/* only preserve the access flags and write permission */
pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
- /*
- * PTE_RDONLY is cleared by default in the asm below, so set it in
- * back if necessary (read-only or clean PTE).
- */
+ /* set PTE_RDONLY if actual read-only or clean PTE */
if (!pte_write(entry) || !pte_sw_dirty(entry))
pte_val(entry) |= PTE_RDONLY;
/*
* Setting the flags must be done atomically to avoid racing with the
- * hardware update of the access/dirty state.
+ * hardware update of the access/dirty state. The PTE_RDONLY bit must
+ * be set to the most permissive (lowest value) of *ptep and entry
+ * (calculated as: a & b == ~(~a | ~b)).
*/
+ pte_val(entry) ^= PTE_RDONLY;
asm volatile("// ptep_set_access_flags\n"
" prfm pstl1strm, %2\n"
"1: ldxr %0, %2\n"
- " and %0, %0, %3 // clear PTE_RDONLY\n"
+ " eor %0, %0, %3 // negate PTE_RDONLY in *ptep\n"
" orr %0, %0, %4 // set flags\n"
+ " eor %0, %0, %3 // negate final PTE_RDONLY\n"
" stxr %w1, %0, %2\n"
" cbnz %w1, 1b\n"
: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
- : "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+ : "L" (PTE_RDONLY), "r" (pte_val(entry)));
flush_tlb_fix_spurious_fault(vma, address);
return 1;
}
#endif
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
/*
* The kernel tried to access some page that wasn't present.
*/
{
/*
* Are we prepared to handle this kernel fault?
+ * We are almost certainly not prepared to handle instruction faults.
*/
- if (fixup_exception(regs))
+ if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
/*
#define VM_FAULT_BADMAP 0x010000
#define VM_FAULT_BADACCESS 0x020000
-#define ESR_LNX_EXEC (1 << 24)
-
static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
unsigned int mm_flags, unsigned long vm_flags,
struct task_struct *tsk)
return fault;
}
+static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs)
+{
+ unsigned int ec = ESR_ELx_EC(esr);
+ unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
+
+ if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+ return false;
+
+ if (system_uses_ttbr0_pan())
+ return fsc_type == ESR_ELx_FSC_FAULT &&
+ (regs->pstate & PSR_PAN_BIT);
+ else
+ return fsc_type == ESR_ELx_FSC_PERM;
+}
+
+static bool is_el0_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
+}
+
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
if (user_mode(regs))
mm_flags |= FAULT_FLAG_USER;
- if (esr & ESR_LNX_EXEC) {
+ if (is_el0_instruction_abort(esr)) {
vm_flags = VM_EXEC;
} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
vm_flags = VM_WRITE;
mm_flags |= FAULT_FLAG_WRITE;
}
- /*
- * PAN bit set implies the fault happened in kernel space, but not
- * in the arch's user access functions.
- */
- if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT))
- goto no_context;
+ if (addr < USER_DS && is_permission_fault(esr, regs)) {
+ /* regs->orig_addr_limit may be 0 if we entered from EL0 */
+ if (regs->orig_addr_limit == KERNEL_DS)
+ die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
+
+ if (is_el1_instruction_abort(esr))
+ die("Attempting to execute userspace memory", regs, esr);
+
+ if (!search_exception_tables(regs->pc))
+ die("Accessing user space memory outside uaccess.h routines", regs, esr);
+ }
/*
* As per x86, we may deadlock here. However, since the kernel only
return 1;
}
-static struct fault_info {
+static const struct fault_info {
int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
int sig;
int code;
debug_fault_info[nr].name = name;
}
-asmlinkage int __exception do_debug_exception(unsigned long addr,
+asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
unsigned int esr,
struct pt_regs *regs)
{
const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
+ unsigned long pc = instruction_pointer(regs);
struct siginfo info;
+ int rv;
- if (!inf->fn(addr, esr, regs))
- return 1;
+ /*
+ * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
+ * already disabled to preserve the last enabled/disabled addresses.
+ */
+ if (interrupts_enabled(regs))
+ trace_hardirqs_off();
- pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
- inf->name, esr, addr);
+ if (!inf->fn(addr_if_watchpoint, esr, regs)) {
+ rv = 1;
+ } else {
+ pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
+ inf->name, esr, pc);
+
+ info.si_signo = inf->sig;
+ info.si_errno = 0;
+ info.si_code = inf->code;
+ info.si_addr = (void __user *)pc;
+ arm64_notify_die("", regs, &info, 0);
+ rv = 0;
+ }
- info.si_signo = inf->sig;
- info.si_errno = 0;
- info.si_code = inf->code;
- info.si_addr = (void __user *)addr;
- arm64_notify_die("", regs, &info, 0);
+ if (interrupts_enabled(regs))
+ trace_hardirqs_on();
- return 0;
+ return rv;
}
#ifdef CONFIG_ARM64_PAN
return 0;
}
#endif /* CONFIG_ARM64_PAN */
+
+#ifdef CONFIG_ARM64_UAO
+/*
+ * Kernel threads have fs=KERNEL_DS by default, and don't need to call
+ * set_fs(), devtmpfs in particular relies on this behaviour.
+ * We need to enable the feature at runtime (instead of adding it to
+ * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
+ */
+int cpu_enable_uao(void *__unused)
+{
+ asm(SET_PSTATE_UAO(1));
+ return 0;
+}
+#endif /* CONFIG_ARM64_UAO */