@@ -35,6 +35,7 @@ typedef struct {
#ifdef CONFIG_X86_64
/* True if mm supports a task running in 32 bit compatibility mode. */
unsigned short ia32_compat;
+ u8 lam;
#endif
struct mutex lock;
@@ -176,6 +176,34 @@ static u8 gen_lam(struct task_struct *tsk, struct mm_struct *mm)
if (!tsk)
return LAM_NONE;
+ if (tsk->flags & PF_KTHREAD) {
+ /*
+ * For kernel thread use the most permissive LAM
+ * used by the mm. It's required to handle kernel thread
+ * memory accesses on behalf of a process.
+ *
+ * Adjust thread flags accodringly, so untagged_addr() would
+ * work correctly.
+ */
+ switch (mm->context.lam) {
+ case LAM_NONE:
+ clear_thread_flag(TIF_LAM_U48);
+ clear_thread_flag(TIF_LAM_U57);
+ return LAM_NONE;
+ case LAM_U57:
+ clear_thread_flag(TIF_LAM_U48);
+ set_thread_flag(TIF_LAM_U57);
+ return LAM_U57;
+ case LAM_U48:
+ set_thread_flag(TIF_LAM_U48);
+ clear_thread_flag(TIF_LAM_U57);
+ return LAM_U48;
+ default:
+ WARN_ON_ONCE(1);
+ return LAM_NONE;
+ }
+ }
+
if (test_ti_thread_flag(ti, TIF_LAM_U57))
return LAM_U57;
if (test_ti_thread_flag(ti, TIF_LAM_U48))
When a kernel thread performs memory access on behalf of a process (like in async I/O, io_uring, etc.) it has to respect tagging setup of the process as user addresses can include tags. Normally, LAM setup is per-thread and recorded in thread flags, but for this use case we also track LAM setup per-mm. mm->context.lam would record LAM that allows the most tag bits among the threads of the mm. The info used by switch_mm_irqs_off() to construct CR3 if the task is kernel thread. Thread flags of the kernel thread get updated according to mm->context.lam. It allows untagged_addr() to work correctly. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> --- arch/x86/include/asm/mmu.h | 1 + arch/x86/mm/tlb.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+)