From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935474AbYD1R2P (ORCPT ); Mon, 28 Apr 2008 13:28:15 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932919AbYD1R1h (ORCPT ); Mon, 28 Apr 2008 13:27:37 -0400 Received: from mga14.intel.com ([143.182.124.37]:37560 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932487AbYD1R1e (ORCPT ); Mon, 28 Apr 2008 13:27:34 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.25,717,1199692800"; d="scan'208";a="238983824" From: PJ Waskiewicz Subject: [PATCH] ARCH 2.6.24.y: Fix 32-bit x86 MSI-X allocation leakage To: stable@kernel.org, linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Date: Fri, 25 Apr 2008 17:59:51 -0700 Message-ID: <20080426005950.7155.44626.stgit@scrappy.jf.intel.com> User-Agent: StGIT/0.14.1 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 28 Apr 2008 17:27:31.0765 (UTC) FILETIME=[23C77E50:01C8A955] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This bug was introduced in the 2.6.24 i386/x86_64 tree merge, where MSI-X vector allocation will eventually fail. The cause is the new bit array tracking used vectors is not getting cleared properly on IRQ destruction on the 32-bit APIC code. This can be seen easily using the ixgbe 10 GbE driver on multi-core systems by simply loading and unloading the driver a few times. Depending on the number of available vectors on the host system, the MSI-X allocation will eventually fail, and the driver will only be able to use legacy interrupts. Signed-off-by: Peter P Waskiewicz Jr --- arch/x86/kernel/io_apic_32.c | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index 232fdeb..9994c52 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -2478,6 +2478,7 @@ void destroy_irq(unsigned int irq) dynamic_irq_cleanup(irq); spin_lock_irqsave(&vector_lock, flags); + clear_bit(irq_vector[irq], used_vectors); irq_vector[irq] = 0; spin_unlock_irqrestore(&vector_lock, flags); }