aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/alternative.c5
-rw-r--r--arch/x86/kernel/apic/apic.c3
-rw-r--r--arch/x86/kernel/apic/io_apic.c74
-rw-r--r--arch/x86/kernel/apic/msi.c118
-rw-r--r--arch/x86/kernel/apic/probe_32.c3
-rw-r--r--arch/x86/kernel/apic/probe_64.c3
-rw-r--r--arch/x86/kernel/apic/vector.c3
-rw-r--r--arch/x86/kernel/cpu/common.c63
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c60
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c92
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h49
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c16
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c85
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--arch/x86/kernel/devicetree.c4
-rw-r--r--arch/x86/kernel/dumpstack.c3
-rw-r--r--arch/x86/kernel/fpu/init.c41
-rw-r--r--arch/x86/kernel/fpu/xstate.c63
-rw-r--r--arch/x86/kernel/hw_breakpoint.c58
-rw-r--r--arch/x86/kernel/kgdb.c5
-rw-r--r--arch/x86/kernel/kprobes/core.c109
-rw-r--r--arch/x86/kernel/kprobes/opt.c5
-rw-r--r--arch/x86/kernel/mpparse.c27
-rw-r--r--arch/x86/kernel/msr.c18
-rw-r--r--arch/x86/kernel/nmi.c5
-rw-r--r--arch/x86/kernel/paravirt.c19
-rw-r--r--arch/x86/kernel/paravirt_patch.c17
-rw-r--r--arch/x86/kernel/process_64.c8
-rw-r--r--arch/x86/kernel/ptrace.c6
-rw-r--r--arch/x86/kernel/setup.c3
-rw-r--r--arch/x86/kernel/static_call.c98
-rw-r--r--arch/x86/kernel/traps.c146
-rw-r--r--arch/x86/kernel/tsc.c10
-rw-r--r--arch/x86/kernel/vmlinux.lds.S40
-rw-r--r--arch/x86/kernel/x86_init.c26
38 files changed, 624 insertions, 673 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e77261db2391..de09af019e23 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -68,6 +68,7 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
obj-y += irqflags.o
+obj-y += static_call.o
obj-y += process.o
obj-y += fpu/
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index cdaab30880b9..4adbe65afe23 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1103,6 +1103,10 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
*/
goto out_put;
+ case RET_INSN_OPCODE:
+ int3_emulate_ret(regs);
+ break;
+
case CALL_INSN_OPCODE:
int3_emulate_call(regs, (long)ip + tp->rel32);
break;
@@ -1277,6 +1281,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
switch (tp->opcode) {
case INT3_INSN_OPCODE:
+ case RET_INSN_OPCODE:
break;
case CALL_INSN_OPCODE:
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5f943b938167..b3eef1d5c903 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1429,6 +1429,9 @@ void __init apic_intr_mode_init(void)
break;
}
+ if (x86_platform.apic_post_init)
+ x86_platform.apic_post_init();
+
apic_bsp_setup(upmode);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 21f9c7f11779..7b3c7e0d4a09 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -860,10 +860,10 @@ void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
{
init_irq_alloc_info(info, NULL);
info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
- info->ioapic_node = node;
- info->ioapic_trigger = trigger;
- info->ioapic_polarity = polarity;
- info->ioapic_valid = 1;
+ info->ioapic.node = node;
+ info->ioapic.trigger = trigger;
+ info->ioapic.polarity = polarity;
+ info->ioapic.valid = 1;
}
#ifndef CONFIG_ACPI
@@ -878,32 +878,32 @@ static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
copy_irq_alloc_info(dst, src);
dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
- dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
- dst->ioapic_pin = pin;
- dst->ioapic_valid = 1;
- if (src && src->ioapic_valid) {
- dst->ioapic_node = src->ioapic_node;
- dst->ioapic_trigger = src->ioapic_trigger;
- dst->ioapic_polarity = src->ioapic_polarity;
+ dst->devid = mpc_ioapic_id(ioapic_idx);
+ dst->ioapic.pin = pin;
+ dst->ioapic.valid = 1;
+ if (src && src->ioapic.valid) {
+ dst->ioapic.node = src->ioapic.node;
+ dst->ioapic.trigger = src->ioapic.trigger;
+ dst->ioapic.polarity = src->ioapic.polarity;
} else {
- dst->ioapic_node = NUMA_NO_NODE;
+ dst->ioapic.node = NUMA_NO_NODE;
if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
- dst->ioapic_trigger = trigger;
- dst->ioapic_polarity = polarity;
+ dst->ioapic.trigger = trigger;
+ dst->ioapic.polarity = polarity;
} else {
/*
* PCI interrupts are always active low level
* triggered.
*/
- dst->ioapic_trigger = IOAPIC_LEVEL;
- dst->ioapic_polarity = IOAPIC_POL_LOW;
+ dst->ioapic.trigger = IOAPIC_LEVEL;
+ dst->ioapic.polarity = IOAPIC_POL_LOW;
}
}
}
static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
{
- return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+ return (info && info->ioapic.valid) ? info->ioapic.node : NUMA_NO_NODE;
}
static void mp_register_handler(unsigned int irq, unsigned long trigger)
@@ -933,14 +933,14 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
* pin with real trigger and polarity attributes.
*/
if (irq < nr_legacy_irqs() && data->count == 1) {
- if (info->ioapic_trigger != data->trigger)
- mp_register_handler(irq, info->ioapic_trigger);
- data->entry.trigger = data->trigger = info->ioapic_trigger;
- data->entry.polarity = data->polarity = info->ioapic_polarity;
+ if (info->ioapic.trigger != data->trigger)
+ mp_register_handler(irq, info->ioapic.trigger);
+ data->entry.trigger = data->trigger = info->ioapic.trigger;
+ data->entry.polarity = data->polarity = info->ioapic.polarity;
}
- return data->trigger == info->ioapic_trigger &&
- data->polarity == info->ioapic_polarity;
+ return data->trigger == info->ioapic.trigger &&
+ data->polarity == info->ioapic.polarity;
}
static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
@@ -1002,7 +1002,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain,
if (!mp_check_pin_attr(irq, info))
return -EBUSY;
if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
- info->ioapic_pin))
+ info->ioapic.pin))
return -ENOMEM;
} else {
info->flags |= X86_IRQ_ALLOC_LEGACY;
@@ -2092,8 +2092,8 @@ static int mp_alloc_timer_irq(int ioapic, int pin)
struct irq_alloc_info info;
ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
- info.ioapic_id = mpc_ioapic_id(ioapic);
- info.ioapic_pin = pin;
+ info.devid = mpc_ioapic_id(ioapic);
+ info.ioapic.pin = pin;
mutex_lock(&ioapic_mutex);
irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
mutex_unlock(&ioapic_mutex);
@@ -2297,9 +2297,9 @@ static int mp_irqdomain_create(int ioapic)
return 0;
init_irq_alloc_info(&info, NULL);
- info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
- info.ioapic_id = mpc_ioapic_id(ioapic);
- parent = irq_remapping_get_ir_irq_domain(&info);
+ info.type = X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT;
+ info.devid = mpc_ioapic_id(ioapic);
+ parent = irq_remapping_get_irq_domain(&info);
if (!parent)
parent = x86_vector_domain;
else
@@ -2933,9 +2933,9 @@ int mp_ioapic_registered(u32 gsi_base)
static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
struct irq_alloc_info *info)
{
- if (info && info->ioapic_valid) {
- data->trigger = info->ioapic_trigger;
- data->polarity = info->ioapic_polarity;
+ if (info && info->ioapic.valid) {
+ data->trigger = info->ioapic.trigger;
+ data->polarity = info->ioapic.polarity;
} else if (acpi_get_override_irq(gsi, &data->trigger,
&data->polarity) < 0) {
/* PCI interrupts are always active low level triggered. */
@@ -2981,7 +2981,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
return -EINVAL;
ioapic = mp_irqdomain_ioapic_idx(domain);
- pin = info->ioapic_pin;
+ pin = info->ioapic.pin;
if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
return -EEXIST;
@@ -2989,7 +2989,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
if (!data)
return -ENOMEM;
- info->ioapic_entry = &data->entry;
+ info->ioapic.entry = &data->entry;
ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
if (ret < 0) {
kfree(data);
@@ -2997,7 +2997,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
}
INIT_LIST_HEAD(&data->irq_2_pin);
- irq_data->hwirq = info->ioapic_pin;
+ irq_data->hwirq = info->ioapic.pin;
irq_data->chip = (domain->parent == x86_vector_domain) ?
&ioapic_chip : &ioapic_ir_chip;
irq_data->chip_data = data;
@@ -3007,8 +3007,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
local_irq_save(flags);
- if (info->ioapic_entry)
- mp_setup_entry(cfg, data, info->ioapic_entry);
+ if (info->ioapic.entry)
+ mp_setup_entry(cfg, data, info->ioapic.entry);
mp_register_handler(virq, data->trigger);
if (virq < nr_legacy_irqs())
legacy_pic->mask(virq);
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index c2b2911feeef..6313f0a05db7 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -21,7 +21,7 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
-static struct irq_domain *msi_default_domain;
+struct irq_domain *x86_pci_msi_default_domain __ro_after_init;
static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
{
@@ -45,7 +45,7 @@ static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
MSI_DATA_VECTOR(cfg->vector);
}
-static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
{
__irq_msi_compose_msg(irqd_cfg(data), msg);
}
@@ -177,40 +177,10 @@ static struct irq_chip pci_msi_controller = {
.irq_mask = pci_msi_mask_irq,
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .irq_compose_msi_msg = irq_msi_compose_msg,
.irq_set_affinity = msi_set_affinity,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
- struct irq_domain *domain;
- struct irq_alloc_info info;
-
- init_irq_alloc_info(&info, NULL);
- info.type = X86_IRQ_ALLOC_TYPE_MSI;
- info.msi_dev = dev;
-
- domain = irq_remapping_get_irq_domain(&info);
- if (domain == NULL)
- domain = msi_default_domain;
- if (domain == NULL)
- return -ENOSYS;
-
- return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
-}
-
-void native_teardown_msi_irq(unsigned int irq)
-{
- irq_domain_free_irqs(irq, 1);
-}
-
-static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
- msi_alloc_info_t *arg)
-{
- return arg->msi_hwirq;
-}
-
int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
msi_alloc_info_t *arg)
{
@@ -218,11 +188,10 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
struct msi_desc *desc = first_pci_msi_entry(pdev);
init_irq_alloc_info(arg, NULL);
- arg->msi_dev = pdev;
if (desc->msi_attrib.is_msix) {
- arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+ arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
} else {
- arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+ arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
}
@@ -230,16 +199,8 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
}
EXPORT_SYMBOL_GPL(pci_msi_prepare);
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
-{
- arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
-}
-EXPORT_SYMBOL_GPL(pci_msi_set_desc);
-
static struct msi_domain_ops pci_msi_domain_ops = {
- .get_hwirq = pci_msi_get_hwirq,
.msi_prepare = pci_msi_prepare,
- .set_desc = pci_msi_set_desc,
};
static struct msi_domain_info pci_msi_domain_info = {
@@ -251,25 +212,32 @@ static struct msi_domain_info pci_msi_domain_info = {
.handler_name = "edge",
};
-void __init arch_init_msi_domain(struct irq_domain *parent)
+struct irq_domain * __init native_create_pci_msi_domain(void)
{
struct fwnode_handle *fn;
+ struct irq_domain *d;
if (disable_apic)
- return;
+ return NULL;
fn = irq_domain_alloc_named_fwnode("PCI-MSI");
- if (fn) {
- msi_default_domain =
- pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
- parent);
- }
- if (!msi_default_domain) {
+ if (!fn)
+ return NULL;
+
+ d = pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
+ x86_vector_domain);
+ if (!d) {
irq_domain_free_fwnode(fn);
- pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
+ pr_warn("Failed to initialize PCI-MSI irqdomain.\n");
} else {
- msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
+ d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
}
+ return d;
+}
+
+void __init x86_create_pci_msi_domain(void)
+{
+ x86_pci_msi_default_domain = x86_init.irqs.create_pci_msi_domain();
}
#ifdef CONFIG_IRQ_REMAP
@@ -279,7 +247,6 @@ static struct irq_chip pci_msi_ir_controller = {
.irq_mask = pci_msi_mask_irq,
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -321,35 +288,28 @@ static struct irq_chip dmar_msi_controller = {
.irq_ack = irq_chip_ack_parent,
.irq_set_affinity = msi_domain_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .irq_compose_msi_msg = irq_msi_compose_msg,
.irq_write_msi_msg = dmar_msi_write_msg,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
- msi_alloc_info_t *arg)
-{
- return arg->dmar_id;
-}
-
static int dmar_msi_init(struct irq_domain *domain,
struct msi_domain_info *info, unsigned int virq,
irq_hw_number_t hwirq, msi_alloc_info_t *arg)
{
- irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
- handle_edge_irq, arg->dmar_data, "edge");
+ irq_domain_set_info(domain, virq, arg->devid, info->chip, NULL,
+ handle_edge_irq, arg->data, "edge");
return 0;
}
static struct msi_domain_ops dmar_msi_domain_ops = {
- .get_hwirq = dmar_msi_get_hwirq,
.msi_init = dmar_msi_init,
};
static struct msi_domain_info dmar_msi_domain_info = {
.ops = &dmar_msi_domain_ops,
.chip = &dmar_msi_controller,
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS,
};
static struct irq_domain *dmar_get_irq_domain(void)
@@ -384,8 +344,9 @@ int dmar_alloc_hwirq(int id, int node, void *arg)
init_irq_alloc_info(&info, NULL);
info.type = X86_IRQ_ALLOC_TYPE_DMAR;
- info.dmar_id = id;
- info.dmar_data = arg;
+ info.devid = id;
+ info.hwirq = id;
+ info.data = arg;
return irq_domain_alloc_irqs(domain, 1, node, &info);
}
@@ -419,24 +380,17 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
.irq_ack = irq_chip_ack_parent,
.irq_set_affinity = msi_domain_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .irq_compose_msi_msg = irq_msi_compose_msg,
.irq_write_msi_msg = hpet_msi_write_msg,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
- msi_alloc_info_t *arg)
-{
- return arg->hpet_index;
-}
-
static int hpet_msi_init(struct irq_domain *domain,
struct msi_domain_info *info, unsigned int virq,
irq_hw_number_t hwirq, msi_alloc_info_t *arg)
{
irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
- irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
- handle_edge_irq, arg->hpet_data, "edge");
+ irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL,
+ handle_edge_irq, arg->data, "edge");
return 0;
}
@@ -448,7 +402,6 @@ static void hpet_msi_free(struct irq_domain *domain,
}
static struct msi_domain_ops hpet_msi_domain_ops = {
- .get_hwirq = hpet_msi_get_hwirq,
.msi_init = hpet_msi_init,
.msi_free = hpet_msi_free,
};
@@ -456,6 +409,7 @@ static struct msi_domain_ops hpet_msi_domain_ops = {
static struct msi_domain_info hpet_msi_domain_info = {
.ops = &hpet_msi_domain_ops,
.chip = &hpet_msi_controller,
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS,
};
struct irq_domain *hpet_create_irq_domain(int hpet_id)
@@ -476,9 +430,9 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id)
domain_info->data = (void *)(long)hpet_id;
init_irq_alloc_info(&info, NULL);
- info.type = X86_IRQ_ALLOC_TYPE_HPET;
- info.hpet_id = hpet_id;
- parent = irq_remapping_get_ir_irq_domain(&info);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT;
+ info.devid = hpet_id;
+ parent = irq_remapping_get_irq_domain(&info);
if (parent == NULL)
parent = x86_vector_domain;
else
@@ -506,9 +460,9 @@ int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc,
init_irq_alloc_info(&info, NULL);
info.type = X86_IRQ_ALLOC_TYPE_HPET;
- info.hpet_data = hc;
- info.hpet_id = hpet_dev_id(domain);
- info.hpet_index = dev_num;
+ info.data = hc;
+ info.devid = hpet_dev_id(domain);
+ info.hwirq = dev_num;
return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
}
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 99ee61c9ba54..67b6f7c049ec 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -170,9 +170,6 @@ void __init default_setup_apic_routing(void)
if (apic->setup_apic_routing)
apic->setup_apic_routing();
-
- if (x86_platform.apic_post_init)
- x86_platform.apic_post_init();
}
void __init generic_apic_probe(void)
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index bd3835d6b535..c46720f185c0 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -32,9 +32,6 @@ void __init default_setup_apic_routing(void)
break;
}
}
-
- if (x86_platform.apic_post_init)
- x86_platform.apic_post_init();
}
int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index f8a56b5dc29f..1eac53632786 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -714,8 +714,6 @@ int __init arch_early_irq_init(void)
BUG_ON(x86_vector_domain == NULL);
irq_set_default_host(x86_vector_domain);
- arch_init_msi_domain(x86_vector_domain);
-
BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
/*
@@ -824,6 +822,7 @@ static struct irq_chip lapic_controller = {
.name = "APIC",
.irq_ack = apic_ack_edge,
.irq_set_affinity = apic_set_affinity,
+ .irq_compose_msi_msg = x86_vector_msi_compose_msg,
.irq_retrigger = apic_retrigger_irq,
};
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c5d6f17d9b9d..7824fc62c7cd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -23,6 +23,7 @@
#include <linux/syscore_ops.h>
#include <linux/pgtable.h>
+#include <asm/cmdline.h>
#include <asm/stackprotector.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
@@ -1221,6 +1222,59 @@ static void detect_nopl(void)
}
/*
+ * We parse cpu parameters early because fpu__init_system() is executed
+ * before parse_early_param().
+ */
+static void __init cpu_parse_early_param(void)
+{
+ char arg[128];
+ char *argptr = arg;
+ int arglen, res, bit;
+
+#ifdef CONFIG_X86_32
+ if (cmdline_find_option_bool(boot_command_line, "no387"))
+#ifdef CONFIG_MATH_EMULATION
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+#else
+ pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
+#endif
+
+ if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
+ setup_clear_cpu_cap(X86_FEATURE_FXSR);
+#endif
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsave"))
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+ if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+ arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
+ if (arglen <= 0)
+ return;
+
+ pr_info("Clearing CPUID bits:");
+ do {
+ res = get_option(&argptr, &bit);
+ if (res == 0 || res == 3)
+ break;
+
+ /* If the argument was too long, the last bit may be cut off */
+ if (res == 1 && arglen >= sizeof(arg))
+ break;
+
+ if (bit >= 0 && bit < NCAPINTS * 32) {
+ pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
+ setup_clear_cpu_cap(bit);
+ }
+ } while (res == 2);
+ pr_cont("\n");
+}
+
+/*
* Do minimum CPU detection early.
* Fields really needed: vendor, cpuid_level, family, model, mask,
* cache alignment.
@@ -1255,6 +1309,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
get_cpu_cap(c);
get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
+ cpu_parse_early_param();
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
@@ -1413,15 +1468,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
* ESPFIX issue, we can change this.
*/
#ifdef CONFIG_X86_32
-# ifdef CONFIG_PARAVIRT_XXL
- do {
- extern void native_iret(void);
- if (pv_ops.cpu.iret == native_iret)
- set_cpu_bug(c, X86_BUG_ESPFIX);
- } while (0);
-# else
set_cpu_bug(c, X86_BUG_ESPFIX);
-# endif
#endif
}
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 3cbe24ca80ab..d502241995a3 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -69,6 +69,8 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES },
+ { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA },
{}
};
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 31125448b174..9834a43cd0fa 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -248,7 +248,7 @@ static void __init ms_hyperv_init_platform(void)
hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF);
}
- if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+ if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
x86_platform.calibrate_tsc = hv_get_tsc_khz;
x86_platform.calibrate_cpu = hv_get_tsc_khz;
@@ -270,7 +270,7 @@ static void __init ms_hyperv_init_platform(void)
crash_kexec_post_notifiers = true;
#ifdef CONFIG_X86_LOCAL_APIC
- if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+ if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
/*
* Get the APIC frequency.
@@ -296,7 +296,7 @@ static void __init ms_hyperv_init_platform(void)
machine_ops.shutdown = hv_machine_shutdown;
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
- if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) {
+ if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
} else {
@@ -330,7 +330,7 @@ static void __init ms_hyperv_init_platform(void)
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback);
/* Setup the IDT for reenlightenment notifications */
- if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) {
+ if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) {
alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
asm_sysvec_hyperv_reenlightenment);
}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 6a9df71c1b9e..e5f4ee8f4c3b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -168,6 +168,7 @@ struct rdt_resource rdt_resources_all[] = {
.name = "MB",
.domains = domain_init(RDT_RESOURCE_MBA),
.cache_level = 3,
+ .parse_ctrlval = parse_bw,
.format_str = "%d=%*u",
.fflags = RFTYPE_RES_MB,
},
@@ -254,22 +255,30 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
{
union cpuid_0x10_3_eax eax;
union cpuid_0x10_x_edx edx;
- u32 ebx, ecx;
+ u32 ebx, ecx, max_delay;
cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
r->num_closid = edx.split.cos_max + 1;
- r->membw.max_delay = eax.split.max_delay + 1;
+ max_delay = eax.split.max_delay + 1;
r->default_ctrl = MAX_MBA_BW;
+ r->membw.arch_needs_linear = true;
if (ecx & MBA_IS_LINEAR) {
r->membw.delay_linear = true;
- r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
- r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+ r->membw.min_bw = MAX_MBA_BW - max_delay;
+ r->membw.bw_gran = MAX_MBA_BW - max_delay;
} else {
if (!rdt_get_mb_table(r))
return false;
+ r->membw.arch_needs_linear = false;
}
r->data_width = 3;
+ if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA))
+ r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
+ else
+ r->membw.throttle_mode = THREAD_THROTTLE_MAX;
+ thread_throttle_mode_init();
+
r->alloc_capable = true;
r->alloc_enabled = true;
@@ -288,7 +297,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
/* AMD does not use delay */
r->membw.delay_linear = false;
+ r->membw.arch_needs_linear = false;
+ /*
+ * AMD does not use memory delay throttle model to control
+ * the allocation like Intel does.
+ */
+ r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED;
r->membw.min_bw = 0;
r->membw.bw_gran = 1;
/* Max value is 2048, Data width should be 4 in decimal */
@@ -346,19 +361,6 @@ static void rdt_get_cdp_l2_config(void)
rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
}
-static int get_cache_id(int cpu, int level)
-{
- struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
- int i;
-
- for (i = 0; i < ci->num_leaves; i++) {
- if (ci->info_list[i].level == level)
- return ci->info_list[i].id;
- }
-
- return -1;
-}
-
static void
mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
{
@@ -556,13 +558,13 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
*/
static void domain_add_cpu(int cpu, struct rdt_resource *r)
{
- int id = get_cache_id(cpu, r->cache_level);
+ int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
struct list_head *add_pos = NULL;
struct rdt_domain *d;
d = rdt_find_domain(r, id, &add_pos);
if (IS_ERR(d)) {
- pr_warn("Could't find cache id for cpu %d\n", cpu);
+ pr_warn("Couldn't find cache id for CPU %d\n", cpu);
return;
}
@@ -602,12 +604,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
static void domain_remove_cpu(int cpu, struct rdt_resource *r)
{
- int id = get_cache_id(cpu, r->cache_level);
+ int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
struct rdt_domain *d;
d = rdt_find_domain(r, id, NULL);
if (IS_ERR_OR_NULL(d)) {
- pr_warn("Could't find cache id for cpu %d\n", cpu);
+ pr_warn("Couldn't find cache id for CPU %d\n", cpu);
return;
}
@@ -918,12 +920,12 @@ static __init void rdt_init_res_defs_intel(void)
r->rid == RDT_RESOURCE_L3CODE ||
r->rid == RDT_RESOURCE_L2 ||
r->rid == RDT_RESOURCE_L2DATA ||
- r->rid == RDT_RESOURCE_L2CODE)
- r->cbm_validate = cbm_validate_intel;
- else if (r->rid == RDT_RESOURCE_MBA) {
+ r->rid == RDT_RESOURCE_L2CODE) {
+ r->cache.arch_has_sparse_bitmaps = false;
+ r->cache.arch_has_empty_bitmaps = false;
+ } else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_THRTL_BASE;
r->msr_update = mba_wrmsr_intel;
- r->parse_ctrlval = parse_bw_intel;
}
}
}
@@ -938,12 +940,12 @@ static __init void rdt_init_res_defs_amd(void)
r->rid == RDT_RESOURCE_L3CODE ||
r->rid == RDT_RESOURCE_L2 ||
r->rid == RDT_RESOURCE_L2DATA ||
- r->rid == RDT_RESOURCE_L2CODE)
- r->cbm_validate = cbm_validate_amd;
- else if (r->rid == RDT_RESOURCE_MBA) {
+ r->rid == RDT_RESOURCE_L2CODE) {
+ r->cache.arch_has_sparse_bitmaps = true;
+ r->cache.arch_has_empty_bitmaps = true;
+ } else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_BW_BASE;
r->msr_update = mba_wrmsr_amd;
- r->parse_ctrlval = parse_bw_amd;
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 934c8fb8a64a..c877642e8a14 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -23,53 +23,6 @@
/*
* Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and maximum bandwidth values specified by
- * the hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate_amd(char *buf, unsigned long *data,
- struct rdt_resource *r)
-{
- unsigned long bw;
- int ret;
-
- ret = kstrtoul(buf, 10, &bw);
- if (ret) {
- rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
- return false;
- }
-
- if (bw < r->membw.min_bw || bw > r->default_ctrl) {
- rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
- r->membw.min_bw, r->default_ctrl);
- return false;
- }
-
- *data = roundup(bw, (unsigned long)r->membw.bw_gran);
- return true;
-}
-
-int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
- struct rdt_domain *d)
-{
- unsigned long bw_val;
-
- if (d->have_new_ctrl) {
- rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
- return -EINVAL;
- }
-
- if (!bw_validate_amd(data->buf, &bw_val, r))
- return -EINVAL;
-
- d->new_ctrl = bw_val;
- d->have_new_ctrl = true;
-
- return 0;
-}
-
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
* checked against the minimum and max bandwidth values specified by the
* hardware. The allocated bandwidth percentage is rounded to the next
* control step available on the hardware.
@@ -82,7 +35,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
/*
* Only linear delay values is supported for current Intel SKUs.
*/
- if (!r->membw.delay_linear) {
+ if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
rdt_last_cmd_puts("No support for non-linear MB domains\n");
return false;
}
@@ -104,8 +57,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return true;
}
-int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
- struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
unsigned long bw_val;
@@ -123,12 +76,14 @@ int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
}
/*
- * Check whether a cache bit mask is valid. The SDM says:
+ * Check whether a cache bit mask is valid.
+ * For Intel the SDM says:
* Please note that all (and only) contiguous '1' combinations
* are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
* Additionally Haswell requires at least two bits set.
+ * AMD allows non-contiguous bitmasks.
*/
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
{
unsigned long first_bit, zero_bit, val;
unsigned int cbm_len = r->cache.cbm_len;
@@ -140,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
return false;
}
- if (val == 0 || val > r->default_ctrl) {
+ if ((!r->cache.arch_has_empty_bitmaps && val == 0) ||
+ val > r->default_ctrl) {
rdt_last_cmd_puts("Mask out of range\n");
return false;
}
@@ -148,7 +104,9 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
first_bit = find_first_bit(&val, cbm_len);
zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
- if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+ /* Are non-contiguous bitmaps allowed? */
+ if (!r->cache.arch_has_sparse_bitmaps &&
+ (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
return false;
}
@@ -164,30 +122,6 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
}
/*
- * Check whether a cache bit mask is valid. AMD allows non-contiguous
- * bitmasks
- */
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 16, &val);
- if (ret) {
- rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
- return false;
- }
-
- if (val > r->default_ctrl) {
- rdt_last_cmd_puts("Mask out of range\n");
- return false;
- }
-
- *data = val;
- return true;
-}
-
-/*
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
@@ -212,7 +146,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
return -EINVAL;
}
- if (!r->cbm_validate(data->buf, &cbm_val, r))
+ if (!cbm_validate(data->buf, &cbm_val, r))
return -EINVAL;
if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 5ffa32256b3b..80fa997fae60 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -283,7 +283,6 @@ struct rftype {
* struct mbm_state - status for each MBM counter in each domain
* @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
* @prev_msr Value of IA32_QM_CTR for this RMID last time we read it
- * @chunks_bw Total local data moved. Used for bandwidth calculation
* @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
* @prev_bw The most recent bandwidth in MBps
* @delta_bw Difference between the current and previous bandwidth
@@ -292,7 +291,6 @@ struct rftype {
struct mbm_state {
u64 chunks;
u64 prev_msr;
- u64 chunks_bw;
u64 prev_bw_msr;
u32 prev_bw;
u32 delta_bw;
@@ -360,6 +358,8 @@ struct msr_param {
* in a cache bit mask
* @shareable_bits: Bitmask of shareable resource with other
* executing entities
+ * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid.
+ * @arch_has_empty_bitmaps: True if the '0' bitmap is valid.
*/
struct rdt_cache {
unsigned int cbm_len;
@@ -367,25 +367,43 @@ struct rdt_cache {
unsigned int cbm_idx_mult;
unsigned int cbm_idx_offset;
unsigned int shareable_bits;
+ bool arch_has_sparse_bitmaps;
+ bool arch_has_empty_bitmaps;
+};
+
+/**
+ * enum membw_throttle_mode - System's memory bandwidth throttling mode
+ * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system
+ * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core
+ * always using smallest bandwidth percentage
+ * assigned to threads, aka "max throttling"
+ * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread
+ */
+enum membw_throttle_mode {
+ THREAD_THROTTLE_UNDEFINED = 0,
+ THREAD_THROTTLE_MAX,
+ THREAD_THROTTLE_PER_THREAD,
};
/**
* struct rdt_membw - Memory bandwidth allocation related data
- * @max_delay: Max throttle delay. Delay is the hardware
- * representation for memory bandwidth.
* @min_bw: Minimum memory bandwidth percentage user can request
* @bw_gran: Granularity at which the memory bandwidth is allocated
* @delay_linear: True if memory B/W delay is in linear scale
+ * @arch_needs_linear: True if we can't configure non-linear resources
+ * @throttle_mode: Bandwidth throttling mode when threads request
+ * different memory bandwidths
* @mba_sc: True if MBA software controller(mba_sc) is enabled
* @mb_map: Mapping of memory B/W percentage to memory B/W delay
*/
struct rdt_membw {
- u32 max_delay;
- u32 min_bw;
- u32 bw_gran;
- u32 delay_linear;
- bool mba_sc;
- u32 *mb_map;
+ u32 min_bw;
+ u32 bw_gran;
+ u32 delay_linear;
+ bool arch_needs_linear;
+ enum membw_throttle_mode throttle_mode;
+ bool mba_sc;
+ u32 *mb_map;
};
static inline bool is_llc_occupancy_enabled(void)
@@ -437,7 +455,6 @@ struct rdt_parse_data {
* @cache: Cache allocation related data
* @format_str: Per resource format string to show domain value
* @parse_ctrlval: Per resource function pointer to parse control values
- * @cbm_validate Cache bitmask validate function
* @evt_list: List of monitoring events
* @num_rmid: Number of RMIDs available
* @mon_scale: cqm counter * mon_scale = occupancy in bytes
@@ -464,7 +481,6 @@ struct rdt_resource {
int (*parse_ctrlval)(struct rdt_parse_data *data,
struct rdt_resource *r,
struct rdt_domain *d);
- bool (*cbm_validate)(char *buf, u32 *data, struct rdt_resource *r);
struct list_head evt_list;
int num_rmid;
unsigned int mon_scale;
@@ -474,10 +490,8 @@ struct rdt_resource {
int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
struct rdt_domain *d);
-int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
- struct rdt_domain *d);
-int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
- struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
@@ -609,8 +623,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
+void __init thread_throttle_mode_init(void);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 837d7d012b7b..54dffe574e67 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -279,8 +279,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
return;
chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
- m->chunks_bw += chunks;
- m->chunks = m->chunks_bw;
+ m->chunks += chunks;
cur_bw = (chunks * r->mon_scale) >> 20;
if (m->delta_comp)
@@ -478,19 +477,13 @@ void cqm_handle_limbo(struct work_struct *work)
mutex_lock(&rdtgroup_mutex);
r = &rdt_resources_all[RDT_RESOURCE_L3];
- d = get_domain_from_cpu(cpu, r);
-
- if (!d) {
- pr_warn_once("Failure to get domain for limbo worker\n");
- goto out_unlock;
- }
+ d = container_of(work, struct rdt_domain, cqm_limbo.work);
__check_limbo(d, false);
if (has_busy_rmid(r, d))
schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
-out_unlock:
mutex_unlock(&rdtgroup_mutex);
}
@@ -520,10 +513,7 @@ void mbm_handle_overflow(struct work_struct *work)
goto out_unlock;
r = &rdt_resources_all[RDT_RESOURCE_L3];
-
- d = get_domain_from_cpu(cpu, r);
- if (!d)
- goto out_unlock;
+ d = container_of(work, struct rdt_domain, mbm_over.work);
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
mbm_update(r, d, prgrp->mon.rmid);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 3f844f14fc0a..b494187632b2 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -592,6 +592,18 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
return ret;
}
+static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
+{
+ return (rdt_alloc_capable &&
+ (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
+}
+
+static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
+{
+ return (rdt_mon_capable &&
+ (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
+}
+
/**
* rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
* @r: Resource group
@@ -607,8 +619,7 @@ int rdtgroup_tasks_assigned(struct rdtgroup *r)
rcu_read_lock();
for_each_process_thread(p, t) {
- if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
- (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+ if (is_closid_match(t, r) || is_rmid_match(t, r)) {
ret = 1;
break;
}
@@ -706,8 +717,7 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
rcu_read_lock();
for_each_process_thread(p, t) {
- if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
- (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
+ if (is_closid_match(t, r) || is_rmid_match(t, r))
seq_printf(s, "%d\n", t->pid);
}
rcu_read_unlock();
@@ -1017,6 +1027,19 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
return 0;
}
+static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+
+ if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
+ seq_puts(seq, "per-thread\n");
+ else
+ seq_puts(seq, "max\n");
+
+ return 0;
+}
+
static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
@@ -1513,6 +1536,17 @@ static struct rftype res_common_files[] = {
.seq_show = rdt_delay_linear_show,
.fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
},
+ /*
+ * Platform specific which (if any) capabilities are provided by
+ * thread_throttle_mode. Defer "fflags" initialization to platform
+ * discovery.
+ */
+ {
+ .name = "thread_throttle_mode",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdt_thread_throttle_mode_show,
+ },
{
.name = "max_threshold_occupancy",
.mode = 0644,
@@ -1583,7 +1617,7 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
lockdep_assert_held(&rdtgroup_mutex);
for (rft = rfts; rft < rfts + len; rft++) {
- if ((fflags & rft->fflags) == rft->fflags) {
+ if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
ret = rdtgroup_add_file(kn, rft);
if (ret)
goto error;
@@ -1600,6 +1634,33 @@ error:
return ret;
}
+static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
+{
+ struct rftype *rfts, *rft;
+ int len;
+
+ rfts = res_common_files;
+ len = ARRAY_SIZE(res_common_files);
+
+ for (rft = rfts; rft < rfts + len; rft++) {
+ if (!strcmp(rft->name, name))
+ return rft;
+ }
+
+ return NULL;
+}
+
+void __init thread_throttle_mode_init(void)
+{
+ struct rftype *rft;
+
+ rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
+ if (!rft)
+ return;
+
+ rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
+}
+
/**
* rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
* @r: The resource group with which the file is associated.
@@ -2245,18 +2306,6 @@ static int reset_all_ctrls(struct rdt_resource *r)
return 0;
}
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
- return (rdt_alloc_capable &&
- (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
- return (rdt_mon_capable &&
- (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
-}
-
/*
* Move tasks from one to the other group. If @from is NULL, then all tasks
* in the systems are moved unconditionally (used for teardown).
@@ -3196,7 +3245,7 @@ int __init rdtgroup_init(void)
* It may also be ok since that would enable debugging of RDT before
* resctrl is mounted.
* The reason why the debugfs directory is created here and not in
- * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+ * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
* during the debugfs directory creation also &sb->s_type->i_mutex_key
* (the lockdep class of inode->i_rwsem). Other filesystem
* interactions (eg. SyS_getdents) have the lock ordering:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3221b71a0df8..2eb0a8c44b35 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -35,6 +35,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
{ X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 },
{ X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 },
+ { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 },
{ X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index a0e8fc7d85f1..ddffd80f5c52 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -229,8 +229,8 @@ static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
it = &of_ioapic_type[type_index];
ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
- tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
- tmp.ioapic_pin = fwspec->param[0];
+ tmp.devid = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+ tmp.ioapic.pin = fwspec->param[0];
return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 48ce44576947..ea8d51ec251b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -115,7 +115,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
unsigned long prologue = regs->ip - PROLOGUE_SIZE;
if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
- printk("%sCode: Bad RIP value.\n", loglvl);
+ printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
+ loglvl, prologue);
} else {
printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
__stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 61ddc3a5e5c2..701f196d7c68 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -5,7 +5,6 @@
#include <asm/fpu/internal.h>
#include <asm/tlbflush.h>
#include <asm/setup.h>
-#include <asm/cmdline.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
@@ -238,51 +237,11 @@ static void __init fpu__init_system_ctx_switch(void)
}
/*
- * We parse fpu parameters early because fpu__init_system() is executed
- * before parse_early_param().
- */
-static void __init fpu__init_parse_early_param(void)
-{
- char arg[32];
- char *argptr = arg;
- int bit;
-
-#ifdef CONFIG_X86_32
- if (cmdline_find_option_bool(boot_command_line, "no387"))
-#ifdef CONFIG_MATH_EMULATION
- setup_clear_cpu_cap(X86_FEATURE_FPU);
-#else
- pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
-#endif
-
- if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
-#endif
-
- if (cmdline_find_option_bool(boot_command_line, "noxsave"))
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-
- if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
- if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
- if (cmdline_find_option(boot_command_line, "clearcpuid", arg,
- sizeof(arg)) &&
- get_option(&argptr, &bit) &&
- bit >= 0 &&
- bit < NCAPINTS * 32)
- setup_clear_cpu_cap(bit);
-}
-
-/*
* Called on the boot CPU once per system bootup, to set up the initial
* FPU state that is later cloned into all processes:
*/
void __init fpu__init_system(struct cpuinfo_x86 *c)
{
- fpu__init_parse_early_param();
fpu__init_system_early_generic(c);
/*
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 038e19c0019e..5d8047441a0a 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -37,6 +37,7 @@ static const char *xfeature_names[] =
"AVX-512 ZMM_Hi256" ,
"Processor Trace (unused)" ,
"Protection Keys User registers",
+ "PASID state",
"unknown xstate feature" ,
};
@@ -51,6 +52,7 @@ static short xsave_cpuid_features[] __initdata = {
X86_FEATURE_AVX512F,
X86_FEATURE_INTEL_PT,
X86_FEATURE_PKU,
+ X86_FEATURE_ENQCMD,
};
/*
@@ -318,6 +320,7 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
+ print_xstate_feature(XFEATURE_MASK_PASID);
}
/*
@@ -592,6 +595,7 @@ static void check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
+ XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state);
/*
* Make *SURE* to add any feature numbers in below if
@@ -601,7 +605,7 @@ static void check_xstate_against_struct(int nr)
if ((nr < XFEATURE_YMM) ||
(nr >= XFEATURE_MAX) ||
(nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
- ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
+ ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
WARN_ONCE(1, "no structure for xstate: %d\n", nr);
XSTATE_WARN_ON(1);
}
@@ -1398,3 +1402,60 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
return 0;
}
#endif /* CONFIG_PROC_PID_ARCH_STATUS */
+
+#ifdef CONFIG_IOMMU_SUPPORT
+void update_pasid(void)
+{
+ u64 pasid_state;
+ u32 pasid;
+
+ if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
+ return;
+
+ if (!current->mm)
+ return;
+
+ pasid = READ_ONCE(current->mm->pasid);
+ /* Set the valid bit in the PASID MSR/state only for valid pasid. */
+ pasid_state = pasid == PASID_DISABLED ?
+ pasid : pasid | MSR_IA32_PASID_VALID;
+
+ /*
+ * No need to hold fregs_lock() since the task's fpstate won't
+ * be changed by others (e.g. ptrace) while the task is being
+ * switched to or is in IPI.
+ */
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ /* The MSR is active and can be directly updated. */
+ wrmsrl(MSR_IA32_PASID, pasid_state);
+ } else {
+ struct fpu *fpu = &current->thread.fpu;
+ struct ia32_pasid_state *ppasid_state;
+ struct xregs_state *xsave;
+
+ /*
+ * The CPU's xstate registers are not currently active. Just
+ * update the PASID state in the memory buffer here. The
+ * PASID MSR will be loaded when returning to user mode.
+ */
+ xsave = &fpu->state.xsave;
+ xsave->header.xfeatures |= XFEATURE_MASK_PASID;
+ ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID);
+ /*
+ * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state
+ * won't be NULL and no need to check its value.
+ *
+ * Only update the task's PASID state when it's different
+ * from the mm's pasid.
+ */
+ if (ppasid_state->pasid != pasid_state) {
+ /*
+ * Invalid fpregs so that state restoring will pick up
+ * the PASID state.
+ */
+ __fpu_invalidate_fpregs_state(fpu);
+ ppasid_state->pasid = pasid_state;
+ }
+ }
+}
+#endif /* CONFIG_IOMMU_SUPPORT */
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index b98ff620ba77..03aa33b58165 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -442,42 +442,6 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
}
/*
- * Dump the debug register contents to the user.
- * We can't dump our per cpu values because it
- * may contain cpu wide breakpoint, something that
- * doesn't belong to the current task.
- *
- * TODO: include non-ptrace user breakpoints (perf)
- */
-void aout_dump_debugregs(struct user *dump)
-{
- int i;
- int dr7 = 0;
- struct perf_event *bp;
- struct arch_hw_breakpoint *info;
- struct thread_struct *thread = &current->thread;
-
- for (i = 0; i < HBP_NUM; i++) {
- bp = thread->ptrace_bps[i];
-
- if (bp && !bp->attr.disabled) {
- dump->u_debugreg[i] = bp->attr.bp_addr;
- info = counter_arch_bp(bp);
- dr7 |= encode_dr7(i, info->len, info->type);
- } else {
- dump->u_debugreg[i] = 0;
- }
- }
-
- dump->u_debugreg[4] = 0;
- dump->u_debugreg[5] = 0;
- dump->u_debugreg[6] = current->thread.debugreg6;
-
- dump->u_debugreg[7] = dr7;
-}
-EXPORT_SYMBOL_GPL(aout_dump_debugregs);
-
-/*
* Release the user breakpoints used by ptrace
*/
void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
@@ -490,7 +454,7 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
t->ptrace_bps[i] = NULL;
}
- t->debugreg6 = 0;
+ t->virtual_dr6 = 0;
t->ptrace_dr7 = 0;
}
@@ -500,7 +464,7 @@ void hw_breakpoint_restore(void)
set_debugreg(__this_cpu_read(cpu_debugreg[1]), 1);
set_debugreg(__this_cpu_read(cpu_debugreg[2]), 2);
set_debugreg(__this_cpu_read(cpu_debugreg[3]), 3);
- set_debugreg(current->thread.debugreg6, 6);
+ set_debugreg(DR6_RESERVED, 6);
set_debugreg(__this_cpu_read(cpu_dr7), 7);
}
EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
@@ -523,10 +487,10 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
*/
static int hw_breakpoint_handler(struct die_args *args)
{
- int i, cpu, rc = NOTIFY_STOP;
+ int i, rc = NOTIFY_STOP;
struct perf_event *bp;
- unsigned long dr6;
unsigned long *dr6_p;
+ unsigned long dr6;
/* The DR6 value is pointed by args->err */
dr6_p = (unsigned long *)ERR_PTR(args->err);
@@ -540,14 +504,6 @@ static int hw_breakpoint_handler(struct die_args *args)
if ((dr6 & DR_TRAP_BITS) == 0)
return NOTIFY_DONE;
- /*
- * Assert that local interrupts are disabled
- * Reset the DRn bits in the virtualized register value.
- * The ptrace trigger routine will add in whatever is needed.
- */
- current->thread.debugreg6 &= ~DR_TRAP_BITS;
- cpu = get_cpu();
-
/* Handle all the breakpoints that were triggered */
for (i = 0; i < HBP_NUM; ++i) {
if (likely(!(dr6 & (DR_TRAP0 << i))))
@@ -561,7 +517,7 @@ static int hw_breakpoint_handler(struct die_args *args)
*/
rcu_read_lock();
- bp = per_cpu(bp_per_reg[i], cpu);
+ bp = this_cpu_read(bp_per_reg[i]);
/*
* Reset the 'i'th TRAP bit in dr6 to denote completion of
* exception handling
@@ -592,12 +548,10 @@ static int hw_breakpoint_handler(struct die_args *args)
* breakpoints (to generate signals) and b) when the system has
* taken exception due to multiple causes
*/
- if ((current->thread.debugreg6 & DR_TRAP_BITS) ||
+ if ((current->thread.virtual_dr6 & DR_TRAP_BITS) ||
(dr6 & (~DR_TRAP_BITS)))
rc = NOTIFY_DONE;
- put_cpu();
-
return rc;
}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index c2f02f308ecf..ff7878df96b4 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -629,9 +629,10 @@ static void kgdb_hw_overflow_handler(struct perf_event *event,
struct task_struct *tsk = current;
int i;
- for (i = 0; i < 4; i++)
+ for (i = 0; i < 4; i++) {
if (breakinfo[i].enabled)
- tsk->thread.debugreg6 |= (DR_TRAP0 << i);
+ tsk->thread.virtual_dr6 |= (DR_TRAP0 << i);
+ }
}
void kgdb_arch_late(void)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fdadc37d72af..db8f8693ab8d 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -767,124 +767,21 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+
/*
* Called from kretprobe_trampoline
*/
__used __visible void *trampoline_handler(struct pt_regs *regs)
{
- struct kretprobe_instance *ri = NULL;
- struct hlist_head *head, empty_rp;
- struct hlist_node *tmp;
- unsigned long flags, orig_ret_address = 0;
- unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
- kprobe_opcode_t *correct_ret_addr = NULL;
- void *frame_pointer;
- bool skipped = false;
-
- /*
- * Set a dummy kprobe for avoiding kretprobe recursion.
- * Since kretprobe never run in kprobe handler, kprobe must not
- * be running at this point.
- */
- kprobe_busy_begin();
-
- INIT_HLIST_HEAD(&empty_rp);
- kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
regs->cs = __KERNEL_CS;
#ifdef CONFIG_X86_32
- regs->cs |= get_kernel_rpl();
regs->gs = 0;
#endif
- /* We use pt_regs->sp for return address holder. */
- frame_pointer = &regs->sp;
- regs->ip = trampoline_address;
+ regs->ip = (unsigned long)&kretprobe_trampoline;
regs->orig_ax = ~0UL;
- /*
- * It is possible to have multiple instances associated with a given
- * task either because multiple functions in the call path have
- * return probes installed on them, and/or more than one
- * return probe was registered for a target function.
- *
- * We can handle this because:
- * - instances are always pushed into the head of the list
- * - when multiple return probes are registered for the same
- * function, the (chronologically) first instance's ret_addr
- * will be the real return address, and all the rest will
- * point to kretprobe_trampoline.
- */
- hlist_for_each_entry(ri, head, hlist) {
- if (ri->task != current)
- /* another task is sharing our hash bucket */
- continue;
- /*
- * Return probes must be pushed on this hash list correct
- * order (same as return order) so that it can be popped
- * correctly. However, if we find it is pushed it incorrect
- * order, this means we find a function which should not be
- * probed, because the wrong order entry is pushed on the
- * path of processing other kretprobe itself.
- */
- if (ri->fp != frame_pointer) {
- if (!skipped)
- pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
- skipped = true;
- continue;
- }
-
- orig_ret_address = (unsigned long)ri->ret_addr;
- if (skipped)
- pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
- ri->rp->kp.addr);
-
- if (orig_ret_address != trampoline_address)
- /*
- * This is the real return address. Any other
- * instances associated with this task are for
- * other calls deeper on the call stack
- */
- break;
- }
-
- kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
- correct_ret_addr = ri->ret_addr;
- hlist_for_each_entry_safe(ri, tmp, head, hlist) {
- if (ri->task != current)
- /* another task is sharing our hash bucket */
- continue;
- if (ri->fp != frame_pointer)
- continue;
-
- orig_ret_address = (unsigned long)ri->ret_addr;
- if (ri->rp && ri->rp->handler) {
- __this_cpu_write(current_kprobe, &ri->rp->kp);
- ri->ret_addr = correct_ret_addr;
- ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, &kprobe_busy);
- }
-
- recycle_rp_inst(ri, &empty_rp);
-
- if (orig_ret_address != trampoline_address)
- /*
- * This is the real return address. Any other
- * instances associated with this task are for
- * other calls deeper on the call stack
- */
- break;
- }
-
- kretprobe_hash_unlock(current, &flags);
-
- kprobe_busy_end();
-
- hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
- hlist_del(&ri->hlist);
- kfree(ri);
- }
- return (void *)orig_ret_address;
+ return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, &regs->sp);
}
NOKPROBE_SYMBOL(trampoline_handler);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 40f380461e6d..15e06408f6ba 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -18,6 +18,7 @@
#include <linux/ftrace.h>
#include <linux/frame.h>
#include <linux/pgtable.h>
+#include <linux/static_call.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -181,7 +182,6 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
/* Save skipped registers */
regs->cs = __KERNEL_CS;
#ifdef CONFIG_X86_32
- regs->cs |= get_kernel_rpl();
regs->gs = 0;
#endif
regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE;
@@ -210,7 +210,8 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
/* Check whether the address range is reserved */
if (ftrace_text_reserved(src, src + len - 1) ||
alternatives_text_reserved(src, src + len - 1) ||
- jump_label_text_reserved(src, src + len - 1))
+ jump_label_text_reserved(src, src + len - 1) ||
+ static_call_text_reserved(src, src + len - 1))
return -EBUSY;
return len;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index baa21090c9be..8f06449aab27 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -24,7 +24,6 @@
#include <asm/irqdomain.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
-#include <asm/io_apic.h>
#include <asm/proto.h>
#include <asm/bios_ebda.h>
#include <asm/e820/api.h>
@@ -46,11 +45,6 @@ static int __init mpf_checksum(unsigned char *mp, int len)
return sum & 0xFF;
}
-int __init default_mpc_apic_id(struct mpc_cpu *m)
-{
- return m->apicid;
-}
-
static void __init MP_processor_info(struct mpc_cpu *m)
{
int apicid;
@@ -61,7 +55,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
return;
}
- apicid = x86_init.mpparse.mpc_apic_id(m);
+ apicid = m->apicid;
if (m->cpuflag & CPU_BOOTPROCESSOR) {
bootup_cpu = " (Bootup-CPU)";
@@ -73,7 +67,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
}
#ifdef CONFIG_X86_IO_APIC
-void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str)
+static void __init mpc_oem_bus_info(struct mpc_bus *m, char *str)
{
memcpy(str, m->bustype, 6);
str[6] = 0;
@@ -84,7 +78,7 @@ static void __init MP_bus_info(struct mpc_bus *m)
{
char str[7];
- x86_init.mpparse.mpc_oem_bus_info(m, str);
+ mpc_oem_bus_info(m, str);
#if MAX_MP_BUSSES < 256
if (m->busid >= MAX_MP_BUSSES) {
@@ -100,9 +94,6 @@ static void __init MP_bus_info(struct mpc_bus *m)
mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
#endif
} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
- if (x86_init.mpparse.mpc_oem_pci_bus)
- x86_init.mpparse.mpc_oem_pci_bus(m);
-
clear_bit(m->busid, mp_bus_not_pci);
#ifdef CONFIG_EISA
mp_bus_id_to_type[m->busid] = MP_BUS_PCI;
@@ -198,8 +189,6 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
1, mpc, mpc->length, 1);
}
-void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
-
static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
{
char str[16];
@@ -218,14 +207,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
if (early)
return 1;
- if (mpc->oemptr)
- x86_init.mpparse.smp_read_mpc_oem(mpc);
-
- /*
- * Now process the configuration blocks.
- */
- x86_init.mpparse.mpc_record(0);
-
+ /* Now process the configuration blocks. */
while (count < mpc->length) {
switch (*mpt) {
case MP_PROCESSOR:
@@ -256,7 +238,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
count = mpc->length;
break;
}
- x86_init.mpparse.mpc_record(1);
}
if (!num_processors)
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 49dcfb85e773..c0d409810658 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -80,18 +80,30 @@ static ssize_t msr_read(struct file *file, char __user *buf,
static int filter_write(u32 reg)
{
+ /*
+ * MSRs writes usually happen all at once, and can easily saturate kmsg.
+ * Only allow one message every 30 seconds.
+ *
+ * It's possible to be smarter here and do it (for example) per-MSR, but
+ * it would certainly be more complex, and this is enough at least to
+ * avoid saturating the ring buffer.
+ */
+ static DEFINE_RATELIMIT_STATE(fw_rs, 30 * HZ, 1);
+
switch (allow_writes) {
case MSR_WRITES_ON: return 0;
case MSR_WRITES_OFF: return -EPERM;
default: break;
}
+ if (!__ratelimit(&fw_rs))
+ return 0;
+
if (reg == MSR_IA32_ENERGY_PERF_BIAS)
return 0;
- pr_err_ratelimited("Write to unrecognized MSR 0x%x by %s\n"
- "Please report to x86@kernel.org\n",
- reg, current->comm);
+ pr_err("Write to unrecognized MSR 0x%x by %s (pid: %d). Please report to x86@kernel.org.\n",
+ reg, current->comm, current->pid);
return 0;
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4fc9954a9560..47381666d6a5 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -102,7 +102,6 @@ fs_initcall(nmi_warning_debugfs);
static void nmi_check_duration(struct nmiaction *action, u64 duration)
{
- u64 whole_msecs = READ_ONCE(action->max_duration);
int remainder_ns, decimal_msecs;
if (duration < nmi_longest_ns || duration < action->max_duration)
@@ -110,12 +109,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
action->max_duration = duration;
- remainder_ns = do_div(whole_msecs, (1000 * 1000));
+ remainder_ns = do_div(duration, (1000 * 1000));
decimal_msecs = remainder_ns / 1000;
printk_ratelimited(KERN_INFO
"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
- action->handler, whole_msecs, decimal_msecs);
+ action->handler, duration, decimal_msecs);
}
static int nmi_handle(unsigned int type, struct pt_regs *regs)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index de2138ba38e5..6c3407ba6ee9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,13 +263,8 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
struct pv_info pv_info = {
.name = "bare hardware",
#ifdef CONFIG_PARAVIRT_XXL
- .kernel_rpl = 0,
- .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
-
-#ifdef CONFIG_X86_64
.extra_user_64bit_cs = __USER_CS,
#endif
-#endif
};
/* 64-bit pagetable entries */
@@ -305,9 +300,7 @@ struct paravirt_patch_template pv_ops = {
.cpu.load_idt = native_load_idt,
.cpu.store_tr = native_store_tr,
.cpu.load_tls = native_load_tls,
-#ifdef CONFIG_X86_64
.cpu.load_gs_index = native_load_gs_index,
-#endif
.cpu.write_ldt_entry = native_write_ldt_entry,
.cpu.write_gdt_entry = native_write_gdt_entry,
.cpu.write_idt_entry = native_write_idt_entry,
@@ -317,9 +310,7 @@ struct paravirt_patch_template pv_ops = {
.cpu.load_sp0 = native_load_sp0,
-#ifdef CONFIG_X86_64
.cpu.usergs_sysret64 = native_usergs_sysret64,
-#endif
.cpu.iret = native_iret,
.cpu.swapgs = native_swapgs,
@@ -369,24 +360,16 @@ struct paravirt_patch_template pv_ops = {
.mmu.release_p4d = paravirt_nop,
.mmu.set_pte = native_set_pte,
- .mmu.set_pte_at = native_set_pte_at,
.mmu.set_pmd = native_set_pmd,
.mmu.ptep_modify_prot_start = __ptep_modify_prot_start,
.mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit,
-#if CONFIG_PGTABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
- .mmu.set_pte_atomic = native_set_pte_atomic,
- .mmu.pte_clear = native_pte_clear,
- .mmu.pmd_clear = native_pmd_clear,
-#endif
.mmu.set_pud = native_set_pud,
.mmu.pmd_val = PTE_IDENT,
.mmu.make_pmd = PTE_IDENT,
-#if CONFIG_PGTABLE_LEVELS >= 4
.mmu.pud_val = PTE_IDENT,
.mmu.make_pud = PTE_IDENT,
@@ -398,8 +381,6 @@ struct paravirt_patch_template pv_ops = {
.mmu.set_pgd = native_set_pgd,
#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
-#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
-#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
.mmu.pte_val = PTE_IDENT,
.mmu.pgd_val = PTE_IDENT,
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 3eff63c090d2..ace6e334cb39 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -26,14 +26,10 @@ struct patch_xxl {
const unsigned char mmu_read_cr3[3];
const unsigned char mmu_write_cr3[3];
const unsigned char irq_restore_fl[2];
-# ifdef CONFIG_X86_64
const unsigned char cpu_wbinvd[2];
const unsigned char cpu_usergs_sysret64[6];
const unsigned char cpu_swapgs[3];
const unsigned char mov64[3];
-# else
- const unsigned char cpu_iret[1];
-# endif
};
static const struct patch_xxl patch_data_xxl = {
@@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = {
.irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax
.mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax
.mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax
-# ifdef CONFIG_X86_64
.mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3
.irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq
.cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd
@@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = {
0x48, 0x0f, 0x07 }, // swapgs; sysretq
.cpu_swapgs = { 0x0f, 0x01, 0xf8 }, // swapgs
.mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax
-# else
- .mmu_write_cr3 = { 0x0f, 0x22, 0xd8 }, // mov %eax, %cr3
- .irq_restore_fl = { 0x50, 0x9d }, // push %eax; popf
- .cpu_iret = { 0xcf }, // iret
-# endif
};
unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
{
-#ifdef CONFIG_X86_64
return PATCH(xxl, mov64, insn_buff, len);
-#endif
- return 0;
}
# endif /* CONFIG_PARAVIRT_XXL */
@@ -98,13 +85,9 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-# ifdef CONFIG_X86_64
PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
PATCH_CASE(cpu, swapgs, xxl, insn_buff, len);
PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-# else
- PATCH_CASE(cpu, iret, xxl, insn_buff, len);
-# endif
#endif
#ifdef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9afefe325acb..df342bedea88 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -407,7 +407,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void)
{
unsigned long gsbase;
- if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+ if (boot_cpu_has(X86_FEATURE_FSGSBASE)) {
unsigned long flags;
local_irq_save(flags);
@@ -422,7 +422,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void)
void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
{
- if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+ if (boot_cpu_has(X86_FEATURE_FSGSBASE)) {
unsigned long flags;
local_irq_save(flags);
@@ -439,7 +439,7 @@ unsigned long x86_fsbase_read_task(struct task_struct *task)
if (task == current)
fsbase = x86_fsbase_read_cpu();
- else if (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+ else if (boot_cpu_has(X86_FEATURE_FSGSBASE) ||
(task->thread.fsindex == 0))
fsbase = task->thread.fsbase;
else
@@ -454,7 +454,7 @@ unsigned long x86_gsbase_read_task(struct task_struct *task)
if (task == current)
gsbase = x86_gsbase_read_cpu_inactive();
- else if (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+ else if (boot_cpu_has(X86_FEATURE_FSGSBASE) ||
(task->thread.gsindex == 0))
gsbase = task->thread.gsbase;
else
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e7537c5440bb..bedca011459c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -465,7 +465,7 @@ static void ptrace_triggered(struct perf_event *bp,
break;
}
- thread->debugreg6 |= (DR_TRAP0 << i);
+ thread->virtual_dr6 |= (DR_TRAP0 << i);
}
/*
@@ -601,7 +601,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
if (bp)
val = bp->hw.info.address;
} else if (n == 6) {
- val = thread->debugreg6;
+ val = thread->virtual_dr6 ^ DR6_RESERVED; /* Flip back to arch polarity */
} else if (n == 7) {
val = thread->ptrace_dr7;
}
@@ -657,7 +657,7 @@ static int ptrace_set_debugreg(struct task_struct *tsk, int n,
if (n < HBP_NUM) {
rc = ptrace_set_breakpoint_addr(tsk, n, val);
} else if (n == 6) {
- thread->debugreg6 = val;
+ thread->virtual_dr6 = val ^ DR6_RESERVED; /* Flip to positive polarity */
rc = 0;
} else if (n == 7) {
rc = ptrace_write_dr7(tsk, val);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..fa16b906ea3f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -19,6 +19,7 @@
#include <linux/hugetlb.h>
#include <linux/tboot.h>
#include <linux/usb/xhci-dbgp.h>
+#include <linux/static_call.h>
#include <uapi/linux/mount.h>
@@ -849,6 +850,7 @@ void __init setup_arch(char **cmdline_p)
early_cpu_init();
arch_init_ideal_nops();
jump_label_init();
+ static_call_init();
early_ioremap_init();
setup_olpc_ofw_pgd();
@@ -1077,6 +1079,7 @@ void __init setup_arch(char **cmdline_p)
efi_fake_memmap();
efi_find_mirror();
efi_esrt_init();
+ efi_mokvar_table_init();
/*
* The EFI specification says that boot service code won't be
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
new file mode 100644
index 000000000000..ca9a380d9c0b
--- /dev/null
+++ b/arch/x86/kernel/static_call.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/static_call.h>
+#include <linux/memory.h>
+#include <linux/bug.h>
+#include <asm/text-patching.h>
+
+enum insn_type {
+ CALL = 0, /* site call */
+ NOP = 1, /* site cond-call */
+ JMP = 2, /* tramp / site tail-call */
+ RET = 3, /* tramp / site cond-tail-call */
+};
+
+static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
+{
+ int size = CALL_INSN_SIZE;
+ const void *code;
+
+ switch (type) {
+ case CALL:
+ code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+ break;
+
+ case NOP:
+ code = ideal_nops[NOP_ATOMIC5];
+ break;
+
+ case JMP:
+ code = text_gen_insn(JMP32_INSN_OPCODE, insn, func);
+ break;
+
+ case RET:
+ code = text_gen_insn(RET_INSN_OPCODE, insn, func);
+ size = RET_INSN_SIZE;
+ break;
+ }
+
+ if (memcmp(insn, code, size) == 0)
+ return;
+
+ if (unlikely(system_state == SYSTEM_BOOTING))
+ return text_poke_early(insn, code, size);
+
+ text_poke_bp(insn, code, size, NULL);
+}
+
+static void __static_call_validate(void *insn, bool tail)
+{
+ u8 opcode = *(u8 *)insn;
+
+ if (tail) {
+ if (opcode == JMP32_INSN_OPCODE ||
+ opcode == RET_INSN_OPCODE)
+ return;
+ } else {
+ if (opcode == CALL_INSN_OPCODE ||
+ !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5))
+ return;
+ }
+
+ /*
+ * If we ever trigger this, our text is corrupt, we'll probably not live long.
+ */
+ WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+}
+
+static inline enum insn_type __sc_insn(bool null, bool tail)
+{
+ /*
+ * Encode the following table without branches:
+ *
+ * tail null insn
+ * -----+-------+------
+ * 0 | 0 | CALL
+ * 0 | 1 | NOP
+ * 1 | 0 | JMP
+ * 1 | 1 | RET
+ */
+ return 2*tail + null;
+}
+
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
+{
+ mutex_lock(&text_mutex);
+
+ if (tramp) {
+ __static_call_validate(tramp, true);
+ __static_call_transform(tramp, __sc_insn(!func, true), func);
+ }
+
+ if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
+ __static_call_validate(site, tail);
+ __static_call_transform(site, __sc_insn(!func, tail), func);
+ }
+
+ mutex_unlock(&text_mutex);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 316ce1c09e84..ec3a2572843f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -745,9 +745,21 @@ static __always_inline unsigned long debug_read_clear_dr6(void)
* Keep it simple: clear DR6 immediately.
*/
get_debugreg(dr6, 6);
- set_debugreg(0, 6);
- /* Filter out all the reserved bits which are preset to 1 */
- dr6 &= ~DR6_RESERVED;
+ set_debugreg(DR6_RESERVED, 6);
+ dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
+ /*
+ * Clear the virtual DR6 value, ptrace routines will set bits here for
+ * things we want signals for.
+ */
+ current->thread.virtual_dr6 = 0;
+
+ /*
+ * The SDM says "The processor clears the BTF flag when it
+ * generates a debug exception." Clear TIF_BLOCKSTEP to keep
+ * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+ */
+ clear_thread_flag(TIF_BLOCKSTEP);
return dr6;
}
@@ -776,74 +788,20 @@ static __always_inline unsigned long debug_read_clear_dr6(void)
*
* May run on IST stack.
*/
-static void handle_debug(struct pt_regs *regs, unsigned long dr6, bool user)
-{
- struct task_struct *tsk = current;
- bool user_icebp;
- int si_code;
-
- /*
- * The SDM says "The processor clears the BTF flag when it
- * generates a debug exception." Clear TIF_BLOCKSTEP to keep
- * TIF_BLOCKSTEP in sync with the hardware BTF flag.
- */
- clear_thread_flag(TIF_BLOCKSTEP);
-
- /*
- * If DR6 is zero, no point in trying to handle it. The kernel is
- * not using INT1.
- */
- if (!user && !dr6)
- return;
+static bool notify_debug(struct pt_regs *regs, unsigned long *dr6)
+{
/*
- * If dr6 has no reason to give us about the origin of this trap,
- * then it's very likely the result of an icebp/int01 trap.
- * User wants a sigtrap for that.
+ * Notifiers will clear bits in @dr6 to indicate the event has been
+ * consumed - hw_breakpoint_handler(), single_stop_cont().
+ *
+ * Notifiers will set bits in @virtual_dr6 to indicate the desire
+ * for signals - ptrace_triggered(), kgdb_hw_overflow_handler().
*/
- user_icebp = user && !dr6;
-
- /* Store the virtualized DR6 value */
- tsk->thread.debugreg6 = dr6;
-
-#ifdef CONFIG_KPROBES
- if (kprobe_debug_handler(regs)) {
- return;
- }
-#endif
-
- if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, 0,
- SIGTRAP) == NOTIFY_STOP) {
- return;
- }
-
- /* It's safe to allow irq's after DR6 has been saved */
- cond_local_irq_enable(regs);
-
- if (v8086_mode(regs)) {
- handle_vm86_trap((struct kernel_vm86_regs *) regs, 0,
- X86_TRAP_DB);
- goto out;
- }
-
- if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) {
- /*
- * Historical junk that used to handle SYSENTER single-stepping.
- * This should be unreachable now. If we survive for a while
- * without anyone hitting this warning, we'll turn this into
- * an oops.
- */
- tsk->thread.debugreg6 &= ~DR_STEP;
- set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
- regs->flags &= ~X86_EFLAGS_TF;
- }
-
- si_code = get_si_code(tsk->thread.debugreg6);
- if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
- send_sigtrap(regs, 0, si_code);
+ if (notify_die(DIE_DEBUG, "debug", regs, (long)dr6, 0, SIGTRAP) == NOTIFY_STOP)
+ return true;
-out:
- cond_local_irq_disable(regs);
+ return false;
}
static __always_inline void exc_debug_kernel(struct pt_regs *regs,
@@ -877,8 +835,32 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
dr6 &= ~DR_STEP;
- handle_debug(regs, dr6, false);
+ if (kprobe_debug_handler(regs))
+ goto out;
+
+ /*
+ * The kernel doesn't use INT1
+ */
+ if (!dr6)
+ goto out;
+ if (notify_debug(regs, &dr6))
+ goto out;
+
+ /*
+ * The kernel doesn't use TF single-step outside of:
+ *
+ * - Kprobes, consumed through kprobe_debug_handler()
+ * - KGDB, consumed through notify_debug()
+ *
+ * So if we get here with DR_STEP set, something is wonky.
+ *
+ * A known way to trigger this is through QEMU's GDB stub,
+ * which leaks #DB into the guest and causes IST recursion.
+ */
+ if (WARN_ON_ONCE(dr6 & DR_STEP))
+ regs->flags &= ~X86_EFLAGS_TF;
+out:
instrumentation_end();
idtentry_exit_nmi(regs, irq_state);
@@ -888,6 +870,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
static __always_inline void exc_debug_user(struct pt_regs *regs,
unsigned long dr6)
{
+ bool icebp;
+
/*
* If something gets miswired and we end up here for a kernel mode
* #DB, we will malfunction.
@@ -906,8 +890,32 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
irqentry_enter_from_user_mode(regs);
instrumentation_begin();
- handle_debug(regs, dr6, true);
+ /*
+ * If dr6 has no reason to give us about the origin of this trap,
+ * then it's very likely the result of an icebp/int01 trap.
+ * User wants a sigtrap for that.
+ */
+ icebp = !dr6;
+ if (notify_debug(regs, &dr6))
+ goto out;
+
+ /* It's safe to allow irq's after DR6 has been saved */
+ local_irq_enable();
+
+ if (v8086_mode(regs)) {
+ handle_vm86_trap((struct kernel_vm86_regs *)regs, 0, X86_TRAP_DB);
+ goto out_irq;
+ }
+
+ /* Add the virtual_dr6 bits for signals. */
+ dr6 |= current->thread.virtual_dr6;
+ if (dr6 & (DR_STEP | DR_TRAP_BITS) || icebp)
+ send_sigtrap(regs, 0, get_si_code(dr6));
+
+out_irq:
+ local_irq_disable();
+out:
instrumentation_end();
irqentry_exit_to_user_mode(regs);
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 49d925043171..f70dffc2771f 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -54,7 +54,7 @@ struct clocksource *art_related_clocksource;
struct cyc2ns {
struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */
- seqcount_t seq; /* 32 + 4 = 36 */
+ seqcount_latch_t seq; /* 32 + 4 = 36 */
}; /* fits one cacheline */
@@ -73,14 +73,14 @@ __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data)
preempt_disable_notrace();
do {
- seq = this_cpu_read(cyc2ns.seq.sequence);
+ seq = this_cpu_read(cyc2ns.seq.seqcount.sequence);
idx = seq & 1;
data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset);
data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul);
data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift);
- } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
+ } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence)));
}
__always_inline void cyc2ns_read_end(void)
@@ -186,7 +186,7 @@ static void __init cyc2ns_init_boot_cpu(void)
{
struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
- seqcount_init(&c2n->seq);
+ seqcount_latch_init(&c2n->seq);
__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
}
@@ -203,7 +203,7 @@ static void __init cyc2ns_init_secondary_cpus(void)
for_each_possible_cpu(cpu) {
if (cpu != this_cpu) {
- seqcount_init(&c2n->seq);
+ seqcount_latch_init(&c2n->seq);
c2n = per_cpu_ptr(&cyc2ns, cpu);
c2n->data[0] = data[0];
c2n->data[1] = data[1];
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9a03e5b23135..bf9e0adb5b7e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -136,6 +136,7 @@ SECTIONS
ENTRY_TEXT
ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
+ STATIC_CALL_TEXT
*(.fixup)
*(.gnu.warning)
@@ -411,10 +412,47 @@ SECTIONS
STABS_DEBUG
DWARF_DEBUG
+ ELF_DETAILS
DISCARDS
-}
+ /*
+ * Make sure that the .got.plt is either completely empty or it
+ * contains only the lazy dispatch entries.
+ */
+ .got.plt (INFO) : { *(.got.plt) }
+ ASSERT(SIZEOF(.got.plt) == 0 ||
+#ifdef CONFIG_X86_64
+ SIZEOF(.got.plt) == 0x18,
+#else
+ SIZEOF(.got.plt) == 0xc,
+#endif
+ "Unexpected GOT/PLT entries detected!")
+
+ /*
+ * Sections that should stay zero sized, which is safer to
+ * explicitly check instead of blindly discarding.
+ */
+ .got : {
+ *(.got) *(.igot.*)
+ }
+ ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!")
+
+ .plt : {
+ *(.plt) *(.plt.*) *(.iplt)
+ }
+ ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+
+ .rel.dyn : {
+ *(.rel.*) *(.rel_*)
+ }
+ ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!")
+
+ .rela.dyn : {
+ *(.rela.*) *(.rela_*)
+ }
+ ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+}
#ifdef CONFIG_X86_32
/*
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 123f1c1f1788..a3038d8deb6a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -24,6 +24,7 @@
#include <asm/tsc.h>
#include <asm/iommu.h>
#include <asm/mach_traps.h>
+#include <asm/irqdomain.h>
void x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
@@ -67,11 +68,7 @@ struct x86_init_ops x86_init __initdata = {
},
.mpparse = {
- .mpc_record = x86_init_uint_noop,
.setup_ioapic_ids = x86_init_noop,
- .mpc_apic_id = default_mpc_apic_id,
- .smp_read_mpc_oem = default_smp_read_mpc_oem,
- .mpc_oem_bus_info = default_mpc_oem_bus_info,
.find_smp_config = default_find_smp_config,
.get_smp_config = default_get_smp_config,
},
@@ -80,7 +77,8 @@ struct x86_init_ops x86_init __initdata = {
.pre_vector_init = init_ISA_irqs,
.intr_init = native_init_IRQ,
.intr_mode_select = apic_intr_mode_select,
- .intr_mode_init = apic_intr_mode_init
+ .intr_mode_init = apic_intr_mode_init,
+ .create_pci_msi_domain = native_create_pci_msi_domain,
},
.oem = {
@@ -148,28 +146,10 @@ EXPORT_SYMBOL_GPL(x86_platform);
#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi __ro_after_init = {
- .setup_msi_irqs = native_setup_msi_irqs,
- .teardown_msi_irq = native_teardown_msi_irq,
- .teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
};
/* MSI arch specific hooks */
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
- return x86_msi.setup_msi_irqs(dev, nvec, type);
-}
-
-void arch_teardown_msi_irqs(struct pci_dev *dev)
-{
- x86_msi.teardown_msi_irqs(dev);
-}
-
-void arch_teardown_msi_irq(unsigned int irq)
-{
- x86_msi.teardown_msi_irq(irq);
-}
-
void arch_restore_msi_irqs(struct pci_dev *dev)
{
x86_msi.restore_msi_irqs(dev);