RISC-V: Fix a race condition during kernel stack overflow

[linux-2.6-block.git] / arch / riscv / kernel / entry.S

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 5fdb6ba096000c4a609c1e70e0734856108660ab..186abd146eaffca06c6c3db10902c42ffa769dbc 100644 (file)
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -108,15 +108,15 @@ _save_context:
 .option pop
 
 #ifdef CONFIG_TRACE_IRQFLAGS
-       call trace_hardirqs_off
+       call __trace_hardirqs_off
 #endif
 
-#ifdef CONFIG_CONTEXT_TRACKING
-       /* If previous state is in user mode, call context_tracking_user_exit. */
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+       /* If previous state is in user mode, call user_exit_callable(). */
        li   a0, SR_PP
        and a0, s1, a0
        bnez a0, skip_context_tracking
-       call context_tracking_user_exit
+       call user_exit_callable
 skip_context_tracking:
 #endif
 
@@ -130,8 +130,7 @@ skip_context_tracking:
 
        /* Handle interrupts */
        move a0, sp /* pt_regs */
-       la a1, handle_arch_irq
-       REG_L a1, (a1)
+       la a1, generic_handle_arch_irq
        jr a1
 1:
        /*
@@ -144,7 +143,7 @@ skip_context_tracking:
        li t0, EXC_BREAKPOINT
        beq s4, t0, 1f
 #ifdef CONFIG_TRACE_IRQFLAGS
-       call trace_hardirqs_on
+       call __trace_hardirqs_on
 #endif
        csrs CSR_STATUS, SR_IE
 
@@ -177,7 +176,7 @@ handle_syscall:
         */
        csrs CSR_STATUS, SR_IE
 #endif
-#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER)
        /* Recover a0 - a7 for system calls */
        REG_L a0, PT_A0(sp)
        REG_L a1, PT_A1(sp)
@@ -208,13 +207,27 @@ check_syscall_nr:
         * Syscall number held in a7.
         * If syscall number is above allowed value, redirect to ni_syscall.
         */
-       bgeu a7, t0, 1f
+       bgeu a7, t0, 3f
+#ifdef CONFIG_COMPAT
+       REG_L s0, PT_STATUS(sp)
+       srli s0, s0, SR_UXL_SHIFT
+       andi s0, s0, (SR_UXL >> SR_UXL_SHIFT)
+       li t0, (SR_UXL_32 >> SR_UXL_SHIFT)
+       sub t0, s0, t0
+       bnez t0, 1f
+
+       /* Call compat_syscall */
+       la s0, compat_sys_call_table
+       j 2f
+1:
+#endif
        /* Call syscall */
        la s0, sys_call_table
+2:
        slli t0, a7, RISCV_LGPTR
        add s0, s0, t0
        REG_L s0, 0(s0)
-1:
+3:
        jalr s0
 
 ret_from_syscall:
@@ -226,6 +239,10 @@ ret_from_syscall:
         * (If it was configured with SECCOMP_RET_ERRNO/TRACE)
         */
 ret_from_syscall_rejected:
+#ifdef CONFIG_DEBUG_RSEQ
+       move a0, sp
+       call rseq_syscall
+#endif
        /* Trace syscalls, but only if requested by the user. */
        REG_L t0, TASK_TI_FLAGS(tp)
        andi t0, t0, _TIF_SYSCALL_WORK
@@ -235,7 +252,7 @@ ret_from_exception:
        REG_L s0, PT_STATUS(sp)
        csrc CSR_STATUS, SR_IE
 #ifdef CONFIG_TRACE_IRQFLAGS
-       call trace_hardirqs_off
+       call __trace_hardirqs_off
 #endif
 #ifdef CONFIG_RISCV_M_MODE
        /* the MPP value is too large to be used as an immediate arg for addi */
@@ -252,8 +269,8 @@ resume_userspace:
        andi s1, s0, _TIF_WORK_MASK
        bnez s1, work_pending
 
-#ifdef CONFIG_CONTEXT_TRACKING
-       call context_tracking_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+       call user_enter_callable
 #endif
 
        /* Save unwound kernel stack pointer in thread_info */
@@ -271,10 +288,10 @@ restore_all:
        REG_L s1, PT_STATUS(sp)
        andi t0, s1, SR_PIE
        beqz t0, 1f
-       call trace_hardirqs_on
+       call __trace_hardirqs_on
        j 2f
 1:
-       call trace_hardirqs_off
+       call __trace_hardirqs_off
 2:
 #endif
        REG_L a0, PT_STATUS(sp)
@@ -557,11 +574,6 @@ ENTRY(__switch_to)
        REG_L s9,  TASK_THREAD_S9_RA(a4)
        REG_L s10, TASK_THREAD_S10_RA(a4)
        REG_L s11, TASK_THREAD_S11_RA(a4)
-       /* Swap the CPU entry around. */
-       lw a3, TASK_TI_CPU(a0)
-       lw a4, TASK_TI_CPU(a1)
-       sw a3, TASK_TI_CPU(a1)
-       sw a4, TASK_TI_CPU(a0)
        /* The offset of thread_info in task_struct is zero. */
        move tp, a1
        ret