From: AMEET M. PARANJAPE <aparanja@redhat.com> Date: Tue, 31 Mar 2009 11:05:36 -0400 Subject: [ppc] reject discontiguous MSI-X requests Message-id: 20090331150323.14954.43782.sendpatchset@squad5-lp1.lab.bos.redhat.com O-Subject: [PATCH RHEL5.4 BZ492580 8/8] Bugzilla: 492580 RH-Acked-by: David Howells <dhowells@redhat.com> RHBZ#: ====== https://bugzilla.redhat.com/show_bug.cgi?id=492580 Description: =========== There's no way for us to express to firmware that we want a discontiguous, or non-zero based, range of MSI-X entries. So we must reject such requests. RHEL Version Found: ================ RHEL 5.3 kABI Status: ============ No symbols were harmed. Brew: ===== Built on all platforms. http://brewweb.devel.redhat.com/brew/taskinfo?taskID=1744271 Upstream Status: ================ http://git.kernel.org/?p=linux/kernel/git/benh/powerpc.git;a=commit;h=94afa5a5f54235c4612198768b6a2fa2e2366f44 Test Status: ============ There is a testcase provided in the Bugzilla. A 'cat /proc/interrupts' should show the device drivers has two interrupt entries for each port. Run I/O tests. Then 'lspci -vv' should display the correct pci capabilities for the installed adapter and show the adapter is using MSI-X interrupts opposed to MSO or LSI interrupts. =============================================================== Ameet Paranjape 978-392-3903 ext 23903 IBM on-site partner Proposed Patch: =============== diff --git a/arch/powerpc/kernel/msi-rtas.c b/arch/powerpc/kernel/msi-rtas.c index 9de7a33..270caa8 100644 --- a/arch/powerpc/kernel/msi-rtas.c +++ b/arch/powerpc/kernel/msi-rtas.c @@ -357,6 +357,27 @@ static int rtas_msi_check_device(struct pci_dev *pdev, int nvec, int type) return 0; } +static int check_msix_entries(struct pci_dn *pdn) +{ + struct msi_desc *entry; + int expected; + + /* There's no way for us to express to firmware that we want + * a discontiguous, or non-zero based, range of MSI-X entries. + * So we must reject such requests. */ + + expected = 0; + list_for_each_entry(entry, &pdn->msi_list, list) { + if (entry->msi_attrib.entry_nr != expected) { + pr_debug("rtas_msi: bad MSI-X entries.\n"); + return -EINVAL; + } + expected++; + } + + return 0; +} + static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct pci_dn *pdn; @@ -368,6 +389,9 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) if (!pdn) return -ENODEV; + if (type == PCI_CAP_ID_MSIX && check_msix_entries(pdev)) + return -EINVAL; + /* * Try the new more explicit firmware interface, if that fails fall * back to the old interface. The old interface is known to never