summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/processor.h
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm/processor.h')
-rw-r--r--arch/x86/include/asm/processor.h85
1 files changed, 45 insertions, 40 deletions
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 028245e1c42b..cc16fa882e3e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PROCESSOR_H
#define _ASM_X86_PROCESSOR_H
@@ -22,6 +23,7 @@ struct vm86;
#include <asm/nops.h>
#include <asm/special_insns.h>
#include <asm/fpu/types.h>
+#include <asm/unwind_hints.h>
#include <linux/personality.h>
#include <linux/cache.h>
@@ -29,6 +31,7 @@ struct vm86;
#include <linux/math64.h>
#include <linux/err.h>
#include <linux/irqflags.h>
+#include <linux/mem_encrypt.h>
/*
* We handle most unaligned accesses in hardware. On the other hand
@@ -129,6 +132,7 @@ struct cpuinfo_x86 {
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
+ unsigned initialized : 1;
} __randomize_layout;
struct cpuid_regs {
@@ -239,9 +243,14 @@ static inline unsigned long read_cr3_pa(void)
return __read_cr3() & CR3_ADDR_MASK;
}
+static inline unsigned long native_read_cr3_pa(void)
+{
+ return __native_read_cr3() & CR3_ADDR_MASK;
+}
+
static inline void load_cr3(pgd_t *pgdir)
{
- write_cr3(__pa(pgdir));
+ write_cr3(__sme_pa(pgdir));
}
#ifdef CONFIG_X86_32
@@ -423,7 +432,9 @@ typedef struct {
struct thread_struct {
/* Cached TLS descriptors: */
struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
+#ifdef CONFIG_X86_32
unsigned long sp0;
+#endif
unsigned long sp;
#ifdef CONFIG_X86_32
unsigned long sysenter_cs;
@@ -510,16 +521,9 @@ static inline void native_set_iopl_mask(unsigned mask)
}
static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+native_load_sp0(unsigned long sp0)
{
- tss->x86_tss.sp0 = thread->sp0;
-#ifdef CONFIG_X86_32
- /* Only happens when SEP is enabled, no need to test "SEP"arately: */
- if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
- tss->x86_tss.ss1 = thread->sysenter_cs;
- wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
- }
-#endif
+ this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
}
static inline void native_swapgs(void)
@@ -539,15 +543,20 @@ static inline unsigned long current_top_of_stack(void)
#endif
}
+static inline bool on_thread_stack(void)
+{
+ return (unsigned long)(current_top_of_stack() -
+ current_stack_pointer) < THREAD_SIZE;
+}
+
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
-static inline void load_sp0(struct tss_struct *tss,
- struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
{
- native_load_sp0(tss, thread);
+ native_load_sp0(sp0);
}
#define set_iopl_mask native_set_iopl_mask
@@ -661,7 +670,7 @@ static inline void sync_core(void)
* In case NMI unmasking or performance ever becomes a problem,
* the next best option appears to be MOV-to-CR2 and an
* unconditional jump. That sequence also works on all CPUs,
- * but it will fault at CPL3 (i.e. Xen PV and lguest).
+ * but it will fault at CPL3 (i.e. Xen PV).
*
* CPUID is the conventional way, but it's nasty: it doesn't
* exist on some 486-like CPUs, and it usually exits to a
@@ -670,8 +679,6 @@ static inline void sync_core(void)
* Like all of Linux's memory ordering operations, this is a
* compiler barrier as well.
*/
- register void *__sp asm(_ASM_SP);
-
#ifdef CONFIG_X86_32
asm volatile (
"pushfl\n\t"
@@ -679,11 +686,12 @@ static inline void sync_core(void)
"pushl $1f\n\t"
"iret\n\t"
"1:"
- : "+r" (__sp) : : "memory");
+ : ASM_CALL_CONSTRAINT : : "memory");
#else
unsigned int tmp;
asm volatile (
+ UNWIND_HINT_SAVE
"mov %%ss, %0\n\t"
"pushq %q0\n\t"
"pushq %%rsp\n\t"
@@ -693,8 +701,9 @@ static inline void sync_core(void)
"pushq %q0\n\t"
"pushq $1f\n\t"
"iretq\n\t"
+ UNWIND_HINT_RESTORE
"1:"
- : "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
+ : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
#endif
}
@@ -796,13 +805,24 @@ static inline void spin_lock_prefetch(const void *x)
#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
TOP_OF_KERNEL_STACK_PADDING)
+#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
+
+#define task_pt_regs(task) \
+({ \
+ unsigned long __ptr = (unsigned long)task_stack_page(task); \
+ __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \
+ ((struct pt_regs *)__ptr) - 1; \
+})
+
#ifdef CONFIG_X86_32
/*
* User space process size: 3GB (default).
*/
#define IA32_PAGE_OFFSET PAGE_OFFSET
#define TASK_SIZE PAGE_OFFSET
+#define TASK_SIZE_LOW TASK_SIZE
#define TASK_SIZE_MAX TASK_SIZE
+#define DEFAULT_MAP_WINDOW TASK_SIZE
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
@@ -813,23 +833,6 @@ static inline void spin_lock_prefetch(const void *x)
.addr_limit = KERNEL_DS, \
}
-/*
- * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
- * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessible even if the CPU haven't stored the SS/ESP registers
- * on the stack (interrupt gate does not save these registers
- * when switching to the same priv ring).
- * Therefore beware: accessing the ss/esp fields of the
- * "struct pt_regs" is possible, but they may contain the
- * completely wrong values.
- */
-#define task_pt_regs(task) \
-({ \
- unsigned long __ptr = (unsigned long)task_stack_page(task); \
- __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \
- ((struct pt_regs *)__ptr) - 1; \
-})
-
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
@@ -842,7 +845,9 @@ static inline void spin_lock_prefetch(const void *x)
* particular problem by preventing anything from being mapped
* at the maximum canonical address.
*/
-#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
+
+#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE)
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
@@ -850,20 +855,20 @@ static inline void spin_lock_prefetch(const void *x)
#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \
0xc0000000 : 0xFFFFe000)
+#define TASK_SIZE_LOW (test_thread_flag(TIF_ADDR32) ? \
+ IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define STACK_TOP TASK_SIZE
+#define STACK_TOP TASK_SIZE_LOW
#define STACK_TOP_MAX TASK_SIZE_MAX
#define INIT_THREAD { \
- .sp0 = TOP_OF_INIT_STACK, \
.addr_limit = KERNEL_DS, \
}
-#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
#endif /* CONFIG_X86_64 */
@@ -876,7 +881,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
* space during mmap's.
*/
#define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3))
-#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE)
+#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
#define KSTK_EIP(task) (task_pt_regs(task)->ip)