summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/amd_nb.c4
-rw-r--r--arch/x86/kernel/apic/apic.c6
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c2
-rw-r--r--arch/x86/kernel/apic/apic_noop.c1
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c1
-rw-r--r--arch/x86/kernel/apic/io_apic.c18
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c1
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c1
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c1
-rw-r--r--arch/x86/kernel/asm-offsets.c4
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c2
-rw-r--r--arch/x86/kernel/cpu/rdrand.c4
-rw-r--r--arch/x86/kernel/dumpstack.c20
-rw-r--r--arch/x86/kernel/dumpstack_64.c12
-rw-r--r--arch/x86/kernel/early-quirks.c105
-rw-r--r--arch/x86/kernel/ebda.c114
-rw-r--r--arch/x86/kernel/head32.c2
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/head_64.S3
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c2
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kernel/platform-quirks.c4
-rw-r--r--arch/x86/kernel/setup.c3
-rw-r--r--arch/x86/kernel/signal_compat.c108
-rw-r--r--arch/x86/kernel/smpboot.c26
-rw-r--r--arch/x86/kernel/vm86_32.c5
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c3
32 files changed, 358 insertions, 107 deletions
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a147e676fc7b..e991d5c8bb3a 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
i++;
- if (i == 0)
- return 0;
+ if (!i)
+ return -ENODEV;
nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
if (!nb)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 60078a67d7e3..f943d2f453a4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2045,7 +2045,7 @@ int generic_processor_info(int apicid, int version)
int thiscpu = max + disabled_cpus - 1;
pr_warning(
- "ACPI: NR_CPUS/possible_cpus limit of %i almost"
+ "APIC: NR_CPUS/possible_cpus limit of %i almost"
" reached. Keeping one slot for boot cpu."
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
@@ -2057,7 +2057,7 @@ int generic_processor_info(int apicid, int version)
int thiscpu = max + disabled_cpus;
pr_warning(
- "ACPI: NR_CPUS/possible_cpus limit of %i reached."
+ "APIC: NR_CPUS/possible_cpus limit of %i reached."
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
disabled_cpus++;
@@ -2085,7 +2085,7 @@ int generic_processor_info(int apicid, int version)
if (topology_update_package_map(apicid, cpu) < 0) {
int thiscpu = max + disabled_cpus;
- pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n",
+ pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
disabled_cpus++;
return -ENOSPC;
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 76f89e2b245a..048747778d37 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -181,7 +181,6 @@ static struct apic apic_flat = {
.get_apic_id = flat_get_apic_id,
.set_apic_id = set_apic_id,
- .apic_id_mask = 0xFFu << 24,
.cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
@@ -278,7 +277,6 @@ static struct apic apic_physflat = {
.get_apic_id = flat_get_apic_id,
.set_apic_id = set_apic_id,
- .apic_id_mask = 0xFFu << 24,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 13d19ed58514..2cebf59092d8 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -141,7 +141,6 @@ struct apic apic_noop = {
.get_apic_id = noop_get_apic_id,
.set_apic_id = NULL,
- .apic_id_mask = 0x0F << 24,
.cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index ab5c2c685a3c..714d4fda0d52 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -269,7 +269,6 @@ static const struct apic apic_numachip1 __refconst = {
.get_apic_id = numachip1_get_apic_id,
.set_apic_id = numachip1_set_apic_id,
- .apic_id_mask = 0xffU << 24,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
@@ -321,7 +320,6 @@ static const struct apic apic_numachip2 __refconst = {
.get_apic_id = numachip2_get_apic_id,
.set_apic_id = numachip2_set_apic_id,
- .apic_id_mask = 0xffU << 24,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index cf9bd896c12d..06dbaa458bfe 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -171,7 +171,6 @@ static struct apic apic_bigsmp = {
.get_apic_id = bigsmp_get_apic_id,
.set_apic_id = NULL,
- .apic_id_mask = 0xFF << 24,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 446702ed99dc..e58729597a7a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2567,29 +2567,25 @@ static struct resource * __init ioapic_setup_resources(void)
unsigned long n;
struct resource *res;
char *mem;
- int i, num = 0;
+ int i;
- for_each_ioapic(i)
- num++;
- if (num == 0)
+ if (nr_ioapics == 0)
return NULL;
n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
- n *= num;
+ n *= nr_ioapics;
mem = alloc_bootmem(n);
res = (void *)mem;
- mem += sizeof(struct resource) * num;
+ mem += sizeof(struct resource) * nr_ioapics;
- num = 0;
for_each_ioapic(i) {
- res[num].name = mem;
- res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ res[i].name = mem;
+ res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
mem += IOAPIC_RESOURCE_NAME_SIZE;
- ioapics[i].iomem_res = &res[num];
- num++;
+ ioapics[i].iomem_res = &res[i];
}
ioapic_resources = res;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f316e34abb42..93edfa01b408 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -101,7 +101,6 @@ static struct apic apic_default = {
.get_apic_id = default_get_apic_id,
.set_apic_id = NULL,
- .apic_id_mask = 0x0F << 24,
.cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index aca8b75c1552..24170d0809ba 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -270,7 +270,6 @@ static struct apic apic_x2apic_cluster = {
.get_apic_id = x2apic_get_apic_id,
.set_apic_id = x2apic_set_apic_id,
- .apic_id_mask = 0xFFFFFFFFu,
.cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index a1242e2c12e6..4f13f54f1b1f 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -126,7 +126,6 @@ static struct apic apic_x2apic_phys = {
.get_apic_id = x2apic_get_apic_id,
.set_apic_id = x2apic_set_apic_id,
- .apic_id_mask = 0xFFFFFFFFu,
.cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 29003154fafd..5a58c917179c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -582,7 +582,6 @@ static struct apic __refdata apic_x2apic_uv_x = {
.get_apic_id = x2apic_get_apic_id,
.set_apic_id = set_apic_id,
- .apic_id_mask = 0xFFFFFFFFu,
.cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and,
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 674134e9f5e5..2bd5c6ff7ee7 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -31,7 +31,9 @@ void common(void) {
BLANK();
OFFSET(TI_flags, thread_info, flags);
OFFSET(TI_status, thread_info, status);
- OFFSET(TI_addr_limit, thread_info, addr_limit);
+
+ BLANK();
+ OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
BLANK();
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0fe6953f421c..d22a7b9c4f0e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1452,7 +1452,7 @@ void cpu_init(void)
struct task_struct *me;
struct tss_struct *t;
unsigned long v;
- int cpu = stack_smp_processor_id();
+ int cpu = raw_smp_processor_id();
int i;
wait_for_master_cpu(cpu);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 34c89a3e8260..83f1a98d37db 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -46,7 +46,7 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
return;
mce_setup(&m);
- m.bank = 1;
+ m.bank = -1;
/* Fake a memory read error with unknown channel */
m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 92e5e37d97bf..58af6300992d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -425,7 +425,7 @@ static u64 mce_rdmsrl(u32 msr)
}
if (rdmsrl_safe(msr, &v)) {
- WARN_ONCE(1, "mce: Unable to read msr %d!\n", msr);
+ WARN_ONCE(1, "mce: Unable to read MSR 0x%x!\n", msr);
/*
* Return zero in case the access faulted. This should
* not happen normally but can happen if the CPU does
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 10b0661651e0..7b7f3be783d4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -93,7 +93,7 @@ const char * const amd_df_mcablock_names[] = {
EXPORT_SYMBOL_GPL(amd_df_mcablock_names);
static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
-static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */
+static DEFINE_PER_CPU(unsigned int, bank_map); /* see which banks are on */
static void amd_threshold_interrupt(void);
static void amd_deferred_error_interrupt(void);
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index f6f50c4ceaec..cfa97ff67bda 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -39,9 +39,9 @@ __setup("nordrand", x86_rdrand_setup);
*/
#define SANITY_CHECK_LOOPS 8
+#ifdef CONFIG_ARCH_RANDOM
void x86_init_rdrand(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_ARCH_RANDOM
unsigned long tmp;
int i;
@@ -55,5 +55,5 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
return;
}
}
-#endif
}
+#endif
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index d66e5ac823b2..92e8f0a7159c 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -87,7 +87,7 @@ static inline int valid_stack_ptr(struct task_struct *task,
else
return 0;
}
- return p > t && p < t + THREAD_SIZE - size;
+ return p >= t && p < t + THREAD_SIZE - size;
}
unsigned long
@@ -98,6 +98,14 @@ print_context_stack(struct task_struct *task,
{
struct stack_frame *frame = (struct stack_frame *)bp;
+ /*
+ * If we overflowed the stack into a guard page, jump back to the
+ * bottom of the usable stack.
+ */
+ if ((unsigned long)task_stack_page(task) - (unsigned long)stack <
+ PAGE_SIZE)
+ stack = (unsigned long *)task_stack_page(task);
+
while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
unsigned long addr;
@@ -231,6 +239,8 @@ unsigned long oops_begin(void)
EXPORT_SYMBOL_GPL(oops_begin);
NOKPROBE_SYMBOL(oops_begin);
+void __noreturn rewind_stack_do_exit(int signr);
+
void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
{
if (regs && kexec_should_crash(current))
@@ -252,7 +262,13 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
- do_exit(signr);
+
+ /*
+ * We're not going to return, but we might be on an IST stack or
+ * have very little stack space left. Rewind the stack and kill
+ * the task.
+ */
+ rewind_stack_do_exit(signr);
}
NOKPROBE_SYMBOL(oops_end);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index a81e1ef73bf2..6dede08dd98b 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -274,6 +274,8 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
+ unsigned long word;
+
if (stack >= irq_stack && stack <= irq_stack_end) {
if (stack == irq_stack_end) {
stack = (unsigned long *) (irq_stack_end[-1]);
@@ -283,12 +285,18 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
if (kstack_end(stack))
break;
}
+
+ if (probe_kernel_address(stack, word))
+ break;
+
if ((i % STACKSLOTS_PER_LINE) == 0) {
if (i != 0)
pr_cont("\n");
- printk("%s %016lx", log_lvl, *stack++);
+ printk("%s %016lx", log_lvl, word);
} else
- pr_cont(" %016lx", *stack++);
+ pr_cont(" %016lx", word);
+
+ stack++;
touch_nmi_watchdog();
}
preempt_enable();
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bca14c899137..57b71373bae3 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -11,7 +11,11 @@
#include <linux/pci.h>
#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/pci_ids.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_regs.h>
#include <drm/i915_drm.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
@@ -21,6 +25,9 @@
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/irq_remapping.h>
+#include <asm/early_ioremap.h>
+
+#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
static void __init fix_hypertransport_config(int num, int slot, int func)
{
@@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func)
#ifdef CONFIG_ACPI
#ifdef CONFIG_X86_IO_APIC
/*
+ * Only applies to Nvidia root ports (bus 0) and not to
+ * Nvidia graphics cards with PCI ports on secondary buses.
+ */
+ if (num)
+ return;
+
+ /*
* All timer overrides on Nvidia are
* wrong unless HPET is enabled.
* Unfortunately that's not true on many Asus boards.
@@ -590,6 +604,61 @@ static void __init force_disable_hpet(int num, int slot, int func)
#endif
}
+#define BCM4331_MMIO_SIZE 16384
+#define BCM4331_PM_CAP 0x40
+#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg)
+#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg)
+
+static void __init apple_airport_reset(int bus, int slot, int func)
+{
+ void __iomem *mmio;
+ u16 pmcsr;
+ u64 addr;
+ int i;
+
+ if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc."))
+ return;
+
+ /* Card may have been put into PCI_D3hot by grub quirk */
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+ write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr);
+ mdelay(10);
+
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ dev_err("Cannot power up Apple AirPort card\n");
+ return;
+ }
+ }
+
+ addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+ addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32;
+ addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+ mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
+ if (!mmio) {
+ dev_err("Cannot iomap Apple AirPort card\n");
+ return;
+ }
+
+ pr_info("Resetting Apple AirPort card (left enabled by EFI)\n");
+
+ for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++)
+ udelay(10);
+
+ bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(1);
+
+ bcma_awrite32(BCMA_RESET_CTL, 0);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(10);
+
+ early_iounmap(mmio, BCM4331_MMIO_SIZE);
+}
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
@@ -603,12 +672,6 @@ struct chipset {
void (*f)(int num, int slot, int func);
};
-/*
- * Only works for devices on the root bus. If you add any devices
- * not on bus 0 readd another loop level in early_quirks(). But
- * be careful because at least the Nvidia quirk here relies on
- * only matching on bus 0.
- */
static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -638,9 +701,13 @@ static struct chipset early_qrk[] __initdata = {
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+ { PCI_VENDOR_ID_BROADCOM, 0x4331,
+ PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
{}
};
+static void __init early_pci_scan_bus(int bus);
+
/**
* check_dev_quirk - apply early quirks to a given PCI device
* @num: bus number
@@ -649,7 +716,7 @@ static struct chipset early_qrk[] __initdata = {
*
* Check the vendor & device ID against the early quirks table.
*
- * If the device is single function, let early_quirks() know so we don't
+ * If the device is single function, let early_pci_scan_bus() know so we don't
* poke at this device again.
*/
static int __init check_dev_quirk(int num, int slot, int func)
@@ -658,6 +725,7 @@ static int __init check_dev_quirk(int num, int slot, int func)
u16 vendor;
u16 device;
u8 type;
+ u8 sec;
int i;
class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
@@ -685,25 +753,36 @@ static int __init check_dev_quirk(int num, int slot, int func)
type = read_pci_config_byte(num, slot, func,
PCI_HEADER_TYPE);
+
+ if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+ sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
+ if (sec > num)
+ early_pci_scan_bus(sec);
+ }
+
if (!(type & 0x80))
return -1;
return 0;
}
-void __init early_quirks(void)
+static void __init early_pci_scan_bus(int bus)
{
int slot, func;
- if (!early_pci_allowed())
- return;
-
/* Poor man's PCI discovery */
- /* Only scan the root bus */
for (slot = 0; slot < 32; slot++)
for (func = 0; func < 8; func++) {
/* Only probe function 0 on single fn devices */
- if (check_dev_quirk(0, slot, func))
+ if (check_dev_quirk(bus, slot, func))
break;
}
}
+
+void __init early_quirks(void)
+{
+ if (!early_pci_allowed())
+ return;
+
+ early_pci_scan_bus(0);
+}
diff --git a/arch/x86/kernel/ebda.c b/arch/x86/kernel/ebda.c
index afe65dffee80..4312f8ae71b7 100644
--- a/arch/x86/kernel/ebda.c
+++ b/arch/x86/kernel/ebda.c
@@ -6,66 +6,92 @@
#include <asm/bios_ebda.h>
/*
+ * This function reserves all conventional PC system BIOS related
+ * firmware memory areas (some of which are data, some of which
+ * are code), that must not be used by the kernel as available
+ * RAM.
+ *
* The BIOS places the EBDA/XBDA at the top of conventional
* memory, and usually decreases the reported amount of
- * conventional memory (int 0x12) too. This also contains a
- * workaround for Dell systems that neglect to reserve EBDA.
- * The same workaround also avoids a problem with the AMD768MPX
- * chipset: reserve a page before VGA to prevent PCI prefetch
- * into it (errata #56). Usually the page is reserved anyways,
- * unless you have no PS/2 mouse plugged in.
+ * conventional memory (int 0x12) too.
+ *
+ * This means that as a first approximation on most systems we can
+ * guess the reserved BIOS area by looking at the low BIOS RAM size
+ * value and assume that everything above that value (up to 1MB) is
+ * reserved.
+ *
+ * But life in firmware country is not that simple:
+ *
+ * - This code also contains a quirk for Dell systems that neglect
+ * to reserve the EBDA area in the 'RAM size' value ...
+ *
+ * - The same quirk also avoids a problem with the AMD768MPX
+ * chipset: reserve a page before VGA to prevent PCI prefetch
+ * into it (errata #56). (Usually the page is reserved anyways,
+ * unless you have no PS/2 mouse plugged in.)
+ *
+ * - Plus paravirt systems don't have a reliable value in the
+ * 'BIOS RAM size' pointer we can rely on, so we must quirk
+ * them too.
+ *
+ * Due to those various problems this function is deliberately
+ * very conservative and tries to err on the side of reserving
+ * too much, to not risk reserving too little.
+ *
+ * Losing a small amount of memory in the bottom megabyte is
+ * rarely a problem, as long as we have enough memory to install
+ * the SMP bootup trampoline which *must* be in this area.
*
- * This functions is deliberately very conservative. Losing
- * memory in the bottom megabyte is rarely a problem, as long
- * as we have enough memory to install the trampoline. Using
- * memory that is in use by the BIOS or by some DMA device
- * the BIOS didn't shut down *is* a big problem.
+ * Using memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem to the kernel,
+ * obviously.
*/
-#define BIOS_LOWMEM_KILOBYTES 0x413
-#define LOWMEM_CAP 0x9f000U /* Absolute maximum */
-#define INSANE_CUTOFF 0x20000U /* Less than this = insane */
+#define BIOS_RAM_SIZE_KB_PTR 0x413
-void __init reserve_ebda_region(void)
+#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */
+#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */
+
+void __init reserve_bios_regions(void)
{
- unsigned int lowmem, ebda_addr;
+ unsigned int bios_start, ebda_start;
/*
- * To determine the position of the EBDA and the
- * end of conventional memory, we need to look at
- * the BIOS data area. In a paravirtual environment
- * that area is absent. We'll just have to assume
- * that the paravirt case can handle memory setup
- * correctly, without our help.
+ * NOTE: In a paravirtual environment the BIOS reserved
+ * area is absent. We'll just have to assume that the
+ * paravirt case can handle memory setup correctly,
+ * without our help.
*/
- if (!x86_platform.legacy.ebda_search)
+ if (!x86_platform.legacy.reserve_bios_regions)
return;
- /* end of low (conventional) memory */
- lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
- lowmem <<= 10;
-
- /* start of EBDA area */
- ebda_addr = get_bios_ebda();
-
/*
- * Note: some old Dells seem to need 4k EBDA without
- * reporting so, so just consider the memory above 0x9f000
- * to be off limits (bugzilla 2990).
+ * BIOS RAM size is encoded in kilobytes, convert it
+ * to bytes to get a first guess at where the BIOS
+ * firmware area starts:
*/
+ bios_start = *(unsigned short *)__va(BIOS_RAM_SIZE_KB_PTR);
+ bios_start <<= 10;
- /* If the EBDA address is below 128K, assume it is bogus */
- if (ebda_addr < INSANE_CUTOFF)
- ebda_addr = LOWMEM_CAP;
+ /*
+ * If bios_start is less than 128K, assume it is bogus
+ * and bump it up to 640K. Similarly, if bios_start is above 640K,
+ * don't trust it.
+ */
+ if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+ bios_start = BIOS_START_MAX;
- /* If lowmem is less than 128K, assume it is bogus */
- if (lowmem < INSANE_CUTOFF)
- lowmem = LOWMEM_CAP;
+ /* Get the start address of the EBDA page: */
+ ebda_start = get_bios_ebda();
- /* Use the lower of the lowmem and EBDA markers as the cutoff */
- lowmem = min(lowmem, ebda_addr);
- lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
+ /*
+ * If the EBDA start address is sane and is below the BIOS region,
+ * then also reserve everything from the EBDA start address up to
+ * the BIOS region.
+ */
+ if (ebda_start >= BIOS_START_MIN && ebda_start < bios_start)
+ bios_start = ebda_start;
- /* reserve all memory between lowmem and the 1MB mark */
- memblock_reserve(lowmem, 0x100000 - lowmem);
+ /* Reserve all memory between bios_start and the 1MB mark: */
+ memblock_reserve(bios_start, 0x100000 - bios_start);
}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index d784bb547a9d..2dda0bc4576e 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -26,7 +26,7 @@ static void __init i386_default_early_setup(void)
x86_init.resources.reserve_resources = i386_reserve_resources;
x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
- reserve_ebda_region();
+ reserve_bios_regions();
}
asmlinkage __visible void __init i386_start_kernel(void)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b72fb0b71dd1..99d48e7d2974 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -183,7 +183,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
copy_bootdata(__va(real_mode_data));
x86_early_init_platform_quirks();
- reserve_ebda_region();
+ reserve_bios_regions();
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_INTEL_MID:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 5df831ef1442..9f8efc9f0075 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -38,7 +38,7 @@
#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET)
+L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
L4_START_KERNEL = pgd_index(__START_KERNEL_map)
L3_START_KERNEL = pud_index(__START_KERNEL_map)
@@ -299,6 +299,7 @@ ENTRY(secondary_startup_64)
pushq $__KERNEL_CS # set correct cs
pushq %rax # target address in negative space
lretq
+ENDPROC(secondary_startup_64)
#include "verify_cpu.S"
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 64341aa485ae..d40ee8a38fed 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -42,3 +42,5 @@ EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(___preempt_schedule);
EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
+
+EXPORT_SYMBOL(__sw_hweight32);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index eea2a6f72b31..1ef5e48b3a36 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -301,8 +301,6 @@ static void kvm_register_steal_time(void)
if (!has_steal_clock)
return;
- memset(st, 0, sizeof(*st));
-
wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
pr_info("kvm-stealtime: cpu %d, msr %llx\n",
cpu, (unsigned long long) slow_virt_to_phys(st));
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index b2f8a33b36ff..24a50301f150 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -7,12 +7,12 @@
void __init x86_early_init_platform_quirks(void)
{
x86_platform.legacy.rtc = 1;
- x86_platform.legacy.ebda_search = 0;
+ x86_platform.legacy.reserve_bios_regions = 0;
x86_platform.legacy.devices.pnpbios = 1;
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_PC:
- x86_platform.legacy.ebda_search = 1;
+ x86_platform.legacy.reserve_bios_regions = 1;
break;
case X86_SUBARCH_XEN:
case X86_SUBARCH_LGUEST:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c4e7b3991b60..a2616584b6e9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -113,6 +113,7 @@
#include <asm/prom.h>
#include <asm/microcode.h>
#include <asm/mmu_context.h>
+#include <asm/kaslr.h>
/*
* max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -942,6 +943,8 @@ void __init setup_arch(char **cmdline_p)
x86_init.oem.arch_setup();
+ kernel_randomize_memory();
+
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
setup_memory_map();
parse_setup_data();
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index dc3c0b1c816f..b44564bf86a8 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -1,11 +1,104 @@
#include <linux/compat.h>
#include <linux/uaccess.h>
+/*
+ * The compat_siginfo_t structure and handing code is very easy
+ * to break in several ways. It must always be updated when new
+ * updates are made to the main siginfo_t, and
+ * copy_siginfo_to_user32() must be updated when the
+ * (arch-independent) copy_siginfo_to_user() is updated.
+ *
+ * It is also easy to put a new member in the compat_siginfo_t
+ * which has implicit alignment which can move internal structure
+ * alignment around breaking the ABI. This can happen if you,
+ * for instance, put a plain 64-bit value in there.
+ */
+static inline void signal_compat_build_tests(void)
+{
+ int _sifields_offset = offsetof(compat_siginfo_t, _sifields);
+
+ /*
+ * If adding a new si_code, there is probably new data in
+ * the siginfo. Make sure folks bumping the si_code
+ * limits also have to look at this code. Make sure any
+ * new fields are handled in copy_siginfo_to_user32()!
+ */
+ BUILD_BUG_ON(NSIGILL != 8);
+ BUILD_BUG_ON(NSIGFPE != 8);
+ BUILD_BUG_ON(NSIGSEGV != 4);
+ BUILD_BUG_ON(NSIGBUS != 5);
+ BUILD_BUG_ON(NSIGTRAP != 4);
+ BUILD_BUG_ON(NSIGCHLD != 6);
+ BUILD_BUG_ON(NSIGSYS != 1);
+
+ /* This is part of the ABI and can never change in size: */
+ BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128);
+ /*
+ * The offsets of all the (unioned) si_fields are fixed
+ * in the ABI, of course. Make sure none of them ever
+ * move and are always at the beginning:
+ */
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
+#define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
+
+ /*
+ * Ensure that the size of each si_field never changes.
+ * If it does, it is a sign that the
+ * copy_siginfo_to_user32() code below needs to updated
+ * along with the size in the CHECK_SI_SIZE().
+ *
+ * We repeat this check for both the generic and compat
+ * siginfos.
+ *
+ * Note: it is OK for these to grow as long as the whole
+ * structure stays within the padding size (checked
+ * above).
+ */
+#define CHECK_CSI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((compat_siginfo_t *)0)->_sifields.name))
+#define CHECK_SI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((siginfo_t *)0)->_sifields.name))
+
+ CHECK_CSI_OFFSET(_kill);
+ CHECK_CSI_SIZE (_kill, 2*sizeof(int));
+ CHECK_SI_SIZE (_kill, 2*sizeof(int));
+
+ CHECK_CSI_OFFSET(_timer);
+ CHECK_CSI_SIZE (_timer, 5*sizeof(int));
+ CHECK_SI_SIZE (_timer, 6*sizeof(int));
+
+ CHECK_CSI_OFFSET(_rt);
+ CHECK_CSI_SIZE (_rt, 3*sizeof(int));
+ CHECK_SI_SIZE (_rt, 4*sizeof(int));
+
+ CHECK_CSI_OFFSET(_sigchld);
+ CHECK_CSI_SIZE (_sigchld, 5*sizeof(int));
+ CHECK_SI_SIZE (_sigchld, 8*sizeof(int));
+
+ CHECK_CSI_OFFSET(_sigchld_x32);
+ CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int));
+ /* no _sigchld_x32 in the generic siginfo_t */
+
+ CHECK_CSI_OFFSET(_sigfault);
+ CHECK_CSI_SIZE (_sigfault, 4*sizeof(int));
+ CHECK_SI_SIZE (_sigfault, 8*sizeof(int));
+
+ CHECK_CSI_OFFSET(_sigpoll);
+ CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int));
+ CHECK_SI_SIZE (_sigpoll, 4*sizeof(int));
+
+ CHECK_CSI_OFFSET(_sigsys);
+ CHECK_CSI_SIZE (_sigsys, 3*sizeof(int));
+ CHECK_SI_SIZE (_sigsys, 4*sizeof(int));
+
+ /* any new si_fields should be added here */
+}
+
int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
{
int err = 0;
bool ia32 = test_thread_flag(TIF_IA32);
+ signal_compat_build_tests();
+
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
@@ -32,6 +125,21 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
&to->_sifields._pad[0]);
switch (from->si_code >> 16) {
case __SI_FAULT >> 16:
+ if (from->si_signo == SIGBUS &&
+ (from->si_code == BUS_MCEERR_AR ||
+ from->si_code == BUS_MCEERR_AO))
+ put_user_ex(from->si_addr_lsb, &to->si_addr_lsb);
+
+ if (from->si_signo == SIGSEGV) {
+ if (from->si_code == SEGV_BNDERR) {
+ compat_uptr_t lower = (unsigned long)&to->si_lower;
+ compat_uptr_t upper = (unsigned long)&to->si_upper;
+ put_user_ex(lower, &to->si_lower);
+ put_user_ex(upper, &to->si_upper);
+ }
+ if (from->si_code == SEGV_PKUERR)
+ put_user_ex(from->si_pkey, &to->si_pkey);
+ }
break;
case __SI_SYS >> 16:
put_user_ex(from->si_syscall, &to->si_syscall);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fafe8b923cac..d0a51939c150 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -105,6 +105,9 @@ static unsigned int max_physical_pkg_id __read_mostly;
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
+/* Maximum number of SMT threads on any online core */
+int __max_smt_threads __read_mostly;
+
static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
{
unsigned long flags;
@@ -493,7 +496,7 @@ void set_cpu_sibling_map(int cpu)
bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct cpuinfo_x86 *o;
- int i;
+ int i, threads;
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
@@ -550,6 +553,10 @@ void set_cpu_sibling_map(int cpu)
if (match_die(c, o) && !topology_same_node(c, o))
primarily_use_numa_for_topology();
}
+
+ threads = cpumask_weight(topology_sibling_cpumask(cpu));
+ if (threads > __max_smt_threads)
+ __max_smt_threads = threads;
}
/* maps the cpu to the sched domain representing multi-core */
@@ -1285,7 +1292,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
cpumask_copy(cpu_callin_mask, cpumask_of(0));
mb();
- current_thread_info()->cpu = 0; /* needed? */
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
@@ -1441,6 +1447,21 @@ __init void prefill_possible_map(void)
#ifdef CONFIG_HOTPLUG_CPU
+/* Recompute SMT state for all CPUs on offline */
+static void recompute_smt_state(void)
+{
+ int max_threads, cpu;
+
+ max_threads = 0;
+ for_each_online_cpu (cpu) {
+ int threads = cpumask_weight(topology_sibling_cpumask(cpu));
+
+ if (threads > max_threads)
+ max_threads = threads;
+ }
+ __max_smt_threads = max_threads;
+}
+
static void remove_siblinginfo(int cpu)
{
int sibling;
@@ -1465,6 +1486,7 @@ static void remove_siblinginfo(int cpu)
c->phys_proc_id = 0;
c->cpu_core_id = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
+ recompute_smt_state();
}
static void remove_cpu_from_maps(int cpu)
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 3dce1ca0a653..01f30e56f99e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -440,10 +440,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
static inline int is_revectored(int nr, struct revectored_struct *bitmap)
{
- __asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
- :"=r" (nr)
- :"m" (*bitmap), "r" (nr));
- return nr;
+ return test_bit(nr, bitmap->__map);
}
#define val_byte(val, n) (((__u8 *)&val)[n])
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index cd05942bc918..f1aebfb49c36 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -44,6 +44,9 @@ EXPORT_SYMBOL(clear_page);
EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(__sw_hweight32);
+EXPORT_SYMBOL(__sw_hweight64);
+
/*
* Export string functions. We normally rely on gcc builtin for most of these,
* but gcc sometimes decides not to inline them.