summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c2
-rw-r--r--arch/x86/kernel/apic/apic_noop.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/apic/msi.c8
-rw-r--r--arch/x86/kernel/apic/probe_32.c2
-rw-r--r--arch/x86/kernel/apic/vector.c24
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c10
-rw-r--r--arch/x86/kernel/asm-offsets_32.c9
-rw-r--r--arch/x86/kernel/asm-offsets_64.c4
-rw-r--r--arch/x86/kernel/cpu/amd.c7
-rw-r--r--arch/x86/kernel/cpu/common.c103
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c13
-rw-r--r--arch/x86/kernel/doublefault.c36
-rw-r--r--arch/x86/kernel/dumpstack.c98
-rw-r--r--arch/x86/kernel/dumpstack_32.c6
-rw-r--r--arch/x86/kernel/dumpstack_64.c12
-rw-r--r--arch/x86/kernel/head_64.S30
-rw-r--r--arch/x86/kernel/ioport.c2
-rw-r--r--arch/x86/kernel/irq.c12
-rw-r--r--arch/x86/kernel/irq_64.c4
-rw-r--r--arch/x86/kernel/ldt.c198
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c2
-rw-r--r--arch/x86/kernel/process.c21
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c14
-rw-r--r--arch/x86/kernel/setup.c5
-rw-r--r--arch/x86/kernel/smpboot.c21
-rw-r--r--arch/x86/kernel/stacktrace.c8
-rw-r--r--arch/x86/kernel/tls.c11
-rw-r--r--arch/x86/kernel/traps.c77
-rw-r--r--arch/x86/kernel/unwind_orc.c88
-rw-r--r--arch/x86/kernel/vmlinux.lds.S17
36 files changed, 553 insertions, 309 deletions
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6e272f3ea984..880441f24146 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2626,11 +2626,13 @@ static int __init apic_set_verbosity(char *arg)
apic_verbosity = APIC_DEBUG;
else if (strcmp("verbose", arg) == 0)
apic_verbosity = APIC_VERBOSE;
+#ifdef CONFIG_X86_64
else {
pr_warning("APIC Verbosity level %s not recognised"
" use apic=verbose or apic=debug\n", arg);
return -EINVAL;
}
+#endif
return 0;
}
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index aa85690e9b64..25a87028cb3f 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -151,7 +151,7 @@ static struct apic apic_flat __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = flat_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
.irq_dest_mode = 1, /* logical */
.disable_esr = 0,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 7b659c4480c9..5078b5ce63a7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = noop_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
/* logical delivery broadcast to all CPUs: */
.irq_dest_mode = 1,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 201579dc5242..8a7963421460 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2988,7 +2988,7 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
}
int mp_irqdomain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early)
+ struct irq_data *irq_data, bool reserve)
{
unsigned long flags;
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 9b18be764422..ce503c99f5c4 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
((apic->irq_dest_mode == 0) ?
MSI_ADDR_DEST_MODE_PHYSICAL :
MSI_ADDR_DEST_MODE_LOGICAL) |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_ADDR_REDIRECTION_CPU :
- MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_REDIRECTION_CPU |
MSI_ADDR_DEST_ID(cfg->dest_apicid);
msg->data =
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED :
- MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_DELIVERY_FIXED |
MSI_DATA_VECTOR(cfg->vector);
}
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index fa22017de806..02e8acb134f8 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = {
.apic_id_valid = default_apic_id_valid,
.apic_id_registered = default_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
/* logical delivery broadcast to all CPUs: */
.irq_dest_mode = 1,
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6a823a25eaff..f8b03bb8e725 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -184,6 +184,7 @@ static void reserve_irq_vector_locked(struct irq_data *irqd)
irq_matrix_reserve(vector_matrix);
apicd->can_reserve = true;
apicd->has_reserved = true;
+ irqd_set_can_reserve(irqd);
trace_vector_reserve(irqd->irq, 0);
vector_assign_managed_shutdown(irqd);
}
@@ -368,8 +369,18 @@ static int activate_reserved(struct irq_data *irqd)
int ret;
ret = assign_irq_vector_any_locked(irqd);
- if (!ret)
+ if (!ret) {
apicd->has_reserved = false;
+ /*
+ * Core might have disabled reservation mode after
+ * allocating the irq descriptor. Ideally this should
+ * happen before allocation time, but that would require
+ * completely convoluted ways of transporting that
+ * information.
+ */
+ if (!irqd_can_reserve(irqd))
+ apicd->can_reserve = false;
+ }
return ret;
}
@@ -398,21 +409,21 @@ static int activate_managed(struct irq_data *irqd)
}
static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
- bool early)
+ bool reserve)
{
struct apic_chip_data *apicd = apic_chip_data(irqd);
unsigned long flags;
int ret = 0;
trace_vector_activate(irqd->irq, apicd->is_managed,
- apicd->can_reserve, early);
+ apicd->can_reserve, reserve);
/* Nothing to do for fixed assigned vectors */
if (!apicd->can_reserve && !apicd->is_managed)
return 0;
raw_spin_lock_irqsave(&vector_lock, flags);
- if (early || irqd_is_managed_and_shutdown(irqd))
+ if (reserve || irqd_is_managed_and_shutdown(irqd))
vector_assign_managed_shutdown(irqd);
else if (apicd->is_managed)
ret = activate_managed(irqd);
@@ -478,6 +489,7 @@ static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd,
} else {
/* Release the vector */
apicd->can_reserve = true;
+ irqd_set_can_reserve(irqd);
clear_irq_vector(irqd);
realloc = true;
}
@@ -542,8 +554,8 @@ error:
}
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
- struct irq_data *irqd, int ind)
+static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
+ struct irq_data *irqd, int ind)
{
unsigned int cpu, vector, prev_cpu, prev_vector;
struct apic_chip_data *apicd;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 622f13ca8a94..8b04234e010b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
.apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
- .irq_delivery_mode = dest_LowestPrio,
+ .irq_delivery_mode = dest_Fixed,
.irq_dest_mode = 1, /* logical */
.disable_esr = 0,
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 8ea78275480d..76417a9aab73 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -17,6 +17,7 @@
#include <asm/sigframe.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
+#include <asm/tlbflush.h>
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -93,4 +94,13 @@ void common(void) {
BLANK();
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+ /* TLB state for the entry code */
+ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
+ /* Layout info for cpu_entry_area */
+ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+ OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
+ OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
+ DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index dedf428b20b6..fa1261eefa16 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -47,13 +47,8 @@ void foo(void)
BLANK();
/* Offset from the sysenter stack to tss.sp0 */
- DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
- offsetofend(struct tss_struct, SYSENTER_stack));
-
- /* Offset from cpu_tss to SYSENTER_stack */
- OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
- /* Size of SYSENTER_stack */
- DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+ DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+ offsetofend(struct cpu_entry_area, entry_stack_page.stack));
#ifdef CONFIG_CC_STACKPROTECTOR
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 630212fa9b9d..bf51e51d808d 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -23,6 +23,9 @@ int main(void)
#ifdef CONFIG_PARAVIRT
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_DEBUG_ENTRY
+ OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+#endif
BLANK();
#endif
@@ -63,6 +66,7 @@ int main(void)
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+ OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
BLANK();
#ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d58184b7cd44..bcb75dc97d44 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -804,8 +804,11 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x17: init_amd_zn(c); break;
}
- /* Enable workaround for FXSAVE leak */
- if (c->x86 >= 6)
+ /*
+ * Enable workaround for FXSAVE leak on CPUs
+ * without a XSaveErPtr feature
+ */
+ if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR)))
set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
cpu_detect_cache_sizes(c);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fa998ca8aa5a..39d7ea865207 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
return NULL; /* Not found */
}
-__u32 cpu_caps_cleared[NCAPINTS];
-__u32 cpu_caps_set[NCAPINTS];
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
void load_percpu_segment(int cpu)
{
@@ -490,28 +490,23 @@ void load_percpu_segment(int cpu)
load_stack_canary_segment();
}
-/* Setup the fixmap mapping only once per-processor */
-static inline void setup_fixmap_gdt(int cpu)
-{
-#ifdef CONFIG_X86_64
- /* On 64-bit systems, we use a read-only fixmap GDT. */
- pgprot_t prot = PAGE_KERNEL_RO;
-#else
- /*
- * On native 32-bit systems, the GDT cannot be read-only because
- * our double fault handler uses a task gate, and entering through
- * a task gate needs to change an available TSS to busy. If the GDT
- * is read-only, that will triple fault.
- *
- * On Xen PV, the GDT must be read-only because the hypervisor requires
- * it.
- */
- pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
- PAGE_KERNEL_RO : PAGE_KERNEL;
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
#endif
- __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
-}
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
+};
+#endif
/* Load the original GDT from the per-cpu structure */
void load_direct_gdt(int cpu)
@@ -747,7 +742,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
{
int i;
- for (i = 0; i < NCAPINTS; i++) {
+ for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
c->x86_capability[i] &= ~cpu_caps_cleared[i];
c->x86_capability[i] |= cpu_caps_set[i];
}
@@ -927,6 +922,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
}
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+ if (c->x86_vendor != X86_VENDOR_AMD)
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
fpu__init_system(c);
#ifdef CONFIG_X86_32
@@ -1250,7 +1249,7 @@ void enable_sep_cpu(void)
return;
cpu = get_cpu();
- tss = &per_cpu(cpu_tss, cpu);
+ tss = &per_cpu(cpu_tss_rw, cpu);
/*
* We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
@@ -1259,11 +1258,7 @@ void enable_sep_cpu(void)
tss->x86_tss.ss1 = __KERNEL_CS;
wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-
- wrmsr(MSR_IA32_SYSENTER_ESP,
- (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
- 0);
-
+ wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
put_cpu();
@@ -1357,25 +1352,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
- [DEBUG_STACK - 1] = DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
- [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
+ extern char _entry_trampoline[];
+ extern char entry_SYSCALL_64_trampoline[];
+
+ int cpu = smp_processor_id();
+ unsigned long SYSCALL64_entry_trampoline =
+ (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+ (entry_SYSCALL_64_trampoline - _entry_trampoline);
+
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ else
+ wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1386,7 +1378,7 @@ void syscall_init(void)
* AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1530,7 +1522,7 @@ void cpu_init(void)
if (cpu)
load_ucode_ap();
- t = &per_cpu(cpu_tss, cpu);
+ t = &per_cpu(cpu_tss_rw, cpu);
oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
@@ -1569,7 +1561,7 @@ void cpu_init(void)
* set up and load the per-CPU TSS
*/
if (!oist->ist[0]) {
- char *estacks = per_cpu(exception_stacks, cpu);
+ char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
estacks += exception_stack_sizes[v];
@@ -1580,7 +1572,7 @@ void cpu_init(void)
}
}
- t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
/*
* <= is required because the CPU will access up to
@@ -1596,11 +1588,12 @@ void cpu_init(void)
enter_lazy_tlb(&init_mm, me);
/*
- * Initialize the TSS. Don't bother initializing sp0, as the initial
- * task never enters user mode.
+ * Initialize the TSS. sp0 points to the entry trampoline stack
+ * regardless of what task is running.
*/
- set_tss_desc(cpu, t);
+ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
+ load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
load_mm_ldt(&init_mm);
@@ -1612,7 +1605,6 @@ void cpu_init(void)
if (is_uv_system())
uv_cpu_init();
- setup_fixmap_gdt(cpu);
load_fixmap_gdt(cpu);
}
@@ -1622,7 +1614,7 @@ void cpu_init(void)
{
int cpu = smp_processor_id();
struct task_struct *curr = current;
- struct tss_struct *t = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
wait_for_master_cpu(cpu);
@@ -1657,12 +1649,12 @@ void cpu_init(void)
* Initialize the TSS. Don't bother initializing sp0, as the initial
* task never enters user mode.
*/
- set_tss_desc(cpu, t);
+ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
load_mm_ldt(&init_mm);
- t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+ t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
#ifdef CONFIG_DOUBLEFAULT
/* Set up doublefault TSS pointer in the GDT */
@@ -1674,7 +1666,6 @@ void cpu_init(void)
fpu__init_cpu();
- setup_fixmap_gdt(cpu);
load_fixmap_gdt(cpu);
}
#endif
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c6daec4bdba5..330b8462d426 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
#define F16H_MPB_MAX_SIZE 3458
+#define F17H_MPB_MAX_SIZE 3200
switch (family) {
case 0x14:
@@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
case 0x16:
max_size = F16H_MPB_MAX_SIZE;
break;
+ case 0x17:
+ max_size = F17H_MPB_MAX_SIZE;
+ break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 7dbcb7adf797..8ccdca6d3f9e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -565,15 +565,6 @@ static void print_ucode(struct ucode_cpu_info *uci)
}
#else
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
- __native_flush_tlb_global_irq_disabled();
-}
-
static inline void print_ucode(struct ucode_cpu_info *uci)
{
struct microcode_intel *mc;
@@ -602,10 +593,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
if (rev != mc->hdr.rev)
return -1;
-#ifdef CONFIG_X86_64
- /* Flush global tlb. This is precaution. */
- flush_tlb_early();
-#endif
uci->cpu_sig.rev = rev;
if (early)
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index 0e662c55ae90..0b8cedb20d6d 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -50,25 +50,23 @@ static void doublefault_fn(void)
cpu_relax();
}
-struct tss_struct doublefault_tss __cacheline_aligned = {
- .x86_tss = {
- .sp0 = STACK_START,
- .ss0 = __KERNEL_DS,
- .ldt = 0,
- .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,
-
- .ip = (unsigned long) doublefault_fn,
- /* 0x2 bit is always set */
- .flags = X86_EFLAGS_SF | 0x2,
- .sp = STACK_START,
- .es = __USER_DS,
- .cs = __KERNEL_CS,
- .ss = __KERNEL_DS,
- .ds = __USER_DS,
- .fs = __KERNEL_PERCPU,
-
- .__cr3 = __pa_nodebug(swapper_pg_dir),
- }
+struct x86_hw_tss doublefault_tss __cacheline_aligned = {
+ .sp0 = STACK_START,
+ .ss0 = __KERNEL_DS,
+ .ldt = 0,
+ .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,
+
+ .ip = (unsigned long) doublefault_fn,
+ /* 0x2 bit is always set */
+ .flags = X86_EFLAGS_SF | 0x2,
+ .sp = STACK_START,
+ .es = __USER_DS,
+ .cs = __KERNEL_CS,
+ .ss = __KERNEL_DS,
+ .ds = __USER_DS,
+ .fs = __KERNEL_PERCPU,
+
+ .__cr3 = __pa_nodebug(swapper_pg_dir),
};
/* dummy for do_double_fault() call */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index f13b4c00a5de..afbecff161d1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,6 +18,7 @@
#include <linux/nmi.h>
#include <linux/sysfs.h>
+#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
@@ -43,6 +44,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
return true;
}
+bool in_entry_stack(unsigned long *stack, struct stack_info *info)
+{
+ struct entry_stack *ss = cpu_entry_stack(smp_processor_id());
+
+ void *begin = ss;
+ void *end = ss + 1;
+
+ if ((void *)stack < begin || (void *)stack >= end)
+ return false;
+
+ info->type = STACK_TYPE_ENTRY;
+ info->begin = begin;
+ info->end = end;
+ info->next_sp = NULL;
+
+ return true;
+}
+
static void printk_stack_address(unsigned long address, int reliable,
char *log_lvl)
{
@@ -50,6 +69,39 @@ static void printk_stack_address(unsigned long address, int reliable,
printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
}
+void show_iret_regs(struct pt_regs *regs)
+{
+ printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+ printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+ regs->sp, regs->flags);
+}
+
+static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
+ bool partial)
+{
+ /*
+ * These on_stack() checks aren't strictly necessary: the unwind code
+ * has already validated the 'regs' pointer. The checks are done for
+ * ordering reasons: if the registers are on the next stack, we don't
+ * want to print them out yet. Otherwise they'll be shown as part of
+ * the wrong stack. Later, when show_trace_log_lvl() switches to the
+ * next stack, this function will be called again with the same regs so
+ * they can be printed in the right context.
+ */
+ if (!partial && on_stack(info, regs, sizeof(*regs))) {
+ __show_regs(regs, 0);
+
+ } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+ IRET_FRAME_SIZE)) {
+ /*
+ * When an interrupt or exception occurs in entry code, the
+ * full pt_regs might not have been saved yet. In that case
+ * just print the iret frame.
+ */
+ show_iret_regs(regs);
+ }
+}
+
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, char *log_lvl)
{
@@ -57,11 +109,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
struct stack_info stack_info = {0};
unsigned long visit_mask = 0;
int graph_idx = 0;
+ bool partial;
printk("%sCall Trace:\n", log_lvl);
unwind_start(&state, task, regs, stack);
stack = stack ? : get_stack_pointer(task, regs);
+ regs = unwind_get_entry_regs(&state, &partial);
/*
* Iterate through the stacks, starting with the current stack pointer.
@@ -71,31 +125,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
* - task stack
* - interrupt stack
* - HW exception stacks (double fault, nmi, debug, mce)
+ * - entry stack
*
- * x86-32 can have up to three stacks:
+ * x86-32 can have up to four stacks:
* - task stack
* - softirq stack
* - hardirq stack
+ * - entry stack
*/
- for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+ for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
const char *stack_name;
- /*
- * If we overflowed the task stack into a guard page, jump back
- * to the bottom of the usable stack.
- */
- if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
- stack = task_stack_page(task);
-
- if (get_stack_info(stack, task, &stack_info, &visit_mask))
- break;
+ if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
+ /*
+ * We weren't on a valid stack. It's possible that
+ * we overflowed a valid stack into a guard page.
+ * See if the next page up is valid so that we can
+ * generate some kind of backtrace if this happens.
+ */
+ stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack);
+ if (get_stack_info(stack, task, &stack_info, &visit_mask))
+ break;
+ }
stack_name = stack_type_name(stack_info.type);
if (stack_name)
printk("%s <%s>\n", log_lvl, stack_name);
- if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
- __show_regs(regs, 0);
+ if (regs)
+ show_regs_if_on_stack(&stack_info, regs, partial);
/*
* Scan the stack, printing any text addresses we find. At the
@@ -119,7 +177,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
/*
* Don't print regs->ip again if it was already printed
- * by __show_regs() below.
+ * by show_regs_if_on_stack().
*/
if (regs && stack == &regs->ip)
goto next;
@@ -154,9 +212,9 @@ next:
unwind_next_frame(&state);
/* if the frame has entry regs, print them */
- regs = unwind_get_entry_regs(&state);
- if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
- __show_regs(regs, 0);
+ regs = unwind_get_entry_regs(&state, &partial);
+ if (regs)
+ show_regs_if_on_stack(&stack_info, regs, partial);
}
if (stack_name)
@@ -252,11 +310,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
unsigned long sp;
#endif
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+ "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
- IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "");
+ IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
+ IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+ (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index daefae83a3aa..04170f63e3a1 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type)
if (type == STACK_TYPE_SOFTIRQ)
return "SOFTIRQ";
+ if (type == STACK_TYPE_ENTRY)
+ return "ENTRY_TRAMPOLINE";
+
return NULL;
}
@@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
if (task != current)
goto unknown;
+ if (in_entry_stack(stack, info))
+ goto recursion_check;
+
if (in_hardirq_stack(stack, info))
goto recursion_check;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 88ce2ffdb110..563e28d14f2c 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -37,6 +37,15 @@ const char *stack_type_name(enum stack_type type)
if (type == STACK_TYPE_IRQ)
return "IRQ";
+ if (type == STACK_TYPE_ENTRY) {
+ /*
+ * On 64-bit, we have a generic entry stack that we
+ * use for all the kernel entry points, including
+ * SYSENTER.
+ */
+ return "ENTRY_TRAMPOLINE";
+ }
+
if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
return exception_stack_names[type - STACK_TYPE_EXCEPTION];
@@ -115,6 +124,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
if (in_irq_stack(stack, info))
goto recursion_check;
+ if (in_entry_stack(stack, info))
+ goto recursion_check;
+
goto unknown;
recursion_check:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7dca675fe78d..04a625f0fcda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
.balign PAGE_SIZE; \
GLOBAL(name)
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned. We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL 512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+ .balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL 0
+#endif
+
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
i = 0 ; \
@@ -350,13 +371,14 @@ GLOBAL(name)
.endr
__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
.fill 511,8,0
#ifdef CONFIG_X86_5LEVEL
.quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#else
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#endif
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
.data
#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.fill 512,8,0
+ .fill PTI_USER_PGD_FILL,8,0
#endif
#ifdef CONFIG_X86_5LEVEL
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 3feb648781c4..2f723301eb58 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
* because the ->io_bitmap_max value must match the bitmap
* contents:
*/
- tss = &per_cpu(cpu_tss, get_cpu());
+ tss = &per_cpu(cpu_tss_rw, get_cpu());
if (turn_on)
bitmap_clear(t->io_bitmap_ptr, from, num);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 49cfd9fe7589..68e1867cca80 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
/* high bit used in ret_from_ code */
unsigned vector = ~regs->orig_ax;
- /*
- * NB: Unlike exception entries, IRQ entries do not reliably
- * handle context tracking in the low-level entry code. This is
- * because syscall entries execute briefly with IRQs on before
- * updating context tracking state, so we can take an IRQ from
- * kernel mode with CONTEXT_USER. The low-level entry code only
- * updates the context if we came from user mode, so we won't
- * switch to CONTEXT_KERNEL. We'll fix that once the syscall
- * code is cleaned up enough that we can cleanly defer enabling
- * IRQs.
- */
-
entering_irq();
/* entering_irq() tells RCU that we're not quiescent. Check it. */
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 020efbf5786b..d86e344f5b3d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs)
if (regs->sp >= estack_top && regs->sp <= estack_bottom)
return;
- WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+ WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
current->comm, curbase, regs->sp,
irq_stack_top, irq_stack_bottom,
- estack_top, estack_bottom);
+ estack_top, estack_bottom, (void *)regs->ip);
if (sysctl_panic_on_stackoverflow)
panic("low stack detected by irq handler - check messages\n");
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 1c1eae961340..26d713ecad34 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -5,6 +5,11 @@
* Copyright (C) 2002 Andi Kleen
*
* This handles calls from both 32bit and 64bit mode.
+ *
+ * Lock order:
+ * contex.ldt_usr_sem
+ * mmap_sem
+ * context.lock
*/
#include <linux/errno.h>
@@ -19,6 +24,7 @@
#include <linux/uaccess.h>
#include <asm/ldt.h>
+#include <asm/tlb.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -42,17 +48,15 @@ static void refresh_ldt_segments(void)
#endif
}
-/* context.lock is held for us, so we don't need any locking. */
+/* context.lock is held by the task which issued the smp function call */
static void flush_ldt(void *__mm)
{
struct mm_struct *mm = __mm;
- mm_context_t *pc;
if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
return;
- pc = &mm->context;
- set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+ load_mm_ldt(mm);
refresh_ldt_segments();
}
@@ -89,25 +93,143 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
return NULL;
}
+ /* The new LDT isn't aliased for PTI yet. */
+ new_ldt->slot = -1;
+
new_ldt->nr_entries = num_entries;
return new_ldt;
}
+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function. Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ bool is_vmalloc, had_top_level_entry;
+ unsigned long va;
+ spinlock_t *ptl;
+ pgd_t *pgd;
+ int i;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return 0;
+
+ /*
+ * Any given ldt_struct should have map_ldt_struct() called at most
+ * once.
+ */
+ WARN_ON(ldt->slot != -1);
+
+ /*
+ * Did we already have the top level entry allocated? We can't
+ * use pgd_none() for this because it doens't do anything on
+ * 4-level page table kernels.
+ */
+ pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ had_top_level_entry = (pgd->pgd != 0);
+
+ is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+ for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+ unsigned long offset = i << PAGE_SHIFT;
+ const void *src = (char *)ldt->entries + offset;
+ unsigned long pfn;
+ pte_t pte, *ptep;
+
+ va = (unsigned long)ldt_slot_va(slot) + offset;
+ pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+ page_to_pfn(virt_to_page(src));
+ /*
+ * Treat the PTI LDT range as a *userspace* range.
+ * get_locked_pte() will allocate all needed pagetables
+ * and account for them in this mm.
+ */
+ ptep = get_locked_pte(mm, va, &ptl);
+ if (!ptep)
+ return -ENOMEM;
+ /*
+ * Map it RO so the easy to find address is not a primary
+ * target via some kernel interface which misses a
+ * permission check.
+ */
+ pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+ set_pte_at(mm, va, ptep, pte);
+ pte_unmap_unlock(ptep, ptl);
+ }
+
+ if (mm->context.ldt) {
+ /*
+ * We already had an LDT. The top-level entry should already
+ * have been allocated and synchronized with the usermode
+ * tables.
+ */
+ WARN_ON(!had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+ } else {
+ /*
+ * This is the first time we're mapping an LDT for this process.
+ * Sync the pgd to the usermode tables.
+ */
+ WARN_ON(had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+ set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+ }
+ }
+
+ va = (unsigned long)ldt_slot_va(slot);
+ flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+ ldt->slot = slot;
+#endif
+ return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ struct mmu_gather tlb;
+ unsigned long start = LDT_BASE_ADDR;
+ unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ free_pgd_range(&tlb, start, end, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
}
-/* context.lock is held */
-static void install_ldt(struct mm_struct *current_mm,
- struct ldt_struct *ldt)
+static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
{
+ mutex_lock(&mm->context.lock);
+
/* Synchronizes with READ_ONCE in load_mm_ldt. */
- smp_store_release(&current_mm->context.ldt, ldt);
+ smp_store_release(&mm->context.ldt, ldt);
- /* Activate the LDT for all CPUs using current_mm. */
- on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+ /* Activate the LDT for all CPUs using currents mm. */
+ on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);
+
+ mutex_unlock(&mm->context.lock);
}
static void free_ldt_struct(struct ldt_struct *ldt)
@@ -124,27 +246,20 @@ static void free_ldt_struct(struct ldt_struct *ldt)
}
/*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
*/
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
{
struct ldt_struct *new_ldt;
- struct mm_struct *old_mm;
int retval = 0;
- mutex_init(&mm->context.lock);
- old_mm = current->mm;
- if (!old_mm) {
- mm->context.ldt = NULL;
+ if (!old_mm)
return 0;
- }
mutex_lock(&old_mm->context.lock);
- if (!old_mm->context.ldt) {
- mm->context.ldt = NULL;
+ if (!old_mm->context.ldt)
goto out_unlock;
- }
new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
if (!new_ldt) {
@@ -156,6 +271,12 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
new_ldt->nr_entries * LDT_ENTRY_SIZE);
finalize_ldt_struct(new_ldt);
+ retval = map_ldt_struct(mm, new_ldt, 0);
+ if (retval) {
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
mm->context.ldt = new_ldt;
out_unlock:
@@ -174,13 +295,18 @@ void destroy_context_ldt(struct mm_struct *mm)
mm->context.ldt = NULL;
}
+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+ free_ldt_pgtables(mm);
+}
+
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
struct mm_struct *mm = current->mm;
unsigned long entries_size;
int retval;
- mutex_lock(&mm->context.lock);
+ down_read(&mm->context.ldt_usr_sem);
if (!mm->context.ldt) {
retval = 0;
@@ -209,7 +335,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
retval = bytecount;
out_unlock:
- mutex_unlock(&mm->context.lock);
+ up_read(&mm->context.ldt_usr_sem);
return retval;
}
@@ -269,7 +395,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
ldt.avl = 0;
}
- mutex_lock(&mm->context.lock);
+ if (down_write_killable(&mm->context.ldt_usr_sem))
+ return -EINTR;
old_ldt = mm->context.ldt;
old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
@@ -286,12 +413,31 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
new_ldt->entries[ldt_info.entry_number] = ldt;
finalize_ldt_struct(new_ldt);
+ /*
+ * If we are using PTI, map the new LDT into the userspace pagetables.
+ * If there is already an LDT, use the other slot so that other CPUs
+ * will continue to use the old LDT until install_ldt() switches
+ * them over to the new LDT.
+ */
+ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+ if (error) {
+ /*
+ * This only can fail for the first LDT setup. If an LDT is
+ * already installed then the PTE page is already
+ * populated. Mop up a half populated page table.
+ */
+ if (!WARN_ON_ONCE(old_ldt))
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
+
install_ldt(mm, new_ldt);
free_ldt_struct(old_ldt);
error = 0;
out_unlock:
- mutex_unlock(&mm->context.lock);
+ up_write(&mm->context.ldt_usr_sem);
out:
return error;
}
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 00bc751c861c..edfede768688 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -48,8 +48,6 @@ static void load_segments(void)
"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
"\tmovl %%eax,%%ds\n"
"\tmovl %%eax,%%es\n"
- "\tmovl %%eax,%%fs\n"
- "\tmovl %%eax,%%gs\n"
"\tmovl %%eax,%%ss\n"
: : : "eax", "memory");
#undef STR
@@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image)
* The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0), 0);
idt_invalidate(phys_to_virt(0));
+ set_gdt(phys_to_virt(0), 0);
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index ac0be8283325..9edadabf04f6 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
@@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_mmu_ops, read_cr2);
PATCH_SITE(pv_mmu_ops, read_cr3);
PATCH_SITE(pv_mmu_ops, write_cr3);
- PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 97fb3e5737f5..832a6acd730f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -47,7 +47,7 @@
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
.x86_tss = {
/*
* .sp0 is only used when entering ring 0 from a lower
@@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
* Poison it.
*/
.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
+
+#ifdef CONFIG_X86_64
+ /*
+ * .sp1 is cpu_current_top_of_stack. The init task never
+ * runs user code, but cpu_current_top_of_stack should still
+ * be well defined before the first context switch.
+ */
+ .sp1 = TOP_OF_INIT_STACK,
+#endif
+
#ifdef CONFIG_X86_32
.ss0 = __KERNEL_DS,
.ss1 = __KERNEL_CS,
@@ -71,11 +81,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
*/
.io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 },
#endif
-#ifdef CONFIG_X86_32
- .SYSENTER_stack_canary = STACK_END_MAGIC,
-#endif
};
-EXPORT_PER_CPU_SYMBOL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
DEFINE_PER_CPU(bool, __tss_limit_invalid);
EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
@@ -104,7 +111,7 @@ void exit_thread(struct task_struct *tsk)
struct fpu *fpu = &t->fpu;
if (bp) {
- struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu());
t->io_bitmap_ptr = NULL;
clear_thread_flag(TIF_IO_BITMAP);
@@ -299,7 +306,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
}
if ((tifp ^ tifn) & _TIF_NOTSC)
- cr4_toggle_bits(X86_CR4_TSD);
+ cr4_toggle_bits_irqsoff(X86_CR4_TSD);
if ((tifp ^ tifn) & _TIF_NOCPUID)
set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 45bf0c5f93e1..5224c6099184 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct fpu *prev_fpu = &prev->fpu;
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index eeeb34f85c25..c75466232016 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all)
unsigned int fsindex, gsindex;
unsigned int ds, cs, es;
- printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
- printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
- regs->sp, regs->flags);
+ show_iret_regs(regs);
+
if (regs->orig_ax != -1)
pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
else
@@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
regs->r13, regs->r14, regs->r15);
+ if (!all)
+ return;
+
asm("movl %%ds,%0" : "=r" (ds));
asm("movl %%cs,%0" : "=r" (cs));
asm("movl %%es,%0" : "=r" (es));
@@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all)
rdmsrl(MSR_GS_BASE, gs);
rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
- if (!all)
- return;
-
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = __read_cr3();
@@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct fpu *prev_fpu = &prev->fpu;
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
this_cpu_read(irq_count) != -1);
@@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
* Switch the PDA and FPU contexts.
*/
this_cpu_write(current_task, next_p);
+ this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
/* Reload sp0. */
update_sp0(next_p);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8af2e8d0c0a1..145810b0edf6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -906,9 +906,6 @@ void __init setup_arch(char **cmdline_p)
set_bit(EFI_BOOT, &efi.flags);
set_bit(EFI_64BIT, &efi.flags);
}
-
- if (efi_enabled(EFI_BOOT))
- efi_memblock_x86_reserve_range();
#endif
x86_init.oem.arch_setup();
@@ -962,6 +959,8 @@ void __init setup_arch(char **cmdline_p)
parse_early_param();
+ if (efi_enabled(EFI_BOOT))
+ efi_memblock_x86_reserve_range();
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3d01df7d7cf6..ed556d50d7ed 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -106,7 +106,7 @@ EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
/* Maximum number of SMT threads on any online core */
-int __max_smt_threads __read_mostly;
+int __read_mostly __max_smt_threads = 1;
/* Flag to indicate if a complete sched domain rebuild is required */
bool x86_topology_update;
@@ -126,14 +126,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}
static inline void smpboot_restore_warm_reset_vector(void)
@@ -141,11 +137,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
unsigned long flags;
/*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
- /*
* Paranoid: Set warm reset code and vector here back
* to default values.
*/
@@ -237,7 +228,7 @@ static void notrace start_secondary(void *unused)
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
-
+ load_current_idt();
cpu_init();
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
@@ -932,12 +923,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
initial_code = (unsigned long)start_secondary;
initial_stack = idle->thread.sp;
- /*
- * Enable the espfix hack for this CPU
- */
-#ifdef CONFIG_X86_ESPFIX64
+ /* Enable the espfix hack for this CPU */
init_espfix_ap(cpu);
-#endif
/* So we see what's up */
announce_cpu(cpu, apicid);
@@ -1304,7 +1291,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
* 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;
+ ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
pr_info("Max logical packages: %u\n", __max_logical_packages);
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 77835bc021c7..093f2ea5dd56 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -102,7 +102,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
- regs = unwind_get_entry_regs(&state);
+ regs = unwind_get_entry_regs(&state, NULL);
if (regs) {
/*
* Kernel mode registers on the stack indicate an
@@ -164,8 +164,12 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk,
{
int ret;
+ /*
+ * If the task doesn't have a stack (e.g., a zombie), the stack is
+ * "reliably" empty.
+ */
if (!try_get_task_stack(tsk))
- return -EINVAL;
+ return 0;
ret = __save_stack_trace_reliable(trace, tsk);
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9a9c9b076955..a5b802a12212 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx,
cpu = get_cpu();
while (n-- > 0) {
- if (LDT_empty(info) || LDT_zero(info)) {
+ if (LDT_empty(info) || LDT_zero(info))
memset(desc, 0, sizeof(*desc));
- } else {
+ else
fill_ldt(desc, info);
-
- /*
- * Always set the accessed bit so that the CPU
- * doesn't try to write to the (read-only) GDT.
- */
- desc->type |= 1;
- }
++info;
++desc;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 989514c94a55..446c9ef8cfc3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
+#include <asm/cpu_entry_area.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
@@ -348,23 +349,42 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
/*
* If IRET takes a non-IST fault on the espfix64 stack, then we
- * end up promoting it to a doublefault. In that case, modify
- * the stack to make it look like we just entered the #GP
- * handler from user space, similar to bad_iret.
+ * end up promoting it to a doublefault. In that case, take
+ * advantage of the fact that we're not using the normal (TSS.sp0)
+ * stack right now. We can write a fake #GP(0) frame at TSS.sp0
+ * and then modify our own IRET frame so that, when we return,
+ * we land directly at the #GP(0) vector with the stack already
+ * set up according to its expectations.
+ *
+ * The net result is that our #GP handler will think that we
+ * entered from usermode with the bad user context.
*
* No need for ist_enter here because we don't use RCU.
*/
- if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
regs->ip == (unsigned long)native_irq_return_iret)
{
- struct pt_regs *normal_regs = task_pt_regs(current);
+ struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
- /* Fake a #GP(0) from userspace. */
- memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
- normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
+ /*
+ * regs->sp points to the failing IRET frame on the
+ * ESPFIX64 stack. Copy it to the entry stack. This fills
+ * in gpregs->ss through gpregs->ip.
+ *
+ */
+ memmove(&gpregs->ip, (void *)regs->sp, 5*8);
+ gpregs->orig_ax = 0; /* Missing (lost) #GP error code */
+
+ /*
+ * Adjust our frame so that we return straight to the #GP
+ * vector with the expected RSP value. This is safe because
+ * we won't enable interupts or schedule before we invoke
+ * general_protection, so nothing will clobber the stack
+ * frame we just set up.
+ */
regs->ip = (unsigned long)general_protection;
- regs->sp = (unsigned long)&normal_regs->orig_ax;
+ regs->sp = (unsigned long)&gpregs->orig_ax;
return;
}
@@ -389,7 +409,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
*
* Processors update CR2 whenever a page fault is detected. If a
* second page fault occurs while an earlier page fault is being
- * deliv- ered, the faulting linear address of the second fault will
+ * delivered, the faulting linear address of the second fault will
* overwrite the contents of CR2 (replacing the previous
* address). These updates to CR2 occur even if the page fault
* results in a double fault or occurs during the delivery of a
@@ -605,14 +625,15 @@ NOKPROBE_SYMBOL(do_int3);
#ifdef CONFIG_X86_64
/*
- * Help handler running on IST stack to switch off the IST stack if the
- * interrupted code was in user mode. The actual stack switch is done in
- * entry_64.S
+ * Help handler running on a per-cpu (IST or entry trampoline) stack
+ * to switch to the normal thread stack if the interrupted code was in
+ * user mode. The actual stack switch is done in entry_64.S
*/
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
- struct pt_regs *regs = task_pt_regs(current);
- *regs = *eregs;
+ struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+ if (regs != eregs)
+ *regs = *eregs;
return regs;
}
NOKPROBE_SYMBOL(sync_regs);
@@ -628,13 +649,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
/*
* This is called from entry_64.S early in handling a fault
* caused by a bad iret to user mode. To handle the fault
- * correctly, we want move our stack frame to task_pt_regs
- * and we want to pretend that the exception came from the
- * iret target.
+ * correctly, we want to move our stack frame to where it would
+ * be had we entered directly on the entry stack (rather than
+ * just below the IRET frame) and we want to pretend that the
+ * exception came from the IRET target.
*/
struct bad_iret_stack *new_stack =
- container_of(task_pt_regs(current),
- struct bad_iret_stack, regs);
+ (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
/* Copy the IRET target to the new stack. */
memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
@@ -795,14 +816,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
debug_stack_usage_dec();
exit:
-#if defined(CONFIG_X86_32)
- /*
- * This is the most likely code path that involves non-trivial use
- * of the SYSENTER stack. Check that we haven't overrun it.
- */
- WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
- "Overran or corrupted SYSENTER stack\n");
-#endif
ist_exit(regs);
}
NOKPROBE_SYMBOL(do_debug);
@@ -929,6 +942,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
void __init trap_init(void)
{
+ /* Init cpu_entry_area before IST entries are set up */
+ setup_cpu_entry_areas();
+
idt_setup_traps();
/*
@@ -936,8 +952,9 @@ void __init trap_init(void)
* "sidt" instruction will not leak the location of the kernel, and
* to defend the IDT against arbitrary memory write vulnerabilities.
* It will be reloaded in cpu_init() */
- __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
- idt_descr.address = fix_to_virt(FIX_RO_IDT);
+ cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
+ PAGE_KERNEL_RO);
+ idt_descr.address = CPU_ENTRY_AREA_RO_IDT;
/*
* Should be a barrier for any external CPU state:
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a3f973b2c97a..be86a865087a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
return NULL;
}
-static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
size_t len)
{
struct stack_info *info = &state->stack_info;
+ void *addr = (void *)_addr;
- /*
- * If the address isn't on the current stack, switch to the next one.
- *
- * We may have to traverse multiple stacks to deal with the possibility
- * that info->next_sp could point to an empty stack and the address
- * could be on a subsequent stack.
- */
- while (!on_stack(info, (void *)addr, len))
- if (get_stack_info(info->next_sp, state->task, info,
- &state->stack_mask))
- return false;
+ if (!on_stack(info, addr, len) &&
+ (get_stack_info(addr, state->task, info, &state->stack_mask)))
+ return false;
return true;
}
@@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
return true;
}
-#define REGS_SIZE (sizeof(struct pt_regs))
-#define SP_OFFSET (offsetof(struct pt_regs, sp))
-#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
-#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
-
static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
- unsigned long *ip, unsigned long *sp, bool full)
+ unsigned long *ip, unsigned long *sp)
{
- size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
- size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
- struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
-
- if (IS_ENABLED(CONFIG_X86_64)) {
- if (!stack_access_ok(state, addr, regs_size))
- return false;
+ struct pt_regs *regs = (struct pt_regs *)addr;
- *ip = regs->ip;
- *sp = regs->sp;
+ /* x86-32 support will be more complicated due to the &regs->sp hack */
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
- return true;
- }
-
- if (!stack_access_ok(state, addr, sp_offset))
+ if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
return false;
*ip = regs->ip;
+ *sp = regs->sp;
+ return true;
+}
- if (user_mode(regs)) {
- if (!stack_access_ok(state, addr + sp_offset,
- REGS_SIZE - SP_OFFSET))
- return false;
+static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
+ unsigned long *ip, unsigned long *sp)
+{
+ struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
- *sp = regs->sp;
- } else
- *sp = (unsigned long)&regs->sp;
+ if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
+ return false;
+ *ip = regs->ip;
+ *sp = regs->sp;
return true;
}
@@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state)
unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
enum stack_type prev_type = state->stack_info.type;
struct orc_entry *orc;
- struct pt_regs *ptregs;
bool indirect = false;
if (unwind_done(state))
@@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state)
break;
case ORC_TYPE_REGS:
- if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+ if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
goto done;
@@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state)
break;
case ORC_TYPE_REGS_IRET:
- if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+ if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
orc_warn("can't dereference iret registers at %p for ip %pB\n",
(void *)sp, (void *)orig_ip);
goto done;
}
- ptregs = container_of((void *)sp, struct pt_regs, ip);
- if ((unsigned long)ptregs >= prev_sp &&
- on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
- state->regs = ptregs;
- state->full_regs = false;
- } else
- state->regs = NULL;
-
+ state->regs = (void *)sp - IRET_FRAME_OFFSET;
+ state->full_regs = false;
state->signal = true;
break;
@@ -553,8 +529,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
}
if (get_stack_info((unsigned long *)state->sp, state->task,
- &state->stack_info, &state->stack_mask))
- return;
+ &state->stack_info, &state->stack_mask)) {
+ /*
+ * We weren't on a valid stack. It's possible that
+ * we overflowed a valid stack into a guard page.
+ * See if the next page up is valid so that we can
+ * generate some kind of backtrace if this happens.
+ */
+ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+ if (get_stack_info(next_page, state->task, &state->stack_info,
+ &state->stack_mask))
+ return;
+ }
/*
* The caller can provide the address of the first frame directly
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a4009fb9be87..1e413a9326aa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -61,11 +61,17 @@ jiffies_64 = jiffies;
. = ALIGN(HPAGE_SIZE); \
__end_rodata_hpage_align = .;
+#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
+#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+
#else
#define X64_ALIGN_RODATA_BEGIN
#define X64_ALIGN_RODATA_END
+#define ALIGN_ENTRY_TEXT_BEGIN
+#define ALIGN_ENTRY_TEXT_END
+
#endif
PHDRS {
@@ -102,11 +108,22 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ALIGN_ENTRY_TEXT_BEGIN
ENTRY_TEXT
IRQENTRY_TEXT
+ ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
+
+#ifdef CONFIG_X86_64
+ . = ALIGN(PAGE_SIZE);
+ _entry_trampoline = .;
+ *(.entry_trampoline)
+ . = ALIGN(PAGE_SIZE);
+ ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
+#endif
+
/* End of text section */
_etext = .;
} :text = 0x9090