summaryrefslogtreecommitdiffstats
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/asm.h2
-rw-r--r--arch/x86/include/asm/cpu_entry_area.h81
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h5
-rw-r--r--arch/x86/include/asm/desc.h14
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/espfix.h7
-rw-r--r--arch/x86/include/asm/fixmap.h7
-rw-r--r--arch/x86/include/asm/hypervisor.h25
-rw-r--r--arch/x86/include/asm/intel_ds.h36
-rw-r--r--arch/x86/include/asm/invpcid.h53
-rw-r--r--arch/x86/include/asm/irqdomain.h2
-rw-r--r--arch/x86/include/asm/irqflags.h3
-rw-r--r--arch/x86/include/asm/kdebug.h1
-rw-r--r--arch/x86/include/asm/kmemcheck.h1
-rw-r--r--arch/x86/include/asm/kvm_emulate.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h16
-rw-r--r--arch/x86/include/asm/mmu.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h113
-rw-r--r--arch/x86/include/asm/paravirt.h9
-rw-r--r--arch/x86/include/asm/pgalloc.h11
-rw-r--r--arch/x86/include/asm/pgtable.h30
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h15
-rw-r--r--arch/x86/include/asm/pgtable_64.h92
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h51
-rw-r--r--arch/x86/include/asm/processor-flags.h5
-rw-r--r--arch/x86/include/asm/processor.h82
-rw-r--r--arch/x86/include/asm/pti.h14
-rw-r--r--arch/x86/include/asm/segment.h12
-rw-r--r--arch/x86/include/asm/stacktrace.h3
-rw-r--r--arch/x86/include/asm/suspend_32.h8
-rw-r--r--arch/x86/include/asm/suspend_64.h19
-rw-r--r--arch/x86/include/asm/switch_to.h13
-rw-r--r--arch/x86/include/asm/thread_info.h2
-rw-r--r--arch/x86/include/asm/tlbflush.h347
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h16
-rw-r--r--arch/x86/include/asm/traps.h1
-rw-r--r--arch/x86/include/asm/unwind.h7
-rw-r--r--arch/x86/include/asm/vsyscall.h1
-rw-r--r--arch/x86/include/uapi/asm/Kbuild1
-rw-r--r--arch/x86/include/uapi/asm/processor-flags.h7
41 files changed, 877 insertions, 251 deletions
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..386a6900e206 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,6 +136,7 @@
#endif
#ifndef __ASSEMBLY__
+#ifndef __BPF__
/*
* This output constraint should be used for any inline asm which has a "call"
* instruction. Otherwise the asm may be inserted before the frame pointer
@@ -145,5 +146,6 @@
register unsigned long current_stack_pointer asm(_ASM_SP);
#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
#endif
+#endif
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
new file mode 100644
index 000000000000..4a7884b8dca5
--- /dev/null
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code. Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+ char gdt[PAGE_SIZE];
+
+ /*
+ * The GDT is just below entry_stack and thus serves (on x86_64) as
+ * a a read-only guard page.
+ */
+ struct entry_stack_page entry_stack_page;
+
+ /*
+ * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because
+ * we need task switches to work, and task switches write to the TSS.
+ */
+ struct tss_struct tss;
+
+ char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+ /*
+ * Exception stacks used for IST entries.
+ *
+ * In the future, this should have a separate slot for each stack
+ * with guard pages between them.
+ */
+ char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+ /*
+ * Per CPU debug store for Intel performance monitoring. Wastes a
+ * full page at the moment.
+ */
+ struct debug_store cpu_debug_store;
+ /*
+ * The actual PEBS/BTS buffers must be mapped to user space
+ * Reserve enough fixmap PTEs.
+ */
+ struct debug_store_buffers cpu_debug_buffers;
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE \
+ (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+ return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bf6a76202a77..ea9a7dde62e5 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c0b0e9e8aa66..07cdd1715705 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -197,11 +197,12 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -266,6 +267,7 @@
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -339,5 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4011cb03ef08..13c5ee878a47 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -7,6 +7,7 @@
#include <asm/mmu.h>
#include <asm/fixmap.h>
#include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
#include <linux/smp.h>
#include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
desc->type = (info->read_exec_only ^ 1) << 1;
desc->type |= info->contents << 2;
+ /* Set the ACCESS bit so it can be mapped RO */
+ desc->type |= 1;
desc->s = 1;
desc->dpl = 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
return this_cpu_ptr(&gdt_page)->gdt;
}
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
- return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
/* Provide the fixmap address of the remapped GDT */
static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
{
- unsigned int idx = get_cpu_gdt_ro_index(cpu);
- return (struct desc_struct *)__fix_to_virt(idx);
+ return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
}
/* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
#endif
}
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
{
struct desc_struct *d = get_cpu_gdt_rw(cpu);
tss_desc tss;
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 14d6d5007314..b027633e7300 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -50,6 +50,12 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI 0
+#else
+# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -60,7 +66,7 @@
#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
-#define DISABLED_MASK7 0
+#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 0211029076ea..6777480d8a42 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_ESPFIX_H
#define _ASM_X86_ESPFIX_H
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
#include <asm/percpu.h>
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
extern void init_espfix_bsp(void);
extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b0c505fe9a95..64c4a30e0d39 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
PAGE_SIZE)
#endif
-
/*
* Here we define all the compile-time 'special' virtual
* addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
FIX_IO_APIC_BASE_0,
FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
#endif
- FIX_RO_IDT, /* Virtual mapping for read-only IDT */
#ifdef CONFIG_X86_32
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
#ifdef CONFIG_X86_INTEL_MID
FIX_LNW_VRTC,
#endif
- /* Fixmap entries to remap the GDTs, one per processor. */
- FIX_GDT_REMAP_BEGIN,
- FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
#ifdef CONFIG_ACPI_APEI_GHES
/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
extern void reserve_top_address(unsigned long reserve);
#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
extern int fixmaps_set;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 1b0a5abcd8ae..96aa6b9884dc 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,16 +20,7 @@
#ifndef _ASM_X86_HYPERVISOR_H
#define _ASM_X86_HYPERVISOR_H
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types */
enum x86_hypervisor_type {
X86_HYPER_NATIVE = 0,
X86_HYPER_VMWARE,
@@ -39,6 +30,12 @@ enum x86_hypervisor_type {
X86_HYPER_KVM,
};
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
struct hypervisor_x86 {
/* Hypervisor name */
const char *name;
@@ -58,7 +55,15 @@ struct hypervisor_x86 {
extern enum x86_hypervisor_type x86_hyper_type;
extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+ return x86_hyper_type == type;
+}
#else
static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+ return type == X86_HYPER_NATIVE;
+}
#endif /* CONFIG_HYPERVISOR_GUEST */
#endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+ char bts_buffer[BTS_BUFFER_SIZE];
+ char pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
new file mode 100644
index 000000000000..989cfa86de85
--- /dev/null
+++ b/arch/x86/include/asm/invpcid.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+ unsigned long type)
+{
+ struct { u64 d[2]; } desc = { { pcid, addr } };
+
+ /*
+ * The memory clobber is because the whole point is to invalidate
+ * stale TLB entries and, especially if we're flushing global
+ * mappings, we don't want the compiler to reorder any subsequent
+ * memory accesses before the TLB flush.
+ *
+ * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+ * invpcid (%rcx), %rax in long mode.
+ */
+ asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+ : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR 0
+#define INVPCID_TYPE_SINGLE_CTXT 1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
+#define INVPCID_TYPE_ALL_NON_GLOBAL 3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+ unsigned long addr)
+{
+ __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+ __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+ __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+ __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index 139feef467f7..c066ffae222b 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs);
extern int mp_irqdomain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early);
+ struct irq_data *irq_data, bool reserve);
extern void mp_irqdomain_deactivate(struct irq_domain *domain,
struct irq_data *irq_data);
extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c8ef23f2c28f..89f08955fff7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
swapgs; \
sysretl
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x) pushfq; popq %rax
+#endif
#else
#define INTERRUPT_RETURN iret
#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f86a8caa561e..395c9631e000 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
extern int __must_check __die(const char *, struct pt_regs *, long);
extern void show_stack_regs(struct pt_regs *regs);
extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
extern unsigned long oops_begin(void);
extern void oops_end(unsigned long, struct pt_regs *, int signr);
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/include/asm/kmemcheck.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
void (*halt)(struct x86_emulate_ctxt *ctxt);
void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
- void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
- void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
int (*intercept)(struct x86_emulate_ctxt *ctxt,
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 977de5fb968b..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_page_cache;
struct kvm_mmu_memory_cache mmu_page_header_cache;
+ /*
+ * QEMU userspace and the guest each have their own FPU state.
+ * In vcpu_run, we switch between the user and guest FPU contexts.
+ * While running a VCPU, the VCPU thread will have the guest FPU
+ * context.
+ *
+ * Note that while the PKRU state lives inside the fpu registers,
+ * it is switched out separately at VMENTER and VMEXIT time. The
+ * "guest_fpu" state here contains the guest FPU context, with the
+ * host PRKU bits.
+ */
+ struct fpu user_fpu;
struct fpu guest_fpu;
+
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
@@ -1435,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+ unsigned long start, unsigned long end);
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9ea26f167497..5ff3e8af2c20 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,6 +3,7 @@
#define _ASM_X86_MMU_H
#include <linux/spinlock.h>
+#include <linux/rwsem.h>
#include <linux/mutex.h>
#include <linux/atomic.h>
@@ -27,7 +28,8 @@ typedef struct {
atomic64_t tlb_gen;
#ifdef CONFIG_MODIFY_LDT_SYSCALL
- struct ldt_struct *ldt;
+ struct rw_semaphore ldt_usr_sem;
+ struct ldt_struct *ldt;
#endif
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 6d16d15d09a0..c931b88982a0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,22 +50,53 @@ struct ldt_struct {
* call gates. On native, we could merge the ldt_struct and LDT
* allocations, but it's not worth trying to optimize.
*/
- struct desc_struct *entries;
- unsigned int nr_entries;
+ struct desc_struct *entries;
+ unsigned int nr_entries;
+
+ /*
+ * If PTI is in use, then the entries array is not mapped while we're
+ * in user mode. The whole array will be aliased at the addressed
+ * given by ldt_slot_va(slot). We use two slots so that we can allocate
+ * and map, and enable a new LDT without invalidating the mapping
+ * of an older, still-in-use LDT.
+ *
+ * slot will be -1 if this LDT doesn't have an alias mapping.
+ */
+ int slot;
};
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+ BUG();
+#endif
+}
+
/*
* Used for LDT copy/destruction.
*/
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+ mm->context.ldt = NULL;
+ init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
#else /* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
- struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+ struct mm_struct *mm)
{
return 0;
}
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
#endif
static inline void load_mm_ldt(struct mm_struct *mm)
@@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
* that we can see.
*/
- if (unlikely(ldt))
- set_ldt(ldt->entries, ldt->nr_entries);
- else
+ if (unlikely(ldt)) {
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+ /*
+ * Whoops -- either the new LDT isn't mapped
+ * (if slot == -1) or is mapped into a bogus
+ * slot (if slot > 1).
+ */
+ clear_LDT();
+ return;
+ }
+
+ /*
+ * If page table isolation is enabled, ldt->entries
+ * will not be mapped in the userspace pagetables.
+ * Tell the CPU to access the LDT through the alias
+ * at ldt_slot_va(ldt->slot).
+ */
+ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+ } else {
+ set_ldt(ldt->entries, ldt->nr_entries);
+ }
+ } else {
clear_LDT();
+ }
#else
clear_LDT();
#endif
@@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
+ mutex_init(&mm->context.lock);
+
mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
atomic64_set(&mm->context.tlb_gen, 0);
- #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
/* pkey 0 is the default and always allocated */
mm->context.pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->context.execute_only_pkey = -1;
}
- #endif
- return init_new_context_ldt(tsk, mm);
+#endif
+ init_new_context_ldt(mm);
+ return 0;
}
static inline void destroy_context(struct mm_struct *mm)
{
@@ -176,15 +231,16 @@ do { \
} while (0)
#endif
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
paravirt_arch_dup_mmap(oldmm, mm);
+ return ldt_dup_context(oldmm, mm);
}
static inline void arch_exit_mmap(struct mm_struct *mm)
{
paravirt_arch_exit_mmap(mm);
+ ldt_arch_exit_mmap(mm);
}
#ifdef CONFIG_X86_64
@@ -282,33 +338,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
}
/*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits. This serves two purposes. It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero. It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
- if (static_cpu_has(X86_FEATURE_PCID)) {
- VM_WARN_ON_ONCE(asid > 4094);
- return __sme_pa(mm->pgd) | (asid + 1);
- } else {
- VM_WARN_ON_ONCE(asid != 0);
- return __sme_pa(mm->pgd);
- }
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
- VM_WARN_ON_ONCE(asid > 4094);
- return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
-/*
* This can be used from process context to figure out what the value of
* CR3 is without needing to do a (slow) __read_cr3().
*
@@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
*/
static inline unsigned long __get_current_cr3_fast(void)
{
- unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+ unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
this_cpu_read(cpu_tlbstate.loaded_mm_asid));
/* For now, be very restrictive about when this can be called. */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 283efcaac8af..892df375b615 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -927,6 +927,15 @@ extern void default_banner(void);
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
CLBR_NONE, \
jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers) \
+ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
+ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
+ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
#endif /* CONFIG_X86_32 */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
*/
extern gfp_t __userpte_alloc_gfp;
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs. Being order-1, it is
+ * both 8k in size and 8k-aligned. That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
/*
* Allocate and free page tables.
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 95e2dfd75521..e42b8943cb1a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
void ptdump_walk_pgd_level_checkwx(void);
#ifdef CONFIG_DEBUG_WX
@@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
static inline int p4d_bad(p4d_t p4d)
{
- return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+ unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (p4d_flags(p4d) & ~ignore_flags) != 0;
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
@@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
static inline int pgd_bad(pgd_t pgd)
{
- return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+ unsigned long ignore_flags = _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}
static inline int pgd_none(pgd_t pgd)
@@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
@@ -1106,7 +1121,14 @@ static inline int pud_write(pud_t pud)
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+ /* Clone the user space pgd as well */
+ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+ count * sizeof(pgd_t));
+#endif
}
#define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index f2ca9b28fd68..ce245b0cdfca 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
#define LAST_PKMAP 1024
#endif
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
- & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE \
+ ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE \
+ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE)
#else
-# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
#endif
#define MODULES_VADDR VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..81462e9a34f6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
#endif
}
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
+ * the user one is in the last 4k. To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr |= BIT(bit);
+ return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr &= ~BIT(bit);
+ return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+ return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+ return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+ return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+ return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return pgd;
+ return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif
+
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+ p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
*p4dp = p4d;
+#endif
}
static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ *pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
*pgdp = pgd;
+#endif
}
static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6d5f45dcd4a1..b97a539bcdee 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -76,32 +76,45 @@ typedef struct { pteval_t pte; } pte_t;
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
#ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE _AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB _AC(12800, UL)
+# define __VMALLOC_BASE _AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY _AC(-112, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#else
-#define VMALLOC_SIZE_TB _AC(32, UL)
-#define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB _AC(32, UL)
+# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY _AC(-4, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif
+
#ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START vmalloc_base
-#define VMEMMAP_START vmemmap_base
+# define VMALLOC_START vmalloc_base
+# define VMEMMAP_START vmemmap_base
#else
-#define VMALLOC_START __VMALLOC_BASE
-#define VMEMMAP_START __VMEMMAP_BASE
+# define VMALLOC_START __VMALLOC_BASE
+# define VMEMMAP_START __VMEMMAP_BASE
#endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
/* The module sections ends with the start of the fixmap */
-#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END (-68 * (_AC(1, UL) << 30))
+#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1)
+#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD _AC(-3, UL)
+#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END (-68 * (_AC(1, UL) << 30))
#define EARLY_DYNAMIC_PAGE_TABLES 64
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..6a60fea90b9d 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull)
#define CR3_PCID_MASK 0xFFFull
#define CR3_NOFLUSH BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_SWITCH_BIT 11
+#endif
+
#else
/*
* CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cc16fa882e3e..d3a67fba200a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -163,9 +163,9 @@ enum cpuid_regs_idx {
extern struct cpuinfo_x86 boot_cpu_data;
extern struct cpuinfo_x86 new_cpu_data;
-extern struct tss_struct doublefault_tss;
-extern __u32 cpu_caps_cleared[NCAPINTS];
-extern __u32 cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss doublefault_tss;
+extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS];
#ifdef CONFIG_SMP
DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
write_cr3(__sme_pa(pgdir));
}
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
#ifdef CONFIG_X86_32
/* This is the TSS defined by the hardware. */
struct x86_hw_tss {
@@ -305,7 +310,13 @@ struct x86_hw_tss {
struct x86_hw_tss {
u32 reserved1;
u64 sp0;
+
+ /*
+ * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+ * Linux does not use ring 1, so sp1 is not otherwise needed.
+ */
u64 sp1;
+
u64 sp2;
u64 reserved2;
u64 ist[7];
@@ -323,12 +334,22 @@ struct x86_hw_tss {
#define IO_BITMAP_BITS 65536
#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
#define INVALID_IO_BITMAP_OFFSET 0x8000
+struct entry_stack {
+ unsigned long words[64];
+};
+
+struct entry_stack_page {
+ struct entry_stack stack;
+} __aligned(PAGE_SIZE);
+
struct tss_struct {
/*
- * The hardware state:
+ * The fixed hardware portion. This must not cross a page boundary
+ * at risk of violating the SDM's advice and potentially triggering
+ * errata.
*/
struct x86_hw_tss x86_tss;
@@ -339,18 +360,9 @@ struct tss_struct {
* be within the limit.
*/
unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
-#ifdef CONFIG_X86_32
- /*
- * Space for the temporary SYSENTER stack.
- */
- unsigned long SYSENTER_stack_canary;
- unsigned long SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
/*
* sizeof(unsigned long) coming from an extra "long" at the end
@@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
#ifdef CONFIG_X86_32
DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
#endif
/*
@@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask)
static inline void
native_load_sp0(unsigned long sp0)
{
- this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+ this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
static inline void native_swapgs(void)
@@ -535,12 +550,12 @@ static inline void native_swapgs(void)
static inline unsigned long current_top_of_stack(void)
{
-#ifdef CONFIG_X86_64
- return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
- /* sp0 on x86_32 is special in and around vm86 mode. */
+ /*
+ * We can't read directly from tss.sp0: sp0 on x86_32 is special in
+ * and around vm86 mode and sp0 on x86_64 is special because of the
+ * entry trampoline.
+ */
return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
}
static inline bool on_thread_stack(void)
@@ -837,13 +852,22 @@ static inline void spin_lock_prefetch(const void *x)
#else
/*
- * User space process size. 47bits minus one guard page. The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously. We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size. This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen. This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
*/
#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index b20f9d623f9c..8f09012b92e7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -236,11 +236,23 @@
*/
#define EARLY_IDT_HANDLER_SIZE 9
+/*
+ * xen_early_idt_handler_array is for Xen pv guests: for each entry in
+ * early_idt_handler_array it contains a prequel in the form of
+ * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
+ * max 8 bytes.
+ */
+#define XEN_EARLY_IDT_HANDLER_SIZE 8
+
#ifndef __ASSEMBLY__
extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
extern void early_ignore_irq(void);
+#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
+#endif
+
/*
* Load a segment. Fall back on loading the zero segment if something goes
* wrong. This variant assumes that loading zero fully clears the segment.
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 8da111b3c342..f73706878772 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -16,6 +16,7 @@ enum stack_type {
STACK_TYPE_TASK,
STACK_TYPE_IRQ,
STACK_TYPE_SOFTIRQ,
+ STACK_TYPE_ENTRY,
STACK_TYPE_EXCEPTION,
STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
};
@@ -28,6 +29,8 @@ struct stack_info {
bool in_task_stack(unsigned long *stack, struct task_struct *task,
struct stack_info *info);
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
+
int get_stack_info(unsigned long *stack, struct task_struct *task,
struct stack_info *info, unsigned long *visit_mask);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 982c325dad33..8be6afb58471 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -12,7 +12,13 @@
/* image of the saved processor state */
struct saved_context {
- u16 es, fs, gs, ss;
+ /*
+ * On x86_32, all segment registers, with the possible exception of
+ * gs, are saved at kernel entry in pt_regs.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+ u16 gs;
+#endif
unsigned long cr0, cr2, cr3, cr4;
u64 misc_enable;
bool misc_enable_saved;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7306e911faee..a7af9f53c0cb 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -20,8 +20,20 @@
*/
struct saved_context {
struct pt_regs regs;
- u16 ds, es, fs, gs, ss;
- unsigned long gs_base, gs_kernel_base, fs_base;
+
+ /*
+ * User CS and SS are saved in current_pt_regs(). The rest of the
+ * segment selectors need to be saved and restored here.
+ */
+ u16 ds, es, fs, gs;
+
+ /*
+ * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+ * so we save them separately. We save the kernelmode GSBASE to
+ * restore percpu access after resume.
+ */
+ unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
unsigned long cr0, cr2, cr3, cr4, cr8;
u64 misc_enable;
bool misc_enable_saved;
@@ -30,8 +42,7 @@ struct saved_context {
u16 gdt_pad; /* Unused */
struct desc_ptr gdt_desc;
u16 idt_pad;
- u16 idt_limit;
- unsigned long idt_base;
+ struct desc_ptr idt;
u16 ldt;
u16 tss;
unsigned long tr;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8c6bd6863db9..eb5f7999a893 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);
/* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *prev,
- struct task_struct *next)
+static inline void prepare_switch_to(struct task_struct *next)
{
#ifdef CONFIG_VMAP_STACK
/*
@@ -70,7 +69,7 @@ struct fork_frame {
#define switch_to(prev, next, last) \
do { \
- prepare_switch_to(prev, next); \
+ prepare_switch_to(next); \
\
((last) = __switch_to_asm((prev), (next))); \
} while (0)
@@ -79,10 +78,10 @@ do { \
static inline void refresh_sysenter_cs(struct thread_struct *thread)
{
/* Only happens when SEP is enabled, no need to test "SEP"arately: */
- if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+ if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
return;
- this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+ this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
}
#endif
@@ -90,10 +89,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
/* This is used when switching tasks or entering/exiting vm86 mode. */
static inline void update_sp0(struct task_struct *task)
{
+ /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
#ifdef CONFIG_X86_32
load_sp0(task->thread.sp0);
#else
- load_sp0(task_top_of_stack(task));
+ if (static_cpu_has(X86_FEATURE_XENPV))
+ load_sp0(task_top_of_stack(task));
#endif
}
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 70f425947dc5..00223333821a 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack,
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
#endif
#endif
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 509046cfa5ce..4a08dd2ab32a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,130 @@
#include <asm/cpufeature.h>
#include <asm/special_insns.h>
#include <asm/smp.h>
+#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
- unsigned long type)
-{
- struct { u64 d[2]; } desc = { { pcid, addr } };
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID - [0, TLB_NR_DYN_ASIDS-1]
+ * the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * the value we write into the PCID part of CR3; corresponds to the
+ * ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * for KPTI each mm has two address spaces and thus needs two
+ * PCID values, but we can still do with a single ASID denomination
+ * for each mm. Corresponds to kPCID + 2048.
+ *
+ */
- /*
- * The memory clobber is because the whole point is to invalidate
- * stale TLB entries and, especially if we're flushing global
- * mappings, we don't want the compiler to reorder any subsequent
- * memory accesses before the TLB flush.
- *
- * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
- * invpcid (%rcx), %rax in long mode.
- */
- asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
- : : "m" (desc), "a" (type), "c" (&desc) : "memory");
-}
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS 12
-#define INVPCID_TYPE_INDIV_ADDR 0
-#define INVPCID_TYPE_SINGLE_CTXT 1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
-#define INVPCID_TYPE_ALL_NON_GLOBAL 3
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS 1
+#else
+# define PTI_CONSUMED_PCID_BITS 0
+#endif
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
- unsigned long addr)
-{
- __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account
+ * for them being zero-based. Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS 6
+
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
{
- __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+ VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ /*
+ * Make sure that the dynamic ASID space does not confict with the
+ * bit we are using to switch between user and kernel ASIDs.
+ */
+ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT));
+
+ /*
+ * The ASID being passed in here should have respected the
+ * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+ */
+ VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT));
+#endif
+ /*
+ * The dynamically-assigned ASIDs that get passed in are small
+ * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set,
+ * so do not bother to clear it.
+ *
+ * If PCID is on, ASID-aware code paths put the ASID+1 into the
+ * PCID bits. This serves two purposes. It prevents a nasty
+ * situation in which PCID-unaware code saves CR3, loads some other
+ * value (with PCID == 0), and then restores CR3, thus corrupting
+ * the TLB for ASID 0 if the saved ASID was nonzero. It also means
+ * that any bugs involving loading a PCID-enabled CR3 with
+ * CR4.PCIDE off will trigger deterministically.
+ */
+ return asid + 1;
}
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
{
- __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+ u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ ret |= 1 << X86_CR3_PTI_SWITCH_BIT;
+#endif
+ return ret;
}
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
- __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+ if (static_cpu_has(X86_FEATURE_PCID)) {
+ return __sme_pa(pgd) | kern_pcid(asid);
+ } else {
+ VM_WARN_ON_ONCE(asid != 0);
+ return __sme_pa(pgd);
+ }
}
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
{
- u64 new_tlb_gen;
-
- /*
- * Bump the generation count. This also serves as a full barrier
- * that synchronizes with switch_mm(): callers are required to order
- * their read of mm_cpumask after their writes to the paging
- * structures.
- */
- smp_mb__before_atomic();
- new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
- smp_mb__after_atomic();
-
- return new_tlb_gen;
+ VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+ VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+ return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
}
#ifdef CONFIG_PARAVIRT
@@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
return !static_cpu_has(X86_FEATURE_PCID);
}
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -139,6 +193,24 @@ struct tlb_state {
bool is_lazy;
/*
+ * If set we changed the page tables in such a way that we
+ * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+ * This tells us to go invalidate all the non-loaded ctxs[]
+ * on the next context switch.
+ *
+ * The current ctx was kept up-to-date as it ran and does not
+ * need to be invalidated.
+ */
+ bool invalidate_other;
+
+ /*
+ * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+ * the corresponding user PCID needs a flush next time we
+ * switch to it; see SWITCH_TO_USER_CR3.
+ */
+ unsigned short user_pcid_flush_mask;
+
+ /*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
*/
@@ -173,40 +245,43 @@ static inline void cr4_init_shadow(void)
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
+static inline void __cr4_set(unsigned long cr4)
+{
+ lockdep_assert_irqs_disabled();
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+}
+
/* Set in this cpu's CR4. */
static inline void cr4_set_bits(unsigned long mask)
{
- unsigned long cr4;
+ unsigned long cr4, flags;
+ local_irq_save(flags);
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 | mask) != cr4) {
- cr4 |= mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
- }
+ if ((cr4 | mask) != cr4)
+ __cr4_set(cr4 | mask);
+ local_irq_restore(flags);
}
/* Clear in this cpu's CR4. */
static inline void cr4_clear_bits(unsigned long mask)
{
- unsigned long cr4;
+ unsigned long cr4, flags;
+ local_irq_save(flags);
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 & ~mask) != cr4) {
- cr4 &= ~mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
- }
+ if ((cr4 & ~mask) != cr4)
+ __cr4_set(cr4 & ~mask);
+ local_irq_restore(flags);
}
-static inline void cr4_toggle_bits(unsigned long mask)
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- cr4 ^= mask;
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
+ __cr4_set(cr4 ^ mask);
}
/* Read the CR4 shadow. */
@@ -216,6 +291,14 @@ static inline unsigned long cr4_read_shadow(void)
}
/*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+ this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
+/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
* up after us can get the correct flags. This should only be used
@@ -234,37 +317,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
extern void initialize_tlbstate_and_flush(void);
-static inline void __native_flush_tlb(void)
+/*
+ * Given an ASID, flush the corresponding user ASID. We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
{
+ /* There is no user ASID if address space separation is off */
+ if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ return;
+
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ * We only have a single ASID if PCID is off and the CR3
+ * write will have flushed it.
*/
- preempt_disable();
- native_write_cr3(__native_read_cr3());
- preempt_enable();
+ if (!cpu_feature_enabled(X86_FEATURE_PCID))
+ return;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ __set_bit(kern_pcid(asid),
+ (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
}
-static inline void __native_flush_tlb_global_irq_disabled(void)
+/*
+ * flush the entire current user mapping
+ */
+static inline void __native_flush_tlb(void)
{
- unsigned long cr4;
+ /*
+ * Preemption or interrupts must be disabled to protect the access
+ * to the per CPU variable and to prevent being preempted between
+ * read_cr3() and write_cr3().
+ */
+ WARN_ON_ONCE(preemptible());
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- /* clear PGE */
- native_write_cr4(cr4 & ~X86_CR4_PGE);
- /* write old PGE again and flush TLBs */
- native_write_cr4(cr4);
+ invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+ /* If current->mm == NULL then the read_cr3() "borrows" an mm */
+ native_write_cr3(__native_read_cr3());
}
+/*
+ * flush everything
+ */
static inline void __native_flush_tlb_global(void)
{
- unsigned long flags;
+ unsigned long cr4, flags;
if (static_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -277,36 +386,69 @@ static inline void __native_flush_tlb_global(void)
*/
raw_local_irq_save(flags);
- __native_flush_tlb_global_irq_disabled();
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ /* toggle PGE */
+ native_write_cr4(cr4 ^ X86_CR4_PGE);
+ /* write old PGE again and flush TLBs */
+ native_write_cr4(cr4);
raw_local_irq_restore(flags);
}
+/*
+ * flush one page in the user mapping
+ */
static inline void __native_flush_tlb_single(unsigned long addr)
{
+ u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+ * Just use invalidate_user_asid() in case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+ invalidate_user_asid(loaded_mm_asid);
+ else
+ invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}
+/*
+ * flush everything
+ */
static inline void __flush_tlb_all(void)
{
- if (boot_cpu_has(X86_FEATURE_PGE))
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
__flush_tlb_global();
- else
+ } else {
+ /*
+ * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+ */
__flush_tlb();
-
- /*
- * Note: if we somehow had PCID but not PGE, then this wouldn't work --
- * we'd end up flushing kernel translations for the current ASID but
- * we might fail to flush kernel translations for other cached ASIDs.
- *
- * To avoid this issue, we force PCID off if PGE is off.
- */
+ }
}
+/*
+ * flush one page in the kernel mapping
+ */
static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+ * but since kernel space is replicated across all, we must also
+ * invalidate all others.
+ */
+ invalidate_other_asid();
}
#define TLB_FLUSH_ALL -1UL
@@ -367,6 +509,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info);
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+ /*
+ * Bump the generation count. This also serves as a full barrier
+ * that synchronizes with switch_mm(): callers are required to order
+ * their read of mm_cpumask after their writes to the paging
+ * structures.
+ */
+ return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm)
{
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 84b9ec0c1bc0..22647a642e98 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -283,34 +283,34 @@ TRACE_EVENT(vector_alloc_managed,
DECLARE_EVENT_CLASS(vector_activate,
TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve,
- bool early),
+ bool reserve),
- TP_ARGS(irq, is_managed, can_reserve, early),
+ TP_ARGS(irq, is_managed, can_reserve, reserve),
TP_STRUCT__entry(
__field( unsigned int, irq )
__field( bool, is_managed )
__field( bool, can_reserve )
- __field( bool, early )
+ __field( bool, reserve )
),
TP_fast_assign(
__entry->irq = irq;
__entry->is_managed = is_managed;
__entry->can_reserve = can_reserve;
- __entry->early = early;
+ __entry->reserve = reserve;
),
- TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d",
+ TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d",
__entry->irq, __entry->is_managed, __entry->can_reserve,
- __entry->early)
+ __entry->reserve)
);
#define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name) \
DEFINE_EVENT_FN(vector_activate, name, \
TP_PROTO(unsigned int irq, bool is_managed, \
- bool can_reserve, bool early), \
- TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL); \
+ bool can_reserve, bool reserve), \
+ TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL); \
DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate);
DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate);
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1fadd310ff68..31051f35cbb7 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
dotraplinkage void do_stack_segment(struct pt_regs *, long);
#ifdef CONFIG_X86_64
dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
#endif
dotraplinkage void do_general_protection(struct pt_regs *, long);
dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index e9cc6fe1fc6f..c1688c2d0a12 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -7,6 +7,9 @@
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
struct unwind_state {
struct stack_info stack_info;
unsigned long stack_mask;
@@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
}
#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+/*
+ * WARNING: The entire pt_regs may not be safe to dereference. In some cases,
+ * only the iret frame registers are accessible. Use with caution!
+ */
static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
{
if (unwind_done(state))
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@
#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
/*
* Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index da1489cb64dc..1e901e421f2d 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generated-y += unistd_32.h
generated-y += unistd_64.h
generated-y += unistd_x32.h
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 7e1e730396ae..bcba3c643e63 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT)
#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */
#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS 12
+#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
/*
* Intel CPU features in CR4