Treat cache write as a read in arm64 data faults
On arm64 we can ask the hardware to perform cache operations from userspace. These require read permission however when the memory is unmapped the kernel will receive a write exception. Add a check to see if the cause of the exception is from the cache and pass a memory read fault type to the vm subsystem. PR: 262836 Reported by: dch Sponsored by: The FreeBSD Foundation
This commit is contained in:
parent
7afec5182a
commit
029c1c4828
@ -318,8 +318,16 @@ data_abort(struct thread *td, struct trapframe *frame, uint64_t esr,
|
||||
ftype = VM_PROT_EXECUTE;
|
||||
break;
|
||||
default:
|
||||
ftype = (esr & ISS_DATA_WnR) == 0 ? VM_PROT_READ :
|
||||
VM_PROT_WRITE;
|
||||
/*
|
||||
* If the exception was because of a read or cache operation
|
||||
* pass a read fault type into the vm code. Cache operations
|
||||
* need read permission but will set the WnR flag when the
|
||||
* memory is unmapped.
|
||||
*/
|
||||
if ((esr & ISS_DATA_WnR) == 0 || (esr & ISS_DATA_CM) != 0)
|
||||
ftype = VM_PROT_READ;
|
||||
else
|
||||
ftype = VM_PROT_WRITE;
|
||||
break;
|
||||
}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user