From c33fcc13ee0d02efe5729588e8fba8b899c8879a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 20:34:21 +0800 Subject: iommu: Use sysfs_emit() for sysfs show Use sysfs_emit() instead of the sprintf() for sysfs entries. sysfs_emit() knows the maximum of the temporary buffer used for outputting sysfs content and avoids overrunning the buffer length. Prefer 'long long' over 'long long int' as suggested by checkpatch.pl. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322123421.278852-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7c2f4bd33582..a366790fb781 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3760,8 +3760,8 @@ static ssize_t version_show(struct device *dev, { struct intel_iommu *iommu = dev_to_intel_iommu(dev); u32 ver = readl(iommu->reg + DMAR_VER_REG); - return sprintf(buf, "%d:%d\n", - DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); + return sysfs_emit(buf, "%d:%d\n", + DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); } static DEVICE_ATTR_RO(version); @@ -3769,7 +3769,7 @@ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->reg_phys); + return sysfs_emit(buf, "%llx\n", iommu->reg_phys); } static DEVICE_ATTR_RO(address); @@ -3777,7 +3777,7 @@ static ssize_t cap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->cap); + return sysfs_emit(buf, "%llx\n", iommu->cap); } static DEVICE_ATTR_RO(cap); @@ -3785,7 +3785,7 @@ static ssize_t ecap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->ecap); + return sysfs_emit(buf, "%llx\n", iommu->ecap); } static DEVICE_ATTR_RO(ecap); @@ -3793,7 +3793,7 @@ static ssize_t domains_supported_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap)); + return sysfs_emit(buf, "%ld\n", cap_ndoms(iommu->cap)); } static DEVICE_ATTR_RO(domains_supported); @@ -3801,8 +3801,9 @@ static ssize_t domains_used_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids, - cap_ndoms(iommu->cap))); + return sysfs_emit(buf, "%d\n", + bitmap_weight(iommu->domain_ids, + cap_ndoms(iommu->cap))); } static DEVICE_ATTR_RO(domains_used); -- cgit v1.2.3 From 760f41d182ec94a651977e70045fd61b57973408 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:07:57 -0700 Subject: iommu/vt-d: Remove virtual command interface Virtual command interface was introduced to allow using host PASIDs inside VMs. It is unused and abandoned due to architectural change. With this patch, we can safely remove this feature and the related helpers. Link: https://lore.kernel.org/r/20230210230206.3160144-2-jacob.jun.pan@linux.intel.com Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20230322200803.869130-2-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/cap_audit.c | 2 - drivers/iommu/intel/dmar.c | 2 - drivers/iommu/intel/iommu.c | 85 ----------------------------------------- drivers/iommu/intel/iommu.h | 2 - 4 files changed, 91 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c index 806986696841..9862dc20b35e 100644 --- a/drivers/iommu/intel/cap_audit.c +++ b/drivers/iommu/intel/cap_audit.c @@ -54,7 +54,6 @@ static inline void check_dmar_capabilities(struct intel_iommu *a, CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK); @@ -101,7 +100,6 @@ static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 6acfe879589c..0f348439ef0e 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -993,8 +993,6 @@ static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } - if (ecap_vcs(iommu->ecap)) - iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a366790fb781..6c2d1ffb5b0a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1722,9 +1722,6 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } - if (vccap_pasid(iommu->vccap)) - ioasid_unregister_allocator(&iommu->pasid_allocator); - #endif } @@ -2797,85 +2794,6 @@ out_unmap: return ret; } -#ifdef CONFIG_INTEL_IOMMU_SVM -static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data) -{ - struct intel_iommu *iommu = data; - ioasid_t ioasid; - - if (!iommu) - return INVALID_IOASID; - /* - * VT-d virtual command interface always uses the full 20 bit - * PASID range. Host can partition guest PASID range based on - * policies but it is out of guest's control. - */ - if (min < PASID_MIN || max > intel_pasid_max_id) - return INVALID_IOASID; - - if (vcmd_alloc_pasid(iommu, &ioasid)) - return INVALID_IOASID; - - return ioasid; -} - -static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data) -{ - struct intel_iommu *iommu = data; - - if (!iommu) - return; - /* - * Sanity check the ioasid owner is done at upper layer, e.g. VFIO - * We can only free the PASID when all the devices are unbound. - */ - if (ioasid_find(NULL, ioasid, NULL)) { - pr_alert("Cannot free active IOASID %d\n", ioasid); - return; - } - vcmd_free_pasid(iommu, ioasid); -} - -static void register_pasid_allocator(struct intel_iommu *iommu) -{ - /* - * If we are running in the host, no need for custom allocator - * in that PASIDs are allocated from the host system-wide. - */ - if (!cap_caching_mode(iommu->cap)) - return; - - if (!sm_supported(iommu)) { - pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n"); - return; - } - - /* - * Register a custom PASID allocator if we are running in a guest, - * guest PASID must be obtained via virtual command interface. - * There can be multiple vIOMMUs in each guest but only one allocator - * is active. All vIOMMU allocators will eventually be calling the same - * host allocator. - */ - if (!vccap_pasid(iommu->vccap)) - return; - - pr_info("Register custom PASID allocator\n"); - iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc; - iommu->pasid_allocator.free = intel_vcmd_ioasid_free; - iommu->pasid_allocator.pdata = (void *)iommu; - if (ioasid_register_allocator(&iommu->pasid_allocator)) { - pr_warn("Custom PASID allocator failed, scalable mode disabled\n"); - /* - * Disable scalable mode on this IOMMU if there - * is no custom allocator. Mixing SM capable vIOMMU - * and non-SM vIOMMU are not supported. - */ - intel_iommu_sm = 0; - } -} -#endif - static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; @@ -2964,9 +2882,6 @@ static int __init init_dmars(void) */ for_each_active_iommu(iommu, drhd) { iommu_flush_write_buffer(iommu); -#ifdef CONFIG_INTEL_IOMMU_SVM - register_pasid_allocator(iommu); -#endif iommu_set_root_entry(iommu); } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..a2010fb120e2 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -198,7 +198,6 @@ #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_slads(e) (((e) >> 45) & 0x1) -#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) (((e) >> 41) & 0x1) #define ecap_pds(e) (((e) >> 42) & 0x1) @@ -676,7 +675,6 @@ struct intel_iommu { unsigned char prq_name[16]; /* Name for PRQ interrupt */ unsigned long prq_seq_number; struct completion prq_complete; - struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; -- cgit v1.2.3 From fffaed1e24b8d114e958d180cb4a8aed3febbb5a Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:08:02 -0700 Subject: iommu/ioasid: Rename INVALID_IOASID INVALID_IOASID and IOMMU_PASID_INVALID are duplicated. Rename INVALID_IOASID and consolidate since we are moving away from IOASID infrastructure. Reviewed-by: Dave Jiang Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-7-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- Documentation/x86/sva.rst | 2 +- arch/x86/kernel/traps.c | 2 +- drivers/dma/idxd/device.c | 8 ++++---- drivers/dma/idxd/idxd.h | 1 + drivers/dma/idxd/init.c | 2 +- drivers/dma/idxd/irq.c | 2 +- drivers/iommu/intel/dmar.c | 4 ++-- drivers/iommu/intel/iommu.c | 2 +- drivers/iommu/intel/svm.c | 2 +- include/linux/ioasid.h | 1 + include/linux/iommu.h | 6 +++--- mm/init-mm.c | 4 ++-- 12 files changed, 19 insertions(+), 17 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/Documentation/x86/sva.rst b/Documentation/x86/sva.rst index 2e9b8b0f9a0f..33cb05005982 100644 --- a/Documentation/x86/sva.rst +++ b/Documentation/x86/sva.rst @@ -107,7 +107,7 @@ process share the same page tables, thus the same MSR value. PASID Life Cycle Management =========================== -PASID is initialized as INVALID_IOASID (-1) when a process is created. +PASID is initialized as IOMMU_PASID_INVALID (-1) when a process is created. Only processes that access SVA-capable devices need to have a PASID allocated. This allocation happens when a process opens/binds an SVA-capable diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d317dc3d06a3..492a60febb11 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 5f321f3b4242..6fca8fa8d3a8 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -1194,7 +1194,7 @@ static void idxd_device_set_perm_entry(struct idxd_device *idxd, { union msix_perm mperm; - if (ie->pasid == INVALID_IOASID) + if (ie->pasid == IOMMU_PASID_INVALID) return; mperm.bits = 0; @@ -1224,7 +1224,7 @@ void idxd_wq_free_irq(struct idxd_wq *wq) idxd_device_clear_perm_entry(idxd, ie); ie->vector = -1; ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; } int idxd_wq_request_irq(struct idxd_wq *wq) @@ -1240,7 +1240,7 @@ int idxd_wq_request_irq(struct idxd_wq *wq) ie = &wq->ie; ie->vector = pci_irq_vector(pdev, ie->id); - ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID; + ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : IOMMU_PASID_INVALID; idxd_device_set_perm_entry(idxd, ie); rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie); @@ -1265,7 +1265,7 @@ err_int_handle: free_irq(ie->vector, ie); err_irq: idxd_device_clear_perm_entry(idxd, ie); - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; return rc; } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 7ced8d283d98..417e602a46b6 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "registers.h" diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 640d3048368e..e6ee267da0ff 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -105,7 +105,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) ie = idxd_get_ie(idxd, msix_idx); ie->id = msix_idx; ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; spin_lock_init(&ie->list_lock); init_llist_head(&ie->pending_llist); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index aa314ebec587..242f1f0b9f09 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -80,7 +80,7 @@ static void idxd_int_handle_revoke_drain(struct idxd_irq_entry *ie) desc.opcode = DSA_OPCODE_DRAIN; desc.priv = 1; - if (ie->pasid != INVALID_IOASID) + if (ie->pasid != IOMMU_PASID_INVALID) desc.pasid = ie->pasid; desc.int_handle = ie->int_handle; portal = idxd_wq_portal_addr(wq); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 0f348439ef0e..10bb20ff50fd 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1958,7 +1958,7 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, return 0; } - if (pasid == INVALID_IOASID) + if (pasid == IOMMU_PASID_INVALID) pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), @@ -2039,7 +2039,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) if (!ratelimited) /* Using pasid -1 if pasid is not present */ dmar_fault_do_one(iommu, type, fault_reason, - pasid_present ? pasid : INVALID_IOASID, + pasid_present ? pasid : IOMMU_PASID_INVALID, source_id, guest_addr); fault_index++; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6c2d1ffb5b0a..350c33605fd3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -876,7 +876,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, return; } /* For request-without-pasid, get the pasid from context entry */ - if (intel_iommu_sm && pasid == INVALID_IOASID) + if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID) pasid = PASID_RID2PASID; dir_index = pasid >> PASID_PDE_SHIFT; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7367f56c3bad..3848a1b0800c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -273,7 +273,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid, if (WARN_ON(!mutex_is_locked(&pasid_mutex))) return -EINVAL; - if (pasid == INVALID_IOASID || pasid >= PASID_MAX) + if (pasid == IOMMU_PASID_INVALID || pasid >= PASID_MAX) return -EINVAL; svm = pasid_private_find(pasid); diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 734bf0e036ee..bbc9c6fd3310 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -7,6 +7,7 @@ #include typedef unsigned int ioasid_t; +#define INVALID_IOASID ((ioasid_t)-1) typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d3f81dc6e4dd..54f535ff9868 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -192,7 +192,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) #ifdef CONFIG_IOMMU_API @@ -1175,12 +1174,13 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream static inline bool pasid_valid(ioasid_t ioasid) { - return ioasid != INVALID_IOASID; + return ioasid != IOMMU_PASID_INVALID; } + #ifdef CONFIG_IOMMU_SVA static inline void mm_pasid_init(struct mm_struct *mm) { - mm->pasid = INVALID_IOASID; + mm->pasid = IOMMU_PASID_INVALID; } void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, diff --git a/mm/init-mm.c b/mm/init-mm.c index c9327abb771c..a084039f55d8 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -10,7 +10,7 @@ #include #include -#include +#include #include #ifndef INIT_MM_CONTEXT @@ -40,7 +40,7 @@ struct mm_struct init_mm = { .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, #ifdef CONFIG_IOMMU_SVA - .pasid = INVALID_IOASID, + .pasid = IOMMU_PASID_INVALID, #endif INIT_MM_CONTEXT(init_mm) }; -- cgit v1.2.3 From 99b5726b44230329f35b4c4d7fe1577d4f4edb31 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 Mar 2023 13:08:03 -0700 Subject: iommu: Remove ioasid infrastructure This has no use anymore, delete it all. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-8-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/dma/idxd/idxd.h | 1 - drivers/iommu/Kconfig | 5 - drivers/iommu/Makefile | 1 - drivers/iommu/intel/iommu.h | 1 - drivers/iommu/intel/svm.c | 1 - drivers/iommu/ioasid.c | 422 -------------------------------------------- drivers/iommu/iommu-sva.h | 1 - include/linux/ioasid.h | 75 -------- 8 files changed, 507 deletions(-) delete mode 100644 drivers/iommu/ioasid.c delete mode 100644 include/linux/ioasid.h (limited to 'drivers/iommu/intel') diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 417e602a46b6..dd2a6ed8949b 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index c4928514e5e2..db98c3f86e8c 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -3,10 +3,6 @@ config IOMMU_IOVA tristate -# The IOASID library may also be used by non-IOMMU_API users -config IOASID - tristate - # IOMMU_API always gets selected by whoever wants it. config IOMMU_API bool @@ -160,7 +156,6 @@ config IOMMU_DMA # Shared Virtual Addressing config IOMMU_SVA bool - select IOASID config FSL_PAMU bool "Freescale IOMMU support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index f461d0651385..769e43d780ce 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o obj-$(CONFIG_IOMMU_IO_PGTABLE_DART) += io-pgtable-dart.o -obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index a2010fb120e2..65b15be72878 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 3848a1b0800c..e95b339e9cdc 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c deleted file mode 100644 index a786c034907c..000000000000 --- a/drivers/iommu/ioasid.c +++ /dev/null @@ -1,422 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * I/O Address Space ID allocator. There is one global IOASID space, split into - * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and - * free IOASIDs with ioasid_alloc() and ioasid_free(). - */ -#include -#include -#include -#include -#include - -struct ioasid_data { - ioasid_t id; - struct ioasid_set *set; - void *private; - struct rcu_head rcu; -}; - -/* - * struct ioasid_allocator_data - Internal data structure to hold information - * about an allocator. There are two types of allocators: - * - * - Default allocator always has its own XArray to track the IOASIDs allocated. - * - Custom allocators may share allocation helpers with different private data. - * Custom allocators that share the same helper functions also share the same - * XArray. - * Rules: - * 1. Default allocator is always available, not dynamically registered. This is - * to prevent race conditions with early boot code that want to register - * custom allocators or allocate IOASIDs. - * 2. Custom allocators take precedence over the default allocator. - * 3. When all custom allocators sharing the same helper functions are - * unregistered (e.g. due to hotplug), all outstanding IOASIDs must be - * freed. Otherwise, outstanding IOASIDs will be lost and orphaned. - * 4. When switching between custom allocators sharing the same helper - * functions, outstanding IOASIDs are preserved. - * 5. When switching between custom allocator and default allocator, all IOASIDs - * must be freed to ensure unadulterated space for the new allocator. - * - * @ops: allocator helper functions and its data - * @list: registered custom allocators - * @slist: allocators share the same ops but different data - * @flags: attributes of the allocator - * @xa: xarray holds the IOASID space - * @rcu: used for kfree_rcu when unregistering allocator - */ -struct ioasid_allocator_data { - struct ioasid_allocator_ops *ops; - struct list_head list; - struct list_head slist; -#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */ - unsigned long flags; - struct xarray xa; - struct rcu_head rcu; -}; - -static DEFINE_SPINLOCK(ioasid_allocator_lock); -static LIST_HEAD(allocators_list); - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque); -static void default_free(ioasid_t ioasid, void *opaque); - -static struct ioasid_allocator_ops default_ops = { - .alloc = default_alloc, - .free = default_free, -}; - -static struct ioasid_allocator_data default_allocator = { - .ops = &default_ops, - .flags = 0, - .xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC), -}; - -static struct ioasid_allocator_data *active_allocator = &default_allocator; - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque) -{ - ioasid_t id; - - if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) { - pr_err("Failed to alloc ioasid from %d to %d\n", min, max); - return INVALID_IOASID; - } - - return id; -} - -static void default_free(ioasid_t ioasid, void *opaque) -{ - struct ioasid_data *ioasid_data; - - ioasid_data = xa_erase(&default_allocator.xa, ioasid); - kfree_rcu(ioasid_data, rcu); -} - -/* Allocate and initialize a new custom allocator with its helper functions */ -static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - - ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC); - if (!ia_data) - return NULL; - - xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC); - INIT_LIST_HEAD(&ia_data->slist); - ia_data->flags |= IOASID_ALLOCATOR_CUSTOM; - ia_data->ops = ops; - - /* For tracking custom allocators that share the same ops */ - list_add_tail(&ops->list, &ia_data->slist); - - return ia_data; -} - -static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b) -{ - return (a->free == b->free) && (a->alloc == b->alloc); -} - -/** - * ioasid_register_allocator - register a custom allocator - * @ops: the custom allocator ops to be registered - * - * Custom allocators take precedence over the default xarray based allocator. - * Private data associated with the IOASID allocated by the custom allocators - * are managed by IOASID framework similar to data stored in xa by default - * allocator. - * - * There can be multiple allocators registered but only one is active. In case - * of runtime removal of a custom allocator, the next one is activated based - * on the registration ordering. - * - * Multiple allocators can share the same alloc() function, in this case the - * IOASID space is shared. - */ -int ioasid_register_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - struct ioasid_allocator_data *pallocator; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - - ia_data = ioasid_alloc_allocator(ops); - if (!ia_data) { - ret = -ENOMEM; - goto out_unlock; - } - - /* - * No particular preference, we activate the first one and keep - * the later registered allocators in a list in case the first one gets - * removed due to hotplug. - */ - if (list_empty(&allocators_list)) { - WARN_ON(active_allocator != &default_allocator); - /* Use this new allocator if default is not active */ - if (xa_empty(&active_allocator->xa)) { - rcu_assign_pointer(active_allocator, ia_data); - list_add_tail(&ia_data->list, &allocators_list); - goto out_unlock; - } - pr_warn("Default allocator active with outstanding IOASID\n"); - ret = -EAGAIN; - goto out_free; - } - - /* Check if the allocator is already registered */ - list_for_each_entry(pallocator, &allocators_list, list) { - if (pallocator->ops == ops) { - pr_err("IOASID allocator already registered\n"); - ret = -EEXIST; - goto out_free; - } else if (use_same_ops(pallocator->ops, ops)) { - /* - * If the new allocator shares the same ops, - * then they will share the same IOASID space. - * We should put them under the same xarray. - */ - list_add_tail(&ops->list, &pallocator->slist); - goto out_free; - } - } - list_add_tail(&ia_data->list, &allocators_list); - - spin_unlock(&ioasid_allocator_lock); - return 0; -out_free: - kfree(ia_data); -out_unlock: - spin_unlock(&ioasid_allocator_lock); - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_register_allocator); - -/** - * ioasid_unregister_allocator - Remove a custom IOASID allocator ops - * @ops: the custom allocator to be removed - * - * Remove an allocator from the list, activate the next allocator in - * the order it was registered. Or revert to default allocator if all - * custom allocators are unregistered without outstanding IOASIDs. - */ -void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *pallocator; - struct ioasid_allocator_ops *sops; - - spin_lock(&ioasid_allocator_lock); - if (list_empty(&allocators_list)) { - pr_warn("No custom IOASID allocators active!\n"); - goto exit_unlock; - } - - list_for_each_entry(pallocator, &allocators_list, list) { - if (!use_same_ops(pallocator->ops, ops)) - continue; - - if (list_is_singular(&pallocator->slist)) { - /* No shared helper functions */ - list_del(&pallocator->list); - /* - * All IOASIDs should have been freed before - * the last allocator that shares the same ops - * is unregistered. - */ - WARN_ON(!xa_empty(&pallocator->xa)); - if (list_empty(&allocators_list)) { - pr_info("No custom IOASID allocators, switch to default.\n"); - rcu_assign_pointer(active_allocator, &default_allocator); - } else if (pallocator == active_allocator) { - rcu_assign_pointer(active_allocator, - list_first_entry(&allocators_list, - struct ioasid_allocator_data, list)); - pr_info("IOASID allocator changed"); - } - kfree_rcu(pallocator, rcu); - break; - } - /* - * Find the matching shared ops to delete, - * but keep outstanding IOASIDs - */ - list_for_each_entry(sops, &pallocator->slist, list) { - if (sops == ops) { - list_del(&ops->list); - break; - } - } - break; - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_unregister_allocator); - -/** - * ioasid_set_data - Set private data for an allocated ioasid - * @ioasid: the ID to set data - * @data: the private data - * - * For IOASID that is already allocated, private data can be set - * via this API. Future lookup can be done via ioasid_find. - */ -int ioasid_set_data(ioasid_t ioasid, void *data) -{ - struct ioasid_data *ioasid_data; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (ioasid_data) - rcu_assign_pointer(ioasid_data->private, data); - else - ret = -ENOENT; - spin_unlock(&ioasid_allocator_lock); - - /* - * Wait for readers to stop accessing the old private data, so the - * caller can free it. - */ - if (!ret) - synchronize_rcu(); - - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_set_data); - -/** - * ioasid_alloc - Allocate an IOASID - * @set: the IOASID set - * @min: the minimum ID (inclusive) - * @max: the maximum ID (inclusive) - * @private: data private to the caller - * - * Allocate an ID between @min and @max. The @private pointer is stored - * internally and can be retrieved with ioasid_find(). - * - * Return: the allocated ID on success, or %INVALID_IOASID on failure. - */ -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private) -{ - struct ioasid_data *data; - void *adata; - ioasid_t id; - - data = kzalloc(sizeof(*data), GFP_ATOMIC); - if (!data) - return INVALID_IOASID; - - data->set = set; - data->private = private; - - /* - * Custom allocator needs allocator data to perform platform specific - * operations. - */ - spin_lock(&ioasid_allocator_lock); - adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data; - id = active_allocator->ops->alloc(min, max, adata); - if (id == INVALID_IOASID) { - pr_err("Failed ASID allocation %lu\n", active_allocator->flags); - goto exit_free; - } - - if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) && - xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) { - /* Custom allocator needs framework to store and track allocation results */ - pr_err("Failed to alloc ioasid from %d\n", id); - active_allocator->ops->free(id, active_allocator->ops->pdata); - goto exit_free; - } - data->id = id; - - spin_unlock(&ioasid_allocator_lock); - return id; -exit_free: - spin_unlock(&ioasid_allocator_lock); - kfree(data); - return INVALID_IOASID; -} -EXPORT_SYMBOL_GPL(ioasid_alloc); - -/** - * ioasid_free - Free an ioasid - * @ioasid: the ID to remove - */ -void ioasid_free(ioasid_t ioasid) -{ - struct ioasid_data *ioasid_data; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (!ioasid_data) { - pr_err("Trying to free unknown IOASID %u\n", ioasid); - goto exit_unlock; - } - - active_allocator->ops->free(ioasid, active_allocator->ops->pdata); - /* Custom allocator needs additional steps to free the xa element */ - if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { - ioasid_data = xa_erase(&active_allocator->xa, ioasid); - kfree_rcu(ioasid_data, rcu); - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_free); - -/** - * ioasid_find - Find IOASID data - * @set: the IOASID set - * @ioasid: the IOASID to find - * @getter: function to call on the found object - * - * The optional getter function allows to take a reference to the found object - * under the rcu lock. The function can also check if the object is still valid: - * if @getter returns false, then the object is invalid and NULL is returned. - * - * If the IOASID exists, return the private pointer passed to ioasid_alloc. - * Private data can be NULL if not set. Return an error if the IOASID is not - * found, or if @set is not NULL and the IOASID does not belong to the set. - */ -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - void *priv; - struct ioasid_data *ioasid_data; - struct ioasid_allocator_data *idata; - - rcu_read_lock(); - idata = rcu_dereference(active_allocator); - ioasid_data = xa_load(&idata->xa, ioasid); - if (!ioasid_data) { - priv = ERR_PTR(-ENOENT); - goto unlock; - } - if (set && ioasid_data->set != set) { - /* data found but does not belong to the set */ - priv = ERR_PTR(-EACCES); - goto unlock; - } - /* Now IOASID and its set is verified, we can return the private data */ - priv = rcu_dereference(ioasid_data->private); - if (getter && !getter(priv)) - priv = NULL; -unlock: - rcu_read_unlock(); - - return priv; -} -EXPORT_SYMBOL_GPL(ioasid_find); - -MODULE_AUTHOR("Jean-Philippe Brucker "); -MODULE_AUTHOR("Jacob Pan "); -MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator"); -MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h index c22d0174ad61..54946b5a7caf 100644 --- a/drivers/iommu/iommu-sva.h +++ b/drivers/iommu/iommu-sva.h @@ -5,7 +5,6 @@ #ifndef _IOMMU_SVA_H #define _IOMMU_SVA_H -#include #include /* I/O Page fault */ diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h deleted file mode 100644 index bbc9c6fd3310..000000000000 --- a/include/linux/ioasid.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_IOASID_H -#define __LINUX_IOASID_H - -#include -#include -#include - -typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) -typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); -typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); - -struct ioasid_set { - int dummy; -}; - -/** - * struct ioasid_allocator_ops - IOASID allocator helper functions and data - * - * @alloc: helper function to allocate IOASID - * @free: helper function to free IOASID - * @list: for tracking ops that share helper functions but not data - * @pdata: data belong to the allocator, provided when calling alloc() - */ -struct ioasid_allocator_ops { - ioasid_alloc_fn_t alloc; - ioasid_free_fn_t free; - struct list_head list; - void *pdata; -}; - -#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } - -#if IS_ENABLED(CONFIG_IOASID) -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private); -void ioasid_free(ioasid_t ioasid); -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)); -int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); -void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); -int ioasid_set_data(ioasid_t ioasid, void *data); - -#else /* !CONFIG_IOASID */ -static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, - ioasid_t max, void *private) -{ - return INVALID_IOASID; -} - -static inline void ioasid_free(ioasid_t ioasid) { } - -static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - return NULL; -} - -static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) -{ - return -ENOTSUPP; -} - -static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) -{ -} - -static inline int ioasid_set_data(ioasid_t ioasid, void *data) -{ - return -ENOTSUPP; -} - -#endif /* CONFIG_IOASID */ -#endif /* __LINUX_IOASID_H */ -- cgit v1.2.3 From a86fb7717320bf2c05701cbcfaab5afc452d1480 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:30 +0800 Subject: iommu/vt-d: Allow SVA with device-specific IOPF Currently enabling SVA requires IOPF support from the IOMMU and device PCI PRI. However, some devices can handle IOPF by itself without ever sending PCI page requests nor advertising PRI capability. Allow SVA support with IOPF handled either by IOMMU (PCI PRI) or device driver (device-specific IOPF). As long as IOPF could be handled, SVA should continue to work. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7c2f4bd33582..caf664448ee9 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4650,7 +4650,21 @@ static int intel_iommu_enable_sva(struct device *dev) if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE)) return -ENODEV; - if (!info->pasid_enabled || !info->pri_enabled || !info->ats_enabled) + if (!info->pasid_enabled || !info->ats_enabled) + return -EINVAL; + + /* + * Devices having device-specific I/O fault handling should not + * support PCI/PRI. The IOMMU side has no means to check the + * capability of device-specific IOPF. Therefore, IOMMU can only + * default that if the device driver enables SVA on a non-PRI + * device, it will handle IOPF in its own way. + */ + if (!info->pri_supported) + return 0; + + /* Devices supporting PRI should have it enabled. */ + if (!info->pri_enabled) return -EINVAL; ret = iopf_queue_add_device(iommu->iopf_queue, dev); -- cgit v1.2.3 From 3d4c7cc3d168dc728dd3472688b2360b6db124e3 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:31 +0800 Subject: iommu/vt-d: Move iopf code from SVA to IOPF enabling path Generally enabling IOMMU_DEV_FEAT_SVA requires IOMMU_DEV_FEAT_IOPF, but some devices manage I/O Page Faults themselves instead of relying on the IOMMU. Move IOPF related code from SVA to IOPF enabling path. For the device drivers that relies on the IOMMU for IOPF through PCI/PRI, IOMMU_DEV_FEAT_IOPF must be enabled before and disabled after IOMMU_DEV_FEAT_SVA. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index caf664448ee9..a6f07c74da2d 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4638,7 +4638,6 @@ static int intel_iommu_enable_sva(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; - int ret; if (!info || dmar_disabled) return -EINVAL; @@ -4667,6 +4666,21 @@ static int intel_iommu_enable_sva(struct device *dev) if (!info->pri_enabled) return -EINVAL; + return 0; +} + +static int intel_iommu_enable_iopf(struct device *dev) +{ + struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu; + int ret; + + if (!info || !info->ats_enabled || !info->pri_enabled) + return -ENODEV; + iommu = info->iommu; + if (!iommu) + return -EINVAL; + ret = iopf_queue_add_device(iommu->iopf_queue, dev); if (ret) return ret; @@ -4678,7 +4692,7 @@ static int intel_iommu_enable_sva(struct device *dev) return ret; } -static int intel_iommu_disable_sva(struct device *dev) +static int intel_iommu_disable_iopf(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; @@ -4695,16 +4709,6 @@ static int intel_iommu_disable_sva(struct device *dev) return ret; } -static int intel_iommu_enable_iopf(struct device *dev) -{ - struct device_domain_info *info = dev_iommu_priv_get(dev); - - if (info && info->pri_supported) - return 0; - - return -ENODEV; -} - static int intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) { @@ -4725,10 +4729,10 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) { switch (feat) { case IOMMU_DEV_FEAT_IOPF: - return 0; + return intel_iommu_disable_iopf(dev); case IOMMU_DEV_FEAT_SVA: - return intel_iommu_disable_sva(dev); + return 0; default: return -ENODEV; -- cgit v1.2.3 From 5ae4008055fed503f7bf42aeed45d3b032a79876 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:32 +0800 Subject: iommu/vt-d: Move pfsid and ats_qdep calculation to device probe path They should be part of the per-device iommu private data initialization. Reviewed-by: Jacob Pan Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a6f07c74da2d..6d77b4072fdd 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1406,20 +1406,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) return; pdev = to_pci_dev(info->dev); - /* For IOMMU that supports device IOTLB throttling (DIT), we assign - * PFSID to the invalidation desc of a VF such that IOMMU HW can gauge - * queue depth at PF level. If DIT is not set, PFSID will be treated as - * reserved, which should be set to 0. - */ - if (!ecap_dit(info->iommu->ecap)) - info->pfsid = 0; - else { - struct pci_dev *pf_pdev; - - /* pdev will be returned if device is not a vf */ - pf_pdev = pci_physfn(pdev); - info->pfsid = pci_dev_id(pf_pdev); - } /* The PCIe spec, in its wisdom, declares that the behaviour of the device if you enable PASID support after ATS support is @@ -1438,7 +1424,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; domain_update_iotlb(info->domain); - info->ats_qdep = pci_ats_queue_depth(pdev); } } @@ -4521,6 +4506,17 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + + /* + * For IOMMU that supports device IOTLB throttling + * (DIT), we assign PFSID to the invalidation desc + * of a VF such that IOMMU HW can gauge queue depth + * at PF level. If DIT is not set, PFSID will be + * treated as reserved, which should be set to 0. + */ + if (ecap_dit(iommu->ecap)) + info->pfsid = pci_dev_id(pci_physfn(pdev)); + info->ats_qdep = pci_ats_queue_depth(pdev); } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { -- cgit v1.2.3 From fbcde5bb92bd3d299688d615dce26c59d3f63694 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:33 +0800 Subject: iommu/vt-d: Move PRI handling to IOPF feature path PRI is only used for IOPF. With this move, the PCI/PRI feature could be controlled by the device driver through iommu_dev_enable/disable_feature() interfaces. Reviewed-by: Jacob Pan Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 53 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 12 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6d77b4072fdd..cd3a3c4b5e64 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1415,11 +1415,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) if (info->pasid_supported && !pci_enable_pasid(pdev, info->pasid_supported & ~1)) info->pasid_enabled = 1; - if (info->pri_supported && - (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1) && - !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH)) - info->pri_enabled = 1; - if (info->ats_supported && pci_ats_page_aligned(pdev) && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; @@ -1442,11 +1437,6 @@ static void iommu_disable_pci_caps(struct device_domain_info *info) domain_update_iotlb(info->domain); } - if (info->pri_enabled) { - pci_disable_pri(pdev); - info->pri_enabled = 0; - } - if (info->pasid_enabled) { pci_disable_pasid(pdev); info->pasid_enabled = 0; @@ -4667,23 +4657,48 @@ static int intel_iommu_enable_sva(struct device *dev) static int intel_iommu_enable_iopf(struct device *dev) { + struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL; struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; int ret; - if (!info || !info->ats_enabled || !info->pri_enabled) + if (!pdev || !info || !info->ats_enabled || !info->pri_supported) return -ENODEV; + + if (info->pri_enabled) + return -EBUSY; + iommu = info->iommu; if (!iommu) return -EINVAL; + /* PASID is required in PRG Response Message. */ + if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev)) + return -EINVAL; + + ret = pci_reset_pri(pdev); + if (ret) + return ret; + ret = iopf_queue_add_device(iommu->iopf_queue, dev); if (ret) return ret; ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); if (ret) - iopf_queue_remove_device(iommu->iopf_queue, dev); + goto iopf_remove_device; + + ret = pci_enable_pri(pdev, PRQ_DEPTH); + if (ret) + goto iopf_unregister_handler; + info->pri_enabled = 1; + + return 0; + +iopf_unregister_handler: + iommu_unregister_device_fault_handler(dev); +iopf_remove_device: + iopf_queue_remove_device(iommu->iopf_queue, dev); return ret; } @@ -4694,6 +4709,20 @@ static int intel_iommu_disable_iopf(struct device *dev) struct intel_iommu *iommu = info->iommu; int ret; + if (!info->pri_enabled) + return -EINVAL; + + /* + * PCIe spec states that by clearing PRI enable bit, the Page + * Request Interface will not issue new page requests, but has + * outstanding page requests that have been transmitted or are + * queued for transmission. This is supposed to be called after + * the device driver has stopped DMA, all PASIDs have been + * unbound and the outstanding PRQs have been drained. + */ + pci_disable_pri(to_pci_dev(dev)); + info->pri_enabled = 0; + ret = iommu_unregister_device_fault_handler(dev); if (ret) return ret; -- cgit v1.2.3 From 7b8aa998d627afeef576ab61bf8e286f56439bb2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:34 +0800 Subject: iommu/vt-d: Remove unnecessary checks in iopf disabling path iommu_unregister_device_fault_handler() and iopf_queue_remove_device() are called after device has stopped issuing new page falut requests and all outstanding page requests have been drained. They should never fail. Trigger a warning if it happens unfortunately. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index cd3a3c4b5e64..c771233d6f2a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4707,7 +4707,6 @@ static int intel_iommu_disable_iopf(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; - int ret; if (!info->pri_enabled) return -EINVAL; @@ -4723,15 +4722,15 @@ static int intel_iommu_disable_iopf(struct device *dev) pci_disable_pri(to_pci_dev(dev)); info->pri_enabled = 0; - ret = iommu_unregister_device_fault_handler(dev); - if (ret) - return ret; - - ret = iopf_queue_remove_device(iommu->iopf_queue, dev); - if (ret) - iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + /* + * With PRI disabled and outstanding PRQs drained, unregistering + * fault handler and removing device from iopf queue should never + * fail. + */ + WARN_ON(iommu_unregister_device_fault_handler(dev)); + WARN_ON(iopf_queue_remove_device(iommu->iopf_queue, dev)); - return ret; + return 0; } static int -- cgit v1.2.3 From 41d71e09a155a05bd9bec08dd195d8d8e0146ad8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 13 Apr 2023 12:06:35 +0800 Subject: iommu/vt-d: Do not use GFP_ATOMIC when not needed There is no need to use GFP_ATOMIC here. GFP_KERNEL is already used for some other memory allocations just a few lines above. Commit e3a981d61d15 ("iommu/vt-d: Convert allocations to GFP_KERNEL") has changed the other memory allocation flags. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/e2a8a1019ffc8a86b4b4ed93def3623f60581274.1675542576.git.christophe.jaillet@wanadoo.fr Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/irq_remapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 6d01fa078c36..013ccc25ee4f 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -552,7 +552,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) goto out_free_table; } - bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC); + bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_KERNEL); if (bitmap == NULL) { pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id); goto out_free_pages; -- cgit v1.2.3 From a06c2ecec113fa882f48eb71e9d7e8fb520b1c78 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:36 +0800 Subject: iommu/vt-d: Remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from drivers/iommu/intel/iommu.h as they are not needed. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230331045452.500265-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..f843493dc4f2 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -796,18 +796,18 @@ static inline bool context_present(struct context_entry *context) return (context->lo & 1); } -extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); - -extern int dmar_enable_qi(struct intel_iommu *iommu); -extern void dmar_disable_qi(struct intel_iommu *iommu); -extern int dmar_reenable_qi(struct intel_iommu *iommu); -extern void qi_global_iec(struct intel_iommu *iommu); - -extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, - u8 fm, u64 type); -extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, - unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, +struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev); + +int dmar_enable_qi(struct intel_iommu *iommu); +void dmar_disable_qi(struct intel_iommu *iommu); +int dmar_reenable_qi(struct intel_iommu *iommu); +void qi_global_iec(struct intel_iommu *iommu); + +void qi_flush_context(struct intel_iommu *iommu, u16 did, + u16 sid, u8 fm, u64 type); +void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, + unsigned int size_order, u64 type); +void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, @@ -830,7 +830,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, */ #define QI_OPT_WAIT_DRAIN BIT(0) -extern int dmar_ir_support(void); +int dmar_ir_support(void); void *alloc_pgtable_page(int node, gfp_t gfp); void free_pgtable_page(void *vaddr); @@ -838,9 +838,9 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM -extern void intel_svm_check(struct intel_iommu *iommu); -extern int intel_svm_enable_prq(struct intel_iommu *iommu); -extern int intel_svm_finish_prq(struct intel_iommu *iommu); +void intel_svm_check(struct intel_iommu *iommu); +int intel_svm_enable_prq(struct intel_iommu *iommu); +int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); struct iommu_domain *intel_svm_domain_alloc(void); @@ -887,8 +887,8 @@ extern const struct iommu_ops intel_iommu_ops; #ifdef CONFIG_INTEL_IOMMU extern int intel_iommu_sm; -extern int iommu_calculate_agaw(struct intel_iommu *iommu); -extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); +int iommu_calculate_agaw(struct intel_iommu *iommu); +int iommu_calculate_max_sagaw(struct intel_iommu *iommu); int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob); static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu) -- cgit v1.2.3 From a7050fbde36e0634f89d41e6384c140fe4ae011e Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 13 Apr 2023 12:06:37 +0800 Subject: iommu/vt-d: Use non-privileged mode for all PASIDs Supervisor Request Enable (SRE) bit in a PASID entry is for permission checking on DMA requests. When SRE = 0, DMA with supervisor privilege will be blocked. However, for in-kernel DMA this is not necessary in that we are targeting kernel memory anyway. There's no need to differentiate user and kernel for in-kernel DMA. Let's use non-privileged (user) permission for all PASIDs used in kernel, it will be consistent with DMA without PASID (RID_PASID) as well. Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230331231137.1947675-2-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c771233d6f2a..f4e536fd5a28 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2316,8 +2316,6 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level != 4 && level != 5) return -EINVAL; - if (pasid != PASID_RID2PASID) - flags |= PASID_FLAG_SUPERVISOR_MODE; if (level == 5) flags |= PASID_FLAG_FL5LP; -- cgit v1.2.3 From 113a031becc8a1b904d7fd873fb3d329f203d2f0 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 13 Apr 2023 12:06:38 +0800 Subject: iommu/vt-d: Remove PASID supervisor request support There's no more usage, remove PASID supervisor support. Suggested-by: Lu Baolu Reviewed-by: Lu Baolu Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230331231137.1947675-3-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/pasid.c | 43 ------------------------------------------- drivers/iommu/intel/pasid.h | 7 ------- 2 files changed, 50 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 633e0a4a01e7..c5d479770e12 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -335,15 +335,6 @@ static inline void pasid_set_fault_enable(struct pasid_entry *pe) pasid_set_bits(&pe->val[0], 1 << 1, 0); } -/* - * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a - * scalable mode PASID entry. - */ -static inline void pasid_set_sre(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 0, 1); -} - /* * Setup the WPE(Write Protect Enable) field (Bit 132) of a * scalable mode PASID entry. @@ -521,23 +512,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, return -EINVAL; } - if (flags & PASID_FLAG_SUPERVISOR_MODE) { -#ifdef CONFIG_X86 - unsigned long cr0 = read_cr0(); - - /* CR0.WP is normally set but just to be sure */ - if (unlikely(!(cr0 & X86_CR0_WP))) { - pr_err("No CPU write protect!\n"); - return -EINVAL; - } -#endif - if (!ecap_srs(iommu->ecap)) { - pr_err("No supervisor request support on %s\n", - iommu->name); - return -EINVAL; - } - } - if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) { pr_err("No 5-level paging support for first-level on %s\n", iommu->name); @@ -560,10 +534,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, /* Setup the first level page table pointer: */ pasid_set_flptr(pte, (u64)__pa(pgd)); - if (flags & PASID_FLAG_SUPERVISOR_MODE) { - pasid_set_sre(pte); - pasid_set_wpe(pte); - } if (flags & PASID_FLAG_FL5LP) pasid_set_flpm(pte, 1); @@ -658,12 +628,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - /* - * Since it is a second level only translation setup, we should - * set SRE bit as well (addresses are expected to be GPAs). - */ - if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -700,13 +664,6 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - - /* - * We should set SRE bit as well since the addresses are expected - * to be GPAs. - */ - if (ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 20c54e50f533..d6b7d21244b1 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -41,13 +41,6 @@ #define FLPT_DEFAULT_DID 1 #define NUM_RESERVED_DID 2 -/* - * The SUPERVISOR_MODE flag indicates a first level translation which - * can be used for access to kernel addresses. It is valid only for - * access to the kernel's static 1:1 mapping of physical memory — not - * to vmalloc or even module mappings. - */ -#define PASID_FLAG_SUPERVISOR_MODE BIT(0) #define PASID_FLAG_NESTED BIT(1) #define PASID_FLAG_PAGE_SNOOP BIT(2) -- cgit v1.2.3 From b31064f881eec6047874ef58df4376b20432859c Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:39 +0800 Subject: iommu/vt-d: Make size of operands same in bitwise operations This addresses the following issue reported by klocwork tool: - operands of different size in bitwise operations Suggested-by: Yongwei Ma Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-2-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 +- drivers/iommu/intel/iommu.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 6acfe879589c..01d0ca0019f2 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1689,7 +1689,7 @@ static void __dmar_enable_qi(struct intel_iommu *iommu) * is present. */ if (ecap_smts(iommu->ecap)) - val |= (1 << 11) | 1; + val |= BIT_ULL(11) | BIT_ULL(0); raw_spin_lock_irqsave(&iommu->register_lock, flags); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f4e536fd5a28..acbf82fa90e7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1870,7 +1870,7 @@ context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) */ static inline void context_set_sm_dte(struct context_entry *context) { - context->lo |= (1 << 2); + context->lo |= BIT_ULL(2); } /* @@ -1879,7 +1879,7 @@ static inline void context_set_sm_dte(struct context_entry *context) */ static inline void context_set_sm_pre(struct context_entry *context) { - context->lo |= (1 << 4); + context->lo |= BIT_ULL(4); } /* Convert value to context PASID directory size field coding. */ -- cgit v1.2.3 From 35dc5d8998efa0f87a25bb184a9c54c46100fec3 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:40 +0800 Subject: iommu/vt-d: Remove BUG_ON on checking valid pfn range When encountering an unexpected invalid pfn range, the kernel should attempt recovery and proceed with execution. Therefore, using WARN_ON to replace BUG_ON to avoid halting the machine. Besides, one redundant checking is reduced. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-3-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index acbf82fa90e7..c4847a5aaf52 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1005,9 +1005,9 @@ static void dma_pte_clear_range(struct dmar_domain *domain, unsigned int large_page; struct dma_pte *first_pte, *pte; - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ do { @@ -1166,9 +1166,9 @@ next: static void domain_unmap(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn, struct list_head *freelist) { - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ dma_pte_clear_level(domain, agaw_to_level(domain->agaw), -- cgit v1.2.3 From 4a627a2593b457336047c6803b5d5c097183a9ca Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:41 +0800 Subject: iommu/vt-d: Remove BUG_ON in handling iotlb cache invalidation VT-d iotlb cache invalidation request with unexpected type is considered as a bug to developers, which can be fixed. So, when such kind of issue comes out, it needs to be reported through the kernel log, instead of halting the system. Replacing BUG_ON with warning reporting. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-4-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c4847a5aaf52..dd61bb554aa7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1272,7 +1272,9 @@ static void __iommu_flush_context(struct intel_iommu *iommu, | DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask); break; default: - BUG(); + pr_warn("%s: Unexpected context-cache invalidation type 0x%llx\n", + iommu->name, type); + return; } val |= DMA_CCMD_ICC; @@ -1308,7 +1310,9 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, val_iva = size_order | addr; break; default: - BUG(); + pr_warn("%s: Unexpected iotlb invalidation type 0x%llx\n", + iommu->name, type); + return; } /* Note: set drain read/write */ #if 0 @@ -1483,7 +1487,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; u16 did = domain_id_iommu(domain, iommu); - BUG_ON(pages == 0); + if (WARN_ON(!pages)) + return; if (ih) ih = 1 << 6; -- cgit v1.2.3 From 998d4c2db30c7279ce6070faf06b914c98f2ae30 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:42 +0800 Subject: iommu/vt-d: Remove BUG_ON when domain->pgd is NULL When performing domain_context_mapping or getting dma_pte of a pfn, the availability of the domain page table directory is ensured. Therefore, the domain->pgd checkings are unnecessary. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-5-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index dd61bb554aa7..f11347a590d7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -915,8 +915,6 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, int level = agaw_to_level(domain->agaw); int offset; - BUG_ON(!domain->pgd); - if (!domain_pfn_supported(domain, pfn)) /* Address beyond IOMMU's addressing capabilities. */ return NULL; @@ -1910,8 +1908,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, pr_debug("Set context mapping for %02x:%02x.%d\n", bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); - BUG_ON(!domain->pgd); - spin_lock(&iommu->lock); ret = -ENOMEM; context = iommu_context_addr(iommu, bus, devfn, 1); -- cgit v1.2.3 From cbf2f9e8badd483e2ee17a56ad8dbd1cfdcead20 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:43 +0800 Subject: iommu/vt-d: Remove BUG_ON in map/unmap() Domain map/unmap with invalid parameters shouldn't crash the kernel. Therefore, using if() replaces the BUG_ON. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-6-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f11347a590d7..ab21ef1ddb3c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2159,7 +2159,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, phys_addr_t pteval; u64 attr; - BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1)); + if (unlikely(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1))) + return -EINVAL; if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; @@ -4314,8 +4315,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, /* Cope with horrid API which requires us to unmap more than the size argument if it happens to be a large-page mapping. */ - BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level, - GFP_ATOMIC)); + if (unlikely(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, + &level, GFP_ATOMIC))) + return 0; if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); -- cgit v1.2.3 From ff45ab96465f013bee39ac88b756bb1129a7bc9d Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:44 +0800 Subject: iommu/vt-d: Remove a useless BUG_ON(dev->is_virtfn) When dmar_alloc_pci_notify_info() is being invoked, the invoker has ensured the dev->is_virtfn is false. So, remove the useless BUG_ON in dmar_alloc_pci_notify_info(). Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-7-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 01d0ca0019f2..9684c96247f8 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -127,8 +127,6 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) struct pci_dev *tmp; struct dmar_pci_notify_info *info; - BUG_ON(dev->is_virtfn); - /* * Ignore devices that have a domain number higher than what can * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 -- cgit v1.2.3 From e60d63e32d239c4c20b370106b57079d7f0994cf Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:45 +0800 Subject: iommu/vt-d: Remove BUG_ON in dmar_insert_dev_scope() The dmar_insert_dev_scope() could fail if any unexpected condition is encountered. However, in this situation, the kernel should attempt recovery and proceed with execution. Remove BUG_ON with WARN_ON, so that kernel can avoid being crashed when an unexpected condition occurs. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-8-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/iommu/intel') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 9684c96247f8..7eceee081235 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -262,7 +262,8 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, get_device(dev)); return 1; } - BUG_ON(i >= devices_cnt); + if (WARN_ON(i >= devices_cnt)) + return -EINVAL; } return 0; -- cgit v1.2.3