731f..dd8ca6f7223 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -57,7 +57,7 @@ static struct pcibios_fwaddrmap *pcibios_fwaddrmap_lookup(struct pci_dev *dev)
{
struct pcibios_fwaddrmap *map;
- WARN_ON(!spin_is_locked(&pcibios_fwaddrmap_lock));
+ WARN_ON_SMP(!spin_is_locked(&pcibios_fwaddrmap_lock));
list_for_each_entry(map, &pcibios_fwaddrmappings, list)
if (map->dev == dev)
diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c
index 66d377e334f..646e3b5b4bb 100644
--- a/arch/x86/platform/geode/net5501.c
+++ b/arch/x86/platform/geode/net5501.c
@@ -63,7 +63,7 @@ static struct gpio_led net5501_leds[] = {
.name = "net5501:1",
.gpio = 6,
.default_trigger = "default-on",
- .active_low = 1,
+ .active_low = 0,
},
};
diff --git a/arch/x86/tools/.gitignore b/arch/x86/tools/.gitignore
new file mode 100644
index 00000000000..be0ed065249
--- /dev/null
+++ b/arch/x86/tools/.gitignore
@@ -0,0 +1 @@
+relocs
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index d511aa97533..733057b435b 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -36,3 +36,7 @@ HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x
$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include
+hostprogs-y += relocs
+relocs: $(obj)/relocs
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/tools/relocs.c
index d3c0b027766..b43cfcd9bf4 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -18,6 +18,8 @@ static void die(char *fmt, ...);
static Elf32_Ehdr ehdr;
static unsigned long reloc_count, reloc_idx;
static unsigned long *relocs;
+static unsigned long reloc16_count, reloc16_idx;
+static unsigned long *relocs16;
struct section {
Elf32_Shdr shdr;
@@ -28,52 +30,86 @@ struct section {
};
static struct section *secs;
+enum symtype {
+ S_ABS,
+ S_REL,
+ S_SEG,
+ S_LIN,
+ S_NSYMTYPES
+};
+
+static const char * const sym_regex_kernel[S_NSYMTYPES] = {
/*
* Following symbols have been audited. There values are constant and do
* not change if bzImage is loaded at a different physical address than
* the address for which it has been compiled. Don't warn user about
* absolute relocations present w.r.t these symbols.
*/
-static const char abs_sym_regex[] =
+ [S_ABS] =
"^(xen_irq_disable_direct_reloc$|"
"xen_save_fl_direct_reloc$|"
"VDSO|"
- "__crc_)";
-static regex_t abs_sym_regex_c;
-static int is_abs_reloc(const char *sym_name)
-{
- return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0);
-}
+ "__crc_)",
/*
* These symbols are known to be relative, even if the linker marks them
* as absolute (typically defined outside any section in the linker script.)
*/
-static const char rel_sym_regex[] =
- "^_end$";
-static regex_t rel_sym_regex_c;
-static int is_rel_reloc(const char *sym_name)
+ [S_REL] =
+ "^(__init_(begin|end)|"
+ "__x86_cpu_dev_(start|end)|"
+ "(__parainstructions|__alt_instructions)(|_end)|"
+ "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|"
+ "_end)$"
+};
+
+
+static const char * const sym_regex_realmode[S_NSYMTYPES] = {
+/*
+ * These are 16-bit segment symbols when compiling 16-bit code.
+ */
+ [S_SEG] =
+ "^real_mode_seg$",
+
+/*
+ * These are offsets belonging to segments, as opposed to linear addresses,
+ * when compiling 16-bit code.
+ */
+ [S_LIN] =
+ "^pa_",
+};
+
+static const char * const *sym_regex;
+
+static regex_t sym_regex_c[S_NSYMTYPES];
+static int is_reloc(enum symtype type, const char *sym_name)
{
- return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0);
+ return sym_regex[type] &&
+ !regexec(&sym_regex_c[type], sym_name, 0, NULL, 0);
}
-static void regex_init(void)
+static void regex_init(int use_real_mode)
{
char errbuf[128];
int err;
-
- err = regcomp(&abs_sym_regex_c, abs_sym_regex,
- REG_EXTENDED|REG_NOSUB);
- if (err) {
- regerror(err, &abs_sym_regex_c, errbuf, sizeof errbuf);
- die("%s", errbuf);
- }
+ int i;
+
+ if (use_real_mode)
+ sym_regex = sym_regex_realmode;
+ else
+ sym_regex = sym_regex_kernel;
- err = regcomp(&rel_sym_regex_c, rel_sym_regex,
- REG_EXTENDED|REG_NOSUB);
- if (err) {
- regerror(err, &rel_sym_regex_c, errbuf, sizeof errbuf);
- die("%s", errbuf);
+ for (i = 0; i < S_NSYMTYPES; i++) {
+ if (!sym_regex[i])
+ continue;
+
+ err = regcomp(&sym_regex_c[i], sym_regex[i],
+ REG_EXTENDED|REG_NOSUB);
+
+ if (err) {
+ regerror(err, &sym_regex_c[i], errbuf, sizeof errbuf);
+ die("%s", errbuf);
+ }
}
}
@@ -154,6 +190,10 @@ static const char *rel_type(unsigned type)
REL_TYPE(R_386_RELATIVE),
REL_TYPE(R_386_GOTOFF),
REL_TYPE(R_386_GOTPC),
+ REL_TYPE(R_386_8),
+ REL_TYPE(R_386_PC8),
+ REL_TYPE(R_386_16),
+ REL_TYPE(R_386_PC16),
#undef REL_TYPE
};
const char *name = "unknown type rel type name";
@@ -189,7 +229,7 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym)
name = sym_strtab + sym->st_name;
}
else {
- name = sec_name(secs[sym->st_shndx].shdr.sh_name);
+ name = sec_name(sym->st_shndx);
}
return name;
}
@@ -403,13 +443,11 @@ static void print_absolute_symbols(void)
for (i = 0; i < ehdr.e_shnum; i++) {
struct section *sec = &secs[i];
char *sym_strtab;
- Elf32_Sym *sh_symtab;
int j;
if (sec->shdr.sh_type != SHT_SYMTAB) {
continue;
}
- sh_symtab = sec->symtab;
sym_strtab = sec->link->strtab;
for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
Elf32_Sym *sym;
@@ -474,7 +512,7 @@ static void print_absolute_relocs(void)
* Before warning check if this absolute symbol
* relocation is harmless.
*/
- if (is_abs_reloc(name) || is_rel_reloc(name))
+ if (is_reloc(S_ABS, name) || is_reloc(S_REL, name))
continue;
if (!printed) {
@@ -498,7 +536,8 @@ static void print_absolute_relocs(void)
printf("\n");
}
-static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
+static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym),
+ int use_real_mode)
{
int i;
/* Walk through the relocations */
@@ -523,30 +562,67 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
Elf32_Rel *rel;
Elf32_Sym *sym;
unsigned r_type;
+ const char *symname;
+ int shn_abs;
+
rel = &sec->reltab[j];
sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
r_type = ELF32_R_TYPE(rel->r_info);
- /* Don't visit relocations to absolute symbols */
- if (sym->st_shndx == SHN_ABS &&
- !is_rel_reloc(sym_name(sym_strtab, sym))) {
- continue;
- }
+
+ shn_abs = sym->st_shndx == SHN_ABS;
+
switch (r_type) {
case R_386_NONE:
case R_386_PC32:
+ case R_386_PC16:
+ case R_386_PC8:
/*
* NONE can be ignored and and PC relative
* relocations don't need to be adjusted.
*/
break;
+
+ case R_386_16:
+ symname = sym_name(sym_strtab, sym);
+ if (!use_real_mode)
+ goto bad;
+ if (shn_abs) {
+ if (is_reloc(S_ABS, symname))
+ break;
+ else if (!is_reloc(S_SEG, symname))
+ goto bad;
+ } else {
+ if (is_reloc(S_LIN, symname))
+ goto bad;
+ else
+ break;
+ }
+ visit(rel, sym);
+ break;
+
case R_386_32:
- /* Visit relocations that need to be adjusted */
+ symname = sym_name(sym_strtab, sym);
+ if (shn_abs) {
+ if (is_reloc(S_ABS, symname))
+ break;
+ else if (!is_reloc(S_REL, symname))
+ goto bad;
+ } else {
+ if (use_real_mode &&
+ !is_reloc(S_LIN, symname))
+ break;
+ }
visit(rel, sym);
break;
default:
die("Unsupported relocation type: %s (%d)\n",
rel_type(r_type), r_type);
break;
+ bad:
+ symname = sym_name(sym_strtab, sym);
+ die("Invalid %s %s relocation: %s\n",
+ shn_abs ? "absolute" : "relative",
+ rel_type(r_type), symname);
}
}
}
@@ -554,13 +630,19 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
{
- reloc_count += 1;
+ if (ELF32_R_TYPE(rel->r_info) == R_386_16)
+ reloc16_count++;
+ else
+ reloc_count++;
}
static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
{
/* Remember the address that needs to be adjusted. */
- relocs[reloc_idx++] = rel->r_offset;
+ if (ELF32_R_TYPE(rel->r_info) == R_386_16)
+ relocs16[reloc16_idx++] = rel->r_offset;
+ else
+ relocs[reloc_idx++] = rel->r_offset;
}
static int cmp_relocs(const void *va, const void *vb)
@@ -570,23 +652,41 @@ static int cmp_relocs(const void *va, const void *vb)
return (*a == *b)? 0 : (*a > *b)? 1 : -1;
}
-static void emit_relocs(int as_text)
+static int write32(unsigned int v, FILE *f)
+{
+ unsigned char buf[4];
+
+ put_unaligned_le32(v, buf);
+ return fwrite(buf, 1, 4, f) == 4 ? 0 : -1;
+}
+
+static void emit_relocs(int as_text, int use_real_mode)
{
int i;
/* Count how many relocations I have and allocate space for them. */
reloc_count = 0;
- walk_relocs(count_reloc);
+ walk_relocs(count_reloc, use_real_mode);
relocs = malloc(reloc_count * sizeof(relocs[0]));
if (!relocs) {
die("malloc of %d entries for relocs failed\n",
reloc_count);
}
+
+ relocs16 = malloc(reloc16_count * sizeof(relocs[0]));
+ if (!relocs16) {
+ die("malloc of %d entries for relocs16 failed\n",
+ reloc16_count);
+ }
/* Collect up the relocations */
reloc_idx = 0;
- walk_relocs(collect_reloc);
+ walk_relocs(collect_reloc, use_real_mode);
+
+ if (reloc16_count && !use_real_mode)
+ die("Segment relocations found but --realmode not specified\n");
/* Order the relocations for more efficient processing */
qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs);
+ qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs);
/* Print the relocations */
if (as_text) {
@@ -595,58 +695,83 @@ static void emit_relocs(int as_text)
*/
printf(".section \".data.reloc\",\"a\"\n");
printf(".balign 4\n");
- for (i = 0; i < reloc_count; i++) {
- printf("\t .long 0x%08lx\n", relocs[i]);
+ if (use_real_mode) {
+ printf("\t.long %lu\n", reloc16_count);
+ for (i = 0; i < reloc16_count; i++)
+ printf("\t.long 0x%08lx\n", relocs16[i]);
+ printf("\t.long %lu\n", reloc_count);
+ for (i = 0; i < reloc_count; i++) {
+ printf("\t.long 0x%08lx\n", relocs[i]);
+ }
+ } else {
+ /* Print a stop */
+ printf("\t.long 0x%08lx\n", (unsigned long)0);
+ for (i = 0; i < reloc_count; i++) {
+ printf("\t.long 0x%08lx\n", relocs[i]);
+ }
}
+
printf("\n");
}
else {
- unsigned char buf[4];
- /* Print a stop */
- fwrite("\0\0\0\0", 4, 1, stdout);
- /* Now print each relocation */
- for (i = 0; i < reloc_count; i++) {
- put_unaligned_le32(relocs[i], buf);
- fwrite(buf, 4, 1, stdout);
+ if (use_real_mode) {
+ write32(reloc16_count, stdout);
+ for (i = 0; i < reloc16_count; i++)
+ write32(relocs16[i], stdout);
+ write32(reloc_count, stdout);
+
+ /* Now print each relocation */
+ for (i = 0; i < reloc_count; i++)
+ write32(relocs[i], stdout);
+ } else {
+ /* Print a stop */
+ write32(0, stdout);
+
+ /* Now print each relocation */
+ for (i = 0; i < reloc_count; i++) {
+ write32(relocs[i], stdout);
+ }
}
}
}
static void usage(void)
{
- die("relocs [--abs-syms |--abs-relocs | --text] vmlinux\n");
+ die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n");
}
int main(int argc, char **argv)
{
int show_absolute_syms, show_absolute_relocs;
- int as_text;
+ int as_text, use_real_mode;
const char *fname;
FILE *fp;
int i;
- regex_init();
-
show_absolute_syms = 0;
show_absolute_relocs = 0;
as_text = 0;
+ use_real_mode = 0;
fname = NULL;
for (i = 1; i < argc; i++) {
char *arg = argv[i];
if (*arg == '-') {
- if (strcmp(argv[1], "--abs-syms") == 0) {
+ if (strcmp(arg, "--abs-syms") == 0) {
show_absolute_syms = 1;
continue;
}
-
- if (strcmp(argv[1], "--abs-relocs") == 0) {
+ if (strcmp(arg, "--abs-relocs") == 0) {
show_absolute_relocs = 1;
continue;
}
- else if (strcmp(argv[1], "--text") == 0) {
+ if (strcmp(arg, "--text") == 0) {
as_text = 1;
continue;
}
+ if (strcmp(arg, "--realmode") == 0) {
+ use_real_mode = 1;
+ continue;
+ }
}
else if (!fname) {
fname = arg;
@@ -657,6 +782,7 @@ int main(int argc, char **argv)
if (!fname) {
usage();
}
+ regex_init(use_real_mode);
fp = fopen(fname, "r");
if (!fp) {
die("Cannot open %s: %s\n",
@@ -675,6 +801,6 @@ int main(int argc, char **argv)
print_absolute_relocs();
return 0;
}
- emit_relocs(as_text);
+ emit_relocs(as_text, use_real_mode);
return 0;
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a8f8844b8d3..95dccce8e97 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -63,6 +63,7 @@
#include <asm/stackprotector.h>
#include <asm/hypervisor.h>
#include <asm/mwait.h>
+#include <asm/pci_x86.h>
#ifdef CONFIG_ACPI
#include <linux/acpi.h>
@@ -809,9 +810,40 @@ static void xen_io_delay(void)
}
#ifdef CONFIG_X86_LOCAL_APIC
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+ WARN_ON(1);
+ return x;
+}
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+ return ((x)>>24) & 0xFFu;
+}
static u32 xen_apic_read(u32 reg)
{
- return 0;
+ struct xen_platform_op op = {
+ .cmd = XENPF_get_cpuinfo,
+ .interface_version = XENPF_INTERFACE_VERSION,
+ .u.pcpu_info.xen_cpuid = 0,
+ };
+ int ret = 0;
+
+ /* Shouldn't need this as APIC is turned off for PV, and we only
+ * get called on the bootup processor. But just in case. */
+ if (!xen_initial_domain() || smp_processor_id())
+ return 0;
+
+ if (reg == APIC_LVR)
+ return 0x10;
+
+ if (reg != APIC_ID)
+ return 0;
+
+ ret = HYPERVISOR_dom0_op(&op);
+ if (ret)
+ return 0;
+
+ return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
@@ -849,6 +881,8 @@ static void set_xen_basic_apic_ops(void)
apic->icr_write = xen_apic_icr_write;
apic->wait_icr_idle = xen_apic_wait_icr_idle;
apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
+ apic->set_apic_id = xen_set_apic_id;
+ apic->get_apic_id = xen_get_apic_id;
}
#endif
@@ -1365,8 +1399,10 @@ asmlinkage void __init xen_start_kernel(void)
/* Make sure ACS will be enabled */
pci_request_acs();
}
-
-
+#ifdef CONFIG_PCI
+ /* PCI BIOS service won't work from a PV guest. */
+ pci_probe &= ~PCI_PROBE_BIOS;
+#endif
xen_raw_console_write("about to get started...\n");
xen_setup_runstate_info(0);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b8e279479a6..69f5857660a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ unsigned long pfn = mfn_to_pfn(mfn);
+
pteval_t flags = val & PTE_FLAGS_MASK;
- val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+ if (unlikely(pfn == ~0))
+ val = flags & ~_PAGE_PRESENT;
+ else
+ val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
}
return val;