Merge tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Thomas Gleixner:

 - Improve retpoline code patching by separating it from alternatives
   which reduces memory footprint and allows to do better optimizations
   in the actual runtime patching.

 - Add proper retpoline support for x86/BPF

 - Address noinstr warnings in x86/kvm, lockdep and paravirtualization
   code

 - Add support to handle pv_opsindirect calls in the noinstr analysis

 - Classify symbols upfront and cache the result to avoid redundant
   str*cmp() invocations.

 - Add a CFI hash to reduce memory consumption which also reduces
   runtime on a allyesconfig by ~50%

 - Adjust XEN code to make objtool handling more robust and as a side
   effect to prevent text fragmentation due to placement of the
   hypercall page.

* tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  bpf,x86: Respect X86_FEATURE_RETPOLINE*
  bpf,x86: Simplify computing label offsets
  x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
  x86/alternative: Add debug prints to apply_retpolines()
  x86/alternative: Try inline spectre_v2=retpoline,amd
  x86/alternative: Handle Jcc __x86_indirect_thunk_\reg
  x86/alternative: Implement .retpoline_sites support
  x86/retpoline: Create a retpoline thunk array
  x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h
  x86/asm: Fixup odd GEN-for-each-reg.h usage
  x86/asm: Fix register order
  x86/retpoline: Remove unused replacement symbols
  objtool,x86: Replace alternatives with .retpoline_sites
  objtool: Shrink struct instruction
  objtool: Explicitly avoid self modifying code in .altinstr_replacement
  objtool: Classify symbols
  objtool: Support pv_opsindirect calls for noinstr
  x86/xen: Rework the xen_{cpu,irq,mmu}_opsarrays
  x86/xen: Mark xen_force_evtchn_callback() noinstr
  x86/xen: Make irq_disable() noinstr
  ...

1 files changed, 59 insertions, 101 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9ea57389c554..39c802525fce 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,7 +15,6 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
-#include <asm/asm-prototypes.h>
 
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -225,6 +224,14 @@ static void jit_fill_hole(void *area, unsigned int size)
 
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
+
+	/*
+	 * Program specific offsets of labels in the code; these rely on the
+	 * JIT doing at least 2 passes, recording the position on the first
+	 * pass, only to generate the correct offset on the second pass.
+	 */
+	int tail_call_direct_label;
+	int tail_call_indirect_label;
 };
 
 /* Maximum number of bytes emitted while JITing one eBPF insn */
@@ -380,20 +387,23 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
-static int get_pop_bytes(bool *callee_regs_used)
+#define EMIT_LFENCE()	EMIT3(0x0F, 0xAE, 0xE8)
+
+static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
-	int bytes = 0;
+	u8 *prog = *pprog;
 
-	if (callee_regs_used[3])
-		bytes += 2;
-	if (callee_regs_used[2])
-		bytes += 2;
-	if (callee_regs_used[1])
-		bytes += 2;
-	if (callee_regs_used[0])
-		bytes += 1;
+#ifdef CONFIG_RETPOLINE
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+		EMIT_LFENCE();
+		EMIT2(0xFF, 0xE0 + reg);
+	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
+	} else
+#endif
+	EMIT2(0xFF, 0xE0 + reg);
 
-	return bytes;
+	*pprog = prog;
 }
 
 /*
@@ -411,29 +421,12 @@ static int get_pop_bytes(bool *callee_regs_used)
  * out:
  */
 static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
-					u32 stack_depth)
+					u32 stack_depth, u8 *ip,
+					struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 42;
-	int off2 = 31;
-	int off3 = 9;
-
-	/* count the additional bytes used for popping callee regs from stack
-	 * that need to be taken into account for each of the offsets that
-	 * are used for bailing out of the tail call
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-	off2 += pop_bytes;
-	off3 += pop_bytes;
-
-	if (stack_depth) {
-		off1 += 7;
-		off2 += 7;
-		off3 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * rdi - pointer to ctx
@@ -448,8 +441,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
-	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JBE, offset);                   /* jbe out */
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -457,8 +451,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JA, OFFSET2);                   /* ja out */
+
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                    /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
@@ -471,12 +466,11 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 *	goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
-#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
-	EMIT2(X86_JE, OFFSET3);                   /* je out */
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+	EMIT2(X86_JE, offset);                    /* je out */
+
+	pop_callee_regs(&prog, callee_regs_used);
 
 	EMIT1(0x58);                              /* pop rax */
 	if (stack_depth)
@@ -493,41 +487,21 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
 	 * rdi == ctx (1st arg)
 	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
-	RETPOLINE_RCX_BPF_JIT();
+	emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));
 
 	/* out: */
+	ctx->tail_call_indirect_label = prog - start;
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image,
-				      bool *callee_regs_used, u32 stack_depth)
+				      u8 **pprog, u8 *ip,
+				      bool *callee_regs_used, u32 stack_depth,
+				      struct jit_context *ctx)
 {
 	int tcc_off = -4 - round_up(stack_depth, 8);
-	u8 *prog = *pprog;
-	int pop_bytes = 0;
-	int off1 = 20;
-	int poke_off;
-
-	/* count the additional bytes used for popping callee regs to stack
-	 * that need to be taken into account for jump offset that is used for
-	 * bailing out from of the tail call when limit is reached
-	 */
-	pop_bytes = get_pop_bytes(callee_regs_used);
-	off1 += pop_bytes;
-
-	/*
-	 * total bytes for:
-	 * - nop5/ jmpq $off
-	 * - pop callee regs
-	 * - sub rsp, $val if depth > 0
-	 * - pop rax
-	 */
-	poke_off = X86_PATCH_SIZE + pop_bytes + 1;
-	if (stack_depth) {
-		poke_off += 7;
-		off1 += 7;
-	}
+	u8 *prog = *pprog, *start = *pprog;
+	int offset;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -535,28 +509,30 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	 */
 	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, off1);                          /* ja out */
+
+	offset = ctx->tail_call_direct_label - (prog + 2 - start);
+	EMIT2(X86_JA, offset);                        /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
-	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->tailcall_bypass = ip + (prog - start);
 	poke->adj_off = X86_TAIL_CALL_OFFSET;
-	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
+	poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;
 	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
 
 	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
 		  poke->tailcall_bypass);
 
-	*pprog = prog;
-	pop_callee_regs(pprog, callee_regs_used);
-	prog = *pprog;
+	pop_callee_regs(&prog, callee_regs_used);
 	EMIT1(0x58);                                  /* pop rax */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
+
 	/* out: */
+	ctx->tail_call_direct_label = prog - start;
 
 	*pprog = prog;
 }
@@ -1222,8 +1198,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* speculation barrier */
 		case BPF_ST | BPF_NOSPEC:
 			if (boot_cpu_has(X86_FEATURE_XMM2))
-				/* Emit 'lfence' */
-				EMIT3(0x0F, 0xAE, 0xE8);
+				EMIT_LFENCE();
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
@@ -1412,13 +1387,16 @@ 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],
-							  &prog, addrs[i], image,
+							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
-							  bpf_prog->aux->stack_depth);
+							  bpf_prog->aux->stack_depth,
+							  ctx);
 			else
 				emit_bpf_tail_call_indirect(&prog,
 							    callee_regs_used,
-							    bpf_prog->aux->stack_depth);
+							    bpf_prog->aux->stack_depth,
+							    image + addrs[i - 1],
+							    ctx);
 			break;
 
 			/* cond jump */
@@ -2124,24 +2102,6 @@ cleanup:
 	return ret;
 }
 
-static int emit_fallback_jump(u8 **pprog)
-{
-	u8 *prog = *pprog;
-	int err = 0;
-
-#ifdef CONFIG_RETPOLINE
-	/* Note that this assumes the the compiler uses external
-	 * thunks for indirect calls. Both clang and GCC use the same
-	 * naming convention for external thunks.
-	 */
-	err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog);
-#else
-	EMIT2(0xFF, 0xE2);	/* jmp rdx */
-#endif
-	*pprog = prog;
-	return err;
-}
-
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 {
 	u8 *jg_reloc, *prog = *pprog;
@@ -2163,9 +2123,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 		if (err)
 			return err;
 
-		err = emit_fallback_jump(&prog);	/* jmp thunk/indirect */
-		if (err)
-			return err;
+		emit_indirect_jump(&prog, 2 /* rdx */, prog);
 
 		*pprog = prog;
 		return 0;