Skip to contentSkip to conversation

PCI fixes

GIT PULL Jesse Barnes 2 participants 2 messages Jun 14, 2008

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

Please pull the final (I hope!) fixes for 2.6.26:
git pull git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6.git for-linus

It's mainly a set of fixes I got from Ingo which have been soaking for awhile, including the resourceN_wc API, which should have been pushed upstream before now, but which has seen a lot of exposure in Ingo's tree. Shortlog, diffstat & diff below.

Note that to take advantage of the new resourceN_wc file in X you'll need something like the patch I just posted to [email protected].

Also, since I pulled the changes from Ingo, there are two duplicates (Bertram & Tony's patches) and a merge commit; hopefully they won't cause trouble.

Thanks,
Jesse

Bertram Felgenhauer (1):
pci, x86: add workaround for bug in ASUS A7V600 BIOS (rev 1005)

Jesse Barnes (2):
Merge branch 'pci-for-jesse' of git://git.kernel.org/.../x86/linux-2.6-tip into for-linus
PCI: fixup write combine comment in pci_mmap_resource

Miquel van Smoorenburg (2):
x86: pci-dma.c: use __GFP_NO_OOM instead of __GFP_NORETRY x86, pci-dma.c: don't always add __GFP_NORETRY to gfp

Pavel Machek (1):
suspend-vs-iommu: prevent suspend if we could not resume

Tony Camuso (1):
PCI: Correct last two HP entries in the bfsort whitelist

Yinghai Lu (1):
PCI: use dev_to_node in pci_call_probe

[email protected] (1):
x86: PAT export resource_wc in pci sysfs

 Documentation/filesystems/sysfs-pci.txt |    1 
 arch/x86/kernel/pci-dma.c               |   14 +++--
 arch/x86/pci/common.c                   |    8 +--
 drivers/pci/pci-driver.c                |    2 
 drivers/pci/pci-sysfs.c                 |   85 +++++++++++++++++++++++---------
 include/linux/pci.h                     |    1 
 6 files changed, 79 insertions(+), 32 deletions(-)
Documentation/filesystems/sysfs-pci.txt +1 -0
index 5daa2aa..68ef488 100644
@@ -36,6 +36,7 @@ files, each with their own function.
        local_cpus	   nearby CPU mask (cpumask, ro)
        resource		   PCI resource host addresses (ascii, ro)
        resource0..N	   PCI resource N, if present (binary, mmap)
+       resource0_wc..N_wc  PCI WC map resource N, if prefetchable (binary, mmap)
        rom		   PCI ROM resource, if present (binary, ro)
        subsystem_device	   PCI subsystem device (ascii, ro)
        subsystem_vendor	   PCI subsystem vendor (ascii, ro)
arch/x86/kernel/pci-dma.c +10 -4
index c5ef1af..dc00a13 100644
@@ -378,6 +378,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	struct page *page;
 	unsigned long dma_mask = 0;
 	dma_addr_t bus;
+	int noretry = 0;
 
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -397,20 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dev->dma_mask == NULL)
 		return NULL;
 
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
+	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+	if (gfp & __GFP_DMA)
+		noretry = 1;
 
 #ifdef CONFIG_X86_64
 	/* Why <=? Even when the mask is smaller than 4GB it is often
 	   larger than 16MB and in this case we have a chance of
 	   finding fitting memory in the next higher zone first. If
 	   not retry with true GFP_DMA. -AK */
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
 		gfp |= GFP_DMA32;
+		if (dma_mask < DMA_32BIT_MASK)
+			noretry = 1;
+	}
 #endif
 
  again:
-	page = dma_alloc_pages(dev, gfp, get_order(size));
+	page = dma_alloc_pages(dev,
+		noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
 	if (page == NULL)
 		return NULL;
 
arch/x86/pci/common.c +4 -4
index 6e64aaf..940185e 100644
@@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 #endif
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 	{}
drivers/pci/pci-driver.c +1 -1
index 72cf61e..e1637bd 100644
@@ -181,7 +181,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	   any need to change it. */
 	struct mempolicy *oldpol;
 	cpumask_t oldmask = current->cpus_allowed;
-	int node = pcibus_to_node(dev->bus);
+	int node = dev_to_node(&dev->dev);
 
 	if (node >= 0) {
 		node_to_cpumask_ptr(nodecpumask, node);
drivers/pci/pci-sysfs.c +62 -23

122 lines not on this page · raw message

include/linux/pci.h +1 -0
index 509159b..d18b1dd 100644
@@ -206,6 +206,7 @@ struct pci_dev {
 	struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */
 	int rom_attr_enabled;		/* has display of the rom attribute been enabled? */
 	struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */
+	struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */
 #ifdef CONFIG_PCI_MSI
 	struct list_head msi_list;
 #endif
#1 lore raw
Quoted 24 lines · Jesse Barnes

Please pull the final (I hope!) fixes for 2.6.26:
git pull git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6.git for-linus

It's mainly a set of fixes I got from Ingo which have been soaking for awhile, including the resourceN_wc API, which should have been pushed upstream before now, but which has seen a lot of exposure in Ingo's tree. Shortlog, diffstat & diff below.

Note that to take advantage of the new resourceN_wc file in X you'll need something like the patch I just posted to [email protected].

Also, since I pulled the changes from Ingo, there are two duplicates (Bertram & Tony's patches) and a merge commit; hopefully they won't cause trouble.

Thanks,
Jesse

Bertram Felgenhauer (1):
pci, x86: add workaround for bug in ASUS A7V600 BIOS (rev 1005)

Jesse Barnes (2):
Merge branch 'pci-for-jesse' of git://git.kernel.org/.../x86/linux-2.6-tip into for-linus
PCI: fixup write combine comment in pci_mmap_resource

Quoted 6 lines

Miquel van Smoorenburg (2):
x86: pci-dma.c: use __GFP_NO_OOM instead of __GFP_NORETRY x86, pci-dma.c: don't always add __GFP_NORETRY to gfp

Pavel Machek (1):
suspend-vs-iommu: prevent suspend if we could not resume

This has been merged already AFAICS, commit
cd76374e9de4501acc74f833dc6cb5e7a5dca115 .

Thanks,
Rafael