mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 10:40:53 +07:00
5f82e71a00
Pull locking updates from Ingo Molnar: - Add 'cross-release' support to lockdep, which allows APIs like completions, where it's not the 'owner' who releases the lock, to be tracked. It's all activated automatically under CONFIG_PROVE_LOCKING=y. - Clean up (restructure) the x86 atomics op implementation to be more readable, in preparation of KASAN annotations. (Dmitry Vyukov) - Fix static keys (Paolo Bonzini) - Add killable versions of down_read() et al (Kirill Tkhai) - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini) - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra) - Remove smp_mb__before_spinlock() and convert its usages, introduce smp_mb__after_spinlock() (Peter Zijlstra) * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits) locking/lockdep/selftests: Fix mixed read-write ABBA tests sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK() acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures smp: Avoid using two cache lines for struct call_single_data locking/lockdep: Untangle xhlock history save/restore from task independence locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being futex: Remove duplicated code and fix undefined behaviour Documentation/locking/atomic: Finish the document... locking/lockdep: Fix workqueue crossrelease annotation workqueue/lockdep: 'Fix' flush_work() annotation locking/lockdep/selftests: Add mixed read-write ABBA tests mm, locking/barriers: Clarify tlb_flush_pending() barriers locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive locking/lockdep: Explicitly initialize wq_barrier::done::map locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING locking/refcounts, x86/asm: Implement fast refcount overflow protection locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease ...
221 lines
6.1 KiB
C
221 lines
6.1 KiB
C
#include <linux/extable.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/sched/debug.h>
|
|
|
|
#include <asm/traps.h>
|
|
#include <asm/kdebug.h>
|
|
|
|
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
|
|
struct pt_regs *, int);
|
|
|
|
static inline unsigned long
|
|
ex_fixup_addr(const struct exception_table_entry *x)
|
|
{
|
|
return (unsigned long)&x->fixup + x->fixup;
|
|
}
|
|
static inline ex_handler_t
|
|
ex_fixup_handler(const struct exception_table_entry *x)
|
|
{
|
|
return (ex_handler_t)((unsigned long)&x->handler + x->handler);
|
|
}
|
|
|
|
bool ex_handler_default(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(ex_handler_default);
|
|
|
|
bool ex_handler_fault(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
regs->ax = trapnr;
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ex_handler_fault);
|
|
|
|
/*
|
|
* Handler for UD0 exception following a failed test against the
|
|
* result of a refcount inc/dec/add/sub.
|
|
*/
|
|
bool ex_handler_refcount(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
/* First unconditionally saturate the refcount. */
|
|
*(int *)regs->cx = INT_MIN / 2;
|
|
|
|
/*
|
|
* Strictly speaking, this reports the fixup destination, not
|
|
* the fault location, and not the actually overflowing
|
|
* instruction, which is the instruction before the "js", but
|
|
* since that instruction could be a variety of lengths, just
|
|
* report the location after the overflow, which should be close
|
|
* enough for finding the overflow, as it's at least back in
|
|
* the function, having returned from .text.unlikely.
|
|
*/
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
|
|
/*
|
|
* This function has been called because either a negative refcount
|
|
* value was seen by any of the refcount functions, or a zero
|
|
* refcount value was seen by refcount_dec().
|
|
*
|
|
* If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
|
|
* wrapped around) will be set. Additionally, seeing the refcount
|
|
* reach 0 will set ZF (Zero Flag: result was zero). In each of
|
|
* these cases we want a report, since it's a boundary condition.
|
|
*
|
|
*/
|
|
if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
|
|
bool zero = regs->flags & X86_EFLAGS_ZF;
|
|
|
|
refcount_error_report(regs, zero ? "hit zero" : "overflow");
|
|
}
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(ex_handler_refcount);
|
|
|
|
bool ex_handler_ext(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
/* Special hack for uaccess_err */
|
|
current->thread.uaccess_err = 1;
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(ex_handler_ext);
|
|
|
|
bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
|
|
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
|
|
show_stack_regs(regs);
|
|
|
|
/* Pretend that the read succeeded and returned 0. */
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
regs->ax = 0;
|
|
regs->dx = 0;
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
|
|
|
|
bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
|
|
(unsigned int)regs->cx, (unsigned int)regs->dx,
|
|
(unsigned int)regs->ax, regs->ip, (void *)regs->ip))
|
|
show_stack_regs(regs);
|
|
|
|
/* Pretend that the write succeeded. */
|
|
regs->ip = ex_fixup_addr(fixup);
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
|
|
|
|
bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
|
|
struct pt_regs *regs, int trapnr)
|
|
{
|
|
if (static_cpu_has(X86_BUG_NULL_SEG))
|
|
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
|
|
asm volatile ("mov %0, %%fs" : : "rm" (0));
|
|
return ex_handler_default(fixup, regs, trapnr);
|
|
}
|
|
EXPORT_SYMBOL(ex_handler_clear_fs);
|
|
|
|
bool ex_has_fault_handler(unsigned long ip)
|
|
{
|
|
const struct exception_table_entry *e;
|
|
ex_handler_t handler;
|
|
|
|
e = search_exception_tables(ip);
|
|
if (!e)
|
|
return false;
|
|
handler = ex_fixup_handler(e);
|
|
|
|
return handler == ex_handler_fault;
|
|
}
|
|
|
|
int fixup_exception(struct pt_regs *regs, int trapnr)
|
|
{
|
|
const struct exception_table_entry *e;
|
|
ex_handler_t handler;
|
|
|
|
#ifdef CONFIG_PNPBIOS
|
|
if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
|
|
extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
|
|
extern u32 pnp_bios_is_utter_crap;
|
|
pnp_bios_is_utter_crap = 1;
|
|
printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n");
|
|
__asm__ volatile(
|
|
"movl %0, %%esp\n\t"
|
|
"jmp *%1\n\t"
|
|
: : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip));
|
|
panic("do_trap: can't hit this");
|
|
}
|
|
#endif
|
|
|
|
e = search_exception_tables(regs->ip);
|
|
if (!e)
|
|
return 0;
|
|
|
|
handler = ex_fixup_handler(e);
|
|
return handler(e, regs, trapnr);
|
|
}
|
|
|
|
extern unsigned int early_recursion_flag;
|
|
|
|
/* Restricted version used during very early boot */
|
|
void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
|
|
{
|
|
/* Ignore early NMIs. */
|
|
if (trapnr == X86_TRAP_NMI)
|
|
return;
|
|
|
|
if (early_recursion_flag > 2)
|
|
goto halt_loop;
|
|
|
|
/*
|
|
* Old CPUs leave the high bits of CS on the stack
|
|
* undefined. I'm not sure which CPUs do this, but at least
|
|
* the 486 DX works this way.
|
|
*/
|
|
if (regs->cs != __KERNEL_CS)
|
|
goto fail;
|
|
|
|
/*
|
|
* The full exception fixup machinery is available as soon as
|
|
* the early IDT is loaded. This means that it is the
|
|
* responsibility of extable users to either function correctly
|
|
* when handlers are invoked early or to simply avoid causing
|
|
* exceptions before they're ready to handle them.
|
|
*
|
|
* This is better than filtering which handlers can be used,
|
|
* because refusing to call a handler here is guaranteed to
|
|
* result in a hard-to-debug panic.
|
|
*
|
|
* Keep in mind that not all vectors actually get here. Early
|
|
* fage faults, for example, are special.
|
|
*/
|
|
if (fixup_exception(regs, trapnr))
|
|
return;
|
|
|
|
if (fixup_bug(regs, trapnr))
|
|
return;
|
|
|
|
fail:
|
|
early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n",
|
|
(unsigned)trapnr, (unsigned long)regs->cs, regs->ip,
|
|
regs->orig_ax, read_cr2());
|
|
|
|
show_regs(regs);
|
|
|
|
halt_loop:
|
|
while (true)
|
|
halt();
|
|
}
|