From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id C097845F20; Mon, 23 Dec 2024 11:36:35 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 3F4A540A84; Mon, 23 Dec 2024 11:36:33 +0100 (CET) Received: from mail-lj1-f172.google.com (mail-lj1-f172.google.com [209.85.208.172]) by mails.dpdk.org (Postfix) with ESMTP id 9382E4025F for ; Thu, 19 Dec 2024 21:53:26 +0100 (CET) Received: by mail-lj1-f172.google.com with SMTP id 38308e7fff4ca-30219437e63so23749081fa.1 for ; Thu, 19 Dec 2024 12:53:26 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1734641606; x=1735246406; darn=dpdk.org; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=bKsT618tRkKughgRkGINW2hkFHhgHucD78i+Cwhmc8U=; b=jVkX3+j0QgrbSoNPeVfW27Nvq/ZpuuPXn8oyK6b5zBJxE35ZgMsB9nrEM0xsickEEq F8VAbNBIlMli/1jlqWQt0UczUuSYb1hiPe4oSkw/71sX00yt/Q/cw7Ufw7X8jh9tbQWO /zkqFWZbnHtiVkvWs61MlYTUgIm1IMu35tgcdbMe1gJ+JFFoGlfbFTRQsy08AD3AOgTJ 0dboYm6BxVQoidvzwHLWOSDoGBYDa4KSwRMuNoxAa4M2jyRPnAhpKxdZ0SC89hsFJ1x5 EB4Rm6eq5JaPH9DDS0GmQ5Rr2U5UxMfR4dWeGpgOKg40uue8kr9Mo9UtpwgfDKSZ69xx 5LtQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1734641606; x=1735246406; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=bKsT618tRkKughgRkGINW2hkFHhgHucD78i+Cwhmc8U=; b=jHo7YnhuRIjVdWfbcwo/OKRM25fwMC5g4GyXHkBoxtNsyHxtGx8SrxnE/JG5sxkpIu 8oLG+JRXF5qpH3sAthWJD9u/pa+4svGK5NF1TsxnjeGlUq4/MYO2g9ZE8kdvpuGzT0wu nXL93/rsagM9fIJIZUvnsN20ZmHgMI4eLTNepTqL3r+NZipnGgeWR9qOPQq0N1dWZa1G lQAJE9EIoz7PmfTtmEE2hScpVkpd6uzjyMiSsH+mE12Y+RnN7xU+4TMOSQ+nz+GTp447 NKWdAjh02Drx+hRW010z4T/XsElOHbAwWOuHbJBqJPubPhhstFnOcO3hYNKFnWCKx1XF hydA== X-Forwarded-Encrypted: i=1; AJvYcCVs4udbgAPHhgDyYWLiW0aMJIIWIXNSyeepdbCHsEwt/y80cKIErI62s7H52rYKhRXcTxM=@dpdk.org X-Gm-Message-State: AOJu0YzjywfEFgnge5VEgJa0+GN79+BFSwL6oF7/5K8zNgrtpg/wPEr1 lk6+LRxft+cLAgzg5la/Esm9j+6ipiixrsFp2EsO9eoVHOsxQYG4ZiDOjqzkHt6AyFF4x6s98wi P2tohx2rOIZT+ld+d7kFBNn0TmEd3Q5PJ7ynn X-Gm-Gg: ASbGncvAIx93L8GfPBgDT13HWfxYurB2owR4eeuTKrOGvK9EKhVdeZWCSiY3glNqq3L 6pzjl/756LuhyJk1jh36BZ709J8oeuI3SrBKrTLUc64xNmzwe66N42DuFbI5NZFnMJvyC X-Google-Smtp-Source: AGHT+IGaWFhenfUcaq9Iag3JZTEXQvExXQrT/tWFMcAvbIpMgweYZWrZDAuxxTZwXUww3ooelKTgAx4ub03+tQDHKy4= X-Received: by 2002:a05:6512:b0f:b0:541:55e6:2012 with SMTP id 2adb3069b0e04-542212e1053mr1566856e87.8.1734641605675; Thu, 19 Dec 2024 12:53:25 -0800 (PST) MIME-Version: 1.0 References: <20241218234635.2009033-1-joshwash@google.com> <20241218195140.60a1f58b@hermes.local> In-Reply-To: <20241218195140.60a1f58b@hermes.local> From: Praveen Kaligineedi Date: Thu, 19 Dec 2024 12:53:14 -0800 Message-ID: Subject: Re: [PATCH] net/gve: Allocate qpl pages using malloc if memzone allocation fails To: stephen@networkplumber.org Cc: Joshua Washington , Jeroen de Borst , Rushil Gupta , dev@dpdk.org, Ferruh Yigit , Praveen Kaligineedi Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Mon, 23 Dec 2024 11:36:30 +0100 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org The TX queue requires IOVA contiguous QPL memory. So, we still need memzone code for TX queues. Regards, Praveen On Wed, Dec 18, 2024 at 7:51=E2=80=AFPM Stephen Hemminger wrote: > > On Wed, 18 Dec 2024 15:46:35 -0800 > Joshua Washington wrote: > > > From: Praveen Kaligineedi > > > > Allocating QPL for an RX queue might fail if enough contiguous IOVA > > memory cannot be allocated. However, the only requirement for QPL > > for RX is that each 4K buffer be IOVA contiguous, not the entire > > QPL. Therefore, use malloc to allocate 4K buffers if the allocation > > using memzone fails. > > > > Signed-off-by: Praveen Kaligineedi > > Reviewed-by: Joshua Washington > > --- > > Why keep the memzone code? rte_malloc and memzone are both coming from > huge pages. Is there any advantage to memzone for what you are doing? > > Better to not have two potential allocation paths to test.