linux/arch/powerpc/sysdev, branch v3.6.4

powerpc/iommu: Fix multiple issues with IOMMU pools code

2012-10-12T20:50:17Z

commit d900bd7366463fd96a907b2c212242e2b68b27d8 upstream. There are a number of issues in the recent IOMMU pools code: - On a preempt kernel we might switch CPUs in the middle of building a scatter gather list. When this happens the handle hint passed in no longer falls within the local CPU's pool. Check for this and fall back to the pool hint. - We were missing a spin_unlock/spin_lock in one spot where we switch pools. - We need to provide locking around dart_tlb_invalidate_all and dart_tlb_invalidate_one now that the global lock is gone. Reported-by: Alexander Graf Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Greg Kroah-Hartman

powerpc: Make sure IPI handlers see data written by IPI senders

2012-09-05T06:05:22Z

We have been observing hangs, both of KVM guest vcpu tasks and more generally, where a process that is woken doesn't properly wake up and continue to run, but instead sticks in TASK_WAKING state. This happens because the update of rq->wake_list in ttwu_queue_remote() is not ordered with the update of ipi_message in smp_muxed_ipi_message_pass(), and the reading of rq->wake_list in scheduler_ipi() is not ordered with the reading of ipi_message in smp_ipi_demux(). Thus it is possible for the IPI receiver not to see the updated rq->wake_list and therefore conclude that there is nothing for it to do. In order to make sure that anything done before smp_send_reschedule() is ordered before anything done in the resulting call to scheduler_ipi(), this adds barriers in smp_muxed_message_pass() and smp_ipi_demux(). The barrier in smp_muxed_message_pass() is a full barrier to ensure that there is a full ordering between the smp_send_reschedule() caller and scheduler_ipi(). In smp_ipi_demux(), we use xchg() rather than xchg_local() because xchg() includes release and acquire barriers. Using xchg() rather than xchg_local() makes sense given that ipi_message is not just accessed locally. This moves the barrier between setting the message and calling the cause_ipi() function into the individual cause_ipi implementations. Most of them -- those that used outb, out_8 or similar -- already had a full barrier because out_8 etc. include a sync before the MMIO store. This adds an explicit barrier in the two remaining cases. These changes made no measurable difference to the speed of IPIs as measured using a simple ping-pong latency test across two CPUs on different cores of a POWER7 machine. The analysis of the reason why processes were not waking up properly is due to Milton Miller. Cc: stable@vger.kernel.org # v3.0+ Reported-by: Milton Miller Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt

powerpc/mpic_msgr: Add missing includes

2012-08-24T10:26:04Z

Add several #includes that mpic_msgr relies on being pulled implicitly, which only happens on certain configs. Signed-off-by: Scott Wood Cc: Meador Inge Cc: Jia Hongtao Signed-off-by: Benjamin Herrenschmidt

powerpc/fsl-pci: Only scan PCI bus if configured as a host

2012-08-03T13:25:52Z

We change fsl_add_bridge to return -ENODEV if the controller is working in agent mode. Then check the return value of fsl_add_bridge to guarantee that only successfully added host bus will be scanned. Signed-off-by: Jia Hongtao Signed-off-by: Li Yang Signed-off-by: Kumar Gala

Merge tag 'irqdomain-for-linus' of git://git.secretlab.ca/git/linux-2.6

2012-08-01T03:44:03Z

Pull irqdomain changes from Grant Likely: "Round of refactoring and enhancements to irq_domain infrastructure. This series starts the process of simplifying irqdomain. The ultimate goal is to merge LEGACY, LINEAR and TREE mappings into a single system, but had to back off from that after some last minute bugs. Instead it mainly reorganizes the code and ensures that the reverse map gets populated when the irq is mapped instead of the first time it is looked up. Merging of the irq_domain types is deferred to v3.7 In other news, this series adds helpers for creating static mappings on a linear or tree mapping." * tag 'irqdomain-for-linus' of git://git.secretlab.ca/git/linux-2.6: irqdomain: Improve diagnostics when a domain mapping fails irqdomain: eliminate slow-path revmap lookups irqdomain: Fix irq_create_direct_mapping() to test irq_domain type. irqdomain: Eliminate dedicated radix lookup functions irqdomain: Support for static IRQ mapping and association. irqdomain: Always update revmap when setting up a virq irqdomain: Split disassociating code into separate function irq_domain: correct a minor wrong comment for linear revmap irq_domain: Standardise legacy/linear domain selection irqdomain: Make ops->map hook optional irqdomain: Remove unnecessary test for IRQ_DOMAIN_MAP_LEGACY irqdomain: Simple NUMA awareness. devicetree: add helper inline for retrieving a node's full name

Merge remote-tracking branch 'kumar/merge' into merge

2012-07-31T05:18:31Z

Kumar says: "A few patches that missed the initial 3.6 window. These are bug fixes at this point."

powerpc/85xx: Fix sram_offset parameter type

2012-07-26T18:24:32Z

The sram_offset parameter represents a physical address and should be of type phys_addr_t. As part of this fix, the extraction of sram_params is being cleaned-up and fixed. This patch fixes now the case when the offset value of 0xfff00000 was being rejected by the driver (returning -EINVAL), although this is a valid offset value. Signed-off-by: Tang Yuantian Signed-off-by: Claudiu Manoil Signed-off-by: Kumar Gala

Merge remote-tracking branch 'origin' into irqdomain/next

2012-07-25T04:34:40Z

Merge tag 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

2012-07-24T23:17:07Z

Pull PCI changes from Bjorn Helgaas: "Host bridge hotplug: - Add MMCONFIG support for hot-added host bridges (Jiang Liu) Device hotplug: - Move fixups from __init to __devinit (Sebastian Andrzej Siewior) - Call FINAL fixups for hot-added devices, too (Myron Stowe) - Factor out generic code for P2P bridge hot-add (Yinghai Lu) - Remove all functions in a slot, not just those with _EJx (Amos Kong) Dynamic resource management: - Track bus number allocation (struct resource tree per domain) (Yinghai Lu) - Make P2P bridge 1K I/O windows work with resource reassignment (Bjorn Helgaas, Yinghai Lu) - Disable decoding while updating 64-bit BARs (Bjorn Helgaas) Power management: - Add PCIe runtime D3cold support (Huang Ying) Virtualization: - Add VFIO infrastructure (ACS, DMA source ID quirks) (Alex Williamson) - Add quirks for devices with broken INTx masking (Jan Kiszka) Miscellaneous: - Fix some PCI Express capability version issues (Myron Stowe) - Factor out some arch code with a weak, generic, pcibios_setup() (Myron Stowe)" * tag 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (122 commits) PCI: hotplug: ensure a consistent return value in error case PCI: fix undefined reference to 'pci_fixup_final_inited' PCI: build resource code for M68K architecture PCI: pciehp: remove unused pciehp_get_max_lnk_width(), pciehp_get_cur_lnk_width() PCI: reorder __pci_assign_resource() (no change) PCI: fix truncation of resource size to 32 bits PCI: acpiphp: merge acpiphp_debug and debug PCI: acpiphp: remove unused res_lock sparc/PCI: replace pci_cfg_fake_ranges() with pci_read_bridge_bases() PCI: call final fixups hot-added devices PCI: move final fixups from __init to __devinit x86/PCI: move final fixups from __init to __devinit MIPS/PCI: move final fixups from __init to __devinit PCI: support sizing P2P bridge I/O windows with 1K granularity PCI: reimplement P2P bridge 1K I/O windows (Intel P64H2) PCI: disable MEM decoding while updating 64-bit MEM BARs PCI: leave MEM and IO decoding disabled during 64-bit BAR sizing, too PCI: never discard enable/suspend/resume_early/resume fixups PCI: release temporary reference in __nv_msi_ht_cap_quirk() PCI: restructure 'pci_do_fixups()' ...

powerpc/mpic: Create a revmap with enough entries for IPIs and timers

2012-07-23T04:20:42Z

The current mpic code creates a linear revmap just big enough for all the sources, which happens to miss the IPIs and timers on some machines. This will in turn break when the irqdomain code loses the fallback of doing a linear search when the revmap fails (and really slows down IPIs otherwise). This happens for example on the U4 based Apple machines such as the dual core PowerMac G5s. Signed-off-by: Benjamin Herrenschmidt