aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/sysdev/dart_iommu.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /arch/powerpc/sysdev/dart_iommu.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to '')
-rw-r--r--arch/powerpc/sysdev/dart_iommu.c444
1 files changed, 444 insertions, 0 deletions
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
new file mode 100644
index 000000000..98096bbfd
--- /dev/null
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -0,0 +1,444 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * arch/powerpc/sysdev/dart_iommu.c
+ *
+ * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
+ * Copyright (C) 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>,
+ * IBM Corporation
+ *
+ * Based on pSeries_iommu.c:
+ * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
+ * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
+ *
+ * Dynamic DMA mapping support, Apple U3, U4 & IBM CPC925 "DART" iommu.
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/suspend.h>
+#include <linux/memblock.h>
+#include <linux/gfp.h>
+#include <linux/kmemleak.h>
+#include <linux/of_address.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/cacheflush.h>
+#include <asm/ppc-pci.h>
+
+#include "dart.h"
+
+/* DART table address and size */
+static u32 *dart_tablebase;
+static unsigned long dart_tablesize;
+
+/* Mapped base address for the dart */
+static unsigned int __iomem *dart;
+
+/* Dummy val that entries are set to when unused */
+static unsigned int dart_emptyval;
+
+static struct iommu_table iommu_table_dart;
+static int iommu_table_dart_inited;
+static int dart_dirty;
+static int dart_is_u4;
+
+#define DART_U4_BYPASS_BASE 0x8000000000ull
+
+#define DBG(...)
+
+static DEFINE_SPINLOCK(invalidate_lock);
+
+static inline void dart_tlb_invalidate_all(void)
+{
+ unsigned long l = 0;
+ unsigned int reg, inv_bit;
+ unsigned long limit;
+ unsigned long flags;
+
+ spin_lock_irqsave(&invalidate_lock, flags);
+
+ DBG("dart: flush\n");
+
+ /* To invalidate the DART, set the DARTCNTL_FLUSHTLB bit in the
+ * control register and wait for it to clear.
+ *
+ * Gotcha: Sometimes, the DART won't detect that the bit gets
+ * set. If so, clear it and set it again.
+ */
+
+ limit = 0;
+
+ inv_bit = dart_is_u4 ? DART_CNTL_U4_FLUSHTLB : DART_CNTL_U3_FLUSHTLB;
+retry:
+ l = 0;
+ reg = DART_IN(DART_CNTL);
+ reg |= inv_bit;
+ DART_OUT(DART_CNTL, reg);
+
+ while ((DART_IN(DART_CNTL) & inv_bit) && l < (1L << limit))
+ l++;
+ if (l == (1L << limit)) {
+ if (limit < 4) {
+ limit++;
+ reg = DART_IN(DART_CNTL);
+ reg &= ~inv_bit;
+ DART_OUT(DART_CNTL, reg);
+ goto retry;
+ } else
+ panic("DART: TLB did not flush after waiting a long "
+ "time. Buggy U3 ?");
+ }
+
+ spin_unlock_irqrestore(&invalidate_lock, flags);
+}
+
+static inline void dart_tlb_invalidate_one(unsigned long bus_rpn)
+{
+ unsigned int reg;
+ unsigned int l, limit;
+ unsigned long flags;
+
+ spin_lock_irqsave(&invalidate_lock, flags);
+
+ reg = DART_CNTL_U4_ENABLE | DART_CNTL_U4_IONE |
+ (bus_rpn & DART_CNTL_U4_IONE_MASK);
+ DART_OUT(DART_CNTL, reg);
+
+ limit = 0;
+wait_more:
+ l = 0;
+ while ((DART_IN(DART_CNTL) & DART_CNTL_U4_IONE) && l < (1L << limit)) {
+ rmb();
+ l++;
+ }
+
+ if (l == (1L << limit)) {
+ if (limit < 4) {
+ limit++;
+ goto wait_more;
+ } else
+ panic("DART: TLB did not flush after waiting a long "
+ "time. Buggy U4 ?");
+ }
+
+ spin_unlock_irqrestore(&invalidate_lock, flags);
+}
+
+static void dart_cache_sync(unsigned int *base, unsigned int count)
+{
+ /*
+ * We add 1 to the number of entries to flush, following a
+ * comment in Darwin indicating that the memory controller
+ * can prefetch unmapped memory under some circumstances.
+ */
+ unsigned long start = (unsigned long)base;
+ unsigned long end = start + (count + 1) * sizeof(unsigned int);
+ unsigned int tmp;
+
+ /* Perform a standard cache flush */
+ flush_dcache_range(start, end);
+
+ /*
+ * Perform the sequence described in the CPC925 manual to
+ * ensure all the data gets to a point the cache incoherent
+ * DART hardware will see.
+ */
+ asm volatile(" sync;"
+ " isync;"
+ " dcbf 0,%1;"
+ " sync;"
+ " isync;"
+ " lwz %0,0(%1);"
+ " isync" : "=r" (tmp) : "r" (end) : "memory");
+}
+
+static void dart_flush(struct iommu_table *tbl)
+{
+ mb();
+ if (dart_dirty) {
+ dart_tlb_invalidate_all();
+ dart_dirty = 0;
+ }
+}
+
+static int dart_build(struct iommu_table *tbl, long index,
+ long npages, unsigned long uaddr,
+ enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ unsigned int *dp, *orig_dp;
+ unsigned int rpn;
+ long l;
+
+ DBG("dart: build at: %lx, %lx, addr: %x\n", index, npages, uaddr);
+
+ orig_dp = dp = ((unsigned int*)tbl->it_base) + index;
+
+ /* On U3, all memory is contiguous, so we can move this
+ * out of the loop.
+ */
+ l = npages;
+ while (l--) {
+ rpn = __pa(uaddr) >> DART_PAGE_SHIFT;
+
+ *(dp++) = DARTMAP_VALID | (rpn & DARTMAP_RPNMASK);
+
+ uaddr += DART_PAGE_SIZE;
+ }
+ dart_cache_sync(orig_dp, npages);
+
+ if (dart_is_u4) {
+ rpn = index;
+ while (npages--)
+ dart_tlb_invalidate_one(rpn++);
+ } else {
+ dart_dirty = 1;
+ }
+ return 0;
+}
+
+
+static void dart_free(struct iommu_table *tbl, long index, long npages)
+{
+ unsigned int *dp, *orig_dp;
+ long orig_npages = npages;
+
+ /* We don't worry about flushing the TLB cache. The only drawback of
+ * not doing it is that we won't catch buggy device drivers doing
+ * bad DMAs, but then no 32-bit architecture ever does either.
+ */
+
+ DBG("dart: free at: %lx, %lx\n", index, npages);
+
+ orig_dp = dp = ((unsigned int *)tbl->it_base) + index;
+
+ while (npages--)
+ *(dp++) = dart_emptyval;
+
+ dart_cache_sync(orig_dp, orig_npages);
+}
+
+static void __init allocate_dart(void)
+{
+ unsigned long tmp;
+
+ /* 512 pages (2MB) is max DART tablesize. */
+ dart_tablesize = 1UL << 21;
+
+ /*
+ * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
+ * will blow up an entire large page anyway in the kernel mapping.
+ */
+ dart_tablebase = memblock_alloc_try_nid_raw(SZ_16M, SZ_16M,
+ MEMBLOCK_LOW_LIMIT, SZ_2G,
+ NUMA_NO_NODE);
+ if (!dart_tablebase)
+ panic("Failed to allocate 16MB below 2GB for DART table\n");
+
+ /* There is no point scanning the DART space for leaks*/
+ kmemleak_no_scan((void *)dart_tablebase);
+
+ /* Allocate a spare page to map all invalid DART pages. We need to do
+ * that to work around what looks like a problem with the HT bridge
+ * prefetching into invalid pages and corrupting data
+ */
+ tmp = memblock_phys_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE);
+ if (!tmp)
+ panic("DART: table allocation failed\n");
+
+ dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) &
+ DARTMAP_RPNMASK);
+
+ printk(KERN_INFO "DART table allocated at: %p\n", dart_tablebase);
+}
+
+static int __init dart_init(struct device_node *dart_node)
+{
+ unsigned int i;
+ unsigned long base, size;
+ struct resource r;
+
+ /* IOMMU disabled by the user ? bail out */
+ if (iommu_is_off)
+ return -ENODEV;
+
+ /*
+ * Only use the DART if the machine has more than 1GB of RAM
+ * or if requested with iommu=on on cmdline.
+ *
+ * 1GB of RAM is picked as limit because some default devices
+ * (i.e. Airport Extreme) have 30 bit address range limits.
+ */
+
+ if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull)
+ return -ENODEV;
+
+ /* Get DART registers */
+ if (of_address_to_resource(dart_node, 0, &r))
+ panic("DART: can't get register base ! ");
+
+ /* Map in DART registers */
+ dart = ioremap(r.start, resource_size(&r));
+ if (dart == NULL)
+ panic("DART: Cannot map registers!");
+
+ /* Allocate the DART and dummy page */
+ allocate_dart();
+
+ /* Fill initial table */
+ for (i = 0; i < dart_tablesize/4; i++)
+ dart_tablebase[i] = dart_emptyval;
+
+ /* Push to memory */
+ dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
+
+ /* Initialize DART with table base and enable it. */
+ base = ((unsigned long)dart_tablebase) >> DART_PAGE_SHIFT;
+ size = dart_tablesize >> DART_PAGE_SHIFT;
+ if (dart_is_u4) {
+ size &= DART_SIZE_U4_SIZE_MASK;
+ DART_OUT(DART_BASE_U4, base);
+ DART_OUT(DART_SIZE_U4, size);
+ DART_OUT(DART_CNTL, DART_CNTL_U4_ENABLE);
+ } else {
+ size &= DART_CNTL_U3_SIZE_MASK;
+ DART_OUT(DART_CNTL,
+ DART_CNTL_U3_ENABLE |
+ (base << DART_CNTL_U3_BASE_SHIFT) |
+ (size << DART_CNTL_U3_SIZE_SHIFT));
+ }
+
+ /* Invalidate DART to get rid of possible stale TLBs */
+ dart_tlb_invalidate_all();
+
+ printk(KERN_INFO "DART IOMMU initialized for %s type chipset\n",
+ dart_is_u4 ? "U4" : "U3");
+
+ return 0;
+}
+
+static struct iommu_table_ops iommu_dart_ops = {
+ .set = dart_build,
+ .clear = dart_free,
+ .flush = dart_flush,
+};
+
+static void iommu_table_dart_setup(void)
+{
+ iommu_table_dart.it_busno = 0;
+ iommu_table_dart.it_offset = 0;
+ /* it_size is in number of entries */
+ iommu_table_dart.it_size = dart_tablesize / sizeof(u32);
+ iommu_table_dart.it_page_shift = IOMMU_PAGE_SHIFT_4K;
+
+ /* Initialize the common IOMMU code */
+ iommu_table_dart.it_base = (unsigned long)dart_tablebase;
+ iommu_table_dart.it_index = 0;
+ iommu_table_dart.it_blocksize = 1;
+ iommu_table_dart.it_ops = &iommu_dart_ops;
+ if (!iommu_init_table(&iommu_table_dart, -1, 0, 0))
+ panic("Failed to initialize iommu table");
+
+ /* Reserve the last page of the DART to avoid possible prefetch
+ * past the DART mapped area
+ */
+ set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
+}
+
+static void pci_dma_bus_setup_dart(struct pci_bus *bus)
+{
+ if (!iommu_table_dart_inited) {
+ iommu_table_dart_inited = 1;
+ iommu_table_dart_setup();
+ }
+}
+
+static bool dart_device_on_pcie(struct device *dev)
+{
+ struct device_node *np = of_node_get(dev->of_node);
+
+ while(np) {
+ if (of_device_is_compatible(np, "U4-pcie") ||
+ of_device_is_compatible(np, "u4-pcie")) {
+ of_node_put(np);
+ return true;
+ }
+ np = of_get_next_parent(np);
+ }
+ return false;
+}
+
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
+{
+ if (dart_is_u4 && dart_device_on_pcie(&dev->dev))
+ dev->dev.archdata.dma_offset = DART_U4_BYPASS_BASE;
+ set_iommu_table_base(&dev->dev, &iommu_table_dart);
+}
+
+static bool iommu_bypass_supported_dart(struct pci_dev *dev, u64 mask)
+{
+ return dart_is_u4 &&
+ dart_device_on_pcie(&dev->dev) &&
+ mask >= DMA_BIT_MASK(40);
+}
+
+void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
+{
+ struct device_node *dn;
+
+ /* Find the DART in the device-tree */
+ dn = of_find_compatible_node(NULL, "dart", "u3-dart");
+ if (dn == NULL) {
+ dn = of_find_compatible_node(NULL, "dart", "u4-dart");
+ if (dn == NULL)
+ return; /* use default direct_dma_ops */
+ dart_is_u4 = 1;
+ }
+
+ /* Initialize the DART HW */
+ if (dart_init(dn) != 0) {
+ of_node_put(dn);
+ return;
+ }
+ /*
+ * U4 supports a DART bypass, we use it for 64-bit capable devices to
+ * improve performance. However, that only works for devices connected
+ * to the U4 own PCIe interface, not bridged through hypertransport.
+ * We need the device to support at least 40 bits of addresses.
+ */
+ controller_ops->dma_dev_setup = pci_dma_dev_setup_dart;
+ controller_ops->dma_bus_setup = pci_dma_bus_setup_dart;
+ controller_ops->iommu_bypass_supported = iommu_bypass_supported_dart;
+
+ /* Setup pci_dma ops */
+ set_pci_dma_ops(&dma_iommu_ops);
+ of_node_put(dn);
+}
+
+#ifdef CONFIG_PM
+static void iommu_dart_restore(void)
+{
+ dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
+ dart_tlb_invalidate_all();
+}
+
+static int __init iommu_init_late_dart(void)
+{
+ if (!dart_tablebase)
+ return 0;
+
+ ppc_md.iommu_restore = iommu_dart_restore;
+
+ return 0;
+}
+
+late_initcall(iommu_init_late_dart);
+#endif /* CONFIG_PM */