| Message ID | 20220403204036.1269562-1-Jason@zx2c4.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2] gcc-plugins: latent_entropy: use /dev/urandom | expand |
On Tue, Apr 05, 2022 at 02:38:58PM +0200, Jason A. Donenfeld wrote: > Hi Kees, > > On 4/5/22, Kees Cook <keescook@chromium.org> wrote: > > On Tue, Apr 05, 2022 at 12:47:14AM +0200, Jason A. Donenfeld wrote: > >> On Mon, Apr 4, 2022 at 8:49 PM Kees Cook <keescook@chromium.org> wrote: > >> > This mixes two changes: the pRNG change and the "use urandom if > >> > non-deterministic" change. I think these should be split, so the pRNG > >> > change can be explicitly justified. > >> > >> Alright, I'll split those. Or, more probably, just drop the xorshift > >> thing. There's not actually a strong reason for preferring xorshift. I > >> did it because it produces more uniformity and is faster to compute and > >> all that. But none of that stuff actually matters here. It was just a > >> sort of "well I'm at it..." thing. > > > > Well, it's nice to have and you already wrote it, so seems a waste to > > just drop it. :) > > > >> > > static struct plugin_info latent_entropy_plugin_info = { > >> > > - .version = "201606141920vanilla", > >> > > + .version = "202203311920vanilla", > >> > > >> > This doesn't really need to be versioned. We can change this to just > >> > "vanilla", IMO. > >> > >> Okay. I suppose you want it to be in a different patch too, right? In > >> which case I'll leave it out and maybe get to it later. (I suppose one > >> probably needs to double check whether it's used for anything > >> interesting like dwarf debug info or whatever, where maybe it's > >> helpful?) > > > > Hm, I don't think it shows up anywhere, but you can just drop the hunk > > that touch it. I can remove them all with a separate patch later. > > > > Okay. That's what I did here > https://lore.kernel.org/lkml/20220404230709.124508-1-Jason@zx2c4.com/ > so awaiting your merge. (I still find all aspects of v2 more > preferable for a variety of weak reasons in case you'd like to merge > that instead, but v3 is available now.) v3 uses a different check for the -f option, though? Isn't that preferred over the v2 method? Also, I did some quick benchmarking, and any difference in runtime is completely lost in the noise, so that's good.
Hi Kees, On 4/5/22, Kees Cook <keescook@chromium.org> wrote: > v3 uses a different check for the -f option, though? Isn't that > preferred over the v2 method? Based on the code comments, I assume this is gcc upstream's intended method. It strikes me as worse, though, because that variable, when it's not set to -1, is set to: `local_tick = (unsigned) tv.tv_sec * 1000 + tv.tv_usec / 1000;` which is on occasion unlucky and hits -1 too. But maybe that's a bug in gcc that should be fixed instead? I don't know really. But anyway that's why I'm /also/ more into that aspect of v2. > Also, I did some quick benchmarking, and any difference in runtime is > completely lost in the noise, so that's good. Oh good to hear. So my 2k buffer is fine then. Jason
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c index 589454bce930..042442013ae1 100644 --- a/scripts/gcc-plugins/latent_entropy_plugin.c +++ b/scripts/gcc-plugins/latent_entropy_plugin.c @@ -82,29 +82,37 @@ __visible int plugin_is_GPL_compatible; static GTY(()) tree latent_entropy_decl; static struct plugin_info latent_entropy_plugin_info = { - .version = "201606141920vanilla", + .version = "202203311920vanilla", .help = "disable\tturn off latent entropy instrumentation\n", }; -static unsigned HOST_WIDE_INT seed; -/* - * get_random_seed() (this is a GCC function) generates the seed. - * This is a simple random generator without any cryptographic security because - * the entropy doesn't come from here. - */ +static unsigned HOST_WIDE_INT deterministic_seed; +static unsigned HOST_WIDE_INT rnd_buf[256]; +static size_t rnd_idx = ARRAY_SIZE(rnd_buf); +static int urandom_fd = -1; + static unsigned HOST_WIDE_INT get_random_const(void) { - unsigned int i; - unsigned HOST_WIDE_INT ret = 0; - - for (i = 0; i < 8 * sizeof(ret); i++) { - ret = (ret << 1) | (seed & 1); - seed >>= 1; - if (ret & 1) - seed ^= 0xD800000000000000ULL; + if (deterministic_seed) { + unsigned HOST_WIDE_INT w = deterministic_seed; + w ^= w << 13; + w ^= w >> 7; + w ^= w << 17; + deterministic_seed = w; + return deterministic_seed; } - return ret; + if (urandom_fd < 0) { + urandom_fd = open("/dev/urandom", O_RDONLY); + if (urandom_fd < 0) + abort(); + } + if (rnd_idx >= ARRAY_SIZE(rnd_buf)) { + if (read(urandom_fd, rnd_buf, sizeof(rnd_buf)) != sizeof(rnd_buf)) + abort(); + rnd_idx = 0; + } + return rnd_buf[rnd_idx++]; } static tree tree_get_random_const(tree type) @@ -537,8 +545,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused, tree type, id; int quals; - seed = get_random_seed(false); - if (in_lto_p) return; @@ -573,6 +579,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, const struct plugin_argument * const argv = plugin_info->argv; int i; + /* + * Call get_random_seed() with noinit=true, so that this returns + * 0 in the case where no seed has been passed via -frandom-seed. + */ + deterministic_seed = get_random_seed(true); + static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = { { .base = &latent_entropy_decl,
While the latent entropy plugin mostly doesn't derive entropy from get_random_const() for measuring the call graph, when __latent_entropy is applied to a constant, then it's initialized statically to output from get_random_const(). In that case, this data is derived from a 64-bit seed, which means a buffer of 512 bits doesn't really have that amount of compile-time entropy. This patch fixes that shortcoming by just buffering chunks of /dev/urandom output and doling it out as requested. At the same time, it's important that we don't break the use of -frandom-seed, for people who want the runtime benefits of the latent entropy plugin, while still having compile-time determinism. In that case, we detect whether gcc's set_random_seed() has been called by making a call to get_random_seed(noinit=true) in the plugin init function, which is called after set_random_seed() is called but before anything that calls get_random_seed(noinit=false), and seeing if it's zero or not. If it's not zero, we're in deterministic mode, and so we just generate numbers with a basic xorshift prng. Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin") Cc: stable@vger.kernel.org Cc: PaX Team <pageexec@freemail.hu> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> --- Changes v1->v2: - Pipacs pointed out that using /dev/urandom unconditionally would break the use of -frandom-seed, so now we check for that and keep with something deterministic in that case. I'm not super familiar with this plugin or its conventions, so pointers would be most welcome if something here looks amiss. The decision to buffer 2k at a time is pretty arbitrary too; I haven't measured usage. scripts/gcc-plugins/latent_entropy_plugin.c | 48 +++++++++++++-------- 1 file changed, 30 insertions(+), 18 deletions(-)