aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/amd_iommu.c108
-rw-r--r--arch/x86/kernel/amd_iommu_init.c4
-rw-r--r--arch/x86/kernel/aperture_64.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c10
-rw-r--r--arch/x86/kernel/apm_32.c5
-rw-r--r--arch/x86/kernel/cpu/amd.c21
-rw-r--r--arch/x86/kernel/cpu/perf_event.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c125
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c19
-rw-r--r--arch/x86/kernel/devicetree.c2
-rw-r--r--arch/x86/kernel/pci-gart_64.c9
-rw-r--r--arch/x86/kernel/pci-iommu_table.c18
-rw-r--r--arch/x86/kernel/ptrace.c36
-rw-r--r--arch/x86/kernel/reboot_32.S12
-rw-r--r--arch/x86/kernel/setup.c5
16 files changed, 319 insertions, 101 deletions
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index d6192bcf9f09..dc5dddafe5c2 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -18,6 +18,7 @@
*/
#include <linux/pci.h>
+#include <linux/pci-ats.h>
#include <linux/bitmap.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
@@ -463,6 +464,37 @@ static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
}
+static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
+ u64 address, size_t size)
+{
+ u64 pages;
+ int s;
+
+ pages = iommu_num_pages(address, size, PAGE_SIZE);
+ s = 0;
+
+ if (pages > 1) {
+ /*
+ * If we have to flush more than one page, flush all
+ * TLB entries for this domain
+ */
+ address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+ s = 1;
+ }
+
+ address &= PAGE_MASK;
+
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->data[0] = devid;
+ cmd->data[0] |= (qdep & 0xff) << 24;
+ cmd->data[1] = devid;
+ cmd->data[2] = lower_32_bits(address);
+ cmd->data[3] = upper_32_bits(address);
+ CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+ if (s)
+ cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+}
+
static void build_inv_all(struct iommu_cmd *cmd)
{
memset(cmd, 0, sizeof(*cmd));
@@ -594,17 +626,47 @@ void iommu_flush_all_caches(struct amd_iommu *iommu)
}
/*
+ * Command send function for flushing on-device TLB
+ */
+static int device_flush_iotlb(struct device *dev, u64 address, size_t size)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct amd_iommu *iommu;
+ struct iommu_cmd cmd;
+ u16 devid;
+ int qdep;
+
+ qdep = pci_ats_queue_depth(pdev);
+ devid = get_device_id(dev);
+ iommu = amd_iommu_rlookup_table[devid];
+
+ build_inv_iotlb_pages(&cmd, devid, qdep, address, size);
+
+ return iommu_queue_command(iommu, &cmd);
+}
+
+/*
* Command send function for invalidating a device table entry
*/
static int device_flush_dte(struct device *dev)
{
struct amd_iommu *iommu;
+ struct pci_dev *pdev;
u16 devid;
+ int ret;
+ pdev = to_pci_dev(dev);
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
- return iommu_flush_dte(iommu, devid);
+ ret = iommu_flush_dte(iommu, devid);
+ if (ret)
+ return ret;
+
+ if (pci_ats_enabled(pdev))
+ ret = device_flush_iotlb(dev, 0, ~0UL);
+
+ return ret;
}
/*
@@ -615,6 +677,7 @@ static int device_flush_dte(struct device *dev)
static void __domain_flush_pages(struct protection_domain *domain,
u64 address, size_t size, int pde)
{
+ struct iommu_dev_data *dev_data;
struct iommu_cmd cmd;
int ret = 0, i;
@@ -631,6 +694,15 @@ static void __domain_flush_pages(struct protection_domain *domain,
ret |= iommu_queue_command(amd_iommus[i], &cmd);
}
+ list_for_each_entry(dev_data, &domain->dev_list, list) {
+ struct pci_dev *pdev = to_pci_dev(dev_data->dev);
+
+ if (!pci_ats_enabled(pdev))
+ continue;
+
+ ret |= device_flush_iotlb(dev_data->dev, address, size);
+ }
+
WARN_ON(ret);
}
@@ -1400,17 +1472,22 @@ static bool dma_ops_domain(struct protection_domain *domain)
return domain->flags & PD_DMA_OPS_MASK;
}
-static void set_dte_entry(u16 devid, struct protection_domain *domain)
+static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
{
u64 pte_root = virt_to_phys(domain->pt_root);
+ u32 flags = 0;
pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
<< DEV_ENTRY_MODE_SHIFT;
pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
- amd_iommu_dev_table[devid].data[2] = domain->id;
- amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
- amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
+ if (ats)
+ flags |= DTE_FLAG_IOTLB;
+
+ amd_iommu_dev_table[devid].data[3] |= flags;
+ amd_iommu_dev_table[devid].data[2] = domain->id;
+ amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root);
+ amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root);
}
static void clear_dte_entry(u16 devid)
@@ -1427,16 +1504,22 @@ static void do_attach(struct device *dev, struct protection_domain *domain)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
+ struct pci_dev *pdev;
+ bool ats = false;
u16 devid;
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
dev_data = get_dev_data(dev);
+ pdev = to_pci_dev(dev);
+
+ if (amd_iommu_iotlb_sup)
+ ats = pci_ats_enabled(pdev);
/* Update data structures */
dev_data->domain = domain;
list_add(&dev_data->list, &domain->dev_list);
- set_dte_entry(devid, domain);
+ set_dte_entry(devid, domain, ats);
/* Do reference counting */
domain->dev_iommu[iommu->index] += 1;
@@ -1450,11 +1533,13 @@ static void do_detach(struct device *dev)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
+ struct pci_dev *pdev;
u16 devid;
devid = get_device_id(dev);
iommu = amd_iommu_rlookup_table[devid];
dev_data = get_dev_data(dev);
+ pdev = to_pci_dev(dev);
/* decrease reference counters */
dev_data->domain->dev_iommu[iommu->index] -= 1;
@@ -1529,9 +1614,13 @@ out_unlock:
static int attach_device(struct device *dev,
struct protection_domain *domain)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
unsigned long flags;
int ret;
+ if (amd_iommu_iotlb_sup)
+ pci_enable_ats(pdev, PAGE_SHIFT);
+
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
ret = __attach_device(dev, domain);
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -1588,12 +1677,16 @@ static void __detach_device(struct device *dev)
*/
static void detach_device(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
unsigned long flags;
/* lock device table */
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
__detach_device(dev);
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+ if (amd_iommu_iotlb_sup && pci_ats_enabled(pdev))
+ pci_disable_ats(pdev);
}
/*
@@ -1743,8 +1836,9 @@ static void update_device_table(struct protection_domain *domain)
struct iommu_dev_data *dev_data;
list_for_each_entry(dev_data, &domain->dev_list, list) {
+ struct pci_dev *pdev = to_pci_dev(dev_data->dev);
u16 devid = get_device_id(dev_data->dev);
- set_dte_entry(devid, domain);
+ set_dte_entry(devid, domain, pci_ats_enabled(pdev));
}
}
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 047905dc3e14..28b078133688 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -137,6 +137,7 @@ int amd_iommus_present;
/* IOMMUs have a non-present cache? */
bool amd_iommu_np_cache __read_mostly;
+bool amd_iommu_iotlb_sup __read_mostly = true;
/*
* The ACPI table parsing functions set this variable on an error
@@ -687,6 +688,9 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
MMIO_GET_LD(range));
iommu->evt_msi_num = MMIO_MSI_NUM(misc);
+ if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+ amd_iommu_iotlb_sup = false;
+
/* read extended feature bits */
low = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4962a7..73fb469908c6 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@ out:
* Don't enable translation yet but enable GART IO and CPU
* accesses and set DISTLBWALKPRB since GART table memory is UC.
*/
- u32 ctl = DISTLBWALKPRB | aper_order << 1;
+ u32 ctl = aper_order << 1;
bus = amd_nb_bus_dev_ranges[i].bus;
dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 68df09bba92e..45fd33d1fd3a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -128,8 +128,8 @@ static int __init parse_noapic(char *str)
}
early_param("noapic", parse_noapic);
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
- struct io_apic_irq_attr *attr);
+static int io_apic_setup_irq_pin(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr);
/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
void mp_save_irq(struct mpc_intsrc *m)
@@ -3570,7 +3570,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
}
#endif /* CONFIG_HT_IRQ */
-int
+static int
io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
{
struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
@@ -3585,8 +3585,8 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
return ret;
}
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
- struct io_apic_irq_attr *attr)
+int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr)
{
unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
int ret;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0b4be431c620..adee12e0da1f 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
#include <linux/kthread.h>
#include <linux/jiffies.h>
#include <linux/acpi.h>
+#include <linux/syscore_ops.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -1238,6 +1239,7 @@ static int suspend(int vetoable)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
@@ -1255,6 +1257,7 @@ static int suspend(int vetoable)
apm_error("suspend", err);
err = (err == APM_SUCCESS) ? 0 : -EIO;
+ syscore_resume();
sysdev_resume();
local_irq_enable();
@@ -1280,6 +1283,7 @@ static void standby(void)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
err = set_system_power_state(APM_STATE_STANDBY);
@@ -1287,6 +1291,7 @@ static void standby(void)
apm_error("standby", err);
local_irq_disable();
+ syscore_resume();
sysdev_resume();
local_irq_enable();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3ecece0217ef..bb9eb29a52dd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
/* As a rule processors have APIC timer running in deep C states */
if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ /*
+ * Disable GART TLB Walk Errors on Fam10h. We do this here
+ * because this is always needed when GART is enabled, even in a
+ * kernel which has no MCE support built in.
+ */
+ if (c->x86 == 0x10) {
+ /*
+ * BIOS should disable GartTlbWlk Errors themself. If
+ * it doesn't do it here as suggested by the BKDG.
+ *
+ * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+ */
+ u64 mask;
+
+ rdmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ mask |= (1 << 10);
+ wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ }
}
#ifdef CONFIG_X86_32
@@ -679,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
*/
const int amd_erratum_400[] =
- AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+ AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
EXPORT_SYMBOL_GPL(amd_erratum_400);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index eed3673a8656..e638689279d3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -586,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
return -EOPNOTSUPP;
}
+ /*
+ * Do not allow config1 (extended registers) to propagate,
+ * there's no sane user-space generalization yet:
+ */
if (attr->type == PERF_TYPE_RAW)
- return x86_pmu_extra_regs(event->attr.config, event);
+ return 0;
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, event);
@@ -609,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event)
/*
* Branch tracing:
*/
- if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
- (hwc->sample_period == 1)) {
+ if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+ !attr->freq && hwc->sample_period == 1) {
/* BTS is not supported by this architecture. */
if (!x86_pmu.bts_active)
return -EOPNOTSUPP;
@@ -1284,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
cpuc = &__get_cpu_var(cpu_hw_events);
+ /*
+ * Some chipsets need to unmask the LVTPC in a particular spot
+ * inside the nmi handler. As a result, the unmasking was pushed
+ * into all the nmi handlers.
+ *
+ * This generic handler doesn't seem to have any issues where the
+ * unmasking occurs so it was left at the top.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
if (!test_bit(idx, cpuc->active_mask)) {
/*
@@ -1370,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self,
return NOTIFY_DONE;
}
- apic_write(APIC_LVTPC, APIC_DM_NMI);
-
handled = x86_pmu.handle_irq(args->regs);
if (!handled)
return NOTIFY_DONE;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62bbd774..cf4e369cea67 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
- [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
+ [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
*
* Exceptions:
*
+ * 0x000 FP PERF_CTL[3], PERF_CTL[5:3] (*)
* 0x003 FP PERF_CTL[3]
+ * 0x004 FP PERF_CTL[3], PERF_CTL[5:3] (*)
* 0x00B FP PERF_CTL[3]
* 0x00D FP PERF_CTL[3]
* 0x023 DE PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
* 0x0DF LS PERF_CTL[5:0]
* 0x1D6 EX PERF_CTL[5:0]
* 0x1D8 EX PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
*/
static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
static struct event_constraint *
amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
{
- unsigned int event_code = amd_get_event_code(&event->hw);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int event_code = amd_get_event_code(hwc);
switch (event_code & AMD_EVENT_TYPE_MASK) {
case AMD_EVENT_FP:
switch (event_code) {
+ case 0x000:
+ if (!(hwc->config & 0x0000F000ULL))
+ break;
+ if (!(hwc->config & 0x00000F00ULL))
+ break;
+ return &amd_f15_PMC3;
+ case 0x004:
+ if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+ break;
+ return &amd_f15_PMC3;
case 0x003:
case 0x00B:
case 0x00D:
return &amd_f15_PMC3;
- default:
- return &amd_f15_PMC53;
}
+ return &amd_f15_PMC53;
case AMD_EVENT_LS:
case AMD_EVENT_DC:
case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2cee1da..447a28de6f09 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -25,7 +25,7 @@ struct intel_percore {
/*
* Intel PerfMon, used on Core and later.
*/
-static const u64 intel_perfmon_event_map[] =
+static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
@@ -184,26 +184,23 @@ static __initconst const u64 snb_hw_cache_event_ids
},
},
[ C(LL ) ] = {
- /*
- * TBD: Need Off-core Response Performance Monitoring support
- */
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
- /* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -285,26 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
- /* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
- [ C(RESULT_ACCESS) ] = 0x01bb,
- /* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -352,16 +349,36 @@ static __initconst const u64 westmere_hw_cache_event_ids
};
/*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
*/
-#define DMND_DATA_RD (1 << 0)
-#define DMND_RFO (1 << 1)
-#define DMND_WB (1 << 3)
-#define PF_DATA_RD (1 << 4)
-#define PF_DATA_RFO (1 << 5)
-#define RESP_UNCORE_HIT (1 << 8)
-#define RESP_MISS (0xf600) /* non uncore hit */
+#define NHM_DMND_DATA_RD (1 << 0)
+#define NHM_DMND_RFO (1 << 1)
+#define NHM_DMND_IFETCH (1 << 2)
+#define NHM_DMND_WB (1 << 3)
+#define NHM_PF_DATA_RD (1 << 4)
+#define NHM_PF_DATA_RFO (1 << 5)
+#define NHM_PF_IFETCH (1 << 6)
+#define NHM_OFFCORE_OTHER (1 << 7)
+#define NHM_UNCORE_HIT (1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP (1 << 9)
+#define NHM_OTHER_CORE_HITM (1 << 10)
+ /* reserved */
+#define NHM_REMOTE_CACHE_FWD (1 << 12)
+#define NHM_REMOTE_DRAM (1 << 13)
+#define NHM_LOCAL_DRAM (1 << 14)
+#define NHM_NON_DRAM (1 << 15)
+
+#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ (NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS)
static __initconst const u64 nehalem_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
@@ -370,16 +387,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS,
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
},
}
};
@@ -391,12 +408,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
{
[ C(L1D) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
- [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
- [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
@@ -933,6 +950,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
cpuc = &__get_cpu_var(cpu_hw_events);
+ /*
+ * Some chipsets need to unmask the LVTPC in a particular spot
+ * inside the nmi handler. As a result, the unmasking was pushed
+ * into all the nmi handlers.
+ *
+ * This handler doesn't seem to have any issues with the unmasking
+ * so it was left at the top.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
@@ -998,6 +1025,9 @@ intel_bts_constraints(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
unsigned int hw_event, bts_event;
+ if (event->attr.freq)
+ return NULL;
+
hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
@@ -1305,7 +1335,7 @@ static void intel_clovertown_quirks(void)
* AJ106 could possibly be worked around by not allowing LBR
* usage from PEBS, including the fixup.
* AJ68 could possibly be worked around by always programming
- * a pebs_event_reset[0] value and coping with the lost events.
+ * a pebs_event_reset[0] value and coping with the lost events.
*
* But taken together it might just make sense to not enable PEBS on
* these chips.
@@ -1409,6 +1439,18 @@ static __init int intel_pmu_init(void)
x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
+
+ if (ebx & 0x40) {
+ /*
+ * Erratum AAJ80 detected, we work it around by using
+ * the BR_MISP_EXEC.ANY event. This will over-count
+ * branch-misses, but it's still much better than the
+ * architectural event which is often completely bogus:
+ */
+ intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+
+ pr_cont("erratum AAJ80 worked around, ");
+ }
pr_cont("Nehalem events, ");
break;
@@ -1425,6 +1467,7 @@ static __init int intel_pmu_init(void)
case 37: /* 32 nm nehalem, "Clarkdale" */
case 44: /* 32 nm nehalem, "Gulftown" */
+ case 47: /* 32 nm Xeon E7 */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index c2520e178d32..e93fcd55fae1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -947,14 +947,23 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
if (!x86_perf_event_set_period(event))
continue;
if (perf_event_overflow(event, 1, &data, regs))
- p4_pmu_disable_event(event);
+ x86_pmu_stop(event, 0);
}
- if (handled) {
- /* p4 quirk: unmask it again */
- apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+ if (handled)
inc_irq_stat(apic_perf_irqs);
- }
+
+ /*
+ * When dealing with the unmasking of the LVTPC on P4 perf hw, it has
+ * been observed that the OVF bit flag has to be cleared first _before_
+ * the LVTPC can be unmasked.
+ *
+ * The reason is the NMI line will continue to be asserted while the OVF
+ * bit is set. This causes a second NMI to generate if the LVTPC is
+ * unmasked before the OVF bit is cleared, leading to unknown NMI
+ * messages.
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 706a9fb46a58..e90f08458e6b 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -391,7 +391,7 @@ static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
- return io_apic_setup_irq_pin(*out_hwirq, cpu_to_node(0), &attr);
+ return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr);
}
static void __init ioapic_add_ofnode(struct device_node *np)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 82ada01625b9..b117efd24f71 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
#define AGPEXTERN
#endif
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR (1ULL << 40)
+
/* backdoor interface to AGP driver */
AGPEXTERN int agp_memory_reserved;
AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
size_t size, int dir, unsigned long align_mask)
{
unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
- unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+ unsigned long iommu_page;
int i;
+ if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+ return bad_dma_addr;
+
+ iommu_page = alloc_iommu(dev, npages, align_mask);
if (iommu_page == -1) {
if (!nonforced_iommu(dev, phys_mem, size))
return phys_mem;
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 55d745ec1181..35ccf75696eb 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -50,20 +50,14 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
struct iommu_table_entry *finish)
{
struct iommu_table_entry *p, *q, *x;
- char sym_p[KSYM_SYMBOL_LEN];
- char sym_q[KSYM_SYMBOL_LEN];
/* Simple cyclic dependency checker. */
for (p = start; p < finish; p++) {
q = find_dependents_of(start, finish, p);
x = find_dependents_of(start, finish, q);
if (p == x) {
- sprint_symbol(sym_p, (unsigned long)p->detect);
- sprint_symbol(sym_q, (unsigned long)q->detect);
-
- printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
- " on %s and vice-versa. BREAKING IT.\n",
- sym_p, sym_q);
+ printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
+ p->detect, q->detect);
/* Heavy handed way..*/
x->depend = 0;
}
@@ -72,12 +66,8 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
for (p = start; p < finish; p++) {
q = find_dependents_of(p, finish, p);
if (q && q > p) {
- sprint_symbol(sym_p, (unsigned long)p->detect);
- sprint_symbol(sym_q, (unsigned long)q->detect);
-
- printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
- "should be called before %s!\n",
- sym_p, sym_q);
+ printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
+ p->detect, q->detect);
}
}
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 45892dc4b72a..f65e5b521dbd 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
unsigned len, type;
struct perf_event *bp;
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
+
data &= ~DR_CONTROL_RESERVED;
old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
restore:
@@ -655,6 +658,9 @@ restore:
}
goto restore;
}
+
+ ptrace_put_breakpoints(tsk);
+
return ((orig_ret < 0) ? orig_ret : rc);
}
@@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
if (n < HBP_NUM) {
struct perf_event *bp;
+
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
+
bp = thread->ptrace_bps[n];
if (!bp)
- return 0;
- val = bp->hw.info.address;
+ val = 0;
+ else
+ val = bp->hw.info.address;
+
+ ptrace_put_breakpoints(tsk);
} else if (n == 6) {
val = thread->debugreg6;
} else if (n == 7) {
@@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
struct perf_event *bp;
struct thread_struct *t = &tsk->thread;
struct perf_event_attr attr;
+ int err = 0;
+
+ if (ptrace_get_breakpoints(tsk) < 0)
+ return -ESRCH;
if (!t->ptrace_bps[nr]) {
ptrace_breakpoint_init(&attr);
@@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
* writing for the user. And anyway this is the previous
* behaviour.
*/
- if (IS_ERR(bp))
- return PTR_ERR(bp);
+ if (IS_ERR(bp)) {
+ err = PTR_ERR(bp);
+ goto put;
+ }
t->ptrace_bps[nr] = bp;
} else {
- int err;
-
bp = t->ptrace_bps[nr];
attr = bp->attr;
attr.bp_addr = addr;
err = modify_user_hw_breakpoint(bp, &attr);
- if (err)
- return err;
}
-
- return 0;
+put:
+ ptrace_put_breakpoints(tsk);
+ return err;
}
/*
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
index 29092b38d816..1d5c46df0d78 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/kernel/reboot_32.S
@@ -21,26 +21,26 @@ r_base = .
/* Get our own relocated address */
call 1f
1: popl %ebx
- subl $1b, %ebx
+ subl $(1b - r_base), %ebx
/* Compute the equivalent real-mode segment */
movl %ebx, %ecx
shrl $4, %ecx
/* Patch post-real-mode segment jump */
- movw dispatch_table(%ebx,%eax,2),%ax
- movw %ax, 101f(%ebx)
- movw %cx, 102f(%ebx)
+ movw (dispatch_table - r_base)(%ebx,%eax,2),%ax
+ movw %ax, (101f - r_base)(%ebx)
+ movw %cx, (102f - r_base)(%ebx)
/* Set up the IDT for real mode. */
- lidtl machine_real_restart_idt(%ebx)
+ lidtl (machine_real_restart_idt - r_base)(%ebx)
/*
* Set up a GDT from which we can load segment descriptors for real
* mode. The GDT is not used in real mode; it is just needed here to
* prepare the descriptors.
*/
- lgdtl machine_real_restart_gdt(%ebx)
+ lgdtl (machine_real_restart_gdt - r_base)(%ebx)
/*
* Load the data segment registers with 16-bit compatible values
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5a0484a95ad6..4be9b398470e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -976,6 +976,11 @@ void __init setup_arch(char **cmdline_p)
paging_init();
x86_init.paging.pagetable_setup_done(swapper_pg_dir);
+ if (boot_cpu_data.cpuid_level >= 0) {
+ /* A CPU has %cr4 if and only if it has CPUID */
+ mmu_cr4_features = read_cr4();
+ }
+
#ifdef CONFIG_X86_32
/* sync back kernel address range */
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
generated by cgit v1.2.3 (git 2.39.1) at 2025-12-13 06:49:35 +0000