Re: [PATCH] x86/pci: intel ioh need to subtract mmconf range

[Yinghai Lu]

On 01/14/2010 03:49 PM, Bjorn Helgaas wrote:
> On Thursday 14 January 2010 04:38:08 pm Yinghai Lu wrote:
>> On 01/14/2010 03:09 PM, Bjorn Helgaas wrote:
>>> On Thursday 14 January 2010 03:46:35 pm Yinghai Lu wrote:
>>>>
>>>> Bjorn pointed out we need to remove mmconf range
>>>>
>>>> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
>>>>
>>>> ---
>>>>  arch/x86/pci/intel_bus.c |   29 +++++++++++++++++++++++++++--
>>>>  1 file changed, 27 insertions(+), 2 deletions(-)
>>>>
>>>> Index: linux-2.6/arch/x86/pci/intel_bus.c
>>>> ===================================================================
>>>> --- linux-2.6.orig/arch/x86/pci/intel_bus.c
>>>> +++ linux-2.6/arch/x86/pci/intel_bus.c
>>>> @@ -46,6 +46,20 @@ static inline void print_ioh_resources(s
>>>>  
>>>>  #define RANGE_NUM 16
>>>>  
>>>> +static void __devinit subtract_mmconf(struct range *range, int nr)
>>>> +{
>>>> +#ifdef CONFIG_PCI_MMCONFIG
>>>> +	struct pci_mmcfg_region *cfg;
>>>> +
>>>> +	if (list_empty(&pci_mmcfg_list))
>>>> +		return;
>>>> +
>>>> +        list_for_each_entry(cfg, &pci_mmcfg_list, list)
>>>> +		subtract_range(range, nr, cfg->res.start,
>>>> +			 cfg->res.end + 1);
>>>> +#endif
>>>
>>> This can't be right, can it?  Let's say the kernel was built with
>>> CONFIG_PCI_MMCONFIG turned off, or the user used "pci=nommconf",
>>> or the kernel decides not to use MMCONFIG for some other reason.
>>>
>>> In that case, the hardware may still be configured to support
>>> MMCONFIG, but the pci_mmcfg_list will be empty, so your code will
>>> leave the window alone.  We might assign some of that MMCONFIG
>>> space to a device, but the hardware will route it to MMCONFIG,
>>> not to the device.
>>
>> so if there is mmconf specified, we just skip the whole function?
> 
> No, I'm saying that intel-bus.c must ALWAYS remove the MMCONFIG region
> from the host bridge apertures, even if Linux isn't using MMCONFIG.
> 
> That means intel-bus.c has to be smart enough to figure out on its
> own what the MMCONFIG area is.  It can't depend on mmconfig-shared.c
> to do it, because mmconfig-shared.c might not be there.

that seems go too far away...

Subject: [PATCH -v2] x86/pci: intel ioh need to subtrac mmconf range

Bjorn pointed out we need to remove mmconf range

-v2: if mmconf is not there, get out early.

Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>

---
 arch/x86/pci/Makefile    |    3 ++-
 arch/x86/pci/intel_bus.c |   30 ++++++++++++++++++++++++++++--
 2 files changed, 30 insertions(+), 3 deletions(-)

Index: linux-2.6/arch/x86/pci/intel_bus.c
===================================================================
--- linux-2.6.orig/arch/x86/pci/intel_bus.c
+++ linux-2.6/arch/x86/pci/intel_bus.c
@@ -46,6 +46,18 @@ static inline void print_ioh_resources(s
 
 #define RANGE_NUM 16
 
+static void __devinit subtract_mmconf(struct range *range, int nr)
+{
+	struct pci_mmcfg_region *cfg;
+
+	if (list_empty(&pci_mmcfg_list))
+		return;
+
+        list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		subtract_range(range, nr, cfg->res.start,
+			 cfg->res.end + 1);
+}
+
 static void __devinit pci_root_bus_res(struct pci_dev *dev)
 {
 	u16 word;
@@ -58,6 +70,9 @@ static void __devinit pci_root_bus_res(s
 	struct range range[RANGE_NUM];
 	int i;
 
+	if (list_empty(&pci_mmcfg_list))
+		return;
+
 	/* some sys doesn't get mmconf enabled */
 	if (dev->cfg_size < 0x200)
 		return;
@@ -96,6 +111,7 @@ static void __devinit pci_root_bus_res(s
 
 		subtract_range(range, RANGE_NUM, vt_base, vt_end + 1);
 	}
+	subtract_mmconf(range, RANGE_NUM);
 	for (i = 0; i < RANGE_NUM; i++) {
 		if (!range[i].end)
 			continue;
@@ -112,8 +128,18 @@ static void __devinit pci_root_bus_res(s
 	mmioh_base |= ((u64)(dword & 0x7ffff)) << 32;
 	pci_read_config_dword(dev, IOH_LMMIOH_LIMITU, &dword);
 	mmioh_end |= ((u64)(dword & 0x7ffff)) << 32;
-	update_res(info, cap_resource(mmioh_base), cap_resource(mmioh_end),
-			 IORESOURCE_MEM, 0);
+	memset(range, 0, sizeof(range));
+	add_range(range, RANGE_NUM, 0, mmioh_base, mmioh_end + 1);
+	/* mmconf could be above 4g */
+	subtract_mmconf(range, RANGE_NUM);
+	for (i = 0; i < RANGE_NUM; i++) {
+		if (!range[i].end)
+			continue;
+
+		update_res(info, cap_resource(range[i].start),
+			   cap_resource(range[i].end - 1),
+			   IORESOURCE_MEM, 0);
+	}
 
 	print_ioh_resources(info);
 }
Index: linux-2.6/arch/x86/pci/Makefile
===================================================================
--- linux-2.6.orig/arch/x86/pci/Makefile
+++ linux-2.6/arch/x86/pci/Makefile
@@ -14,7 +14,8 @@ obj-$(CONFIG_X86_VISWS)		+= visws.o
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 
 obj-y				+= common.o early.o
-obj-y				+= amd_bus.o bus_numa.o intel_bus.o
+obj-y				+= amd_bus.o bus_numa.o
+obj-$(CONFIG_PCI_MMCONFIG)	+= intel_bus.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
--
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/