diff mbox series

[v2,07/17] linux-user: Fix guest_addr_valid vs reserved_va

Message ID 20200605041733.415188-8-richard.henderson@linaro.org
State Superseded
Headers show
Series target-arm: Implement ARMv8.5-MemTag, user mode | expand

Commit Message

Richard Henderson June 5, 2020, 4:17 a.m. UTC
We must always use GUEST_ADDR_MAX, because even 32-bit hosts can
use -R <reserved_va> to restrict the memory address of the guest.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 include/exec/cpu_ldst.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

-- 
2.25.1

Comments

Peter Maydell June 25, 2020, 4:37 p.m. UTC | #1
On Fri, 5 Jun 2020 at 05:17, Richard Henderson
<richard.henderson@linaro.org> wrote:
>

> We must always use GUEST_ADDR_MAX, because even 32-bit hosts can

> use -R <reserved_va> to restrict the memory address of the guest.

>

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

> ---

>  include/exec/cpu_ldst.h | 9 ++++-----

>  1 file changed, 4 insertions(+), 5 deletions(-)


Doesn't this run into trouble with the arm32 commpage?
The reserved_va is set there to 0xffff0000 (stopping
at the commpage), but the addresses within the commpage
themselves are still valid guest addresses.

thanks
-- PMM
Richard Henderson July 11, 2020, 7:26 p.m. UTC | #2
On 6/25/20 9:37 AM, Peter Maydell wrote:
> On Fri, 5 Jun 2020 at 05:17, Richard Henderson

> <richard.henderson@linaro.org> wrote:

>>

>> We must always use GUEST_ADDR_MAX, because even 32-bit hosts can

>> use -R <reserved_va> to restrict the memory address of the guest.

>>

>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

>> ---

>>  include/exec/cpu_ldst.h | 9 ++++-----

>>  1 file changed, 4 insertions(+), 5 deletions(-)

> 

> Doesn't this run into trouble with the arm32 commpage?

> The reserved_va is set there to 0xffff0000 (stopping

> at the commpage), but the addresses within the commpage

> themselves are still valid guest addresses.


Not really.  The commpage is Special, and gets allocated differently.  Normal
binaries work, e.g. our standard busybox ls.

I would imagine the corner case that doesn't work is that you couldn't issue a
syscall to the commpage, e.g.

    write(1, 0xfffff000, 1);

because the commpage is now outside the normal address space.

But given that it only matters with an explicit -R command-line option, this
falls into the Well Don't Do That Then category. This is a generic option, and
works as expected with other 32-bit guests.


r~
diff mbox series

Patch

diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 3930362e20..066cf33f70 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -72,11 +72,10 @@  typedef uint64_t abi_ptr;
 /* All direct uses of g2h and h2g need to go away for usermode softmmu.  */
 #define g2h(x) ((void *)((unsigned long)(abi_ptr)(x) + guest_base))
 
-#if HOST_LONG_BITS <= TARGET_VIRT_ADDR_SPACE_BITS
-#define guest_addr_valid(x) (1)
-#else
-#define guest_addr_valid(x) ((x) <= GUEST_ADDR_MAX)
-#endif
+static inline bool guest_addr_valid(abi_ptr x)
+{
+    return x <= GUEST_ADDR_MAX;
+}
 
 static inline int guest_range_valid(unsigned long start, unsigned long len)
 {