Merge tag 'x86_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Add a AMX ptrace self test

 - Prevent a false-positive warning when retrieving the (invalid)
   address of dynamic FPU features in their init state which are not
   saved in init_fpstate at all

 - Randomize per-CPU entry areas only when KASLR is enabled

* tag 'x86_urgent_for_v6.3_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  selftests/x86/amx: Add a ptrace test
  x86/fpu/xstate: Prevent false-positive warning in __copy_xstate_uabi_buf()
  x86/mm: Do not shuffle CPU entry areas without KASLR

arch/x86/kernel/fpu/xstate.c

@@ -1118,21 +1118,20 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	zerofrom = offsetof(struct xregs_state, extended_state_area);
 
 	/*
-	 * The ptrace buffer is in non-compacted XSAVE format.  In
-	 * non-compacted format disabled features still occupy state space,
-	 * but there is no state to copy from in the compacted
-	 * init_fpstate. The gap tracking will zero these states.
-	 */
-	mask = fpstate->user_xfeatures;
-
-	/*
-	 * Dynamic features are not present in init_fpstate. When they are
-	 * in an all zeros init state, remove those from 'mask' to zero
-	 * those features in the user buffer instead of retrieving them
-	 * from init_fpstate.
+	 * This 'mask' indicates which states to copy from fpstate.
+	 * Those extended states that are not present in fpstate are
+	 * either disabled or initialized:
+	 *
+	 * In non-compacted format, disabled features still occupy
+	 * state space but there is no state to copy from in the
+	 * compacted init_fpstate. The gap tracking will zero these
+	 * states.
+	 *
+	 * The extended features have an all zeroes init state. Thus,
+	 * remove them from 'mask' to zero those features in the user
+	 * buffer instead of retrieving them from init_fpstate.
 	 */
-	if (fpu_state_size_dynamic())
-		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+	mask = header.xfeatures;
 
 	for_each_extended_xfeature(i, mask) {
 		/*
@@ -1151,9 +1150,8 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			pkru.pkru = pkru_val;
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
-			copy_feature(header.xfeatures & BIT_ULL(i), &to,
+			membuf_write(&to,
 				     __raw_xsave_addr(xsave, i),
-				     __raw_xsave_addr(xinit, i),
 				     xstate_sizes[i]);
 		}
 		/*

arch/x86/mm/cpu_entry_area.c

@@ -10,6 +10,7 @@
 #include <asm/fixmap.h>
 #include <asm/desc.h>
 #include <asm/kasan.h>
+#include <asm/setup.h>
 
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
@@ -29,6 +30,12 @@ static __init void init_cea_offsets(void)
 	unsigned int max_cea;
 	unsigned int i, j;
 
+	if (!kaslr_enabled()) {
+		for_each_possible_cpu(i)
+			per_cpu(_cea_offset, i) = i;
+		return;
+	}
+
 	max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE;
 
 	/* O(sodding terrible) */

tools/testing/selftests/x86/amx.c

@@ -14,8 +14,10 @@
 #include <sys/auxv.h>
 #include <sys/mman.h>
 #include <sys/shm.h>
+#include <sys/ptrace.h>
 #include <sys/syscall.h>
 #include <sys/wait.h>
+#include <sys/uio.h>
 
 #include "../kselftest.h" /* For __cpuid_count() */
 
@@ -583,6 +585,13 @@ static void test_dynamic_state(void)
 	_exit(0);
 }
 
+static inline int __compare_tiledata_state(struct xsave_buffer *xbuf1, struct xsave_buffer *xbuf2)
+{
+	return memcmp(&xbuf1->bytes[xtiledata.xbuf_offset],
+		      &xbuf2->bytes[xtiledata.xbuf_offset],
+		      xtiledata.size);
+}
+
 /*
  * Save current register state and compare it to @xbuf1.'
  *
@@ -599,9 +608,7 @@ static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1)
 		fatal_error("failed to allocate XSAVE buffer\n");
 
 	xsave(xbuf2, XFEATURE_MASK_XTILEDATA);
-	ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset],
-		     &xbuf2->bytes[xtiledata.xbuf_offset],
-		     xtiledata.size);
+	ret = __compare_tiledata_state(xbuf1, xbuf2);
 
 	free(xbuf2);
 
@@ -826,6 +833,99 @@ static void test_context_switch(void)
 	free(finfo);
 }
 
+/* Ptrace test */
+
+/*
+ * Make sure the ptracee has the expanded kernel buffer on the first
+ * use. Then, initialize the state before performing the state
+ * injection from the ptracer.
+ */
+static inline void ptracee_firstuse_tiledata(void)
+{
+	load_rand_tiledata(stashed_xsave);
+	init_xtiledata();
+}
+
+/*
+ * Ptracer injects the randomized tile data state. It also reads
+ * before and after that, which will execute the kernel's state copy
+ * functions. So, the tester is advised to double-check any emitted
+ * kernel messages.
+ */
+static void ptracer_inject_tiledata(pid_t target)
+{
+	struct xsave_buffer *xbuf;
+	struct iovec iov;
+
+	xbuf = alloc_xbuf();
+	if (!xbuf)
+		fatal_error("unable to allocate XSAVE buffer");
+
+	printf("\tRead the init'ed tiledata via ptrace().\n");
+
+	iov.iov_base = xbuf;
+	iov.iov_len = xbuf_size;
+
+	memset(stashed_xsave, 0, xbuf_size);
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		fatal_error("PTRACE_GETREGSET");
+
+	if (!__compare_tiledata_state(stashed_xsave, xbuf))
+		printf("[OK]\tThe init'ed tiledata was read from ptracee.\n");
+	else
+		printf("[FAIL]\tThe init'ed tiledata was not read from ptracee.\n");
+
+	printf("\tInject tiledata via ptrace().\n");
+
+	load_rand_tiledata(xbuf);
+
+	memcpy(&stashed_xsave->bytes[xtiledata.xbuf_offset],
+	       &xbuf->bytes[xtiledata.xbuf_offset],
+	       xtiledata.size);
+
+	if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		fatal_error("PTRACE_SETREGSET");
+
+	if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+		fatal_error("PTRACE_GETREGSET");
+
+	if (!__compare_tiledata_state(stashed_xsave, xbuf))
+		printf("[OK]\tTiledata was correctly written to ptracee.\n");
+	else
+		printf("[FAIL]\tTiledata was not correctly written to ptracee.\n");
+}
+
+static void test_ptrace(void)
+{
+	pid_t child;
+	int status;
+
+	child = fork();
+	if (child < 0) {
+		err(1, "fork");
+	} else if (!child) {
+		if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
+			err(1, "PTRACE_TRACEME");
+
+		ptracee_firstuse_tiledata();
+
+		raise(SIGTRAP);
+		_exit(0);
+	}
+
+	do {
+		wait(&status);
+	} while (WSTOPSIG(status) != SIGTRAP);
+
+	ptracer_inject_tiledata(child);
+
+	ptrace(PTRACE_DETACH, child, NULL, NULL);
+	wait(&status);
+	if (!WIFEXITED(status) || WEXITSTATUS(status))
+		err(1, "ptrace test");
+}
+
 int main(void)
 {
 	/* Check hardware availability at first */
@@ -846,6 +946,8 @@ int main(void)
 	ctxtswtest_config.num_threads = 5;
 	test_context_switch();
 
+	test_ptrace();
+
 	clearhandler(SIGILL);
 	free_stashed_xsave();