[PATCH 1/6] powerpc/powernv: Enable M64 aperatus for PHB3

Wei Yang weiyang at linux.vnet.ibm.com
Tue Jul 15 12:55:25 EST 2014


On Thu, Jul 10, 2014 at 09:53:41PM +0800, Guo Chao wrote:
>This patch enable M64 aperatus for PHB3.
>
>We already had platform hook (ppc_md.pcibios_window_alignment) to affect
>the PCI resource assignment done in PCI core so that each PE's M32 resource
>was built on basis of M32 segment size. Similarly, we're using that for
>M64 assignment on basis of M64 segment size.
>
>   * We're using last M64 BAR to cover M64 aperatus, and it's shared by all
>     256 PEs.
>   * We don't support P7IOC yet. However, some function callbacks are added
>     to (struct pnv_phb) so that we can reuse them on P7IOC in future.
>   * PE, corresponding to PCI bus with large M64 BAR device attached, might
>     span multiple M64 segments. We introduce "compound" PE to cover the case.
>     The compound PE is a list of PEs and the master PE is used as before.
>     The slave PEs are just for MMIO isolation.
>
>Signed-off-by: Guo Chao <yan at linux.vnet.ibm.com>
>---
> arch/powerpc/include/asm/opal.h           |   8 +-
> arch/powerpc/platforms/powernv/pci-ioda.c | 284 ++++++++++++++++++++++++++++--
> arch/powerpc/platforms/powernv/pci.h      |  20 +++
> 3 files changed, 297 insertions(+), 15 deletions(-)
>
>diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
>index 0da1dbd..ae885cc 100644
>--- a/arch/powerpc/include/asm/opal.h
>+++ b/arch/powerpc/include/asm/opal.h
>@@ -340,6 +340,12 @@ enum OpalMveEnableAction {
> 	OPAL_ENABLE_MVE = 1
> };
> 
>+enum OpalM64EnableAction {
>+	OPAL_DISABLE_M64 = 0,
>+	OPAL_ENABLE_M64_SPLIT = 1,
>+	OPAL_ENABLE_M64_NON_SPLIT = 2
>+};
>+
> enum OpalPciResetScope {
> 	OPAL_PHB_COMPLETE = 1, OPAL_PCI_LINK = 2, OPAL_PHB_ERROR = 3,
> 	OPAL_PCI_HOT_RESET = 4, OPAL_PCI_FUNDAMENTAL_RESET = 5,
>@@ -768,7 +774,7 @@ int64_t opal_pci_set_phb_mem_window(uint64_t phb_id, uint16_t window_type,
> 				    uint16_t window_num,
> 				    uint64_t starting_real_address,
> 				    uint64_t starting_pci_address,
>-				    uint16_t segment_size);
>+				    uint64_t size);
> int64_t opal_pci_map_pe_mmio_window(uint64_t phb_id, uint16_t pe_number,
> 				    uint16_t window_type, uint16_t window_num,
> 				    uint16_t segment_num);
>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
>index de19ede..851e615 100644
>--- a/arch/powerpc/platforms/powernv/pci-ioda.c
>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
>@@ -36,6 +36,7 @@
> #include <asm/tce.h>
> #include <asm/xics.h>
> #include <asm/debug.h>
>+#include <asm/firmware.h>
> 
> #include "powernv.h"
> #include "pci.h"
>@@ -82,6 +83,12 @@ static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
> 		: : "r" (val), "r" (paddr) : "memory");
> }
> 
>+static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
>+{
>+	return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) ==
>+		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
>+}
>+
> static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
> {
> 	unsigned long pe;
>@@ -106,6 +113,243 @@ static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
> 	clear_bit(pe, phb->ioda.pe_alloc);
> }
> 
>+/* The default M64 BAR is shared by all PEs */
>+static int pnv_ioda2_init_m64(struct pnv_phb *phb)
>+{
>+	const char *desc;
>+	struct resource *r;
>+	s64 rc;
>+
>+	/* Configure the default M64 BAR */
>+	rc = opal_pci_set_phb_mem_window(phb->opal_id,
>+					 OPAL_M64_WINDOW_TYPE,
>+					 phb->ioda.m64_bar_idx,
>+					 phb->ioda.m64_base,
>+					 0, /* unused */
>+					 phb->ioda.m64_size);
>+	if (rc != OPAL_SUCCESS) {
>+		desc = "configuring";
>+		goto fail;
>+	}
>+
>+	/* Enable the default M64 BAR */
>+	rc = opal_pci_phb_mmio_enable(phb->opal_id,
>+				      OPAL_M64_WINDOW_TYPE,
>+				      phb->ioda.m64_bar_idx,
>+				      OPAL_ENABLE_M64_SPLIT);
>+	if (rc != OPAL_SUCCESS) {
>+		desc = "enabling";
>+		goto fail;
>+	}
>+
>+	/* Mark the M64 BAR assigned */
>+	set_bit(phb->ioda.m64_bar_idx, &phb->ioda.m64_bar_alloc);
>+
>+	/*
>+	 * Strip off the segment used by the reserved PE, which is
>+	 * expected to be 0 or last one of PE capabicity.
>+	 */
>+	r = &phb->hose->mem_resources[1];
>+	if (phb->ioda.reserved_pe == 0)
>+		r->start += phb->ioda.m64_segsize;
>+	else if (phb->ioda.reserved_pe == (phb->ioda.total_pe - 1))
>+		r->end -= phb->ioda.m64_segsize;
>+	else
>+		pr_warn("  Cannot strip M64 segment for reserved PE#%d\n",
>+			phb->ioda.reserved_pe);
>+
>+	return 0;
>+
>+fail:
>+	pr_warn("  Failure %lld %s M64 BAR#%d\n",
>+		rc, desc, phb->ioda.m64_bar_idx);
>+	opal_pci_phb_mmio_enable(phb->opal_id,
>+				 OPAL_M64_WINDOW_TYPE,
>+				 phb->ioda.m64_bar_idx,
>+				 OPAL_DISABLE_M64);
>+	return -EIO;
>+}
>+
>+static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb)
>+{
>+	resource_size_t sgsz = phb->ioda.m64_segsize;
>+	struct pci_dev *pdev;
>+	struct resource *r;
>+	int base, step, i;
>+
>+	/*
>+	 * Root bus always has full M64 range and root port has
>+	 * M64 range used in reality. So we're checking root port
>+	 * instead of root bus.
>+	 */
>+	list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) {
>+		for (i = PCI_BRIDGE_RESOURCES;
>+		     i <= PCI_BRIDGE_RESOURCE_END; i++) {
>+			r = &pdev->resource[i];
>+			if (!r->parent ||
>+			    !pnv_pci_is_mem_pref_64(r->flags))
>+				continue;
>+
>+			base = (r->start - phb->ioda.m64_base) / sgsz;
>+			for (step = 0; step < resource_size(r) / sgsz; step++)
>+				set_bit(base + step, phb->ioda.pe_alloc);
>+		}
>+	}
>+}
>+
>+static int pnv_ioda2_pick_m64_pe(struct pnv_phb *phb,
>+				 struct pci_bus *bus, int all)
>+{
>+	resource_size_t segsz = phb->ioda.m64_segsize;
>+	struct pci_dev *pdev;
>+	struct resource *r;
>+	struct pnv_ioda_pe *master_pe, *pe;
>+	unsigned long size, *pe_alloc;
>+	bool found;
>+	int start, i, j;
>+
>+	/* Root bus shouldn't use M64 */
>+	if (pci_is_root_bus(bus))
>+		return IODA_INVALID_PE;
>+
>+	/* We support only one M64 window on each bus */
>+	found = false;
>+	pci_bus_for_each_resource(bus, r, i) {
>+		if (r && r->parent &&
>+		    pnv_pci_is_mem_pref_64(r->flags)) {
>+			found = true;
>+			break;
>+		}
>+	}
>+
>+	/* No M64 window found ? */
>+	if (!found)
>+		return IODA_INVALID_PE;
>+
>+	/* Allocate bitmap */
>+	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
>+	pe_alloc = kzalloc(size, GFP_KERNEL);
>+	if (!pe_alloc) {
>+		pr_warn("%s: Out of memory !\n",
>+			__func__);
>+		return IODA_INVALID_PE;
>+	}
>+
>+	/*
>+	 * Figure out reserved PE numbers by the PE
>+	 * the its child PEs.
>+	 */
>+	start = (r->start - phb->ioda.m64_base) / segsz;
>+	for (i = 0; i < resource_size(r) / segsz; i++)
>+		set_bit(start + i, pe_alloc);
>+
>+	if (all)
>+		goto done;
>+
>+	/*
>+	 * If the PE doesn't cover all subordinate buses,
>+	 * we need subtract from reserved PEs for children.
>+	 */
>+	list_for_each_entry(pdev, &bus->devices, bus_list) {
>+		if (!pdev->subordinate)
>+			continue;
>+
>+		pci_bus_for_each_resource(pdev->subordinate, r, i) {
>+			if (!r || !r->parent ||
>+			    !pnv_pci_is_mem_pref_64(r->flags))
>+				continue;
>+
>+			start = (r->start - phb->ioda.m64_base) / segsz;
>+			for (j = 0; j < resource_size(r) / segsz ; j++)
>+				clear_bit(start + j, pe_alloc);
>+                }
>+        }
>+
>+	/*
>+	 * the current bus might not own M64 window and that's all
>+	 * contributed by its child buses. For the case, we needn't
>+	 * pick M64 dependent PE#.
>+	 */
>+	if (bitmap_empty(pe_alloc, phb->ioda.total_pe)) {
>+		kfree(pe_alloc);
>+		return IODA_INVALID_PE;
>+	}
>+
>+	/*
>+	 * Figure out the master PE and put all slave PEs to master
>+	 * PE's list to form compound PE.
>+	 */
>+done:
>+	master_pe = NULL;
>+	i = -1;
>+	while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
>+		phb->ioda.total_pe) {
>+		pe = &phb->ioda.pe_array[i];
>+		pe->phb = phb;
>+		pe->pe_number = i;
>+
>+		if (!master_pe) {
>+			pe->flags |= PNV_IODA_PE_MASTER;
>+			INIT_LIST_HEAD(&pe->slaves);
>+			master_pe = pe;
>+		} else {
>+			pe->flags |= PNV_IODA_PE_SLAVE;
>+			pe->master = master_pe;
>+			list_add_tail(&pe->list, &master_pe->slaves);
>+		}
>+	}
>+
>+	kfree(pe_alloc);
>+	return master_pe->pe_number;
>+}
>+
>+static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
>+{
>+	struct pci_controller *hose = phb->hose;
>+	struct device_node *dn = hose->dn;
>+	struct resource *res;
>+	const u32 *r;
>+	u64 pci_addr;
>+
>+	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
>+		pr_info("  Firmware too old to support M64 window\n");
>+		return;
>+	}
>+
>+	r = of_get_property(dn, "ibm,opal-m64-window", NULL);
>+	if (!r) {
>+		pr_info("  No <ibm,opal-m64-window> on %s\n",
>+			dn->full_name);
>+		return;
>+	}
>+
>+	/* FIXME: Support M64 for P7IOC */
>+	if (phb->type != PNV_PHB_IODA2) {
>+		pr_info("  Not support M64 window\n");
>+		return;
>+	}
>+
>+	res = &hose->mem_resources[1];
>+	res->start = of_translate_address(dn, r + 2);
>+	res->end = res->start + of_read_number(r + 4, 2) - 1;
>+	res->flags = (IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
>+	pci_addr = of_read_number(r, 2);
>+	hose->mem_offset[1] = res->start - pci_addr;
>+
>+	phb->ioda.m64_size = resource_size(res);
>+	phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe;
>+	phb->ioda.m64_base = pci_addr;
>+
>+	/* Use last M64 BAR to cover M64 window */
>+	phb->ioda.m64_bar_idx = 15;
>+	phb->init_m64 = pnv_ioda2_init_m64;
>+	phb->alloc_m64_pe = pnv_ioda2_alloc_m64_pe;
>+	phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
>+
>+	pr_info(" MEM 0x%016llx..0x%016llx -> 0x%016llx Prefetchable\n",
>+		res->start, res->end, pci_addr);

In pnv_pci_init_ioda_phb(), we have following code to print the M32
information.

	pr_info("  %d (%d) PE's M32: 0x%x [segment=0x%x]"
		" IO: 0x%x [segment=0x%x]\n",
		phb->ioda.total_pe,
		phb->ioda.reserved_pe,
		phb->ioda.m32_size, phb->ioda.m32_segsize,
		phb->ioda.io_size, phb->ioda.io_segsize);

Suggest to have similar one for M64.

>+}
>+
> /* Currently those 2 are only used when MSIs are enabled, this will change
>  * but in the meantime, we need to protect them to avoid warnings
>  */
>@@ -363,9 +607,16 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
> 	struct pci_controller *hose = pci_bus_to_host(bus);
> 	struct pnv_phb *phb = hose->private_data;
> 	struct pnv_ioda_pe *pe;
>-	int pe_num;
>+	int pe_num = IODA_INVALID_PE;
>+
>+	/* Check if PE is determined by M64 */
>+	if (phb->pick_m64_pe)
>+		pe_num = phb->pick_m64_pe(phb, bus, all);
>+
>+	/* The PE number isn't pinned by M64 */
>+	if (pe_num == IODA_INVALID_PE)
>+		pe_num = pnv_ioda_alloc_pe(phb);
> 
>-	pe_num = pnv_ioda_alloc_pe(phb);
> 	if (pe_num == IODA_INVALID_PE) {
> 		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
> 			__func__, pci_domain_nr(bus), bus->number);
>@@ -441,8 +692,15 @@ static void pnv_ioda_setup_PEs(struct pci_bus *bus)
> static void pnv_pci_ioda_setup_PEs(void)
> {
> 	struct pci_controller *hose, *tmp;
>+	struct pnv_phb *phb;
> 
> 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
>+		phb = hose->private_data;
>+
>+		/* M64 layout might affect PE allocation */
>+		if (phb->alloc_m64_pe)
>+			phb->alloc_m64_pe(phb);
>+
> 		pnv_ioda_setup_PEs(hose->bus);
> 	}
> }
>@@ -1055,9 +1313,6 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
> 				index++;
> 			}
> 		} else if (res->flags & IORESOURCE_MEM) {
>-			/* WARNING: Assumes M32 is mem region 0 in PHB. We need to
>-			 * harden that algorithm when we start supporting M64
>-			 */
> 			region.start = res->start -
> 				       hose->mem_offset[0] -
> 				       phb->ioda.m32_pci_base;
>@@ -1178,7 +1433,8 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
> 		bridge = bridge->bus->self;
> 	}
> 
>-	/* We need support prefetchable memory window later */
>+	if (pnv_pci_is_mem_pref_64(type))
>+		return phb->ioda.m64_segsize;
> 	if (type & IORESOURCE_MEM)
> 		return phb->ioda.m32_segsize;
> 
>@@ -1299,6 +1555,10 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
> 	prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL);
> 	if (prop32)
> 		phb->ioda.reserved_pe = be32_to_cpup(prop32);
>+
>+	/* Parse 64-bit MMIO range */
>+	pnv_ioda_parse_m64_window(phb);
>+
> 	phb->ioda.m32_size = resource_size(&hose->mem_resources[0]);
> 	/* FW Has already off top 64k of M32 space (MSI space) */
> 	phb->ioda.m32_size += 0x10000;
>@@ -1334,14 +1594,6 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
> 	/* Calculate how many 32-bit TCE segments we have */
> 	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
> 
>-	/* Clear unusable m64 */
>-	hose->mem_resources[1].flags = 0;
>-	hose->mem_resources[1].start = 0;
>-	hose->mem_resources[1].end = 0;
>-	hose->mem_resources[2].flags = 0;
>-	hose->mem_resources[2].start = 0;
>-	hose->mem_resources[2].end = 0;
>-
> #if 0 /* We should really do that ... */
> 	rc = opal_pci_set_phb_mem_window(opal->phb_id,
> 					 window_type,
>@@ -1404,6 +1656,10 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
> 		ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
> 		ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET);
> 	}
>+
>+	/* Configure M64 window */
>+	if (phb->init_m64 && phb->init_m64(phb))
>+		hose->mem_resources[1].flags = 0;
> }
> 
> void __init pnv_pci_init_ioda2_phb(struct device_node *np)
>diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
>index 676232c..def7171 100644
>--- a/arch/powerpc/platforms/powernv/pci.h
>+++ b/arch/powerpc/platforms/powernv/pci.h
>@@ -21,6 +21,8 @@ enum pnv_phb_model {
> #define PNV_IODA_PE_DEV		(1 << 0)	/* PE has single PCI device	*/
> #define PNV_IODA_PE_BUS		(1 << 1)	/* PE has primary PCI bus	*/
> #define PNV_IODA_PE_BUS_ALL	(1 << 2)	/* PE has subordinate buses	*/
>+#define PNV_IODA_PE_MASTER	(1 << 3)	/* Master PE in compound case	*/
>+#define PNV_IODA_PE_SLAVE	(1 << 4)	/* Slave PE in compound case	*/
> 
> /* Data associated with a PE, including IOMMU tracking etc.. */
> struct pnv_phb;
>@@ -64,6 +66,10 @@ struct pnv_ioda_pe {
> 	 */
> 	int			mve_number;
> 
>+	/* PEs in compound case */
>+	struct pnv_ioda_pe	*master;
>+	struct list_head	slaves;
>+
> 	/* Link in list of PE#s */
> 	struct list_head	dma_link;
> 	struct list_head	list;
>@@ -119,6 +125,9 @@ struct pnv_phb {
> 	void (*fixup_phb)(struct pci_controller *hose);
> 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
> 	void (*shutdown)(struct pnv_phb *phb);
>+	int (*init_m64)(struct pnv_phb *phb);
>+	void (*alloc_m64_pe)(struct pnv_phb *phb);
>+	int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
> 
> 	union {
> 		struct {
>@@ -129,9 +138,20 @@ struct pnv_phb {
> 			/* Global bridge info */
> 			unsigned int		total_pe;
> 			unsigned int		reserved_pe;
>+
>+			/* 32-bit MMIO window */
> 			unsigned int		m32_size;
> 			unsigned int		m32_segsize;
> 			unsigned int		m32_pci_base;
>+
>+			/* 64-bit MMIO window */
>+			unsigned int		m64_bar_idx;

idx is the abbreviation of index, which will move from the beginning to the
end for some calculation. While the m64_bar_idx in your patch is set to a
fixed value to mark the last(15th) M64 BAR is used.

My suggestion is to rename it to m64_bar_num, which we may retrieve it from
firmware. Then we could use this value not only to mark the last M64 BAR, but
also could be used to track the usage of M64 BARs in later.

>+			unsigned long		m64_size;
>+			unsigned long		m64_segsize;
>+			unsigned long		m64_base;
>+			unsigned long		m64_bar_alloc;
>+
>+			/* IO ports */
> 			unsigned int		io_size;
> 			unsigned int		io_segsize;
> 			unsigned int		io_pci_base;
>-- 
>1.8.3.1
>
>_______________________________________________
>Linuxppc-dev mailing list
>Linuxppc-dev at lists.ozlabs.org
>https://lists.ozlabs.org/listinfo/linuxppc-dev

-- 
Richard Yang
Help you, Help me



More information about the Linuxppc-dev mailing list