From ed36d04e8f8d7b00db451b0fa56a54e8e02ec43e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:02 +0100 Subject: iommu: Introduce device_iommu_capable() iommu_capable() only really works for systems where all IOMMU instances are completely homogeneous, and all devices are IOMMU-mapped. Implement the new variant which will be able to give a more accurate answer for whichever device the caller is actually interested in, and even more so once all the external users have been converted and we can reliably pass the device pointer through the internal driver interface too. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/8407eb9586677995b7a9fd70d0fd82d85929a9bb.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..e26cf84e5d82 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -417,6 +417,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); +extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); @@ -689,6 +690,11 @@ static inline bool iommu_present(struct bus_type *bus) return false; } +static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) +{ + return false; +} + static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) { return false; -- cgit v1.2.3-71-gd317 From d0be55fbeb6ac694d15af5d1aad19cdec8cd64e5 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:03 +0100 Subject: iommu: Add capability for pre-boot DMA protection VT-d's dmar_platform_optin() actually represents a combination of properties fairly well standardised by Microsoft as "Pre-boot DMA Protection" and "Kernel DMA Protection"[1]. As such, we can provide interested consumers with an abstracted capability rather than driver-specific interfaces that won't scale. We name it for the former aspect since that's what external callers are most likely to be interested in; the latter is for the IOMMU layer to handle itself. [1] https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-kernel-dma-protection Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Lu Baolu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/d6218dff2702472da80db6aec2c9589010684551.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 2 ++ include/linux/iommu.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index df5c62ecf942..0edf6084dc14 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4551,6 +4551,8 @@ static bool intel_iommu_capable(enum iommu_cap cap) return domain_update_iommu_snooping(NULL); if (cap == IOMMU_CAP_INTR_REMAP) return irq_remapping_enabled == 1; + if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION) + return dmar_platform_optin(); return false; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e26cf84e5d82..4123693ae319 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -107,6 +107,8 @@ enum iommu_cap { transactions */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ + IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for + DMA protection and we should too */ }; /* These are the possible reserved region types */ -- cgit v1.2.3-71-gd317 From 86eaf4a5b4312bea8676fb79399d9e08b53d8e71 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:04 +0100 Subject: thunderbolt: Make iommu_dma_protection more accurate Between me trying to get rid of iommu_present() and Mario wanting to support the AMD equivalent of DMAR_PLATFORM_OPT_IN, scrutiny has shown that the iommu_dma_protection attribute is being far too optimistic. Even if an IOMMU might be present for some PCI segment in the system, that doesn't necessarily mean it provides translation for the device(s) we care about. Furthermore, all that DMAR_PLATFORM_OPT_IN really does is tell us that memory was protected before the kernel was loaded, and prevent the user from disabling the intel-iommu driver entirely. While that lets us assume kernel integrity, what matters for actual runtime DMA protection is whether we trust individual devices, based on the "external facing" property that we expect firmware to describe for Thunderbolt ports. It's proven challenging to determine the appropriate ports accurately given the variety of possible topologies, so while still not getting a perfect answer, by putting enough faith in firmware we can at least get a good bit closer. If we can see that any device near a Thunderbolt NHI has all the requisites for Kernel DMA Protection, chances are that it *is* a relevant port, but moreover that implies that firmware is playing the game overall, so we'll use that to assume that all Thunderbolt ports should be correctly marked and thus will end up fully protected. CC: Mario Limonciello Reviewed-by: Christoph Hellwig Acked-by: Mika Westerberg Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b153f208bc9eafab5105bad0358b77366509d2d4.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/thunderbolt/domain.c | 12 +++--------- drivers/thunderbolt/nhi.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/thunderbolt.h | 2 ++ 3 files changed, 49 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index 7018d959f775..2889a214dadc 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -7,9 +7,7 @@ */ #include -#include #include -#include #include #include #include @@ -257,13 +255,9 @@ static ssize_t iommu_dma_protection_show(struct device *dev, struct device_attribute *attr, char *buf) { - /* - * Kernel DMA protection is a feature where Thunderbolt security is - * handled natively using IOMMU. It is enabled when IOMMU is - * enabled and ACPI DMAR table has DMAR_PLATFORM_OPT_IN set. - */ - return sprintf(buf, "%d\n", - iommu_present(&pci_bus_type) && dmar_platform_optin()); + struct tb *tb = container_of(dev, struct tb, dev); + + return sysfs_emit(buf, "%d\n", tb->nhi->iommu_dma_protection); } static DEVICE_ATTR_RO(iommu_dma_protection); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 4a582183f675..4bc87b0f003a 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -15,9 +15,11 @@ #include #include #include +#include #include #include #include +#include #include "nhi.h" #include "nhi_regs.h" @@ -1103,6 +1105,47 @@ static void nhi_check_quirks(struct tb_nhi *nhi) nhi->quirks |= QUIRK_AUTO_CLEAR_INT; } +static int nhi_check_iommu_pdev(struct pci_dev *pdev, void *data) +{ + if (!pdev->external_facing || + !device_iommu_capable(&pdev->dev, IOMMU_CAP_PRE_BOOT_PROTECTION)) + return 0; + *(bool *)data = true; + return 1; /* Stop walking */ +} + +static void nhi_check_iommu(struct tb_nhi *nhi) +{ + struct pci_bus *bus = nhi->pdev->bus; + bool port_ok = false; + + /* + * Ideally what we'd do here is grab every PCI device that + * represents a tunnelling adapter for this NHI and check their + * status directly, but unfortunately USB4 seems to make it + * obnoxiously difficult to reliably make any correlation. + * + * So for now we'll have to bodge it... Hoping that the system + * is at least sane enough that an adapter is in the same PCI + * segment as its NHI, if we can find *something* on that segment + * which meets the requirements for Kernel DMA Protection, we'll + * take that to imply that firmware is aware and has (hopefully) + * done the right thing in general. We need to know that the PCI + * layer has seen the ExternalFacingPort property which will then + * inform the IOMMU layer to enforce the complete "untrusted DMA" + * flow, but also that the IOMMU driver itself can be trusted not + * to have been subverted by a pre-boot DMA attack. + */ + while (bus->parent) + bus = bus->parent; + + pci_walk_bus(bus, nhi_check_iommu_pdev, &port_ok); + + nhi->iommu_dma_protection = port_ok; + dev_dbg(&nhi->pdev->dev, "IOMMU DMA protection is %s\n", + str_enabled_disabled(port_ok)); +} + static int nhi_init_msi(struct tb_nhi *nhi) { struct pci_dev *pdev = nhi->pdev; @@ -1220,6 +1263,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; nhi_check_quirks(nhi); + nhi_check_iommu(nhi); res = nhi_init_msi(nhi); if (res) { diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..7a8ad984e651 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -465,6 +465,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @msix_ida: Used to allocate MSI-X vectors for rings * @going_away: The host controller device is about to disappear so when * this flag is set, avoid touching the hardware anymore. + * @iommu_dma_protection: An IOMMU will isolate external-facing ports. * @interrupt_work: Work scheduled to handle ring interrupt when no * MSI-X is used. * @hop_count: Number of rings (end point hops) supported by NHI. @@ -479,6 +480,7 @@ struct tb_nhi { struct tb_ring **rx_rings; struct ida msix_ida; bool going_away; + bool iommu_dma_protection; struct work_struct interrupt_work; u32 hop_count; unsigned long quirks; -- cgit v1.2.3-71-gd317 From 1ea2a07a532b0e22aabe7e8483f935c672b9e7ed Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:50 +0800 Subject: iommu: Add DMA ownership management interfaces Multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. These devices must either be entirely under kernel control or userspace control, never a mixture. This adds dma ownership management in iommu core and exposes several interfaces for the device drivers and the device userspace assignment framework (i.e. VFIO), so that any conflict between user and kernel controlled dma could be detected at the beginning. The device driver oriented interfaces are, int iommu_device_use_default_domain(struct device *dev); void iommu_device_unuse_default_domain(struct device *dev); By calling iommu_device_use_default_domain(), the device driver tells the iommu layer that the device dma is handled through the kernel DMA APIs. The iommu layer will manage the IOVA and use the default domain for DMA address translation. The device user-space assignment framework oriented interfaces are, int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); The device userspace assignment must be disallowed if the DMA owner claiming interface returns failure. Signed-off-by: Jason Gunthorpe Signed-off-by: Kevin Tian Signed-off-by: Lu Baolu Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20220418005000.897664-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 153 +++++++++++++++++++++++++++++++++++++++++++++++++- include/linux/iommu.h | 31 ++++++++++ 2 files changed, 181 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index f2c45b85b9fc..eba8e8ccf19d 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -48,6 +48,8 @@ struct iommu_group { struct iommu_domain *default_domain; struct iommu_domain *domain; struct list_head entry; + unsigned int owner_cnt; + void *owner; }; struct group_device { @@ -294,7 +296,11 @@ int iommu_probe_device(struct device *dev) mutex_lock(&group->mutex); iommu_alloc_default_domain(group, dev); - if (group->default_domain) { + /* + * If device joined an existing group which has been claimed, don't + * attach the default domain. + */ + if (group->default_domain && !group->owner) { ret = __iommu_attach_device(group->default_domain, dev); if (ret) { mutex_unlock(&group->mutex); @@ -2109,7 +2115,7 @@ static int __iommu_attach_group(struct iommu_domain *domain, { int ret; - if (group->default_domain && group->domain != group->default_domain) + if (group->domain && group->domain != group->default_domain) return -EBUSY; ret = __iommu_group_for_each_dev(group, domain, @@ -2146,7 +2152,11 @@ static void __iommu_detach_group(struct iommu_domain *domain, { int ret; - if (!group->default_domain) { + /* + * If the group has been claimed already, do not re-attach the default + * domain. + */ + if (!group->default_domain || group->owner) { __iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device); group->domain = NULL; @@ -3095,3 +3105,140 @@ out: return ret; } + +/** + * iommu_device_use_default_domain() - Device driver wants to handle device + * DMA through the kernel DMA API. + * @dev: The device. + * + * The device driver about to bind @dev wants to do DMA through the kernel + * DMA API. Return 0 if it is allowed, otherwise an error. + */ +int iommu_device_use_default_domain(struct device *dev) +{ + struct iommu_group *group = iommu_group_get(dev); + int ret = 0; + + if (!group) + return 0; + + mutex_lock(&group->mutex); + if (group->owner_cnt) { + if (group->domain != group->default_domain || + group->owner) { + ret = -EBUSY; + goto unlock_out; + } + } + + group->owner_cnt++; + +unlock_out: + mutex_unlock(&group->mutex); + iommu_group_put(group); + + return ret; +} + +/** + * iommu_device_unuse_default_domain() - Device driver stops handling device + * DMA through the kernel DMA API. + * @dev: The device. + * + * The device driver doesn't want to do DMA through kernel DMA API anymore. + * It must be called after iommu_device_use_default_domain(). + */ +void iommu_device_unuse_default_domain(struct device *dev) +{ + struct iommu_group *group = iommu_group_get(dev); + + if (!group) + return; + + mutex_lock(&group->mutex); + if (!WARN_ON(!group->owner_cnt)) + group->owner_cnt--; + + mutex_unlock(&group->mutex); + iommu_group_put(group); +} + +/** + * iommu_group_claim_dma_owner() - Set DMA ownership of a group + * @group: The group. + * @owner: Caller specified pointer. Used for exclusive ownership. + * + * This is to support backward compatibility for vfio which manages + * the dma ownership in iommu_group level. New invocations on this + * interface should be prohibited. + */ +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) +{ + int ret = 0; + + mutex_lock(&group->mutex); + if (group->owner_cnt) { + ret = -EPERM; + goto unlock_out; + } else { + if (group->domain && group->domain != group->default_domain) { + ret = -EBUSY; + goto unlock_out; + } + + group->owner = owner; + if (group->domain) + __iommu_detach_group(group->domain, group); + } + + group->owner_cnt++; +unlock_out: + mutex_unlock(&group->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner); + +/** + * iommu_group_release_dma_owner() - Release DMA ownership of a group + * @group: The group. + * + * Release the DMA ownership claimed by iommu_group_claim_dma_owner(). + */ +void iommu_group_release_dma_owner(struct iommu_group *group) +{ + mutex_lock(&group->mutex); + if (WARN_ON(!group->owner_cnt || !group->owner)) + goto unlock_out; + + group->owner_cnt = 0; + /* + * The UNMANAGED domain should be detached before all USER + * owners have been released. + */ + if (!WARN_ON(group->domain) && group->default_domain) + __iommu_attach_group(group->default_domain, group); + group->owner = NULL; +unlock_out: + mutex_unlock(&group->mutex); +} +EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner); + +/** + * iommu_group_dma_owner_claimed() - Query group dma ownership status + * @group: The group. + * + * This provides status query on a given group. It is racy and only for + * non-binding status reporting. + */ +bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + unsigned int user; + + mutex_lock(&group->mutex); + user = group->owner_cnt; + mutex_unlock(&group->mutex); + + return user; +} +EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..77972ef978b5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -675,6 +675,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +int iommu_device_use_default_domain(struct device *dev); +void iommu_device_unuse_default_domain(struct device *dev); + +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); +void iommu_group_release_dma_owner(struct iommu_group *group); +bool iommu_group_dma_owner_claimed(struct iommu_group *group); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -1031,6 +1038,30 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; } + +static inline int iommu_device_use_default_domain(struct device *dev) +{ + return 0; +} + +static inline void iommu_device_unuse_default_domain(struct device *dev) +{ +} + +static inline int +iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) +{ + return -ENODEV; +} + +static inline void iommu_group_release_dma_owner(struct iommu_group *group) +{ +} + +static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + return false; +} #endif /* CONFIG_IOMMU_API */ /** -- cgit v1.2.3-71-gd317 From 25f3bcfc54bcf7b0e45d140ec8bfbbf10ba11869 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:51 +0800 Subject: driver core: Add dma_cleanup callback in bus_type The bus_type structure defines dma_configure() callback for bus drivers to configure DMA on the devices. This adds the paired dma_cleanup() callback and calls it during driver unbinding so that bus drivers can do some cleanup work. One use case for this paired DMA callbacks is for the bus driver to check for DMA ownership conflicts during driver binding, where multiple devices belonging to a same IOMMU group (the minimum granularity of isolation and protection) may be assigned to kernel drivers or user space respectively. Without this change, for example, the vfio driver has to listen to a bus BOUND_DRIVER event and then BUG_ON() in case of dma ownership conflict. This leads to bad user experience since careless driver binding operation may crash the system if the admin overlooks the group restriction. Aside from bad design, this leads to a security problem as a root user, even with lockdown=integrity, can force the kernel to BUG. With this change, the bus driver could check and set the DMA ownership in driver binding process and fail on ownership conflicts. The DMA ownership should be released during driver unbinding. Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/base/dd.c | 5 +++++ include/linux/device/bus.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 3fc3b5940bb3..94b7ac9bf459 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -671,6 +671,8 @@ sysfs_failed: if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); + if (dev->bus && dev->bus->dma_cleanup) + dev->bus->dma_cleanup(dev); pinctrl_bind_failed: device_links_no_driver(dev); device_unbind_cleanup(dev); @@ -1199,6 +1201,9 @@ static void __device_release_driver(struct device *dev, struct device *parent) device_remove(dev); + if (dev->bus && dev->bus->dma_cleanup) + dev->bus->dma_cleanup(dev); + device_links_driver_cleanup(dev); device_unbind_cleanup(dev); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index a039ab809753..d8b29ccd07e5 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -59,6 +59,8 @@ struct fwnode_handle; * bus supports. * @dma_configure: Called to setup DMA configuration on a device on * this bus. + * @dma_cleanup: Called to cleanup DMA configuration on a device on + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -103,6 +105,7 @@ struct bus_type { int (*num_vf)(struct device *dev); int (*dma_configure)(struct device *dev); + void (*dma_cleanup)(struct device *dev); const struct dev_pm_ops *pm; -- cgit v1.2.3-71-gd317 From 4a6d9dd564d0e7339fc15ecc5ce66db4ad842be2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:52 +0800 Subject: amba: Stop sharing platform_dma_configure() Stop sharing platform_dma_configure() helper as they are about to have their own bus dma_configure callbacks. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/amba/bus.c | 19 ++++++++++++++++++- drivers/base/platform.c | 3 +-- include/linux/platform_device.h | 2 -- 3 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index d3bd14aaabf6..76b52bd2c2a4 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #define to_amba_driver(d) container_of(d, struct amba_driver, drv) @@ -273,6 +275,21 @@ static void amba_shutdown(struct device *dev) drv->shutdown(to_amba_device(dev)); } +static int amba_dma_configure(struct device *dev) +{ + enum dev_dma_attr attr; + int ret = 0; + + if (dev->of_node) { + ret = of_dma_configure(dev, dev->of_node, true); + } else if (has_acpi_companion(dev)) { + attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode)); + ret = acpi_dma_configure(dev, attr); + } + + return ret; +} + #ifdef CONFIG_PM /* * Hooks to provide runtime PM of the pclk (bus clock). It is safe to @@ -341,7 +358,7 @@ struct bus_type amba_bustype = { .probe = amba_probe, .remove = amba_remove, .shutdown = amba_shutdown, - .dma_configure = platform_dma_configure, + .dma_configure = amba_dma_configure, .pm = &amba_pm, }; EXPORT_SYMBOL_GPL(amba_bustype); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 8cc272fd5c99..d7915734d931 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1454,8 +1454,7 @@ static void platform_shutdown(struct device *_dev) drv->shutdown(dev); } - -int platform_dma_configure(struct device *dev) +static int platform_dma_configure(struct device *dev) { enum dev_dma_attr attr; int ret = 0; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..17fde717df68 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -328,8 +328,6 @@ extern int platform_pm_restore(struct device *dev); #define platform_pm_restore NULL #endif -extern int platform_dma_configure(struct device *dev); - #ifdef CONFIG_PM_SLEEP #define USE_PLATFORM_PM_SLEEP_OPS \ .suspend = platform_pm_suspend, \ -- cgit v1.2.3-71-gd317 From 512881eacfa72c2136b27b9934b7b27504a9efc2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:53 +0800 Subject: bus: platform,amba,fsl-mc,PCI: Add device DMA ownership management The devices on platform/amba/fsl-mc/PCI buses could be bound to drivers with the device DMA managed by kernel drivers or user-space applications. Unfortunately, multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. The DMA on these devices must either be entirely under kernel control or userspace control, never a mixture. Otherwise the driver integrity is not guaranteed because they could access each other through the peer-to-peer accesses which by-pass the IOMMU protection. This checks and sets the default DMA mode during driver binding, and cleanups during driver unbinding. In the default mode, the device DMA is managed by the device driver which handles DMA operations through the kernel DMA APIs (see Documentation/core-api/dma-api.rst). For cases where the devices are assigned for userspace control through the userspace driver framework(i.e. VFIO), the drivers(for example, vfio_pci/ vfio_platfrom etc.) may set a new flag (driver_managed_dma) to skip this default setting in the assumption that the drivers know what they are doing with the device DMA. Calling iommu_device_use_default_domain() before {of,acpi}_dma_configure is currently a problem. As things stand, the IOMMU driver ignored the initial iommu_probe_device() call when the device was added, since at that point it had no fwspec yet. In this situation, {of,acpi}_iommu_configure() are retriggering iommu_probe_device() after the IOMMU driver has seen the firmware data via .of_xlate to learn that it actually responsible for the given device. As the result, before that gets fixed, iommu_use_default_domain() goes at the end, and calls arch_teardown_dma_ops() if it fails. Cc: Greg Kroah-Hartman Cc: Bjorn Helgaas Cc: Stuart Yoder Cc: Laurentiu Tudor Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Reviewed-by: Robin Murphy Tested-by: Eric Auger Link: https://lore.kernel.org/r/20220418005000.897664-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/amba/bus.c | 18 ++++++++++++++++++ drivers/base/platform.c | 18 ++++++++++++++++++ drivers/bus/fsl-mc/fsl-mc-bus.c | 24 ++++++++++++++++++++++-- drivers/pci/pci-driver.c | 18 ++++++++++++++++++ include/linux/amba/bus.h | 8 ++++++++ include/linux/fsl/mc.h | 8 ++++++++ include/linux/pci.h | 8 ++++++++ include/linux/platform_device.h | 8 ++++++++ 8 files changed, 108 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 76b52bd2c2a4..a0ec61232b6c 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #define to_amba_driver(d) container_of(d, struct amba_driver, drv) @@ -277,6 +279,7 @@ static void amba_shutdown(struct device *dev) static int amba_dma_configure(struct device *dev) { + struct amba_driver *drv = to_amba_driver(dev->driver); enum dev_dma_attr attr; int ret = 0; @@ -287,9 +290,23 @@ static int amba_dma_configure(struct device *dev) ret = acpi_dma_configure(dev, attr); } + if (!ret && !drv->driver_managed_dma) { + ret = iommu_device_use_default_domain(dev); + if (ret) + arch_teardown_dma_ops(dev); + } + return ret; } +static void amba_dma_cleanup(struct device *dev) +{ + struct amba_driver *drv = to_amba_driver(dev->driver); + + if (!drv->driver_managed_dma) + iommu_device_unuse_default_domain(dev); +} + #ifdef CONFIG_PM /* * Hooks to provide runtime PM of the pclk (bus clock). It is safe to @@ -359,6 +376,7 @@ struct bus_type amba_bustype = { .remove = amba_remove, .shutdown = amba_shutdown, .dma_configure = amba_dma_configure, + .dma_cleanup = amba_dma_cleanup, .pm = &amba_pm, }; EXPORT_SYMBOL_GPL(amba_bustype); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index d7915734d931..70bc30cf575c 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -30,6 +30,8 @@ #include #include #include +#include +#include #include "base.h" #include "power/power.h" @@ -1456,6 +1458,7 @@ static void platform_shutdown(struct device *_dev) static int platform_dma_configure(struct device *dev) { + struct platform_driver *drv = to_platform_driver(dev->driver); enum dev_dma_attr attr; int ret = 0; @@ -1466,9 +1469,23 @@ static int platform_dma_configure(struct device *dev) ret = acpi_dma_configure(dev, attr); } + if (!ret && !drv->driver_managed_dma) { + ret = iommu_device_use_default_domain(dev); + if (ret) + arch_teardown_dma_ops(dev); + } + return ret; } +static void platform_dma_cleanup(struct device *dev) +{ + struct platform_driver *drv = to_platform_driver(dev->driver); + + if (!drv->driver_managed_dma) + iommu_device_unuse_default_domain(dev); +} + static const struct dev_pm_ops platform_dev_pm_ops = { SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL) USE_PLATFORM_PM_SLEEP_OPS @@ -1483,6 +1500,7 @@ struct bus_type platform_bus_type = { .remove = platform_remove, .shutdown = platform_shutdown, .dma_configure = platform_dma_configure, + .dma_cleanup = platform_dma_cleanup, .pm = &platform_dev_pm_ops, }; EXPORT_SYMBOL_GPL(platform_bus_type); diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 8fd4a356a86e..76648c4fdaf4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "fsl-mc-private.h" @@ -140,15 +141,33 @@ static int fsl_mc_dma_configure(struct device *dev) { struct device *dma_dev = dev; struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); + struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver); u32 input_id = mc_dev->icid; + int ret; while (dev_is_fsl_mc(dma_dev)) dma_dev = dma_dev->parent; if (dev_of_node(dma_dev)) - return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id); + ret = of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id); + else + ret = acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id); + + if (!ret && !mc_drv->driver_managed_dma) { + ret = iommu_device_use_default_domain(dev); + if (ret) + arch_teardown_dma_ops(dev); + } + + return ret; +} + +static void fsl_mc_dma_cleanup(struct device *dev) +{ + struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver); - return acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id); + if (!mc_drv->driver_managed_dma) + iommu_device_unuse_default_domain(dev); } static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, @@ -312,6 +331,7 @@ struct bus_type fsl_mc_bus_type = { .match = fsl_mc_bus_match, .uevent = fsl_mc_bus_uevent, .dma_configure = fsl_mc_dma_configure, + .dma_cleanup = fsl_mc_dma_cleanup, .dev_groups = fsl_mc_dev_groups, .bus_groups = fsl_mc_bus_groups, }; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 4ceeb75fc899..f83f7fbac68f 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "pci.h" #include "pcie/portdrv.h" @@ -1601,6 +1602,7 @@ static int pci_bus_num_vf(struct device *dev) */ static int pci_dma_configure(struct device *dev) { + struct pci_driver *driver = to_pci_driver(dev->driver); struct device *bridge; int ret = 0; @@ -1616,9 +1618,24 @@ static int pci_dma_configure(struct device *dev) } pci_put_host_bridge_device(bridge); + + if (!ret && !driver->driver_managed_dma) { + ret = iommu_device_use_default_domain(dev); + if (ret) + arch_teardown_dma_ops(dev); + } + return ret; } +static void pci_dma_cleanup(struct device *dev) +{ + struct pci_driver *driver = to_pci_driver(dev->driver); + + if (!driver->driver_managed_dma) + iommu_device_unuse_default_domain(dev); +} + struct bus_type pci_bus_type = { .name = "pci", .match = pci_bus_match, @@ -1632,6 +1649,7 @@ struct bus_type pci_bus_type = { .pm = PCI_PM_OPS_PTR, .num_vf = pci_bus_num_vf, .dma_configure = pci_dma_configure, + .dma_cleanup = pci_dma_cleanup, }; EXPORT_SYMBOL(pci_bus_type); diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6562f543c3e0..2ddce9bcd00e 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -79,6 +79,14 @@ struct amba_driver { void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; /* diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 7b6c42bfb660..27efef8affb1 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -32,6 +32,13 @@ struct fsl_mc_io; * @shutdown: Function called at shutdown time to quiesce the device * @suspend: Function called when a device is stopped * @resume: Function called when a device is resumed + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. * * Generic DPAA device driver object for device drivers that are registered * with a DPRC bus. This structure is to be embedded in each device-specific @@ -45,6 +52,7 @@ struct fsl_mc_driver { void (*shutdown)(struct fsl_mc_device *dev); int (*suspend)(struct fsl_mc_device *dev, pm_message_t state); int (*resume)(struct fsl_mc_device *dev); + bool driver_managed_dma; }; #define to_fsl_mc_driver(_drv) \ diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..b933d2b08d4d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -895,6 +895,13 @@ struct module; * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. */ struct pci_driver { struct list_head node; @@ -913,6 +920,7 @@ struct pci_driver { const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; + bool driver_managed_dma; }; static inline struct pci_driver *to_pci_driver(struct device_driver *drv) diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 17fde717df68..b3d9c744f1e5 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -210,6 +210,14 @@ struct platform_driver { struct device_driver driver; const struct platform_device_id *id_table; bool prevent_deferred_probe; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; #define to_platform_driver(drv) (container_of((drv), struct platform_driver, \ -- cgit v1.2.3-71-gd317 From a5f1bd1afacd7b1e088f93f66af5453df0d8be9a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:50:00 +0800 Subject: iommu: Remove iommu group changes notifier The iommu group changes notifer is not referenced in the tree. Remove it to avoid dead code. Suggested-by: Christoph Hellwig Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 75 --------------------------------------------------- include/linux/iommu.h | 23 ---------------- 2 files changed, 98 deletions(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index eba8e8ccf19d..0c42ece25854 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -40,7 +39,6 @@ struct iommu_group { struct kobject *devices_kobj; struct list_head devices; struct mutex mutex; - struct blocking_notifier_head notifier; void *iommu_data; void (*iommu_data_release)(void *iommu_data); char *name; @@ -632,7 +630,6 @@ struct iommu_group *iommu_group_alloc(void) mutex_init(&group->mutex); INIT_LIST_HEAD(&group->devices); INIT_LIST_HEAD(&group->entry); - BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL); if (ret < 0) { @@ -905,10 +902,6 @@ rename: if (ret) goto err_put_group; - /* Notify any listeners about change to group. */ - blocking_notifier_call_chain(&group->notifier, - IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); - trace_add_device_to_group(group->id, dev); dev_info(dev, "Adding to iommu group %d\n", group->id); @@ -950,10 +943,6 @@ void iommu_group_remove_device(struct device *dev) dev_info(dev, "Removing from iommu group %d\n", group->id); - /* Pre-notify listeners that a device is being removed. */ - blocking_notifier_call_chain(&group->notifier, - IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); - mutex_lock(&group->mutex); list_for_each_entry(tmp_device, &group->devices, list) { if (tmp_device->dev == dev) { @@ -1075,36 +1064,6 @@ void iommu_group_put(struct iommu_group *group) } EXPORT_SYMBOL_GPL(iommu_group_put); -/** - * iommu_group_register_notifier - Register a notifier for group changes - * @group: the group to watch - * @nb: notifier block to signal - * - * This function allows iommu group users to track changes in a group. - * See include/linux/iommu.h for actions sent via this notifier. Caller - * should hold a reference to the group throughout notifier registration. - */ -int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&group->notifier, nb); -} -EXPORT_SYMBOL_GPL(iommu_group_register_notifier); - -/** - * iommu_group_unregister_notifier - Unregister a notifier - * @group: the group to watch - * @nb: notifier block to signal - * - * Unregister a previously registered group notifier block. - */ -int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&group->notifier, nb); -} -EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); - /** * iommu_register_device_fault_handler() - Register a device fault handler * @dev: the device @@ -1650,14 +1609,8 @@ static int remove_iommu_group(struct device *dev, void *data) static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { - unsigned long group_action = 0; struct device *dev = data; - struct iommu_group *group; - /* - * ADD/DEL call into iommu driver ops if provided, which may - * result in ADD/DEL notifiers to group->notifier - */ if (action == BUS_NOTIFY_ADD_DEVICE) { int ret; @@ -1668,34 +1621,6 @@ static int iommu_bus_notifier(struct notifier_block *nb, return NOTIFY_OK; } - /* - * Remaining BUS_NOTIFYs get filtered and republished to the - * group, if anyone is listening - */ - group = iommu_group_get(dev); - if (!group) - return 0; - - switch (action) { - case BUS_NOTIFY_BIND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; - break; - case BUS_NOTIFY_BOUND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; - break; - case BUS_NOTIFY_UNBIND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; - break; - case BUS_NOTIFY_UNBOUND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; - break; - } - - if (group_action) - blocking_notifier_call_chain(&group->notifier, - group_action, dev); - - iommu_group_put(group); return 0; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 77972ef978b5..6ef2df258673 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -407,13 +407,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ -#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ -#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ -#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ -#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ -#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ - extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); @@ -478,10 +471,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, extern struct iommu_group *iommu_group_get(struct device *dev); extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); -extern int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb); -extern int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb); extern int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, void *data); @@ -878,18 +867,6 @@ static inline void iommu_group_put(struct iommu_group *group) { } -static inline int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return -ENODEV; -} - -static inline int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return 0; -} - static inline int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, -- cgit v1.2.3-71-gd317 From 6043257b1de069fbb5a2a52d7211c0275bc8c0e0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:05 -0300 Subject: iommu: Introduce the domain op enforce_cache_coherency() This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU. Currently only Intel and AMD IOMMUs are known to support this feature. They both implement it as an IOPTE bit, that when set, will cause PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though the no-snoop bit was clear. The new API is triggered by calling enforce_cache_coherency() before mapping any IOVA to the domain which globally switches on no-snoop blocking. This allows other implementations that might block no-snoop globally and outside the IOPTE - AMD also documents such a HW capability. Leave AMD out of sync with Intel and have it block no-snoop even for in-kernel users. This can be trivially resolved in a follow up patch. Only VFIO needs to call this API because it does not have detailed control over the device to avoid requesting no-snoop behavior at the device level. Other places using domains with real kernel drivers should simply avoid asking their devices to set the no-snoop bit. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/iommu.c | 7 +++++++ drivers/iommu/intel/iommu.c | 14 +++++++++++++- include/linux/intel-iommu.h | 1 + include/linux/iommu.h | 4 ++++ 4 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 038e104b922c..840831d5d2ad 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2266,6 +2266,12 @@ static int amd_iommu_def_domain_type(struct device *dev) return 0; } +static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain) +{ + /* IOMMU_PTE_FC is always set */ + return true; +} + const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, @@ -2288,6 +2294,7 @@ const struct iommu_ops amd_iommu_ops = { .flush_iotlb_all = amd_iommu_flush_iotlb_all, .iotlb_sync = amd_iommu_iotlb_sync, .free = amd_iommu_domain_free, + .enforce_cache_coherency = amd_iommu_enforce_cache_coherency, } }; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 0edf6084dc14..161199f62270 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4422,7 +4422,8 @@ static int intel_iommu_map(struct iommu_domain *domain, prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) prot |= DMA_PTE_WRITE; - if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) + if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) || + dmar_domain->force_snooping) prot |= DMA_PTE_SNP; max_addr = iova + size; @@ -4545,6 +4546,16 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, return phys; } +static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + + if (!dmar_domain->iommu_snooping) + return false; + dmar_domain->force_snooping = true; + return true; +} + static bool intel_iommu_capable(enum iommu_cap cap) { if (cap == IOMMU_CAP_CACHE_COHERENCY) @@ -4900,6 +4911,7 @@ const struct iommu_ops intel_iommu_ops = { .iotlb_sync = intel_iommu_tlb_sync, .iova_to_phys = intel_iommu_iova_to_phys, .free = intel_iommu_domain_free, + .enforce_cache_coherency = intel_iommu_enforce_cache_coherency, } }; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2f9891cb3d00..4c2baf2446c2 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 iommu_snooping: 1; /* indicate snooping control feature */ + u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4123693ae319..c7ad6b10e261 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -274,6 +274,9 @@ struct iommu_ops { * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address + * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, + * including no-snoop TLPs on PCIe or other platform + * specific mechanisms. * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @free: Release the domain after use. @@ -302,6 +305,7 @@ struct iommu_domain_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); + bool (*enforce_cache_coherency)(struct iommu_domain *domain); int (*enable_nesting)(struct iommu_domain *domain); int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks); -- cgit v1.2.3-71-gd317 From 71cfafda9c9bd9812cdb62ddb94daf65a1af12c1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:06 -0300 Subject: vfio: Move the Intel no-snoop control off of IOMMU_CACHE IOMMU_CACHE means "normal DMA to this iommu_domain's IOVA should be cache coherent" and is used by the DMA API. The definition allows for special non-coherent DMA to exist - ie processing of the no-snoop flag in PCIe TLPs - so long as this behavior is opt-in by the device driver. The flag is mainly used by the DMA API to synchronize the IOMMU setting with the expected cache behavior of the DMA master. eg based on dev_is_dma_coherent() in some case. For Intel IOMMU IOMMU_CACHE was redefined to mean 'force all DMA to be cache coherent' which has the practical effect of causing the IOMMU to ignore the no-snoop bit in a PCIe TLP. x86 platforms are always IOMMU_CACHE, so Intel should ignore this flag. Instead use the new domain op enforce_cache_coherency() which causes every IOPTE created in the domain to have the no-snoop blocking behavior. Reconfigure VFIO to always use IOMMU_CACHE and call enforce_cache_coherency() to operate the special Intel behavior. Remove the IOMMU_CACHE test from Intel IOMMU. Ultimately VFIO plumbs the result of enforce_cache_coherency() back into the x86 platform code through kvm_arch_register_noncoherent_dma() which controls if the WBINVD instruction is available in the guest. No other archs implement kvm_arch_register_noncoherent_dma() nor are there any other known consumers of VFIO_DMA_CC_IOMMU that might be affected by the user visible result change on non-x86 archs. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Alex Williamson Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 7 ++----- drivers/vfio/vfio_iommu_type1.c | 30 +++++++++++++++++++----------- include/linux/intel-iommu.h | 1 - 3 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 161199f62270..38441cb06c8c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -641,7 +641,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain) static void domain_update_iommu_cap(struct dmar_domain *domain) { domain_update_iommu_coherency(domain); - domain->iommu_snooping = domain_update_iommu_snooping(NULL); domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL); /* @@ -4283,7 +4282,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->agaw = width_to_agaw(adjust_width); domain->iommu_coherency = false; - domain->iommu_snooping = false; domain->iommu_superpage = 0; domain->max_addr = 0; @@ -4422,8 +4420,7 @@ static int intel_iommu_map(struct iommu_domain *domain, prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) prot |= DMA_PTE_WRITE; - if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) || - dmar_domain->force_snooping) + if (dmar_domain->force_snooping) prot |= DMA_PTE_SNP; max_addr = iova + size; @@ -4550,7 +4547,7 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); - if (!dmar_domain->iommu_snooping) + if (!domain_update_iommu_snooping(NULL)) return false; dmar_domain->force_snooping = true; return true; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 9394aa9444c1..c13b9290e357 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -84,8 +84,8 @@ struct vfio_domain { struct iommu_domain *domain; struct list_head next; struct list_head group_list; - int prot; /* IOMMU_CACHE */ - bool fgsp; /* Fine-grained super pages */ + bool fgsp : 1; /* Fine-grained super pages */ + bool enforce_cache_coherency : 1; }; struct vfio_dma { @@ -1461,7 +1461,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova, list_for_each_entry(d, &iommu->domain_list, next) { ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT, - npage << PAGE_SHIFT, prot | d->prot); + npage << PAGE_SHIFT, prot | IOMMU_CACHE); if (ret) goto unwind; @@ -1771,7 +1771,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, } ret = iommu_map(domain->domain, iova, phys, - size, dma->prot | domain->prot); + size, dma->prot | IOMMU_CACHE); if (ret) { if (!dma->iommu_mapped) { vfio_unpin_pages_remote(dma, iova, @@ -1859,7 +1859,7 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain) return; ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2, - IOMMU_READ | IOMMU_WRITE | domain->prot); + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); if (!ret) { size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE); @@ -2267,8 +2267,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_detach; } - if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY)) - domain->prot |= IOMMU_CACHE; + /* + * If the IOMMU can block non-coherent operations (ie PCIe TLPs with + * no-snoop set) then VFIO always turns this feature on because on Intel + * platforms it optimizes KVM to disable wbinvd emulation. + */ + if (domain->domain->ops->enforce_cache_coherency) + domain->enforce_cache_coherency = + domain->domain->ops->enforce_cache_coherency( + domain->domain); /* * Try to match an existing compatible domain. We don't want to @@ -2279,7 +2286,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, */ list_for_each_entry(d, &iommu->domain_list, next) { if (d->domain->ops == domain->domain->ops && - d->prot == domain->prot) { + d->enforce_cache_coherency == + domain->enforce_cache_coherency) { iommu_detach_group(domain->domain, group->iommu_group); if (!iommu_attach_group(d->domain, group->iommu_group)) { @@ -2611,14 +2619,14 @@ static void vfio_iommu_type1_release(void *iommu_data) kfree(iommu); } -static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu) +static int vfio_domains_have_enforce_cache_coherency(struct vfio_iommu *iommu) { struct vfio_domain *domain; int ret = 1; mutex_lock(&iommu->lock); list_for_each_entry(domain, &iommu->domain_list, next) { - if (!(domain->prot & IOMMU_CACHE)) { + if (!(domain->enforce_cache_coherency)) { ret = 0; break; } @@ -2641,7 +2649,7 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu, case VFIO_DMA_CC_IOMMU: if (!iommu) return 0; - return vfio_domains_have_iommu_cache(iommu); + return vfio_domains_have_enforce_cache_coherency(iommu); default: return 0; } diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4c2baf2446c2..72e5d7900e71 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -539,7 +539,6 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ - u8 iommu_snooping: 1; /* indicate snooping control feature */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ -- cgit v1.2.3-71-gd317 From f78dc1dad829e505d83e33dc0879887f074c52e1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:07 -0300 Subject: iommu: Redefine IOMMU_CAP_CACHE_COHERENCY as the cap flag for IOMMU_CACHE While the comment was correct that this flag was intended to convey the block no-snoop support in the IOMMU, it has become widely implemented and used to mean the IOMMU supports IOMMU_CACHE as a map flag. Only the Intel driver was different. Now that the Intel driver is using enforce_cache_coherency() update the comment to make it clear that IOMMU_CAP_CACHE_COHERENCY is only about IOMMU_CACHE. Fix the Intel driver to return true since IOMMU_CACHE always works. The two places that test this flag, usnic and vdpa, are both assigning userspace pages to a driver controlled iommu_domain and require IOMMU_CACHE behavior as they offer no way for userspace to synchronize caches. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 2 +- include/linux/iommu.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 38441cb06c8c..efcecfa5952a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4556,7 +4556,7 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) static bool intel_iommu_capable(enum iommu_cap cap) { if (cap == IOMMU_CAP_CACHE_COHERENCY) - return domain_update_iommu_snooping(NULL); + return true; if (cap == IOMMU_CAP_INTR_REMAP) return irq_remapping_enabled == 1; if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c7ad6b10e261..575ab27ede5b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -103,8 +103,7 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain) } enum iommu_cap { - IOMMU_CAP_CACHE_COHERENCY, /* IOMMU can enforce cache coherent DMA - transactions */ + IOMMU_CAP_CACHE_COHERENCY, /* IOMMU_CACHE is supported */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for -- cgit v1.2.3-71-gd317 From 6625ffb90f44efc28a3fe1432191a4eacb08c915 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:52 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for MM IOMMU This patch adds descriptions for mt8195 IOMMU which also use ARM Short-Descriptor translation table format. In mt8195, there are two smi-common HW and IOMMU, one is for vdo(video output), the other is for vpp(video processing pipe). They connects with different smi-larbs, then some setting(larbid_remap) is different. Differentiate them with the compatible string. Something like this: IOMMU(VDO) IOMMU(VPP) | | SMI_COMMON_VDO SMI_COMMON_VPP --------------- ---------------- | | ... | | ... larb0 larb2 ... larb1 larb3 ... Another change is that we have a new IOMMU that is for infra master like PCIe and USB. The infra master don't have the larb and ports, thus we rename the port header file to mt8195-memory-port.h rather than mt8195-larb-port.h. Also, the IOMMU is not only for MM, thus, we don't call it "m4u" which means "MultiMedia Memory Management UNIT". thus, use the "iommu" as the compatiable string. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-2-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/iommu/mediatek,iommu.yaml | 7 + include/dt-bindings/memory/mt8195-memory-port.h | 390 +++++++++++++++++++++ 2 files changed, 397 insertions(+) create mode 100644 include/dt-bindings/memory/mt8195-memory-port.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml index 97e8c471a5e8..2223408e91a9 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml @@ -77,6 +77,8 @@ properties: - mediatek,mt8173-m4u # generation two - mediatek,mt8183-m4u # generation two - mediatek,mt8192-m4u # generation two + - mediatek,mt8195-iommu-vdo # generation two + - mediatek,mt8195-iommu-vpp # generation two - description: mt7623 generation one items: @@ -120,6 +122,7 @@ properties: dt-binding/memory/mt8173-larb-port.h for mt8173, dt-binding/memory/mt8183-larb-port.h for mt8183, dt-binding/memory/mt8192-larb-port.h for mt8192. + dt-binding/memory/mt8195-memory-port.h for mt8195. power-domains: maxItems: 1 @@ -141,6 +144,8 @@ allOf: - mediatek,mt2712-m4u - mediatek,mt8173-m4u - mediatek,mt8192-m4u + - mediatek,mt8195-iommu-vdo + - mediatek,mt8195-iommu-vpp then: required: @@ -151,6 +156,8 @@ allOf: compatible: enum: - mediatek,mt8192-m4u + - mediatek,mt8195-iommu-vdo + - mediatek,mt8195-iommu-vpp then: required: diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h new file mode 100644 index 000000000000..c10e8b61f1e8 --- /dev/null +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -0,0 +1,390 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2/3 + * vcodec 4G ~ 8G larb19/20/21/22/23/24 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb18: port 0/1 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb18: port 2/3 + * + * This SoC have two IOMMU HWs, this is the detailed connected information: + * iommu-vdo: larb0/2/5/7/9/10/11/13/17/19/21/24/25/28 + * iommu-vpp: larb1/3/4/6/8/12/14/16/18/20/22/23/26/27 + */ + +/* MM IOMMU ports */ +/* larb0 */ +#define M4U_PORT_L0_DISP_RDMA0 MTK_M4U_ID(0, 0) +#define M4U_PORT_L0_DISP_WDMA0 MTK_M4U_ID(0, 1) +#define M4U_PORT_L0_DISP_OVL0_RDMA0 MTK_M4U_ID(0, 2) +#define M4U_PORT_L0_DISP_OVL0_RDMA1 MTK_M4U_ID(0, 3) +#define M4U_PORT_L0_DISP_OVL0_HDR MTK_M4U_ID(0, 4) +#define M4U_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 5) + +/* larb1 */ +#define M4U_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 0) +#define M4U_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 1) +#define M4U_PORT_L1_DISP_OVL0_RDMA0 MTK_M4U_ID(1, 2) +#define M4U_PORT_L1_DISP_OVL0_RDMA1 MTK_M4U_ID(1, 3) +#define M4U_PORT_L1_DISP_OVL0_HDR MTK_M4U_ID(1, 4) +#define M4U_PORT_L1_DISP_FAKE0 MTK_M4U_ID(1, 5) + +/* larb2 */ +#define M4U_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define M4U_PORT_L2_MDP_RDMA2 MTK_M4U_ID(2, 1) +#define M4U_PORT_L2_MDP_RDMA4 MTK_M4U_ID(2, 2) +#define M4U_PORT_L2_MDP_RDMA6 MTK_M4U_ID(2, 3) +#define M4U_PORT_L2_DISP_FAKE1 MTK_M4U_ID(2, 4) + +/* larb3 */ +#define M4U_PORT_L3_MDP_RDMA1 MTK_M4U_ID(3, 0) +#define M4U_PORT_L3_MDP_RDMA3 MTK_M4U_ID(3, 1) +#define M4U_PORT_L3_MDP_RDMA5 MTK_M4U_ID(3, 2) +#define M4U_PORT_L3_MDP_RDMA7 MTK_M4U_ID(3, 3) +#define M4U_PORT_L3_HDR_DS MTK_M4U_ID(3, 4) +#define M4U_PORT_L3_HDR_ADL MTK_M4U_ID(3, 5) +#define M4U_PORT_L3_DISP_FAKE1 MTK_M4U_ID(3, 6) + +/* larb4 */ +#define M4U_PORT_L4_MDP_RDMA MTK_M4U_ID(4, 0) +#define M4U_PORT_L4_MDP_FG MTK_M4U_ID(4, 1) +#define M4U_PORT_L4_MDP_OVL MTK_M4U_ID(4, 2) +#define M4U_PORT_L4_MDP_WROT MTK_M4U_ID(4, 3) +#define M4U_PORT_L4_FAKE MTK_M4U_ID(4, 4) + +/* larb5 */ +#define M4U_PORT_L5_SVPP1_MDP_RDMA MTK_M4U_ID(5, 0) +#define M4U_PORT_L5_SVPP1_MDP_FG MTK_M4U_ID(5, 1) +#define M4U_PORT_L5_SVPP1_MDP_OVL MTK_M4U_ID(5, 2) +#define M4U_PORT_L5_SVPP1_MDP_WROT MTK_M4U_ID(5, 3) +#define M4U_PORT_L5_SVPP2_MDP_RDMA MTK_M4U_ID(5, 4) +#define M4U_PORT_L5_SVPP2_MDP_FG MTK_M4U_ID(5, 5) +#define M4U_PORT_L5_SVPP2_MDP_WROT MTK_M4U_ID(5, 6) +#define M4U_PORT_L5_FAKE MTK_M4U_ID(5, 7) + +/* larb6 */ +#define M4U_PORT_L6_SVPP3_MDP_RDMA MTK_M4U_ID(6, 0) +#define M4U_PORT_L6_SVPP3_MDP_FG MTK_M4U_ID(6, 1) +#define M4U_PORT_L6_SVPP3_MDP_WROT MTK_M4U_ID(6, 2) +#define M4U_PORT_L6_FAKE MTK_M4U_ID(6, 3) + +/* larb7 */ +#define M4U_PORT_L7_IMG_WPE_RDMA0 MTK_M4U_ID(7, 0) +#define M4U_PORT_L7_IMG_WPE_RDMA1 MTK_M4U_ID(7, 1) +#define M4U_PORT_L7_IMG_WPE_WDMA0 MTK_M4U_ID(7, 2) + +/* larb8 */ +#define M4U_PORT_L8_IMG_WPE_RDMA0 MTK_M4U_ID(8, 0) +#define M4U_PORT_L8_IMG_WPE_RDMA1 MTK_M4U_ID(8, 1) +#define M4U_PORT_L8_IMG_WPE_WDMA0 MTK_M4U_ID(8, 2) + +/* larb9 */ +#define M4U_PORT_L9_IMG_IMGI_T1_A MTK_M4U_ID(9, 0) +#define M4U_PORT_L9_IMG_IMGBI_T1_A MTK_M4U_ID(9, 1) +#define M4U_PORT_L9_IMG_IMGCI_T1_A MTK_M4U_ID(9, 2) +#define M4U_PORT_L9_IMG_SMTI_T1_A MTK_M4U_ID(9, 3) +#define M4U_PORT_L9_IMG_TNCSTI_T1_A MTK_M4U_ID(9, 4) +#define M4U_PORT_L9_IMG_TNCSTI_T4_A MTK_M4U_ID(9, 5) +#define M4U_PORT_L9_IMG_YUVO_T1_A MTK_M4U_ID(9, 6) +#define M4U_PORT_L9_IMG_TIMGO_T1_A MTK_M4U_ID(9, 7) +#define M4U_PORT_L9_IMG_YUVO_T2_A MTK_M4U_ID(9, 8) +#define M4U_PORT_L9_IMG_IMGI_T1_B MTK_M4U_ID(9, 9) +#define M4U_PORT_L9_IMG_IMGBI_T1_B MTK_M4U_ID(9, 10) +#define M4U_PORT_L9_IMG_IMGCI_T1_B MTK_M4U_ID(9, 11) +#define M4U_PORT_L9_IMG_YUVO_T5_A MTK_M4U_ID(9, 12) +#define M4U_PORT_L9_IMG_SMTI_T1_B MTK_M4U_ID(9, 13) +#define M4U_PORT_L9_IMG_TNCSO_T1_A MTK_M4U_ID(9, 14) +#define M4U_PORT_L9_IMG_SMTO_T1_A MTK_M4U_ID(9, 15) +#define M4U_PORT_L9_IMG_TNCSTO_T1_A MTK_M4U_ID(9, 16) +#define M4U_PORT_L9_IMG_YUVO_T2_B MTK_M4U_ID(9, 17) +#define M4U_PORT_L9_IMG_YUVO_T5_B MTK_M4U_ID(9, 18) +#define M4U_PORT_L9_IMG_SMTO_T1_B MTK_M4U_ID(9, 19) + +/* larb10 */ +#define M4U_PORT_L10_IMG_IMGI_D1_A MTK_M4U_ID(10, 0) +#define M4U_PORT_L10_IMG_IMGCI_D1_A MTK_M4U_ID(10, 1) +#define M4U_PORT_L10_IMG_DEPI_D1_A MTK_M4U_ID(10, 2) +#define M4U_PORT_L10_IMG_DMGI_D1_A MTK_M4U_ID(10, 3) +#define M4U_PORT_L10_IMG_VIPI_D1_A MTK_M4U_ID(10, 4) +#define M4U_PORT_L10_IMG_TNRWI_D1_A MTK_M4U_ID(10, 5) +#define M4U_PORT_L10_IMG_RECI_D1_A MTK_M4U_ID(10, 6) +#define M4U_PORT_L10_IMG_SMTI_D1_A MTK_M4U_ID(10, 7) +#define M4U_PORT_L10_IMG_SMTI_D6_A MTK_M4U_ID(10, 8) +#define M4U_PORT_L10_IMG_PIMGI_P1_A MTK_M4U_ID(10, 9) +#define M4U_PORT_L10_IMG_PIMGBI_P1_A MTK_M4U_ID(10, 10) +#define M4U_PORT_L10_IMG_PIMGCI_P1_A MTK_M4U_ID(10, 11) +#define M4U_PORT_L10_IMG_PIMGI_P1_B MTK_M4U_ID(10, 12) +#define M4U_PORT_L10_IMG_PIMGBI_P1_B MTK_M4U_ID(10, 13) +#define M4U_PORT_L10_IMG_PIMGCI_P1_B MTK_M4U_ID(10, 14) +#define M4U_PORT_L10_IMG_IMG3O_D1_A MTK_M4U_ID(10, 15) +#define M4U_PORT_L10_IMG_IMG4O_D1_A MTK_M4U_ID(10, 16) +#define M4U_PORT_L10_IMG_IMG3CO_D1_A MTK_M4U_ID(10, 17) +#define M4U_PORT_L10_IMG_FEO_D1_A MTK_M4U_ID(10, 18) +#define M4U_PORT_L10_IMG_IMG2O_D1_A MTK_M4U_ID(10, 19) +#define M4U_PORT_L10_IMG_TNRWO_D1_A MTK_M4U_ID(10, 20) +#define M4U_PORT_L10_IMG_SMTO_D1_A MTK_M4U_ID(10, 21) +#define M4U_PORT_L10_IMG_WROT_P1_A MTK_M4U_ID(10, 22) +#define M4U_PORT_L10_IMG_WROT_P1_B MTK_M4U_ID(10, 23) + +/* larb11 */ +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA0_A MTK_M4U_ID(11, 0) +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA1_A MTK_M4U_ID(11, 1) +#define M4U_PORT_L11_IMG_WPE_EIS_WDMA0_A MTK_M4U_ID(11, 2) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA0_A MTK_M4U_ID(11, 3) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA1_A MTK_M4U_ID(11, 4) +#define M4U_PORT_L11_IMG_WPE_TNR_WDMA0_A MTK_M4U_ID(11, 5) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ0_A MTK_M4U_ID(11, 6) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ1_A MTK_M4U_ID(11, 7) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ0_A MTK_M4U_ID(11, 8) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ1_A MTK_M4U_ID(11, 9) + +/* larb12 */ +#define M4U_PORT_L12_IMG_FDVT_RDA MTK_M4U_ID(12, 0) +#define M4U_PORT_L12_IMG_FDVT_RDB MTK_M4U_ID(12, 1) +#define M4U_PORT_L12_IMG_FDVT_WRA MTK_M4U_ID(12, 2) +#define M4U_PORT_L12_IMG_FDVT_WRB MTK_M4U_ID(12, 3) +#define M4U_PORT_L12_IMG_ME_RDMA MTK_M4U_ID(12, 4) +#define M4U_PORT_L12_IMG_ME_WDMA MTK_M4U_ID(12, 5) +#define M4U_PORT_L12_IMG_DVS_RDMA MTK_M4U_ID(12, 6) +#define M4U_PORT_L12_IMG_DVS_WDMA MTK_M4U_ID(12, 7) +#define M4U_PORT_L12_IMG_DVP_RDMA MTK_M4U_ID(12, 8) +#define M4U_PORT_L12_IMG_DVP_WDMA MTK_M4U_ID(12, 9) + +/* larb13 */ +#define M4U_PORT_L13_CAM_CAMSV_CQI_E1 MTK_M4U_ID(13, 0) +#define M4U_PORT_L13_CAM_CAMSV_CQI_E2 MTK_M4U_ID(13, 1) +#define M4U_PORT_L13_CAM_GCAMSV_A_IMGO_0 MTK_M4U_ID(13, 2) +#define M4U_PORT_L13_CAM_SCAMSV_A_IMGO_0 MTK_M4U_ID(13, 3) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(13, 4) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(13, 5) +#define M4U_PORT_L13_CAM_GCAMSV_A_UFEO_0 MTK_M4U_ID(13, 6) +#define M4U_PORT_L13_CAM_GCAMSV_B_UFEO_0 MTK_M4U_ID(13, 7) +#define M4U_PORT_L13_CAM_PDAI_0 MTK_M4U_ID(13, 8) +#define M4U_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 9) + +/* larb14 */ +#define M4U_PORT_L14_CAM_GCAMSV_A_IMGO_1 MTK_M4U_ID(14, 0) +#define M4U_PORT_L14_CAM_SCAMSV_A_IMGO_1 MTK_M4U_ID(14, 1) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(14, 2) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(14, 3) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_0 MTK_M4U_ID(14, 4) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_1 MTK_M4U_ID(14, 5) +#define M4U_PORT_L14_CAM_IPUI MTK_M4U_ID(14, 6) +#define M4U_PORT_L14_CAM_IPU2I MTK_M4U_ID(14, 7) +#define M4U_PORT_L14_CAM_IPUO MTK_M4U_ID(14, 8) +#define M4U_PORT_L14_CAM_IPU2O MTK_M4U_ID(14, 9) +#define M4U_PORT_L14_CAM_IPU3O MTK_M4U_ID(14, 10) +#define M4U_PORT_L14_CAM_GCAMSV_A_UFEO_1 MTK_M4U_ID(14, 11) +#define M4U_PORT_L14_CAM_GCAMSV_B_UFEO_1 MTK_M4U_ID(14, 12) +#define M4U_PORT_L14_CAM_PDAI_1 MTK_M4U_ID(14, 13) +#define M4U_PORT_L14_CAM_PDAO MTK_M4U_ID(14, 14) + +/* larb15: null */ + +/* larb16 */ +#define M4U_PORT_L16_CAM_IMGO_R1 MTK_M4U_ID(16, 0) +#define M4U_PORT_L16_CAM_CQI_R1 MTK_M4U_ID(16, 1) +#define M4U_PORT_L16_CAM_CQI_R2 MTK_M4U_ID(16, 2) +#define M4U_PORT_L16_CAM_BPCI_R1 MTK_M4U_ID(16, 3) +#define M4U_PORT_L16_CAM_LSCI_R1 MTK_M4U_ID(16, 4) +#define M4U_PORT_L16_CAM_RAWI_R2 MTK_M4U_ID(16, 5) +#define M4U_PORT_L16_CAM_RAWI_R3 MTK_M4U_ID(16, 6) +#define M4U_PORT_L16_CAM_UFDI_R2 MTK_M4U_ID(16, 7) +#define M4U_PORT_L16_CAM_UFDI_R3 MTK_M4U_ID(16, 8) +#define M4U_PORT_L16_CAM_RAWI_R4 MTK_M4U_ID(16, 9) +#define M4U_PORT_L16_CAM_RAWI_R5 MTK_M4U_ID(16, 10) +#define M4U_PORT_L16_CAM_AAI_R1 MTK_M4U_ID(16, 11) +#define M4U_PORT_L16_CAM_FHO_R1 MTK_M4U_ID(16, 12) +#define M4U_PORT_L16_CAM_AAO_R1 MTK_M4U_ID(16, 13) +#define M4U_PORT_L16_CAM_TSFSO_R1 MTK_M4U_ID(16, 14) +#define M4U_PORT_L16_CAM_FLKO_R1 MTK_M4U_ID(16, 15) + +/* larb17 */ +#define M4U_PORT_L17_CAM_YUVO_R1 MTK_M4U_ID(17, 0) +#define M4U_PORT_L17_CAM_YUVO_R3 MTK_M4U_ID(17, 1) +#define M4U_PORT_L17_CAM_YUVCO_R1 MTK_M4U_ID(17, 2) +#define M4U_PORT_L17_CAM_YUVO_R2 MTK_M4U_ID(17, 3) +#define M4U_PORT_L17_CAM_RZH1N2TO_R1 MTK_M4U_ID(17, 4) +#define M4U_PORT_L17_CAM_DRZS4NO_R1 MTK_M4U_ID(17, 5) +#define M4U_PORT_L17_CAM_TNCSO_R1 MTK_M4U_ID(17, 6) + +/* larb18 */ +#define M4U_PORT_L18_CAM_CCUI MTK_M4U_ID(18, 0) +#define M4U_PORT_L18_CAM_CCUO MTK_M4U_ID(18, 1) +#define M4U_PORT_L18_CAM_CCUI2 MTK_M4U_ID(18, 2) +#define M4U_PORT_L18_CAM_CCUO2 MTK_M4U_ID(18, 3) + +/* larb19 */ +#define M4U_PORT_L19_VENC_RCPU MTK_M4U_ID(19, 0) +#define M4U_PORT_L19_VENC_REC MTK_M4U_ID(19, 1) +#define M4U_PORT_L19_VENC_BSDMA MTK_M4U_ID(19, 2) +#define M4U_PORT_L19_VENC_SV_COMV MTK_M4U_ID(19, 3) +#define M4U_PORT_L19_VENC_RD_COMV MTK_M4U_ID(19, 4) +#define M4U_PORT_L19_VENC_NBM_RDMA MTK_M4U_ID(19, 5) +#define M4U_PORT_L19_VENC_NBM_RDMA_LITE MTK_M4U_ID(19, 6) +#define M4U_PORT_L19_JPGENC_Y_RDMA MTK_M4U_ID(19, 7) +#define M4U_PORT_L19_JPGENC_C_RDMA MTK_M4U_ID(19, 8) +#define M4U_PORT_L19_JPGENC_Q_TABLE MTK_M4U_ID(19, 9) +#define M4U_PORT_L19_VENC_SUB_W_LUMA MTK_M4U_ID(19, 10) +#define M4U_PORT_L19_VENC_FCS_NBM_RDMA MTK_M4U_ID(19, 11) +#define M4U_PORT_L19_JPGENC_BSDMA MTK_M4U_ID(19, 12) +#define M4U_PORT_L19_JPGDEC_WDMA0 MTK_M4U_ID(19, 13) +#define M4U_PORT_L19_JPGDEC_BSDMA0 MTK_M4U_ID(19, 14) +#define M4U_PORT_L19_VENC_NBM_WDMA MTK_M4U_ID(19, 15) +#define M4U_PORT_L19_VENC_NBM_WDMA_LITE MTK_M4U_ID(19, 16) +#define M4U_PORT_L19_VENC_FCS_NBM_WDMA MTK_M4U_ID(19, 17) +#define M4U_PORT_L19_JPGDEC_WDMA1 MTK_M4U_ID(19, 18) +#define M4U_PORT_L19_JPGDEC_BSDMA1 MTK_M4U_ID(19, 19) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(19, 20) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(19, 21) +#define M4U_PORT_L19_VENC_CUR_LUMA MTK_M4U_ID(19, 22) +#define M4U_PORT_L19_VENC_CUR_CHROMA MTK_M4U_ID(19, 23) +#define M4U_PORT_L19_VENC_REF_LUMA MTK_M4U_ID(19, 24) +#define M4U_PORT_L19_VENC_REF_CHROMA MTK_M4U_ID(19, 25) +#define M4U_PORT_L19_VENC_SUB_R_CHROMA MTK_M4U_ID(19, 26) + +/* larb20 */ +#define M4U_PORT_L20_VENC_RCPU MTK_M4U_ID(20, 0) +#define M4U_PORT_L20_VENC_REC MTK_M4U_ID(20, 1) +#define M4U_PORT_L20_VENC_BSDMA MTK_M4U_ID(20, 2) +#define M4U_PORT_L20_VENC_SV_COMV MTK_M4U_ID(20, 3) +#define M4U_PORT_L20_VENC_RD_COMV MTK_M4U_ID(20, 4) +#define M4U_PORT_L20_VENC_NBM_RDMA MTK_M4U_ID(20, 5) +#define M4U_PORT_L20_VENC_NBM_RDMA_LITE MTK_M4U_ID(20, 6) +#define M4U_PORT_L20_JPGENC_Y_RDMA MTK_M4U_ID(20, 7) +#define M4U_PORT_L20_JPGENC_C_RDMA MTK_M4U_ID(20, 8) +#define M4U_PORT_L20_JPGENC_Q_TABLE MTK_M4U_ID(20, 9) +#define M4U_PORT_L20_VENC_SUB_W_LUMA MTK_M4U_ID(20, 10) +#define M4U_PORT_L20_VENC_FCS_NBM_RDMA MTK_M4U_ID(20, 11) +#define M4U_PORT_L20_JPGENC_BSDMA MTK_M4U_ID(20, 12) +#define M4U_PORT_L20_JPGDEC_WDMA0 MTK_M4U_ID(20, 13) +#define M4U_PORT_L20_JPGDEC_BSDMA0 MTK_M4U_ID(20, 14) +#define M4U_PORT_L20_VENC_NBM_WDMA MTK_M4U_ID(20, 15) +#define M4U_PORT_L20_VENC_NBM_WDMA_LITE MTK_M4U_ID(20, 16) +#define M4U_PORT_L20_VENC_FCS_NBM_WDMA MTK_M4U_ID(20, 17) +#define M4U_PORT_L20_JPGDEC_WDMA1 MTK_M4U_ID(20, 18) +#define M4U_PORT_L20_JPGDEC_BSDMA1 MTK_M4U_ID(20, 19) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(20, 20) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(20, 21) +#define M4U_PORT_L20_VENC_CUR_LUMA MTK_M4U_ID(20, 22) +#define M4U_PORT_L20_VENC_CUR_CHROMA MTK_M4U_ID(20, 23) +#define M4U_PORT_L20_VENC_REF_LUMA MTK_M4U_ID(20, 24) +#define M4U_PORT_L20_VENC_REF_CHROMA MTK_M4U_ID(20, 25) +#define M4U_PORT_L20_VENC_SUB_R_CHROMA MTK_M4U_ID(20, 26) + +/* larb21 */ +#define M4U_PORT_L21_VDEC_MC_EXT MTK_M4U_ID(21, 0) +#define M4U_PORT_L21_VDEC_UFO_EXT MTK_M4U_ID(21, 1) +#define M4U_PORT_L21_VDEC_PP_EXT MTK_M4U_ID(21, 2) +#define M4U_PORT_L21_VDEC_PRED_RD_EXT MTK_M4U_ID(21, 3) +#define M4U_PORT_L21_VDEC_PRED_WR_EXT MTK_M4U_ID(21, 4) +#define M4U_PORT_L21_VDEC_PPWRAP_EXT MTK_M4U_ID(21, 5) +#define M4U_PORT_L21_VDEC_TILE_EXT MTK_M4U_ID(21, 6) +#define M4U_PORT_L21_VDEC_VLD_EXT MTK_M4U_ID(21, 7) +#define M4U_PORT_L21_VDEC_VLD2_EXT MTK_M4U_ID(21, 8) +#define M4U_PORT_L21_VDEC_AVC_MV_EXT MTK_M4U_ID(21, 9) + +/* larb22 */ +#define M4U_PORT_L22_VDEC_MC_EXT MTK_M4U_ID(22, 0) +#define M4U_PORT_L22_VDEC_UFO_EXT MTK_M4U_ID(22, 1) +#define M4U_PORT_L22_VDEC_PP_EXT MTK_M4U_ID(22, 2) +#define M4U_PORT_L22_VDEC_PRED_RD_EXT MTK_M4U_ID(22, 3) +#define M4U_PORT_L22_VDEC_PRED_WR_EXT MTK_M4U_ID(22, 4) +#define M4U_PORT_L22_VDEC_PPWRAP_EXT MTK_M4U_ID(22, 5) +#define M4U_PORT_L22_VDEC_TILE_EXT MTK_M4U_ID(22, 6) +#define M4U_PORT_L22_VDEC_VLD_EXT MTK_M4U_ID(22, 7) +#define M4U_PORT_L22_VDEC_VLD2_EXT MTK_M4U_ID(22, 8) +#define M4U_PORT_L22_VDEC_AVC_MV_EXT MTK_M4U_ID(22, 9) + +/* larb23 */ +#define M4U_PORT_L23_VDEC_UFO_ENC_EXT MTK_M4U_ID(23, 0) +#define M4U_PORT_L23_VDEC_RDMA_EXT MTK_M4U_ID(23, 1) + +/* larb24 */ +#define M4U_PORT_L24_VDEC_LAT0_VLD_EXT MTK_M4U_ID(24, 0) +#define M4U_PORT_L24_VDEC_LAT0_VLD2_EXT MTK_M4U_ID(24, 1) +#define M4U_PORT_L24_VDEC_LAT0_AVC_MC_EXT MTK_M4U_ID(24, 2) +#define M4U_PORT_L24_VDEC_LAT0_PRED_RD_EXT MTK_M4U_ID(24, 3) +#define M4U_PORT_L24_VDEC_LAT0_TILE_EXT MTK_M4U_ID(24, 4) +#define M4U_PORT_L24_VDEC_LAT0_WDMA_EXT MTK_M4U_ID(24, 5) +#define M4U_PORT_L24_VDEC_LAT1_VLD_EXT MTK_M4U_ID(24, 6) +#define M4U_PORT_L24_VDEC_LAT1_VLD2_EXT MTK_M4U_ID(24, 7) +#define M4U_PORT_L24_VDEC_LAT1_AVC_MC_EXT MTK_M4U_ID(24, 8) +#define M4U_PORT_L24_VDEC_LAT1_PRED_RD_EXT MTK_M4U_ID(24, 9) +#define M4U_PORT_L24_VDEC_LAT1_TILE_EXT MTK_M4U_ID(24, 10) +#define M4U_PORT_L24_VDEC_LAT1_WDMA_EXT MTK_M4U_ID(24, 11) + +/* larb25 */ +#define M4U_PORT_L25_CAM_MRAW0_LSCI_M1 MTK_M4U_ID(25, 0) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M1 MTK_M4U_ID(25, 1) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M2 MTK_M4U_ID(25, 2) +#define M4U_PORT_L25_CAM_MRAW0_IMGO_M1 MTK_M4U_ID(25, 3) +#define M4U_PORT_L25_CAM_MRAW0_IMGBO_M1 MTK_M4U_ID(25, 4) +#define M4U_PORT_L25_CAM_MRAW2_LSCI_M1 MTK_M4U_ID(25, 5) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M1 MTK_M4U_ID(25, 6) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M2 MTK_M4U_ID(25, 7) +#define M4U_PORT_L25_CAM_MRAW2_IMGO_M1 MTK_M4U_ID(25, 8) +#define M4U_PORT_L25_CAM_MRAW2_IMGBO_M1 MTK_M4U_ID(25, 9) +#define M4U_PORT_L25_CAM_MRAW0_AFO_M1 MTK_M4U_ID(25, 10) +#define M4U_PORT_L25_CAM_MRAW2_AFO_M1 MTK_M4U_ID(25, 11) + +/* larb26 */ +#define M4U_PORT_L26_CAM_MRAW1_LSCI_M1 MTK_M4U_ID(26, 0) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M1 MTK_M4U_ID(26, 1) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M2 MTK_M4U_ID(26, 2) +#define M4U_PORT_L26_CAM_MRAW1_IMGO_M1 MTK_M4U_ID(26, 3) +#define M4U_PORT_L26_CAM_MRAW1_IMGBO_M1 MTK_M4U_ID(26, 4) +#define M4U_PORT_L26_CAM_MRAW3_LSCI_M1 MTK_M4U_ID(26, 5) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M1 MTK_M4U_ID(26, 6) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M2 MTK_M4U_ID(26, 7) +#define M4U_PORT_L26_CAM_MRAW3_IMGO_M1 MTK_M4U_ID(26, 8) +#define M4U_PORT_L26_CAM_MRAW3_IMGBO_M1 MTK_M4U_ID(26, 9) +#define M4U_PORT_L26_CAM_MRAW1_AFO_M1 MTK_M4U_ID(26, 10) +#define M4U_PORT_L26_CAM_MRAW3_AFO_M1 MTK_M4U_ID(26, 11) + +/* larb27 */ +#define M4U_PORT_L27_CAM_IMGO_R1 MTK_M4U_ID(27, 0) +#define M4U_PORT_L27_CAM_CQI_R1 MTK_M4U_ID(27, 1) +#define M4U_PORT_L27_CAM_CQI_R2 MTK_M4U_ID(27, 2) +#define M4U_PORT_L27_CAM_BPCI_R1 MTK_M4U_ID(27, 3) +#define M4U_PORT_L27_CAM_LSCI_R1 MTK_M4U_ID(27, 4) +#define M4U_PORT_L27_CAM_RAWI_R2 MTK_M4U_ID(27, 5) +#define M4U_PORT_L27_CAM_RAWI_R3 MTK_M4U_ID(27, 6) +#define M4U_PORT_L27_CAM_UFDI_R2 MTK_M4U_ID(27, 7) +#define M4U_PORT_L27_CAM_UFDI_R3 MTK_M4U_ID(27, 8) +#define M4U_PORT_L27_CAM_RAWI_R4 MTK_M4U_ID(27, 9) +#define M4U_PORT_L27_CAM_RAWI_R5 MTK_M4U_ID(27, 10) +#define M4U_PORT_L27_CAM_AAI_R1 MTK_M4U_ID(27, 11) +#define M4U_PORT_L27_CAM_FHO_R1 MTK_M4U_ID(27, 12) +#define M4U_PORT_L27_CAM_AAO_R1 MTK_M4U_ID(27, 13) +#define M4U_PORT_L27_CAM_TSFSO_R1 MTK_M4U_ID(27, 14) +#define M4U_PORT_L27_CAM_FLKO_R1 MTK_M4U_ID(27, 15) + +/* larb28 */ +#define M4U_PORT_L28_CAM_YUVO_R1 MTK_M4U_ID(28, 0) +#define M4U_PORT_L28_CAM_YUVO_R3 MTK_M4U_ID(28, 1) +#define M4U_PORT_L28_CAM_YUVCO_R1 MTK_M4U_ID(28, 2) +#define M4U_PORT_L28_CAM_YUVO_R2 MTK_M4U_ID(28, 3) +#define M4U_PORT_L28_CAM_RZH1N2TO_R1 MTK_M4U_ID(28, 4) +#define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) +#define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) + +#endif -- cgit v1.2.3-71-gd317 From dc1d99342db705efbeec517f9c6187f3b93ab423 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:53 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for infra IOMMU In mt8195, we have a new IOMMU that is for INFRA IOMMU. its masters mainly are PCIe and USB. Different with MM IOMMU, all these masters connect with IOMMU directly, there is no mediatek,larbs property for infra IOMMU. Another thing is about PCIe ports. currently the function "of_iommu_configure_dev_id" only support the id number is 1, But our PCIe have two ports, one is for reading and the other is for writing. see more about the PCIe patch in this patchset. Thus, I only list the reading id here and add the other id in our driver. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-3-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/iommu/mediatek,iommu.yaml | 13 ++++++++++++- include/dt-bindings/memory/mt8195-memory-port.h | 18 ++++++++++++++++++ include/dt-bindings/memory/mtk-memory-port.h | 2 ++ 3 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml index 2223408e91a9..eed59ec00e78 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml @@ -79,6 +79,7 @@ properties: - mediatek,mt8192-m4u # generation two - mediatek,mt8195-iommu-vdo # generation two - mediatek,mt8195-iommu-vpp # generation two + - mediatek,mt8195-iommu-infra # generation two - description: mt7623 generation one items: @@ -131,7 +132,6 @@ required: - compatible - reg - interrupts - - mediatek,larbs - '#iommu-cells' allOf: @@ -163,6 +163,17 @@ allOf: required: - power-domains + - if: # The IOMMUs don't have larbs. + not: + properties: + compatible: + contains: + const: mediatek,mt8195-iommu-infra + + then: + required: + - mediatek,larbs + additionalProperties: false examples: diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h index c10e8b61f1e8..70ba9f498eeb 100644 --- a/include/dt-bindings/memory/mt8195-memory-port.h +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -387,4 +387,22 @@ #define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) #define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) +/* Infra iommu ports */ +/* PCIe1: read: BIT16; write BIT17. */ +#define IOMMU_PORT_INFRA_PCIE1 MTK_IFAIOMMU_PERI_ID(16) +/* PCIe0: read: BIT18; write BIT19. */ +#define IOMMU_PORT_INFRA_PCIE0 MTK_IFAIOMMU_PERI_ID(18) +#define IOMMU_PORT_INFRA_SSUSB_P3_R MTK_IFAIOMMU_PERI_ID(20) +#define IOMMU_PORT_INFRA_SSUSB_P3_W MTK_IFAIOMMU_PERI_ID(21) +#define IOMMU_PORT_INFRA_SSUSB_P2_R MTK_IFAIOMMU_PERI_ID(22) +#define IOMMU_PORT_INFRA_SSUSB_P2_W MTK_IFAIOMMU_PERI_ID(23) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_R MTK_IFAIOMMU_PERI_ID(24) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_W MTK_IFAIOMMU_PERI_ID(25) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_R MTK_IFAIOMMU_PERI_ID(26) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_W MTK_IFAIOMMU_PERI_ID(27) +#define IOMMU_PORT_INFRA_SSUSB2_R MTK_IFAIOMMU_PERI_ID(28) +#define IOMMU_PORT_INFRA_SSUSB2_W MTK_IFAIOMMU_PERI_ID(29) +#define IOMMU_PORT_INFRA_SSUSB_R MTK_IFAIOMMU_PERI_ID(30) +#define IOMMU_PORT_INFRA_SSUSB_W MTK_IFAIOMMU_PERI_ID(31) + #endif diff --git a/include/dt-bindings/memory/mtk-memory-port.h b/include/dt-bindings/memory/mtk-memory-port.h index 7d64103209af..2f68a0511a25 100644 --- a/include/dt-bindings/memory/mtk-memory-port.h +++ b/include/dt-bindings/memory/mtk-memory-port.h @@ -12,4 +12,6 @@ #define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0x1f) #define MTK_M4U_TO_PORT(id) ((id) & 0x1f) +#define MTK_IFAIOMMU_PERI_ID(port) MTK_M4U_ID(0, port) + #endif -- cgit v1.2.3-71-gd317 From 2d555a3844142b9e0f876925a8475cc830cd472a Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:54 +0800 Subject: dt-bindings: mediatek: mt8186: Add binding for MM iommu Add mt8186 iommu binding. "-mm" means the iommu is for Multimedia. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220503071427.2285-4-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/iommu/mediatek,iommu.yaml | 4 + include/dt-bindings/memory/mt8186-memory-port.h | 217 +++++++++++++++++++++ 2 files changed, 221 insertions(+) create mode 100644 include/dt-bindings/memory/mt8186-memory-port.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml index eed59ec00e78..91a3629a8e6e 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml @@ -76,6 +76,7 @@ properties: - mediatek,mt8167-m4u # generation two - mediatek,mt8173-m4u # generation two - mediatek,mt8183-m4u # generation two + - mediatek,mt8186-iommu-mm # generation two - mediatek,mt8192-m4u # generation two - mediatek,mt8195-iommu-vdo # generation two - mediatek,mt8195-iommu-vpp # generation two @@ -122,6 +123,7 @@ properties: dt-binding/memory/mt8167-larb-port.h for mt8167, dt-binding/memory/mt8173-larb-port.h for mt8173, dt-binding/memory/mt8183-larb-port.h for mt8183, + dt-binding/memory/mt8186-memory-port.h for mt8186, dt-binding/memory/mt8192-larb-port.h for mt8192. dt-binding/memory/mt8195-memory-port.h for mt8195. @@ -143,6 +145,7 @@ allOf: - mediatek,mt2701-m4u - mediatek,mt2712-m4u - mediatek,mt8173-m4u + - mediatek,mt8186-iommu-mm - mediatek,mt8192-m4u - mediatek,mt8195-iommu-vdo - mediatek,mt8195-iommu-vpp @@ -155,6 +158,7 @@ allOf: properties: compatible: enum: + - mediatek,mt8186-iommu-mm - mediatek,mt8192-m4u - mediatek,mt8195-iommu-vdo - mediatek,mt8195-iommu-vpp diff --git a/include/dt-bindings/memory/mt8186-memory-port.h b/include/dt-bindings/memory/mt8186-memory-port.h new file mode 100644 index 000000000000..2bc6e4433048 --- /dev/null +++ b/include/dt-bindings/memory/mt8186-memory-port.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * + * Author: Anan Sun + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2 + * vcodec 4G ~ 8G larb4/7 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb13: port 9/10 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb14: port 4/5 + */ + +/* MM IOMMU ports */ +/* LARB 0 -- MMSYS */ +#define IOMMU_PORT_L0_DISP_POSTMASK0 MTK_M4U_ID(0, 0) +#define IOMMU_PORT_L0_REVERSED MTK_M4U_ID(0, 1) +#define IOMMU_PORT_L0_OVL_RDMA0 MTK_M4U_ID(0, 2) +#define IOMMU_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 3) + +/* LARB 1 -- MMSYS */ +#define IOMMU_PORT_L1_DISP_RDMA1 MTK_M4U_ID(1, 0) +#define IOMMU_PORT_L1_OVL_2L_RDMA0 MTK_M4U_ID(1, 1) +#define IOMMU_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 2) +#define IOMMU_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 3) +#define IOMMU_PORT_L1_DISP_FAKE1 MTK_M4U_ID(1, 4) + +/* LARB 2 -- MMSYS */ +#define IOMMU_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define IOMMU_PORT_L2_MDP_RDMA1 MTK_M4U_ID(2, 1) +#define IOMMU_PORT_L2_MDP_WROT0 MTK_M4U_ID(2, 2) +#define IOMMU_PORT_L2_MDP_WROT1 MTK_M4U_ID(2, 3) +#define IOMMU_PORT_L2_DISP_FAKE0 MTK_M4U_ID(2, 4) + +/* LARB 4 -- VDEC */ +#define IOMMU_PORT_L4_HW_VDEC_MC_EXT MTK_M4U_ID(4, 0) +#define IOMMU_PORT_L4_HW_VDEC_UFO_EXT MTK_M4U_ID(4, 1) +#define IOMMU_PORT_L4_HW_VDEC_PP_EXT MTK_M4U_ID(4, 2) +#define IOMMU_PORT_L4_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(4, 3) +#define IOMMU_PORT_L4_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(4, 4) +#define IOMMU_PORT_L4_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(4, 5) +#define IOMMU_PORT_L4_HW_VDEC_TILE_EXT MTK_M4U_ID(4, 6) +#define IOMMU_PORT_L4_HW_VDEC_VLD_EXT MTK_M4U_ID(4, 7) +#define IOMMU_PORT_L4_HW_VDEC_VLD2_EXT MTK_M4U_ID(4, 8) +#define IOMMU_PORT_L4_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(4, 9) +#define IOMMU_PORT_L4_HW_VDEC_UFO_ENC_EXT MTK_M4U_ID(4, 10) +#define IOMMU_PORT_L4_HW_VDEC_RG_CTRL_DMA_EXT MTK_M4U_ID(4, 11) +#define IOMMU_PORT_L4_HW_MINI_MDP_R0_EXT MTK_M4U_ID(4, 12) +#define IOMMU_PORT_L4_HW_MINI_MDP_W0_EXT MTK_M4U_ID(4, 13) + +/* LARB 7 -- VENC */ +#define IOMMU_PORT_L7_VENC_RCPU MTK_M4U_ID(7, 0) +#define IOMMU_PORT_L7_VENC_REC MTK_M4U_ID(7, 1) +#define IOMMU_PORT_L7_VENC_BSDMA MTK_M4U_ID(7, 2) +#define IOMMU_PORT_L7_VENC_SV_COMV MTK_M4U_ID(7, 3) +#define IOMMU_PORT_L7_VENC_RD_COMV MTK_M4U_ID(7, 4) +#define IOMMU_PORT_L7_VENC_CUR_LUMA MTK_M4U_ID(7, 5) +#define IOMMU_PORT_L7_VENC_CUR_CHROMA MTK_M4U_ID(7, 6) +#define IOMMU_PORT_L7_VENC_REF_LUMA MTK_M4U_ID(7, 7) +#define IOMMU_PORT_L7_VENC_REF_CHROMA MTK_M4U_ID(7, 8) +#define IOMMU_PORT_L7_JPGENC_Y_RDMA MTK_M4U_ID(7, 9) +#define IOMMU_PORT_L7_JPGENC_C_RDMA MTK_M4U_ID(7, 10) +#define IOMMU_PORT_L7_JPGENC_Q_TABLE MTK_M4U_ID(7, 11) +#define IOMMU_PORT_L7_JPGENC_BSDMA MTK_M4U_ID(7, 12) + +/* LARB 8 -- WPE */ +#define IOMMU_PORT_L8_WPE_RDMA_0 MTK_M4U_ID(8, 0) +#define IOMMU_PORT_L8_WPE_RDMA_1 MTK_M4U_ID(8, 1) +#define IOMMU_PORT_L8_WPE_WDMA_0 MTK_M4U_ID(8, 2) + +/* LARB 9 -- IMG-1 */ +#define IOMMU_PORT_L9_IMG_IMGI_D1 MTK_M4U_ID(9, 0) +#define IOMMU_PORT_L9_IMG_IMGBI_D1 MTK_M4U_ID(9, 1) +#define IOMMU_PORT_L9_IMG_DMGI_D1 MTK_M4U_ID(9, 2) +#define IOMMU_PORT_L9_IMG_DEPI_D1 MTK_M4U_ID(9, 3) +#define IOMMU_PORT_L9_IMG_LCE_D1 MTK_M4U_ID(9, 4) +#define IOMMU_PORT_L9_IMG_SMTI_D1 MTK_M4U_ID(9, 5) +#define IOMMU_PORT_L9_IMG_SMTO_D2 MTK_M4U_ID(9, 6) +#define IOMMU_PORT_L9_IMG_SMTO_D1 MTK_M4U_ID(9, 7) +#define IOMMU_PORT_L9_IMG_CRZO_D1 MTK_M4U_ID(9, 8) +#define IOMMU_PORT_L9_IMG_IMG3O_D1 MTK_M4U_ID(9, 9) +#define IOMMU_PORT_L9_IMG_VIPI_D1 MTK_M4U_ID(9, 10) +#define IOMMU_PORT_L9_IMG_SMTI_D5 MTK_M4U_ID(9, 11) +#define IOMMU_PORT_L9_IMG_TIMGO_D1 MTK_M4U_ID(9, 12) +#define IOMMU_PORT_L9_IMG_UFBC_W0 MTK_M4U_ID(9, 13) +#define IOMMU_PORT_L9_IMG_UFBC_R0 MTK_M4U_ID(9, 14) +#define IOMMU_PORT_L9_IMG_WPE_RDMA1 MTK_M4U_ID(9, 15) +#define IOMMU_PORT_L9_IMG_WPE_RDMA0 MTK_M4U_ID(9, 16) +#define IOMMU_PORT_L9_IMG_WPE_WDMA MTK_M4U_ID(9, 17) +#define IOMMU_PORT_L9_IMG_MFB_RDMA0 MTK_M4U_ID(9, 18) +#define IOMMU_PORT_L9_IMG_MFB_RDMA1 MTK_M4U_ID(9, 19) +#define IOMMU_PORT_L9_IMG_MFB_RDMA2 MTK_M4U_ID(9, 20) +#define IOMMU_PORT_L9_IMG_MFB_RDMA3 MTK_M4U_ID(9, 21) +#define IOMMU_PORT_L9_IMG_MFB_RDMA4 MTK_M4U_ID(9, 22) +#define IOMMU_PORT_L9_IMG_MFB_RDMA5 MTK_M4U_ID(9, 23) +#define IOMMU_PORT_L9_IMG_MFB_WDMA0 MTK_M4U_ID(9, 24) +#define IOMMU_PORT_L9_IMG_MFB_WDMA1 MTK_M4U_ID(9, 25) +#define IOMMU_PORT_L9_IMG_RESERVE6 MTK_M4U_ID(9, 26) +#define IOMMU_PORT_L9_IMG_RESERVE7 MTK_M4U_ID(9, 27) +#define IOMMU_PORT_L9_IMG_RESERVE8 MTK_M4U_ID(9, 28) + +/* LARB 11 -- IMG-2 */ +#define IOMMU_PORT_L11_IMG_IMGI_D1 MTK_M4U_ID(11, 0) +#define IOMMU_PORT_L11_IMG_IMGBI_D1 MTK_M4U_ID(11, 1) +#define IOMMU_PORT_L11_IMG_DMGI_D1 MTK_M4U_ID(11, 2) +#define IOMMU_PORT_L11_IMG_DEPI_D1 MTK_M4U_ID(11, 3) +#define IOMMU_PORT_L11_IMG_LCE_D1 MTK_M4U_ID(11, 4) +#define IOMMU_PORT_L11_IMG_SMTI_D1 MTK_M4U_ID(11, 5) +#define IOMMU_PORT_L11_IMG_SMTO_D2 MTK_M4U_ID(11, 6) +#define IOMMU_PORT_L11_IMG_SMTO_D1 MTK_M4U_ID(11, 7) +#define IOMMU_PORT_L11_IMG_CRZO_D1 MTK_M4U_ID(11, 8) +#define IOMMU_PORT_L11_IMG_IMG3O_D1 MTK_M4U_ID(11, 9) +#define IOMMU_PORT_L11_IMG_VIPI_D1 MTK_M4U_ID(11, 10) +#define IOMMU_PORT_L11_IMG_SMTI_D5 MTK_M4U_ID(11, 11) +#define IOMMU_PORT_L11_IMG_TIMGO_D1 MTK_M4U_ID(11, 12) +#define IOMMU_PORT_L11_IMG_UFBC_W0 MTK_M4U_ID(11, 13) +#define IOMMU_PORT_L11_IMG_UFBC_R0 MTK_M4U_ID(11, 14) +#define IOMMU_PORT_L11_IMG_WPE_RDMA1 MTK_M4U_ID(11, 15) +#define IOMMU_PORT_L11_IMG_WPE_RDMA0 MTK_M4U_ID(11, 16) +#define IOMMU_PORT_L11_IMG_WPE_WDMA MTK_M4U_ID(11, 17) +#define IOMMU_PORT_L11_IMG_MFB_RDMA0 MTK_M4U_ID(11, 18) +#define IOMMU_PORT_L11_IMG_MFB_RDMA1 MTK_M4U_ID(11, 19) +#define IOMMU_PORT_L11_IMG_MFB_RDMA2 MTK_M4U_ID(11, 20) +#define IOMMU_PORT_L11_IMG_MFB_RDMA3 MTK_M4U_ID(11, 21) +#define IOMMU_PORT_L11_IMG_MFB_RDMA4 MTK_M4U_ID(11, 22) +#define IOMMU_PORT_L11_IMG_MFB_RDMA5 MTK_M4U_ID(11, 23) +#define IOMMU_PORT_L11_IMG_MFB_WDMA0 MTK_M4U_ID(11, 24) +#define IOMMU_PORT_L11_IMG_MFB_WDMA1 MTK_M4U_ID(11, 25) +#define IOMMU_PORT_L11_IMG_RESERVE6 MTK_M4U_ID(11, 26) +#define IOMMU_PORT_L11_IMG_RESERVE7 MTK_M4U_ID(11, 27) +#define IOMMU_PORT_L11_IMG_RESERVE8 MTK_M4U_ID(11, 28) + +/* LARB 13 -- CAM */ +#define IOMMU_PORT_L13_CAM_MRAWI MTK_M4U_ID(13, 0) +#define IOMMU_PORT_L13_CAM_MRAWO_0 MTK_M4U_ID(13, 1) +#define IOMMU_PORT_L13_CAM_MRAWO_1 MTK_M4U_ID(13, 2) +#define IOMMU_PORT_L13_CAM_CAMSV_4 MTK_M4U_ID(13, 6) +#define IOMMU_PORT_L13_CAM_CAMSV_5 MTK_M4U_ID(13, 7) +#define IOMMU_PORT_L13_CAM_CAMSV_6 MTK_M4U_ID(13, 8) +#define IOMMU_PORT_L13_CAM_CCUI MTK_M4U_ID(13, 9) +#define IOMMU_PORT_L13_CAM_CCUO MTK_M4U_ID(13, 10) +#define IOMMU_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 11) + +/* LARB 14 -- CAM */ +#define IOMMU_PORT_L14_CAM_CCUI MTK_M4U_ID(14, 4) +#define IOMMU_PORT_L14_CAM_CCUO MTK_M4U_ID(14, 5) + +/* LARB 16 -- RAW-A */ +#define IOMMU_PORT_L16_CAM_IMGO_R1_A MTK_M4U_ID(16, 0) +#define IOMMU_PORT_L16_CAM_RRZO_R1_A MTK_M4U_ID(16, 1) +#define IOMMU_PORT_L16_CAM_CQI_R1_A MTK_M4U_ID(16, 2) +#define IOMMU_PORT_L16_CAM_BPCI_R1_A MTK_M4U_ID(16, 3) +#define IOMMU_PORT_L16_CAM_YUVO_R1_A MTK_M4U_ID(16, 4) +#define IOMMU_PORT_L16_CAM_UFDI_R2_A MTK_M4U_ID(16, 5) +#define IOMMU_PORT_L16_CAM_RAWI_R2_A MTK_M4U_ID(16, 6) +#define IOMMU_PORT_L16_CAM_RAWI_R3_A MTK_M4U_ID(16, 7) +#define IOMMU_PORT_L16_CAM_AAO_R1_A MTK_M4U_ID(16, 8) +#define IOMMU_PORT_L16_CAM_AFO_R1_A MTK_M4U_ID(16, 9) +#define IOMMU_PORT_L16_CAM_FLKO_R1_A MTK_M4U_ID(16, 10) +#define IOMMU_PORT_L16_CAM_LCESO_R1_A MTK_M4U_ID(16, 11) +#define IOMMU_PORT_L16_CAM_CRZO_R1_A MTK_M4U_ID(16, 12) +#define IOMMU_PORT_L16_CAM_LTMSO_R1_A MTK_M4U_ID(16, 13) +#define IOMMU_PORT_L16_CAM_RSSO_R1_A MTK_M4U_ID(16, 14) +#define IOMMU_PORT_L16_CAM_AAHO_R1_A MTK_M4U_ID(16, 15) +#define IOMMU_PORT_L16_CAM_LSCI_R1_A MTK_M4U_ID(16, 16) + +/* LARB 17 -- RAW-B */ +#define IOMMU_PORT_L17_CAM_IMGO_R1_B MTK_M4U_ID(17, 0) +#define IOMMU_PORT_L17_CAM_RRZO_R1_B MTK_M4U_ID(17, 1) +#define IOMMU_PORT_L17_CAM_CQI_R1_B MTK_M4U_ID(17, 2) +#define IOMMU_PORT_L17_CAM_BPCI_R1_B MTK_M4U_ID(17, 3) +#define IOMMU_PORT_L17_CAM_YUVO_R1_B MTK_M4U_ID(17, 4) +#define IOMMU_PORT_L17_CAM_UFDI_R2_B MTK_M4U_ID(17, 5) +#define IOMMU_PORT_L17_CAM_RAWI_R2_B MTK_M4U_ID(17, 6) +#define IOMMU_PORT_L17_CAM_RAWI_R3_B MTK_M4U_ID(17, 7) +#define IOMMU_PORT_L17_CAM_AAO_R1_B MTK_M4U_ID(17, 8) +#define IOMMU_PORT_L17_CAM_AFO_R1_B MTK_M4U_ID(17, 9) +#define IOMMU_PORT_L17_CAM_FLKO_R1_B MTK_M4U_ID(17, 10) +#define IOMMU_PORT_L17_CAM_LCESO_R1_B MTK_M4U_ID(17, 11) +#define IOMMU_PORT_L17_CAM_CRZO_R1_B MTK_M4U_ID(17, 12) +#define IOMMU_PORT_L17_CAM_LTMSO_R1_B MTK_M4U_ID(17, 13) +#define IOMMU_PORT_L17_CAM_RSSO_R1_B MTK_M4U_ID(17, 14) +#define IOMMU_PORT_L17_CAM_AAHO_R1_B MTK_M4U_ID(17, 15) +#define IOMMU_PORT_L17_CAM_LSCI_R1_B MTK_M4U_ID(17, 16) + +/* LARB 19 -- IPE */ +#define IOMMU_PORT_L19_IPE_DVS_RDMA MTK_M4U_ID(19, 0) +#define IOMMU_PORT_L19_IPE_DVS_WDMA MTK_M4U_ID(19, 1) +#define IOMMU_PORT_L19_IPE_DVP_RDMA MTK_M4U_ID(19, 2) +#define IOMMU_PORT_L19_IPE_DVP_WDMA MTK_M4U_ID(19, 3) + +/* LARB 20 -- IPE */ +#define IOMMU_PORT_L20_IPE_FDVT_RDA MTK_M4U_ID(20, 0) +#define IOMMU_PORT_L20_IPE_FDVT_RDB MTK_M4U_ID(20, 1) +#define IOMMU_PORT_L20_IPE_FDVT_WRA MTK_M4U_ID(20, 2) +#define IOMMU_PORT_L20_IPE_FDVT_WRB MTK_M4U_ID(20, 3) +#define IOMMU_PORT_L20_IPE_RSC_RDMA0 MTK_M4U_ID(20, 4) +#define IOMMU_PORT_L20_IPE_RSC_WDMA MTK_M4U_ID(20, 5) + +#endif -- cgit v1.2.3-71-gd317 From ea661ad6e1573d5b08c27444ff2ed403bf39ff66 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:03 +0800 Subject: iommu/vt-d: Size Page Request Queue to avoid overflow condition PRQ overflow may cause I/O throughput congestion, resulting in unnecessary degradation of I/O performance. Appropriately increasing the length of PRQ can greatly reduce the occurrence of PRQ overflow. The count of maximum page requests that can be generated in parallel by a PCIe device is statically defined in the Outstanding Page Request Capacity field of the PCIe ATS configure space. The new length of PRQ is calculated by summing up the value of Outstanding Page Request Capacity register across all devices where Page Requests are supported on the real PR-capable platform (Intel Sapphire Rapids). The result is round to the nearest higher power of 2. The PRQ length is also double sized as the VT-d IOMMU driver only updates the Page Request Queue Head Register (PQH_REG) after processing the entire queue. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220421113558.3504874-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-svm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index b3b125b332aa..207ef06ba3e1 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -9,7 +9,7 @@ #define __INTEL_SVM_H__ /* Page Request Queue depth */ -#define PRQ_ORDER 2 +#define PRQ_ORDER 4 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) -- cgit v1.2.3-71-gd317 From fc0051cb95909ab56bd8c929f24d48c9870c3e3a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:05 +0800 Subject: iommu/vt-d: Check domain force_snooping against attached devices As domain->force_snooping only impacts the devices attached with the domain, there's no need to check against all IOMMU units. On the other hand, force_snooping could be set on a domain no matter whether it has been attached or not, and once set it is an immutable flag. If no device attached, the operation always succeeds. Then this empty domain can be only attached to a device of which the IOMMU supports snoop control. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220508123525.1973626-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 53 ++++++++++++++++++++++++++++++++++++++++++--- drivers/iommu/intel/pasid.c | 42 +++++++++++++++++++++++++++++++++++ drivers/iommu/intel/pasid.h | 2 ++ include/linux/intel-iommu.h | 1 + 4 files changed, 95 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 23985cb5c8ee..f366e8c49636 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2438,7 +2438,7 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level == 5) flags |= PASID_FLAG_FL5LP; - if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED) + if (domain->force_snooping) flags |= PASID_FLAG_PAGE_SNOOP; return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid, @@ -4410,7 +4410,7 @@ static int intel_iommu_map(struct iommu_domain *domain, prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) prot |= DMA_PTE_WRITE; - if (dmar_domain->force_snooping) + if (dmar_domain->set_pte_snp) prot |= DMA_PTE_SNP; max_addr = iova + size; @@ -4533,13 +4533,60 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, return phys; } +static bool domain_support_force_snooping(struct dmar_domain *domain) +{ + struct device_domain_info *info; + bool support = true; + + assert_spin_locked(&device_domain_lock); + list_for_each_entry(info, &domain->devices, link) { + if (!ecap_sc_support(info->iommu->ecap)) { + support = false; + break; + } + } + + return support; +} + +static void domain_set_force_snooping(struct dmar_domain *domain) +{ + struct device_domain_info *info; + + assert_spin_locked(&device_domain_lock); + + /* + * Second level page table supports per-PTE snoop control. The + * iommu_map() interface will handle this by setting SNP bit. + */ + if (!domain_use_first_level(domain)) { + domain->set_pte_snp = true; + return; + } + + list_for_each_entry(info, &domain->devices, link) + intel_pasid_setup_page_snoop_control(info->iommu, info->dev, + PASID_RID2PASID); +} + static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); + unsigned long flags; - if (!domain_update_iommu_snooping(NULL)) + if (dmar_domain->force_snooping) + return true; + + spin_lock_irqsave(&device_domain_lock, flags); + if (!domain_support_force_snooping(dmar_domain)) { + spin_unlock_irqrestore(&device_domain_lock, flags); return false; + } + + domain_set_force_snooping(dmar_domain); dmar_domain->force_snooping = true; + spin_unlock_irqrestore(&device_domain_lock, flags); + return true; } diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index f8d215d85695..d19dd66a670c 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -762,3 +762,45 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, return 0; } + +/* + * Set the page snoop control for a pasid entry which has been set up. + */ +void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu, + struct device *dev, u32 pasid) +{ + struct pasid_entry *pte; + u16 did; + + spin_lock(&iommu->lock); + pte = intel_pasid_get_entry(dev, pasid); + if (WARN_ON(!pte || !pasid_pte_is_present(pte))) { + spin_unlock(&iommu->lock); + return; + } + + pasid_set_pgsnp(pte); + did = pasid_get_domain_id(pte); + spin_unlock(&iommu->lock); + + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(pte, sizeof(*pte)); + + /* + * VT-d spec 3.4 table23 states guides for cache invalidation: + * + * - PASID-selective-within-Domain PASID-cache invalidation + * - PASID-selective PASID-based IOTLB invalidation + * - If (pasid is RID_PASID) + * - Global Device-TLB invalidation to affected functions + * Else + * - PASID-based Device-TLB invalidation (with S=1 and + * Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions + */ + pasid_cache_invalidation_with_pasid(iommu, did, pasid); + qi_flush_piotlb(iommu, did, pasid, 0, -1, 0); + + /* Device IOTLB doesn't need to be flushed in caching mode. */ + if (!cap_caching_mode(iommu->cap)) + devtlb_invalidation_with_pasid(iommu, dev, pasid); +} diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index ab4408c824a5..583ea67fc783 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -123,4 +123,6 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, bool fault_ignore); int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid); void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid); +void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu, + struct device *dev, u32 pasid); #endif /* __INTEL_PASID_H */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 72e5d7900e71..4f29139bbfc3 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ + u8 set_pte_snp:1; struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ -- cgit v1.2.3-71-gd317