Updated ACS override patch

1 files changed, 199 insertions, 0 deletions

diff --git a/0001-Updated-ACS-override-patch-for-4.6.2.patch b/0001-Updated-ACS-override-patch-for-4.6.2.patch
new file mode 100644
index 000000000000..ecead3de3aff
--- /dev/null
+++ b/0001-Updated-ACS-override-patch-for-4.6.2.patch
@@ -0,0 +1,199 @@
+From 9441bfb6810bbbf7c099f23ace0357165a9abd4c Mon Sep 17 00:00:00 2001
+From: Dan Ziemba <zman0900@gmail.com>
+Date: Mon, 13 Jun 2016 18:37:29 -0400
+Subject: [PATCH] Updated ACS override patch for 4.6.2
+
+This an updated version of Alex Williamson's patch from:
+https://lkml.org/lkml/2013/5/30/513
+I don't currently use hardware requiring acs override, so this is
+untested.
+
+Original commit message follows:
+---
+PCIe ACS (Access Control Services) is the PCIe 2.0+ feature that
+allows us to control whether transactions are allowed to be redirected
+in various subnodes of a PCIe topology.  For instance, if two
+endpoints are below a root port or downsteam switch port, the
+downstream port may optionally redirect transactions between the
+devices, bypassing upstream devices.  The same can happen internally
+on multifunction devices.  The transaction may never be visible to the
+upstream devices.
+
+One upstream device that we particularly care about is the IOMMU.  If
+a redirection occurs in the topology below the IOMMU, then the IOMMU
+cannot provide isolation between devices.  This is why the PCIe spec
+encourages topologies to include ACS support.  Without it, we have to
+assume peer-to-peer DMA within a hierarchy can bypass IOMMU isolation.
+
+Unfortunately, far too many topologies do not support ACS to make this
+a steadfast requirement.  Even the latest chipsets from Intel are only
+sporadically supporting ACS.  We have trouble getting interconnect
+vendors to include the PCIe spec required PCIe capability, let alone
+suggested features.
+
+Therefore, we need to add some flexibility.  The pcie_acs_override=
+boot option lets users opt-in specific devices or sets of devices to
+assume ACS support.  The "downstream" option assumes full ACS support
+on root ports and downstream switch ports.  The "multifunction"
+option assumes the subset of ACS features available on multifunction
+endpoints and upstream switch ports are supported.  The "id:nnnn:nnnn"
+option enables ACS support on devices matching the provided vendor
+and device IDs, allowing more strategic ACS overrides.  These options
+may be combined in any order.  A maximum of 16 id specific overrides
+are available.  It's suggested to use the most limited set of options
+necessary to avoid completely disabling ACS across the topology.
+Note to hardware vendors, we have facilities to permanently quirk
+specific devices which enforce isolation but not provide an ACS
+capability.  Please contact me to have your devices added and save
+your customers the hassle of this boot option.
+
+Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
+---
+ Documentation/kernel-parameters.txt |  10 ++++
+ drivers/pci/quirks.c                | 102 ++++++++++++++++++++++++++++++++++++
+ 2 files changed, 112 insertions(+)
+
+diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
+index 0b3de80..3eb47aa 100644
+--- a/Documentation/kernel-parameters.txt
++++ b/Documentation/kernel-parameters.txt
+@@ -3012,6 +3012,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
+ 		nomsi	Do not use MSI for native PCIe PME signaling (this makes
+ 			all PCIe root ports use INTx for all services).
+ 
++	pcie_acs_override =
++			[PCIE] Override missing PCIe ACS support for:
++		downstream
++			All downstream ports - full ACS capabilties
++		multifunction
++			All multifunction devices - multifunction ACS subset
++		id:nnnn:nnnn
++			Specfic device - full ACS capabilities
++			Specified as vid:did (vendor/device ID) in hex
++
+ 	pcmv=		[HW,PCMCIA] BadgePAD 4
+ 
+ 	pd_ignore_unused
+diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
+index 8e67802..db7a808 100644
+--- a/drivers/pci/quirks.c
++++ b/drivers/pci/quirks.c
+@@ -3418,6 +3418,107 @@ static int __init pci_apply_final_quirks(void)
+ 
+ fs_initcall_sync(pci_apply_final_quirks);
+ 
++static bool acs_on_downstream;
++static bool acs_on_multifunction;
++
++#define NUM_ACS_IDS 16
++struct acs_on_id {
++	unsigned short vendor;
++	unsigned short device;
++};
++static struct acs_on_id acs_on_ids[NUM_ACS_IDS];
++static u8 max_acs_id;
++
++static __init int pcie_acs_override_setup(char *p)
++{
++	if (!p)
++		return -EINVAL;
++
++	while (*p) {
++		if (!strncmp(p, "downstream", 10))
++			acs_on_downstream = true;
++		if (!strncmp(p, "multifunction", 13))
++			acs_on_multifunction = true;
++		if (!strncmp(p, "id:", 3)) {
++			char opt[5];
++			int ret;
++			long val;
++
++			if (max_acs_id >= NUM_ACS_IDS - 1) {
++				pr_warn("Out of PCIe ACS override slots (%d)\n",
++					NUM_ACS_IDS);
++				goto next;
++			}
++
++			p += 3;
++			snprintf(opt, 5, "%s", p);
++			ret = kstrtol(opt, 16, &val);
++			if (ret) {
++				pr_warn("PCIe ACS ID parse error %d\n", ret);
++				goto next;
++			}
++			acs_on_ids[max_acs_id].vendor = val;
++
++			p += strcspn(p, ":");
++			if (*p != ':') {
++				pr_warn("PCIe ACS invalid ID\n");
++				goto next;
++			}
++
++			p++;
++			snprintf(opt, 5, "%s", p);
++			ret = kstrtol(opt, 16, &val);
++			if (ret) {
++				pr_warn("PCIe ACS ID parse error %d\n", ret);
++				goto next;
++			}
++			acs_on_ids[max_acs_id].device = val;
++			max_acs_id++;
++		}
++next:
++		p += strcspn(p, ",");
++		if (*p == ',')
++			p++;
++	}
++
++	if (acs_on_downstream || acs_on_multifunction || max_acs_id)
++		pr_warn("Warning: PCIe ACS overrides enabled; This may allow non-IOMMU protected peer-to-peer DMA\n");
++
++	return 0;
++}
++early_param("pcie_acs_override", pcie_acs_override_setup);
++
++static int pcie_acs_overrides(struct pci_dev *dev, u16 acs_flags)
++{
++	int i;
++
++	/* Never override ACS for legacy devices or devices with ACS caps */
++	if (!pci_is_pcie(dev) ||
++	    pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS))
++		return -ENOTTY;
++
++	for (i = 0; i < max_acs_id; i++)
++		if (acs_on_ids[i].vendor == dev->vendor &&
++		    acs_on_ids[i].device == dev->device)
++			return 1;
++
++	switch (pci_pcie_type(dev)) {
++	case PCI_EXP_TYPE_DOWNSTREAM:
++	case PCI_EXP_TYPE_ROOT_PORT:
++		if (acs_on_downstream)
++			return 1;
++		break;
++	case PCI_EXP_TYPE_ENDPOINT:
++	case PCI_EXP_TYPE_UPSTREAM:
++	case PCI_EXP_TYPE_LEG_END:
++	case PCI_EXP_TYPE_RC_END:
++		if (acs_on_multifunction && dev->multifunction)
++			return 1;
++	}
++
++	return -ENOTTY;
++}
++
+ /*
+  * Followings are device-specific reset methods which can be used to
+  * reset a single function if other methods (e.g. FLR, PM D0->D3) are
+@@ -4028,6 +4129,7 @@ static const struct pci_dev_acs_enabled {
+ 	{ 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */
+ 	/* Cavium ThunderX */
+ 	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
++	{ PCI_ANY_ID, PCI_ANY_ID, pcie_acs_overrides },
+ 	{ 0 }
+ };
+ 
+-- 
+2.8.3
+