|
@@ -18,6 +18,68 @@ even though there is theoretically space in the PAE PTEs. These
|
|
|
permissions are enforced on data access only and have no effect on
|
|
|
instruction fetches.
|
|
|
|
|
|
+=========================== Syscalls ===========================
|
|
|
+
|
|
|
+There are 2 system calls which directly interact with pkeys:
|
|
|
+
|
|
|
+ int pkey_alloc(unsigned long flags, unsigned long init_access_rights)
|
|
|
+ int pkey_free(int pkey);
|
|
|
+ int pkey_mprotect(unsigned long start, size_t len,
|
|
|
+ unsigned long prot, int pkey);
|
|
|
+
|
|
|
+Before a pkey can be used, it must first be allocated with
|
|
|
+pkey_alloc(). An application calls the WRPKRU instruction
|
|
|
+directly in order to change access permissions to memory covered
|
|
|
+with a key. In this example WRPKRU is wrapped by a C function
|
|
|
+called pkey_set().
|
|
|
+
|
|
|
+ int real_prot = PROT_READ|PROT_WRITE;
|
|
|
+ pkey = pkey_alloc(0, PKEY_DENY_WRITE);
|
|
|
+ ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
|
|
|
+ ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey);
|
|
|
+ ... application runs here
|
|
|
+
|
|
|
+Now, if the application needs to update the data at 'ptr', it can
|
|
|
+gain access, do the update, then remove its write access:
|
|
|
+
|
|
|
+ pkey_set(pkey, 0); // clear PKEY_DENY_WRITE
|
|
|
+ *ptr = foo; // assign something
|
|
|
+ pkey_set(pkey, PKEY_DENY_WRITE); // set PKEY_DENY_WRITE again
|
|
|
+
|
|
|
+Now when it frees the memory, it will also free the pkey since it
|
|
|
+is no longer in use:
|
|
|
+
|
|
|
+ munmap(ptr, PAGE_SIZE);
|
|
|
+ pkey_free(pkey);
|
|
|
+
|
|
|
+=========================== Behavior ===========================
|
|
|
+
|
|
|
+The kernel attempts to make protection keys consistent with the
|
|
|
+behavior of a plain mprotect(). For instance if you do this:
|
|
|
+
|
|
|
+ mprotect(ptr, size, PROT_NONE);
|
|
|
+ something(ptr);
|
|
|
+
|
|
|
+you can expect the same effects with protection keys when doing this:
|
|
|
+
|
|
|
+ pkey = pkey_alloc(0, PKEY_DISABLE_WRITE | PKEY_DISABLE_READ);
|
|
|
+ pkey_mprotect(ptr, size, PROT_READ|PROT_WRITE, pkey);
|
|
|
+ something(ptr);
|
|
|
+
|
|
|
+That should be true whether something() is a direct access to 'ptr'
|
|
|
+like:
|
|
|
+
|
|
|
+ *ptr = foo;
|
|
|
+
|
|
|
+or when the kernel does the access on the application's behalf like
|
|
|
+with a read():
|
|
|
+
|
|
|
+ read(fd, ptr, 1);
|
|
|
+
|
|
|
+The kernel will send a SIGSEGV in both cases, but si_code will be set
|
|
|
+to SEGV_PKERR when violating protection keys versus SEGV_ACCERR when
|
|
|
+the plain mprotect() permissions are violated.
|
|
|
+
|
|
|
=========================== Config Option ===========================
|
|
|
|
|
|
This config option adds approximately 1.5kb of text. and 50 bytes of
|