summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c24
-rw-r--r--arch/x86/kernel/acpi/cstate.c4
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/aperture_64.c20
-rw-r--r--arch/x86/kernel/apic/Makefile3
-rw-r--r--arch/x86/kernel/apic/apic.c17
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c4
-rw-r--r--arch/x86/kernel/apic/apic_noop.c3
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c3
-rw-r--r--arch/x86/kernel/apic/es7000_32.c746
-rw-r--r--arch/x86/kernel/apic/numaq_32.c525
-rw-r--r--arch/x86/kernel/apic/probe_32.c3
-rw-r--r--arch/x86/kernel/apic/summit_32.c551
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c50
-rw-r--r--arch/x86/kernel/cpu/centaur.c272
-rw-r--r--arch/x86/kernel/cpu/common.c11
-rw-r--r--arch/x86/kernel/cpu/intel.c57
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c13
-rw-r--r--arch/x86/kernel/cpu/match.c42
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c24
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c33
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c18
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c84
-rw-r--r--arch/x86/kernel/cpu/perf_event.c46
-rw-r--r--arch/x86/kernel/cpu/perf_event.h8
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_uncore.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c54
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c547
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h5
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c34
-rw-r--r--arch/x86/kernel/cpuid.c15
-rw-r--r--arch/x86/kernel/crash.c2
-rw-r--r--arch/x86/kernel/dumpstack_32.c46
-rw-r--r--arch/x86/kernel/dumpstack_64.c118
-rw-r--r--arch/x86/kernel/early-quirks.c228
-rw-r--r--arch/x86/kernel/ftrace.c55
-rw-r--r--arch/x86/kernel/head_32.S7
-rw-r--r--arch/x86/kernel/head_64.S6
-rw-r--r--arch/x86/kernel/hpet.c10
-rw-r--r--arch/x86/kernel/i387.c15
-rw-r--r--arch/x86/kernel/irq.c6
-rw-r--r--arch/x86/kernel/irq_32.c83
-rw-r--r--arch/x86/kernel/kprobes/core.c16
-rw-r--r--arch/x86/kernel/kvm.c1
-rw-r--r--arch/x86/kernel/kvmclock.c2
-rw-r--r--arch/x86/kernel/ldt.c11
-rw-r--r--arch/x86/kernel/machine_kexec_64.c2
-rw-r--r--arch/x86/kernel/module.c46
-rw-r--r--arch/x86/kernel/msr.c16
-rw-r--r--arch/x86/kernel/nmi.c37
-rw-r--r--arch/x86/kernel/pci-calgary_64.c31
-rw-r--r--arch/x86/kernel/process.c5
-rw-r--r--arch/x86/kernel/process_32.c4
-rw-r--r--arch/x86/kernel/ptrace.c8
-rw-r--r--arch/x86/kernel/quirks.c2
-rw-r--r--arch/x86/kernel/reboot.c69
-rw-r--r--arch/x86/kernel/setup.c17
-rw-r--r--arch/x86/kernel/smpboot.c20
-rw-r--r--arch/x86/kernel/time.c4
-rw-r--r--arch/x86/kernel/tsc.c5
-rw-r--r--arch/x86/kernel/vmlinux.lds.S8
-rw-r--r--arch/x86/kernel/vsyscall_64.c51
-rw-r--r--arch/x86/kernel/vsyscall_gtod.c69
69 files changed, 1477 insertions, 2764 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cb648c84b327..f4d96000d33a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,7 +26,7 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-y += probe_roms.o
obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
-obj-y += syscall_$(BITS).o
+obj-y += syscall_$(BITS).o vsyscall_gtod.o
obj-$(CONFIG_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1dac94265b59..86281ffb96d6 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -53,10 +53,6 @@ EXPORT_SYMBOL(acpi_disabled);
# include <asm/proto.h>
#endif /* X86 */
-#define BAD_MADT_ENTRY(entry, end) ( \
- (!entry) || (unsigned long)entry + sizeof(*entry) > end || \
- ((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
-
#define PREFIX "ACPI: "
int acpi_noirq; /* skip ACPI IRQ initialization */
@@ -613,10 +609,10 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
int nid;
nid = acpi_get_node(handle);
- if (nid == -1 || !node_online(nid))
- return;
- set_apicid_to_node(physid, nid);
- numa_set_node(cpu, nid);
+ if (nid != -1) {
+ set_apicid_to_node(physid, nid);
+ numa_set_node(cpu, nid);
+ }
#endif
}
@@ -907,10 +903,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
-#ifdef CONFIG_X86_ES7000
-extern int es7000_plat;
-#endif
-
void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
{
int ioapic;
@@ -960,14 +952,6 @@ void __init mp_config_acpi_legacy_irqs(void)
set_bit(MP_ISA_BUS, mp_bus_not_pci);
pr_debug("Bus #%d is ISA\n", MP_ISA_BUS);
-#ifdef CONFIG_X86_ES7000
- /*
- * Older generations of ES7000 have no legacy identity mappings
- */
- if (es7000_plat == 1)
- return;
-#endif
-
/*
* Use the default configuration for the IRQs 0-15. Unless
* overridden by (MADT) interrupt source override entries.
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index e69182fd01cf..4b28159e0421 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -87,7 +87,9 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
retval = 0;
- if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
+ /* If the HW does not support any sub-states in this C-state */
+ if (num_cstate_subtype == 0) {
+ pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
retval = -1;
goto out;
}
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index dec8de4e1663..f04dbb3069b8 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -22,6 +22,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{}
};
EXPORT_SYMBOL(amd_nb_misc_ids);
@@ -30,6 +31,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
{}
};
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3e4cbb..9fa8aa051f54 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
#include <linux/pci_ids.h>
#include <linux/pci.h>
#include <linux/bitops.h>
-#include <linux/ioport.h>
#include <linux/suspend.h>
#include <asm/e820.h>
#include <asm/io.h>
@@ -54,18 +53,6 @@ int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
-static struct resource gart_resource = {
- .name = "GART",
- .flags = IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
- gart_resource.start = aper_base;
- gart_resource.end = aper_base + aper_size - 1;
- insert_resource(&iomem_resource, &gart_resource);
-}
-
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
@@ -96,7 +83,6 @@ static u32 __init allocate_aperture(void)
memblock_reserve(addr, aper_size);
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
- insert_aperture_resource((u32)addr, aper_size);
register_nosave_region(addr >> PAGE_SHIFT,
(addr+aper_size) >> PAGE_SHIFT);
@@ -444,12 +430,8 @@ int __init gart_iommu_hole_init(void)
out:
if (!fix && !fallback_aper_force) {
- if (last_aper_base) {
- unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
- insert_aperture_resource((u32)last_aper_base, n);
+ if (last_aper_base)
return 1;
- }
return 0;
}
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 0ae0323b1f9c..dcb5b15401ce 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -18,10 +18,7 @@ obj-y += apic_flat_64.o
endif
# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
-obj-$(CONFIG_X86_SUMMIT) += summit_32.o
obj-$(CONFIG_X86_BIGSMP) += bigsmp_32.o
-obj-$(CONFIG_X86_ES7000) += es7000_32.o
# For 32bit, probe_32 need to be listed last
obj-$(CONFIG_X86_LOCAL_APIC) += probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a70a9e..ad28db7e6bde 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -133,6 +133,10 @@ static inline void imcr_apic_to_pic(void)
* +1=force-enable
*/
static int force_enable_local_apic __initdata;
+
+/* Control whether x2APIC mode is enabled or not */
+static bool nox2apic __initdata;
+
/*
* APIC command line parameters
*/
@@ -162,8 +166,7 @@ int x2apic_mode;
/* x2apic enabled before OS handover */
int x2apic_preenabled;
static int x2apic_disabled;
-static int nox2apic;
-static __init int setup_nox2apic(char *str)
+static int __init setup_nox2apic(char *str)
{
if (x2apic_enabled()) {
int apicid = native_apic_msr_read(APIC_ID);
@@ -178,7 +181,7 @@ static __init int setup_nox2apic(char *str)
} else
setup_clear_cpu_cap(X86_FEATURE_X2APIC);
- nox2apic = 1;
+ nox2apic = true;
return 0;
}
@@ -283,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void)
void native_apic_icr_write(u32 low, u32 id)
{
+ unsigned long flags;
+
+ local_irq_save(flags);
apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
apic_write(APIC_ICR, low);
+ local_irq_restore(flags);
}
u64 native_apic_icr_read(void)
@@ -1989,7 +1996,8 @@ static inline void __smp_error_interrupt(struct pt_regs *regs)
};
/* First tickle the hardware, only then report what went on. -- REW */
- apic_write(APIC_ESR, 0);
+ if (lapic_get_maxlvt() > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
v = apic_read(APIC_ESR);
ack_APIC_irq();
atomic_inc(&irq_err_count);
@@ -2129,7 +2137,6 @@ int generic_processor_info(int apicid, int version)
*
* - arch/x86/kernel/mpparse.c: MP_processor_info()
* - arch/x86/mm/amdtopology.c: amd_numa_init()
- * - arch/x86/platform/visws/visws_quirks.c: MP_processor_info()
*
* This function is executed with the modified
* boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 2c621a6b901a..7c1b29479513 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -198,7 +198,7 @@ static struct apic apic_flat = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = default_inquire_remote_apic,
@@ -314,7 +314,7 @@ static struct apic apic_physflat = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 191ce75c0e54..8c7c98249c20 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -172,8 +172,7 @@ struct apic apic_noop = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
-
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 3e67f9e3d7ef..a5b45df8bc88 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -248,7 +248,7 @@ static const struct apic apic_numachip __refconst = {
.wakeup_secondary_cpu = numachip_wakeup_secondary,
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL, /* REMRD not supported */
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d50e3640d5ae..e4840aa7a255 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -199,8 +199,7 @@ static struct apic apic_bigsmp = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = default_wait_for_init_deassert,
-
+ .wait_for_init_deassert = true,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
deleted file mode 100644
index c55224731b2d..000000000000
--- a/arch/x86/kernel/apic/es7000_32.c
+++ /dev/null
@@ -1,746 +0,0 @@
-/*
- * Written by: Garry Forsgren, Unisys Corporation
- * Natalie Protasevich, Unisys Corporation
- *
- * This file contains the code to configure and interface
- * with Unisys ES7000 series hardware system manager.
- *
- * Copyright (c) 2003 Unisys Corporation.
- * Copyright (C) 2009, Red Hat, Inc., Ingo Molnar
- *
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * Contact information: Unisys Corporation, Township Line & Union Meeting
- * Roads-A, Unisys Way, Blue Bell, Pennsylvania, 19424, or:
- *
- * http://www.unisys.com
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/notifier.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
-#include <linux/threads.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/reboot.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/acpi.h>
-#include <linux/init.h>
-#include <linux/gfp.h>
-#include <linux/nmi.h>
-#include <linux/smp.h>
-#include <linux/io.h>
-
-#include <asm/apicdef.h>
-#include <linux/atomic.h>
-#include <asm/fixmap.h>
-#include <asm/mpspec.h>
-#include <asm/setup.h>
-#include <asm/apic.h>
-#include <asm/ipi.h>
-
-/*
- * ES7000 chipsets
- */
-
-#define NON_UNISYS 0
-#define ES7000_CLASSIC 1
-#define ES7000_ZORRO 2
-
-#define MIP_REG 1
-#define MIP_PSAI_REG 4
-
-#define MIP_BUSY 1
-#define MIP_SPIN 0xf0000
-#define MIP_VALID 0x0100000000000000ULL
-#define MIP_SW_APIC 0x1020b
-
-#define MIP_PORT(val) ((val >> 32) & 0xffff)
-
-#define MIP_RD_LO(val) (val & 0xffffffff)
-
-struct mip_reg {
- unsigned long long off_0x00;
- unsigned long long off_0x08;
- unsigned long long off_0x10;
- unsigned long long off_0x18;
- unsigned long long off_0x20;
- unsigned long long off_0x28;
- unsigned long long off_0x30;
- unsigned long long off_0x38;
-};
-
-struct mip_reg_info {
- unsigned long long mip_info;
- unsigned long long delivery_info;
- unsigned long long host_reg;
- unsigned long long mip_reg;
-};
-
-struct psai {
- unsigned long long entry_type;
- unsigned long long addr;
- unsigned long long bep_addr;
-};
-
-#ifdef CONFIG_ACPI
-
-struct es7000_oem_table {
- struct acpi_table_header Header;
- u32 OEMTableAddr;
- u32 OEMTableSize;
-};
-
-static unsigned long oem_addrX;
-static unsigned long oem_size;
-
-#endif
-
-/*
- * ES7000 Globals
- */
-
-static volatile unsigned long *psai;
-static struct mip_reg *mip_reg;
-static struct mip_reg *host_reg;
-static int mip_port;
-static unsigned long mip_addr;
-static unsigned long host_addr;
-
-int es7000_plat;
-
-/*
- * GSI override for ES7000 platforms.
- */
-
-
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
-{
- unsigned long vect = 0, psaival = 0;
-
- if (psai == NULL)
- return -1;
-
- vect = ((unsigned long)__pa(eip)/0x1000) << 16;
- psaival = (0x1000000 | vect | cpu);
-
- while (*psai & 0x1000000)
- ;
-
- *psai = psaival;
-
- return 0;
-}
-
-static int es7000_apic_is_cluster(void)
-{
- /* MPENTIUMIII */
- if (boot_cpu_data.x86 == 6 &&
- (boot_cpu_data.x86_model >= 7 && boot_cpu_data.x86_model <= 11))
- return 1;
-
- return 0;
-}
-
-static void setup_unisys(void)
-{
- /*
- * Determine the generation of the ES7000 currently running.
- *
- * es7000_plat = 1 if the machine is a 5xx ES7000 box
- * es7000_plat = 2 if the machine is a x86_64 ES7000 box
- *
- */
- if (!(boot_cpu_data.x86 <= 15 && boot_cpu_data.x86_model <= 2))
- es7000_plat = ES7000_ZORRO;
- else
- es7000_plat = ES7000_CLASSIC;
-}
-
-/*
- * Parse the OEM Table:
- */
-static int parse_unisys_oem(char *oemptr)
-{
- int i;
- int success = 0;
- unsigned char type, size;
- unsigned long val;
- char *tp = NULL;
- struct psai *psaip = NULL;
- struct mip_reg_info *mi;
- struct mip_reg *host, *mip;
-
- tp = oemptr;
-
- tp += 8;
-
- for (i = 0; i <= 6; i++) {
- type = *tp++;
- size = *tp++;
- tp -= 2;
- switch (type) {
- case MIP_REG:
- mi = (struct mip_reg_info *)tp;
- val = MIP_RD_LO(mi->host_reg);
- host_addr = val;
- host = (struct mip_reg *)val;
- host_reg = __va(host);
- val = MIP_RD_LO(mi->mip_reg);
- mip_port = MIP_PORT(mi->mip_info);
- mip_addr = val;
- mip = (struct mip_reg *)val;
- mip_reg = __va(mip);
- pr_debug("host_reg = 0x%lx\n",
- (unsigned long)host_reg);
- pr_debug("mip_reg = 0x%lx\n",
- (unsigned long)mip_reg);
- success++;
- break;
- case MIP_PSAI_REG:
- psaip = (struct psai *)tp;
- if (tp != NULL) {
- if (psaip->addr)
- psai = __va(psaip->addr);
- else
- psai = NULL;
- success++;
- }
- break;
- default:
- break;
- }
- tp += size;
- }
-
- if (success < 2)
- es7000_plat = NON_UNISYS;
- else
- setup_unisys();
-
- return es7000_plat;
-}
-
-#ifdef CONFIG_ACPI
-static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
-{
- struct acpi_table_header *header = NULL;
- struct es7000_oem_table *table;
- acpi_size tbl_size;
- acpi_status ret;
- int i = 0;
-
- for (;;) {
- ret = acpi_get_table_with_size("OEM1", i++, &header, &tbl_size);
- if (!ACPI_SUCCESS(ret))
- return -1;
-
- if (!memcmp((char *) &header->oem_id, "UNISYS", 6))
- break;
-
- early_acpi_os_unmap_memory(header, tbl_size);
- }
-
- table = (void *)header;
-
- oem_addrX = table->OEMTableAddr;
- oem_size = table->OEMTableSize;
-
- early_acpi_os_unmap_memory(header, tbl_size);
-
- *oem_addr = (unsigned long)__acpi_map_table(oem_addrX, oem_size);
-
- return 0;
-}
-
-static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
-{
- if (!oem_addr)
- return;
-
- __acpi_unmap_table((char *)oem_addr, oem_size);
-}
-
-static int es7000_check_dsdt(void)
-{
- struct acpi_table_header header;
-
- if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
- !strncmp(header.oem_id, "UNISYS", 6))
- return 1;
- return 0;
-}
-
-static int es7000_acpi_ret;
-
-/* Hook from generic ACPI tables.c */
-static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
- unsigned long oem_addr = 0;
- int check_dsdt;
- int ret = 0;
-
- /* check dsdt at first to avoid clear fix_map for oem_addr */
- check_dsdt = es7000_check_dsdt();
-
- if (!find_unisys_acpi_oem_table(&oem_addr)) {
- if (check_dsdt) {
- ret = parse_unisys_oem((char *)oem_addr);
- } else {
- setup_unisys();
- ret = 1;
- }
- /*
- * we need to unmap it
- */
- unmap_unisys_acpi_oem_table(oem_addr);
- }
-
- es7000_acpi_ret = ret;
-
- return ret && !es7000_apic_is_cluster();
-}
-
-static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id)
-{
- int ret = es7000_acpi_ret;
-
- return ret && es7000_apic_is_cluster();
-}
-
-#else /* !CONFIG_ACPI: */
-static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
- return 0;
-}
-
-static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id)
-{
- return 0;
-}
-#endif /* !CONFIG_ACPI */
-
-static void es7000_spin(int n)
-{
- int i = 0;
-
- while (i++ < n)
- rep_nop();
-}
-
-static int es7000_mip_write(struct mip_reg *mip_reg)
-{
- int status = 0;
- int spin;
-
- spin = MIP_SPIN;
- while ((host_reg->off_0x38 & MIP_VALID) != 0) {
- if (--spin <= 0) {
- WARN(1, "Timeout waiting for Host Valid Flag\n");
- return -1;
- }
- es7000_spin(MIP_SPIN);
- }
-
- memcpy(host_reg, mip_reg, sizeof(struct mip_reg));
- outb(1, mip_port);
-
- spin = MIP_SPIN;
-
- while ((mip_reg->off_0x38 & MIP_VALID) == 0) {
- if (--spin <= 0) {
- WARN(1, "Timeout waiting for MIP Valid Flag\n");
- return -1;
- }
- es7000_spin(MIP_SPIN);
- }
-
- status = (mip_reg->off_0x00 & 0xffff0000000000ULL) >> 48;
- mip_reg->off_0x38 &= ~MIP_VALID;
-
- return status;
-}
-
-static void es7000_enable_apic_mode(void)
-{
- struct mip_reg es7000_mip_reg;
- int mip_status;
-
- if (!es7000_plat)
- return;
-
- pr_info("Enabling APIC mode.\n");
- memset(&es7000_mip_reg, 0, sizeof(struct mip_reg));
- es7000_mip_reg.off_0x00 = MIP_SW_APIC;
- es7000_mip_reg.off_0x38 = MIP_VALID;
-
- while ((mip_status = es7000_mip_write(&es7000_mip_reg)) != 0)
- WARN(1, "Command failed, status = %x\n", mip_status);
-}
-
-static void es7000_wait_for_init_deassert(atomic_t *deassert)
-{
- while (!atomic_read(deassert))
- cpu_relax();
-}
-
-static unsigned int es7000_get_apic_id(unsigned long x)
-{
- return (x >> 24) & 0xFF;
-}
-
-static void es7000_send_IPI_mask(const struct cpumask *mask, int vector)
-{
- default_send_IPI_mask_sequence_phys(mask, vector);
-}
-
-static void es7000_send_IPI_allbutself(int vector)
-{
- default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void es7000_send_IPI_all(int vector)
-{
- es7000_send_IPI_mask(cpu_online_mask, vector);
-}
-
-static int es7000_apic_id_registered(void)
-{
- return 1;
-}
-
-static const struct cpumask *target_cpus_cluster(void)
-{
- return cpu_all_mask;
-}
-
-static const struct cpumask *es7000_target_cpus(void)
-{
- return cpumask_of(smp_processor_id());
-}
-
-static unsigned long es7000_check_apicid_used(physid_mask_t *map, int apicid)
-{
- return 0;
-}
-
-static unsigned long es7000_check_apicid_present(int bit)
-{
- return physid_isset(bit, phys_cpu_present_map);
-}
-
-static int es7000_early_logical_apicid(int cpu)
-{
- /* on es7000, logical apicid is the same as physical */
- return early_per_cpu(x86_bios_cpu_apicid, cpu);
-}
-
-static unsigned long calculate_ldr(int cpu)
-{
- unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu);
-
- return SET_APIC_LOGICAL_ID(id);
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LdR and TPR before enabling
- * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116). So here it goes...
- */
-static void es7000_init_apic_ldr_cluster(void)
-{
- unsigned long val;
- int cpu = smp_processor_id();
-
- apic_write(APIC_DFR, APIC_DFR_CLUSTER);
- val = calculate_ldr(cpu);
- apic_write(APIC_LDR, val);
-}
-
-static void es7000_init_apic_ldr(void)
-{
- unsigned long val;
- int cpu = smp_processor_id();
-
- apic_write(APIC_DFR, APIC_DFR_FLAT);
- val = calculate_ldr(cpu);
- apic_write(APIC_LDR, val);
-}
-
-static void es7000_setup_apic_routing(void)
-{
- int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
-
- pr_info("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n",
- (apic_version[apic] == 0x14) ?
- "Physical Cluster" : "Logical Cluster",
- nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
-}
-
-static int es7000_cpu_present_to_apicid(int mps_cpu)
-{
- if (!mps_cpu)
- return boot_cpu_physical_apicid;
- else if (mps_cpu < nr_cpu_ids)
- return per_cpu(x86_bios_cpu_apicid, mps_cpu);
- else
- return BAD_APICID;
-}
-
-static int cpu_id;
-
-static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap)
-{
- physid_set_mask_of_physid(cpu_id, retmap);
- ++cpu_id;
-}
-
-static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
-{
- /* For clustered we don't have a good way to do this yet - hack */
- physids_promote(0xFFL, retmap);
-}
-
-static int es7000_check_phys_apicid_present(int cpu_physical_apicid)
-{
- boot_cpu_physical_apicid = read_apic_id();
- return 1;
-}
-
-static inline int
-es7000_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id)
-{
- unsigned int round = 0;
- unsigned int cpu, uninitialized_var(apicid);
-
- /*
- * The cpus in the mask must all be on the apic cluster.
- */
- for_each_cpu_and(cpu, cpumask, cpu_online_mask) {
- int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-
- if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
- WARN(1, "Not a valid mask!");
-
- return -EINVAL;
- }
- apicid |= new_apicid;
- round++;
- }
- if (!round)
- return -EINVAL;
- *dest_id = apicid;
- return 0;
-}
-
-static int
-es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
- const struct cpumask *andmask,
- unsigned int *apicid)
-{
- cpumask_var_t cpumask;
- *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
-
- if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
- return 0;
-
- cpumask_and(cpumask, inmask, andmask);
- es7000_cpu_mask_to_apicid(cpumask, apicid);
-
- free_cpumask_var(cpumask);
-
- return 0;
-}
-
-static int es7000_phys_pkg_id(int cpuid_apic, int index_msb)
-{
- return cpuid_apic >> index_msb;
-}
-
-static int probe_es7000(void)
-{
- /* probed later in mptable/ACPI hooks */
- return 0;
-}
-
-static int es7000_mps_ret;
-static int es7000_mps_oem_check(struct mpc_table *mpc, char *oem,
- char *productid)
-{
- int ret = 0;
-
- if (mpc->oemptr) {
- struct mpc_oemtable *oem_table =
- (struct mpc_oemtable *)mpc->oemptr;
-
- if (!strncmp(oem, "UNISYS", 6))
- ret = parse_unisys_oem((char *)oem_table);
- }
-
- es7000_mps_ret = ret;
-
- return ret && !es7000_apic_is_cluster();
-}
-
-static int es7000_mps_oem_check_cluster(struct mpc_table *mpc, char *oem,
- char *productid)
-{
- int ret = es7000_mps_ret;
-
- return ret && es7000_apic_is_cluster();
-}
-
-/* We've been warned by a false positive warning.Use __refdata to keep calm. */
-static struct apic __refdata apic_es7000_cluster = {
-
- .name = "es7000",
- .probe = probe_es7000,
- .acpi_madt_oem_check = es7000_acpi_madt_oem_check_cluster,
- .apic_id_valid = default_apic_id_valid,
- .apic_id_registered = es7000_apic_id_registered,
-
- .irq_delivery_mode = dest_LowestPrio,
- /* logical delivery broadcast to all procs: */
- .irq_dest_mode = 1,
-
- .target_cpus = target_cpus_cluster,
- .disable_esr = 1,
- .dest_logical = 0,
- .check_apicid_used = es7000_check_apicid_used,
- .check_apicid_present = es7000_check_apicid_present,
-
- .vector_allocation_domain = flat_vector_allocation_domain,
- .init_apic_ldr = es7000_init_apic_ldr_cluster,
-
- .ioapic_phys_id_map = es7000_ioapic_phys_id_map,
- .setup_apic_routing = es7000_setup_apic_routing,
- .multi_timer_check = NULL,
- .cpu_present_to_apicid = es7000_cpu_present_to_apicid,
- .apicid_to_cpu_present = es7000_apicid_to_cpu_present,
- .setup_portio_remap = NULL,
- .check_phys_apicid_present = es7000_check_phys_apicid_present,
- .enable_apic_mode = es7000_enable_apic_mode,
- .phys_pkg_id = es7000_phys_pkg_id,
- .mps_oem_check = es7000_mps_oem_check_cluster,
-
- .get_apic_id = es7000_get_apic_id,
- .set_apic_id = NULL,
- .apic_id_mask = 0xFF << 24,
-
- .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and,
-
- .send_IPI_mask = es7000_send_IPI_mask,
- .send_IPI_mask_allbutself = NULL,
- .send_IPI_allbutself = es7000_send_IPI_allbutself,
- .send_IPI_all = es7000_send_IPI_all,
- .send_IPI_self = default_send_IPI_self,
-
- .wakeup_secondary_cpu = wakeup_secondary_cpu_via_mip,
-
- .trampoline_phys_low = 0x467,
- .trampoline_phys_high = 0x469,
-
- .wait_for_init_deassert = NULL,
-
- /* Nothing to do for most platforms, since cleared by the INIT cycle: */
- .smp_callin_clear_local_apic = NULL,
- .inquire_remote_apic = default_inquire_remote_apic,
-
- .read = native_apic_mem_read,
- .write = native_apic_mem_write,
- .eoi_write = native_apic_mem_write,
- .icr_read = native_apic_icr_read,
- .icr_write = native_apic_icr_write,
- .wait_icr_idle = native_apic_wait_icr_idle,
- .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
-
- .x86_32_early_logical_apicid = es7000_early_logical_apicid,
-};
-
-static struct apic __refdata apic_es7000 = {
-
- .name = "es7000",
- .probe = probe_es7000,
- .acpi_madt_oem_check = es7000_acpi_madt_oem_check,
- .apic_id_valid = default_apic_id_valid,
- .apic_id_registered = es7000_apic_id_registered,
-
- .irq_delivery_mode = dest_Fixed,
- /* phys delivery to target CPUs: */
- .irq_dest_mode = 0,
-
- .target_cpus = es7000_target_cpus,
- .disable_esr = 1,
- .dest_logical = 0,
- .check_apicid_used = es7000_check_apicid_used,
- .check_apicid_present = es7000_check_apicid_present,
-
- .vector_allocation_domain = flat_vector_allocation_domain,
- .init_apic_ldr = es7000_init_apic_ldr,
-
- .ioapic_phys_id_map = es7000_ioapic_phys_id_map,
- .setup_apic_routing = es7000_setup_apic_routing,
- .multi_timer_check = NULL,
- .cpu_present_to_apicid = es7000_cpu_present_to_apicid,
- .apicid_to_cpu_present = es7000_apicid_to_cpu_present,
- .setup_portio_remap = NULL,
- .check_phys_apicid_present = es7000_check_phys_apicid_present,
- .enable_apic_mode = es7000_enable_apic_mode,
- .phys_pkg_id = es7000_phys_pkg_id,
- .mps_oem_check = es7000_mps_oem_check,
-
- .get_apic_id = es7000_get_apic_id,
- .set_apic_id = NULL,
- .apic_id_mask = 0xFF << 24,
-
- .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and,
-
- .send_IPI_mask = es7000_send_IPI_mask,
- .send_IPI_mask_allbutself = NULL,
- .send_IPI_allbutself = es7000_send_IPI_allbutself,
- .send_IPI_all = es7000_send_IPI_all,
- .send_IPI_self = default_send_IPI_self,
-
- .trampoline_phys_low = 0x467,
- .trampoline_phys_high = 0x469,
-
- .wait_for_init_deassert = es7000_wait_for_init_deassert,
-
- /* Nothing to do for most platforms, since cleared by the INIT cycle: */
- .smp_callin_clear_local_apic = NULL,
- .inquire_remote_apic = default_inquire_remote_apic,
-
- .read = native_apic_mem_read,
- .write = native_apic_mem_write,
- .eoi_write = native_apic_mem_write,
- .icr_read = native_apic_icr_read,
- .icr_write = native_apic_icr_write,
- .wait_icr_idle = native_apic_wait_icr_idle,
- .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
-
- .x86_32_early_logical_apicid = es7000_early_logical_apicid,
-};
-
-/*
- * Need to check for es7000 followed by es7000_cluster, so this order
- * in apic_drivers is important.
- */
-apic_drivers(apic_es7000, apic_es7000_cluster);
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
deleted file mode 100644
index 1e42e8f305ee..000000000000
--- a/arch/x86/kernel/apic/numaq_32.c
+++ /dev/null
@@ -1,525 +0,0 @@
-/*
- * Written by: Patricia Gaughen, IBM Corporation
- *
- * Copyright (C) 2002, IBM Corp.
- * Copyright (C) 2009, Red Hat, Inc., Ingo Molnar
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <gone@us.ibm.com>
- */
-#include <linux/nodemask.h>
-#include <linux/topology.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/kernel.h>
-#include <linux/mmzone.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/numa.h>
-#include <linux/smp.h>
-#include <linux/io.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/fixmap.h>
-#include <asm/mpspec.h>
-#include <asm/numaq.h>
-#include <asm/setup.h>
-#include <asm/apic.h>
-#include <asm/e820.h>
-#include <asm/ipi.h>
-
-int found_numaq;
-
-/*
- * Have to match translation table entries to main table entries by counter
- * hence the mpc_record variable .... can't see a less disgusting way of
- * doing this ....
- */
-struct mpc_trans {
- unsigned char mpc_type;
- unsigned char trans_len;
- unsigned char trans_type;
- unsigned char trans_quad;
- unsigned char trans_global;
- unsigned char trans_local;
- unsigned short trans_reserved;
-};
-
-static int mpc_record;
-
-static struct mpc_trans *translation_table[MAX_MPC_ENTRY];
-
-int mp_bus_id_to_node[MAX_MP_BUSSES];
-int mp_bus_id_to_local[MAX_MP_BUSSES];
-int quad_local_to_mp_bus_id[NR_CPUS/4][4];
-
-
-static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
-{
- struct eachquadmem *eq = scd->eq + node;
- u64 start = (u64)(eq->hi_shrd_mem_start - eq->priv_mem_size) << 20;
- u64 end = (u64)(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size) << 20;
- int ret;
-
- node_set(node, numa_nodes_parsed);
- ret = numa_add_memblk(node, start, end);
- BUG_ON(ret < 0);
-}
-
-/*
- * Function: smp_dump_qct()
- *
- * Description: gets memory layout from the quad config table. This
- * function also updates numa_nodes_parsed with the nodes (quads) present.
- */
-static void __init smp_dump_qct(void)
-{
- struct sys_cfg_data *scd;
- int node;
-
- scd = (void *)__va(SYS_CFG_DATA_PRIV_ADDR);
-
- for_each_node(node) {
- if (scd->quads_present31_0 & (1 << node))
- numaq_register_node(node, scd);
- }
-}
-
-void numaq_tsc_disable(void)
-{
- if (!found_numaq)
- return;
-
- if (num_online_nodes() > 1) {
- printk(KERN_DEBUG "NUMAQ: disabling TSC\n");
- setup_clear_cpu_cap(X86_FEATURE_TSC);
- }
-}
-
-static void __init numaq_tsc_init(void)
-{
- numaq_tsc_disable();
-}
-
-static inline int generate_logical_apicid(int quad, int phys_apicid)
-{
- return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
-}
-
-/* x86_quirks member */
-static int mpc_apic_id(struct mpc_cpu *m)
-{
- int quad = translation_table[mpc_record]->trans_quad;
- int logical_apicid = generate_logical_apicid(quad, m->apicid);
-
- printk(KERN_DEBUG
- "Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
- m->apicid, (m->cpufeature & CPU_FAMILY_MASK) >> 8,
- (m->cpufeature & CPU_MODEL_MASK) >> 4,
- m->apicver, quad, logical_apicid);
-
- return logical_apicid;
-}
-
-/* x86_quirks member */
-static void mpc_oem_bus_info(struct mpc_bus *m, char *name)
-{
- int quad = translation_table[mpc_record]->trans_quad;
- int local = translation_table[mpc_record]->trans_local;
-
- mp_bus_id_to_node[m->busid] = quad;
- mp_bus_id_to_local[m->busid] = local;
-
- printk(KERN_INFO "Bus #%d is %s (node %d)\n", m->busid, name, quad);
-}
-
-/* x86_quirks member */
-static void mpc_oem_pci_bus(struct mpc_bus *m)
-{
- int quad = translation_table[mpc_record]->trans_quad;
- int local = translation_table[mpc_record]->trans_local;
-
- quad_local_to_mp_bus_id[quad][local] = m->busid;
-}
-
-/*
- * Called from mpparse code.
- * mode = 0: prescan
- * mode = 1: one mpc entry scanned
- */
-static void numaq_mpc_record(unsigned int mode)
-{
- if (!mode)
- mpc_record = 0;
- else
- mpc_record++;
-}
-
-static void __init MP_translation_info(struct mpc_trans *m)
-{
- printk(KERN_INFO
- "Translation: record %d, type %d, quad %d, global %d, local %d\n",
- mpc_record, m->trans_type, m->trans_quad, m->trans_global,
- m->trans_local);
-
- if (mpc_record >= MAX_MPC_ENTRY)
- printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n");
- else
- translation_table[mpc_record] = m; /* stash this for later */
-
- if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad))
- node_set_online(m->trans_quad);
-}
-
-static int __init mpf_checksum(unsigned char *mp, int len)
-{
- int sum = 0;
-
- while (len--)
- sum += *mp++;
-
- return sum & 0xFF;
-}
-
-/*
- * Read/parse the MPC oem tables
- */
-static void __init smp_read_mpc_oem(struct mpc_table *mpc)
-{
- struct mpc_oemtable *oemtable = (void *)(long)mpc->oemptr;
- int count = sizeof(*oemtable); /* the header size */
- unsigned char *oemptr = ((unsigned char *)oemtable) + count;
-
- mpc_record = 0;
- printk(KERN_INFO
- "Found an OEM MPC table at %8p - parsing it...\n", oemtable);
-
- if (memcmp(oemtable->signature, MPC_OEM_SIGNATURE, 4)) {
- printk(KERN_WARNING
- "SMP mpc oemtable: bad signature [%c%c%c%c]!\n",
- oemtable->signature[0], oemtable->signature[1],
- oemtable->signature[2], oemtable->signature[3]);
- return;
- }
-
- if (mpf_checksum((unsigned char *)oemtable, oemtable->length)) {
- printk(KERN_WARNING "SMP oem mptable: checksum error!\n");
- return;
- }
-
- while (count < oemtable->length) {
- switch (*oemptr) {
- case MP_TRANSLATION:
- {
- struct mpc_trans *m = (void *)oemptr;
-
- MP_translation_info(m);
- oemptr += sizeof(*m);
- count += sizeof(*m);
- ++mpc_record;
- break;
- }
- default:
- printk(KERN_WARNING
- "Unrecognised OEM table entry type! - %d\n",
- (int)*oemptr);
- return;
- }
- }
-}
-
-static __init void early_check_numaq(void)
-{
- /*
- * get boot-time SMP configuration:
- */
- if (smp_found_config)
- early_get_smp_config();
-
- if (found_numaq) {
- x86_init.mpparse.mpc_record = numaq_mpc_record;
- x86_init.mpparse.setup_ioapic_ids = x86_init_noop;
- x86_init.mpparse.mpc_apic_id = mpc_apic_id;
- x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem;
- x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus;
- x86_init.mpparse.mpc_oem_bus_info = mpc_oem_bus_info;
- x86_init.timers.tsc_pre_init = numaq_tsc_init;
- x86_init.pci.init = pci_numaq_init;
- }
-}
-
-int __init numaq_numa_init(void)
-{
- early_check_numaq();
- if (!found_numaq)
- return -ENOENT;
- smp_dump_qct();
-
- return 0;
-}
-
-#define NUMAQ_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
-
-static inline unsigned int numaq_get_apic_id(unsigned long x)
-{
- return (x >> 24) & 0x0F;
-}
-
-static inline void numaq_send_IPI_mask(const struct cpumask *mask, int vector)
-{
- default_send_IPI_mask_sequence_logical(mask, vector);
-}
-
-static inline void numaq_send_IPI_allbutself(int vector)
-{
- default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
-}
-
-static inline void numaq_send_IPI_all(int vector)
-{
- numaq_send_IPI_mask(cpu_online_mask, vector);
-}
-
-#define NUMAQ_TRAMPOLINE_PHYS_LOW (0x8)
-#define NUMAQ_TRAMPOLINE_PHYS_HIGH (0xa)
-
-/*
- * Because we use NMIs rather than the INIT-STARTUP sequence to
- * bootstrap the CPUs, the APIC may be in a weird state. Kick it:
- */
-static inline void numaq_smp_callin_clear_local_apic(void)
-{
- clear_local_APIC();
-}
-
-static inline const struct cpumask *numaq_target_cpus(void)
-{
- return cpu_all_mask;
-}
-
-static unsigned long numaq_check_apicid_used(physid_mask_t *map, int apicid)
-{
- return physid_isset(apicid, *map);
-}
-
-static inline unsigned long numaq_check_apicid_present(int bit)
-{
- return physid_isset(bit, phys_cpu_present_map);
-}
-
-static inline int numaq_apic_id_registered(void)
-{
- return 1;
-}
-
-static inline void numaq_init_apic_ldr(void)
-{
- /* Already done in NUMA-Q firmware */
-}
-
-static inline void numaq_setup_apic_routing(void)
-{
- printk(KERN_INFO
- "Enabling APIC mode: NUMA-Q. Using %d I/O APICs\n",
- nr_ioapics);
-}
-
-/*
- * Skip adding the timer int on secondary nodes, which causes
- * a small but painful rift in the time-space continuum.
- */
-static inline int numaq_multi_timer_check(int apic, int irq)
-{
- return apic != 0 && irq == 0;
-}
-
-static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
-{
- /* We don't have a good way to do this yet - hack */
- return physids_promote(0xFUL, retmap);
-}
-
-/*
- * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
- * cpu to APIC ID relation to properly interact with the intelligent
- * mode of the cluster controller.
- */
-static inline int numaq_cpu_present_to_apicid(int mps_cpu)
-{
- if (mps_cpu < 60)
- return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
- else
- return BAD_APICID;
-}
-
-static inline int numaq_apicid_to_node(int logical_apicid)
-{
- return logical_apicid >> 4;
-}
-
-static int numaq_numa_cpu_node(int cpu)
-{
- int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-
- if (logical_apicid != BAD_APICID)
- return numaq_apicid_to_node(logical_apicid);
- return NUMA_NO_NODE;
-}
-
-static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap)
-{
- int node = numaq_apicid_to_node(logical_apicid);
- int cpu = __ffs(logical_apicid & 0xf);
-
- physid_set_mask_of_physid(cpu + 4*node, retmap);
-}
-
-/* Where the IO area was mapped on multiquad, always 0 otherwise */
-void *xquad_portio;
-
-static inline int numaq_check_phys_apicid_present(int phys_apicid)
-{
- return 1;
-}
-
-/*
- * We use physical apicids here, not logical, so just return the default
- * physical broadcast to stop people from breaking us
- */
-static int
-numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask,
- unsigned int *apicid)
-{
- *apicid = 0x0F;
- return 0;
-}
-
-/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
-static inline int numaq_phys_pkg_id(int cpuid_apic, int index_msb)
-{
- return cpuid_apic >> index_msb;
-}
-
-static int
-numaq_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid)
-{
- if (strncmp(oem, "IBM NUMA", 8))
- printk(KERN_ERR "Warning! Not a NUMA-Q system!\n");
- else
- found_numaq = 1;
-
- return found_numaq;
-}
-
-static int probe_numaq(void)
-{
- /* already know from get_memcfg_numaq() */
- return found_numaq;
-}
-
-static void numaq_setup_portio_remap(void)
-{
- int num_quads = num_online_nodes();
-
- if (num_quads <= 1)
- return;
-
- printk(KERN_INFO
- "Remapping cross-quad port I/O for %d quads\n", num_quads);
-
- xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
-
- printk(KERN_INFO
- "xquad_portio vaddr 0x%08lx, len %08lx\n",
- (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
-}
-
-/* Use __refdata to keep false positive warning calm. */
-static struct apic __refdata apic_numaq = {
-
- .name = "NUMAQ",
- .probe = probe_numaq,
- .acpi_madt_oem_check = NULL,
- .apic_id_valid = default_apic_id_valid,
- .apic_id_registered = numaq_apic_id_registered,
-
- .irq_delivery_mode = dest_LowestPrio,
- /* physical delivery on LOCAL quad: */
- .irq_dest_mode = 0,
-
- .target_cpus = numaq_target_cpus,
- .disable_esr = 1,
- .dest_logical = APIC_DEST_LOGICAL,
- .check_apicid_used = numaq_check_apicid_used,
- .check_apicid_present = numaq_check_apicid_present,
-
- .vector_allocation_domain = flat_vector_allocation_domain,
- .init_apic_ldr = numaq_init_apic_ldr,
-
- .ioapic_phys_id_map = numaq_ioapic_phys_id_map,
- .setup_apic_routing = numaq_setup_apic_routing,
- .multi_timer_check = numaq_multi_timer_check,
- .cpu_present_to_apicid = numaq_cpu_present_to_apicid,
- .apicid_to_cpu_present = numaq_apicid_to_cpu_present,
- .setup_portio_remap = numaq_setup_portio_remap,
- .check_phys_apicid_present = numaq_check_phys_apicid_present,
- .enable_apic_mode = NULL,
- .phys_pkg_id = numaq_phys_pkg_id,
- .mps_oem_check = numaq_mps_oem_check,
-
- .get_apic_id = numaq_get_apic_id,
- .set_apic_id = NULL,
- .apic_id_mask = 0x0F << 24,
-
- .cpu_mask_to_apicid_and = numaq_cpu_mask_to_apicid_and,
-
- .send_IPI_mask = numaq_send_IPI_mask,
- .send_IPI_mask_allbutself = NULL,
- .send_IPI_allbutself = numaq_send_IPI_allbutself,
- .send_IPI_all = numaq_send_IPI_all,
- .send_IPI_self = default_send_IPI_self,
-
- .wakeup_secondary_cpu = wakeup_secondary_cpu_via_nmi,
- .trampoline_phys_low = NUMAQ_TRAMPOLINE_PHYS_LOW,
- .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH,
-
- /* We don't do anything here because we use NMI's to boot instead */
- .wait_for_init_deassert = NULL,
-
- .smp_callin_clear_local_apic = numaq_smp_callin_clear_local_apic,
- .inquire_remote_apic = NULL,
-
- .read = native_apic_mem_read,
- .write = native_apic_mem_write,
- .eoi_write = native_apic_mem_write,
- .icr_read = native_apic_icr_read,
- .icr_write = native_apic_icr_write,
- .wait_icr_idle = native_apic_wait_icr_idle,
- .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
-
- .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid,
- .x86_32_numa_cpu_node = numaq_numa_cpu_node,
-};
-
-apic_driver(apic_numaq);
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index eb35ef9ee63f..cceb352c968c 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -119,8 +119,7 @@ static struct apic apic_default = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = default_wait_for_init_deassert,
-
+ .wait_for_init_deassert = true,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
deleted file mode 100644
index 00146f9b0254..000000000000
--- a/arch/x86/kernel/apic/summit_32.c
+++ /dev/null
@@ -1,551 +0,0 @@
-/*
- * IBM Summit-Specific Code
- *
- * Written By: Matthew Dobson, IBM Corporation
- *
- * Copyright (c) 2003 IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <colpatch@us.ibm.com>
- *
- */
-
-#define pr_fmt(fmt) "summit: %s: " fmt, __func__
-
-#include <linux/mm.h>
-#include <asm/io.h>
-#include <asm/bios_ebda.h>
-
-/*
- * APIC driver for the IBM "Summit" chipset.
- */
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#include <asm/smp.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
-#include <asm/ipi.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/smp.h>
-
-static unsigned summit_get_apic_id(unsigned long x)
-{
- return (x >> 24) & 0xFF;
-}
-
-static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector)
-{
- default_send_IPI_mask_sequence_logical(mask, vector);
-}
-
-static void summit_send_IPI_allbutself(int vector)
-{
- default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
-}
-
-static void summit_send_IPI_all(int vector)
-{
- summit_send_IPI_mask(cpu_online_mask, vector);
-}
-
-#include <asm/tsc.h>
-
-extern int use_cyclone;
-
-#ifdef CONFIG_X86_SUMMIT_NUMA
-static void setup_summit(void);
-#else
-static inline void setup_summit(void) {}
-#endif
-
-static int summit_mps_oem_check(struct mpc_table *mpc, char *oem,
- char *productid)
-{
- if (!strncmp(oem, "IBM ENSW", 8) &&
- (!strncmp(productid, "VIGIL SMP", 9)
- || !strncmp(productid, "EXA", 3)
- || !strncmp(productid, "RUTHLESS SMP", 12))){
- mark_tsc_unstable("Summit based system");
- use_cyclone = 1; /*enable cyclone-timer*/
- setup_summit();
- return 1;
- }
- return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
- if (!strncmp(oem_id, "IBM", 3) &&
- (!strncmp(oem_table_id, "SERVIGIL", 8)
- || !strncmp(oem_table_id, "EXA", 3))){
- mark_tsc_unstable("Summit based system");
- use_cyclone = 1; /*enable cyclone-timer*/
- setup_summit();
- return 1;
- }
- return 0;
-}
-
-struct rio_table_hdr {
- unsigned char version; /* Version number of this data structure */
- /* Version 3 adds chassis_num & WP_index */
- unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil) */
- unsigned char num_rio_dev; /* # of RIO I/O devices (Cyclones and Winnipegs) */
-} __attribute__((packed));
-
-struct scal_detail {
- unsigned char node_id; /* Scalability Node ID */
- unsigned long CBAR; /* Address of 1MB register space */
- unsigned char port0node; /* Node ID port connected to: 0xFF=None */
- unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */
- unsigned char port1node; /* Node ID port connected to: 0xFF = None */
- unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */
- unsigned char port2node; /* Node ID port connected to: 0xFF = None */
- unsigned char port2port; /* Port num port connected to: 0,1,2, or 0xFF=None */
- unsigned char chassis_num; /* 1 based Chassis number (1 = boot node) */
-} __attribute__((packed));
-
-struct rio_detail {
- unsigned char node_id; /* RIO Node ID */
- unsigned long BBAR; /* Address of 1MB register space */
- unsigned char type; /* Type of device */
- unsigned char owner_id; /* For WPEG: Node ID of Cyclone that owns this WPEG*/
- /* For CYC: Node ID of Twister that owns this CYC */
- unsigned char port0node; /* Node ID port connected to: 0xFF=None */
- unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */
- unsigned char port1node; /* Node ID port connected to: 0xFF=None */
- unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */
- unsigned char first_slot; /* For WPEG: Lowest slot number below this WPEG */
- /* For CYC: 0 */
- unsigned char status; /* For WPEG: Bit 0 = 1 : the XAPIC is used */
- /* = 0 : the XAPIC is not used, ie:*/
- /* ints fwded to another XAPIC */
- /* Bits1:7 Reserved */
- /* For CYC: Bits0:7 Reserved */
- unsigned char WP_index; /* For WPEG: WPEG instance index - lower ones have */
- /* lower slot numbers/PCI bus numbers */
- /* For CYC: No meaning */
- unsigned char chassis_num; /* 1 based Chassis number */
- /* For LookOut WPEGs this field indicates the */
- /* Expansion Chassis #, enumerated from Boot */
- /* Node WPEG external port, then Boot Node CYC */
- /* external port, then Next Vigil chassis WPEG */
- /* external port, etc. */
- /* Shared Lookouts have only 1 chassis number (the */
- /* first one assigned) */
-} __attribute__((packed));
-
-
-typedef enum {
- CompatTwister = 0, /* Compatibility Twister */
- AltTwister = 1, /* Alternate Twister of internal 8-way */
- CompatCyclone = 2, /* Compatibility Cyclone */
- AltCyclone = 3, /* Alternate Cyclone of internal 8-way */
- CompatWPEG = 4, /* Compatibility WPEG */
- AltWPEG = 5, /* Second Planar WPEG */
- LookOutAWPEG = 6, /* LookOut WPEG */
- LookOutBWPEG = 7, /* LookOut WPEG */
-} node_type;
-
-static inline int is_WPEG(struct rio_detail *rio){
- return (rio->type == CompatWPEG || rio->type == AltWPEG ||
- rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
-}
-
-#define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER)
-
-static const struct cpumask *summit_target_cpus(void)
-{
- /* CPU_MASK_ALL (0xff) has undefined behaviour with
- * dest_LowestPrio mode logical clustered apic interrupt routing
- * Just start on cpu 0. IRQ balancing will spread load
- */
- return cpumask_of(0);
-}
-
-static unsigned long summit_check_apicid_used(physid_mask_t *map, int apicid)
-{
- return 0;
-}
-
-/* we don't use the phys_cpu_present_map to indicate apicid presence */
-static unsigned long summit_check_apicid_present(int bit)
-{
- return 1;
-}
-
-static int summit_early_logical_apicid(int cpu)
-{
- int count = 0;
- u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu);
- u8 my_cluster = APIC_CLUSTER(my_id);
-#ifdef CONFIG_SMP
- u8 lid;
- int i;
-
- /* Create logical APIC IDs by counting CPUs already in cluster. */
- for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
- lid = early_per_cpu(x86_cpu_to_logical_apicid, i);
- if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
- ++count;
- }
-#endif
- /* We only have a 4 wide bitmap in cluster mode. If a deranged
- * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
- BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
- return my_cluster | (1UL << count);
-}
-
-static void summit_init_apic_ldr(void)
-{
- int cpu = smp_processor_id();
- unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
- unsigned long val;
-
- apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
- val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- val |= SET_APIC_LOGICAL_ID(id);
- apic_write(APIC_LDR, val);
-}
-
-static int summit_apic_id_registered(void)
-{
- return 1;
-}
-
-static void summit_setup_apic_routing(void)
-{
- pr_info("Enabling APIC mode: Summit. Using %d I/O APICs\n",
- nr_ioapics);
-}
-
-static int summit_cpu_present_to_apicid(int mps_cpu)
-{
- if (mps_cpu < nr_cpu_ids)
- return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
- else
- return BAD_APICID;
-}
-
-static void summit_ioapic_phys_id_map(physid_mask_t *phys_id_map, physid_mask_t *retmap)
-{
- /* For clustered we don't have a good way to do this yet - hack */
- physids_promote(0x0FL, retmap);
-}
-
-static void summit_apicid_to_cpu_present(int apicid, physid_mask_t *retmap)
-{
- physid_set_mask_of_physid(0, retmap);
-}
-
-static int summit_check_phys_apicid_present(int physical_apicid)
-{
- return 1;
-}
-
-static inline int
-summit_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id)
-{
- unsigned int round = 0;
- unsigned int cpu, apicid = 0;
-
- /*
- * The cpus in the mask must all be on the apic cluster.
- */
- for_each_cpu_and(cpu, cpumask, cpu_online_mask) {
- int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-
- if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
- pr_err("Not a valid mask!\n");
- return -EINVAL;
- }
- apicid |= new_apicid;
- round++;
- }
- if (!round)
- return -EINVAL;
- *dest_id = apicid;
- return 0;
-}
-
-static int
-summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
- const struct cpumask *andmask,
- unsigned int *apicid)
-{
- cpumask_var_t cpumask;
- *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
-
- if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
- return 0;
-
- cpumask_and(cpumask, inmask, andmask);
- summit_cpu_mask_to_apicid(cpumask, apicid);
-
- free_cpumask_var(cpumask);
-
- return 0;
-}
-
-/*
- * cpuid returns the value latched in the HW at reset, not the APIC ID
- * register's value. For any box whose BIOS changes APIC IDs, like
- * clustered APIC systems, we must use hard_smp_processor_id.
- *
- * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
- */
-static int summit_phys_pkg_id(int cpuid_apic, int index_msb)
-{
- return hard_smp_processor_id() >> index_msb;
-}
-
-static int probe_summit(void)
-{
- /* probed later in mptable/ACPI hooks */
- return 0;
-}
-
-#ifdef CONFIG_X86_SUMMIT_NUMA
-static struct rio_table_hdr *rio_table_hdr;
-static struct scal_detail *scal_devs[MAX_NUMNODES];
-static struct rio_detail *rio_devs[MAX_NUMNODES*4];
-
-#ifndef CONFIG_X86_NUMAQ
-static int mp_bus_id_to_node[MAX_MP_BUSSES];
-#endif
-
-static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus)
-{
- int twister = 0, node = 0;
- int i, bus, num_buses;
-
- for (i = 0; i < rio_table_hdr->num_rio_dev; i++) {
- if (rio_devs[i]->node_id == rio_devs[wpeg_num]->owner_id) {
- twister = rio_devs[i]->owner_id;
- break;
- }
- }
- if (i == rio_table_hdr->num_rio_dev) {
- pr_err("Couldn't find owner Cyclone for Winnipeg!\n");
- return last_bus;
- }
-
- for (i = 0; i < rio_table_hdr->num_scal_dev; i++) {
- if (scal_devs[i]->node_id == twister) {
- node = scal_devs[i]->node_id;
- break;
- }
- }
- if (i == rio_table_hdr->num_scal_dev) {
- pr_err("Couldn't find owner Twister for Cyclone!\n");
- return last_bus;
- }
-
- switch (rio_devs[wpeg_num]->type) {
- case CompatWPEG:
- /*
- * The Compatibility Winnipeg controls the 2 legacy buses,
- * the 66MHz PCI bus [2 slots] and the 2 "extra" buses in case
- * a PCI-PCI bridge card is used in either slot: total 5 buses.
- */
- num_buses = 5;
- break;
- case AltWPEG:
- /*
- * The Alternate Winnipeg controls the 2 133MHz buses [1 slot
- * each], their 2 "extra" buses, the 100MHz bus [2 slots] and
- * the "extra" buses for each of those slots: total 7 buses.
- */
- num_buses = 7;
- break;
- case LookOutAWPEG:
- case LookOutBWPEG:
- /*
- * A Lookout Winnipeg controls 3 100MHz buses [2 slots each]
- * & the "extra" buses for each of those slots: total 9 buses.
- */
- num_buses = 9;
- break;
- default:
- pr_info("Unsupported Winnipeg type!\n");
- return last_bus;
- }
-
- for (bus = last_bus; bus < last_bus + num_buses; bus++)
- mp_bus_id_to_node[bus] = node;
- return bus;
-}
-
-static int build_detail_arrays(void)
-{
- unsigned long ptr;
- int i, scal_detail_size, rio_detail_size;
-
- if (rio_table_hdr->num_scal_dev > MAX_NUMNODES) {
- pr_warn("MAX_NUMNODES too low! Defined as %d, but system has %d nodes\n",
- MAX_NUMNODES, rio_table_hdr->num_scal_dev);
- return 0;
- }
-
- switch (rio_table_hdr->version) {
- default:
- pr_warn("Invalid Rio Grande Table Version: %d\n",
- rio_table_hdr->version);
- return 0;
- case 2:
- scal_detail_size = 11;
- rio_detail_size = 13;
- break;
- case 3:
- scal_detail_size = 12;
- rio_detail_size = 15;
- break;
- }
-
- ptr = (unsigned long)rio_table_hdr + 3;
- for (i = 0; i < rio_table_hdr->num_scal_dev; i++, ptr += scal_detail_size)
- scal_devs[i] = (struct scal_detail *)ptr;
-
- for (i = 0; i < rio_table_hdr->num_rio_dev; i++, ptr += rio_detail_size)
- rio_devs[i] = (struct rio_detail *)ptr;
-
- return 1;
-}
-
-void setup_summit(void)
-{
- unsigned long ptr;
- unsigned short offset;
- int i, next_wpeg, next_bus = 0;
-
- /* The pointer to the EBDA is stored in the word @ phys 0x40E(40:0E) */
- ptr = get_bios_ebda();
- ptr = (unsigned long)phys_to_virt(ptr);
-
- rio_table_hdr = NULL;
- offset = 0x180;
- while (offset) {
- /* The block id is stored in the 2nd word */
- if (*((unsigned short *)(ptr + offset + 2)) == 0x4752) {
- /* set the pointer past the offset & block id */
- rio_table_hdr = (struct rio_table_hdr *)(ptr + offset + 4);
- break;
- }
- /* The next offset is stored in the 1st word. 0 means no more */
- offset = *((unsigned short *)(ptr + offset));
- }
- if (!rio_table_hdr) {
- pr_err("Unable to locate Rio Grande Table in EBDA - bailing!\n");
- return;
- }
-
- if (!build_detail_arrays())
- return;
-
- /* The first Winnipeg we're looking for has an index of 0 */
- next_wpeg = 0;
- do {
- for (i = 0; i < rio_table_hdr->num_rio_dev; i++) {
- if (is_WPEG(rio_devs[i]) && rio_devs[i]->WP_index == next_wpeg) {
- /* It's the Winnipeg we're looking for! */
- next_bus = setup_pci_node_map_for_wpeg(i, next_bus);
- next_wpeg++;
- break;
- }
- }
- /*
- * If we go through all Rio devices and don't find one with
- * the next index, it means we've found all the Winnipegs,
- * and thus all the PCI buses.
- */
- if (i == rio_table_hdr->num_rio_dev)
- next_wpeg = 0;
- } while (next_wpeg != 0);
-}
-#endif
-
-static struct apic apic_summit = {
-
- .name = "summit",
- .probe = probe_summit,
- .acpi_madt_oem_check = summit_acpi_madt_oem_check,
- .apic_id_valid = default_apic_id_valid,
- .apic_id_registered = summit_apic_id_registered,
-
- .irq_delivery_mode = dest_LowestPrio,
- /* logical delivery broadcast to all CPUs: */
- .irq_dest_mode = 1,
-
- .target_cpus = summit_target_cpus,
- .disable_esr = 1,
- .dest_logical = APIC_DEST_LOGICAL,
- .check_apicid_used = summit_check_apicid_used,
- .check_apicid_present = summit_check_apicid_present,
-
- .vector_allocation_domain = flat_vector_allocation_domain,
- .init_apic_ldr = summit_init_apic_ldr,
-
- .ioapic_phys_id_map = summit_ioapic_phys_id_map,
- .setup_apic_routing = summit_setup_apic_routing,
- .multi_timer_check = NULL,
- .cpu_present_to_apicid = summit_cpu_present_to_apicid,
- .apicid_to_cpu_present = summit_apicid_to_cpu_present,
- .setup_portio_remap = NULL,
- .check_phys_apicid_present = summit_check_phys_apicid_present,
- .enable_apic_mode = NULL,
- .phys_pkg_id = summit_phys_pkg_id,
- .mps_oem_check = summit_mps_oem_check,
-
- .get_apic_id = summit_get_apic_id,
- .set_apic_id = NULL,
- .apic_id_mask = 0xFF << 24,
-
- .cpu_mask_to_apicid_and = summit_cpu_mask_to_apicid_and,
-
- .send_IPI_mask = summit_send_IPI_mask,
- .send_IPI_mask_allbutself = NULL,
- .send_IPI_allbutself = summit_send_IPI_allbutself,
- .send_IPI_all = summit_send_IPI_all,
- .send_IPI_self = default_send_IPI_self,
-
- .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
- .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-
- .wait_for_init_deassert = default_wait_for_init_deassert,
-
- .smp_callin_clear_local_apic = NULL,
- .inquire_remote_apic = default_inquire_remote_apic,
-
- .read = native_apic_mem_read,
- .write = native_apic_mem_write,
- .eoi_write = native_apic_mem_write,
- .icr_read = native_apic_icr_read,
- .icr_write = native_apic_icr_write,
- .wait_icr_idle = native_apic_wait_icr_idle,
- .safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
-
- .x86_32_early_logical_apicid = summit_early_logical_apicid,
-};
-
-apic_driver(apic_summit);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cac85ee6913f..e66766bf1641 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -279,7 +279,7 @@ static struct apic apic_x2apic_cluster = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index de231e328cae..6d600ebf6c12 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -133,7 +133,7 @@ static struct apic apic_x2apic_phys = {
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d263b1307de1..7834389ba5be 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -396,7 +396,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
.wakeup_secondary_cpu = uv_wakeup_secondary,
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
- .wait_for_init_deassert = NULL,
+ .wait_for_init_deassert = false,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL,
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c67ffa686064..ce8b8ff0e0ef 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -218,7 +218,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
*/
WARN_ONCE(1, "WARNING: This combination of AMD"
" processors is not suitable for SMP.\n");
- add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
}
static void init_amd_k7(struct cpuinfo_x86 *c)
@@ -233,9 +233,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
if (c->x86_model >= 6 && c->x86_model <= 10) {
if (!cpu_has(c, X86_FEATURE_XMM)) {
printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
- rdmsr(MSR_K7_HWCR, l, h);
- l &= ~0x00008000;
- wrmsr(MSR_K7_HWCR, l, h);
+ msr_clear_bit(MSR_K7_HWCR, 15);
set_cpu_cap(c, X86_FEATURE_XMM);
}
}
@@ -509,14 +507,8 @@ static void early_init_amd(struct cpuinfo_x86 *c)
#endif
/* F16h erratum 793, CVE-2013-6885 */
- if (c->x86 == 0x16 && c->x86_model <= 0xf) {
- u64 val;
-
- rdmsrl(MSR_AMD64_LS_CFG, val);
- if (!(val & BIT(15)))
- wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
- }
-
+ if (c->x86 == 0x16 && c->x86_model <= 0xf)
+ msr_set_bit(MSR_AMD64_LS_CFG, 15);
}
static const int amd_erratum_383[];
@@ -536,11 +528,8 @@ static void init_amd(struct cpuinfo_x86 *c)
* Errata 63 for SH-B3 steppings
* Errata 122 for all steppings (F+ have it disabled by default)
*/
- if (c->x86 == 0xf) {
- rdmsrl(MSR_K7_HWCR, value);
- value |= 1 << 6;
- wrmsrl(MSR_K7_HWCR, value);
- }
+ if (c->x86 == 0xf)
+ msr_set_bit(MSR_K7_HWCR, 6);
#endif
early_init_amd(c);
@@ -623,14 +612,11 @@ static void init_amd(struct cpuinfo_x86 *c)
(c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
!cpu_has(c, X86_FEATURE_TOPOEXT)) {
- if (!rdmsrl_safe(0xc0011005, &value)) {
- value |= 1ULL << 54;
- wrmsrl_safe(0xc0011005, value);
+ if (msr_set_bit(0xc0011005, 54) > 0) {
rdmsrl(0xc0011005, value);
- if (value & (1ULL << 54)) {
+ if (value & BIT_64(54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
- printk(KERN_INFO FW_INFO "CPU: Re-enabling "
- "disabled Topology Extensions Support\n");
+ pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
}
}
}
@@ -709,19 +695,12 @@ static void init_amd(struct cpuinfo_x86 *c)
* Disable GART TLB Walk Errors on Fam10h. We do this here
* because this is always needed when GART is enabled, even in a
* kernel which has no MCE support built in.
- * BIOS should disable GartTlbWlk Errors themself. If
- * it doesn't do it here as suggested by the BKDG.
+ * BIOS should disable GartTlbWlk Errors already. If
+ * it doesn't, do it here as suggested by the BKDG.
*
* Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
*/
- u64 mask;
- int err;
-
- err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
- if (err == 0) {
- mask |= (1 << 10);
- wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
- }
+ msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
/*
* On family 10h BIOS may not have properly enabled WC+ support,
@@ -733,10 +712,7 @@ static void init_amd(struct cpuinfo_x86 *c)
* NOTE: we want to use the _safe accessors so as not to #GP kvm
* guests on older kvm hosts.
*/
-
- rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
- value &= ~(1ULL << 24);
- wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
+ msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
if (cpu_has_amd_erratum(c, amd_erratum_383))
set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779edab684e..d8fba5c15fbd 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
#include "cpu.h"
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
- u32 s = 1;
-
- while (s <= x)
- s <<= 1;
-
- return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
- u32 lo, hi;
-
- hi = base & ~0xFFF;
- lo = ~(size-1); /* Size is a power of 2 so this makes a mask */
- lo &= ~0xFFF; /* Remove the ctrl value bits */
- lo |= key; /* Attribute we wish to set */
- wrmsr(reg+MSR_IDT_MCR0, lo, hi);
- mtrr_centaur_report_mcr(reg, lo, hi); /* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
- u32 clip = 0xFFFFFFFFUL;
- u32 top = 0;
- int i;
-
- for (i = 0; i < e820.nr_map; i++) {
- unsigned long start, end;
-
- if (e820.map[i].addr > 0xFFFFFFFFUL)
- continue;
- /*
- * Don't MCR over reserved space. Ignore the ISA hole
- * we frob around that catastrophe already
- */
- if (e820.map[i].type == E820_RESERVED) {
- if (e820.map[i].addr >= 0x100000UL &&
- e820.map[i].addr < clip)
- clip = e820.map[i].addr;
- continue;
- }
- start = e820.map[i].addr;
- end = e820.map[i].addr + e820.map[i].size;
- if (start >= end)
- continue;
- if (end > top)
- top = end;
- }
- /*
- * Everything below 'top' should be RAM except for the ISA hole.
- * Because of the limited MCR's we want to map NV/ACPI into our
- * MCR range for gunk in RAM
- *
- * Clip might cause us to MCR insufficient RAM but that is an
- * acceptable failure mode and should only bite obscure boxes with
- * a VESA hole at 15Mb
- *
- * The second case Clip sometimes kicks in is when the EBDA is marked
- * as reserved. Again we fail safe with reasonable results
- */
- if (top > clip)
- top = clip;
-
- return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
- u32 mem = ramtop();
- u32 root = power2(mem);
- u32 base = root;
- u32 top = root;
- u32 floor = 0;
- int ct = 0;
-
- while (ct < nr) {
- u32 fspace = 0;
- u32 high;
- u32 low;
-
- /*
- * Find the largest block we will fill going upwards
- */
- high = power2(mem-top);
-
- /*
- * Find the largest block we will fill going downwards
- */
- low = base/2;
-
- /*
- * Don't fill below 1Mb going downwards as there
- * is an ISA hole in the way.
- */
- if (base <= 1024*1024)
- low = 0;
-
- /*
- * See how much space we could cover by filling below
- * the ISA hole
- */
-
- if (floor == 0)
- fspace = 512*1024;
- else if (floor == 512*1024)
- fspace = 128*1024;
-
- /* And forget ROM space */
-
- /*
- * Now install the largest coverage we get
- */
- if (fspace > high && fspace > low) {
- centaur_mcr_insert(ct, floor, fspace, key);
- floor += fspace;
- } else if (high > low) {
- centaur_mcr_insert(ct, top, high, key);
- top += high;
- } else if (low > 0) {
- base -= low;
- centaur_mcr_insert(ct, base, low, key);
- } else
- break;
- ct++;
- }
- /*
- * We loaded ct values. We now need to set the mask. The caller
- * must do this bit.
- */
- return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining and weak write ordered.
- *
- * To experiment with: Linux never uses stack operations for
- * mmio spaces so we could globally enable stack operation wc
- *
- * Load the registers with type 31 - full write combining, all
- * writes weakly ordered.
- */
- used = centaur_mcr_compute(6, 31);
-
- /*
- * Wipe unused MCRs
- */
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
- u32 lo, hi;
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining, weak store ordered.
- *
- * Load the registers with type 25
- * 8 - weak write ordering
- * 16 - weak read ordering
- * 1 - write combining
- */
- used = centaur_mcr_compute(6, 25);
-
- /*
- * Mark the registers we are using.
- */
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- for (i = 0; i < used; i++)
- lo |= 1<<(9+i);
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
- /*
- * Wipe unused MCRs
- */
-
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
- u32 lo, hi;
- u32 key;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- key = (lo>>17) & 7;
- lo |= key<<6; /* replace with unlock key */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
- u32 lo, hi;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
#define ACE_PRESENT (1 << 6)
#define ACE_ENABLED (1 << 7)
#define ACE_FCR (1 << 28) /* MSR_VIA_FCR */
@@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c)
fcr_clr = DPDC;
printk(KERN_NOTICE "Disabling bugged TSC.\n");
clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
- centaur_create_optimal_mcr();
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- *
- * The C6 original lacks weak read order
- *
- * Note 0x120 is write only on Winchip 1
- */
- wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
break;
case 8:
switch (c->x86_mask) {
@@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c)
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
case 9:
name = "3";
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
default:
name = "??";
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..a135239badb7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1025,7 +1025,8 @@ __setup("show_msr=", setup_show_msr);
static __init int setup_noclflush(char *arg)
{
- setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+ setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
+ setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
return 1;
}
__setup("noclflush", setup_noclflush);
@@ -1078,6 +1079,10 @@ static __init int setup_disablecpuid(char *arg)
}
__setup("clearcpuid=", setup_disablecpuid);
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+ (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
+
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1094,10 +1099,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
&init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
DEFINE_PER_CPU(char *, irq_stack_ptr) =
init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfabd645..a80029035bf2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -31,11 +31,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
/* Unmask CPUID levels if masked: */
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
- rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
- if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
- misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
- wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+ if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
c->cpuid_level = cpuid_eax(0);
get_cpu_cap(c);
}
@@ -129,16 +126,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
* Ingo Molnar reported a Pentium D (model 6) and a Xeon
* (model 2) with the same problem.
*/
- if (c->x86 == 15) {
- rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
- if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
- printk(KERN_INFO "kmemcheck: Disabling fast string operations\n");
-
- misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
- wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
- }
- }
+ if (c->x86 == 15)
+ if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
+ pr_info("kmemcheck: Disabling fast string operations\n");
#endif
/*
@@ -195,10 +186,16 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
}
}
-static void intel_workarounds(struct cpuinfo_x86 *c)
+static int forcepae;
+static int __init forcepae_setup(char *__unused)
{
- unsigned long lo, hi;
+ forcepae = 1;
+ return 1;
+}
+__setup("forcepae", forcepae_setup);
+static void intel_workarounds(struct cpuinfo_x86 *c)
+{
#ifdef CONFIG_X86_F00F_BUG
/*
* All current models of Pentium and Pentium with MMX technology CPUs
@@ -225,16 +222,26 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
clear_cpu_cap(c, X86_FEATURE_SEP);
/*
+ * PAE CPUID issue: many Pentium M report no PAE but may have a
+ * functionally usable PAE implementation.
+ * Forcefully enable PAE if kernel parameter "forcepae" is present.
+ */
+ if (forcepae) {
+ printk(KERN_WARNING "PAE forced!\n");
+ set_cpu_cap(c, X86_FEATURE_PAE);
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
+ }
+
+ /*
* P4 Xeon errata 037 workaround.
* Hardware prefetcher may cause stale data to be loaded into the cache.
*/
if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
- rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
- if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
- printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
- printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
- lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
- wrmsr(MSR_IA32_MISC_ENABLE, lo, hi);
+ if (msr_set_bit(MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+ > 0) {
+ pr_info("CPU: C0 stepping P4 Xeon detected.\n");
+ pr_info("CPU: Disabling hardware prefetching (Errata 037)\n");
}
}
@@ -267,10 +274,6 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
}
#endif
-#ifdef CONFIG_X86_NUMAQ
- numaq_tsc_disable();
-#endif
-
intel_smp_check(c);
}
#else
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0641113e2965..a952e9c85b6f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1225,21 +1225,24 @@ static struct notifier_block cacheinfo_cpu_notifier = {
static int __init cache_sysfs_init(void)
{
- int i;
+ int i, err = 0;
if (num_cache_leaves == 0)
return 0;
+ cpu_notifier_register_begin();
for_each_online_cpu(i) {
- int err;
struct device *dev = get_cpu_device(i);
err = cache_add_dev(dev);
if (err)
- return err;
+ goto out;
}
- register_hotcpu_notifier(&cacheinfo_cpu_notifier);
- return 0;
+ __register_hotcpu_notifier(&cacheinfo_cpu_notifier);
+
+out:
+ cpu_notifier_register_done();
+ return err;
}
device_initcall(cache_sysfs_init);
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 36565373af87..afa9f0d487ea 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -47,45 +47,3 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
return NULL;
}
EXPORT_SYMBOL(x86_match_cpu);
-
-ssize_t arch_print_cpu_modalias(struct device *dev,
- struct device_attribute *attr,
- char *bufptr)
-{
- int size = PAGE_SIZE;
- int i, n;
- char *buf = bufptr;
-
- n = snprintf(buf, size, "x86cpu:vendor:%04X:family:%04X:"
- "model:%04X:feature:",
- boot_cpu_data.x86_vendor,
- boot_cpu_data.x86,
- boot_cpu_data.x86_model);
- size -= n;
- buf += n;
- size -= 1;
- for (i = 0; i < NCAPINTS*32; i++) {
- if (boot_cpu_has(i)) {
- n = snprintf(buf, size, ",%04X", i);
- if (n >= size) {
- WARN(1, "x86 features overflow page\n");
- break;
- }
- size -= n;
- buf += n;
- }
- }
- *buf++ = '\n';
- return buf - bufptr;
-}
-
-int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
- char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (buf) {
- arch_print_cpu_modalias(NULL, NULL, buf);
- add_uevent_var(env, "MODALIAS=%s", buf);
- kfree(buf);
- }
- return 0;
-}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 4d5419b249da..68317c80de7f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -89,6 +89,9 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
static DEFINE_PER_CPU(struct mce, mces_seen);
static int cpu_missing;
+/* CMCI storm detection filter */
+static DEFINE_PER_CPU(unsigned long, mce_polled_error);
+
/*
* MCA banks polled by the period polling timer for corrected events.
* With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
@@ -614,6 +617,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(m.status & MCI_STATUS_VAL))
continue;
+ this_cpu_write(mce_polled_error, 1);
/*
* Uncorrected or signalled events are handled by the exception
* handler when it is enabled, so don't process those here.
@@ -1278,10 +1282,18 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
static unsigned long (*mce_adjust_timer)(unsigned long interval) =
mce_adjust_timer_default;
+static int cmc_error_seen(void)
+{
+ unsigned long *v = &__get_cpu_var(mce_polled_error);
+
+ return test_and_clear_bit(0, v);
+}
+
static void mce_timer_fn(unsigned long data)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
unsigned long iv;
+ int notify;
WARN_ON(smp_processor_id() != data);
@@ -1296,7 +1308,9 @@ static void mce_timer_fn(unsigned long data)
* polling interval, otherwise increase the polling interval.
*/
iv = __this_cpu_read(mce_next_interval);
- if (mce_notify_irq()) {
+ notify = mce_notify_irq();
+ notify |= cmc_error_seen();
+ if (notify) {
iv = max(iv / 2, (unsigned long) HZ/100);
} else {
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
@@ -2434,14 +2448,18 @@ static __init int mcheck_init_device(void)
if (err)
return err;
+ cpu_notifier_register_begin();
for_each_online_cpu(i) {
err = mce_device_create(i);
- if (err)
+ if (err) {
+ cpu_notifier_register_done();
return err;
+ }
}
register_syscore_ops(&mce_syscore_ops);
- register_hotcpu_notifier(&mce_cpu_notifier);
+ __register_hotcpu_notifier(&mce_cpu_notifier);
+ cpu_notifier_register_done();
/* register character device /dev/mcelog */
misc_register(&mce_chrdev_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index fb6156fee6f7..9a316b21df8b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -9,6 +9,7 @@
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/sched.h>
+#include <linux/cpumask.h>
#include <asm/apic.h>
#include <asm/processor.h>
#include <asm/msr.h>
@@ -41,7 +42,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
* cmci_discover_lock protects against parallel discovery attempts
* which could race against each other.
*/
-static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
+static DEFINE_SPINLOCK(cmci_discover_lock);
#define CMCI_THRESHOLD 1
#define CMCI_POLL_INTERVAL (30 * HZ)
@@ -137,6 +138,22 @@ unsigned long mce_intel_adjust_timer(unsigned long interval)
}
}
+static void cmci_storm_disable_banks(void)
+{
+ unsigned long flags, *owned;
+ int bank;
+ u64 val;
+
+ spin_lock_irqsave(&cmci_discover_lock, flags);
+ owned = __get_cpu_var(mce_banks_owned);
+ for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ val &= ~MCI_CTL2_CMCI_EN;
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ }
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
static bool cmci_storm_detect(void)
{
unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -158,7 +175,7 @@ static bool cmci_storm_detect(void)
if (cnt <= CMCI_STORM_THRESHOLD)
return false;
- cmci_clear();
+ cmci_storm_disable_banks();
__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
r = atomic_add_return(1, &cmci_storm_on_cpus);
mce_timer_kick(CMCI_POLL_INTERVAL);
@@ -194,7 +211,7 @@ static void cmci_discover(int banks)
int i;
int bios_wrong_thresh = 0;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
int bios_zero_thresh = 0;
@@ -249,7 +266,7 @@ static void cmci_discover(int banks)
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
pr_info_once(
"bios_cmci_threshold: Some banks do not have valid thresholds set\n");
@@ -299,10 +316,10 @@ void cmci_clear(void)
if (!cmci_supported(&banks))
return;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++)
__cmci_disable_bank(i);
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
static void cmci_rediscover_work_func(void *arg)
@@ -343,9 +360,9 @@ void cmci_disable_bank(int bank)
if (!cmci_supported(&banks))
return;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
__cmci_disable_bank(bank);
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
static void intel_init_cmci(void)
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 3eec7de76efb..d921b7ee6595 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -271,9 +271,6 @@ static void thermal_throttle_remove_dev(struct device *dev)
sysfs_remove_group(&dev->kobj, &thermal_attr_group);
}
-/* Mutex protecting device creation against CPU hotplug: */
-static DEFINE_MUTEX(therm_cpu_lock);
-
/* Get notified when a cpu comes on/off. Be hotplug friendly. */
static int
thermal_throttle_cpu_callback(struct notifier_block *nfb,
@@ -289,18 +286,14 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- mutex_lock(&therm_cpu_lock);
err = thermal_throttle_add_dev(dev, cpu);
- mutex_unlock(&therm_cpu_lock);
WARN_ON(err);
break;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- mutex_lock(&therm_cpu_lock);
thermal_throttle_remove_dev(dev);
- mutex_unlock(&therm_cpu_lock);
break;
}
return notifier_from_errno(err);
@@ -319,19 +312,16 @@ static __init int thermal_throttle_init_device(void)
if (!atomic_read(&therm_throt_en))
return 0;
- register_hotcpu_notifier(&thermal_throttle_cpu_notifier);
+ cpu_notifier_register_begin();
-#ifdef CONFIG_HOTPLUG_CPU
- mutex_lock(&therm_cpu_lock);
-#endif
/* connect live CPUs to sysfs */
for_each_online_cpu(cpu) {
err = thermal_throttle_add_dev(get_cpu_device(cpu), cpu);
WARN_ON(err);
}
-#ifdef CONFIG_HOTPLUG_CPU
- mutex_unlock(&therm_cpu_lock);
-#endif
+
+ __register_hotcpu_notifier(&thermal_throttle_cpu_notifier);
+ cpu_notifier_register_done();
return 0;
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9f7ca266864a..76f98fe5b35c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
#include <linux/hardirq.h>
#include <linux/efi.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <asm/hyperv.h>
@@ -26,10 +27,50 @@
#include <asm/irq_regs.h>
#include <asm/i8259.h>
#include <asm/apic.h>
+#include <asm/timer.h>
struct ms_hyperv_info ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);
+#if IS_ENABLED(CONFIG_HYPERV)
+static void (*vmbus_handler)(void);
+
+void hyperv_vector_handler(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ irq_enter();
+ exit_idle();
+
+ inc_irq_stat(irq_hv_callback_count);
+ if (vmbus_handler)
+ vmbus_handler();
+
+ irq_exit();
+ set_irq_regs(old_regs);
+}
+
+void hv_setup_vmbus_irq(void (*handler)(void))
+{
+ vmbus_handler = handler;
+ /*
+ * Setup the IDT for hypervisor callback. Prevent reallocation
+ * at module reload.
+ */
+ if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors))
+ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
+ hyperv_callback_vector);
+}
+
+void hv_remove_vmbus_irq(void)
+{
+ /* We have no way to deallocate the interrupt gate */
+ vmbus_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
+EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+#endif
+
static uint32_t __init ms_hyperv_platform(void)
{
u32 eax;
@@ -105,6 +146,11 @@ static void __init ms_hyperv_init_platform(void)
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+ no_timer_check = 1;
+#endif
+
}
const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -113,41 +159,3 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.init_platform = ms_hyperv_init_platform,
};
EXPORT_SYMBOL(x86_hyper_ms_hyperv);
-
-#if IS_ENABLED(CONFIG_HYPERV)
-static int vmbus_irq = -1;
-static irq_handler_t vmbus_isr;
-
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
- /*
- * Setup the IDT for hypervisor callback.
- */
- alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-
- vmbus_irq = irq;
- vmbus_isr = handler;
-}
-
-void hyperv_vector_handler(struct pt_regs *regs)
-{
- struct pt_regs *old_regs = set_irq_regs(regs);
- struct irq_desc *desc;
-
- irq_enter();
- exit_idle();
-
- desc = irq_to_desc(vmbus_irq);
-
- if (desc)
- generic_handle_irq_desc(vmbus_irq, desc);
-
- irq_exit();
- set_irq_regs(old_regs);
-}
-#else
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
-}
-#endif
-EXPORT_SYMBOL_GPL(hv_register_vmbus_handler);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 895604f2e916..ae407f7226c8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -892,7 +892,6 @@ static void x86_pmu_enable(struct pmu *pmu)
* hw_perf_group_sched_in() or x86_pmu_enable()
*
* step1: save events moving to new counters
- * step2: reprogram moved events into new counters
*/
for (i = 0; i < n_running; i++) {
event = cpuc->event_list[i];
@@ -918,6 +917,9 @@ static void x86_pmu_enable(struct pmu *pmu)
x86_pmu_stop(event, PERF_EF_UPDATE);
}
+ /*
+ * step2: reprogram moved events into new counters
+ */
for (i = 0; i < cpuc->n_events; i++) {
event = cpuc->event_list[i];
hwc = &event->hw;
@@ -1043,7 +1045,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
/*
* If group events scheduling transaction was started,
* skip the schedulability test here, it will be performed
- * at commit time (->commit_txn) as a whole
+ * at commit time (->commit_txn) as a whole.
*/
if (cpuc->group_flag & PERF_EVENT_TXN)
goto done_collect;
@@ -1058,6 +1060,10 @@ static int x86_pmu_add(struct perf_event *event, int flags)
memcpy(cpuc->assign, assign, n*sizeof(int));
done_collect:
+ /*
+ * Commit the collect_events() state. See x86_pmu_del() and
+ * x86_pmu_*_txn().
+ */
cpuc->n_events = n;
cpuc->n_added += n - n0;
cpuc->n_txn += n - n0;
@@ -1183,25 +1189,38 @@ static void x86_pmu_del(struct perf_event *event, int flags)
* If we're called during a txn, we don't need to do anything.
* The events never got scheduled and ->cancel_txn will truncate
* the event_list.
+ *
+ * XXX assumes any ->del() called during a TXN will only be on
+ * an event added during that same TXN.
*/
if (cpuc->group_flag & PERF_EVENT_TXN)
return;
+ /*
+ * Not a TXN, therefore cleanup properly.
+ */
x86_pmu_stop(event, PERF_EF_UPDATE);
for (i = 0; i < cpuc->n_events; i++) {
- if (event == cpuc->event_list[i]) {
+ if (event == cpuc->event_list[i])
+ break;
+ }
- if (x86_pmu.put_event_constraints)
- x86_pmu.put_event_constraints(cpuc, event);
+ if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */
+ return;
- while (++i < cpuc->n_events)
- cpuc->event_list[i-1] = cpuc->event_list[i];
+ /* If we have a newly added event; make sure to decrease n_added. */
+ if (i >= cpuc->n_events - cpuc->n_added)
+ --cpuc->n_added;
+
+ if (x86_pmu.put_event_constraints)
+ x86_pmu.put_event_constraints(cpuc, event);
+
+ /* Delete the array entry. */
+ while (++i < cpuc->n_events)
+ cpuc->event_list[i-1] = cpuc->event_list[i];
+ --cpuc->n_events;
- --cpuc->n_events;
- break;
- }
- }
perf_event_update_userpage(event);
}
@@ -1595,7 +1614,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
{
__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
/*
- * Truncate the collected events.
+ * Truncate collected array by the number of events added in this
+ * transaction. See x86_pmu_add() and x86_pmu_*_txn().
*/
__this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
__this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
@@ -1606,6 +1626,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
* Commit group events scheduling transaction
* Perform the group schedulability test as a whole
* Return 0 if success
+ *
+ * Does not cancel the transaction on failure; expects the caller to do this.
*/
static int x86_pmu_commit_txn(struct pmu *pmu)
{
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 4972c244d0bc..3b2f9bdd974b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -130,9 +130,11 @@ struct cpu_hw_events {
unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
int enabled;
- int n_events;
- int n_added;
- int n_txn;
+ int n_events; /* the # of events in the below arrays */
+ int n_added; /* the # last events in the below arrays;
+ they've never been enabled yet */
+ int n_txn; /* the # last events in the below arrays;
+ added in the current transaction */
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 4b8e4d3cd6ea..4c36bbe3173a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -926,13 +926,13 @@ static __init int amd_ibs_init(void)
goto out;
perf_ibs_pm_init();
- get_online_cpus();
+ cpu_notifier_register_begin();
ibs_caps = caps;
/* make ibs_caps visible to other cpus: */
smp_mb();
- perf_cpu_notifier(perf_ibs_cpu_notifier);
smp_call_function(setup_APIC_ibs, NULL, 1);
- put_online_cpus();
+ __perf_cpu_notifier(perf_ibs_cpu_notifier);
+ cpu_notifier_register_done();
ret = perf_event_ibs_init();
out:
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 754291adec33..3bbdf4cd38b9 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -531,15 +531,16 @@ static int __init amd_uncore_init(void)
if (ret)
return -ENODEV;
- get_online_cpus();
+ cpu_notifier_register_begin();
+
/* init cpus already online before registering for hotplug notifier */
for_each_online_cpu(cpu) {
amd_uncore_cpu_up_prepare(cpu);
smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
}
- register_cpu_notifier(&amd_uncore_cpu_notifier_block);
- put_online_cpus();
+ __register_cpu_notifier(&amd_uncore_cpu_notifier_block);
+ cpu_notifier_register_done();
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5ad35ad94d0f..7c87424d4140 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -59,7 +59,7 @@
#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT 3 /* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
/* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT)
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
+ 1<<RAPL_IDX_PKG_NRG_STAT|\
+ 1<<RAPL_IDX_RAM_NRG_STAT|\
+ 1<<RAPL_IDX_PP1_NRG_STAT)
+
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
NULL,
};
+static struct attribute *rapl_events_hsw_attr[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_ram),
+
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_ram_unit),
+
+ EVENT_PTR(rapl_cores_scale),
+ EVENT_PTR(rapl_pkg_scale),
+ EVENT_PTR(rapl_gpu_scale),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
static struct attribute_group rapl_pmu_events_group = {
.name = "events",
.attrs = NULL, /* patched at runtime */
@@ -511,6 +535,7 @@ static int rapl_cpu_prepare(int cpu)
struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
int phys_id = topology_physical_package_id(cpu);
u64 ms;
+ u64 msr_rapl_power_unit_bits;
if (pmu)
return 0;
@@ -518,6 +543,9 @@ static int rapl_cpu_prepare(int cpu)
if (phys_id < 0)
return -1;
+ if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+ return -1;
+
pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
if (!pmu)
return -1;
@@ -531,8 +559,7 @@ static int rapl_cpu_prepare(int cpu)
*
* we cache in local PMU instance
*/
- rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
- pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+ pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
pmu->pmu = &rapl_pmu_class;
/*
@@ -631,11 +658,14 @@ static int __init rapl_pmu_init(void)
switch (boot_cpu_data.x86_model) {
case 42: /* Sandy Bridge */
case 58: /* Ivy Bridge */
- case 60: /* Haswell */
- case 69: /* Haswell-Celeron */
rapl_cntr_mask = RAPL_IDX_CLN;
rapl_pmu_events_group.attrs = rapl_events_cln_attr;
break;
+ case 60: /* Haswell */
+ case 69: /* Haswell-Celeron */
+ rapl_cntr_mask = RAPL_IDX_HSW;
+ rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+ break;
case 45: /* Sandy Bridge-EP */
case 62: /* IvyTown */
rapl_cntr_mask = RAPL_IDX_SRV;
@@ -646,19 +676,22 @@ static int __init rapl_pmu_init(void)
/* unsupported */
return 0;
}
- get_online_cpus();
+
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu) {
- rapl_cpu_prepare(cpu);
+ ret = rapl_cpu_prepare(cpu);
+ if (ret)
+ goto out;
rapl_cpu_init(cpu);
}
- perf_cpu_notifier(rapl_cpu_notifier);
+ __perf_cpu_notifier(rapl_cpu_notifier);
ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
if (WARN_ON(ret)) {
pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
- put_online_cpus();
+ cpu_notifier_register_done();
return -1;
}
@@ -672,7 +705,8 @@ static int __init rapl_pmu_init(void)
hweight32(rapl_cntr_mask),
ktime_to_ms(pmu->timer_interval));
- put_online_cpus();
+out:
+ cpu_notifier_register_done();
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c88f7f4b03ee..65bbbea38b9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -66,6 +66,47 @@ DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+static void uncore_pmu_event_read(struct perf_event *event);
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+ return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+ struct intel_uncore_box *box;
+
+ box = *per_cpu_ptr(pmu->box, cpu);
+ if (box)
+ return box;
+
+ raw_spin_lock(&uncore_box_lock);
+ list_for_each_entry(box, &pmu->box_list, list) {
+ if (box->phys_id == topology_physical_package_id(cpu)) {
+ atomic_inc(&box->refcnt);
+ *per_cpu_ptr(pmu->box, cpu) = box;
+ break;
+ }
+ }
+ raw_spin_unlock(&uncore_box_lock);
+
+ return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+ /*
+ * perf core schedules event on the basis of cpu, uncore events are
+ * collected by one of the cpus inside a physical package.
+ */
+ return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+}
+
static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
{
u64 count;
@@ -1639,6 +1680,349 @@ static struct intel_uncore_type *snb_msr_uncores[] = {
&snb_uncore_cbox,
NULL,
};
+
+enum {
+ SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"),
+ INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+ INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+ { /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+ .name = "format",
+ .attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+ resource_size_t addr;
+ u32 pci_dword;
+
+ pci_read_config_dword(pdev, where, &pci_dword);
+ addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ pci_read_config_dword(pdev, where + 4, &pci_dword);
+ addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+ addr &= ~(PAGE_SIZE - 1);
+
+ box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+ box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+ int idx, base;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ pmu = uncore_event_to_pmu(event);
+ /* no device found for this pmu */
+ if (pmu->func_id < 0)
+ return -ENOENT;
+
+ /* Sampling not supported yet */
+ if (hwc->sample_period)
+ return -EINVAL;
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ event->attr.sample_period) /* no sampling */
+ return -EINVAL;
+
+ /*
+ * Place all uncore events for a particular physical package
+ * onto a single cpu
+ */
+ if (event->cpu < 0)
+ return -EINVAL;
+
+ /* check only supported bits are set */
+ if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+ return -EINVAL;
+
+ box = uncore_pmu_to_box(pmu, event->cpu);
+ if (!box || box->cpu < 0)
+ return -EINVAL;
+
+ event->cpu = box->cpu;
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+ event->hw.extra_reg.idx = EXTRA_REG_NONE;
+ event->hw.branch_reg.idx = EXTRA_REG_NONE;
+ /*
+ * check event is known (whitelist, determines counter)
+ */
+ switch (cfg) {
+ case SNB_UNCORE_PCI_IMC_DATA_READS:
+ base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+ idx = UNCORE_PMC_IDX_FIXED;
+ break;
+ case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+ base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+ idx = UNCORE_PMC_IDX_FIXED + 1;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* must be done before validate_group */
+ event->hw.event_base = base;
+ event->hw.config = cfg;
+ event->hw.idx = idx;
+
+ /* no group validation needed, we have free running counters */
+
+ return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ u64 count;
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ event->hw.state = 0;
+ box->n_active++;
+
+ list_add_tail(&event->active_entry, &box->active_list);
+
+ count = snb_uncore_imc_read_counter(box, event);
+ local64_set(&event->hw.prev_count, count);
+
+ if (box->n_active == 1)
+ uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ box->n_active--;
+
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+
+ list_del(&event->active_entry);
+
+ if (box->n_active == 0)
+ uncore_pmu_cancel_hrtimer(box);
+ }
+
+ if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ uncore_perf_event_update(box, event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box)
+ return -ENODEV;
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+ if (!(flags & PERF_EF_START))
+ hwc->state |= PERF_HES_ARCH;
+
+ snb_uncore_imc_event_start(event, 0);
+
+ box->n_events++;
+
+ return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int i;
+
+ snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+ for (i = 0; i < box->n_events; i++) {
+ if (event == box->event_list[i]) {
+ --box->n_events;
+ break;
+ }
+ }
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+ struct pci_dev *dev = NULL;
+ int bus;
+
+ dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+ if (!dev)
+ return -ENOTTY;
+
+ bus = dev->bus->number;
+
+ pcibus_to_physid[bus] = 0;
+
+ pci_dev_put(dev);
+
+ return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = snb_uncore_imc_event_init,
+ .add = snb_uncore_imc_event_add,
+ .del = snb_uncore_imc_event_del,
+ .start = snb_uncore_imc_event_start,
+ .stop = snb_uncore_imc_event_stop,
+ .read = uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+ .init_box = snb_uncore_imc_init_box,
+ .enable_box = snb_uncore_imc_enable_box,
+ .disable_box = snb_uncore_imc_disable_box,
+ .disable_event = snb_uncore_imc_disable_event,
+ .enable_event = snb_uncore_imc_enable_event,
+ .hw_config = snb_uncore_imc_hw_config,
+ .read_counter = snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+ .name = "imc",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 32,
+ .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE,
+ .event_descs = snb_uncore_imc_events,
+ .format_group = &snb_uncore_imc_format_group,
+ .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+ .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK,
+ .ops = &snb_uncore_imc_ops,
+ .pmu = &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+ [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc,
+ NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snb_uncore_pci_ids) = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivb_uncore_pci_ids) = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hsw_uncore_pci_ids) = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+ .name = "snb_uncore",
+ .id_table = snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+ .name = "ivb_uncore",
+ .id_table = ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+ .name = "hsw_uncore",
+ .id_table = hsw_uncore_pci_ids,
+};
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
@@ -2789,6 +3173,7 @@ again:
static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
{
struct intel_uncore_box *box;
+ struct perf_event *event;
unsigned long flags;
int bit;
@@ -2801,19 +3186,27 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
*/
local_irq_save(flags);
+ /*
+ * handle boxes with an active event list as opposed to active
+ * counters
+ */
+ list_for_each_entry(event, &box->active_list, active_entry) {
+ uncore_perf_event_update(box, event);
+ }
+
for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
uncore_perf_event_update(box, box->events[bit]);
local_irq_restore(flags);
- hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+ hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
return HRTIMER_RESTART;
}
static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
__hrtimer_start_range_ns(&box->hrtimer,
- ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+ ns_to_ktime(box->hrtimer_duration), 0,
HRTIMER_MODE_REL_PINNED, 0);
}
@@ -2847,43 +3240,12 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
box->cpu = -1;
box->phys_id = -1;
- return box;
-}
+ /* set default hrtimer timeout */
+ box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
-{
- struct intel_uncore_box *box;
+ INIT_LIST_HEAD(&box->active_list);
- box = *per_cpu_ptr(pmu->box, cpu);
- if (box)
- return box;
-
- raw_spin_lock(&uncore_box_lock);
- list_for_each_entry(box, &pmu->box_list, list) {
- if (box->phys_id == topology_physical_package_id(cpu)) {
- atomic_inc(&box->refcnt);
- *per_cpu_ptr(pmu->box, cpu) = box;
- break;
- }
- }
- raw_spin_unlock(&uncore_box_lock);
-
- return *per_cpu_ptr(pmu->box, cpu);
-}
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
- return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
-
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
- /*
- * perf core schedules event on the basis of cpu, uncore events are
- * collected by one of the cpus inside a physical package.
- */
- return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+ return box;
}
static int
@@ -3279,16 +3641,21 @@ static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
{
int ret;
- pmu->pmu = (struct pmu) {
- .attr_groups = pmu->type->attr_groups,
- .task_ctx_nr = perf_invalid_context,
- .event_init = uncore_pmu_event_init,
- .add = uncore_pmu_event_add,
- .del = uncore_pmu_event_del,
- .start = uncore_pmu_event_start,
- .stop = uncore_pmu_event_stop,
- .read = uncore_pmu_event_read,
- };
+ if (!pmu->type->pmu) {
+ pmu->pmu = (struct pmu) {
+ .attr_groups = pmu->type->attr_groups,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = uncore_pmu_event_init,
+ .add = uncore_pmu_event_add,
+ .del = uncore_pmu_event_del,
+ .start = uncore_pmu_event_start,
+ .stop = uncore_pmu_event_stop,
+ .read = uncore_pmu_event_read,
+ };
+ } else {
+ pmu->pmu = *pmu->type->pmu;
+ pmu->pmu.attr_groups = pmu->type->attr_groups;
+ }
if (pmu->type->num_boxes == 1) {
if (strlen(pmu->type->name) > 0)
@@ -3334,6 +3701,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
if (!pmus)
return -ENOMEM;
+ type->pmus = pmus;
+
type->unconstrainted = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
0, type->num_counters, 0, 0);
@@ -3369,7 +3738,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
}
type->pmu_group = &uncore_pmu_attr_group;
- type->pmus = pmus;
return 0;
fail:
uncore_type_exit(type);
@@ -3501,6 +3869,28 @@ static int __init uncore_pci_init(void)
pci_uncores = ivt_pci_uncores;
uncore_pci_driver = &ivt_uncore_pci_driver;
break;
+ case 42: /* Sandy Bridge */
+ ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
+ if (ret)
+ return ret;
+ pci_uncores = snb_pci_uncores;
+ uncore_pci_driver = &snb_uncore_pci_driver;
+ break;
+ case 58: /* Ivy Bridge */
+ ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
+ if (ret)
+ return ret;
+ pci_uncores = snb_pci_uncores;
+ uncore_pci_driver = &ivb_uncore_pci_driver;
+ break;
+ case 60: /* Haswell */
+ case 69: /* Haswell Celeron */
+ ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
+ if (ret)
+ return ret;
+ pci_uncores = snb_pci_uncores;
+ uncore_pci_driver = &hsw_uncore_pci_driver;
+ break;
default:
return 0;
}
@@ -3772,7 +4162,7 @@ static void __init uncore_cpu_setup(void *dummy)
static int __init uncore_cpu_init(void)
{
- int ret, cpu, max_cores;
+ int ret, max_cores;
max_cores = boot_cpu_data.x86_max_cores;
switch (boot_cpu_data.x86_model) {
@@ -3816,29 +4206,6 @@ static int __init uncore_cpu_init(void)
if (ret)
return ret;
- get_online_cpus();
-
- for_each_online_cpu(cpu) {
- int i, phys_id = topology_physical_package_id(cpu);
-
- for_each_cpu(i, &uncore_cpu_mask) {
- if (phys_id == topology_physical_package_id(i)) {
- phys_id = -1;
- break;
- }
- }
- if (phys_id < 0)
- continue;
-
- uncore_cpu_prepare(cpu, phys_id);
- uncore_event_init_cpu(cpu);
- }
- on_each_cpu(uncore_cpu_setup, NULL, 1);
-
- register_cpu_notifier(&uncore_cpu_nb);
-
- put_online_cpus();
-
return 0;
}
@@ -3867,6 +4234,41 @@ static int __init uncore_pmus_register(void)
return 0;
}
+static void __init uncore_cpumask_init(void)
+{
+ int cpu;
+
+ /*
+ * ony invoke once from msr or pci init code
+ */
+ if (!cpumask_empty(&uncore_cpu_mask))
+ return;
+
+ cpu_notifier_register_begin();
+
+ for_each_online_cpu(cpu) {
+ int i, phys_id = topology_physical_package_id(cpu);
+
+ for_each_cpu(i, &uncore_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i)) {
+ phys_id = -1;
+ break;
+ }
+ }
+ if (phys_id < 0)
+ continue;
+
+ uncore_cpu_prepare(cpu, phys_id);
+ uncore_event_init_cpu(cpu);
+ }
+ on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+ __register_cpu_notifier(&uncore_cpu_nb);
+
+ cpu_notifier_register_done();
+}
+
+
static int __init intel_uncore_init(void)
{
int ret;
@@ -3885,6 +4287,7 @@ static int __init intel_uncore_init(void)
uncore_pci_exit();
goto fail;
}
+ uncore_cpumask_init();
uncore_pmus_register();
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index a80ab71a883d..90236f0c94a9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -6,6 +6,7 @@
#define UNCORE_PMU_NAME_LEN 32
#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC)
+#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC)
#define UNCORE_FIXED_EVENT 0xff
#define UNCORE_PMC_IDX_MAX_GENERIC 8
@@ -440,6 +441,7 @@ struct intel_uncore_type {
struct intel_uncore_ops *ops;
struct uncore_event_desc *event_descs;
const struct attribute_group *attr_groups[4];
+ struct pmu *pmu; /* for custom pmu ops */
};
#define pmu_group attr_groups[0]
@@ -488,8 +490,11 @@ struct intel_uncore_box {
u64 tags[UNCORE_PMC_IDX_MAX];
struct pci_dev *pci_dev;
struct intel_uncore_pmu *pmu;
+ u64 hrtimer_duration; /* hrtimer timeout for this box */
struct hrtimer hrtimer;
struct list_head list;
+ struct list_head active_list;
+ void *io_addr;
struct intel_uncore_extra_reg shared_regs[0];
};
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3486e6660357..5d466b7d8609 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1257,7 +1257,24 @@ again:
pass++;
goto again;
}
-
+ /*
+ * Perf does test runs to see if a whole group can be assigned
+ * together succesfully. There can be multiple rounds of this.
+ * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config
+ * bits, such that the next round of group assignments will
+ * cause the above p4_should_swap_ts to pass instead of fail.
+ * This leads to counters exclusive to thread0 being used by
+ * thread1.
+ *
+ * Solve this with a cheap hack, reset the idx back to -1 to
+ * force a new lookup (p4_next_cntr) to get the right counter
+ * for the right thread.
+ *
+ * This probably doesn't comply with the general spirit of how
+ * perf wants to work, but P4 is special. :-(
+ */
+ if (p4_should_swap_ts(hwc->config, cpu))
+ hwc->idx = -1;
p4_pmu_swap_config_ts(hwc, cpu);
if (assign)
assign[i] = cntr_idx;
@@ -1322,6 +1339,7 @@ static __initconst const struct x86_pmu p4_pmu = {
__init int p4_pmu_init(void)
{
unsigned int low, high;
+ int i, reg;
/* If we get stripped -- indexing fails */
BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
@@ -1340,5 +1358,19 @@ __init int p4_pmu_init(void)
x86_pmu = p4_pmu;
+ /*
+ * Even though the counters are configured to interrupt a particular
+ * logical processor when an overflow happens, testing has shown that
+ * on kdump kernels (which uses a single cpu), thread1's counter
+ * continues to run and will report an NMI on thread0. Due to the
+ * overflow bug, this leads to a stream of unknown NMIs.
+ *
+ * Solve this by zero'ing out the registers to mimic a reset.
+ */
+ for (i = 0; i < x86_pmu.num_counters; i++) {
+ reg = x86_pmu_config_addr(i);
+ wrmsrl_safe(reg, 0ULL);
+ }
+
return 0;
}
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 7d9481c743f8..3225ae6c5180 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -198,14 +198,15 @@ static int __init cpuid_init(void)
goto out_chrdev;
}
cpuid_class->devnode = cpuid_devnode;
- get_online_cpus();
+
+ cpu_notifier_register_begin();
for_each_online_cpu(i) {
err = cpuid_device_create(i);
if (err != 0)
goto out_class;
}
- register_hotcpu_notifier(&cpuid_class_cpu_notifier);
- put_online_cpus();
+ __register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ cpu_notifier_register_done();
err = 0;
goto out;
@@ -215,7 +216,7 @@ out_class:
for_each_online_cpu(i) {
cpuid_device_destroy(i);
}
- put_online_cpus();
+ cpu_notifier_register_done();
class_destroy(cpuid_class);
out_chrdev:
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -227,13 +228,13 @@ static void __exit cpuid_exit(void)
{
int cpu = 0;
- get_online_cpus();
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu)
cpuid_device_destroy(cpu);
class_destroy(cpuid_class);
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
- unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
- put_online_cpus();
+ __unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ cpu_notifier_register_done();
}
module_init(cpuid_init);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a57902efe2d5..507de8066594 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -57,9 +57,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
struct pt_regs fixed_regs;
-#endif
-#ifdef CONFIG_X86_32
if (!user_mode_vm(regs)) {
crash_fixup_ss_esp(&fixed_regs, regs);
regs = &fixed_regs;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index f2a1770ca176..5abd4cd4230c 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,12 +16,35 @@
#include <asm/stacktrace.h>
+static void *is_irq_stack(void *p, void *irq)
+{
+ if (p < irq || p >= (irq + THREAD_SIZE))
+ return NULL;
+ return irq + THREAD_SIZE;
+}
+
+
+static void *is_hardirq_stack(unsigned long *stack, int cpu)
+{
+ void *irq = per_cpu(hardirq_stack, cpu);
+
+ return is_irq_stack(stack, irq);
+}
+
+static void *is_softirq_stack(unsigned long *stack, int cpu)
+{
+ void *irq = per_cpu(softirq_stack, cpu);
+
+ return is_irq_stack(stack, irq);
+}
void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
+ const unsigned cpu = get_cpu();
int graph = 0;
+ u32 *prev_esp;
if (!task)
task = current;
@@ -30,7 +53,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long dummy;
stack = &dummy;
- if (task && task != current)
+ if (task != current)
stack = (unsigned long *)task->thread.sp;
}
@@ -39,18 +62,31 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
for (;;) {
struct thread_info *context;
+ void *end_stack;
+
+ end_stack = is_hardirq_stack(stack, cpu);
+ if (!end_stack)
+ end_stack = is_softirq_stack(stack, cpu);
- context = (struct thread_info *)
- ((unsigned long)stack & (~(THREAD_SIZE - 1)));
- bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph);
+ context = task_thread_info(task);
+ bp = ops->walk_stack(context, stack, bp, ops, data,
+ end_stack, &graph);
- stack = (unsigned long *)context->previous_esp;
+ /* Stop if not on irq stack */
+ if (!end_stack)
+ break;
+
+ /* The previous esp is saved on the bottom of the stack */
+ prev_esp = (u32 *)(end_stack - THREAD_SIZE);
+ stack = (unsigned long *)*prev_esp;
if (!stack)
break;
+
if (ops->stack(data, "IRQ") < 0)
break;
touch_nmi_watchdog();
}
+ put_cpu();
}
EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..1abcb50b48ae 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -104,6 +104,44 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
return (stack >= irq_stack && stack < irq_stack_end);
}
+static const unsigned long irq_stack_size =
+ (IRQ_STACK_SIZE - 64) / sizeof(unsigned long);
+
+enum stack_type {
+ STACK_IS_UNKNOWN,
+ STACK_IS_NORMAL,
+ STACK_IS_EXCEPTION,
+ STACK_IS_IRQ,
+};
+
+static enum stack_type
+analyze_stack(int cpu, struct task_struct *task, unsigned long *stack,
+ unsigned long **stack_end, unsigned long *irq_stack,
+ unsigned *used, char **id)
+{
+ unsigned long addr;
+
+ addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+ if ((unsigned long)task_stack_page(task) == addr)
+ return STACK_IS_NORMAL;
+
+ *stack_end = in_exception_stack(cpu, (unsigned long)stack,
+ used, id);
+ if (*stack_end)
+ return STACK_IS_EXCEPTION;
+
+ if (!irq_stack)
+ return STACK_IS_NORMAL;
+
+ *stack_end = irq_stack;
+ irq_stack = irq_stack - irq_stack_size;
+
+ if (in_irq_stack(stack, irq_stack, *stack_end))
+ return STACK_IS_IRQ;
+
+ return STACK_IS_UNKNOWN;
+}
+
/*
* x86-64 can have up to three kernel stacks:
* process stack
@@ -116,12 +154,12 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- unsigned long *irq_stack_end =
- (unsigned long *)per_cpu(irq_stack_ptr, cpu);
- unsigned used = 0;
struct thread_info *tinfo;
- int graph = 0;
+ unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned long dummy;
+ unsigned used = 0;
+ int graph = 0;
+ int done = 0;
if (!task)
task = current;
@@ -143,49 +181,61 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
* exceptions
*/
tinfo = task_thread_info(task);
- for (;;) {
+ while (!done) {
+ unsigned long *stack_end;
+ enum stack_type stype;
char *id;
- unsigned long *estack_end;
- estack_end = in_exception_stack(cpu, (unsigned long)stack,
- &used, &id);
- if (estack_end) {
+ stype = analyze_stack(cpu, task, stack, &stack_end,
+ irq_stack, &used, &id);
+
+ /* Default finish unless specified to continue */
+ done = 1;
+
+ switch (stype) {
+
+ /* Break out early if we are on the thread stack */
+ case STACK_IS_NORMAL:
+ break;
+
+ case STACK_IS_EXCEPTION:
+
if (ops->stack(data, id) < 0)
break;
bp = ops->walk_stack(tinfo, stack, bp, ops,
- data, estack_end, &graph);
+ data, stack_end, &graph);
ops->stack(data, "<EOE>");
/*
* We link to the next stack via the
* second-to-last pointer (index -2 to end) in the
* exception stack:
*/
- stack = (unsigned long *) estack_end[-2];
- continue;
- }
- if (irq_stack_end) {
- unsigned long *irq_stack;
- irq_stack = irq_stack_end -
- (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
-
- if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
- if (ops->stack(data, "IRQ") < 0)
- break;
- bp = ops->walk_stack(tinfo, stack, bp,
- ops, data, irq_stack_end, &graph);
- /*
- * We link to the next stack (which would be
- * the process stack normally) the last
- * pointer (index -1 to end) in the IRQ stack:
- */
- stack = (unsigned long *) (irq_stack_end[-1]);
- irq_stack_end = NULL;
- ops->stack(data, "EOI");
- continue;
- }
+ stack = (unsigned long *) stack_end[-2];
+ done = 0;
+ break;
+
+ case STACK_IS_IRQ:
+
+ if (ops->stack(data, "IRQ") < 0)
+ break;
+ bp = ops->walk_stack(tinfo, stack, bp,
+ ops, data, stack_end, &graph);
+ /*
+ * We link to the next stack (which would be
+ * the process stack normally) the last
+ * pointer (index -1 to end) in the IRQ stack:
+ */
+ stack = (unsigned long *) (stack_end[-1]);
+ irq_stack = NULL;
+ ops->stack(data, "EOI");
+ done = 0;
+ break;
+
+ case STACK_IS_UNKNOWN:
+ ops->stack(data, "UNK");
+ break;
}
- break;
}
/*
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bc4a088f9023..6e2537c32190 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
/*
- * Revision 13 of all triggering devices id in this quirk have
- * a problem draining interrupts when irq remapping is enabled,
- * and should be flagged as broken. Additionally revisions 0x12
- * and 0x22 of device id 0x3405 has this problem.
+ * Revision <= 13 of all triggering devices id in this quirk
+ * have a problem draining interrupts when irq remapping is
+ * enabled, and should be flagged as broken. Additionally
+ * revision 0x22 of device id 0x3405 has this problem.
*/
- if (revision == 0x13)
+ if (revision <= 0x13)
set_irq_remapping_broken();
- else if ((device == 0x3405) &&
- ((revision == 0x12) ||
- (revision == 0x22)))
+ else if (device == 0x3405 && revision == 0x22)
set_irq_remapping_broken();
-
}
/*
@@ -228,7 +225,7 @@ static void __init intel_remapping_check(int num, int slot, int func)
*
* And yes, so far on current devices the base addr is always under 4G.
*/
-static u32 __init intel_stolen_base(int num, int slot, int func)
+static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_size)
{
u32 base;
@@ -243,10 +240,118 @@ static u32 __init intel_stolen_base(int num, int slot, int func)
return base;
}
-#define KB(x) ((x) * 1024)
+#define KB(x) ((x) * 1024UL)
#define MB(x) (KB (KB (x)))
#define GB(x) (MB (KB (x)))
+static size_t __init i830_tseg_size(void)
+{
+ u8 tmp = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
+
+ if (!(tmp & TSEG_ENABLE))
+ return 0;
+
+ if (tmp & I830_TSEG_SIZE_1M)
+ return MB(1);
+ else
+ return KB(512);
+}
+
+static size_t __init i845_tseg_size(void)
+{
+ u8 tmp = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
+
+ if (!(tmp & TSEG_ENABLE))
+ return 0;
+
+ switch (tmp & I845_TSEG_SIZE_MASK) {
+ case I845_TSEG_SIZE_512K:
+ return KB(512);
+ case I845_TSEG_SIZE_1M:
+ return MB(1);
+ default:
+ WARN_ON(1);
+ return 0;
+ }
+}
+
+static size_t __init i85x_tseg_size(void)
+{
+ u8 tmp = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
+
+ if (!(tmp & TSEG_ENABLE))
+ return 0;
+
+ return MB(1);
+}
+
+static size_t __init i830_mem_size(void)
+{
+ return read_pci_config_byte(0, 0, 0, I830_DRB3) * MB(32);
+}
+
+static size_t __init i85x_mem_size(void)
+{
+ return read_pci_config_byte(0, 0, 1, I85X_DRB3) * MB(32);
+}
+
+/*
+ * On 830/845/85x the stolen memory base isn't available in any
+ * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
+ */
+static u32 __init i830_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+ return i830_mem_size() - i830_tseg_size() - stolen_size;
+}
+
+static u32 __init i845_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+ return i830_mem_size() - i845_tseg_size() - stolen_size;
+}
+
+static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+ return i85x_mem_size() - i85x_tseg_size() - stolen_size;
+}
+
+static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+ /*
+ * FIXME is the graphics stolen memory region
+ * always at TOUD? Ie. is it always the last
+ * one to be allocated by the BIOS?
+ */
+ return read_pci_config_16(0, 0, 0, I865_TOUD) << 16;
+}
+
+static size_t __init i830_stolen_size(int num, int slot, int func)
+{
+ size_t stolen_size;
+ u16 gmch_ctrl;
+
+ gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
+
+ switch (gmch_ctrl & I830_GMCH_GMS_MASK) {
+ case I830_GMCH_GMS_STOLEN_512:
+ stolen_size = KB(512);
+ break;
+ case I830_GMCH_GMS_STOLEN_1024:
+ stolen_size = MB(1);
+ break;
+ case I830_GMCH_GMS_STOLEN_8192:
+ stolen_size = MB(8);
+ break;
+ case I830_GMCH_GMS_LOCAL:
+ /* local memory isn't part of the normal address space */
+ stolen_size = 0;
+ break;
+ default:
+ return 0;
+ }
+
+ return stolen_size;
+}
+
static size_t __init gen3_stolen_size(int num, int slot, int func)
{
size_t stolen_size;
@@ -313,7 +418,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
return gmch_ctrl << 25; /* 32 MB units */
}
-static inline size_t gen8_stolen_size(int num, int slot, int func)
+static size_t gen8_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
@@ -323,31 +428,74 @@ static inline size_t gen8_stolen_size(int num, int slot, int func)
return gmch_ctrl << 25; /* 32 MB units */
}
-typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+
+struct intel_stolen_funcs {
+ size_t (*size)(int num, int slot, int func);
+ u32 (*base)(int num, int slot, int func, size_t size);
+};
+
+static const struct intel_stolen_funcs i830_stolen_funcs = {
+ .base = i830_stolen_base,
+ .size = i830_stolen_size,
+};
+
+static const struct intel_stolen_funcs i845_stolen_funcs = {
+ .base = i845_stolen_base,
+ .size = i830_stolen_size,
+};
+
+static const struct intel_stolen_funcs i85x_stolen_funcs = {
+ .base = i85x_stolen_base,
+ .size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs i865_stolen_funcs = {
+ .base = i865_stolen_base,
+ .size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen3_stolen_funcs = {
+ .base = intel_stolen_base,
+ .size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen6_stolen_funcs = {
+ .base = intel_stolen_base,
+ .size = gen6_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen8_stolen_funcs = {
+ .base = intel_stolen_base,
+ .size = gen8_stolen_size,
+};
static struct pci_device_id intel_stolen_ids[] __initdata = {
- INTEL_I915G_IDS(gen3_stolen_size),
- INTEL_I915GM_IDS(gen3_stolen_size),
- INTEL_I945G_IDS(gen3_stolen_size),
- INTEL_I945GM_IDS(gen3_stolen_size),
- INTEL_VLV_M_IDS(gen6_stolen_size),
- INTEL_VLV_D_IDS(gen6_stolen_size),
- INTEL_PINEVIEW_IDS(gen3_stolen_size),
- INTEL_I965G_IDS(gen3_stolen_size),
- INTEL_G33_IDS(gen3_stolen_size),
- INTEL_I965GM_IDS(gen3_stolen_size),
- INTEL_GM45_IDS(gen3_stolen_size),
- INTEL_G45_IDS(gen3_stolen_size),
- INTEL_IRONLAKE_D_IDS(gen3_stolen_size),
- INTEL_IRONLAKE_M_IDS(gen3_stolen_size),
- INTEL_SNB_D_IDS(gen6_stolen_size),
- INTEL_SNB_M_IDS(gen6_stolen_size),
- INTEL_IVB_M_IDS(gen6_stolen_size),
- INTEL_IVB_D_IDS(gen6_stolen_size),
- INTEL_HSW_D_IDS(gen6_stolen_size),
- INTEL_HSW_M_IDS(gen6_stolen_size),
- INTEL_BDW_M_IDS(gen8_stolen_size),
- INTEL_BDW_D_IDS(gen8_stolen_size)
+ INTEL_I830_IDS(&i830_stolen_funcs),
+ INTEL_I845G_IDS(&i845_stolen_funcs),
+ INTEL_I85X_IDS(&i85x_stolen_funcs),
+ INTEL_I865G_IDS(&i865_stolen_funcs),
+ INTEL_I915G_IDS(&gen3_stolen_funcs),
+ INTEL_I915GM_IDS(&gen3_stolen_funcs),
+ INTEL_I945G_IDS(&gen3_stolen_funcs),
+ INTEL_I945GM_IDS(&gen3_stolen_funcs),
+ INTEL_VLV_M_IDS(&gen6_stolen_funcs),
+ INTEL_VLV_D_IDS(&gen6_stolen_funcs),
+ INTEL_PINEVIEW_IDS(&gen3_stolen_funcs),
+ INTEL_I965G_IDS(&gen3_stolen_funcs),
+ INTEL_G33_IDS(&gen3_stolen_funcs),
+ INTEL_I965GM_IDS(&gen3_stolen_funcs),
+ INTEL_GM45_IDS(&gen3_stolen_funcs),
+ INTEL_G45_IDS(&gen3_stolen_funcs),
+ INTEL_IRONLAKE_D_IDS(&gen3_stolen_funcs),
+ INTEL_IRONLAKE_M_IDS(&gen3_stolen_funcs),
+ INTEL_SNB_D_IDS(&gen6_stolen_funcs),
+ INTEL_SNB_M_IDS(&gen6_stolen_funcs),
+ INTEL_IVB_M_IDS(&gen6_stolen_funcs),
+ INTEL_IVB_D_IDS(&gen6_stolen_funcs),
+ INTEL_HSW_D_IDS(&gen6_stolen_funcs),
+ INTEL_HSW_M_IDS(&gen6_stolen_funcs),
+ INTEL_BDW_M_IDS(&gen8_stolen_funcs),
+ INTEL_BDW_D_IDS(&gen8_stolen_funcs)
};
static void __init intel_graphics_stolen(int num, int slot, int func)
@@ -364,11 +512,13 @@ static void __init intel_graphics_stolen(int num, int slot, int func)
for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) {
if (intel_stolen_ids[i].device == device) {
- stolen_size_fn stolen_size =
- (stolen_size_fn)intel_stolen_ids[i].driver_data;
- size = stolen_size(num, slot, func);
- start = intel_stolen_base(num, slot, func);
+ const struct intel_stolen_funcs *stolen_funcs =
+ (const struct intel_stolen_funcs *)intel_stolen_ids[i].driver_data;
+ size = stolen_funcs->size(num, slot, func);
+ start = stolen_funcs->base(num, slot, func, size);
if (size && start) {
+ printk(KERN_INFO "Reserving Intel graphics stolen memory at 0x%x-0x%x\n",
+ start, start + (u32)size - 1);
/* Mark this space as reserved */
e820_add_region(start, size, E820_RESERVED);
sanitize_e820_map(e820.map,
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index e6253195a301..52819e816f87 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -308,7 +308,10 @@ static int ftrace_write(unsigned long ip, const char *val, int size)
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
ip = (unsigned long)__va(__pa_symbol(ip));
- return probe_kernel_write((void *)ip, val, size);
+ if (probe_kernel_write((void *)ip, val, size))
+ return -EPERM;
+
+ return 0;
}
static int add_break(unsigned long ip, const char *old)
@@ -323,10 +326,7 @@ static int add_break(unsigned long ip, const char *old)
if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
return -EINVAL;
- if (ftrace_write(ip, &brk, 1))
- return -EPERM;
-
- return 0;
+ return ftrace_write(ip, &brk, 1);
}
static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -425,7 +425,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
/* If this does not have a breakpoint, we are done */
if (ins[0] != brk)
- return -1;
+ return 0;
nop = ftrace_nop_replace();
@@ -455,7 +455,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
}
update:
- return probe_kernel_write((void *)ip, &nop[0], 1);
+ return ftrace_write(ip, nop, 1);
}
static int add_update_code(unsigned long ip, unsigned const char *new)
@@ -463,9 +463,7 @@ static int add_update_code(unsigned long ip, unsigned const char *new)
/* skip breakpoint */
ip++;
new++;
- if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
- return -EPERM;
- return 0;
+ return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
}
static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -520,10 +518,7 @@ static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
new = ftrace_call_replace(ip, addr);
- if (ftrace_write(ip, new, 1))
- return -EPERM;
-
- return 0;
+ return ftrace_write(ip, new, 1);
}
static int finish_update_nop(struct dyn_ftrace *rec)
@@ -533,9 +528,7 @@ static int finish_update_nop(struct dyn_ftrace *rec)
new = ftrace_nop_replace();
- if (ftrace_write(ip, new, 1))
- return -EPERM;
- return 0;
+ return ftrace_write(ip, new, 1);
}
static int finish_update(struct dyn_ftrace *rec, int enable)
@@ -632,8 +625,14 @@ void ftrace_replace_code(int enable)
printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
for_ftrace_rec_iter(iter) {
rec = ftrace_rec_iter_record(iter);
- remove_breakpoint(rec);
+ /*
+ * Breakpoints are handled only when this function is in
+ * progress. The system could not work with them.
+ */
+ if (remove_breakpoint(rec))
+ BUG();
}
+ run_sync();
}
static int
@@ -655,16 +654,19 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
run_sync();
ret = ftrace_write(ip, new_code, 1);
- if (ret) {
- ret = -EPERM;
- goto out;
- }
- run_sync();
+ /*
+ * The breakpoint is handled only when this function is in progress.
+ * The system could not work if we could not remove it.
+ */
+ BUG_ON(ret);
out:
+ run_sync();
return ret;
fail_update:
- probe_kernel_write((void *)ip, &old_code[0], 1);
+ /* Also here the system could not work with the breakpoint */
+ if (ftrace_write(ip, old_code, 1))
+ BUG();
goto out;
}
@@ -678,11 +680,8 @@ void arch_ftrace_update_code(int command)
atomic_dec(&modifying_ftrace_code);
}
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
{
- /* The return code is retured via data */
- *(unsigned long *)data = 0;
-
return 0;
}
#endif
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba27679f18..f36bd42d6f0c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
/* This is global to keep gas from relaxing the jumps */
ENTRY(early_idt_handler)
cld
+
+ cmpl $2,(%esp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,%ss:early_recursion_flag
je hlt_loop
incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
pop %edx
pop %ecx
pop %eax
- addl $8,%esp /* drop vector number and error code */
decl %ss:early_recursion_flag
+is_nmi:
+ addl $8,%esp /* drop vector number and error code */
iret
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb314c8..a468c0a65c42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
ENTRY(early_idt_handler)
cld
+ cmpl $2,(%rsp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,early_recursion_flag(%rip)
jz 1f
incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
popq %rdx
popq %rcx
popq %rax
- addq $16,%rsp # drop vector number and error code
decl early_recursion_flag(%rip)
+is_nmi:
+ addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index da85a8e830a1..8d80ae011603 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -521,7 +521,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
{
if (request_irq(dev->irq, hpet_interrupt_handler,
- IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+ IRQF_TIMER | IRQF_NOBALANCING,
dev->name, dev))
return -1;
@@ -699,7 +699,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
/* FIXME: add schedule_work_on() */
schedule_delayed_work_on(cpu, &work.work, 0);
wait_for_completion(&work.complete);
- destroy_timer_on_stack(&work.work.timer);
+ destroy_delayed_work_on_stack(&work.work);
break;
case CPU_DEAD:
if (hdev) {
@@ -752,9 +752,7 @@ static struct clocksource clocksource_hpet = {
.mask = HPET_MASK,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.resume = hpet_resume_counter,
-#ifdef CONFIG_X86_64
.archdata = { .vclock_mode = VCLOCK_HPET },
-#endif
};
static int hpet_clocksource_register(void)
@@ -943,12 +941,14 @@ static __init int hpet_late_init(void)
if (boot_cpu_has(X86_FEATURE_ARAT))
return 0;
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu) {
hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
}
/* This notifier should be called after workqueue is ready */
- hotcpu_notifier(hpet_cpuhp_notify, -20);
+ __hotcpu_notifier(hpet_cpuhp_notify, -20);
+ cpu_notifier_register_done();
return 0;
}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6dd2a2..d5dd80814419 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
void __kernel_fpu_end(void)
{
- if (use_eager_fpu())
- math_state_restore();
- else
+ if (use_eager_fpu()) {
+ /*
+ * For eager fpu, most the time, tsk_used_math() is true.
+ * Restore the user math as we are done with the kernel usage.
+ * At few instances during thread exit, signal handling etc,
+ * tsk_used_math() is false. Those few places will take proper
+ * actions, so we don't need to restore the math here.
+ */
+ if (likely(tsk_used_math(current)))
+ math_state_restore();
+ } else {
stts();
+ }
}
EXPORT_SYMBOL(__kernel_fpu_end);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index d99f31d9a750..283a76a9cc40 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -125,6 +125,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
seq_printf(p, " Machine check polls\n");
#endif
+#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
+ seq_printf(p, "%*s: ", prec, "THR");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
+ seq_printf(p, " Hypervisor callback interrupts\n");
+#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index d7fcbedc9c43..63ce838e5a54 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -55,16 +55,8 @@ static inline int check_stack_overflow(void) { return 0; }
static inline void print_stack_overflow(void) { }
#endif
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
- struct thread_info tinfo;
- u32 stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(THREAD_SIZE)));
-
-static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
static void call_on_stack(void *func, void *stack)
{
@@ -77,14 +69,26 @@ static void call_on_stack(void *func, void *stack)
: "memory", "cc", "edx", "ecx", "eax");
}
+/* how to get the current stack pointer from C */
+#define current_stack_pointer ({ \
+ unsigned long sp; \
+ asm("mov %%esp,%0" : "=g" (sp)); \
+ sp; \
+})
+
+static inline void *current_stack(void)
+{
+ return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
static inline int
execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
{
- union irq_ctx *curctx, *irqctx;
- u32 *isp, arg1, arg2;
+ struct irq_stack *curstk, *irqstk;
+ u32 *isp, *prev_esp, arg1, arg2;
- curctx = (union irq_ctx *) current_thread_info();
- irqctx = __this_cpu_read(hardirq_ctx);
+ curstk = (struct irq_stack *) current_stack();
+ irqstk = __this_cpu_read(hardirq_stack);
/*
* this is where we switch to the IRQ stack. However, if we are
@@ -92,13 +96,14 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
* handler) we can't do that and just have to keep using the
* current stack (which is the irq stack already after all)
*/
- if (unlikely(curctx == irqctx))
+ if (unlikely(curstk == irqstk))
return 0;
- /* build the stack frame on the IRQ stack */
- isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
- irqctx->tinfo.task = curctx->tinfo.task;
- irqctx->tinfo.previous_esp = current_stack_pointer;
+ isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+ /* Save the next esp at the bottom of the stack */
+ prev_esp = (u32 *)irqstk;
+ *prev_esp = current_stack_pointer;
if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
@@ -118,46 +123,40 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
*/
void irq_ctx_init(int cpu)
{
- union irq_ctx *irqctx;
+ struct irq_stack *irqstk;
- if (per_cpu(hardirq_ctx, cpu))
+ if (per_cpu(hardirq_stack, cpu))
return;
- irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+ irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
THREADINFO_GFP,
THREAD_SIZE_ORDER));
- memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
- irqctx->tinfo.cpu = cpu;
- irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
-
- per_cpu(hardirq_ctx, cpu) = irqctx;
+ per_cpu(hardirq_stack, cpu) = irqstk;
- irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+ irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
THREADINFO_GFP,
THREAD_SIZE_ORDER));
- memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
- irqctx->tinfo.cpu = cpu;
- irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
-
- per_cpu(softirq_ctx, cpu) = irqctx;
+ per_cpu(softirq_stack, cpu) = irqstk;
printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
- cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu));
+ cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu));
}
void do_softirq_own_stack(void)
{
- struct thread_info *curctx;
- union irq_ctx *irqctx;
- u32 *isp;
+ struct thread_info *curstk;
+ struct irq_stack *irqstk;
+ u32 *isp, *prev_esp;
- curctx = current_thread_info();
- irqctx = __this_cpu_read(softirq_ctx);
- irqctx->tinfo.task = curctx->task;
- irqctx->tinfo.previous_esp = current_stack_pointer;
+ curstk = current_stack();
+ irqstk = __this_cpu_read(softirq_stack);
/* build the stack frame on the softirq stack */
- isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+ isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+ /* Push the previous esp onto the stack */
+ prev_esp = (u32 *)irqstk;
+ *prev_esp = current_stack_pointer;
call_on_stack(__do_softirq, isp);
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 79a3f9682871..61b17dc2c277 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -897,9 +897,10 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- switch (kcb->kprobe_status) {
- case KPROBE_HIT_SS:
- case KPROBE_REENTER:
+ if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) {
+ /* This must happen on single-stepping */
+ WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS &&
+ kcb->kprobe_status != KPROBE_REENTER);
/*
* We are here because the instruction being single
* stepped caused a page fault. We reset the current
@@ -914,9 +915,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
else
reset_current_kprobe();
preempt_enable_no_resched();
- break;
- case KPROBE_HIT_ACTIVE:
- case KPROBE_HIT_SSDONE:
+ } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
+ kcb->kprobe_status == KPROBE_HIT_SSDONE) {
/*
* We increment the nmissed count for accounting,
* we can also use npre/npostfault count for accounting
@@ -945,10 +945,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
* fixup routine could not handle it,
* Let do_page_fault() fix it.
*/
- break;
- default:
- break;
}
+
return 0;
}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 713f1b3bad52..0331cb389d68 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -417,7 +417,6 @@ void kvm_disable_steal_time(void)
#ifdef CONFIG_SMP
static void __init kvm_smp_prepare_boot_cpu(void)
{
- WARN_ON(kvm_register_clock("primary cpu clock"));
kvm_guest_cpu_init();
native_smp_prepare_boot_cpu();
kvm_spinlock_init();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index e6041094ff26..d9156ceecdff 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -242,7 +242,7 @@ void __init kvmclock_init(void)
hv_clock = __va(mem);
memset(hv_clock, 0, size);
- if (kvm_register_clock("boot clock")) {
+ if (kvm_register_clock("primary cpu clock")) {
hv_clock = NULL;
memblock_free(mem, size);
return;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc987398923..af1d14a9ebda 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,17 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
}
}
+ /*
+ * On x86-64 we do not support 16-bit segments due to
+ * IRET leaking the high bits of the kernel stack address.
+ */
+#ifdef CONFIG_X86_64
+ if (!ldt_info.seg_32bit) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+#endif
+
fill_ldt(&ldt, &ldt_info);
if (oldmode)
ldt.avl = 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc160696f..679cef0791cd 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_SYMBOL(node_data);
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
#endif
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+ (unsigned long)&_text - __START_KERNEL);
}
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 18be189368bb..e69f9882bf95 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -28,6 +28,7 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/jump_label.h>
+#include <linux/random.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -43,13 +44,52 @@ do { \
} while (0)
#endif
+#ifdef CONFIG_RANDOMIZE_BASE
+static unsigned long module_load_offset;
+static int randomize_modules = 1;
+
+/* Mutex protects the module_load_offset. */
+static DEFINE_MUTEX(module_kaslr_mutex);
+
+static int __init parse_nokaslr(char *p)
+{
+ randomize_modules = 0;
+ return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
+static unsigned long int get_module_load_offset(void)
+{
+ if (randomize_modules) {
+ mutex_lock(&module_kaslr_mutex);
+ /*
+ * Calculate the module_load_offset the first time this
+ * code is called. Once calculated it stays the same until
+ * reboot.
+ */
+ if (module_load_offset == 0)
+ module_load_offset =
+ (get_random_int() % 1024 + 1) * PAGE_SIZE;
+ mutex_unlock(&module_kaslr_mutex);
+ }
+ return module_load_offset;
+}
+#else
+static unsigned long int get_module_load_offset(void)
+{
+ return 0;
+}
+#endif
+
void *module_alloc(unsigned long size)
{
if (PAGE_ALIGN(size) > MODULES_LEN)
return NULL;
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
- GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
- NUMA_NO_NODE, __builtin_return_address(0));
+ return __vmalloc_node_range(size, 1,
+ MODULES_VADDR + get_module_load_offset(),
+ MODULES_END, GFP_KERNEL | __GFP_HIGHMEM,
+ PAGE_KERNEL_EXEC, NUMA_NO_NODE,
+ __builtin_return_address(0));
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 05266b5aae22..c9603ac80de5 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -259,14 +259,15 @@ static int __init msr_init(void)
goto out_chrdev;
}
msr_class->devnode = msr_devnode;
- get_online_cpus();
+
+ cpu_notifier_register_begin();
for_each_online_cpu(i) {
err = msr_device_create(i);
if (err != 0)
goto out_class;
}
- register_hotcpu_notifier(&msr_class_cpu_notifier);
- put_online_cpus();
+ __register_hotcpu_notifier(&msr_class_cpu_notifier);
+ cpu_notifier_register_done();
err = 0;
goto out;
@@ -275,7 +276,7 @@ out_class:
i = 0;
for_each_online_cpu(i)
msr_device_destroy(i);
- put_online_cpus();
+ cpu_notifier_register_done();
class_destroy(msr_class);
out_chrdev:
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -286,13 +287,14 @@ out:
static void __exit msr_exit(void)
{
int cpu = 0;
- get_online_cpus();
+
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu)
msr_device_destroy(cpu);
class_destroy(msr_class);
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
- unregister_hotcpu_notifier(&msr_class_cpu_notifier);
- put_online_cpus();
+ __unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+ cpu_notifier_register_done();
}
module_init(msr_init);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6fcb49ce50a1..b4872b999a71 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -87,6 +87,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
#define nmi_to_desc(type) (&nmi_desc[type])
static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+
static int __init nmi_warning_debugfs(void)
{
debugfs_create_u64("nmi_longest_ns", 0644,
@@ -95,6 +96,20 @@ static int __init nmi_warning_debugfs(void)
}
fs_initcall(nmi_warning_debugfs);
+static void nmi_max_handler(struct irq_work *w)
+{
+ struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
+ int remainder_ns, decimal_msecs;
+ u64 whole_msecs = ACCESS_ONCE(a->max_duration);
+
+ remainder_ns = do_div(whole_msecs, (1000 * 1000));
+ decimal_msecs = remainder_ns / 1000;
+
+ printk_ratelimited(KERN_INFO
+ "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+ a->handler, whole_msecs, decimal_msecs);
+}
+
static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
{
struct nmi_desc *desc = nmi_to_desc(type);
@@ -110,26 +125,20 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
* to handle those situations.
*/
list_for_each_entry_rcu(a, &desc->head, list) {
- u64 before, delta, whole_msecs;
- int remainder_ns, decimal_msecs, thishandled;
+ int thishandled;
+ u64 delta;
- before = sched_clock();
+ delta = sched_clock();
thishandled = a->handler(type, regs);
handled += thishandled;
- delta = sched_clock() - before;
+ delta = sched_clock() - delta;
trace_nmi_handler(a->handler, (int)delta, thishandled);
- if (delta < nmi_longest_ns)
+ if (delta < nmi_longest_ns || delta < a->max_duration)
continue;
- nmi_longest_ns = delta;
- whole_msecs = delta;
- remainder_ns = do_div(whole_msecs, (1000 * 1000));
- decimal_msecs = remainder_ns / 1000;
- printk_ratelimited(KERN_INFO
- "INFO: NMI handler (%ps) took too long to run: "
- "%lld.%03d msecs\n", a->handler, whole_msecs,
- decimal_msecs);
+ a->max_duration = delta;
+ irq_work_queue(&a->irq_work);
}
rcu_read_unlock();
@@ -146,6 +155,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
if (!action->handler)
return -EINVAL;
+ init_irq_work(&action->irq_work, nmi_max_handler);
+
spin_lock_irqsave(&desc->lock, flags);
/*
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 299d49302e7d..0497f719977d 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1207,23 +1207,31 @@ error:
return ret;
}
-static inline int __init determine_tce_table_size(u64 ram)
+static inline int __init determine_tce_table_size(void)
{
int ret;
if (specified_table_size != TCE_TABLE_SIZE_UNSPECIFIED)
return specified_table_size;
- /*
- * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to
- * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each
- * larger table size has twice as many entries, so shift the
- * max ram address by 13 to divide by 8K and then look at the
- * order of the result to choose between 0-7.
- */
- ret = get_order(ram >> 13);
- if (ret > TCE_TABLE_SIZE_8M)
+ if (is_kdump_kernel() && saved_max_pfn) {
+ /*
+ * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to
+ * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each
+ * larger table size has twice as many entries, so shift the
+ * max ram address by 13 to divide by 8K and then look at the
+ * order of the result to choose between 0-7.
+ */
+ ret = get_order((saved_max_pfn * PAGE_SIZE) >> 13);
+ if (ret > TCE_TABLE_SIZE_8M)
+ ret = TCE_TABLE_SIZE_8M;
+ } else {
+ /*
+ * Use 8M by default (suggested by Muli) if it's not
+ * kdump kernel and saved_max_pfn isn't set.
+ */
ret = TCE_TABLE_SIZE_8M;
+ }
return ret;
}
@@ -1418,8 +1426,7 @@ int __init detect_calgary(void)
return -ENOMEM;
}
- specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
- saved_max_pfn : max_pfn) * PAGE_SIZE);
+ specified_table_size = determine_tce_table_size();
for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
struct calgary_bus_info *info = &bus_info[bus];
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3fb8d95ab8b5..4505e2a950d8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -298,10 +298,7 @@ void arch_cpu_idle_dead(void)
*/
void arch_cpu_idle(void)
{
- if (cpuidle_idle_call())
- x86_idle();
- else
- local_irq_enable();
+ x86_idle();
}
/*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0de43e98ce08..7bc86bbe7485 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -314,6 +314,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
*/
arch_end_context_switch(next_p);
+ this_cpu_write(kernel_stack,
+ (unsigned long)task_stack_page(next_p) +
+ THREAD_SIZE - KERNEL_STACK_OFFSET);
+
/*
* Restore %gs if needed (which is common)
*/
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 7461f50d5bb1..678c0ada3b3c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -184,14 +184,14 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs)
{
unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
unsigned long sp = (unsigned long)&regs->sp;
- struct thread_info *tinfo;
+ u32 *prev_esp;
if (context == (sp & ~(THREAD_SIZE - 1)))
return sp;
- tinfo = (struct thread_info *)context;
- if (tinfo->previous_esp)
- return tinfo->previous_esp;
+ prev_esp = (u32 *)(context);
+ if (prev_esp)
+ return (unsigned long)prev_esp;
return (unsigned long)regs;
}
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4b8995..ff898bbf579d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
return;
pci_read_config_dword(nb_ht, 0x60, &val);
- node = val & 7;
+ node = pcibus_to_node(dev->bus) | (val & 7);
/*
* Some hardware may return an invalid node ID,
* so check it first:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c752cb43e52f..3399d3a99730 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -114,8 +114,8 @@ EXPORT_SYMBOL(machine_real_restart);
*/
static int __init set_pci_reboot(const struct dmi_system_id *d)
{
- if (reboot_type != BOOT_CF9) {
- reboot_type = BOOT_CF9;
+ if (reboot_type != BOOT_CF9_FORCE) {
+ reboot_type = BOOT_CF9_FORCE;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
d->ident, "PCI");
}
@@ -458,17 +458,23 @@ void __attribute__((weak)) mach_reboot_fixups(void)
}
/*
- * Windows compatible x86 hardware expects the following on reboot:
+ * To the best of our knowledge Windows compatible x86 hardware expects
+ * the following on reboot:
*
* 1) If the FADT has the ACPI reboot register flag set, try it
* 2) If still alive, write to the keyboard controller
* 3) If still alive, write to the ACPI reboot register again
* 4) If still alive, write to the keyboard controller again
+ * 5) If still alive, call the EFI runtime service to reboot
+ * 6) If no EFI runtime service, call the BIOS to do a reboot
*
- * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (4) we'll
- * try to force a triple fault and then cycle between hitting the keyboard
- * controller and doing that
+ * We default to following the same pattern. We also have
+ * two other reboot methods: 'triple fault' and 'PCI', which
+ * can be triggered via the reboot= kernel boot option or
+ * via quirks.
+ *
+ * This means that this function can never return, it can misbehave
+ * by not rebooting properly and hanging.
*/
static void native_machine_emergency_restart(void)
{
@@ -489,6 +495,11 @@ static void native_machine_emergency_restart(void)
for (;;) {
/* Could also try the reset bit in the Hammer NB */
switch (reboot_type) {
+ case BOOT_ACPI:
+ acpi_reboot();
+ reboot_type = BOOT_KBD;
+ break;
+
case BOOT_KBD:
mach_reboot_fixups(); /* For board specific fixups */
@@ -502,45 +513,33 @@ static void native_machine_emergency_restart(void)
attempt = 1;
reboot_type = BOOT_ACPI;
} else {
- reboot_type = BOOT_TRIPLE;
+ reboot_type = BOOT_EFI;
}
break;
- case BOOT_TRIPLE:
- load_idt(&no_idt);
- __asm__ __volatile__("int3");
-
- reboot_type = BOOT_KBD;
- break;
-
- case BOOT_BIOS:
- machine_real_restart(MRR_BIOS);
-
- reboot_type = BOOT_KBD;
- break;
-
- case BOOT_ACPI:
- acpi_reboot();
- reboot_type = BOOT_KBD;
- break;
-
case BOOT_EFI:
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
- reboot_type = BOOT_KBD;
+ reboot_type = BOOT_BIOS;
+ break;
+
+ case BOOT_BIOS:
+ machine_real_restart(MRR_BIOS);
+
+ /* We're probably dead after this, but... */
+ reboot_type = BOOT_CF9_SAFE;
break;
- case BOOT_CF9:
+ case BOOT_CF9_FORCE:
port_cf9_safe = true;
/* Fall through */
- case BOOT_CF9_COND:
+ case BOOT_CF9_SAFE:
if (port_cf9_safe) {
- u8 reboot_code = reboot_mode == REBOOT_WARM ?
- 0x06 : 0x0E;
+ u8 reboot_code = reboot_mode == REBOOT_WARM ? 0x06 : 0x0E;
u8 cf9 = inb(0xcf9) & ~reboot_code;
outb(cf9|2, 0xcf9); /* Request hard reset */
udelay(50);
@@ -548,6 +547,14 @@ static void native_machine_emergency_restart(void)
outb(cf9|reboot_code, 0xcf9);
udelay(50);
}
+ reboot_type = BOOT_TRIPLE;
+ break;
+
+ case BOOT_TRIPLE:
+ load_idt(&no_idt);
+ __asm__ __volatile__("int3");
+
+ /* We're probably dead after this, but... */
reboot_type = BOOT_KBD;
break;
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..09c76d265550 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -869,7 +869,6 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
- visws_early_detect();
/*
* copy kernel address range established so far and switch
@@ -926,11 +925,11 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL32", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL64", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
- set_bit(EFI_64BIT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
+ set_bit(EFI_64BIT, &efi.flags);
}
if (efi_enabled(EFI_BOOT))
@@ -1239,14 +1238,8 @@ void __init setup_arch(char **cmdline_p)
register_refined_jiffies(CLOCK_TICK_RATE);
#ifdef CONFIG_EFI
- /* Once setup is done above, unmap the EFI memory map on
- * mismatched firmware/kernel archtectures since there is no
- * support for runtime services.
- */
- if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
- pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
- efi_unmap_memmap();
- }
+ if (efi_enabled(EFI_BOOT))
+ efi_apply_memmap_quirks();
#endif
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a32da804252e..34826934d4a7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -122,8 +122,9 @@ static void smp_callin(void)
* Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
*/
cpuid = smp_processor_id();
- if (apic->wait_for_init_deassert && cpuid != 0)
- apic->wait_for_init_deassert(&init_deasserted);
+ if (apic->wait_for_init_deassert && cpuid)
+ while (!atomic_read(&init_deasserted))
+ cpu_relax();
/*
* (This works even if the APIC is not enabled.)
@@ -701,11 +702,15 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
int id;
int boot_error;
+ preempt_disable();
+
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
- if (cpu)
- return wakeup_secondary_cpu_via_init(apicid, start_ip);
+ if (cpu) {
+ boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+ goto out;
+ }
/*
* Wake up BSP by nmi.
@@ -725,6 +730,9 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
}
+out:
+ preempt_enable();
+
return boot_error;
}
@@ -758,10 +766,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
#else
clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
+#endif
per_cpu(kernel_stack, cpu) =
(unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
-#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
stack_start = idle->thread.sp;
@@ -1379,7 +1387,7 @@ static inline void mwait_play_dead(void)
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
- if (!this_cpu_has(X86_FEATURE_CLFLSH))
+ if (!this_cpu_has(X86_FEATURE_CLFLUSH))
return;
if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
return;
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 24d3c91e9812..bf7ef5ce29df 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
#include <asm/time.h>
#ifdef CONFIG_X86_64
-DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
+__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
#endif
unsigned long profile_pc(struct pt_regs *regs)
@@ -62,7 +62,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
static struct irqaction irq0 = {
.handler = timer_interrupt,
- .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
+ .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
.name = "timer"
};
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfbe99f88830..57e5ce126d5a 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -914,8 +914,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
tsc_khz_ref = tsc_khz;
}
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
- (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
- (val == CPUFREQ_RESUMECHANGE)) {
+ (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
*lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
@@ -985,9 +984,7 @@ static struct clocksource clocksource_tsc = {
.mask = CLOCKSOURCE_MASK(64),
.flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
-#ifdef CONFIG_X86_64
.archdata = { .vclock_mode = VCLOCK_TSC },
-#endif
};
void mark_tsc_unstable(char *reason)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index da6b35a98260..49edf2dd3613 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -147,7 +147,6 @@ SECTIONS
_edata = .;
} :data
-#ifdef CONFIG_X86_64
. = ALIGN(PAGE_SIZE);
__vvar_page = .;
@@ -165,12 +164,15 @@ SECTIONS
#undef __VVAR_KERNEL_LDS
#undef EMIT_VVAR
+ /*
+ * Pad the rest of the page with zeros. Otherwise the loader
+ * can leave garbage here.
+ */
+ . = __vvar_beginning_hack + PAGE_SIZE;
} :data
. = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
-#endif /* CONFIG_X86_64 */
-
/* Init code and data - will be freed after init */
. = ALIGN(PAGE_SIZE);
.init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f9347ed9..8b3b3eb3cead 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -47,14 +47,12 @@
#include <asm/segment.h>
#include <asm/desc.h>
#include <asm/topology.h>
-#include <asm/vgtod.h>
#include <asm/traps.h>
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
@@ -77,48 +75,6 @@ static int __init vsyscall_setup(char *str)
}
early_param("vsyscall", vsyscall_setup);
-void update_vsyscall_tz(void)
-{
- vsyscall_gtod_data.sys_tz = sys_tz;
-}
-
-void update_vsyscall(struct timekeeper *tk)
-{
- struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
-
- write_seqcount_begin(&vdata->seq);
-
- /* copy vsyscall data */
- vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode;
- vdata->clock.cycle_last = tk->clock->cycle_last;
- vdata->clock.mask = tk->clock->mask;
- vdata->clock.mult = tk->mult;
- vdata->clock.shift = tk->shift;
-
- vdata->wall_time_sec = tk->xtime_sec;
- vdata->wall_time_snsec = tk->xtime_nsec;
-
- vdata->monotonic_time_sec = tk->xtime_sec
- + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_snsec = tk->xtime_nsec
- + (tk->wall_to_monotonic.tv_nsec
- << tk->shift);
- while (vdata->monotonic_time_snsec >=
- (((u64)NSEC_PER_SEC) << tk->shift)) {
- vdata->monotonic_time_snsec -=
- ((u64)NSEC_PER_SEC) << tk->shift;
- vdata->monotonic_time_sec++;
- }
-
- vdata->wall_time_coarse.tv_sec = tk->xtime_sec;
- vdata->wall_time_coarse.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
-
- vdata->monotonic_time_coarse = timespec_add(vdata->wall_time_coarse,
- tk->wall_to_monotonic);
-
- write_seqcount_end(&vdata->seq);
-}
-
static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
const char *message)
{
@@ -374,7 +330,6 @@ void __init map_vsyscall(void)
{
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- extern char __vvar_page;
unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
@@ -393,9 +348,13 @@ static int __init vsyscall_init(void)
{
BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
+ cpu_notifier_register_begin();
+
on_each_cpu(cpu_vsyscall_init, NULL, 1);
/* notifier priority > KVM */
- hotcpu_notifier(cpu_vsyscall_notifier, 30);
+ __hotcpu_notifier(cpu_vsyscall_notifier, 30);
+
+ cpu_notifier_register_done();
return 0;
}
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
new file mode 100644
index 000000000000..f9c6e56e14b5
--- /dev/null
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Modified for x86 32 bit architecture by
+ * Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ * Thanks to hpa@transmeta.com for some useful hint.
+ * Special thanks to Ingo Molnar for his early experience with
+ * a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ */
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
+
+void update_vsyscall_tz(void)
+{
+ vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
+ vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+ struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+
+ gtod_write_begin(vdata);
+
+ /* copy vsyscall data */
+ vdata->vclock_mode = tk->clock->archdata.vclock_mode;
+ vdata->cycle_last = tk->clock->cycle_last;
+ vdata->mask = tk->clock->mask;
+ vdata->mult = tk->mult;
+ vdata->shift = tk->shift;
+
+ vdata->wall_time_sec = tk->xtime_sec;
+ vdata->wall_time_snsec = tk->xtime_nsec;
+
+ vdata->monotonic_time_sec = tk->xtime_sec
+ + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_snsec = tk->xtime_nsec
+ + (tk->wall_to_monotonic.tv_nsec
+ << tk->shift);
+ while (vdata->monotonic_time_snsec >=
+ (((u64)NSEC_PER_SEC) << tk->shift)) {
+ vdata->monotonic_time_snsec -=
+ ((u64)NSEC_PER_SEC) << tk->shift;
+ vdata->monotonic_time_sec++;
+ }
+
+ vdata->wall_time_coarse_sec = tk->xtime_sec;
+ vdata->wall_time_coarse_nsec = (long)(tk->xtime_nsec >> tk->shift);
+
+ vdata->monotonic_time_coarse_sec =
+ vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_coarse_nsec =
+ vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+
+ while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
+ vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
+ vdata->monotonic_time_coarse_sec++;
+ }
+
+ gtod_write_end(vdata);
+}