From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-qt1-f175.google.com (mail-qt1-f175.google.com [209.85.160.175]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1FDFB391E43 for ; Fri, 12 Jun 2026 16:33:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.160.175 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781282041; cv=none; b=nXPTDYihjkksKa5TbGgmIvgxdY0XdlpOrCpJM3oen+eXG8cgtCb7w1ZHyWUByDVRjKlNBiC/tQVvprO+Oyr4+998a+9X2Xk1dRgyXJVgZDvQqeLeeoUrFzPVVPOvFb1Q3r1JhQt+vWR+IHPsmrNt0aN+zzunm2mVLVBfRy24Ncc= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781282041; c=relaxed/simple; bh=XzhhPac03BBb0tAwkNL2ee4iZn73fDNM+6QfRdfae9I=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=FuQgK89ZA/yw10od52E5Dodu8QddrVYh69PpsMk/oUz6gE/EHsQcHhLcb1SNbPNLj2odecoptUerbiEJHgdoBpb5G3l3J1dce6xXn1Np8O/wQYFrM+9oZKWHLxGQgwMU/znrxQaM/KEZNCPPbdGspvlXbx3ndynfu8/AfYx3Cgg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=cmpxchg.org; spf=pass smtp.mailfrom=cmpxchg.org; dkim=pass (2048-bit key) header.d=cmpxchg.org header.i=@cmpxchg.org header.b=lnbumRZE; arc=none smtp.client-ip=209.85.160.175 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=cmpxchg.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=cmpxchg.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=cmpxchg.org header.i=@cmpxchg.org header.b="lnbumRZE" Received: by mail-qt1-f175.google.com with SMTP id d75a77b69052e-51780bbc560so18749211cf.0 for ; Fri, 12 Jun 2026 09:33:55 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cmpxchg.org; s=google; t=1781282034; x=1781886834; darn=vger.kernel.org; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:from:to:cc:subject:date:message-id:reply-to; bh=gaALrUtMzS13T301LDMZjCtTFcOTia8kl+f7FBSPKoE=; b=lnbumRZEf6xzh9agKrX8mUup5R3W9iUhzWvyX7rPLPKthbAbkVwGwkyz617UO3EiOm WcEVKFwA7VFBl53awd9qlIkGnUuKwTNhnnAfinuakHOP9gnC35/o1c3HnHuPeOY4A/H3 sOJWFWrEqSKsqKGpOu8dNRHp5A74vu9ciPsB0D4i6OYMtAhEJGuC3thxBA9XoFyhwdtw mGZeCyPRSD6QuyuKR7deuOEYrCh73NLJeonPYRra2egQJaPcElPsphv4s4vB5JpXjvde t8GQ4/NPjsZ/V35etCAygD54Tpil9FaRe5lSVsPlt9/NM8a6Jkr3oS13llieLp9+qhqp Udjw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1781282034; x=1781886834; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:x-gm-gg:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=gaALrUtMzS13T301LDMZjCtTFcOTia8kl+f7FBSPKoE=; b=plUM9X3HiVMRtdTV2HTmqH2mRk11P6veJw74NZWvbeQlWTzsoaiAK8rIAFBcZ0W6yr kAia/dRIP2FvaAIr0NDdwS8Vs6gjIJ/Ptj7qEV8jk8MqUSVXFS1819uGigyEdxuYJAis obYutPKZSu1Ryt0elXeRZzWRS4bkOEBqT8pTtOxmsfIHcmNHogn6eZbZIVdSd/m0koqT k2jmnObHfeuV41FmuS/KNwxkTyC/bYbS0EcZHHJU1Zf8diQEYTNYcEPvvs8zBcCpE3Ep Qz6OWrgice3McNABwzYMfGkKSIytRfBcbIxHhJLVQmOq49t+PnFYI+bvtYX8z8YzRvKP za5g== X-Forwarded-Encrypted: i=1; AFNElJ+ehTcEUDCBAxUDo6dfjkBXSB1B5UzxUENfh3Z05bUxxmqs3REMC2T+evdRPY6gDqGYPujfHTYqqwM7LME=@vger.kernel.org X-Gm-Message-State: AOJu0Yw3F9GmtXTs8Q7w+R9pTJNj1jEizMvagRZfaqHs65f7IbWrWIIV SK0dObrjUXeNCRBpLB7QBWloPuU+qwWYu7NA7CDvXMXDVwhjCbWOTmjqVBdKMUZZEUoCojm0EQM a8Bh7gDw= X-Gm-Gg: Acq92OGyZJ7WKq2ptScPDtpndo+ciowp58BjWfRGq11JM+pisIVnGAztMVdCnlGngbu Ku6hCqRYMxLxOzlMejQwsJsQs1YG01wU/isG3OLN8uuAkA8mNLMHTcWSS7ItcZDbaJ1Ue+oX/Ig KYSKBa6y6lGMgkybo/4xivOw6OJTpwlcCnROXDpL5Wly7yO+4DgMkD6T4+AVKryVbK+fSSl60JA WtVnMcD0U7/85qT8C75T7EwCxKZ7zq0GwkKlgQ0N1vXY271f8YtxWM1FeC85ZSZvYK0Dnda6N8r DkYSokxTSPmand806G3FyMJjbMe5ohDv0Ng1Iw2q5ke19RRnwzDSDGOhF+nX05UzjYfzUnND2fk mTyAIrbwV/JF+faNDnnVA7BAHZspmEM3YLhBXc74hhiktkwYBB53kI/nHnh8XwfFHa6x40IdA44 vdMLSopNpFbLIAfskTMKO/mg== X-Received: by 2002:a05:622a:60e:b0:517:74f2:e578 with SMTP id d75a77b69052e-517fbcb0132mr51491051cf.12.1781282034506; Fri, 12 Jun 2026 09:33:54 -0700 (PDT) Received: from localhost ([2603:7001:f100:500:365a:60ff:fe62:ff29]) by smtp.gmail.com with ESMTPSA id d75a77b69052e-517fb642541sm25722601cf.10.2026.06.12.09.33.53 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 12 Jun 2026 09:33:53 -0700 (PDT) Date: Fri, 12 Jun 2026 12:33:52 -0400 From: Johannes Weiner To: Brendan Jackman Cc: Andrew Morton , Vlastimil Babka , Suren Baghdasaryan , Michal Hocko , Zi Yan , "Harry Yoo (Oracle)" , Gregory Price , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] mm/page_alloc: drop flag-conversion "optimisation" Message-ID: References: <20260612-gfp-pessimisation-v1-1-936eb04202e7@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20260612-gfp-pessimisation-v1-1-936eb04202e7@google.com> On Fri, Jun 12, 2026 at 02:15:44PM +0000, Brendan Jackman wrote: > This code uses flag equivalences to try to optimise conversion from > GFP_ to ALLOC_ but there's no clear reason to believe it makes things > faster. Even if it gets rid of conditional branches, it just trades them > for a data dependency. > > CPUs are pretty good at conditional branches. But, in my GCC x86 build > it doesn't look like there are any branches anyway, the compiler found > some conditional instruction tricks. (Caveat: This was extracted & > annotated by Gemini AI, I did not actually read the disasm myself) > > Old code: > > ae50: 8b 04 24 mov (%rsp),%eax # Load gfp_mask > ... > ae5d: 41 89 c4 mov %eax,%r12d > ae64: 41 81 e4 20 08 00 00 and $0x820,%r12d # Mask both flags at once > ... > ae6f: 44 89 e1 mov %r12d,%ecx > ae77: 83 c9 40 or $0x40,%ecx # OR with ALLOC_CPUSET (0x40) > ae7a: 89 4c 24 60 mov %ecx,0x60(%rsp) # Store to alloc_flags > > New code: > > For __GFP_HIGH ( 0x20 ): > It uses the Carry Flag (via sbb ) to conditionally add 0x20 to the base 0x40 ( ALLOC_CPUSET ) flag: > > ae63: 83 e0 20 and $0x20,%eax # Test __GFP_HIGH > ... > ae6a: 83 f8 01 cmp $0x1,%eax # Set carry flag if 0 > ae6f: 45 19 e4 sbb %r12d,%r12d # %r12d = (gfp & 0x20) ? 0 : -1 > ae80: 41 83 e4 e0 and $0xffffffe0,%r12d # %r12d = (gfp & 0x20) ? 0 : -32 > ae87: 41 83 c4 60 add $0x60,%r12d # %r12d = (gfp & 0x20) ? 0x60 : 0x40 > > For __GFP_KSWAPD_RECLAIM ( 0x800 ): > It uses a conditional move ( cmov ) later in the function to set the ALLOC_KSWAPD ( 0x800 ) bit: > > ae72: 25 00 08 00 00 and $0x800,%eax # Test __GFP_KSWAPD_RECLAIM > ae77: 89 44 24 30 mov %eax,0x30(%rsp) # Store result > ... > af2c: 80 cf 08 or $0x8,%bh # Set ALLOC_KSWAPD (0x800) in temp reg > af2f: 45 85 c9 test %r9d,%r9d # Check if __GFP_KSWAPD_RECLAIM was set > af32: 0f 44 d8 cmove %eax,%ebx # If not, revert to flags without it > > Testing with a modified version[0] of lib/free_pages_test.c (adding > printks with timing)... > > [0] https://github.com/bjackman/aethelred/blob/2ccdc84ef087c2a631914f58e106e99e19bd3b98/page-alloc-test/page-alloc-test.c > > Old results from a Sapphire Rapids consumer CPU: > > [ 67.157118] page_alloc_test: Testing with GFP_KERNEL > [ 67.157122] page_alloc_test: Starting 1,000,000 allocations... > [ 70.704446] page_alloc_test: Completed. Time: 3543002 us (Avg: 3543.00 ns per alloc+free loop) > [ 70.704456] page_alloc_test: Testing with GFP_KERNEL | __GFP_COMP > [ 70.704460] page_alloc_test: Starting 1,000,000 allocations... > [ 70.944672] page_alloc_test: Completed. Time: 239980 us (Avg: 239.98 ns per alloc+free loop) > [ 70.944675] page_alloc_test: Test completed > > New results: > > [ 70.079015] page_alloc_test: Testing with GFP_KERNEL > [ 70.079020] page_alloc_test: Starting 1,000,000 allocations... > [ 73.669396] page_alloc_test: Completed. Time: 3586954 us (Avg: 3586.95 ns per alloc+free loop) > [ 73.669402] page_alloc_test: Testing with GFP_KERNEL | __GFP_COMP > [ 73.669405] page_alloc_test: Starting 1,000,000 allocations... > [ 73.905084] page_alloc_test: Completed. Time: 235496 us (Avg: 235.49 ns per alloc+free loop) > [ 73.905086] page_alloc_test: Test completed > > Seems like a wash. > > So, drop the flag value coupling here and let the compiler and CPU do > their job. Superscalar CPUs are pretty neat after all. > > (Used AI for the disasm but the rest is all manual). > > Signed-off-by: Brendan Jackman Nice. With the _nofragment() bits folded: Acked-by: Johannes Weiner