bpf: Add support for BTF pointers to x86 JIT

Pointer to BTF object is a pointer to kernel object or NULL.
Such pointers can only be used by BPF_LDX instructions.
The verifier changed their opcode from LDX|MEM|size
to LDX|PROBE_MEM|size to make JITing easier.
The number of entries in extable is the number of BPF_LDX insns
that access kernel memory via "pointer to BTF type".
Only these load instructions can fault.
Since x86 extable is relative it has to be allocated in the same
memory region as JITed code.
Allocate it prior to last pass of JITing and let the last pass populate it.
Pointer to extable in bpf_prog_aux is necessary to make page fault
handling fast.
Page fault handling is done in two steps:
1. bpf_prog_kallsyms_find() finds BPF program that page faulted.
   It's done by walking rb tree.
2. then extable for given bpf program is binary searched.
This process is similar to how page faulting is done for kernel modules.
The exception handler skips over faulting x86 instruction and
initializes destination register with zero. This mimics exact
behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed).

JITs for other architectures can add support in similar way.
Until then they will reject unknown opcode and fallback to interpreter.

Since extable should be aligned and placed near JITed code
make bpf_jit_binary_alloc() return 4 byte aligned image offset,
so that extable aligning formula in bpf_int_jit_compile() doesn't need
to rely on internal implementation of bpf_jit_binary_alloc().
On x86 gcc defaults to 16-byte alignment for regular kernel functions
due to better performance. JITed code may be aligned to 16 in the future,
but it will use 4 in the meantime.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org

3 files changed, 22 insertions, 1 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8a765bbd33f0..673f5d40a93e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -30,7 +30,7 @@
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
 #include <linux/perf_event.h>
-
+#include <linux/extable.h>
 #include <asm/unaligned.h>
 
 /* Registers */
@@ -712,6 +712,24 @@ bool is_bpf_text_address(unsigned long addr)
 	return ret;
 }
 
+const struct exception_table_entry *search_bpf_extables(unsigned long addr)
+{
+	const struct exception_table_entry *e = NULL;
+	struct bpf_prog *prog;
+
+	rcu_read_lock();
+	prog = bpf_prog_kallsyms_find(addr);
+	if (!prog)
+		goto out;
+	if (!prog->aux->num_exentries)
+		goto out;
+
+	e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr);
+out:
+	rcu_read_unlock();
+	return e;
+}
+
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4b6a2cfcd47..fba9ef6a831b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8729,6 +8729,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 			insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
+			env->prog->aux->num_exentries++;
 			continue;
 		default:
 			continue;
diff --git a/kernel/extable.c b/kernel/extable.c
index f6c9406eec7d..f6920a11e28a 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -56,6 +56,8 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	e = search_kernel_exception_table(addr);
 	if (!e)
 		e = search_module_extables(addr);
+	if (!e)
+		e = search_bpf_extables(addr);
 	return e;
 }