summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c61
-rw-r--r--arch/x86/kernel/apic/Makefile1
-rw-r--r--arch/x86/kernel/apic/htirq.c198
-rw-r--r--arch/x86/kernel/apic/vector.c5
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/mpparse.c6
-rw-r--r--arch/x86/kernel/smpboot.c128
-rw-r--r--arch/x86/kernel/sys_x86_64.c10
-rw-r--r--arch/x86/kernel/umip.c88
9 files changed, 167 insertions, 332 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ef9e02e614d0..f4c463df8b08 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -342,13 +342,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+ u8 trigger, u32 gsi);
+
static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
u32 gsi)
{
- int ioapic;
- int pin;
- struct mpc_intsrc mp_irq;
-
/*
* Check bus_irq boundary.
*/
@@ -358,14 +357,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
}
/*
- * Convert 'gsi' to 'ioapic.pin'.
- */
- ioapic = mp_find_ioapic(gsi);
- if (ioapic < 0)
- return;
- pin = mp_find_ioapic_pin(ioapic, gsi);
-
- /*
* TBD: This check is for faulty timer entries, where the override
* erroneously sets the trigger to level, resulting in a HUGE
* increase of timer interrupts!
@@ -373,16 +364,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
if ((bus_irq == 0) && (trigger == 3))
trigger = 1;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = (trigger << 2) | polarity;
- mp_irq.srcbus = MP_ISA_BUS;
- mp_irq.srcbusirq = bus_irq; /* IRQ */
- mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
- mp_irq.dstirq = pin; /* INTIN# */
-
- mp_save_irq(&mp_irq);
-
+ if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0)
+ return;
/*
* Reset default identity mapping if gsi is also an legacy IRQ,
* otherwise there will be more than one entry with the same GSI
@@ -429,6 +412,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
return 0;
}
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+ u8 trigger, u32 gsi)
+{
+ struct mpc_intsrc mp_irq;
+ int ioapic, pin;
+
+ /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0) {
+ pr_warn("Failed to find ioapic for gsi : %u\n", gsi);
+ return ioapic;
+ }
+
+ pin = mp_find_ioapic_pin(ioapic, gsi);
+
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger << 2) | polarity;
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.srcbusirq = bus_irq;
+ mp_irq.dstapic = mpc_ioapic_id(ioapic);
+ mp_irq.dstirq = pin;
+
+ mp_save_irq(&mp_irq);
+
+ return 0;
+}
+
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
@@ -473,7 +484,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK)
polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
- mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+ if (bus_irq < NR_IRQS_LEGACY)
+ mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+ else
+ mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi);
+
acpi_penalize_sci_irq(bus_irq, trigger, polarity);
/*
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index a9e08924927e..a6fcaf16cdbf 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -12,7 +12,6 @@ obj-y += hw_nmi.o
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
obj-$(CONFIG_PCI_MSI) += msi.o
-obj-$(CONFIG_HT_IRQ) += htirq.o
obj-$(CONFIG_SMP) += ipi.o
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
deleted file mode 100644
index b07075dce8b7..000000000000
--- a/arch/x86/kernel/apic/htirq.c
+++ /dev/null
@@ -1,198 +0,0 @@
-/*
- * Support Hypertransport IRQ
- *
- * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
- * Moved from arch/x86/kernel/apic/io_apic.c.
- * Jiang Liu <jiang.liu@linux.intel.com>
- * Add support of hierarchical irqdomain
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/pci.h>
-#include <linux/htirq.h>
-#include <asm/irqdomain.h>
-#include <asm/hw_irq.h>
-#include <asm/apic.h>
-#include <asm/hypertransport.h>
-
-static struct irq_domain *htirq_domain;
-
-/*
- * Hypertransport interrupt support
- */
-static int
-ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
- struct irq_data *parent = data->parent_data;
- int ret;
-
- ret = parent->chip->irq_set_affinity(parent, mask, force);
- if (ret >= 0) {
- struct ht_irq_msg msg;
- struct irq_cfg *cfg = irqd_cfg(data);
-
- fetch_ht_irq_msg(data->irq, &msg);
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
- HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
- HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
- write_ht_irq_msg(data->irq, &msg);
- }
-
- return ret;
-}
-
-static struct irq_chip ht_irq_chip = {
- .name = "PCI-HT",
- .irq_mask = mask_ht_irq,
- .irq_unmask = unmask_ht_irq,
- .irq_ack = irq_chip_ack_parent,
- .irq_set_affinity = ht_set_affinity,
- .irq_retrigger = irq_chip_retrigger_hierarchy,
- .flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
-static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
- unsigned int nr_irqs, void *arg)
-{
- struct ht_irq_cfg *ht_cfg;
- struct irq_alloc_info *info = arg;
- struct pci_dev *dev;
- irq_hw_number_t hwirq;
- int ret;
-
- if (nr_irqs > 1 || !info)
- return -EINVAL;
-
- dev = info->ht_dev;
- hwirq = (info->ht_idx & 0xFF) |
- PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
- (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
- if (irq_find_mapping(domain, hwirq) > 0)
- return -EEXIST;
-
- ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
- if (!ht_cfg)
- return -ENOMEM;
-
- ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
- if (ret < 0) {
- kfree(ht_cfg);
- return ret;
- }
-
- /* Initialize msg to a value that will never match the first write. */
- ht_cfg->msg.address_lo = 0xffffffff;
- ht_cfg->msg.address_hi = 0xffffffff;
- ht_cfg->dev = info->ht_dev;
- ht_cfg->update = info->ht_update;
- ht_cfg->pos = info->ht_pos;
- ht_cfg->idx = 0x10 + (info->ht_idx * 2);
- irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
- handle_edge_irq, ht_cfg, "edge");
-
- return 0;
-}
-
-static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
- unsigned int nr_irqs)
-{
- struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
-
- BUG_ON(nr_irqs != 1);
- kfree(irq_data->chip_data);
- irq_domain_free_irqs_top(domain, virq, nr_irqs);
-}
-
-static int htirq_domain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early)
-{
- struct ht_irq_msg msg;
- struct irq_cfg *cfg = irqd_cfg(irq_data);
-
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
- msg.address_lo =
- HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
- HT_IRQ_LOW_VECTOR(cfg->vector) |
- ((apic->irq_dest_mode == 0) ?
- HT_IRQ_LOW_DM_PHYSICAL :
- HT_IRQ_LOW_DM_LOGICAL) |
- HT_IRQ_LOW_RQEOI_EDGE |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- HT_IRQ_LOW_MT_FIXED :
- HT_IRQ_LOW_MT_ARBITRATED) |
- HT_IRQ_LOW_IRQ_MASKED;
- write_ht_irq_msg(irq_data->irq, &msg);
- return 0;
-}
-
-static void htirq_domain_deactivate(struct irq_domain *domain,
- struct irq_data *irq_data)
-{
- struct ht_irq_msg msg;
-
- memset(&msg, 0, sizeof(msg));
- write_ht_irq_msg(irq_data->irq, &msg);
-}
-
-static const struct irq_domain_ops htirq_domain_ops = {
- .alloc = htirq_domain_alloc,
- .free = htirq_domain_free,
- .activate = htirq_domain_activate,
- .deactivate = htirq_domain_deactivate,
-};
-
-void __init arch_init_htirq_domain(struct irq_domain *parent)
-{
- struct fwnode_handle *fn;
-
- if (disable_apic)
- return;
-
- fn = irq_domain_alloc_named_fwnode("PCI-HT");
- if (!fn)
- goto warn;
-
- htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL);
- irq_domain_free_fwnode(fn);
- if (!htirq_domain)
- goto warn;
-
- htirq_domain->parent = parent;
- return;
-
-warn:
- pr_warn("Failed to initialize irqdomain for HTIRQ.\n");
-}
-
-int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
- ht_irq_update_t *update)
-{
- struct irq_alloc_info info;
-
- if (!htirq_domain)
- return -ENOSYS;
-
- init_irq_alloc_info(&info, NULL);
- info.ht_idx = idx;
- info.ht_pos = pos;
- info.ht_dev = dev;
- info.ht_update = update;
-
- return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
- &info);
-}
-
-void arch_teardown_ht_irq(unsigned int irq)
-{
- irq_domain_free_irqs(irq, 1);
-}
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 05c85e693a5d..6a823a25eaff 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -1,5 +1,5 @@
/*
- * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc.
+ * Local APIC related interfaces to support IOAPIC, MSI, etc.
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
@@ -601,7 +601,7 @@ int __init arch_probe_nr_irqs(void)
nr_irqs = NR_VECTORS * nr_cpu_ids;
nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
-#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+#if defined(CONFIG_PCI_MSI)
/*
* for MSI and HT dyn irq
*/
@@ -663,7 +663,6 @@ int __init arch_early_irq_init(void)
irq_set_default_host(x86_vector_domain);
arch_init_msi_domain(x86_vector_domain);
- arch_init_htirq_domain(x86_vector_domain);
BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 13ae9e5eec2f..fa998ca8aa5a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -341,6 +341,8 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
cr4_set_bits(X86_CR4_UMIP);
+ pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n");
+
return;
out:
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 410c5dadcee3..3a4b12809ab5 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -431,6 +431,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
}
static unsigned long mpf_base;
+static bool mpf_found;
static unsigned long __init get_mpc_size(unsigned long physptr)
{
@@ -504,7 +505,7 @@ void __init default_get_smp_config(unsigned int early)
if (!smp_found_config)
return;
- if (!mpf_base)
+ if (!mpf_found)
return;
if (acpi_lapic && early)
@@ -593,6 +594,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
smp_found_config = 1;
#endif
mpf_base = base;
+ mpf_found = true;
pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
base, base + sizeof(*mpf) - 1, mpf);
@@ -858,7 +860,7 @@ static int __init update_mp_table(void)
if (!enable_update_mptable)
return 0;
- if (!mpf_base)
+ if (!mpf_found)
return 0;
mpf = early_memremap(mpf_base, sizeof(*mpf));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5f59e6bee123..3d01df7d7cf6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,9 +101,6 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
/* Logical package management. We might want to allocate that dynamically */
-static int *physical_to_logical_pkg __read_mostly;
-static unsigned long *physical_package_map __read_mostly;;
-static unsigned int max_physical_pkg_id __read_mostly;
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
@@ -281,108 +278,48 @@ static void notrace start_secondary(void *unused)
}
/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->initialized && c->phys_proc_id == phys_pkg)
+ return c->logical_proc_id;
+ }
+ return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
+/**
* topology_update_package_map - Update the physical to logical package map
* @pkg: The physical package id as retrieved via CPUID
* @cpu: The cpu for which this is updated
*/
int topology_update_package_map(unsigned int pkg, unsigned int cpu)
{
- unsigned int new;
+ int new;
- /* Called from early boot ? */
- if (!physical_package_map)
- return 0;
-
- if (pkg >= max_physical_pkg_id)
- return -EINVAL;
-
- /* Set the logical package id */
- if (test_and_set_bit(pkg, physical_package_map))
+ /* Already available somewhere? */
+ new = topology_phys_to_logical_pkg(pkg);
+ if (new >= 0)
goto found;
- if (logical_packages >= __max_logical_packages) {
- pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n",
- logical_packages, cpu, __max_logical_packages);
- return -ENOSPC;
- }
-
new = logical_packages++;
if (new != pkg) {
pr_info("CPU %u Converting physical %u to logical package %u\n",
cpu, pkg, new);
}
- physical_to_logical_pkg[pkg] = new;
-
found:
- cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+ cpu_data(cpu).logical_proc_id = new;
return 0;
}
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
- if (phys_pkg >= max_physical_pkg_id)
- return -1;
- return physical_to_logical_pkg[phys_pkg];
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
-static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
-{
- unsigned int ncpus;
- size_t size;
-
- /*
- * Today neither Intel nor AMD support heterogenous systems. That
- * might change in the future....
- *
- * While ideally we'd want '* smp_num_siblings' in the below @ncpus
- * computation, this won't actually work since some Intel BIOSes
- * report inconsistent HT data when they disable HT.
- *
- * In particular, they reduce the APIC-IDs to only include the cores,
- * but leave the CPUID topology to say there are (2) siblings.
- * This means we don't know how many threads there will be until
- * after the APIC enumeration.
- *
- * By not including this we'll sometimes over-estimate the number of
- * logical packages by the amount of !present siblings, but this is
- * still better than MAX_LOCAL_APIC.
- *
- * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited
- * on the command line leading to a similar issue as the HT disable
- * problem because the hyperthreads are usually enumerated after the
- * primary cores.
- */
- ncpus = boot_cpu_data.x86_max_cores;
- if (!ncpus) {
- pr_warn("x86_max_cores == zero !?!?");
- ncpus = 1;
- }
-
- __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
- logical_packages = 0;
-
- /*
- * Possibly larger than what we need as the number of apic ids per
- * package can be smaller than the actual used apic ids.
- */
- max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
- size = max_physical_pkg_id * sizeof(unsigned int);
- physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
- memset(physical_to_logical_pkg, 0xff, size);
- size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
- physical_package_map = kzalloc(size, GFP_KERNEL);
-
- pr_info("Max logical packages: %u\n", __max_logical_packages);
-
- topology_update_package_map(c->phys_proc_id, cpu);
-}
-
void __init smp_store_boot_cpu_info(void)
{
int id = 0; /* CPU 0 */
@@ -390,7 +327,8 @@ void __init smp_store_boot_cpu_info(void)
*c = boot_cpu_data;
c->cpu_index = id;
- smp_init_package_map(c, id);
+ topology_update_package_map(c->phys_proc_id, id);
+ c->initialized = true;
}
/*
@@ -401,13 +339,16 @@ void smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
- *c = boot_cpu_data;
+ /* Copy boot_cpu_data only on the first bringup */
+ if (!c->initialized)
+ *c = boot_cpu_data;
c->cpu_index = id;
/*
* During boot time, CPU0 has this setup already. Save the info when
* bringing up AP or offlined CPU0.
*/
identify_secondary_cpu(c);
+ c->initialized = true;
}
static bool
@@ -1356,7 +1297,16 @@ void __init native_smp_prepare_boot_cpu(void)
void __init native_smp_cpus_done(unsigned int max_cpus)
{
+ int ncpus;
+
pr_debug("Boot done\n");
+ /*
+ * Today neither Intel nor AMD support heterogenous systems so
+ * extrapolate the boot cpu's data to all packages.
+ */
+ ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+ __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+ pr_info("Max logical packages: %u\n", __max_logical_packages);
if (x86_has_numa_in_package)
set_sched_topology(x86_numa_in_package_topology);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index a63fe77b3217..676774b9bb8d 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -188,6 +188,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
if (len > TASK_SIZE)
return -ENOMEM;
+ /* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED)
return addr;
@@ -197,12 +198,15 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
/* requesting a specific address */
if (addr) {
- addr = PAGE_ALIGN(addr);
+ addr &= PAGE_MASK;
+ if (!mmap_address_hint_valid(addr, len))
+ goto get_unmapped_area;
+
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
+ if (!vma || addr + len <= vm_start_gap(vma))
return addr;
}
+get_unmapped_area:
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 6ba82be68cff..f44ce0fb3583 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -78,7 +78,60 @@
#define UMIP_INST_SGDT 0 /* 0F 01 /0 */
#define UMIP_INST_SIDT 1 /* 0F 01 /1 */
-#define UMIP_INST_SMSW 3 /* 0F 01 /4 */
+#define UMIP_INST_SMSW 2 /* 0F 01 /4 */
+#define UMIP_INST_SLDT 3 /* 0F 00 /0 */
+#define UMIP_INST_STR 4 /* 0F 00 /1 */
+
+const char * const umip_insns[5] = {
+ [UMIP_INST_SGDT] = "SGDT",
+ [UMIP_INST_SIDT] = "SIDT",
+ [UMIP_INST_SMSW] = "SMSW",
+ [UMIP_INST_SLDT] = "SLDT",
+ [UMIP_INST_STR] = "STR",
+};
+
+#define umip_pr_err(regs, fmt, ...) \
+ umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__)
+#define umip_pr_warning(regs, fmt, ...) \
+ umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__)
+
+/**
+ * umip_printk() - Print a rate-limited message
+ * @regs: Register set with the context in which the warning is printed
+ * @log_level: Kernel log level to print the message
+ * @fmt: The text string to print
+ *
+ * Print the text contained in @fmt. The print rate is limited to bursts of 5
+ * messages every two minutes. The purpose of this customized version of
+ * printk() is to print messages when user space processes use any of the
+ * UMIP-protected instructions. Thus, the printed text is prepended with the
+ * task name and process ID number of the current task as well as the
+ * instruction and stack pointers in @regs as seen when entering kernel mode.
+ *
+ * Returns:
+ *
+ * None.
+ */
+static __printf(3, 4)
+void umip_printk(const struct pt_regs *regs, const char *log_level,
+ const char *fmt, ...)
+{
+ /* Bursts of 5 messages every two minutes */
+ static DEFINE_RATELIMIT_STATE(ratelimit, 2 * 60 * HZ, 5);
+ struct task_struct *tsk = current;
+ struct va_format vaf;
+ va_list args;
+
+ if (!__ratelimit(&ratelimit))
+ return;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk("%s" pr_fmt("%s[%d] ip:%lx sp:%lx: %pV"), log_level, tsk->comm,
+ task_pid_nr(tsk), regs->ip, regs->sp, &vaf);
+ va_end(args);
+}
/**
* identify_insn() - Identify a UMIP-protected instruction
@@ -118,10 +171,16 @@ static int identify_insn(struct insn *insn)
default:
return -EINVAL;
}
+ } else if (insn->opcode.bytes[1] == 0x0) {
+ if (X86_MODRM_REG(insn->modrm.value) == 0)
+ return UMIP_INST_SLDT;
+ else if (X86_MODRM_REG(insn->modrm.value) == 1)
+ return UMIP_INST_STR;
+ else
+ return -EINVAL;
+ } else {
+ return -EINVAL;
}
-
- /* SLDT AND STR are not emulated */
- return -EINVAL;
}
/**
@@ -228,10 +287,8 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV)))
return;
- pr_err_ratelimited("%s[%d] umip emulation segfault ip:%lx sp:%lx error:%x in %lx\n",
- tsk->comm, task_pid_nr(tsk), regs->ip,
- regs->sp, X86_PF_USER | X86_PF_WRITE,
- regs->ip);
+ umip_pr_err(regs, "segfault in emulation. error%x\n",
+ X86_PF_USER | X86_PF_WRITE);
}
/**
@@ -262,15 +319,11 @@ bool fixup_umip_exception(struct pt_regs *regs)
unsigned char buf[MAX_INSN_SIZE];
void __user *uaddr;
struct insn insn;
- char seg_defs;
+ int seg_defs;
if (!regs)
return false;
- /* Do not emulate 64-bit processes. */
- if (user_64bit_mode(regs))
- return false;
-
/*
* If not in user-space long mode, a custom code segment could be in
* use. This is true in protected mode (if the process defined a local
@@ -322,6 +375,15 @@ bool fixup_umip_exception(struct pt_regs *regs)
if (umip_inst < 0)
return false;
+ umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
+ umip_insns[umip_inst]);
+
+ /* Do not emulate SLDT, STR or user long mode processes. */
+ if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+ return false;
+
+ umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
+
if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
return false;
generated by cgit (git 2.34.1) at 2024-04-28 13:16:04 +0000