1/* SPDX-License-Identifier: GPL-2.0 */
2#ifndef __POWERNV_PCI_H
3#define __POWERNV_PCI_H
4
5#include <linux/compiler.h>		/* for __printf */
6#include <linux/iommu.h>
7#include <asm/iommu.h>
8#include <asm/msi_bitmap.h>
9
10struct pci_dn;
11
12enum pnv_phb_type {
13	PNV_PHB_IODA1		= 0,
14	PNV_PHB_IODA2		= 1,
15	PNV_PHB_NPU_NVLINK	= 2,
16	PNV_PHB_NPU_OCAPI	= 3,
17};
18
19/* Precise PHB model for error management */
20enum pnv_phb_model {
21	PNV_PHB_MODEL_UNKNOWN,
22	PNV_PHB_MODEL_P7IOC,
23	PNV_PHB_MODEL_PHB3,
24	PNV_PHB_MODEL_NPU,
25	PNV_PHB_MODEL_NPU2,
26};
27
28#define PNV_PCI_DIAG_BUF_SIZE	8192
29#define PNV_IODA_PE_DEV		(1 << 0)	/* PE has single PCI device	*/
30#define PNV_IODA_PE_BUS		(1 << 1)	/* PE has primary PCI bus	*/
31#define PNV_IODA_PE_BUS_ALL	(1 << 2)	/* PE has subordinate buses	*/
32#define PNV_IODA_PE_MASTER	(1 << 3)	/* Master PE in compound case	*/
33#define PNV_IODA_PE_SLAVE	(1 << 4)	/* Slave PE in compound case	*/
34#define PNV_IODA_PE_VF		(1 << 5)	/* PE for one VF 		*/
35
36/*
37 * A brief note on PNV_IODA_PE_BUS_ALL
38 *
39 * This is needed because of the behaviour of PCIe-to-PCI bridges. The PHB uses
40 * the Requester ID field of the PCIe request header to determine the device
41 * (and PE) that initiated a DMA. In legacy PCI individual memory read/write
42 * requests aren't tagged with the RID. To work around this the PCIe-to-PCI
43 * bridge will use (secondary_bus_no << 8) | 0x00 as the RID on the PCIe side.
44 *
45 * PCIe-to-X bridges have a similar issue even though PCI-X requests also have
46 * a RID in the transaction header. The PCIe-to-X bridge is permitted to "take
47 * ownership" of a transaction by a PCI-X device when forwarding it to the PCIe
48 * side of the bridge.
49 *
50 * To work around these problems we use the BUS_ALL flag since every subordinate
51 * bus of the bridge should go into the same PE.
52 */
53
54/* Indicates operations are frozen for a PE: MMIO in PESTA & DMA in PESTB. */
55#define PNV_IODA_STOPPED_STATE	0x8000000000000000
56
57/* Data associated with a PE, including IOMMU tracking etc.. */
58struct pnv_phb;
59struct pnv_ioda_pe {
60	unsigned long		flags;
61	struct pnv_phb		*phb;
62	int			device_count;
63
64	/* A PE can be associated with a single device or an
65	 * entire bus (& children). In the former case, pdev
66	 * is populated, in the later case, pbus is.
67	 */
68#ifdef CONFIG_PCI_IOV
69	struct pci_dev          *parent_dev;
70#endif
71	struct pci_dev		*pdev;
72	struct pci_bus		*pbus;
73
74	/* Effective RID (device RID for a device PE and base bus
75	 * RID with devfn 0 for a bus PE)
76	 */
77	unsigned int		rid;
78
79	/* PE number */
80	unsigned int		pe_number;
81
82	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
83	struct iommu_table_group table_group;
84	struct npu_comp		*npucomp;
85
86	/* 64-bit TCE bypass region */
87	bool			tce_bypass_enabled;
88	uint64_t		tce_bypass_base;
89
90	/*
91	 * Used to track whether we've done DMA setup for this PE or not. We
92	 * want to defer allocating TCE tables, etc until we've added a
93	 * non-bridge device to the PE.
94	 */
95	bool			dma_setup_done;
96
97	/* MSIs. MVE index is identical for 32 and 64 bit MSI
98	 * and -1 if not supported. (It's actually identical to the
99	 * PE number)
100	 */
101	int			mve_number;
102
103	/* PEs in compound case */
104	struct pnv_ioda_pe	*master;
105	struct list_head	slaves;
106
107	/* Link in list of PE#s */
108	struct list_head	list;
109};
110
111#define PNV_PHB_FLAG_EEH	(1 << 0)
112
113struct pnv_phb {
114	struct pci_controller	*hose;
115	enum pnv_phb_type	type;
116	enum pnv_phb_model	model;
117	u64			hub_id;
118	u64			opal_id;
119	int			flags;
120	void __iomem		*regs;
121	u64			regs_phys;
122	int			initialized;
123	spinlock_t		lock;
124
125#ifdef CONFIG_DEBUG_FS
126	int			has_dbgfs;
127	struct dentry		*dbgfs;
128#endif
129
130	unsigned int		msi_base;
131	unsigned int		msi32_support;
132	struct msi_bitmap	msi_bmp;
133	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
134			 unsigned int hwirq, unsigned int virq,
135			 unsigned int is_64, struct msi_msg *msg);
136	int (*init_m64)(struct pnv_phb *phb);
137	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
138	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
139	int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
140
141	struct {
142		/* Global bridge info */
143		unsigned int		total_pe_num;
144		unsigned int		reserved_pe_idx;
145		unsigned int		root_pe_idx;
146
147		/* 32-bit MMIO window */
148		unsigned int		m32_size;
149		unsigned int		m32_segsize;
150		unsigned int		m32_pci_base;
151
152		/* 64-bit MMIO window */
153		unsigned int		m64_bar_idx;
154		unsigned long		m64_size;
155		unsigned long		m64_segsize;
156		unsigned long		m64_base;
157#define MAX_M64_BARS 64
158		unsigned long		m64_bar_alloc;
159
160		/* IO ports */
161		unsigned int		io_size;
162		unsigned int		io_segsize;
163		unsigned int		io_pci_base;
164
165		/* PE allocation */
166		struct mutex		pe_alloc_mutex;
167		unsigned long		*pe_alloc;
168		struct pnv_ioda_pe	*pe_array;
169
170		/* M32 & IO segment maps */
171		unsigned int		*m64_segmap;
172		unsigned int		*m32_segmap;
173		unsigned int		*io_segmap;
174
175		/* DMA32 segment maps - IODA1 only */
176		unsigned int		dma32_count;
177		unsigned int		*dma32_segmap;
178
179		/* IRQ chip */
180		int			irq_chip_init;
181		struct irq_chip		irq_chip;
182
183		/* Sorted list of used PE's based
184		 * on the sequence of creation
185		 */
186		struct list_head	pe_list;
187		struct mutex            pe_list_mutex;
188
189		/* Reverse map of PEs, indexed by {bus, devfn} */
190		unsigned int		pe_rmap[0x10000];
191	} ioda;
192
193	/* PHB and hub diagnostics */
194	unsigned int		diag_data_size;
195	u8			*diag_data;
196};
197
198
199/* IODA PE management */
200
201static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
202{
203	/*
204	 * WARNING: We cannot rely on the resource flags. The Linux PCI
205	 * allocation code sometimes decides to put a 64-bit prefetchable
206	 * BAR in the 32-bit window, so we have to compare the addresses.
207	 *
208	 * For simplicity we only test resource start.
209	 */
210	return (r->start >= phb->ioda.m64_base &&
211		r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
212}
213
214static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
215{
216	unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
217
218	return (resource_flags & flags) == flags;
219}
220
221int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
222int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
223
224void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
225void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe);
226
227struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb, int count);
228void pnv_ioda_free_pe(struct pnv_ioda_pe *pe);
229
230#ifdef CONFIG_PCI_IOV
231/*
232 * For SR-IOV we want to put each VF's MMIO resource in to a separate PE.
233 * This requires a bit of acrobatics with the MMIO -> PE configuration
234 * and this structure is used to keep track of it all.
235 */
236struct pnv_iov_data {
237	/* number of VFs enabled */
238	u16     num_vfs;
239
240	/* pointer to the array of VF PEs. num_vfs long*/
241	struct pnv_ioda_pe *vf_pe_arr;
242
243	/* Did we map the VF BAR with single-PE IODA BARs? */
244	bool    m64_single_mode[PCI_SRIOV_NUM_BARS];
245
246	/*
247	 * True if we're using any segmented windows. In that case we need
248	 * shift the start of the IOV resource the segment corresponding to
249	 * the allocated PE.
250	 */
251	bool    need_shift;
252
253	/*
254	 * Bit mask used to track which m64 windows are used to map the
255	 * SR-IOV BARs for this device.
256	 */
257	DECLARE_BITMAP(used_m64_bar_mask, MAX_M64_BARS);
258
259	/*
260	 * If we map the SR-IOV BARs with a segmented window then
261	 * parts of that window will be "claimed" by other PEs.
262	 *
263	 * "holes" here is used to reserve the leading portion
264	 * of the window that is used by other (non VF) PEs.
265	 */
266	struct resource holes[PCI_SRIOV_NUM_BARS];
267};
268
269static inline struct pnv_iov_data *pnv_iov_get(struct pci_dev *pdev)
270{
271	return pdev->dev.archdata.iov_data;
272}
273
274void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev);
275resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, int resno);
276
277int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs);
278int pnv_pcibios_sriov_disable(struct pci_dev *pdev);
279#endif /* CONFIG_PCI_IOV */
280
281extern struct pci_ops pnv_pci_ops;
282
283void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
284				unsigned char *log_buff);
285int pnv_pci_cfg_read(struct pci_dn *pdn,
286		     int where, int size, u32 *val);
287int pnv_pci_cfg_write(struct pci_dn *pdn,
288		      int where, int size, u32 val);
289extern struct iommu_table *pnv_pci_table_alloc(int nid);
290
291extern void pnv_pci_init_ioda_hub(struct device_node *np);
292extern void pnv_pci_init_ioda2_phb(struct device_node *np);
293extern void pnv_pci_init_npu_phb(struct device_node *np);
294extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
295extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
296extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
297extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
298
299extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
300extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
301extern struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn);
302extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
303extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
304extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
305		__u64 window_size, __u32 levels);
306extern int pnv_eeh_post_init(void);
307
308__printf(3, 4)
309extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
310			    const char *fmt, ...);
311#define pe_err(pe, fmt, ...)					\
312	pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
313#define pe_warn(pe, fmt, ...)					\
314	pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
315#define pe_info(pe, fmt, ...)					\
316	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
317
318/* Nvlink functions */
319extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
320extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
321extern void pnv_pci_npu_setup_iommu_groups(void);
322
323/* pci-ioda-tce.c */
324#define POWERNV_IOMMU_DEFAULT_LEVELS	2
325#define POWERNV_IOMMU_MAX_LEVELS	5
326
327extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
328		unsigned long uaddr, enum dma_data_direction direction,
329		unsigned long attrs);
330extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages);
331extern int pnv_tce_xchg(struct iommu_table *tbl, long index,
332		unsigned long *hpa, enum dma_data_direction *direction,
333		bool alloc);
334extern __be64 *pnv_tce_useraddrptr(struct iommu_table *tbl, long index,
335		bool alloc);
336extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);
337
338extern long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
339		__u32 page_shift, __u64 window_size, __u32 levels,
340		bool alloc_userspace_copy, struct iommu_table *tbl);
341extern void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
342
343extern long pnv_pci_link_table_and_group(int node, int num,
344		struct iommu_table *tbl,
345		struct iommu_table_group *table_group);
346extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
347		struct iommu_table_group *table_group);
348extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
349		void *tce_mem, u64 tce_size,
350		u64 dma_offset, unsigned int page_shift);
351
352extern unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb);
353
354static inline struct pnv_phb *pci_bus_to_pnvhb(struct pci_bus *bus)
355{
356	struct pci_controller *hose = bus->sysdata;
357
358	if (hose)
359		return hose->private_data;
360
361	return NULL;
362}
363
364#endif /* __POWERNV_PCI_H */
365