[PATCH bpf-next 6/6] selftests/bpf: Add arena fault tests for atomics with fetch

Add stream_arena_xchg_fault and stream_arena_cmpxchg_fault next to the
existing read, write and load-acquire fault tests, covering the two
places a read-modify-write can deposit the old value: src_reg for a
BPF_XCHG and r0 for a BPF_CMPXCHG. Both cover both halves of the JIT
bug that left the fetch destination alone when a RMW on an arena pointer
faulted:

  - the fault has to be reported as a WRITE, and at the address held by
    the destination register, which __stderr() and test_address() check
  - the register receiving the fetched value has to be cleared by the
    fault handler, which the programs check by poisoning it before the
    atomic and returning it, so __retval(0) fails if it is left untouched

Note, the atomics are open coded since linux/filter.h cannot be included
alongside vmlinux.h.

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t stream
  [...]
  #464/1   stream_arena_fault_address/read_fault:OK
  #464/2   stream_arena_fault_address/write_fault:OK
  #464/3   stream_arena_fault_address/load_acquire_fault:OK
  #464/4   stream_arena_fault_address/xchg_fault:OK
  #464/5   stream_arena_fault_address/cmpxchg_fault:OK
  #464     stream_arena_fault_address:OK
  [...]
  #466/5   stream_success/stream_arena_write_fault:OK
  #466/6   stream_success/stream_arena_read_fault:OK
  #466/7   stream_success/stream_arena_load_acquire_fault:OK
  #466/8   stream_success/stream_arena_xchg_fault:OK
  #466/9   stream_success/stream_arena_cmpxchg_fault:OK
  [...]
  Summary: 4/22 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <[email protected]>
---
 .../testing/selftests/bpf/prog_tests/stream.c |   4 +
 tools/testing/selftests/bpf/progs/stream.c    | 101 ++++++++++++++++++
 2 files changed, 105 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c
index 15dd3ae2a84b..e4e9374309e2 100644
--- a/tools/testing/selftests/bpf/prog_tests/stream.c
+++ b/tools/testing/selftests/bpf/prog_tests/stream.c
@@ -105,6 +105,10 @@ void test_stream_arena_fault_address(void)
 		test_address(skel->progs.stream_arena_write_fault, &skel->bss->fault_addr);
 	if (test__start_subtest("load_acquire_fault"))
 		test_address(skel->progs.stream_arena_load_acquire_fault, &skel->bss->fault_addr);
+	if (test__start_subtest("xchg_fault"))
+		test_address(skel->progs.stream_arena_xchg_fault, &skel->bss->fault_addr);
+	if (test__start_subtest("cmpxchg_fault"))
+		test_address(skel->progs.stream_arena_cmpxchg_fault, &skel->bss->fault_addr);
 
 	stream__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c
index cf5533e11f39..00a37933e411 100644
--- a/tools/testing/selftests/bpf/progs/stream.c
+++ b/tools/testing/selftests/bpf/progs/stream.c
@@ -229,6 +229,107 @@ int stream_arena_load_acquire_fault(void *ctx)
 	return val;
 }
 
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_xchg_fault(void *ctx)
+{
+	static const struct bpf_insn xchg_insn = {
+		.code	 = 0xc3,	/* BPF_STX | BPF_ATOMIC | BPF_W */
+		.dst_reg = 1,		/* BPF_REG_1 */
+		.src_reg = 2,		/* BPF_REG_2 */
+		.off	 = 0x7fff,
+		.imm	 = 0xe1,	/* BPF_XCHG */
+	};
+	struct bpf_arena *ptr = (void *)&arena;
+	u64 user_vm_start, val;
+
+	/*
+	 * Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+	 * triggers bounds checking since the map definition is smaller than
+	 * struct bpf_arena. barrier_var() makes the pointer opaque to GCC,
+	 * preventing the bounds analysis.
+	 */
+	barrier_var(ptr);
+	user_vm_start = ptr->user_vm_start;
+	fault_addr = user_vm_start + 0x7fff;
+	bpf_addr_space_cast(user_vm_start, 0, 1);
+	/*
+	 * A read-modify-write carrying BPF_FETCH writes to memory, so the fault
+	 * has to be reported as a WRITE from the dst_reg address, but it also
+	 * reads the old value into src_reg, so the exception handler has to
+	 * clear src_reg. Poison it up front, the returned value must be 0.
+	 */
+	asm volatile (
+		"r1 = %[user_vm_start];"
+		"r2 = 1;"
+		".8byte %[xchg_insn];" /* r2 = xchg((u32 *)(r1 + 0x7fff), r2) */
+		"%[val] = r2;"
+		: [val] "=r" (val)
+		: [user_vm_start] "r" (user_vm_start),
+		  __imm_insn(xchg_insn, xchg_insn)
+		: "r1", "r2"
+	);
+	return val;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_cmpxchg_fault(void *ctx)
+{
+	static const struct bpf_insn cmpxchg_insn = {
+		.code	 = 0xc3,	/* BPF_STX | BPF_ATOMIC | BPF_W */
+		.dst_reg = 1,		/* BPF_REG_1 */
+		.src_reg = 2,		/* BPF_REG_2 */
+		.off	 = 0x7fff,
+		.imm	 = 0xf1,	/* BPF_CMPXCHG */
+	};
+	struct bpf_arena *ptr = (void *)&arena;
+	u64 user_vm_start, val;
+
+	/*
+	 * Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+	 * triggers bounds checking since the map definition is smaller than
+	 * struct bpf_arena. barrier_var() makes the pointer opaque to GCC,
+	 * preventing the bounds analysis.
+	 */
+	barrier_var(ptr);
+	user_vm_start = ptr->user_vm_start;
+	fault_addr = user_vm_start + 0x7fff;
+	bpf_addr_space_cast(user_vm_start, 0, 1);
+	/*
+	 * Same as the exchange above, except that a BPF_CMPXCHG reads the old
+	 * value into r0 rather than into src_reg, so r0 is the register the
+	 * exception handler has to clear. It doubles as the compare value, but
+	 * the comparison never happens since the access faults first.
+	 */
+	asm volatile (
+		"r1 = %[user_vm_start];"
+		"r0 = 1;"
+		"r2 = 2;"
+		".8byte %[cmpxchg_insn];" /* r0 = cmpxchg((u32 *)(r1 + 0x7fff), r0, r2) */
+		"%[val] = r0;"
+		: [val] "=r" (val)
+		: [user_vm_start] "r" (user_vm_start),
+		  __imm_insn(cmpxchg_insn, cmpxchg_insn)
+		: "r0", "r1", "r2"
+	);
+	return val;
+}
+
 static __noinline void subprog(void)
 {
 	int __arena *addr = (int __arena *)0xdeadbeef;
-- 
2.43.0