Message-ID: <56C5B83F.4010602@huawei.com>
Date:	Thu, 18 Feb 2016 20:25:35 +0800
From:	"liudongdong (C)" <liudongdong3@...wei.com>
To:	Tomasz Nowicki <tn@...ihalf.com>, <helgaas@...nel.org>,
	<arnd@...db.de>, <will.deacon@....com>, <catalin.marinas@....com>,
	<rafael@...nel.org>, <hanjun.guo@...aro.org>,
	<Lorenzo.Pieralisi@....com>, <okaya@...eaurora.org>,
	<jiang.liu@...ux.intel.com>, <jchandra@...adcom.com>,
	<Stefano.Stabellini@...citrix.com>
CC:	<jcm@...hat.com>, <linaro-acpi@...ts.linaro.org>,
	<linux-pci@...r.kernel.org>, <Liviu.Dudau@....com>,
	<ddaney@...iumnetworks.com>, <linux-kernel@...r.kernel.org>,
	<linux-acpi@...r.kernel.org>, <robert.richter@...iumnetworks.com>,
	<wangyijing@...wei.com>, <mw@...ihalf.com>,
	<linux-arm-kernel@...ts.infradead.org>
Subject: Re: [Linaro-acpi] [PATCH V5 01/15] ACPI: MCFG: Move mmcfg_list
 management to drivers/acpi

Hi Tomasz

在 2016/2/16 21:53, Tomasz Nowicki 写道:
> From: Jayachandran C <jchandra@...adcom.com>
>
> Move pci_mmcfg_list handling to a drivers/acpi/pci_mcfg.c. This is
> to share the API and code with ARM64 later. The corresponding
> declarations are moved from asm/pci_x86.h to linux/pci-acpi.h
>
> As a part of this we introduce three functions that can be
> implemented by the arch code: pci_mmconfig_map_resource() to map a
> mcfg entry, pci_mmconfig_unmap_resource to do the corresponding
> unmap and pci_mmconfig_enabled to see if the arch setup of
> mcfg entries was successful. We also provide weak implementations
> of these, which will be used from ARM64. On x86, we retain the
> old logic by providing platform specific implementation.
>
> This patch is purely rearranging code, it should not have any
> impact on the logic of MCFG parsing or list handling.
>
> Signed-off-by: Jayachandran C <jchandra@...adcom.com>
> [Xen parts:]
> Acked-by: David Vrabel <david.vrabel@...rix.com>
> ---
>   arch/x86/include/asm/pci_x86.h |  24 +---
>   arch/x86/pci/mmconfig-shared.c | 269 +++++------------------------------
>   arch/x86/pci/mmconfig_32.c     |   1 +
>   arch/x86/pci/mmconfig_64.c     |   1 +
>   arch/x86/pci/numachip.c        |   1 +
>   drivers/acpi/Makefile          |   1 +
>   drivers/acpi/pci_mcfg.c        | 312 +++++++++++++++++++++++++++++++++++++++++
>   drivers/xen/pci.c              |   5 +-
>   include/linux/pci-acpi.h       |  33 +++++
>   9 files changed, 386 insertions(+), 261 deletions(-)
>   create mode 100644 drivers/acpi/pci_mcfg.c
>
> diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
> index 46873fb..7824626 100644
> --- a/arch/x86/include/asm/pci_x86.h
> +++ b/arch/x86/include/asm/pci_x86.h
> @@ -122,33 +122,11 @@ extern int pci_legacy_init(void);
>   extern void pcibios_fixup_irqs(void);
>
>   /* pci-mmconfig.c */
> -
> -/* "PCI MMCONFIG %04x [bus %02x-%02x]" */
> -#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2)
> -
> -struct pci_mmcfg_region {
> -	struct list_head list;
> -	struct resource res;
> -	u64 address;
> -	char __iomem *virt;
> -	u16 segment;
> -	u8 start_bus;
> -	u8 end_bus;
> -	char name[PCI_MMCFG_RESOURCE_NAME_LEN];
> -};
> -
> +struct pci_mmcfg_region;
>   extern int __init pci_mmcfg_arch_init(void);
>   extern void __init pci_mmcfg_arch_free(void);
>   extern int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg);
>   extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg);
> -extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
> -			       phys_addr_t addr);
> -extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end);
> -extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
> -
> -extern struct list_head pci_mmcfg_list;
> -
> -#define PCI_MMCFG_BUS_OFFSET(bus)      ((bus) << 20)
>
>   /*
>    * On AMD Fam10h CPUs, all PCI MMIO configuration space accesses must use
> diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
> index dd30b7e..626710b 100644
> --- a/arch/x86/pci/mmconfig-shared.c
> +++ b/arch/x86/pci/mmconfig-shared.c
> @@ -12,13 +12,12 @@
>
>   #include <linux/pci.h>
>   #include <linux/init.h>
> -#include <linux/sfi_acpi.h>
>   #include <linux/bitmap.h>
> -#include <linux/dmi.h>
>   #include <linux/slab.h>
>   #include <linux/mutex.h>
>   #include <linux/rculist.h>
>   #include <asm/e820.h>
> +#include <linux/pci-acpi.h>
>   #include <asm/pci_x86.h>
>   #include <asm/acpi.h>
>
> @@ -27,9 +26,6 @@
>   /* Indicate if the mmcfg resources have been placed into the resource table. */
>   static bool pci_mmcfg_running_state;
>   static bool pci_mmcfg_arch_init_failed;
> -static DEFINE_MUTEX(pci_mmcfg_lock);
> -
> -LIST_HEAD(pci_mmcfg_list);
>
>   static void __init pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
>   {
> @@ -48,83 +44,6 @@ static void __init free_all_mmcfg(void)
>   		pci_mmconfig_remove(cfg);
>   }
>
> -static void list_add_sorted(struct pci_mmcfg_region *new)
> -{
> -	struct pci_mmcfg_region *cfg;
> -
> -	/* keep list sorted by segment and starting bus number */
> -	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) {
> -		if (cfg->segment > new->segment ||
> -		    (cfg->segment == new->segment &&
> -		     cfg->start_bus >= new->start_bus)) {
> -			list_add_tail_rcu(&new->list, &cfg->list);
> -			return;
> -		}
> -	}
> -	list_add_tail_rcu(&new->list, &pci_mmcfg_list);
> -}
> -
> -static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
> -						   int end, u64 addr)
> -{
> -	struct pci_mmcfg_region *new;
> -	struct resource *res;
> -
> -	if (addr == 0)
> -		return NULL;
> -
> -	new = kzalloc(sizeof(*new), GFP_KERNEL);
> -	if (!new)
> -		return NULL;
> -
> -	new->address = addr;
> -	new->segment = segment;
> -	new->start_bus = start;
> -	new->end_bus = end;
> -
> -	res = &new->res;
> -	res->start = addr + PCI_MMCFG_BUS_OFFSET(start);
> -	res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
> -	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
> -	snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
> -		 "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
> -	res->name = new->name;
> -
> -	return new;
> -}
> -
> -static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
> -							int end, u64 addr)
> -{
> -	struct pci_mmcfg_region *new;
> -
> -	new = pci_mmconfig_alloc(segment, start, end, addr);
> -	if (new) {
> -		mutex_lock(&pci_mmcfg_lock);
> -		list_add_sorted(new);
> -		mutex_unlock(&pci_mmcfg_lock);
> -
> -		pr_info(PREFIX
> -		       "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
> -		       "(base %#lx)\n",
> -		       segment, start, end, &new->res, (unsigned long)addr);
> -	}
> -
> -	return new;
> -}
> -
> -struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
> -{
> -	struct pci_mmcfg_region *cfg;
> -
> -	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
> -		if (cfg->segment == segment &&
> -		    cfg->start_bus <= bus && bus <= cfg->end_bus)
> -			return cfg;
> -
> -	return NULL;
> -}
> -
>   static const char *__init pci_mmcfg_e7520(void)
>   {
>   	u32 win;
> @@ -543,73 +462,6 @@ static void __init pci_mmcfg_reject_broken(int early)
>   	}
>   }
>
> -static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
> -					struct acpi_mcfg_allocation *cfg)
> -{
> -	int year;
> -
> -	if (cfg->address < 0xFFFFFFFF)
> -		return 0;
> -
> -	if (!strncmp(mcfg->header.oem_id, "SGI", 3))
> -		return 0;
> -
> -	if (mcfg->header.revision >= 1) {
> -		if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
> -		    year >= 2010)
> -			return 0;
> -	}
> -
> -	pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
> -	       "is above 4GB, ignored\n", cfg->pci_segment,
> -	       cfg->start_bus_number, cfg->end_bus_number, cfg->address);
> -	return -EINVAL;
> -}
> -
> -static int __init pci_parse_mcfg(struct acpi_table_header *header)
> -{
> -	struct acpi_table_mcfg *mcfg;
> -	struct acpi_mcfg_allocation *cfg_table, *cfg;
> -	unsigned long i;
> -	int entries;
> -
> -	if (!header)
> -		return -EINVAL;
> -
> -	mcfg = (struct acpi_table_mcfg *)header;
> -
> -	/* how many config structures do we have */
> -	free_all_mmcfg();
> -	entries = 0;
> -	i = header->length - sizeof(struct acpi_table_mcfg);
> -	while (i >= sizeof(struct acpi_mcfg_allocation)) {
> -		entries++;
> -		i -= sizeof(struct acpi_mcfg_allocation);
> -	}
> -	if (entries == 0) {
> -		pr_err(PREFIX "MMCONFIG has no entries\n");
> -		return -ENODEV;
> -	}
> -
> -	cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
> -	for (i = 0; i < entries; i++) {
> -		cfg = &cfg_table[i];
> -		if (acpi_mcfg_check_entry(mcfg, cfg)) {
> -			free_all_mmcfg();
> -			return -ENODEV;
> -		}
> -
> -		if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
> -				   cfg->end_bus_number, cfg->address) == NULL) {
> -			pr_warn(PREFIX "no memory for MCFG entries\n");
> -			free_all_mmcfg();
> -			return -ENOMEM;
> -		}
> -	}
> -
> -	return 0;
> -}
> -
>   #ifdef CONFIG_ACPI_APEI
>   extern int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size,
>   				     void *data), void *data);
> @@ -662,13 +514,20 @@ static void __init __pci_mmcfg_init(int early)
>
>   static int __initdata known_bridge;
>
> +static void __init pci_mmcfg_list_setup(void)
> +{
> +	free_all_mmcfg();
> +	if (pci_mmconfig_parse_table())
> +		free_all_mmcfg();
> +}
> +
>   void __init pci_mmcfg_early_init(void)
>   {
>   	if (pci_probe & PCI_PROBE_MMCONF) {
>   		if (pci_mmcfg_check_hostbridge())
>   			known_bridge = 1;
>   		else
> -			acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
> +			pci_mmcfg_list_setup();
>   		__pci_mmcfg_init(1);
>
>   		set_apei_filter();
> @@ -686,7 +545,7 @@ void __init pci_mmcfg_late_init(void)
>
>   	/* MMCONFIG hasn't been enabled yet, try again */
>   	if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) {
> -		acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
> +		pci_mmcfg_list_setup();
>   		__pci_mmcfg_init(0);
>   	}
>   }
> @@ -720,99 +579,41 @@ static int __init pci_mmcfg_late_insert_resources(void)
>    */
>   late_initcall(pci_mmcfg_late_insert_resources);
>
> -/* Add MMCFG information for host bridges */
> -int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
> -			phys_addr_t addr)
> +int pci_mmconfig_map_resource(struct device *dev, struct pci_mmcfg_region *cfg)
>   {
> -	int rc;
> -	struct resource *tmp = NULL;
> -	struct pci_mmcfg_region *cfg;
> +	struct resource *tmp;
>
> -	if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
> -		return -ENODEV;
> -
> -	if (start > end)
> -		return -EINVAL;
> -
> -	mutex_lock(&pci_mmcfg_lock);
> -	cfg = pci_mmconfig_lookup(seg, start);
> -	if (cfg) {
> -		if (cfg->end_bus < end)
> -			dev_info(dev, FW_INFO
> -				 "MMCONFIG for "
> -				 "domain %04x [bus %02x-%02x] "
> -				 "only partially covers this bridge\n",
> -				  cfg->segment, cfg->start_bus, cfg->end_bus);
> -		mutex_unlock(&pci_mmcfg_lock);
> -		return -EEXIST;
> -	}
> -
> -	if (!addr) {
> -		mutex_unlock(&pci_mmcfg_lock);
> -		return -EINVAL;
> -	}
> -
> -	rc = -EBUSY;
> -	cfg = pci_mmconfig_alloc(seg, start, end, addr);
> -	if (cfg == NULL) {
> -		dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
> -		rc = -ENOMEM;
> -	} else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
> +	if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
>   		dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n",
>   			 &cfg->res);
> -	} else {
> -		/* Insert resource if it's not in boot stage */
> -		if (pci_mmcfg_running_state)
> -			tmp = insert_resource_conflict(&iomem_resource,
> -						       &cfg->res);
> -
> +		return -EBUSY;
> +	}
> +	/* Insert resource if it's not in boot stage */
> +	if (pci_mmcfg_running_state) {
> +		tmp = insert_resource_conflict(&iomem_resource,
> +					       &cfg->res);
>   		if (tmp) {
> -			dev_warn(dev,
> -				 "MMCONFIG %pR conflicts with "
> -				 "%s %pR\n",
> -				 &cfg->res, tmp->name, tmp);
> -		} else if (pci_mmcfg_arch_map(cfg)) {
> -			dev_warn(dev, "fail to map MMCONFIG %pR.\n",
> -				 &cfg->res);
> -		} else {
> -			list_add_sorted(cfg);
> -			dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
> -				 &cfg->res, (unsigned long)addr);
> -			cfg = NULL;
> -			rc = 0;
> +			dev_warn(dev, "MMCONFIG %pR conflicts with %s %pR\n",
> +				&cfg->res, tmp->name, tmp);
> +			return -EBUSY;
>   		}
>   	}
> -
> -	if (cfg) {
> -		if (cfg->res.parent)
> -			release_resource(&cfg->res);
> -		kfree(cfg);
> +	if (pci_mmcfg_arch_map(cfg)) {
> +		dev_warn(dev, "fail to map MMCONFIG %pR.\n", &cfg->res);
> +		return -EBUSY;
>   	}
> -
> -	mutex_unlock(&pci_mmcfg_lock);
> -
> -	return rc;
> +	return 0;
>   }
>
> -/* Delete MMCFG information for host bridges */
> -int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
> +void pci_mmconfig_unmap_resource(struct pci_mmcfg_region *cfg)
>   {
> -	struct pci_mmcfg_region *cfg;
> -
> -	mutex_lock(&pci_mmcfg_lock);
> -	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
> -		if (cfg->segment == seg && cfg->start_bus == start &&
> -		    cfg->end_bus == end) {
> -			list_del_rcu(&cfg->list);
> -			synchronize_rcu();
> -			pci_mmcfg_arch_unmap(cfg);
> -			if (cfg->res.parent)
> -				release_resource(&cfg->res);
> -			mutex_unlock(&pci_mmcfg_lock);
> -			kfree(cfg);
> -			return 0;
> -		}
> -	mutex_unlock(&pci_mmcfg_lock);
> +	pci_mmcfg_arch_unmap(cfg);
> +	if (cfg->res.parent)
> +		release_resource(&cfg->res);
> +	cfg->res.parent = NULL;
> +}
>
> -	return -ENOENT;
> +int pci_mmconfig_enabled(void)
> +{
> +	return (pci_probe & PCI_PROBE_MMCONF) && !pci_mmcfg_arch_init_failed;
>   }
> diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
> index 43984bc..38a37f8 100644
> --- a/arch/x86/pci/mmconfig_32.c
> +++ b/arch/x86/pci/mmconfig_32.c
> @@ -12,6 +12,7 @@
>   #include <linux/pci.h>
>   #include <linux/init.h>
>   #include <linux/rcupdate.h>
> +#include <linux/pci-acpi.h>
>   #include <asm/e820.h>
>   #include <asm/pci_x86.h>
>
> diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
> index bea5249..29253ec 100644
> --- a/arch/x86/pci/mmconfig_64.c
> +++ b/arch/x86/pci/mmconfig_64.c
> @@ -10,6 +10,7 @@
>   #include <linux/acpi.h>
>   #include <linux/bitmap.h>
>   #include <linux/rcupdate.h>
> +#include <linux/pci-acpi.h>
>   #include <asm/e820.h>
>   #include <asm/pci_x86.h>
>
> diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
> index 2e565e6..c181eeb 100644
> --- a/arch/x86/pci/numachip.c
> +++ b/arch/x86/pci/numachip.c
> @@ -14,6 +14,7 @@
>    */
>
>   #include <linux/pci.h>
> +#include <linux/pci-acpi.h>
>   #include <asm/pci_x86.h>
>
>   static u8 limit __read_mostly;
> diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
> index 7ea903d..e5e4393 100644
> --- a/drivers/acpi/Makefile
> +++ b/drivers/acpi/Makefile
> @@ -40,6 +40,7 @@ acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o
>   acpi-y				+= ec.o
>   acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
>   acpi-y				+= pci_root.o pci_link.o pci_irq.o
> +acpi-$(CONFIG_PCI_MMCONFIG)	+= pci_mcfg.o
>   acpi-y				+= acpi_lpss.o acpi_apd.o
>   acpi-y				+= acpi_platform.o
>   acpi-y				+= acpi_pnp.o
> diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
> new file mode 100644
> index 0000000..ea84365
> --- /dev/null
> +++ b/drivers/acpi/pci_mcfg.c
> @@ -0,0 +1,312 @@
> +/*
> + * pci_mcfg.c
> + *
> + * Common code to maintain the MCFG areas and mappings
> + *
> + * This has been extracted from arch/x86/pci/mmconfig-shared.c
> + * and moved here so that other architectures can use this code.
> + */
> +
> +#include <linux/pci.h>
> +#include <linux/init.h>
> +#include <linux/dmi.h>
> +#include <linux/pci-acpi.h>
> +#include <linux/sfi_acpi.h>
> +#include <linux/slab.h>
> +#include <linux/mutex.h>
> +#include <linux/rculist.h>
> +
> +#define PREFIX	"ACPI: "
> +
> +static DEFINE_MUTEX(pci_mmcfg_lock);
> +LIST_HEAD(pci_mmcfg_list);
> +
> +static void list_add_sorted(struct pci_mmcfg_region *new)
> +{
> +	struct pci_mmcfg_region *cfg;
> +
> +	/* keep list sorted by segment and starting bus number */
> +	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) {
> +		if (cfg->segment > new->segment ||
> +		    (cfg->segment == new->segment &&
> +		     cfg->start_bus >= new->start_bus)) {
> +			list_add_tail_rcu(&new->list, &cfg->list);
> +			return;
> +		}
> +	}
> +	list_add_tail_rcu(&new->list, &pci_mmcfg_list);
> +}
> +
> +static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
> +						   int end, u64 addr)
> +{
> +	struct pci_mmcfg_region *new;
> +	struct resource *res;
> +
> +	if (addr == 0)
> +		return NULL;
> +
> +	new = kzalloc(sizeof(*new), GFP_KERNEL);
> +	if (!new)
> +		return NULL;
> +
> +	new->address = addr;
> +	new->segment = segment;
> +	new->start_bus = start;
> +	new->end_bus = end;
> +
> +	res = &new->res;
> +	res->start = addr + PCI_MMCFG_BUS_OFFSET(start);
> +	res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
> +	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
> +	snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
> +		 "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
> +	res->name = new->name;
> +
> +	return new;
> +}
> +
> +struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
> +							int end, u64 addr)
> +{
> +	struct pci_mmcfg_region *new;
> +
> +	new = pci_mmconfig_alloc(segment, start, end, addr);
> +	if (new) {
> +		mutex_lock(&pci_mmcfg_lock);
> +		list_add_sorted(new);
> +		mutex_unlock(&pci_mmcfg_lock);
> +
> +		pr_info(PREFIX
> +		       "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
> +		       "(base %#lx)\n",
> +		       segment, start, end, &new->res, (unsigned long)addr);
> +	}
> +
> +	return new;
> +}
> +
> +struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
> +{
> +	struct pci_mmcfg_region *cfg;
> +
> +	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
> +		if (cfg->segment == segment &&
> +		    cfg->start_bus <= bus && bus <= cfg->end_bus)
> +			return cfg;
> +
> +	return NULL;
> +}
> +
> +/*
> + * Map a pci_mmcfg_region, can be overrriden by arch
> + */
> +int __weak pci_mmconfig_map_resource(struct device *dev,
> +	struct pci_mmcfg_region *mcfg)
> +{
> +	struct resource *tmp;
> +	void __iomem *vaddr;
> +
> +	tmp = insert_resource_conflict(&iomem_resource, &mcfg->res);
> +	if (tmp) {
> +		dev_warn(dev, "MMCONFIG %pR conflicts with %s %pR\n",
> +			&mcfg->res, tmp->name, tmp);
> +		return -EBUSY;
> +	}
> +
> +	vaddr =  ioremap(mcfg->res.start, resource_size(&mcfg->res));
> +	if (!vaddr) {
> +		release_resource(&mcfg->res);
> +		return -ENOMEM;
> +	}
> +
> +	mcfg->virt = vaddr;
Here should be changed to
	mcfg->virt = vaddr - PCI_MMCFG_BUS_OFFSET(mcfg->start_bus);

or when pcie host "start_bus" is not 0, the configuraion access will be wrong.

See v3 or v4 patchset "addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus);"
static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg)
{
	void __iomem *addr;
	u64 start, size;
	int num_buses;

	start = cfg->address + PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
	num_buses = cfg->end_bus - cfg->start_bus + 1;
	size = PCI_MMCFG_BUS_OFFSET(num_buses);
	addr = ioremap_nocache(start, size);
	if (addr)
		addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
	return addr;
}

Dongdong
Thanks

> +	return 0;
> +}
> +
> +/*
> + * Unmap a pci_mmcfg_region, can be overrriden by arch
> + */
> +void __weak pci_mmconfig_unmap_resource(struct pci_mmcfg_region *mcfg)
> +{
> +	if (mcfg->virt) {
> +		iounmap(mcfg->virt);
> +		mcfg->virt = NULL;
> +	}
> +	if (mcfg->res.parent) {
> +		release_resource(&mcfg->res);
> +		mcfg->res.parent = NULL;
> +	}
> +}
> +
> +/*
> + * check if the mmconfig is enabled and configured
> + */
> +int __weak pci_mmconfig_enabled(void)
> +{
> +	return 1;
> +}
> +
> +/* Add MMCFG information for host bridges */
> +int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
> +			phys_addr_t addr)
> +{
> +	struct pci_mmcfg_region *cfg;
> +	int rc;
> +
> +	if (!pci_mmconfig_enabled())
> +		return -ENODEV;
> +	if (start > end)
> +		return -EINVAL;
> +
> +	mutex_lock(&pci_mmcfg_lock);
> +	cfg = pci_mmconfig_lookup(seg, start);
> +	if (cfg) {
> +		if (cfg->end_bus < end)
> +			dev_info(dev, FW_INFO
> +				 "MMCONFIG for "
> +				 "domain %04x [bus %02x-%02x] "
> +				 "only partially covers this bridge\n",
> +				  cfg->segment, cfg->start_bus, cfg->end_bus);
> +		rc = -EEXIST;
> +		goto err;
> +	}
> +
> +	if (!addr) {
> +		rc = -EINVAL;
> +		goto err;
> +	}
> +
> +	cfg = pci_mmconfig_alloc(seg, start, end, addr);
> +	if (cfg == NULL) {
> +		dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
> +		rc = -ENOMEM;
> +		goto err;
> +	}
> +	rc = pci_mmconfig_map_resource(dev, cfg);
> +	if (!rc) {
> +		list_add_sorted(cfg);
> +		dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
> +				 &cfg->res, (unsigned long)addr);
> +		return 0;
> +	} else {
> +		if (cfg->res.parent)
> +			release_resource(&cfg->res);
> +		kfree(cfg);
> +	}
> +
> +err:
> +	mutex_unlock(&pci_mmcfg_lock);
> +	return rc;
> +}
> +
> +/* Delete MMCFG information for host bridges */
> +int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
> +{
> +	struct pci_mmcfg_region *cfg;
> +
> +	mutex_lock(&pci_mmcfg_lock);
> +	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
> +		if (cfg->segment == seg && cfg->start_bus == start &&
> +		    cfg->end_bus == end) {
> +			list_del_rcu(&cfg->list);
> +			synchronize_rcu();
> +			pci_mmconfig_unmap_resource(cfg);
> +			mutex_unlock(&pci_mmcfg_lock);
> +			kfree(cfg);
> +			return 0;
> +		}
> +	mutex_unlock(&pci_mmcfg_lock);
> +
> +	return -ENOENT;
> +}
> +
> +static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
> +					struct acpi_mcfg_allocation *cfg)
> +{
> +	int year;
> +
> +	if (!config_enabled(CONFIG_X86))
> +		return 0;
> +
> +	if (cfg->address < 0xFFFFFFFF)
> +		return 0;
> +
> +	if (!strncmp(mcfg->header.oem_id, "SGI", 3))
> +		return 0;
> +
> +	if (mcfg->header.revision >= 1) {
> +		if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
> +		    year >= 2010)
> +			return 0;
> +	}
> +
> +	pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
> +	       "is above 4GB, ignored\n", cfg->pci_segment,
> +	       cfg->start_bus_number, cfg->end_bus_number, cfg->address);
> +	return -EINVAL;
> +}
> +
> +static int __init pci_parse_mcfg(struct acpi_table_header *header)
> +{
> +	struct acpi_table_mcfg *mcfg;
> +	struct acpi_mcfg_allocation *cfg_table, *cfg;
> +	unsigned long i;
> +	int entries;
> +
> +	if (!header)
> +		return -EINVAL;
> +
> +	mcfg = (struct acpi_table_mcfg *)header;
> +
> +	/* how many config structures do we have */
> +	entries = 0;
> +	i = header->length - sizeof(struct acpi_table_mcfg);
> +	while (i >= sizeof(struct acpi_mcfg_allocation)) {
> +		entries++;
> +		i -= sizeof(struct acpi_mcfg_allocation);
> +	}
> +	if (entries == 0) {
> +		pr_err(PREFIX "MMCONFIG has no entries\n");
> +		return -ENODEV;
> +	}
> +
> +	cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
> +	for (i = 0; i < entries; i++) {
> +		cfg = &cfg_table[i];
> +		if (acpi_mcfg_check_entry(mcfg, cfg))
> +			return -ENODEV;
> +
> +		if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
> +				   cfg->end_bus_number, cfg->address) == NULL) {
> +			pr_warn(PREFIX "no memory for MCFG entries\n");
> +			return -ENOMEM;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
> +int __init pci_mmconfig_parse_table(void)
> +{
> +	return acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
> +}
> +
> +void __weak __init pci_mmcfg_late_init(void)
> +{
> +	int err, n = 0;
> +	struct pci_mmcfg_region *cfg;
> +
> +	err = pci_mmconfig_parse_table();
> +	if (err) {
> +		pr_err(PREFIX " Failed to parse MCFG (%d)\n", err);
> +		return;
> +	}
> +
> +	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
> +		pci_mmconfig_map_resource(NULL, cfg);
> +		n++;
> +	}
> +
> +	pr_info(PREFIX " MCFG table loaded %d entries\n", n);
> +}
> diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
> index 7494dbe..97aa9d3 100644
> --- a/drivers/xen/pci.c
> +++ b/drivers/xen/pci.c
> @@ -27,9 +27,6 @@
>   #include <asm/xen/hypervisor.h>
>   #include <asm/xen/hypercall.h>
>   #include "../pci/pci.h"
> -#ifdef CONFIG_PCI_MMCONFIG
> -#include <asm/pci_x86.h>
> -#endif
>
>   static bool __read_mostly pci_seg_supported = true;
>
> @@ -221,7 +218,7 @@ static int __init xen_mcfg_late(void)
>   	if (!xen_initial_domain())
>   		return 0;
>
> -	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
> +	if (!pci_mmconfig_enabled())
>   		return 0;
>
>   	if (list_empty(&pci_mmcfg_list))
> diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
> index 89ab057..e9450ef 100644
> --- a/include/linux/pci-acpi.h
> +++ b/include/linux/pci-acpi.h
> @@ -106,6 +106,39 @@ extern const u8 pci_acpi_dsm_uuid[];
>   #define RESET_DELAY_DSM		0x08
>   #define FUNCTION_DELAY_DSM	0x09
>
> +/* common API to maintain list of MCFG regions */
> +/* "PCI MMCONFIG %04x [bus %02x-%02x]" */
> +#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2)
> +
> +struct pci_mmcfg_region {
> +	struct list_head list;
> +	struct resource res;
> +	u64 address;
> +	char __iomem *virt;
> +	u16 segment;
> +	u8 start_bus;
> +	u8 end_bus;
> +	char name[PCI_MMCFG_RESOURCE_NAME_LEN];
> +};
> +
> +extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
> +			       phys_addr_t addr);
> +extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end);
> +
> +extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
> +extern struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
> +							int end, u64 addr);
> +extern int pci_mmconfig_map_resource(struct device *dev,
> +	struct pci_mmcfg_region *mcfg);
> +extern void pci_mmconfig_unmap_resource(struct pci_mmcfg_region *mcfg);
> +extern int pci_mmconfig_enabled(void);
> +extern int __init pci_mmconfig_parse_table(void);
> +
> +extern struct list_head pci_mmcfg_list;
> +
> +#define PCI_MMCFG_BUS_OFFSET(bus)      ((bus) << 20)
> +#define PCI_MMCFG_OFFSET(bus, devfn)   ((bus) << 20 | (devfn) << 12)
> +
>   #else	/* CONFIG_ACPI */
>   static inline void acpi_pci_add_bus(struct pci_bus *bus) { }
>   static inline void acpi_pci_remove_bus(struct pci_bus *bus) { }
>

Powered by blists - more mailing lists