bpf: Implement BPF exceptions

This patch implements BPF exceptions, and introduces a bpf_throw kfunc
to allow programs to throw exceptions during their execution at runtime.
A bpf_throw invocation is treated as an immediate termination of the
program, returning back to its caller within the kernel, unwinding all
stack frames.

This allows the program to simplify its implementation, by testing for
runtime conditions which the verifier has no visibility into, and assert
that they are true. In case they are not, the program can simply throw
an exception from the other branch.

BPF exceptions are explicitly *NOT* an unlikely slowpath error handling
primitive, and this objective has guided design choices of the
implementation of the them within the kernel (with the bulk of the cost
for unwinding the stack offloaded to the bpf_throw kfunc).

The implementation of this mechanism requires use of add_hidden_subprog
mechanism introduced in the previous patch, which generates a couple of
instructions to move R1 to R0 and exit. The JIT then rewrites the
prologue of this subprog to take the stack pointer and frame pointer as
inputs and reset the stack frame, popping all callee-saved registers
saved by the main subprog. The bpf_throw function then walks the stack
at runtime, and invokes this exception subprog with the stack and frame
pointers as parameters.

Reviewers must take note that currently the main program is made to save
all callee-saved registers on x86_64 during entry into the program. This
is because we must do an equivalent of a lightweight context switch when
unwinding the stack, therefore we need the callee-saved registers of the
caller of the BPF program to be able to return with a sane state.

Note that we have to additionally handle r12, even though it is not used
by the program, because when throwing the exception the program makes an
entry into the kernel which could clobber r12 after saving it on the
stack. To be able to preserve the value we received on program entry, we
push r12 and restore it from the generated subprogram when unwinding the
stack.

For now, bpf_throw invocation fails when lingering resources or locks
exist in that path of the program. In a future followup, bpf_throw will
be extended to perform frame-by-frame unwinding to release lingering
resources for each stack frame, removing this limitation.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 77 insertions, 12 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d0c24b5a6abb..84005f2114e0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -18,6 +18,8 @@
 #include <asm/text-patching.h>
 #include <asm/unwind.h>
 
+static bool all_callee_regs_used[4] = {true, true, true, true};
+
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
 	if (len == 1)
@@ -256,6 +258,14 @@ struct jit_context {
 /* Number of bytes that will be skipped on tailcall */
 #define X86_TAIL_CALL_OFFSET	(11 + ENDBR_INSN_SIZE)
 
+static void push_r12(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x54);   /* push r12 */
+	*pprog = prog;
+}
+
 static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
 	u8 *prog = *pprog;
@@ -271,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+static void pop_r12(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x5C);   /* pop r12 */
+	*pprog = prog;
+}
+
 static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
 	u8 *prog = *pprog;
@@ -292,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
  * while jumping to another program
  */
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
-			  bool tail_call_reachable, bool is_subprog)
+			  bool tail_call_reachable, bool is_subprog,
+			  bool is_exception_cb)
 {
 	u8 *prog = *pprog;
 
@@ -312,8 +331,22 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 			/* Keep the same instruction layout. */
 			EMIT2(0x66, 0x90); /* nop2 */
 	}
-	EMIT1(0x55);             /* push rbp */
-	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	/* Exception callback receives FP as third parameter */
+	if (is_exception_cb) {
+		EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */
+		EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */
+		/* The main frame must have exception_boundary as true, so we
+		 * first restore those callee-saved regs from stack, before
+		 * reusing the stack frame.
+		 */
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+		/* Reset the stack frame. */
+		EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */
+	} else {
+		EMIT1(0x55);             /* push rbp */
+		EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+	}
 
 	/* X86_TAIL_CALL_OFFSET is here */
 	EMIT_ENDBR();
@@ -472,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip)
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+					u8 **pprog, bool *callee_regs_used,
 					u32 stack_depth, u8 *ip,
 					struct jit_context *ctx)
 {
@@ -522,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
 	EMIT2(X86_JE, offset);                    /* je out */
 
-	pop_callee_regs(&prog, callee_regs_used);
+	if (bpf_prog->aux->exception_boundary) {
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+	} else {
+		pop_callee_regs(&prog, callee_regs_used);
+	}
 
 	EMIT1(0x58);                              /* pop rax */
 	if (stack_depth)
@@ -546,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	*pprog = prog;
 }
 
-static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
+static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+				      struct bpf_jit_poke_descriptor *poke,
 				      u8 **pprog, u8 *ip,
 				      bool *callee_regs_used, u32 stack_depth,
 				      struct jit_context *ctx)
@@ -575,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
 		  poke->tailcall_bypass);
 
-	pop_callee_regs(&prog, callee_regs_used);
+	if (bpf_prog->aux->exception_boundary) {
+		pop_callee_regs(&prog, all_callee_regs_used);
+		pop_r12(&prog);
+	} else {
+		pop_callee_regs(&prog, callee_regs_used);
+	}
+
 	EMIT1(0x58);                                  /* pop rax */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
@@ -1050,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
-		      bpf_is_subprog(bpf_prog));
-	push_callee_regs(&prog, callee_regs_used);
+		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
+	/* Exception callback will clobber callee regs for its own use, and
+	 * restore the original callee regs from main prog's stack frame.
+	 */
+	if (bpf_prog->aux->exception_boundary) {
+		/* We also need to save r12, which is not mapped to any BPF
+		 * register, as we throw after entry into the kernel, which may
+		 * overwrite r12.
+		 */
+		push_r12(&prog);
+		push_callee_regs(&prog, all_callee_regs_used);
+	} else {
+		push_callee_regs(&prog, callee_regs_used);
+	}
 
 	ilen = prog - temp;
 	if (rw_image)
@@ -1648,13 +1706,15 @@ st:			if (is_imm8(insn->off))
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
-				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
+				emit_bpf_tail_call_direct(bpf_prog,
+							  &bpf_prog->aux->poke_tab[imm32 - 1],
 							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
 							  bpf_prog->aux->stack_depth,
 							  ctx);
 			else
-				emit_bpf_tail_call_indirect(&prog,
+				emit_bpf_tail_call_indirect(bpf_prog,
+							    &prog,
 							    callee_regs_used,
 							    bpf_prog->aux->stack_depth,
 							    image + addrs[i - 1],
@@ -1907,7 +1967,12 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			pop_callee_regs(&prog, callee_regs_used);
+			if (bpf_prog->aux->exception_boundary) {
+				pop_callee_regs(&prog, all_callee_regs_used);
+				pop_r12(&prog);
+			} else {
+				pop_callee_regs(&prog, callee_regs_used);
+			}
 			EMIT1(0xC9);         /* leave */
 			emit_return(&prog, image + addrs[i - 1] + (prog - temp));
 			break;