linux-tkg/linux-tkg/linux-tkg-patches/5.8/0006-add-acs-overrides_iommu.patch
Tony ea29e81042
Merge linux-tkg packages into a single package, add Void Linux and Clang/LLVM support (#63)
* Add Clang/LLVM and Void Linux support

* merge packages, update .gitignore

* Stage 2 of merge

* Stage 3 of merge

* Stage 4 of merge

* Stage 5 of mrege, almost done

* Complete merge of linux-tkg, sync with master (undead PDS 5.8)

* Complete merge of linux-tkg, sync with master (undead PDS 5.8)

* Forgot to add all the patches

* Fix prompt, add config_hardened files

* Fix some stuff for Void

* Merge linux-tkg README, add Void Linux info

* typo

* Fix broken MuQSS on Void at least, Fix CPU opts patch apply

* update to 5.8.8, 5.4.64, block LLVM build with kernel 5.7 because it
seems to segfault at linking vmlinux, fix RC building on Void Linux

* update to 5.8.8, 5.4.64. seems making a confdir variable wasn't
necessary, revert it. sync with master.

* remove variables for messages in favor of defined functions in the Void
template

* resync Linux58-tkg back to master

* Clear patches is the same file for every version

* glitched base is the same file for 5.8 and 5.9, fix wrong version in kernel selection for 5.8, also just use * since it's the same .-.

* merge some patches that are the same together, fix building 5.4 BMQ

* BMQ and PDS ondemand are the same file, fix missing space on kernel version selection

* add Clang makedepends to PKGBUILD, add missing compiler option in customization.cfg, make GCC recommended

* Add kernel selection to install.sh

* Somehow this wasn't edited

* Add optional clang deps to install.sh

* Update gitignore to just ignore linux-5.x instead of commenting it out

* Missing fi

* forgot to sync back install.sh...

* generalize desktop profile configs, uncomment fsync and bcachefs in
customization.cfg, add Project C /PDS and Undead PDS to README, credit
plug, add kernel version selection to customization.cfg, fallback for
compiler selection

* Fix compiler selection error out on Void (for some reason xbps-src always
runs the else statement) also avoid conflict with _compiler, rename it
to _compiler_opt for the actual options in the make command

* oops

* Fix Void extra config not appearing, missing indent for _configfile,
missed PKGBUILD in other commit...

* remove globbing in install.sh

* Move loading of external configuration to the beginning of _tkg_initscript

* Change MuQSS note in README

* 5.4.68, 5.8.12, 5.9-rc7

* Update Project C patchset to v5.8-r3

* 5.8 bcachefs

* LLVM=1 was required to be used on make commands otherwise it would reset
config, we don't need to know if gcc was used to build a kernel (since
llvm is appended to llvm builds), remove the compiler_name if not using
llvm, make kernel versions variables in prepare

* _compileropt does not need to be llvm specific

* add fix for AMD GPU DCN3.0 build with clang in glitched base 5.9
https://lore.kernel.org/amd-gfx/4b5927dd-9f2d-40f9-ef63-007cf7b65f37@amd.com/T/#t

* Revert "add fix for AMD GPU DCN3.0 build with clang in glitched base 5.9"

This reverts commit 276e219f9fe89397332c91e601f34a37b3a0503f.

merged upstream

* Sync with linux-tkg master

* Just stick every patch into it's own kernel version folder

* update 5.4.72, 5.8.16

* check for sum check fail on Void, fix fsync patch

* Update README.md

* README.md formatting

* forgot to move that

* linux59-tkg: Import 5.9 version of the bcachefs patchset - https://gthub.com/koverstreet/bcachefs

Co-authored-by: Lukáš Horáček <flgx@protonmail.com>
2020-10-26 00:43:11 +01:00

194 lines
6.5 KiB
Diff

From cdeab384f48dd9c88e2dff2e9ad8d57dca1a1b1c Mon Sep 17 00:00:00 2001
From: Mark Weiman <mark.weiman@markzz.com>
Date: Sun, 12 Aug 2018 11:36:21 -0400
Subject: [PATCH] pci: Enable overrides for missing ACS capabilities
This an updated version of Alex Williamson's patch from:
https://lkml.org/lkml/2013/5/30/513
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: Mark Weiman <mark.weiman@markzz.com>
---
.../admin-guide/kernel-parameters.txt | 9 ++
drivers/pci/quirks.c | 101 ++++++++++++++++++
2 files changed, 110 insertions(+)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index aefd358a5ca3..173b3596fd9e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3190,6 +3190,15 @@
nomsi [MSI] If the PCI_MSI kernel config parameter is
enabled, this kernel boot option can be used to
disable the use of MSI interrupts system-wide.
+ pcie_acs_override =
+ [PCIE] Override missing PCIe ACS support for:
+ downstream
+ All downstream ports - full ACS capabilities
+ multifunction
+ All multifunction devices - multifunction ACS subset
+ id:nnnn:nnnn
+ Specific device - full ACS capabilities
+ Specified as vid:did (vendor/device ID) in hex
noioapicquirk [APIC] Disable all boot interrupt quirks.
Safety option to keep boot IRQs enabled. This
should never be necessary.
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 4700d24e5d55..8f7a3d7fd9c1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3372,6 +3372,106 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET;
}
+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;
+}
/*
* Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
* The device will throw a Link Down error on AER-capable systems and
@@ -4513,6 +4613,7 @@ static const struct pci_dev_acs_enabled {
{ PCI_VENDOR_ID_ZHAOXIN, 0x9083, pci_quirk_mf_endpoint_acs },
/* Zhaoxin Root/Downstream Ports */
{ PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs },
+ { PCI_ANY_ID, PCI_ANY_ID, pcie_acs_overrides },
{ 0 }
};