arm64: Make USER_DS an inclusive limit

Currently, USER_DS represents an exclusive limit while KERNEL_DS is
inclusive. In order to do some clever trickery for speculation-safe
masking, we need them both to behave equivalently - there aren't enough
bits to make KERNEL_DS exclusive, so we have precisely one option. This
also happens to correct a longstanding false negative for a range
ending on the very top byte of kernel memory.

Mark Rutland points out that we've actually got the semantics of
addresses vs. segments muddled up in most of the places we need to
amend, so shuffle the {USER,KERNEL}_DS definitions around such that we
can correct those properly instead of just pasting "-1"s everywhere.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index cee4ae2..dfefbf3 100644 (file)
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -21,6 +21,9 @@
 
 #define TASK_SIZE_64           (UL(1) << VA_BITS)
 
+#define KERNEL_DS      UL(-1)
+#define USER_DS                (TASK_SIZE_64 - 1)
+
 #ifndef __ASSEMBLY__
 
 /*

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 59fda52..f2fc026 100644 (file)
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -35,10 +35,7 @@
 #include <asm/compiler.h>
 #include <asm/extable.h>
 
-#define KERNEL_DS      (-1UL)
 #define get_ds()       (KERNEL_DS)
-
-#define USER_DS                TASK_SIZE_64
 #define get_fs()       (current_thread_info()->addr_limit)
 
 static inline void set_fs(mm_segment_t fs)
@@ -66,22 +63,32 @@ static inline void set_fs(mm_segment_t fs)
  * Returns 1 if the range is valid, 0 otherwise.
  *
  * This is equivalent to the following test:
- * (u65)addr + (u65)size <= current->addr_limit
- *
- * This needs 65-bit arithmetic.
+ * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
  */
-#define __range_ok(addr, size)                                         \
-({                                                                     \
-       unsigned long __addr = (unsigned long)(addr);                   \
-       unsigned long flag, roksum;                                     \
-       __chk_user_ptr(addr);                                           \
-       asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"         \
-               : "=&r" (flag), "=&r" (roksum)                          \
-               : "1" (__addr), "Ir" (size),                            \
-                 "r" (current_thread_info()->addr_limit)               \
-               : "cc");                                                \
-       flag;                                                           \
-})
+static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
+{
+       unsigned long limit = current_thread_info()->addr_limit;
+
+       __chk_user_ptr(addr);
+       asm volatile(
+       // A + B <= C + 1 for all A,B,C, in four easy steps:
+       // 1: X = A + B; X' = X % 2^64
+       "       adds    %0, %0, %2\n"
+       // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
+       "       csel    %1, xzr, %1, hi\n"
+       // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
+       //    to compensate for the carry flag being set in step 4. For
+       //    X > 2^64, X' merely has to remain nonzero, which it does.
+       "       csinv   %0, %0, xzr, cc\n"
+       // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1
+       //    comes from the carry in being clear. Otherwise, we are
+       //    testing X' - C == 0, subject to the previous adjustments.
+       "       sbcs    xzr, %0, %1\n"
+       "       cset    %0, ls\n"
+       : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc");
+
+       return addr;
+}
 
 /*
  * When dealing with data aborts, watchpoints, or instruction traps we may end
@@ -90,7 +97,7 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define untagged_addr(addr)            sign_extend64(addr, 55)
 
-#define access_ok(type, addr, size)    __range_ok(addr, size)
+#define access_ok(type, addr, size)    __range_ok((unsigned long)(addr), size)
 #define user_addr_max                  get_fs
 
 #define _ASM_EXTABLE(from, to)                                         \

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 9b8635d..17c15f7 100644 (file)
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -167,10 +167,10 @@ alternative_else_nop_endif
        .else
        add     x21, sp, #S_FRAME_SIZE
        get_thread_info tsk
-       /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+       /* Save the task's original addr_limit and set USER_DS */
        ldr     x20, [tsk, #TSK_TI_ADDR_LIMIT]
        str     x20, [sp, #S_ORIG_ADDR_LIMIT]
-       mov     x20, #TASK_SIZE_64
+       mov     x20, #USER_DS
        str     x20, [tsk, #TSK_TI_ADDR_LIMIT]
        /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
        .endif /* \el == 0 */

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 0e671dd..af530eb 100644 (file)
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -240,7 +240,7 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
        if (fsc_type == ESR_ELx_FSC_PERM)
                return true;
 
-       if (addr < USER_DS && system_uses_ttbr0_pan())
+       if (addr < TASK_SIZE && system_uses_ttbr0_pan())
                return fsc_type == ESR_ELx_FSC_FAULT &&
                        (regs->pstate & PSR_PAN_BIT);
 
@@ -414,7 +414,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
                mm_flags |= FAULT_FLAG_WRITE;
        }
 
-       if (addr < USER_DS && is_permission_fault(esr, regs, addr)) {
+       if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) {
                /* 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);