arm64/cfi,bpf: Support kCFI + BPF on arm64

Currently, bpf_dispatcher_*_func() is marked with `__nocfi` therefore
calling BPF programs from this interface doesn't cause CFI warnings.

When BPF programs are called directly from C: from BPF helpers or
struct_ops, CFI warnings are generated.

Implement proper CFI prologues for the BPF programs and callbacks and
drop __nocfi for arm64. Fix the trampoline generation code to emit kCFI
prologue when a struct_ops trampoline is being prepared.

Signed-off-by: Puranjay Mohan <[email protected]>
Co-developed-by: Maxwell Bland <[email protected]>
Signed-off-by: Maxwell Bland <[email protected]>
Co-developed-by: Sami Tolvanen <[email protected]>
Signed-off-by: Sami Tolvanen <[email protected]>
Tested-by: Dao Huang <[email protected]>
Acked-by: Will Deacon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: puranjaymohan

arch/arm64/include/asm/cfi.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_CFI_H
+#define _ASM_ARM64_CFI_H
+
+#define __bpfcall
+
+#endif /* _ASM_ARM64_CFI_H */

arch/arm64/net/bpf_jit_comp.c

@@ -10,6 +10,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/bitfield.h>
 #include <linux/bpf.h>
+#include <linux/cfi.h>
 #include <linux/filter.h>
 #include <linux/memory.h>
 #include <linux/printk.h>
@@ -114,6 +115,14 @@ static inline void emit(const u32 insn, struct jit_ctx *ctx)
 	ctx->idx++;
 }
 
+static inline void emit_u32_data(const u32 data, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL && ctx->write)
+		ctx->image[ctx->idx] = data;
+
+	ctx->idx++;
+}
+
 static inline void emit_a64_mov_i(const int is64, const int reg,
 				  const s32 val, struct jit_ctx *ctx)
 {
@@ -174,6 +183,12 @@ static inline void emit_bti(u32 insn, struct jit_ctx *ctx)
 		emit(insn, ctx);
 }
 
+static inline void emit_kcfi(u32 hash, struct jit_ctx *ctx)
+{
+	if (IS_ENABLED(CONFIG_CFI_CLANG))
+		emit_u32_data(hash, ctx);
+}
+
 /*
  * Kernel addresses in the vmalloc space use at most 48 bits, and the
  * remaining bits are guaranteed to be 0x1. So we can compose the address
@@ -503,7 +518,6 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
 	const u8 priv_sp = bpf2a64[PRIVATE_SP];
 	void __percpu *priv_stack_ptr;
-	const int idx0 = ctx->idx;
 	int cur_offset;
 
 	/*
@@ -529,6 +543,9 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
+	emit_kcfi(is_main_prog ? cfi_bpf_hash : cfi_bpf_subprog_hash, ctx);
+	const int idx0 = ctx->idx;
+
 	/* bpf function may be invoked by 3 instruction types:
 	 * 1. bl, attached via freplace to bpf prog via short jump
 	 * 2. br, attached via freplace to bpf prog via long jump
@@ -2146,9 +2163,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		jit_data->ro_header = ro_header;
 	}
 
-	prog->bpf_func = (void *)ctx.ro_image;
+	prog->bpf_func = (void *)ctx.ro_image + cfi_get_offset();
 	prog->jited = 1;
-	prog->jited_len = prog_size;
+	prog->jited_len = prog_size - cfi_get_offset();
 
 	if (!prog->is_func || extra_pass) {
 		int i;
@@ -2527,6 +2544,12 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	/* return address locates above FP */
 	retaddr_off = stack_size + 8;
 
+	if (flags & BPF_TRAMP_F_INDIRECT) {
+		/*
+		 * Indirect call for bpf_struct_ops
+		 */
+		emit_kcfi(cfi_get_func_hash(func_addr), ctx);
+	}
 	/* bpf trampoline may be invoked by 3 instruction types:
 	 * 1. bl, attached to bpf prog or kernel function via short jump
 	 * 2. br, attached to bpf prog or kernel function via long jump
@@ -3045,6 +3068,7 @@ void bpf_jit_free(struct bpf_prog *prog)
 					   sizeof(jit_data->header->size));
 			kfree(jit_data);
 		}
+		prog->bpf_func -= cfi_get_offset();
 		hdr = bpf_jit_binary_pack_hdr(prog);
 		bpf_jit_binary_pack_free(hdr, NULL);
 		priv_stack_ptr = prog->aux->priv_stack_ptr;