summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2014-04-14 16:44:42 +0200
committerIngo Molnar <mingo@kernel.org>2014-04-14 16:44:42 +0200
commit740c699a8d316c8bf8593f19e2ca47795e690622 (patch)
treea78886955770a477945c5d84e06b2e7678733b54 /arch/x86/kernel
parente69af4657e7764d03ad555f0b583d9c4217bcefa (diff)
parentc9eaa447e77efe77b7fa4c953bd62de8297fd6c5 (diff)
downloadlinux-740c699a8d316c8bf8593f19e2ca47795e690622.tar.bz2
Merge tag 'v3.15-rc1' into perf/urgent
Pick up the latest fixes. Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c16
-rw-r--r--arch/x86/kernel/acpi/cstate.c4
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/apic/Makefile3
-rw-r--r--arch/x86/kernel/apic/apic.c4
-rw-r--r--arch/x86/kernel/apic/es7000_32.c738
-rw-r--r--arch/x86/kernel/apic/numaq_32.c524
-rw-r--r--arch/x86/kernel/apic/summit_32.c550
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-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.c26
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c19
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c18
-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.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c6
-rw-r--r--arch/x86/kernel/cpuid.c15
-rw-r--r--arch/x86/kernel/dumpstack_64.c25
-rw-r--r--arch/x86/kernel/early-quirks.c211
-rw-r--r--arch/x86/kernel/ftrace.c55
-rw-r--r--arch/x86/kernel/hpet.c6
-rw-r--r--arch/x86/kernel/irq.c2
-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/msr.c16
-rw-r--r--arch/x86/kernel/pci-calgary_64.c31
-rw-r--r--arch/x86/kernel/setup.c1
-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
35 files changed, 430 insertions, 2072 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 9f46f2b1cfc2..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 */
@@ -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/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 53e20531470e..ad28db7e6bde 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1996,7 +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);
@@ -2136,7 +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/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
deleted file mode 100644
index 6f8f8b348a39..000000000000
--- a/arch/x86/kernel/apic/es7000_32.c
+++ /dev/null
@@ -1,738 +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 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 = false,
- /* 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 = true,
- /* 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 030ea1c04f72..000000000000
--- a/arch/x86/kernel/apic/numaq_32.c
+++ /dev/null
@@ -1,524 +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 = false,
- .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/summit_32.c b/arch/x86/kernel/apic/summit_32.c
deleted file mode 100644
index b656128611cd..000000000000
--- a/arch/x86/kernel/apic/summit_32.c
+++ /dev/null
@@ -1,550 +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 = true,
- .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/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 897d6201ef10..a80029035bf2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -274,10 +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..eeee23ff75ef 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).
@@ -595,6 +598,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce m;
int i;
+ unsigned long *v;
this_cpu_inc(mce_poll_count);
@@ -614,6 +618,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(m.status & MCI_STATUS_VAL))
continue;
+ v = &get_cpu_var(mce_polled_error);
+ set_bit(0, v);
/*
* Uncorrected or signalled events are handled by the exception
* handler when it is enabled, so don't process those here.
@@ -1278,10 +1284,18 @@ 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 +1310,9 @@ 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 +2450,18 @@ 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..3bdb95ae8c43 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>
@@ -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;
+
+ raw_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);
+ }
+ raw_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);
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/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 3cec947e3b98..4b9a9e9466bd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -673,19 +673,20 @@ 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);
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;
}
@@ -699,7 +700,7 @@ static int __init rapl_pmu_init(void)
hweight32(rapl_cntr_mask),
ktime_to_ms(pmu->timer_interval));
- put_online_cpus();
+ 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 bd2253d40cff..65bbbea38b9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -4244,7 +4244,7 @@ static void __init uncore_cpumask_init(void)
if (!cpumask_empty(&uncore_cpu_mask))
return;
- get_online_cpus();
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu) {
int i, phys_id = topology_physical_package_id(cpu);
@@ -4263,9 +4263,9 @@ static void __init uncore_cpumask_init(void)
}
on_each_cpu(uncore_cpu_setup, NULL, 1);
- register_cpu_notifier(&uncore_cpu_nb);
+ __register_cpu_notifier(&uncore_cpu_nb);
- put_online_cpus();
+ cpu_notifier_register_done();
}
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/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 346b1df2412e..1abcb50b48ae 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -115,27 +115,26 @@ enum stack_type {
};
static enum stack_type
-analyze_stack(int cpu, struct task_struct *task,
- unsigned long *stack, unsigned long **stack_end, char **id)
+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 *irq_stack;
unsigned long addr;
- unsigned used = 0;
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);
+ used, id);
if (*stack_end)
return STACK_IS_EXCEPTION;
- *stack_end = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
- if (!*stack_end)
- return STACK_IS_UNKNOWN;
+ if (!irq_stack)
+ return STACK_IS_NORMAL;
- irq_stack = *stack_end - irq_stack_size;
+ *stack_end = irq_stack;
+ irq_stack = irq_stack - irq_stack_size;
if (in_irq_stack(stack, irq_stack, *stack_end))
return STACK_IS_IRQ;
@@ -156,8 +155,9 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
{
const unsigned cpu = get_cpu();
struct thread_info *tinfo;
- unsigned long *irq_stack;
+ unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned long dummy;
+ unsigned used = 0;
int graph = 0;
int done = 0;
@@ -186,7 +186,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
enum stack_type stype;
char *id;
- stype = analyze_stack(cpu, task, stack, &stack_end, &id);
+ stype = analyze_stack(cpu, task, stack, &stack_end,
+ irq_stack, &used, &id);
/* Default finish unless specified to continue */
done = 1;
@@ -226,7 +227,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
* pointer (index -1 to end) in the IRQ stack:
*/
stack = (unsigned long *) (stack_end[-1]);
- irq_stack = stack_end - irq_stack_size;
+ irq_stack = NULL;
ops->stack(data, "EOI");
done = 0;
break;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6d7d5a1260a6..b0cc3809723d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -225,7 +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;
@@ -244,6 +244,114 @@ static u32 __init intel_stolen_base(int num, int slot, int func)
#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;
@@ -310,7 +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;
@@ -320,31 +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)
@@ -361,11 +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/hpet.c b/arch/x86/kernel/hpet.c
index 014618dbaa7b..8d80ae011603 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -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/irq.c b/arch/x86/kernel/irq.c
index 42805fac0092..283a76a9cc40 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -125,7 +125,7 @@ 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 defined(CONFIG_HYPERV) || defined(CONFIG_XEN)
+#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);
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/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/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/setup.c b/arch/x86/kernel/setup.c
index fa511acff7e6..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
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);
+}