Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 19 Jan 2022 20:14:21 -0800
From:   Alexei Starovoitov <alexei.starovoitov@gmail.com>
To:     Song Liu <song@kernel.org>
Cc:     bpf@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net,
        andrii@kernel.org, kernel-team@fb.com, peterz@infradead.org,
        x86@kernel.org, Song Liu <songliubraving@fb.com>
Subject: Re: [PATCH v4 bpf-next 6/7] bpf: introduce bpf_prog_pack allocator
Message-ID: <20220120041421.ngrxukhb4t6b7tlq@ast-mbp.dhcp.thefacebook.com>
References: <20220119230620.3137425-1-song@kernel.org>
 <20220119230620.3137425-7-song@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220119230620.3137425-7-song@kernel.org>
Precedence: bulk

On Wed, Jan 19, 2022 at 03:06:19PM -0800, Song Liu wrote:
>  
> +/*
> + * BPF program pack allocator.
> + *
> + * Most BPF programs are pretty small. Allocating a hole page for each
> + * program is sometime a waste. Many small bpf program also adds pressure
> + * to instruction TLB. To solve this issue, we introduce a BPF program pack
> + * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86)
> + * to host BPF programs.
> + */
> +#define BPF_PROG_PACK_SIZE	HPAGE_PMD_SIZE
> +#define BPF_PROG_MAX_PACK_PROG_SIZE	HPAGE_PMD_SIZE

We have a synthetic test with 1M bpf instructions. How did it JIT?
Are you saying we were lucky that every BPF insn was JITed to <2 bytes x86?
Did I misread the 2MB limit?