powerpc/powernv: remove the nvlink support

This code was only used by the vfio-nvlink2 code, which itself had no
proper use.  Drop this huge chunk of code build into every powernv
or generic build.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210326061311.1497642-3-hch@lst.de

arch/powerpc/include/asm/opal.h

@@ -28,9 +28,6 @@ extern struct device_node *opal_node;
 
 /* API functions */
 int64_t opal_invalid_call(void);
-int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf);
-int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr,
-			uint64_t bdf);
 int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
 			uint64_t lpcr);
 int64_t opal_npu_spa_setup(uint64_t phb_id, uint32_t bdfn,

arch/powerpc/include/asm/pci-bridge.h

@@ -126,7 +126,6 @@ struct pci_controller {
 #endif	/* CONFIG_PPC64 */
 
 	void *private_data;
-	struct npu *npu;
 };
 
 /* These are used for config access before all the PCI probing

arch/powerpc/include/asm/pci.h

@@ -119,11 +119,4 @@ extern void pcibios_scan_phb(struct pci_controller *hose);
 
 #endif	/* __KERNEL__ */
 
-extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev);
-extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index);
-extern int pnv_npu2_init(struct pci_controller *hose);
-extern int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid,
-		unsigned long msr);
-extern int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev);
-
 #endif /* __ASM_POWERPC_PCI_H */

arch/powerpc/platforms/powernv/Makefile

@@ -10,7 +10,7 @@ obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_PRESERVE_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_OPAL_CORE)	+= opal-core.o
-obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
+obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o pci-ioda-tce.o
 obj-$(CONFIG_PCI_IOV)   += pci-sriov.o
 obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o

arch/powerpc/platforms/powernv/opal-call.c

@@ -267,8 +267,6 @@ OPAL_CALL(opal_xive_get_queue_state,		OPAL_XIVE_GET_QUEUE_STATE);
 OPAL_CALL(opal_xive_set_queue_state,		OPAL_XIVE_SET_QUEUE_STATE);
 OPAL_CALL(opal_xive_get_vp_state,		OPAL_XIVE_GET_VP_STATE);
 OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
-OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
-OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
 OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
 OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
 OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -47,8 +47,7 @@
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
 #define PNV_IODA1_DMA32_SEGSIZE	0x10000000
 
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
-					      "NPU_OCAPI" };
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_OCAPI" };
 
 static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 static void pnv_pci_configure_bus(struct pci_bus *bus);
@@ -192,8 +191,6 @@ void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
-	WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
-	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
 
 	mutex_lock(&phb->ioda.pe_alloc_mutex);
@@ -875,7 +872,7 @@ int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Release from all parents PELT-V. NPUs don't have a PELTV
 	 * table
 	 */
-	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+	if (phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_unset_peltv(phb, pe, parent);
 
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
@@ -946,7 +943,7 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Configure PELTV. NPUs don't have a PELTV table so skip
 	 * configuration on them.
 	 */
-	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+	if (phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_set_peltv(phb, pe, true);
 
 	/* Setup reverse map */
@@ -1002,8 +999,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	/* NOTE: We don't get a reference for the pointer in the PE
 	 * data structure, both the device and PE structures should be
-	 * destroyed at the same time. However, removing nvlink
-	 * devices will need some work.
+	 * destroyed at the same time.
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
@@ -1099,113 +1095,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 	return pe;
 }
 
-static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
-{
-	int pe_num, found_pe = false, rc;
-	long rid;
-	struct pnv_ioda_pe *pe;
-	struct pci_dev *gpu_pdev;
-	struct pci_dn *npu_pdn;
-	struct pnv_phb *phb = pci_bus_to_pnvhb(npu_pdev->bus);
-
-	/*
-	 * Intentionally leak a reference on the npu device (for
-	 * nvlink only; this is not an opencapi path) to make sure it
-	 * never goes away, as it's been the case all along and some
-	 * work is needed otherwise.
-	 */
-	pci_dev_get(npu_pdev);
-
-	/*
-	 * Due to a hardware errata PE#0 on the NPU is reserved for
-	 * error handling. This means we only have three PEs remaining
-	 * which need to be assigned to four links, implying some
-	 * links must share PEs.
-	 *
-	 * To achieve this we assign PEs such that NPUs linking the
-	 * same GPU get assigned the same PE.
-	 */
-	gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev);
-	for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
-		pe = &phb->ioda.pe_array[pe_num];
-		if (!pe->pdev)
-			continue;
-
-		if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) {
-			/*
-			 * This device has the same peer GPU so should
-			 * be assigned the same PE as the existing
-			 * peer NPU.
-			 */
-			dev_info(&npu_pdev->dev,
-				"Associating to existing PE %x\n", pe_num);
-			npu_pdn = pci_get_pdn(npu_pdev);
-			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
-			npu_pdn->pe_number = pe_num;
-			phb->ioda.pe_rmap[rid] = pe->pe_number;
-			pe->device_count++;
-
-			/* Map the PE to this link */
-			rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
-					OpalPciBusAll,
-					OPAL_COMPARE_RID_DEVICE_NUMBER,
-					OPAL_COMPARE_RID_FUNCTION_NUMBER,
-					OPAL_MAP_PE);
-			WARN_ON(rc != OPAL_SUCCESS);
-			found_pe = true;
-			break;
-		}
-	}
-
-	if (!found_pe)
-		/*
-		 * Could not find an existing PE so allocate a new
-		 * one.
-		 */
-		return pnv_ioda_setup_dev_PE(npu_pdev);
-	else
-		return pe;
-}
-
-static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
-{
-	struct pci_dev *pdev;
-
-	list_for_each_entry(pdev, &bus->devices, bus_list)
-		pnv_ioda_setup_npu_PE(pdev);
-}
-
-static void pnv_pci_ioda_setup_nvlink(void)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
-	struct pnv_ioda_pe *pe;
-
-	list_for_each_entry(hose, &hose_list, list_node) {
-		phb = hose->private_data;
-		if (phb->type == PNV_PHB_NPU_NVLINK) {
-			/* PE#0 is needed for error reporting */
-			pnv_ioda_reserve_pe(phb, 0);
-			pnv_ioda_setup_npu_PEs(hose->bus);
-			if (phb->model == PNV_PHB_MODEL_NPU2)
-				WARN_ON_ONCE(pnv_npu2_init(hose));
-		}
-	}
-	list_for_each_entry(hose, &hose_list, list_node) {
-		phb = hose->private_data;
-		if (phb->type != PNV_PHB_IODA2)
-			continue;
-
-		list_for_each_entry(pe, &phb->ioda.pe_list, list)
-			pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV);
-	}
-
-#ifdef CONFIG_IOMMU_API
-	/* setup iommu groups so we can do nvlink pass-thru */
-	pnv_pci_npu_setup_iommu_groups();
-#endif
-}
-
 static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe);
 
@@ -1468,18 +1357,6 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 #define PHB3_TCE_KILL_INVAL_PE		PPC_BIT(1)
 #define PHB3_TCE_KILL_INVAL_ONE		PPC_BIT(2)
 
-static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
-	const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
-
-	mb(); /* Ensure previous TCE table stores are visible */
-	if (rm)
-		__raw_rm_writeq_be(val, invalidate);
-	else
-		__raw_writeq_be(val, invalidate);
-}
-
 static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
 {
 	/* 01xb - invalidate TCEs that match the specified PE# */
@@ -1539,20 +1416,6 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 		struct pnv_phb *phb = pe->phb;
 		unsigned int shift = tbl->it_page_shift;
 
-		/*
-		 * NVLink1 can use the TCE kill register directly as
-		 * it's the same as PHB3. NVLink2 is different and
-		 * should go via the OPAL call.
-		 */
-		if (phb->model == PNV_PHB_MODEL_NPU) {
-			/*
-			 * The NVLink hardware does not support TCE kill
-			 * per TCE entry so we have to invalidate
-			 * the entire cache for it.
-			 */
-			pnv_pci_phb3_tce_invalidate_entire(phb, rm);
-			continue;
-		}
 		if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
 			pnv_pci_phb3_tce_invalidate(pe, rm, shift,
 						    index, npages);
@@ -1564,14 +1427,6 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 	}
 }
 
-void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
-	if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
-		pnv_pci_phb3_tce_invalidate_entire(phb, rm);
-	else
-		opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
-}
-
 static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 		long npages, unsigned long uaddr,
 		enum dma_data_direction direction,
@@ -2451,7 +2306,6 @@ static void pnv_pci_enable_bridges(void)
 
 static void pnv_pci_ioda_fixup(void)
 {
-	pnv_pci_ioda_setup_nvlink();
 	pnv_pci_ioda_create_dbgfs();
 
 	pnv_pci_enable_bridges();
@@ -2824,15 +2678,6 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
 		pnv_ioda_release_pe(pe);
 }
 
-static void pnv_npu_disable_device(struct pci_dev *pdev)
-{
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
-	struct eeh_pe *eehpe = edev ? edev->pe : NULL;
-
-	if (eehpe && eeh_ops && eeh_ops->reset)
-		eeh_ops->reset(eehpe, EEH_RESET_HOT);
-}
-
 static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
@@ -2874,16 +2719,6 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
-	.setup_msi_irqs		= pnv_setup_msi_irqs,
-	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
-	.enable_device_hook	= pnv_pci_enable_device_hook,
-	.window_alignment	= pnv_pci_window_alignment,
-	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.shutdown		= pnv_pci_ioda_shutdown,
-	.disable_device		= pnv_npu_disable_device,
-};
-
 static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
 	.enable_device_hook	= pnv_ocapi_enable_device_hook,
 	.release_device		= pnv_pci_release_device,
@@ -2957,10 +2792,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		phb->model = PNV_PHB_MODEL_P7IOC;
 	else if (of_device_is_compatible(np, "ibm,power8-pciex"))
 		phb->model = PNV_PHB_MODEL_PHB3;
-	else if (of_device_is_compatible(np, "ibm,power8-npu-pciex"))
-		phb->model = PNV_PHB_MODEL_NPU;
-	else if (of_device_is_compatible(np, "ibm,power9-npu-pciex"))
-		phb->model = PNV_PHB_MODEL_NPU2;
 	else
 		phb->model = PNV_PHB_MODEL_UNKNOWN;
 
@@ -3118,9 +2949,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 
 	switch (phb->type) {
-	case PNV_PHB_NPU_NVLINK:
-		hose->controller_ops = pnv_npu_ioda_controller_ops;
-		break;
 	case PNV_PHB_NPU_OCAPI:
 		hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
 		break;
@@ -3173,11 +3001,6 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
 
-void __init pnv_pci_init_npu_phb(struct device_node *np)
-{
-	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_NVLINK);
-}
-
 void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
 {
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_OCAPI);

arch/powerpc/platforms/powernv/pci.c

@@ -926,17 +926,6 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda3-phb")
 		pnv_pci_init_ioda2_phb(np);
 
-	/* Look for NPU PHBs */
-	for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb")
-		pnv_pci_init_npu_phb(np);
-
-	/*
-	 * Look for NPU2 PHBs which we treat mostly as NPU PHBs with
-	 * the exception of TCE kill which requires an OPAL call.
-	 */
-	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-phb")
-		pnv_pci_init_npu_phb(np);
-
 	/* Look for NPU2 OpenCAPI PHBs */
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-opencapi-phb")
 		pnv_pci_init_npu2_opencapi_phb(np);

arch/powerpc/platforms/powernv/pci.h

@@ -10,10 +10,9 @@
 struct pci_dn;
 
 enum pnv_phb_type {
-	PNV_PHB_IODA1		= 0,
-	PNV_PHB_IODA2		= 1,
-	PNV_PHB_NPU_NVLINK	= 2,
-	PNV_PHB_NPU_OCAPI	= 3,
+	PNV_PHB_IODA1,
+	PNV_PHB_IODA2,
+	PNV_PHB_NPU_OCAPI,
 };
 
 /* Precise PHB model for error management */
@@ -21,8 +20,6 @@ enum pnv_phb_model {
 	PNV_PHB_MODEL_UNKNOWN,
 	PNV_PHB_MODEL_P7IOC,
 	PNV_PHB_MODEL_PHB3,
-	PNV_PHB_MODEL_NPU,
-	PNV_PHB_MODEL_NPU2,
 };
 
 #define PNV_PCI_DIAG_BUF_SIZE	8192
@@ -81,7 +78,6 @@ struct pnv_ioda_pe {
 
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	struct iommu_table_group table_group;
-	struct npu_comp		*npucomp;
 
 	/* 64-bit TCE bypass region */
 	bool			tce_bypass_enabled;
@@ -289,9 +285,7 @@ extern struct iommu_table *pnv_pci_table_alloc(int nid);
 
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
-extern void pnv_pci_init_npu_phb(struct device_node *np);
 extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
-extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
@@ -314,11 +308,6 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 #define pe_info(pe, fmt, ...)					\
 	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
-/* Nvlink functions */
-extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
-extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
-extern void pnv_pci_npu_setup_iommu_groups(void);
-
 /* pci-ioda-tce.c */
 #define POWERNV_IOMMU_DEFAULT_LEVELS	2
 #define POWERNV_IOMMU_MAX_LEVELS	5

arch/powerpc/platforms/pseries/pci.c

@@ -224,8 +224,6 @@ static void __init pSeries_request_regions(void)
 
 void __init pSeries_final_fixup(void)
 {
-	struct pci_controller *hose;
-
 	pSeries_request_regions();
 
 	eeh_show_enabled();
@@ -234,27 +232,6 @@ void __init pSeries_final_fixup(void)
 	ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pseries_pcibios_sriov_disable;
 #endif
-	list_for_each_entry(hose, &hose_list, list_node) {
-		struct device_node *dn = hose->dn, *nvdn;
-
-		while (1) {
-			dn = of_find_all_nodes(dn);
-			if (!dn)
-				break;
-			nvdn = of_parse_phandle(dn, "ibm,nvlink", 0);
-			if (!nvdn)
-				continue;
-			if (!of_device_is_compatible(nvdn, "ibm,npu-link"))
-				continue;
-			if (!of_device_is_compatible(nvdn->parent,
-						"ibm,power9-npu"))
-				continue;
-#ifdef CONFIG_PPC_POWERNV
-			WARN_ON_ONCE(pnv_npu2_init(hose));
-#endif
-			break;
-		}
-	}
 }
 
 /*