// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2014 Intel Corp. * Author: Jiang Liu <[email protected]> * * This file is licensed under GPLv2. * * This file contains common code to support Message Signaled Interrupts for * PCI compatible and non PCI compatible devices. */ #include <linux/device.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/mutex.h> #include <linux/pci.h> #include <linux/slab.h> #include <linux/sysfs.h> #include <linux/types.h> #include <linux/xarray.h> #include "internals.h" /** * struct msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers * @mutex: Mutex protecting the MSI descriptor store * @__domains: Internal data for per device MSI domains * @__iter_idx: Index to search the next entry for iterators */ struct msi_device_data { … }; /** * struct msi_ctrl - MSI internal management control structure * @domid: ID of the domain on which management operations should be done * @first: First (hardware) slot index to operate on * @last: Last (hardware) slot index to operate on * @nirqs: The number of Linux interrupts to allocate. Can be larger * than the range due to PCI/multi-MSI. */ struct msi_ctrl { … }; /* Invalid Xarray index which is outside of any searchable range */ #define MSI_XA_MAX_INDEX … /* The maximum domain size */ #define MSI_XA_DOMAIN_SIZE … static void msi_domain_free_locked(struct device *dev, struct msi_ctrl *ctrl); static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid); static inline int msi_sysfs_create_group(struct device *dev); /** * msi_alloc_desc - Allocate an initialized msi_desc * @dev: Pointer to the device for which this is allocated * @nvec: The number of vectors used in this entry * @affinity: Optional pointer to an affinity mask array size of @nvec * * If @affinity is not %NULL then an affinity array[@nvec] is allocated * and the affinity masks and flags from @affinity are copied. * * Return: pointer to allocated &msi_desc on success or %NULL on failure */ static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, const struct irq_affinity_desc *affinity) { … } static void msi_free_desc(struct msi_desc *desc) { … } static int msi_insert_desc(struct device *dev, struct msi_desc *desc, unsigned int domid, unsigned int index) { … } /** * msi_domain_insert_msi_desc - Allocate and initialize a MSI descriptor and * insert it at @init_desc->msi_index * * @dev: Pointer to the device for which the descriptor is allocated * @domid: The id of the interrupt domain to which the desriptor is added * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor * * Return: 0 on success or an appropriate failure code. */ int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, struct msi_desc *init_desc) { … } static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) { … } static bool msi_ctrl_valid(struct device *dev, struct msi_ctrl *ctrl) { … } static void msi_domain_free_descs(struct device *dev, struct msi_ctrl *ctrl) { … } /** * msi_domain_free_msi_descs_range - Free a range of MSI descriptors of a device in an irqdomain * @dev: Device for which to free the descriptors * @domid: Id of the domain to operate on * @first: Index to start freeing from (inclusive) * @last: Last index to be freed (inclusive) */ void msi_domain_free_msi_descs_range(struct device *dev, unsigned int domid, unsigned int first, unsigned int last) { … } /** * msi_domain_add_simple_msi_descs - Allocate and initialize MSI descriptors * @dev: Pointer to the device for which the descriptors are allocated * @ctrl: Allocation control struct * * Return: 0 on success or an appropriate failure code. */ static int msi_domain_add_simple_msi_descs(struct device *dev, struct msi_ctrl *ctrl) { … } void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { … } void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) { … } EXPORT_SYMBOL_GPL(…); static void msi_device_data_release(struct device *dev, void *res) { … } /** * msi_setup_device_data - Setup MSI device data * @dev: Device for which MSI device data should be set up * * Return: 0 on success, appropriate error code otherwise * * This can be called more than once for @dev. If the MSI device data is * already allocated the call succeeds. The allocated memory is * automatically released when the device is destroyed. */ int msi_setup_device_data(struct device *dev) { … } /** * msi_lock_descs - Lock the MSI descriptor storage of a device * @dev: Device to operate on */ void msi_lock_descs(struct device *dev) { … } EXPORT_SYMBOL_GPL(…); /** * msi_unlock_descs - Unlock the MSI descriptor storage of a device * @dev: Device to operate on */ void msi_unlock_descs(struct device *dev) { … } EXPORT_SYMBOL_GPL(…); static struct msi_desc *msi_find_desc(struct msi_device_data *md, unsigned int domid, enum msi_desc_filter filter) { … } /** * msi_domain_first_desc - Get the first MSI descriptor of an irqdomain associated to a device * @dev: Device to operate on * @domid: The id of the interrupt domain which should be walked. * @filter: Descriptor state filter * * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs() * must be invoked before the call. * * Return: Pointer to the first MSI descriptor matching the search * criteria, NULL if none found. */ struct msi_desc *msi_domain_first_desc(struct device *dev, unsigned int domid, enum msi_desc_filter filter) { … } EXPORT_SYMBOL_GPL(…); /** * msi_next_desc - Get the next MSI descriptor of a device * @dev: Device to operate on * @domid: The id of the interrupt domain which should be walked. * @filter: Descriptor state filter * * The first invocation of msi_next_desc() has to be preceeded by a * successful invocation of __msi_first_desc(). Consecutive invocations are * only valid if the previous one was successful. All these operations have * to be done within the same MSI mutex held region. * * Return: Pointer to the next MSI descriptor matching the search * criteria, NULL if none found. */ struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid, enum msi_desc_filter filter) { … } EXPORT_SYMBOL_GPL(…); /** * msi_domain_get_virq - Lookup the Linux interrupt number for a MSI index on a interrupt domain * @dev: Device to operate on * @domid: Domain ID of the interrupt domain associated to the device * @index: MSI interrupt index to look for (0-based) * * Return: The Linux interrupt number on success (> 0), 0 if not found */ unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigned int index) { … } EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_SYSFS static struct attribute *msi_dev_attrs[] = …; static const struct attribute_group msi_irqs_group = …; static inline int msi_sysfs_create_group(struct device *dev) { … } static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { … } static void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { … } static int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { … } #if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN) /** * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) which will get sysfs entries */ int msi_device_populate_sysfs(struct device *dev) { … } /** * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) for which to remove * sysfs entries */ void msi_device_destroy_sysfs(struct device *dev) { … } #endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */ #else /* CONFIG_SYSFS */ static inline int msi_sysfs_create_group(struct device *dev) { return 0; } static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { } #endif /* !CONFIG_SYSFS */ static struct irq_domain *msi_get_device_domain(struct device *dev, unsigned int domid) { … } static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid) { … } static inline void irq_chip_write_msi_msg(struct irq_data *data, struct msi_msg *msg) { … } static void msi_check_level(struct irq_domain *domain, struct msi_msg *msg) { … } /** * msi_domain_set_affinity - Generic affinity setter function for MSI domains * @irq_data: The irq data associated to the interrupt * @mask: The affinity mask to set * @force: Flag to enforce setting (disable online checks) * * Intended to be used by MSI interrupt controllers which are * implemented with hierarchical domains. * * Return: IRQ_SET_MASK_* result code */ int msi_domain_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { … } static int msi_domain_activate(struct irq_domain *domain, struct irq_data *irq_data, bool early) { … } static void msi_domain_deactivate(struct irq_domain *domain, struct irq_data *irq_data) { … } static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { … } static void msi_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { … } static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fwspec, irq_hw_number_t *hwirq, unsigned int *type) { … } static const struct irq_domain_ops msi_domain_ops = …; static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info, msi_alloc_info_t *arg) { … } static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { … } static void msi_domain_ops_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { … } static int msi_domain_ops_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { … } static struct msi_domain_ops msi_domain_ops_default = …; static void msi_domain_update_dom_ops(struct msi_domain_info *info) { … } static void msi_domain_update_chip_ops(struct msi_domain_info *info) { … } static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, unsigned int flags, struct irq_domain *parent) { … } /** * msi_create_irq_domain - Create an MSI interrupt domain * @fwnode: Optional fwnode of the interrupt controller * @info: MSI domain info * @parent: Parent irq domain * * Return: pointer to the created &struct irq_domain or %NULL on failure */ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { … } /** * msi_parent_init_dev_msi_info - Delegate initialization of device MSI info down * in the domain hierarchy * @dev: The device for which the domain should be created * @domain: The domain in the hierarchy this op is being called on * @msi_parent_domain: The IRQ_DOMAIN_FLAG_MSI_PARENT domain for the child to * be created * @msi_child_info: The MSI domain info of the IRQ_DOMAIN_FLAG_MSI_DEVICE * domain to be created * * Return: true on success, false otherwise * * This is the most complex problem of per device MSI domains and the * underlying interrupt domain hierarchy: * * The device domain to be initialized requests the broadest feature set * possible and the underlying domain hierarchy puts restrictions on it. * * That's trivial for a simple parent->child relationship, but it gets * interesting with an intermediate domain: root->parent->child. The * intermediate 'parent' can expand the capabilities which the 'root' * domain is providing. So that creates a classic hen and egg problem: * Which entity is doing the restrictions/expansions? * * One solution is to let the root domain handle the initialization that's * why there is the @domain and the @msi_parent_domain pointer. */ bool msi_parent_init_dev_msi_info(struct device *dev, struct irq_domain *domain, struct irq_domain *msi_parent_domain, struct msi_domain_info *msi_child_info) { … } /** * msi_create_device_irq_domain - Create a device MSI interrupt domain * @dev: Pointer to the device * @domid: Domain id * @template: MSI domain info bundle used as template * @hwsize: Maximum number of MSI table entries (0 if unknown or unlimited) * @domain_data: Optional pointer to domain specific data which is set in * msi_domain_info::data * @chip_data: Optional pointer to chip specific data which is set in * msi_domain_info::chip_data * * Return: True on success, false otherwise * * There is no firmware node required for this interface because the per * device domains are software constructs which are actually closer to the * hardware reality than any firmware can describe them. * * The domain name and the irq chip name for a MSI device domain are * composed by: "$(PREFIX)$(CHIPNAME)-$(DEVNAME)" * * $PREFIX: Optional prefix provided by the underlying MSI parent domain * via msi_parent_ops::prefix. If that pointer is NULL the prefix * is empty. * $CHIPNAME: The name of the irq_chip in @template * $DEVNAME: The name of the device * * This results in understandable chip names and hardware interrupt numbers * in e.g. /proc/interrupts * * PCI-MSI-0000:00:1c.0 0-edge Parent domain has no prefix * IR-PCI-MSI-0000:00:1c.4 0-edge Same with interrupt remapping prefix 'IR-' * * IR-PCI-MSIX-0000:3d:00.0 0-edge Hardware interrupt numbers reflect * IR-PCI-MSIX-0000:3d:00.0 1-edge the real MSI-X index on that device * IR-PCI-MSIX-0000:3d:00.0 2-edge * * On IMS domains the hardware interrupt number is either a table entry * index or a purely software managed index but it is guaranteed to be * unique. * * The domain pointer is stored in @dev::msi::data::__irqdomains[]. All * subsequent operations on the domain depend on the domain id. * * The domain is automatically freed when the device is removed via devres * in the context of @dev::msi::data freeing, but it can also be * independently removed via @msi_remove_device_irq_domain(). */ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, const struct msi_domain_template *template, unsigned int hwsize, void *domain_data, void *chip_data) { … } /** * msi_remove_device_irq_domain - Free a device MSI interrupt domain * @dev: Pointer to the device * @domid: Domain id */ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) { … } /** * msi_match_device_irq_domain - Match a device irq domain against a bus token * @dev: Pointer to the device * @domid: Domain id * @bus_token: Bus token to match against the domain bus token * * Return: True if device domain exists and bus tokens match. */ bool msi_match_device_irq_domain(struct device *dev, unsigned int domid, enum irq_domain_bus_token bus_token) { … } static int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { … } /* * Carefully check whether the device can use reservation mode. If * reservation mode is enabled then the early activation will assign a * dummy vector to the device. If the PCI/MSI device does not support * masking of the entry then this can result in spurious interrupts when * the device driver is not absolutely careful. But even then a malfunction * of the hardware could result in a spurious interrupt on the dummy vector * and render the device unusable. If the entry can be masked then the core * logic will prevent the spurious interrupt and reservation mode can be * used. For now reservation mode is restricted to PCI/MSI. */ static bool msi_check_reservation_mode(struct irq_domain *domain, struct msi_domain_info *info, struct device *dev) { … } static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, int allocated) { … } #define VIRQ_CAN_RESERVE … #define VIRQ_ACTIVATE … static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags) { … } static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain, struct msi_ctrl *ctrl) { … } static int msi_domain_alloc_simple_msi_descs(struct device *dev, struct msi_domain_info *info, struct msi_ctrl *ctrl) { … } static int __msi_domain_alloc_locked(struct device *dev, struct msi_ctrl *ctrl) { … } static int msi_domain_alloc_locked(struct device *dev, struct msi_ctrl *ctrl) { … } /** * msi_domain_alloc_irqs_range_locked - Allocate interrupts from a MSI interrupt domain * @dev: Pointer to device struct of the device for which the interrupts * are allocated * @domid: Id of the interrupt domain to operate on * @first: First index to allocate (inclusive) * @last: Last index to allocate (inclusive) * * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() * pair. Use this for MSI irqdomains which implement their own descriptor * allocation/free. * * Return: %0 on success or an error code. */ int msi_domain_alloc_irqs_range_locked(struct device *dev, unsigned int domid, unsigned int first, unsigned int last) { … } /** * msi_domain_alloc_irqs_range - Allocate interrupts from a MSI interrupt domain * @dev: Pointer to device struct of the device for which the interrupts * are allocated * @domid: Id of the interrupt domain to operate on * @first: First index to allocate (inclusive) * @last: Last index to allocate (inclusive) * * Return: %0 on success or an error code. */ int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid, unsigned int first, unsigned int last) { … } EXPORT_SYMBOL_GPL(…); /** * msi_domain_alloc_irqs_all_locked - Allocate all interrupts from a MSI interrupt domain * * @dev: Pointer to device struct of the device for which the interrupts * are allocated * @domid: Id of the interrupt domain to operate on * @nirqs: The number of interrupts to allocate * * This function scans all MSI descriptors of the MSI domain and allocates interrupts * for all unassigned ones. That function is to be used for MSI domain usage where * the descriptor allocation is handled at the call site, e.g. PCI/MSI[X]. * * Return: %0 on success or an error code. */ int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int nirqs) { … } static struct msi_map __msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, const struct irq_affinity_desc *affdesc, union msi_instance_cookie *icookie) { … } /** * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at * a given index - or at the next free index * * @dev: Pointer to device struct of the device for which the interrupts * are allocated * @domid: Id of the interrupt domain to operate on * @index: Index for allocation. If @index == %MSI_ANY_INDEX the allocation * uses the next free index. * @affdesc: Optional pointer to an interrupt affinity descriptor structure * @icookie: Optional pointer to a domain specific per instance cookie. If * non-NULL the content of the cookie is stored in msi_desc::data. * Must be NULL for MSI-X allocations * * This requires a MSI interrupt domain which lets the core code manage the * MSI descriptors. * * Return: struct msi_map * * On success msi_map::index contains the allocated index number and * msi_map::virq the corresponding Linux interrupt number * * On failure msi_map::index contains the error code and msi_map::virq * is %0. */ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, const struct irq_affinity_desc *affdesc, union msi_instance_cookie *icookie) { … } /** * msi_device_domain_alloc_wired - Allocate a "wired" interrupt on @domain * @domain: The domain to allocate on * @hwirq: The hardware interrupt number to allocate for * @type: The interrupt type * * This weirdness supports wire to MSI controllers like MBIGEN. * * @hwirq is the hardware interrupt number which is handed in from * irq_create_fwspec_mapping(). As the wire to MSI domain is sparse, but * sized in firmware, the hardware interrupt number cannot be used as MSI * index. For the underlying irq chip the MSI index is irrelevant and * all it needs is the hardware interrupt number. * * To handle this the MSI index is allocated with MSI_ANY_INDEX and the * hardware interrupt number is stored along with the type information in * msi_desc::cookie so the underlying interrupt chip and domain code can * retrieve it. * * Return: The Linux interrupt number (> 0) or an error code */ int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq, unsigned int type) { … } static void __msi_domain_free_irqs(struct device *dev, struct irq_domain *domain, struct msi_ctrl *ctrl) { … } static void msi_domain_free_locked(struct device *dev, struct msi_ctrl *ctrl) { … } /** * msi_domain_free_irqs_range_locked - Free a range of interrupts from a MSI interrupt domain * associated to @dev with msi_lock held * @dev: Pointer to device struct of the device for which the interrupts * are freed * @domid: Id of the interrupt domain to operate on * @first: First index to free (inclusive) * @last: Last index to free (inclusive) */ void msi_domain_free_irqs_range_locked(struct device *dev, unsigned int domid, unsigned int first, unsigned int last) { … } /** * msi_domain_free_irqs_range - Free a range of interrupts from a MSI interrupt domain * associated to @dev * @dev: Pointer to device struct of the device for which the interrupts * are freed * @domid: Id of the interrupt domain to operate on * @first: First index to free (inclusive) * @last: Last index to free (inclusive) */ void msi_domain_free_irqs_range(struct device *dev, unsigned int domid, unsigned int first, unsigned int last) { … } EXPORT_SYMBOL_GPL(…); /** * msi_domain_free_irqs_all_locked - Free all interrupts from a MSI interrupt domain * associated to a device * @dev: Pointer to device struct of the device for which the interrupts * are freed * @domid: The id of the domain to operate on * * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() * pair. Use this for MSI irqdomains which implement their own vector * allocation. */ void msi_domain_free_irqs_all_locked(struct device *dev, unsigned int domid) { … } /** * msi_domain_free_irqs_all - Free all interrupts from a MSI interrupt domain * associated to a device * @dev: Pointer to device struct of the device for which the interrupts * are freed * @domid: The id of the domain to operate on */ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid) { … } /** * msi_device_domain_free_wired - Free a wired interrupt in @domain * @domain: The domain to free the interrupt on * @virq: The Linux interrupt number to free * * This is the counterpart of msi_device_domain_alloc_wired() for the * weird wired to MSI converting domains. */ void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq) { … } /** * msi_get_domain_info - Get the MSI interrupt domain info for @domain * @domain: The interrupt domain to retrieve data from * * Return: the pointer to the msi_domain_info stored in @domain->host_data. */ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { … } /** * msi_device_has_isolated_msi - True if the device has isolated MSI * @dev: The device to check * * Isolated MSI means that HW modeled by an irq_domain on the path from the * initiating device to the CPU will validate that the MSI message specifies an * interrupt number that the device is authorized to trigger. This must block * devices from triggering interrupts they are not authorized to trigger. * Currently authorization means the MSI vector is one assigned to the device. * * This is interesting for securing VFIO use cases where a rouge MSI (eg created * by abusing a normal PCI MemWr DMA) must not allow the VFIO userspace to * impact outside its security domain, eg userspace triggering interrupts on * kernel drivers, a VM triggering interrupts on the hypervisor, or a VM * triggering interrupts on another VM. */ bool msi_device_has_isolated_msi(struct device *dev) { … } EXPORT_SYMBOL_GPL(…);