Re: [Patch v2] Make PCI extended config space (MMCONFIG) a driver opt-in

From: Matthew Wilcox
Date: Mon Jan 14 2008 - 17:52:43 EST

On Sun, Jan 13, 2008 at 09:01:08AM -0800, Arjan van de Ven wrote:
> would be nice the "reg > 256 && raw_pci_Ext_ops==NULL" case would just
> call the raw_pci_ops-> pointer, to give that a chance of refusal
> (but I guess that shouldn't really happen)

We don't have a situation where that can happen -- all the other current
config methods on x86 are limited to <256 bytes. If we get another
method, we can revisit this.

> > - pci_conf1_read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win);
> > + pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win);
>
> couldn't this (at least in some next patch) use the vector if it exists?

I thought so, but due to the way that things are initialised, mmconfig
happens before conf1. conf1 is known to be usable, but hasn't set
raw_pci_ops at this point. Confusing, and not ideal, but fixing this
isn't in scope for 2.6.24.

> > printk(KERN_INFO "PCI: Using MMCONFIG\n");
> > raw_pci_ops = &pci_mmcfg;
> > + raw_pci_ext_ops = &pci_mmcfg;
>
> why set BOTH vectors? you probably ONLY want to set the ext one, so
> that calls to the lower 256 go to the original

I had misunderstood how the x86 pci init happened -- I thought conf1
would override this. It doesn't.

The following patch has been tested on ia64, x86 and x86_64.
It successfully avoids the hang on my G33 machine (ie BAR probing
problem), when applied *after* Ivan's patch.

Greg, please apply Ivan's patch and then this one.

---

PCI: Rationalise raw_pci_ops

Replace raw_pci_ops with raw_pci_read() and raw_pci_write(). This is
a better interface for ACPI, ia64 and now x86.

Make pci_raw_ops private to the x86 arch, and use it to implement
raw_pci_read/write. Add a raw_pci_ext_ops for extended config space.

Signed-off-by: Matthew Wilcox <willy@xxxxxxxxxxxxxxx>

diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 488e48a..8fd7e82 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -43,8 +43,7 @@
#define PCI_SAL_EXT_ADDRESS(seg, bus, devfn, reg) \
(((u64) seg << 28) | (bus << 20) | (devfn << 12) | (reg))

-static int
-pci_sal_read (unsigned int seg, unsigned int bus, unsigned int devfn,
+int raw_pci_read(unsigned int seg, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *value)
{
u64 addr, data = 0;
@@ -68,8 +67,7 @@ pci_sal_read (unsigned int seg, unsigned int bus, unsigned int devfn,
return 0;
}

-static int
-pci_sal_write (unsigned int seg, unsigned int bus, unsigned int devfn,
+int raw_pci_write(unsigned int seg, unsigned int bus, unsigned int devfn,
int reg, int len, u32 value)
{
u64 addr;
@@ -91,24 +89,17 @@ pci_sal_write (unsigned int seg, unsigned int bus, unsigned int devfn,
return 0;
}

-static struct pci_raw_ops pci_sal_ops = {
- .read = pci_sal_read,
- .write = pci_sal_write
-};
-
-struct pci_raw_ops *raw_pci_ops = &pci_sal_ops;
-
-static int
-pci_read (struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+ int size, u32 *value)
{
- return raw_pci_ops->read(pci_domain_nr(bus), bus->number,
+ return raw_pci_read(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}

-static int
-pci_write (struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+ int size, u32 value)
{
- return raw_pci_ops->write(pci_domain_nr(bus), bus->number,
+ return raw_pci_write(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}

diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c
index e1a3e19..999f14f 100644
--- a/arch/ia64/sn/pci/tioce_provider.c
+++ b/arch/ia64/sn/pci/tioce_provider.c
@@ -752,13 +752,13 @@ tioce_kern_init(struct tioce_common *tioce_common)
* Determine the secondary bus number of the port2 logical PPB.
* This is used to decide whether a given pci device resides on
* port1 or port2. Note: We don't have enough plumbing set up
- * here to use pci_read_config_xxx() so use the raw_pci_ops vector.
+ * here to use pci_read_config_xxx() so use raw_pci_read().
*/

seg = tioce_common->ce_pcibus.bs_persist_segment;
bus = tioce_common->ce_pcibus.bs_persist_busnum;

- raw_pci_ops->read(seg, bus, PCI_DEVFN(2, 0), PCI_SECONDARY_BUS, 1,&tmp);
+ raw_pci_read(seg, bus, PCI_DEVFN(2, 0), PCI_SECONDARY_BUS, 1,&tmp);
tioce_kern->ce_port1_secondary = (u8) tmp;

/*
@@ -799,11 +799,11 @@ tioce_kern_init(struct tioce_common *tioce_common)

/* mem base/limit */

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_MEMORY_BASE, 2, &tmp);
base = (u64)tmp << 16;

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_MEMORY_LIMIT, 2, &tmp);
limit = (u64)tmp << 16;
limit |= 0xfffffUL;
@@ -817,21 +817,21 @@ tioce_kern_init(struct tioce_common *tioce_common)
* attributes.
*/

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_PREF_MEMORY_BASE, 2, &tmp);
base = ((u64)tmp & PCI_PREF_RANGE_MASK) << 16;

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_PREF_BASE_UPPER32, 4, &tmp);
base |= (u64)tmp << 32;

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_PREF_MEMORY_LIMIT, 2, &tmp);

limit = ((u64)tmp & PCI_PREF_RANGE_MASK) << 16;
limit |= 0xfffffUL;

- raw_pci_ops->read(seg, bus, PCI_DEVFN(dev, 0),
+ raw_pci_read(seg, bus, PCI_DEVFN(dev, 0),
PCI_PREF_LIMIT_UPPER32, 4, &tmp);
limit |= (u64)tmp << 32;

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index fab30e1..7f73f7c 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -27,7 +27,7 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
pci_write_config_byte(dev, 0xf4, config|0x2);

/* read xTPR register */
- raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word);
+ raw_pci_read(0, 0, 0x40, 0x4c, 2, &word);

if (!(word & (1 << 13))) {
printk(KERN_INFO "Intel E7520/7320/7525 detected. "
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8627463..f2bd9f3 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -26,16 +26,37 @@ int pcibios_last_bus = -1;
unsigned long pirq_table_addr;
struct pci_bus *pci_root_bus;
struct pci_raw_ops *raw_pci_ops;
+struct pci_raw_ops *raw_pci_ext_ops;
+
+int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 *val)
+{
+ if (reg < 256 && raw_pci_ops)
+ return raw_pci_ops->read(domain, bus, devfn, reg, len, val);
+ if (raw_pci_ext_ops)
+ return raw_pci_ext_ops->read(domain, bus, devfn, reg, len, val);
+ return -EINVAL;
+}
+
+int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 val)
+{
+ if (reg < 256 && raw_pci_ops)
+ return raw_pci_ops->write(domain, bus, devfn, reg, len, val);
+ if (raw_pci_ext_ops)
+ return raw_pci_ext_ops->write(domain, bus, devfn, reg, len, val);
+ return -EINVAL;
+}

static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
{
- return raw_pci_ops->read(pci_domain_nr(bus), bus->number,
+ return raw_pci_read(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}

static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
{
- return raw_pci_ops->write(pci_domain_nr(bus), bus->number,
+ return raw_pci_write(pci_domain_nr(bus), bus->number,
devfn, where, size, value);
}

diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 431c9a5..42f3e4c 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -14,7 +14,7 @@
#define PCI_CONF1_ADDRESS(bus, devfn, reg) \
(0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3))

-int pci_conf1_read(unsigned int seg, unsigned int bus,
+static int pci_conf1_read(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 *value)
{
unsigned long flags;
@@ -45,7 +45,7 @@ int pci_conf1_read(unsigned int seg, unsigned int bus,
return 0;
}

-int pci_conf1_write(unsigned int seg, unsigned int bus,
+static int pci_conf1_write(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 value)
{
unsigned long flags;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 6cff66d..b31cd6a 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -215,7 +215,8 @@ static int quirk_aspm_offset[MAX_PCIEROOT << 3];

static int quirk_pcie_aspm_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
{
- return raw_pci_ops->read(0, bus->number, devfn, where, size, value);
+ return raw_pci_read(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
}

/*
@@ -231,7 +232,8 @@ static int quirk_pcie_aspm_write(struct pci_bus *bus, unsigned int devfn, int wh
if ((offset) && (where == offset))
value = value & 0xfffffffc;

- return raw_pci_ops->write(0, bus->number, devfn, where, size, value);
+ return raw_pci_write(pci_domain_nr(bus), bus->number,
+ devfn, where, size, value);
}

static struct pci_ops quirk_pcie_aspm_ops = {
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 5565d70..e041ced 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -22,7 +22,7 @@ static void __devinit pcibios_fixup_peer_bridges(void)
if (pci_find_bus(0, n))
continue;
for (devfn = 0; devfn < 256; devfn += 8) {
- if (!raw_pci_ops->read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
+ if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
l != 0x0000 && l != 0xffff) {
DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 6b521d3..8d54df4 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -28,7 +28,7 @@ static int __initdata pci_mmcfg_resources_inserted;
static const char __init *pci_mmcfg_e7520(void)
{
u32 win;
- pci_conf1_read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win);
+ pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win);

win = win & 0xf000;
if(win == 0x0000 || win == 0xf000)
@@ -53,7 +53,7 @@ static const char __init *pci_mmcfg_intel_945(void)

pci_mmcfg_config_num = 1;

- pci_conf1_read(0, 0, PCI_DEVFN(0,0), 0x48, 4, &pciexbar);
+ pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0x48, 4, &pciexbar);

/* Enable bit */
if (!(pciexbar & 1))
@@ -118,7 +118,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
int i;
const char *name;

- pci_conf1_read(0, 0, PCI_DEVFN(0,0), 0, 4, &l);
+ pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0, 4, &l);
vendor = l & 0xffff;
device = (l >> 16) & 0xffff;

diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index 7b75e65..081816a 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -68,9 +68,6 @@ err: *value = -1;
return -EINVAL;
}

- if (reg < 256)
- return pci_conf1_read(seg,bus,devfn,reg,len,value);
-
base = get_base_addr(seg, bus, devfn);
if (!base)
goto err;
@@ -104,9 +101,6 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
if ((bus > 255) || (devfn > 255) || (reg > 4095))
return -EINVAL;

- if (reg < 256)
- return pci_conf1_write(seg,bus,devfn,reg,len,value);
-
base = get_base_addr(seg, bus, devfn);
if (!base)
return -EINVAL;
@@ -138,7 +132,7 @@ static struct pci_raw_ops pci_mmcfg = {

int __init pci_mmcfg_arch_init(void)
{
- printk(KERN_INFO "PCI: Using MMCONFIG\n");
- raw_pci_ops = &pci_mmcfg;
+ printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n");
+ raw_pci_ext_ops = &pci_mmcfg;
return 1;
}
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index c4cf318..9207fd4 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -58,9 +58,6 @@ err: *value = -1;
return -EINVAL;
}

- if (reg < 256)
- return pci_conf1_read(seg,bus,devfn,reg,len,value);
-
addr = pci_dev_base(seg, bus, devfn);
if (!addr)
goto err;
@@ -89,9 +86,6 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
return -EINVAL;

- if (reg < 256)
- return pci_conf1_write(seg,bus,devfn,reg,len,value);
-
addr = pci_dev_base(seg, bus, devfn);
if (!addr)
return -EINVAL;
@@ -150,6 +144,6 @@ int __init pci_mmcfg_arch_init(void)
return 0;
}
}
- raw_pci_ops = &pci_mmcfg;
+ raw_pci_ext_ops = &pci_mmcfg;
return 1;
}
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index 36cb44c..3431518 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -85,10 +85,17 @@ extern spinlock_t pci_config_lock;
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
extern void (*pcibios_disable_irq)(struct pci_dev *dev);

-extern int pci_conf1_write(unsigned int seg, unsigned int bus,
- unsigned int devfn, int reg, int len, u32 value);
-extern int pci_conf1_read(unsigned int seg, unsigned int bus,
- unsigned int devfn, int reg, int len, u32 *value);
+struct pci_raw_ops {
+ int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 *val);
+ int (*write)(unsigned int domain, unsigned int bus, unsigned int devfn,
+ int reg, int len, u32 val);
+};
+
+extern struct pci_raw_ops *raw_pci_ops;
+extern struct pci_raw_ops *raw_pci_ext_ops;
+
+extern struct pci_raw_ops pci_direct_conf1;

extern int pci_direct_probe(void);
extern void pci_direct_init(int type);
diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c
index 8ecb1c7..c2df4e9 100644
--- a/arch/x86/pci/visws.c
+++ b/arch/x86/pci/visws.c
@@ -13,9 +13,6 @@

#include "pci.h"

-
-extern struct pci_raw_ops pci_direct_conf1;
-
static int pci_visws_enable_irq(struct pci_dev *dev) { return 0; }
static void pci_visws_disable_irq(struct pci_dev *dev) { }

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index e3a673a..f190db9 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -139,15 +139,6 @@ acpi_status __init acpi_os_initialize(void)

acpi_status acpi_os_initialize1(void)
{
- /*
- * Initialize PCI configuration space access, as we'll need to access
- * it while walking the namespace (bus 0 and root bridges w/ _BBNs).
- */
- if (!raw_pci_ops) {
- printk(KERN_ERR PREFIX
- "Access to PCI configuration space unavailable\n");
- return AE_NULL_ENTRY;
- }
kacpid_wq = create_singlethread_workqueue("kacpid");
kacpi_notify_wq = create_singlethread_workqueue("kacpi_notify");
BUG_ON(!kacpid_wq);
@@ -498,11 +489,9 @@ acpi_os_read_pci_configuration(struct acpi_pci_id * pci_id, u32 reg,
return AE_ERROR;
}

- BUG_ON(!raw_pci_ops);
-
- result = raw_pci_ops->read(pci_id->segment, pci_id->bus,
- PCI_DEVFN(pci_id->device, pci_id->function),
- reg, size, value);
+ result = raw_pci_read(pci_id->segment, pci_id->bus,
+ PCI_DEVFN(pci_id->device, pci_id->function),
+ reg, size, value);

return (result ? AE_ERROR : AE_OK);
}
@@ -529,11 +518,9 @@ acpi_os_write_pci_configuration(struct acpi_pci_id * pci_id, u32 reg,
return AE_ERROR;
}

- BUG_ON(!raw_pci_ops);
-
- result = raw_pci_ops->write(pci_id->segment, pci_id->bus,
- PCI_DEVFN(pci_id->device, pci_id->function),
- reg, size, value);
+ result = raw_pci_write(pci_id->segment, pci_id->bus,
+ PCI_DEVFN(pci_id->device, pci_id->function),
+ reg, size, value);

return (result ? AE_ERROR : AE_OK);
}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 0dd93bb..f4f1edd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -304,14 +304,14 @@ struct pci_ops {
int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val);
};

-struct pci_raw_ops {
- int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
- int reg, int len, u32 *val);
- int (*write)(unsigned int domain, unsigned int bus, unsigned int devfn,
- int reg, int len, u32 val);
-};
-
-extern struct pci_raw_ops *raw_pci_ops;
+/*
+ * ACPI needs to be able to access PCI config space before we've done a
+ * PCI bus scan and created pci_bus structures.
+ */
+extern int raw_pci_read(unsigned int domain, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 *val);
+extern int raw_pci_write(unsigned int domain, unsigned int bus,
+ unsigned int devfn, int reg, int len, u32 val);

struct pci_bus_region {
unsigned long start;

--
Intel are signing my paycheques ... these opinions are still mine
"Bill, look, we understand that you're interested in selling us this
operating system, but compare it to ours. We can't possibly take such
a retrograde step."
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/