mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 21:56:40 +07:00
fdf5563a72
Pull x86 cleanups from Ingo Molnar: "This topic tree contains more commits than usual: - most of it are uaccess cleanups/reorganization by Al - there's a bunch of prototype declaration (--Wmissing-prototypes) cleanups - misc other cleanups all around the map" * 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits) x86/mm/set_memory: Fix -Wmissing-prototypes warnings x86/efi: Add a prototype for efi_arch_mem_reserve() x86/mm: Mark setup_emu2phys_nid() static x86/jump_label: Move 'inline' keyword placement x86/platform/uv: Add a missing prototype for uv_bau_message_interrupt() kill uaccess_try() x86: unsafe_put-style macro for sigmask x86: x32_setup_rt_frame(): consolidate uaccess areas x86: __setup_rt_frame(): consolidate uaccess areas x86: __setup_frame(): consolidate uaccess areas x86: setup_sigcontext(): list user_access_{begin,end}() into callers x86: get rid of put_user_try in __setup_rt_frame() (both 32bit and 64bit) x86: ia32_setup_rt_frame(): consolidate uaccess areas x86: ia32_setup_frame(): consolidate uaccess areas x86: ia32_setup_sigcontext(): lift user_access_{begin,end}() into the callers x86/alternatives: Mark text_poke_loc_init() static x86/cpu: Fix a -Wmissing-prototypes warning for init_ia32_feat_ctl() x86/mm: Drop pud_mknotpresent() x86: Replace setup_irq() by request_irq() x86/configs: Slightly reduce defconfigs ...
434 lines
11 KiB
C
434 lines
11 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* common.c - C code for kernel entry and exit
|
|
* Copyright (c) 2015 Andrew Lutomirski
|
|
*
|
|
* Based on asm and ptrace code by many authors. The code here originated
|
|
* in ptrace.c and signal.c.
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/task_stack.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/tracehook.h>
|
|
#include <linux/audit.h>
|
|
#include <linux/seccomp.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/export.h>
|
|
#include <linux/context_tracking.h>
|
|
#include <linux/user-return-notifier.h>
|
|
#include <linux/nospec.h>
|
|
#include <linux/uprobes.h>
|
|
#include <linux/livepatch.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/desc.h>
|
|
#include <asm/traps.h>
|
|
#include <asm/vdso.h>
|
|
#include <asm/cpufeature.h>
|
|
#include <asm/fpu/api.h>
|
|
#include <asm/nospec-branch.h>
|
|
#include <asm/io_bitmap.h>
|
|
#include <asm/syscall.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/syscalls.h>
|
|
|
|
#ifdef CONFIG_CONTEXT_TRACKING
|
|
/* Called on entry from user mode with IRQs off. */
|
|
__visible inline void enter_from_user_mode(void)
|
|
{
|
|
CT_WARN_ON(ct_state() != CONTEXT_USER);
|
|
user_exit_irqoff();
|
|
}
|
|
#else
|
|
static inline void enter_from_user_mode(void) {}
|
|
#endif
|
|
|
|
static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
|
|
{
|
|
#ifdef CONFIG_X86_64
|
|
if (arch == AUDIT_ARCH_X86_64) {
|
|
audit_syscall_entry(regs->orig_ax, regs->di,
|
|
regs->si, regs->dx, regs->r10);
|
|
} else
|
|
#endif
|
|
{
|
|
audit_syscall_entry(regs->orig_ax, regs->bx,
|
|
regs->cx, regs->dx, regs->si);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Returns the syscall nr to run (which should match regs->orig_ax) or -1
|
|
* to skip the syscall.
|
|
*/
|
|
static long syscall_trace_enter(struct pt_regs *regs)
|
|
{
|
|
u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
|
|
|
|
struct thread_info *ti = current_thread_info();
|
|
unsigned long ret = 0;
|
|
u32 work;
|
|
|
|
if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
|
|
BUG_ON(regs != task_pt_regs(current));
|
|
|
|
work = READ_ONCE(ti->flags);
|
|
|
|
if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
|
|
ret = tracehook_report_syscall_entry(regs);
|
|
if (ret || (work & _TIF_SYSCALL_EMU))
|
|
return -1L;
|
|
}
|
|
|
|
#ifdef CONFIG_SECCOMP
|
|
/*
|
|
* Do seccomp after ptrace, to catch any tracer changes.
|
|
*/
|
|
if (work & _TIF_SECCOMP) {
|
|
struct seccomp_data sd;
|
|
|
|
sd.arch = arch;
|
|
sd.nr = regs->orig_ax;
|
|
sd.instruction_pointer = regs->ip;
|
|
#ifdef CONFIG_X86_64
|
|
if (arch == AUDIT_ARCH_X86_64) {
|
|
sd.args[0] = regs->di;
|
|
sd.args[1] = regs->si;
|
|
sd.args[2] = regs->dx;
|
|
sd.args[3] = regs->r10;
|
|
sd.args[4] = regs->r8;
|
|
sd.args[5] = regs->r9;
|
|
} else
|
|
#endif
|
|
{
|
|
sd.args[0] = regs->bx;
|
|
sd.args[1] = regs->cx;
|
|
sd.args[2] = regs->dx;
|
|
sd.args[3] = regs->si;
|
|
sd.args[4] = regs->di;
|
|
sd.args[5] = regs->bp;
|
|
}
|
|
|
|
ret = __secure_computing(&sd);
|
|
if (ret == -1)
|
|
return ret;
|
|
}
|
|
#endif
|
|
|
|
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
|
|
trace_sys_enter(regs, regs->orig_ax);
|
|
|
|
do_audit_syscall_entry(regs, arch);
|
|
|
|
return ret ?: regs->orig_ax;
|
|
}
|
|
|
|
#define EXIT_TO_USERMODE_LOOP_FLAGS \
|
|
(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
|
|
_TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
|
|
|
|
static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
|
|
{
|
|
/*
|
|
* In order to return to user mode, we need to have IRQs off with
|
|
* none of EXIT_TO_USERMODE_LOOP_FLAGS set. Several of these flags
|
|
* can be set at any time on preemptible kernels if we have IRQs on,
|
|
* so we need to loop. Disabling preemption wouldn't help: doing the
|
|
* work to clear some of the flags can sleep.
|
|
*/
|
|
while (true) {
|
|
/* We have work to do. */
|
|
local_irq_enable();
|
|
|
|
if (cached_flags & _TIF_NEED_RESCHED)
|
|
schedule();
|
|
|
|
if (cached_flags & _TIF_UPROBE)
|
|
uprobe_notify_resume(regs);
|
|
|
|
if (cached_flags & _TIF_PATCH_PENDING)
|
|
klp_update_patch_state(current);
|
|
|
|
/* deal with pending signal delivery */
|
|
if (cached_flags & _TIF_SIGPENDING)
|
|
do_signal(regs);
|
|
|
|
if (cached_flags & _TIF_NOTIFY_RESUME) {
|
|
clear_thread_flag(TIF_NOTIFY_RESUME);
|
|
tracehook_notify_resume(regs);
|
|
rseq_handle_notify_resume(NULL, regs);
|
|
}
|
|
|
|
if (cached_flags & _TIF_USER_RETURN_NOTIFY)
|
|
fire_user_return_notifiers();
|
|
|
|
/* Disable IRQs and retry */
|
|
local_irq_disable();
|
|
|
|
cached_flags = READ_ONCE(current_thread_info()->flags);
|
|
|
|
if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* Called with IRQs disabled. */
|
|
__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
|
|
{
|
|
struct thread_info *ti = current_thread_info();
|
|
u32 cached_flags;
|
|
|
|
addr_limit_user_check();
|
|
|
|
lockdep_assert_irqs_disabled();
|
|
lockdep_sys_exit();
|
|
|
|
cached_flags = READ_ONCE(ti->flags);
|
|
|
|
if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
|
|
exit_to_usermode_loop(regs, cached_flags);
|
|
|
|
/* Reload ti->flags; we may have rescheduled above. */
|
|
cached_flags = READ_ONCE(ti->flags);
|
|
|
|
if (unlikely(cached_flags & _TIF_IO_BITMAP))
|
|
tss_update_io_bitmap();
|
|
|
|
fpregs_assert_state_consistent();
|
|
if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
|
|
switch_fpu_return();
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
/*
|
|
* Compat syscalls set TS_COMPAT. Make sure we clear it before
|
|
* returning to user mode. We need to clear it *after* signal
|
|
* handling, because syscall restart has a fixup for compat
|
|
* syscalls. The fixup is exercised by the ptrace_syscall_32
|
|
* selftest.
|
|
*
|
|
* We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
|
|
* special case only applies after poking regs and before the
|
|
* very next return to user mode.
|
|
*/
|
|
ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
|
|
#endif
|
|
|
|
user_enter_irqoff();
|
|
|
|
mds_user_clear_cpu_buffers();
|
|
}
|
|
|
|
#define SYSCALL_EXIT_WORK_FLAGS \
|
|
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
|
|
_TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
|
|
|
|
static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
|
|
{
|
|
bool step;
|
|
|
|
audit_syscall_exit(regs);
|
|
|
|
if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
|
|
trace_sys_exit(regs, regs->ax);
|
|
|
|
/*
|
|
* If TIF_SYSCALL_EMU is set, we only get here because of
|
|
* TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
|
|
* We already reported this syscall instruction in
|
|
* syscall_trace_enter().
|
|
*/
|
|
step = unlikely(
|
|
(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
|
|
== _TIF_SINGLESTEP);
|
|
if (step || cached_flags & _TIF_SYSCALL_TRACE)
|
|
tracehook_report_syscall_exit(regs, step);
|
|
}
|
|
|
|
/*
|
|
* Called with IRQs on and fully valid regs. Returns with IRQs off in a
|
|
* state such that we can immediately switch to user mode.
|
|
*/
|
|
__visible inline void syscall_return_slowpath(struct pt_regs *regs)
|
|
{
|
|
struct thread_info *ti = current_thread_info();
|
|
u32 cached_flags = READ_ONCE(ti->flags);
|
|
|
|
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
|
|
|
|
if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
|
|
WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
|
|
local_irq_enable();
|
|
|
|
rseq_syscall(regs);
|
|
|
|
/*
|
|
* First do one-time work. If these work items are enabled, we
|
|
* want to run them exactly once per syscall exit with IRQs on.
|
|
*/
|
|
if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
|
|
syscall_slow_exit_work(regs, cached_flags);
|
|
|
|
local_irq_disable();
|
|
prepare_exit_to_usermode(regs);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_64
|
|
__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
|
|
{
|
|
struct thread_info *ti;
|
|
|
|
enter_from_user_mode();
|
|
local_irq_enable();
|
|
ti = current_thread_info();
|
|
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
|
|
nr = syscall_trace_enter(regs);
|
|
|
|
if (likely(nr < NR_syscalls)) {
|
|
nr = array_index_nospec(nr, NR_syscalls);
|
|
regs->ax = sys_call_table[nr](regs);
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
} else if (likely((nr & __X32_SYSCALL_BIT) &&
|
|
(nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) {
|
|
nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT,
|
|
X32_NR_syscalls);
|
|
regs->ax = x32_sys_call_table[nr](regs);
|
|
#endif
|
|
}
|
|
|
|
syscall_return_slowpath(regs);
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
|
|
/*
|
|
* Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does
|
|
* all entry and exit work and returns with IRQs off. This function is
|
|
* extremely hot in workloads that use it, and it's usually called from
|
|
* do_fast_syscall_32, so forcibly inline it to improve performance.
|
|
*/
|
|
static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
|
|
{
|
|
struct thread_info *ti = current_thread_info();
|
|
unsigned int nr = (unsigned int)regs->orig_ax;
|
|
|
|
#ifdef CONFIG_IA32_EMULATION
|
|
ti->status |= TS_COMPAT;
|
|
#endif
|
|
|
|
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
|
|
/*
|
|
* Subtlety here: if ptrace pokes something larger than
|
|
* 2^32-1 into orig_ax, this truncates it. This may or
|
|
* may not be necessary, but it matches the old asm
|
|
* behavior.
|
|
*/
|
|
nr = syscall_trace_enter(regs);
|
|
}
|
|
|
|
if (likely(nr < IA32_NR_syscalls)) {
|
|
nr = array_index_nospec(nr, IA32_NR_syscalls);
|
|
regs->ax = ia32_sys_call_table[nr](regs);
|
|
}
|
|
|
|
syscall_return_slowpath(regs);
|
|
}
|
|
|
|
/* Handles int $0x80 */
|
|
__visible void do_int80_syscall_32(struct pt_regs *regs)
|
|
{
|
|
enter_from_user_mode();
|
|
local_irq_enable();
|
|
do_syscall_32_irqs_on(regs);
|
|
}
|
|
|
|
/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
|
|
__visible long do_fast_syscall_32(struct pt_regs *regs)
|
|
{
|
|
/*
|
|
* Called using the internal vDSO SYSENTER/SYSCALL32 calling
|
|
* convention. Adjust regs so it looks like we entered using int80.
|
|
*/
|
|
|
|
unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
|
|
vdso_image_32.sym_int80_landing_pad;
|
|
|
|
/*
|
|
* SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
|
|
* so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
|
|
* Fix it up.
|
|
*/
|
|
regs->ip = landing_pad;
|
|
|
|
enter_from_user_mode();
|
|
|
|
local_irq_enable();
|
|
|
|
/* Fetch EBP from where the vDSO stashed it. */
|
|
if (
|
|
#ifdef CONFIG_X86_64
|
|
/*
|
|
* Micro-optimization: the pointer we're following is explicitly
|
|
* 32 bits, so it can't be out of range.
|
|
*/
|
|
__get_user(*(u32 *)®s->bp,
|
|
(u32 __user __force *)(unsigned long)(u32)regs->sp)
|
|
#else
|
|
get_user(*(u32 *)®s->bp,
|
|
(u32 __user __force *)(unsigned long)(u32)regs->sp)
|
|
#endif
|
|
) {
|
|
|
|
/* User code screwed up. */
|
|
local_irq_disable();
|
|
regs->ax = -EFAULT;
|
|
prepare_exit_to_usermode(regs);
|
|
return 0; /* Keep it simple: use IRET. */
|
|
}
|
|
|
|
/* Now this is just like a normal syscall. */
|
|
do_syscall_32_irqs_on(regs);
|
|
|
|
#ifdef CONFIG_X86_64
|
|
/*
|
|
* Opportunistic SYSRETL: if possible, try to return using SYSRETL.
|
|
* SYSRETL is available on all 64-bit CPUs, so we don't need to
|
|
* bother with SYSEXIT.
|
|
*
|
|
* Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
|
|
* because the ECX fixup above will ensure that this is essentially
|
|
* never the case.
|
|
*/
|
|
return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
|
|
regs->ip == landing_pad &&
|
|
(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
|
|
#else
|
|
/*
|
|
* Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
|
|
*
|
|
* Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
|
|
* because the ECX fixup above will ensure that this is essentially
|
|
* never the case.
|
|
*
|
|
* We don't allow syscalls at all from VM86 mode, but we still
|
|
* need to check VM, because we might be returning from sys_vm86.
|
|
*/
|
|
return static_cpu_has(X86_FEATURE_SEP) &&
|
|
regs->cs == __USER_CS && regs->ss == __USER_DS &&
|
|
regs->ip == landing_pad &&
|
|
(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
|
|
#endif
|
|
}
|
|
#endif
|
|
|
|
SYSCALL_DEFINE0(ni_syscall)
|
|
{
|
|
return -ENOSYS;
|
|
}
|