From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/arch/powerpc/platforms/powernv/pci.h | 170 +++++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 130 insertions(+), 40 deletions(-)
diff --git a/kernel/arch/powerpc/platforms/powernv/pci.h b/kernel/arch/powerpc/platforms/powernv/pci.h
index e302aa0..739a0b3 100644
--- a/kernel/arch/powerpc/platforms/powernv/pci.h
+++ b/kernel/arch/powerpc/platforms/powernv/pci.h
@@ -2,14 +2,12 @@
#ifndef __POWERNV_PCI_H
#define __POWERNV_PCI_H
+#include <linux/compiler.h> /* for __printf */
#include <linux/iommu.h>
#include <asm/iommu.h>
#include <asm/msi_bitmap.h>
struct pci_dn;
-
-/* Maximum possible number of ATSD MMIO registers per NPU */
-#define NV_NMMU_ATSD_REGS 8
enum pnv_phb_type {
PNV_PHB_IODA1 = 0,
@@ -34,6 +32,24 @@
#define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */
#define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */
#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */
+
+/*
+ * A brief note on PNV_IODA_PE_BUS_ALL
+ *
+ * This is needed because of the behaviour of PCIe-to-PCI bridges. The PHB uses
+ * the Requester ID field of the PCIe request header to determine the device
+ * (and PE) that initiated a DMA. In legacy PCI individual memory read/write
+ * requests aren't tagged with the RID. To work around this the PCIe-to-PCI
+ * bridge will use (secondary_bus_no << 8) | 0x00 as the RID on the PCIe side.
+ *
+ * PCIe-to-X bridges have a similar issue even though PCI-X requests also have
+ * a RID in the transaction header. The PCIe-to-X bridge is permitted to "take
+ * ownership" of a transaction by a PCI-X device when forwarding it to the PCIe
+ * side of the bridge.
+ *
+ * To work around these problems we use the BUS_ALL flag since every subordinate
+ * bus of the bridge should go into the same PE.
+ */
/* Indicates operations are frozen for a PE: MMIO in PESTA & DMA in PESTB. */
#define PNV_IODA_STOPPED_STATE 0x8000000000000000
@@ -65,12 +81,20 @@
/* "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;
uint64_t tce_bypass_base;
- /* MSIs. MVE index is identical for for 32 and 64 bit MSI
+ /*
+ * Used to track whether we've done DMA setup for this PE or not. We
+ * want to defer allocating TCE tables, etc until we've added a
+ * non-bridge device to the PE.
+ */
+ bool dma_setup_done;
+
+ /* MSIs. MVE index is identical for 32 and 64 bit MSI
* and -1 if not supported. (It's actually identical to the
* PE number)
*/
@@ -79,9 +103,6 @@
/* PEs in compound case */
struct pnv_ioda_pe *master;
struct list_head slaves;
-
- /* PCI peer-to-peer*/
- int p2p_initiator_count;
/* Link in list of PE#s */
struct list_head list;
@@ -106,20 +127,13 @@
struct dentry *dbgfs;
#endif
-#ifdef CONFIG_PCI_MSI
unsigned int msi_base;
unsigned int msi32_support;
struct msi_bitmap msi_bmp;
-#endif
int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg);
- void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
- void (*fixup_phb)(struct pci_controller *hose);
int (*init_m64)(struct pnv_phb *phb);
- void (*reserve_m64_pe)(struct pci_bus *bus,
- unsigned long *pe_bitmap, bool all);
- struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all);
int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
@@ -129,7 +143,6 @@
unsigned int total_pe_num;
unsigned int reserved_pe_idx;
unsigned int root_pe_idx;
- bool root_pe_populated;
/* 32-bit MMIO window */
unsigned int m32_size;
@@ -141,6 +154,7 @@
unsigned long m64_size;
unsigned long m64_segsize;
unsigned long m64_base;
+#define MAX_M64_BARS 64
unsigned long m64_bar_alloc;
/* IO ports */
@@ -179,22 +193,90 @@
/* PHB and hub diagnostics */
unsigned int diag_data_size;
u8 *diag_data;
-
- /* Nvlink2 data */
- struct npu {
- int index;
- __be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS];
- unsigned int mmio_atsd_count;
-
- /* Bitmask for MMIO register usage */
- unsigned long mmio_atsd_usage;
-
- /* Do we need to explicitly flush the nest mmu? */
- bool nmmu_flush;
- } npu;
-
- int p2p_target_count;
};
+
+
+/* IODA PE management */
+
+static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
+{
+ /*
+ * WARNING: We cannot rely on the resource flags. The Linux PCI
+ * allocation code sometimes decides to put a 64-bit prefetchable
+ * BAR in the 32-bit window, so we have to compare the addresses.
+ *
+ * For simplicity we only test resource start.
+ */
+ return (r->start >= phb->ioda.m64_base &&
+ r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
+}
+
+static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
+{
+ unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
+
+ return (resource_flags & flags) == flags;
+}
+
+int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
+int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
+
+void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe);
+void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe);
+
+struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb, int count);
+void pnv_ioda_free_pe(struct pnv_ioda_pe *pe);
+
+#ifdef CONFIG_PCI_IOV
+/*
+ * For SR-IOV we want to put each VF's MMIO resource in to a separate PE.
+ * This requires a bit of acrobatics with the MMIO -> PE configuration
+ * and this structure is used to keep track of it all.
+ */
+struct pnv_iov_data {
+ /* number of VFs enabled */
+ u16 num_vfs;
+
+ /* pointer to the array of VF PEs. num_vfs long*/
+ struct pnv_ioda_pe *vf_pe_arr;
+
+ /* Did we map the VF BAR with single-PE IODA BARs? */
+ bool m64_single_mode[PCI_SRIOV_NUM_BARS];
+
+ /*
+ * True if we're using any segmented windows. In that case we need
+ * shift the start of the IOV resource the segment corresponding to
+ * the allocated PE.
+ */
+ bool need_shift;
+
+ /*
+ * Bit mask used to track which m64 windows are used to map the
+ * SR-IOV BARs for this device.
+ */
+ DECLARE_BITMAP(used_m64_bar_mask, MAX_M64_BARS);
+
+ /*
+ * If we map the SR-IOV BARs with a segmented window then
+ * parts of that window will be "claimed" by other PEs.
+ *
+ * "holes" here is used to reserve the leading portion
+ * of the window that is used by other (non VF) PEs.
+ */
+ struct resource holes[PCI_SRIOV_NUM_BARS];
+};
+
+static inline struct pnv_iov_data *pnv_iov_get(struct pci_dev *pdev)
+{
+ return pdev->dev.archdata.iov_data;
+}
+
+void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev);
+resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, int resno);
+
+int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs);
+int pnv_pcibios_sriov_disable(struct pci_dev *pdev);
+#endif /* CONFIG_PCI_IOV */
extern struct pci_ops pnv_pci_ops;
@@ -210,18 +292,20 @@
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);
-extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
-extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
+extern struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn);
extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
-extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels);
extern int pnv_eeh_post_init(void);
+__printf(3, 4)
extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
const char *fmt, ...);
#define pe_err(pe, fmt, ...) \
@@ -234,13 +318,7 @@
/* 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 struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
-extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
- struct iommu_table *tbl);
-extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num);
-extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe);
-extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
-extern int pnv_npu2_init(struct pnv_phb *phb);
+extern void pnv_pci_npu_setup_iommu_groups(void);
/* pci-ioda-tce.c */
#define POWERNV_IOMMU_DEFAULT_LEVELS 2
@@ -271,4 +349,16 @@
void *tce_mem, u64 tce_size,
u64 dma_offset, unsigned int page_shift);
+extern unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb);
+
+static inline struct pnv_phb *pci_bus_to_pnvhb(struct pci_bus *bus)
+{
+ struct pci_controller *hose = bus->sysdata;
+
+ if (hose)
+ return hose->private_data;
+
+ return NULL;
+}
+
#endif /* __POWERNV_PCI_H */
--
Gitblit v1.6.2