From 3f3f67cbf64227fc9c06113585d9570baddc9bcd Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Mon, 9 May 2016 13:48:27 +0200 Subject: PCI: Add DT binding for Axis ARTPEC-6 PCIe controller Add the Device Tree binding documentation that allows to describe the PCIe controller found in the Axis ARTPEC-6 SoC. Signed-off-by: Niklas Cassel Signed-off-by: Bjorn Helgaas Acked-by: Rob Herring --- .../devicetree/bindings/pci/axis,artpec6-pcie.txt | 46 ++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt b/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt new file mode 100644 index 000000000000..330a45b5f0b5 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt @@ -0,0 +1,46 @@ +* Axis ARTPEC-6 PCIe interface + +This PCIe host controller is based on the Synopsys DesignWare PCIe IP +and thus inherits all the common properties defined in designware-pcie.txt. + +Required properties: +- compatible: "axis,artpec6-pcie", "snps,dw-pcie" +- reg: base addresses and lengths of the PCIe controller (DBI), + the phy controller, and configuration address space. +- reg-names: Must include the following entries: + - "dbi" + - "phy" + - "config" +- interrupts: A list of interrupt outputs of the controller. Must contain an + entry for each entry in the interrupt-names property. +- interrupt-names: Must include the following entries: + - "msi": The interrupt that is asserted when an MSI is received +- axis,syscon-pcie: A phandle pointing to the ARTPEC-6 system controller, + used to enable and control the Synopsys IP. + +Example: + + pcie@f8050000 { + compatible = "axis,artpec6-pcie", "snps,dw-pcie"; + reg = <0xf8050000 0x2000 + 0xf8040000 0x1000 + 0xc0000000 0x1000>; + reg-names = "dbi", "phy", "config"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + /* downstream I/O */ + ranges = <0x81000000 0 0x00010000 0xc0010000 0 0x00010000 + /* non-prefetchable memory */ + 0x82000000 0 0xc0020000 0xc0020000 0 0x1ffe0000>; + num-lanes = <2>; + interrupts = ; + interrupt-names = "msi"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0x7>; + interrupt-map = <0 0 0 1 &intc GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>; + axis,syscon-pcie = <&syscon>; + }; -- cgit v1.2.3 From 9d26d3a8f1b0c442339a235f9508bdad8af91043 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 2 Jun 2016 11:17:12 +0300 Subject: PCI: Put PCIe ports into D3 during suspend Currently the Linux PCI core does not touch power state of PCI bridges and PCIe ports when system suspend is entered. Leaving them in D0 consumes power unnecessarily and may prevent the CPU from entering deeper C-states. With recent PCIe hardware we can power down the ports to save power given that we take into account few restrictions: - The PCIe port hardware is recent enough, starting from 2015. - Devices connected to PCIe ports are effectively in D3cold once the port is transitioned to D3 (the config space is not accessible anymore and the link may be powered down). - Devices behind the PCIe port need to be allowed to transition to D3cold and back. There is a way both drivers and userspace can forbid this. - If the device behind the PCIe port is capable of waking the system it needs to be able to do so from D3cold. This patch adds a new flag to struct pci_device called 'bridge_d3'. This flag is set and cleared by the PCI core whenever there is a change in power management state of any of the devices behind the PCIe port. When system later on is suspended we only need to check this flag and if it is true transition the port to D3 otherwise we leave it in D0. Also provide override mechanism via command line parameter "pcie_port_pm=[off|force]" that can be used to disable or enable the feature regardless of the BIOS manufacturing date. Tested-by: Lukas Wunner Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- Documentation/kernel-parameters.txt | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82b42c958d1c..86edee4cedd4 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3047,6 +3047,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. compat Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe ports driver. + pcie_port_pm= [PCIE] PCIe port power management handling: + off Disable power management of all PCIe ports + force Forcibly enable power management of all PCIe ports + pcie_pme= [PCIE,PM] Native PCIe PME signaling options: nomsi Do not use MSI for native PCIe PME signaling (this makes all PCIe root ports use INTx for all services). -- cgit v1.2.3 From 644a544fd9bcd65f524768b85ab22f62ed08e107 Mon Sep 17 00:00:00 2001 From: "Koehrer Mathias (ETAS/ESW5)" Date: Tue, 7 Jun 2016 14:24:17 +0000 Subject: PCI: Extending pci=resource_alignment to specify device/vendor IDs Some uio-based PCI drivers, e.g., uio_cif do not work if the assigned PCI memory resources are not page aligned. By using the kernel option "pci=resource_alignment" it is possible to force single PCI boards to use page alignment for their memory resources. However, this is fairly cumbersome if several of these boards are in use as the specification of the cards has to be done via PCI bus/slot/function number which might change, e.g., by adding another board. Extend the kernel option "pci=resource_alignment" to allow specification of relevant devices via PCI device/vendor (and subdevice/subvendor) IDs. The specification of the devices via device/vendor is indicated by a leading string "pci:" as argument to "pci=resource_alignment". The format of the specification is pci::[::] Signed-off-by: Mathias Koehrer Signed-off-by: Bjorn Helgaas --- Documentation/kernel-parameters.txt | 2 ++ 1 file changed, 2 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82b42c958d1c..0618cdd5707e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2998,6 +2998,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. resource_alignment= Format: [@][:]:.[; ...] + [@]pci::\ + [::][; ...] Specifies alignment and device to reassign aligned memory resources. If is not specified, -- cgit v1.2.3 From aff171641d181ea573380efc3f559c9de4741fc5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Jul 2016 18:20:17 +0900 Subject: PCI: Provide sensible IRQ vector alloc/free routines Add a function to allocate and free a range of interrupt vectors, using MSI-X, MSI or legacy vectors (in that order) based on the capabilities of the underlying device and PCIe complex. Additionally a new helper is provided to get the Linux IRQ number for given device-relative vector so that the drivers don't need to allocate their own arrays to keep track of the vectors for the multi vector MSI-X case. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- Documentation/PCI/MSI-HOWTO.txt | 467 +++++++--------------------------------- 1 file changed, 76 insertions(+), 391 deletions(-) (limited to 'Documentation') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 1179850f453c..0ac612b8c3fb 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -78,422 +78,107 @@ CONFIG_PCI_MSI option. 4.2 Using MSI -Most of the hard work is done for the driver in the PCI layer. It simply -has to request that the PCI layer set up the MSI capability for this +Most of the hard work is done for the driver in the PCI layer. The driver +simply has to request that the PCI layer set up the MSI capability for this device. -4.2.1 pci_enable_msi +To automatically use MSI or MSI-X interrupt vectors, use the following +function: -int pci_enable_msi(struct pci_dev *dev) + int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags); -A successful call allocates ONE interrupt to the device, regardless -of how many MSIs the device supports. The device is switched from -pin-based interrupt mode to MSI mode. The dev->irq number is changed -to a new number which represents the message signaled interrupt; -consequently, this function should be called before the driver calls -request_irq(), because an MSI is delivered via a vector that is -different from the vector of a pin-based interrupt. +which allocates up to max_vecs interrupt vectors for a PCI device. It +returns the number of vectors allocated or a negative error. If the device +has a requirements for a minimum number of vectors the driver can pass a +min_vecs argument set to this limit, and the PCI core will return -ENOSPC +if it can't meet the minimum number of vectors. -4.2.2 pci_enable_msi_range +The flags argument should normally be set to 0, but can be used to pass the +PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support +MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in +case the device does not support legacy interrupt lines. -int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) +To get the Linux IRQ numbers passed to request_irq() and free_irq() and the +vectors, use the following function: -This function allows a device driver to request any number of MSI -interrupts within specified range from 'minvec' to 'maxvec'. + int pci_irq_vector(struct pci_dev *dev, unsigned int nr); -If this function returns a positive number it indicates the number of -MSI interrupts that have been successfully allocated. In this case -the device is switched from pin-based interrupt mode to MSI mode and -updates dev->irq to be the lowest of the new interrupts assigned to it. -The other interrupts assigned to the device are in the range dev->irq -to dev->irq + returned value - 1. Device driver can use the returned -number of successfully allocated MSI interrupts to further allocate -and initialize device resources. +Any allocated resources should be freed before removing the device using +the following function: -If this function returns a negative number, it indicates an error and -the driver should not attempt to request any more MSI interrupts for -this device. + void pci_free_irq_vectors(struct pci_dev *dev); -This function should be called before the driver calls request_irq(), -because MSI interrupts are delivered via vectors that are different -from the vector of a pin-based interrupt. +If a device supports both MSI-X and MSI capabilities, this API will use the +MSI-X facilities in preference to the MSI facilities. MSI-X supports any +number of interrupts between 1 and 2048. In contrast, MSI is restricted to +a maximum of 32 interrupts (and must be a power of two). In addition, the +MSI interrupt vectors must be allocated consecutively, so the system might +not be able to allocate as many vectors for MSI as it could for MSI-X. On +some platforms, MSI interrupts must all be targeted at the same set of CPUs +whereas MSI-X interrupts can all be targeted at different CPUs. -It is ideal if drivers can cope with a variable number of MSI interrupts; -there are many reasons why the platform may not be able to provide the -exact number that a driver asks for. +If a device supports neither MSI-X or MSI it will fall back to a single +legacy IRQ vector. -There could be devices that can not operate with just any number of MSI -interrupts within a range. See chapter 4.3.1.3 to get the idea how to -handle such devices for MSI-X - the same logic applies to MSI. +The typical usage of MSI or MSI-X interrupts is to allocate as many vectors +as possible, likely up to the limit supported by the device. If nvec is +larger than the number supported by the device it will automatically be +capped to the supported limit, so there is no need to query the number of +vectors supported beforehand: -4.2.1.1 Maximum possible number of MSI interrupts - -The typical usage of MSI interrupts is to allocate as many vectors as -possible, likely up to the limit returned by pci_msi_vec_count() function: - -static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) -{ - return pci_enable_msi_range(pdev, 1, nvec); -} - -Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, -the value of 0 would be meaningless and could result in error. - -Some devices have a minimal limit on number of MSI interrupts. -In this case the function could look like this: - -static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) -{ - return pci_enable_msi_range(pdev, FOO_DRIVER_MINIMUM_NVEC, nvec); -} - -4.2.1.2 Exact number of MSI interrupts + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + if (nvec < 0) + goto out_err; If a driver is unable or unwilling to deal with a variable number of MSI -interrupts it could request a particular number of interrupts by passing -that number to pci_enable_msi_range() function as both 'minvec' and 'maxvec' -parameters: - -static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) -{ - return pci_enable_msi_range(pdev, nvec, nvec); -} - -Note, unlike pci_enable_msi_exact() function, which could be also used to -enable a particular number of MSI-X interrupts, pci_enable_msi_range() -returns either a negative errno or 'nvec' (not negative errno or 0 - as -pci_enable_msi_exact() does). - -4.2.1.3 Single MSI mode - -The most notorious example of the request type described above is -enabling the single MSI mode for a device. It could be done by passing -two 1s as 'minvec' and 'maxvec': - -static int foo_driver_enable_single_msi(struct pci_dev *pdev) -{ - return pci_enable_msi_range(pdev, 1, 1); -} - -Note, unlike pci_enable_msi() function, which could be also used to -enable the single MSI mode, pci_enable_msi_range() returns either a -negative errno or 1 (not negative errno or 0 - as pci_enable_msi() -does). - -4.2.3 pci_enable_msi_exact - -int pci_enable_msi_exact(struct pci_dev *dev, int nvec) - -This variation on pci_enable_msi_range() call allows a device driver to -request exactly 'nvec' MSIs. - -If this function returns a negative number, it indicates an error and -the driver should not attempt to request any more MSI interrupts for -this device. - -By contrast with pci_enable_msi_range() function, pci_enable_msi_exact() -returns zero in case of success, which indicates MSI interrupts have been -successfully allocated. - -4.2.4 pci_disable_msi - -void pci_disable_msi(struct pci_dev *dev) - -This function should be used to undo the effect of pci_enable_msi_range(). -Calling it restores dev->irq to the pin-based interrupt number and frees -the previously allocated MSIs. The interrupts may subsequently be assigned -to another device, so drivers should not cache the value of dev->irq. - -Before calling this function, a device driver must always call free_irq() -on any interrupt for which it previously called request_irq(). -Failure to do so results in a BUG_ON(), leaving the device with -MSI enabled and thus leaking its vector. - -4.2.4 pci_msi_vec_count - -int pci_msi_vec_count(struct pci_dev *dev) - -This function could be used to retrieve the number of MSI vectors the -device requested (via the Multiple Message Capable register). The MSI -specification only allows the returned value to be a power of two, -up to a maximum of 2^5 (32). - -If this function returns a negative number, it indicates the device is -not capable of sending MSIs. - -If this function returns a positive number, it indicates the maximum -number of MSI interrupt vectors that could be allocated. - -4.3 Using MSI-X - -The MSI-X capability is much more flexible than the MSI capability. -It supports up to 2048 interrupts, each of which can be controlled -independently. To support this flexibility, drivers must use an array of -`struct msix_entry': - -struct msix_entry { - u16 vector; /* kernel uses to write alloc vector */ - u16 entry; /* driver uses to specify entry */ -}; - -This allows for the device to use these interrupts in a sparse fashion; -for example, it could use interrupts 3 and 1027 and yet allocate only a -two-element array. The driver is expected to fill in the 'entry' value -in each element of the array to indicate for which entries the kernel -should assign interrupts; it is invalid to fill in two entries with the -same number. - -4.3.1 pci_enable_msix_range - -int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, - int minvec, int maxvec) - -Calling this function asks the PCI subsystem to allocate any number of -MSI-X interrupts within specified range from 'minvec' to 'maxvec'. -The 'entries' argument is a pointer to an array of msix_entry structs -which should be at least 'maxvec' entries in size. - -On success, the device is switched into MSI-X mode and the function -returns the number of MSI-X interrupts that have been successfully -allocated. In this case the 'vector' member in entries numbered from -0 to the returned value - 1 is populated with the interrupt number; -the driver should then call request_irq() for each 'vector' that it -decides to use. The device driver is responsible for keeping track of the -interrupts assigned to the MSI-X vectors so it can free them again later. -Device driver can use the returned number of successfully allocated MSI-X -interrupts to further allocate and initialize device resources. - -If this function returns a negative number, it indicates an error and -the driver should not attempt to allocate any more MSI-X interrupts for -this device. - -This function, in contrast with pci_enable_msi_range(), does not adjust -dev->irq. The device will not generate interrupts for this interrupt -number once MSI-X is enabled. - -Device drivers should normally call this function once per device -during the initialization phase. - -It is ideal if drivers can cope with a variable number of MSI-X interrupts; -there are many reasons why the platform may not be able to provide the -exact number that a driver asks for. - -There could be devices that can not operate with just any number of MSI-X -interrupts within a range. E.g., an network adapter might need let's say -four vectors per each queue it provides. Therefore, a number of MSI-X -interrupts allocated should be a multiple of four. In this case interface -pci_enable_msix_range() can not be used alone to request MSI-X interrupts -(since it can allocate any number within the range, without any notion of -the multiple of four) and the device driver should master a custom logic -to request the required number of MSI-X interrupts. - -4.3.1.1 Maximum possible number of MSI-X interrupts - -The typical usage of MSI-X interrupts is to allocate as many vectors as -possible, likely up to the limit returned by pci_msix_vec_count() function: - -static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) -{ - return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, - 1, nvec); -} - -Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, -the value of 0 would be meaningless and could result in error. - -Some devices have a minimal limit on number of MSI-X interrupts. -In this case the function could look like this: - -static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) -{ - return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, - FOO_DRIVER_MINIMUM_NVEC, nvec); -} - -4.3.1.2 Exact number of MSI-X interrupts - -If a driver is unable or unwilling to deal with a variable number of MSI-X -interrupts it could request a particular number of interrupts by passing -that number to pci_enable_msix_range() function as both 'minvec' and 'maxvec' -parameters: - -static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) -{ - return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, - nvec, nvec); -} - -Note, unlike pci_enable_msix_exact() function, which could be also used to -enable a particular number of MSI-X interrupts, pci_enable_msix_range() -returns either a negative errno or 'nvec' (not negative errno or 0 - as -pci_enable_msix_exact() does). - -4.3.1.3 Specific requirements to the number of MSI-X interrupts - -As noted above, there could be devices that can not operate with just any -number of MSI-X interrupts within a range. E.g., let's assume a device that -is only capable sending the number of MSI-X interrupts which is a power of -two. A routine that enables MSI-X mode for such device might look like this: - -/* - * Assume 'minvec' and 'maxvec' are non-zero - */ -static int foo_driver_enable_msix(struct foo_adapter *adapter, - int minvec, int maxvec) -{ - int rc; - - minvec = roundup_pow_of_two(minvec); - maxvec = rounddown_pow_of_two(maxvec); - - if (minvec > maxvec) - return -ERANGE; - -retry: - rc = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, - maxvec, maxvec); - /* - * -ENOSPC is the only error code allowed to be analyzed - */ - if (rc == -ENOSPC) { - if (maxvec == 1) - return -ENOSPC; - - maxvec /= 2; - - if (minvec > maxvec) - return -ENOSPC; - - goto retry; - } - - return rc; -} - -Note how pci_enable_msix_range() return value is analyzed for a fallback - -any error code other than -ENOSPC indicates a fatal error and should not -be retried. - -4.3.2 pci_enable_msix_exact - -int pci_enable_msix_exact(struct pci_dev *dev, - struct msix_entry *entries, int nvec) - -This variation on pci_enable_msix_range() call allows a device driver to -request exactly 'nvec' MSI-Xs. - -If this function returns a negative number, it indicates an error and -the driver should not attempt to allocate any more MSI-X interrupts for -this device. - -By contrast with pci_enable_msix_range() function, pci_enable_msix_exact() -returns zero in case of success, which indicates MSI-X interrupts have been -successfully allocated. - -Another version of a routine that enables MSI-X mode for a device with -specific requirements described in chapter 4.3.1.3 might look like this: - -/* - * Assume 'minvec' and 'maxvec' are non-zero - */ -static int foo_driver_enable_msix(struct foo_adapter *adapter, - int minvec, int maxvec) -{ - int rc; - - minvec = roundup_pow_of_two(minvec); - maxvec = rounddown_pow_of_two(maxvec); - - if (minvec > maxvec) - return -ERANGE; - -retry: - rc = pci_enable_msix_exact(adapter->pdev, - adapter->msix_entries, maxvec); - - /* - * -ENOSPC is the only error code allowed to be analyzed - */ - if (rc == -ENOSPC) { - if (maxvec == 1) - return -ENOSPC; - - maxvec /= 2; - - if (minvec > maxvec) - return -ENOSPC; - - goto retry; - } else if (rc < 0) { - return rc; - } - - return maxvec; -} - -4.3.3 pci_disable_msix - -void pci_disable_msix(struct pci_dev *dev) - -This function should be used to undo the effect of pci_enable_msix_range(). -It frees the previously allocated MSI-X interrupts. The interrupts may -subsequently be assigned to another device, so drivers should not cache -the value of the 'vector' elements over a call to pci_disable_msix(). - -Before calling this function, a device driver must always call free_irq() -on any interrupt for which it previously called request_irq(). -Failure to do so results in a BUG_ON(), leaving the device with -MSI-X enabled and thus leaking its vector. - -4.3.3 The MSI-X Table - -The MSI-X capability specifies a BAR and offset within that BAR for the -MSI-X Table. This address is mapped by the PCI subsystem, and should not -be accessed directly by the device driver. If the driver wishes to -mask or unmask an interrupt, it should call disable_irq() / enable_irq(). +interrupts it can request a particular number of interrupts by passing that +number to pci_alloc_irq_vectors() function as both 'min_vecs' and +'max_vecs' parameters: -4.3.4 pci_msix_vec_count + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + if (ret < 0) + goto out_err; -int pci_msix_vec_count(struct pci_dev *dev) +The most notorious example of the request type described above is enabling +the single MSI mode for a device. It could be done by passing two 1s as +'min_vecs' and 'max_vecs': -This function could be used to retrieve number of entries in the device -MSI-X table. + ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + if (ret < 0) + goto out_err; -If this function returns a negative number, it indicates the device is -not capable of sending MSI-Xs. +Some devices might not support using legacy line interrupts, in which case +the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform +can't provide MSI or MSI-X interrupts: -If this function returns a positive number, it indicates the maximum -number of MSI-X interrupt vectors that could be allocated. + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + if (nvec < 0) + goto out_err; -4.4 Handling devices implementing both MSI and MSI-X capabilities +4.3 Legacy APIs -If a device implements both MSI and MSI-X capabilities, it can -run in either MSI mode or MSI-X mode, but not both simultaneously. -This is a requirement of the PCI spec, and it is enforced by the -PCI layer. Calling pci_enable_msi_range() when MSI-X is already -enabled or pci_enable_msix_range() when MSI is already enabled -results in an error. If a device driver wishes to switch between MSI -and MSI-X at runtime, it must first quiesce the device, then switch -it back to pin-interrupt mode, before calling pci_enable_msi_range() -or pci_enable_msix_range() and resuming operation. This is not expected -to be a common operation but may be useful for debugging or testing -during development. +The following old APIs to enable and disable MSI or MSI-X interrupts should +not be used in new code: -4.5 Considerations when using MSIs + pci_enable_msi() /* deprecated */ + pci_enable_msi_range() /* deprecated */ + pci_enable_msi_exact() /* deprecated */ + pci_disable_msi() /* deprecated */ + pci_enable_msix_range() /* deprecated */ + pci_enable_msix_exact() /* deprecated */ + pci_disable_msix() /* deprecated */ -4.5.1 Choosing between MSI-X and MSI +Additionally there are APIs to provide the number of supported MSI or MSI-X +vectors: pci_msi_vec_count() and pci_msix_vec_count(). In general these +should be avoided in favor of letting pci_alloc_irq_vectors() cap the +number of vectors. If you have a legitimate special use case for the count +of vectors we might have to revisit that decision and add a +pci_nr_irq_vectors() helper that handles MSI and MSI-X transparently. -If your device supports both MSI-X and MSI capabilities, you should use -the MSI-X facilities in preference to the MSI facilities. As mentioned -above, MSI-X supports any number of interrupts between 1 and 2048. -In contrast, MSI is restricted to a maximum of 32 interrupts (and -must be a power of two). In addition, the MSI interrupt vectors must -be allocated consecutively, so the system might not be able to allocate -as many vectors for MSI as it could for MSI-X. On some platforms, MSI -interrupts must all be targeted at the same set of CPUs whereas MSI-X -interrupts can all be targeted at different CPUs. +4.4 Considerations when using MSIs -4.5.2 Spinlocks +4.4.1 Spinlocks Most device drivers have a per-device spinlock which is taken in the interrupt handler. With pin-based interrupts or a single MSI, it is not @@ -505,7 +190,7 @@ acquire the spinlock. Such deadlocks can be avoided by using spin_lock_irqsave() or spin_lock_irq() which disable local interrupts and acquire the lock (see Documentation/DocBook/kernel-locking). -4.6 How to tell whether MSI/MSI-X is enabled on a device +4.5 How to tell whether MSI/MSI-X is enabled on a device Using 'lspci -v' (as root) may show some devices with "MSI", "Message Signalled Interrupts" or "MSI-X" capabilities. Each of these capabilities -- cgit v1.2.3 From 4ef33685aa0957d771e068b60a5f3ca6b47ade1c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Jul 2016 18:20:18 +0900 Subject: PCI: Spread interrupt vectors in pci_alloc_irq_vectors() Set the affinity_mask in the PCI device before allocating vectors so that the affinity can be propagated through the MSI descriptor structures to the core IRQ code. To facilitate this, new __pci_enable_msi_range() and __pci_enable_msix_range() helpers are factored out of their not prefixed variants which assigning the new IRQ affinity mask in the PCI device so that the low-level interrupt code can perform the interrupt affinity assignment and do node-local allocations. A new PCI_IRQ_NOAFFINITY flag is added to pci_alloc_irq_vectors() so that this function can also be used by drivers that don't wish to use the automatic affinity assignment. [bhelgaas: omit "else" after "return" consistently] Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- Documentation/PCI/MSI-HOWTO.txt | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'Documentation') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 0ac612b8c3fb..c55df2911136 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -99,6 +99,10 @@ PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in case the device does not support legacy interrupt lines. +By default this function will spread the interrupts around the available +CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY +flag. + To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: -- cgit v1.2.3 From e16b46605960bd071a3e26f316e0bb600ae91e37 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 21 Jul 2016 21:40:28 -0600 Subject: PCI: Allow additional bus numbers for hotplug bridges A user may hot add a switch requiring more than one bus to enumerate. This previously required a system reboot if BIOS did not sufficiently pad the bus resource, which they frequently don't do. Add a kernel parameter so a user can specify the minimum number of bus numbers to reserve for a hotplug bridge's subordinate buses so rebooting won't be necessary. The default is 1, which is equivalent to previous behavior. Signed-off-by: Keith Busch Signed-off-by: Bjorn Helgaas --- Documentation/kernel-parameters.txt | 3 +++ 1 file changed, 3 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82b42c958d1c..487e799b1da2 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3016,6 +3016,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. hpmemsize=nn[KMG] The fixed amount of bus space which is reserved for hotplug bridge's memory window. Default size is 2 megabytes. + hpbussize=nn The minimum amount of additional bus numbers + reserved for buses below a hotplug bridge. + Default is 1. realloc= Enable/disable reallocating PCI bridge resources if allocations done by BIOS are too small to accommodate resources required by all child -- cgit v1.2.3 From 0a00ab1204e065bfc2f0ecf4794ad9cbf66e86a7 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 30 Jun 2016 11:32:30 +0200 Subject: dt-bindings: add DT binding for the Aardvark PCIe controller Add the documentation for the Device Tree binding for the Aardvark PCIe controller, found on Marvell Armada 3700 ARM64 SoCs. Signed-off-by: Thomas Petazzoni Signed-off-by: Bjorn Helgaas --- .../devicetree/bindings/pci/aardvark-pci.txt | 56 ++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 Documentation/devicetree/bindings/pci/aardvark-pci.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/pci/aardvark-pci.txt b/Documentation/devicetree/bindings/pci/aardvark-pci.txt new file mode 100644 index 000000000000..bbcd9f4c501f --- /dev/null +++ b/Documentation/devicetree/bindings/pci/aardvark-pci.txt @@ -0,0 +1,56 @@ +Aardvark PCIe controller + +This PCIe controller is used on the Marvell Armada 3700 ARM64 SoC. + +The Device Tree node describing an Aardvark PCIe controller must +contain the following properties: + + - compatible: Should be "marvell,armada-3700-pcie" + - reg: range of registers for the PCIe controller + - interrupts: the interrupt line of the PCIe controller + - #address-cells: set to <3> + - #size-cells: set to <2> + - device_type: set to "pci" + - ranges: ranges for the PCI memory and I/O regions + - #interrupt-cells: set to <1> + - msi-controller: indicates that the PCIe controller can itself + handle MSI interrupts + - msi-parent: pointer to the MSI controller to be used + - interrupt-map-mask and interrupt-map: standard PCI properties to + define the mapping of the PCIe interface to interrupt numbers. + - bus-range: PCI bus numbers covered + +In addition, the Device Tree describing an Aardvark PCIe controller +must include a sub-node that describes the legacy interrupt controller +built into the PCIe controller. This sub-node must have the following +properties: + + - interrupt-controller + - #interrupt-cells: set to <1> + +Example: + + pcie0: pcie@d0070000 { + compatible = "marvell,armada-3700-pcie"; + device_type = "pci"; + status = "disabled"; + reg = <0 0xd0070000 0 0x20000>; + #address-cells = <3>; + #size-cells = <2>; + bus-range = <0x00 0xff>; + interrupts = ; + #interrupt-cells = <1>; + msi-controller; + msi-parent = <&pcie0>; + ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x1000000 /* Port 0 MEM */ + 0x81000000 0 0xe9000000 0 0xe9000000 0 0x10000>; /* Port 0 IO*/ + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + pcie_intc: interrupt-controller { + interrupt-controller; + #interrupt-cells = <1>; + }; + }; -- cgit v1.2.3