Re: [PATCH v2 bpf-next 02/17] bpf: Add bpf_arch_text_poke() helper

From: Song Liu <songliubraving@fb.com>
To: Alexei Starovoitov <ast@kernel.org>
Cc: David Miller <davem@davemloft.net>,
	"daniel@iogearbox.net" <daniel@iogearbox.net>,
	"x86@kernel.org" <x86@kernel.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	Kernel Team <Kernel-team@fb.com>
Subject: Re: [PATCH v2 bpf-next 02/17] bpf: Add bpf_arch_text_poke() helper
Date: Thu, 7 Nov 2019 17:20:27 +0000	[thread overview]
Message-ID: <EE50EB7D-8FB0-4D37-A3F1-3439981A6141@fb.com> (raw)
In-Reply-To: <20191107054644.1285697-3-ast@kernel.org>

> On Nov 6, 2019, at 9:46 PM, Alexei Starovoitov <ast@kernel.org> wrote:
> 
> Add bpf_arch_text_poke() helper that is used by BPF trampoline logic to patch
> nops/calls in kernel text into calls into BPF trampoline and to patch
> calls/nops inside BPF programs too.
> 
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> ---
> arch/x86/net/bpf_jit_comp.c | 51 +++++++++++++++++++++++++++++++++++++
> include/linux/bpf.h         |  8 ++++++
> kernel/bpf/core.c           |  6 +++++
> 3 files changed, 65 insertions(+)
> 
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index 0399b1f83c23..8631d3bd637f 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
> @@ -9,9 +9,11 @@
> #include <linux/filter.h>
> #include <linux/if_vlan.h>
> #include <linux/bpf.h>
> +#include <linux/memory.h>
> #include <asm/extable.h>
> #include <asm/set_memory.h>
> #include <asm/nospec-branch.h>
> +#include <asm/text-patching.h>
> 
> static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
> {
> @@ -487,6 +489,55 @@ static int emit_call(u8 **pprog, void *func, void *ip)
> 	return 0;
> }
> 
> +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
> +		       void *old_addr, void *new_addr)
> +{
> +	u8 old_insn[NOP_ATOMIC5] = {};
> +	u8 new_insn[NOP_ATOMIC5] = {};
> +	u8 *prog;
> +	int ret;
> +
> +	if (!is_kernel_text((long)ip))
> +		/* BPF trampoline in modules is not supported */
> +		return -EINVAL;
> +
> +	if (old_addr) {
> +		prog = old_insn;
> +		ret = emit_call(&prog, old_addr, (void *)ip);
> +		if (ret)
> +			return ret;
> +	}
> +	if (old_addr) {
		^ should be new_addr?
> +		prog = new_insn;
> +		ret = emit_call(&prog, old_addr, (void *)ip);
					^^^ and here? 
> +		if (ret)
> +			return ret;
> +	}
> +	ret = -EBUSY;
> +	mutex_lock(&text_mutex);
> +	switch (t) {
> +	case BPF_MOD_NOP_TO_CALL:
> +		if (memcmp(ip, ideal_nops, 5))

Maybe use X86_CALL_SIZE instead of 5? And the five more "5" below?

> +			goto out;
> +		text_poke(ip, new_insn, 5);
> +		break;
> +	case BPF_MOD_CALL_TO_CALL:
> +		if (memcmp(ip, old_insn, 5))
> +			goto out;
> +		text_poke(ip, new_insn, 5);
> +		break;
> +	case BPF_MOD_CALL_TO_NOP:
> +		if (memcmp(ip, old_insn, 5))
> +			goto out;
> +		text_poke(ip, ideal_nops, 5);
> +		break;
> +	}
> +	ret = 0;
> +out:
> +	mutex_unlock(&text_mutex);
> +	return ret;
> +}
> +
> static bool ex_handler_bpf(const struct exception_table_entry *x,
> 			   struct pt_regs *regs, int trapnr,
> 			   unsigned long error_code, unsigned long fault_addr)
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 7c7f518811a6..8b90db25348a 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1157,4 +1157,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
> }
> #endif /* CONFIG_INET */
> 
> +enum bpf_text_poke_type {
> +	BPF_MOD_NOP_TO_CALL,
> +	BPF_MOD_CALL_TO_CALL,
> +	BPF_MOD_CALL_TO_NOP,
> +};
> +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
> +		       void *addr1, void *addr2);
> +
> #endif /* _LINUX_BPF_H */
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index 97e37d82a1cc..856564e97943 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -2140,6 +2140,12 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
> 	return -EFAULT;
> }
> 
> +int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
> +			      void *addr1, void *addr2)
> +{
> +	return -ENOTSUPP;
> +}
> +
> DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
> EXPORT_SYMBOL(bpf_stats_enabled_key);
> 
> -- 
> 2.23.0
> 