aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_scatterlist.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 /drivers/gpu/drm/i915/i915_scatterlist.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 'drivers/gpu/drm/i915/i915_scatterlist.c')
-rw-r--r--drivers/gpu/drm/i915/i915_scatterlist.c229
1 files changed, 229 insertions, 0 deletions
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
new file mode 100644
index 000000000..114e5e39a
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -0,0 +1,229 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2016 Intel Corporation
+ */
+
+#include "i915_scatterlist.h"
+#include "i915_ttm_buddy_manager.h"
+
+#include <drm/drm_buddy.h>
+#include <drm/drm_mm.h>
+
+#include <linux/slab.h>
+
+bool i915_sg_trim(struct sg_table *orig_st)
+{
+ struct sg_table new_st;
+ struct scatterlist *sg, *new_sg;
+ unsigned int i;
+
+ if (orig_st->nents == orig_st->orig_nents)
+ return false;
+
+ if (sg_alloc_table(&new_st, orig_st->nents, GFP_KERNEL | __GFP_NOWARN))
+ return false;
+
+ new_sg = new_st.sgl;
+ for_each_sg(orig_st->sgl, sg, orig_st->nents, i) {
+ sg_set_page(new_sg, sg_page(sg), sg->length, 0);
+ sg_dma_address(new_sg) = sg_dma_address(sg);
+ sg_dma_len(new_sg) = sg_dma_len(sg);
+
+ new_sg = sg_next(new_sg);
+ }
+ GEM_BUG_ON(new_sg); /* Should walk exactly nents and hit the end */
+
+ sg_free_table(orig_st);
+
+ *orig_st = new_st;
+ return true;
+}
+
+static void i915_refct_sgt_release(struct kref *ref)
+{
+ struct i915_refct_sgt *rsgt =
+ container_of(ref, typeof(*rsgt), kref);
+
+ sg_free_table(&rsgt->table);
+ kfree(rsgt);
+}
+
+static const struct i915_refct_sgt_ops rsgt_ops = {
+ .release = i915_refct_sgt_release
+};
+
+/**
+ * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with default ops
+ * @rsgt: The struct i915_refct_sgt to initialize.
+ * size: The size of the underlying memory buffer.
+ */
+void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
+{
+ __i915_refct_sgt_init(rsgt, size, &rsgt_ops);
+}
+
+/**
+ * i915_rsgt_from_mm_node - Create a refcounted sg_table from a struct
+ * drm_mm_node
+ * @node: The drm_mm_node.
+ * @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
+ *
+ * Create a struct sg_table, initializing it from a struct drm_mm_node,
+ * taking a maximum segment length into account, splitting into segments
+ * if necessary.
+ *
+ * Return: A pointer to a kmalloced struct i915_refct_sgt on success, negative
+ * error code cast to an error pointer on failure.
+ */
+struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
+ u64 region_start,
+ u32 page_alignment)
+{
+ const u32 max_segment = round_down(UINT_MAX, page_alignment);
+ const u32 segment_pages = max_segment >> PAGE_SHIFT;
+ u64 block_size, offset, prev_end;
+ struct i915_refct_sgt *rsgt;
+ struct sg_table *st;
+ struct scatterlist *sg;
+
+ GEM_BUG_ON(!max_segment);
+
+ rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
+ if (!rsgt)
+ return ERR_PTR(-ENOMEM);
+
+ i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
+ st = &rsgt->table;
+ if (sg_alloc_table(st, DIV_ROUND_UP_ULL(node->size, segment_pages),
+ GFP_KERNEL)) {
+ i915_refct_sgt_put(rsgt);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ sg = st->sgl;
+ st->nents = 0;
+ prev_end = (resource_size_t)-1;
+ block_size = node->size << PAGE_SHIFT;
+ offset = node->start << PAGE_SHIFT;
+
+ while (block_size) {
+ u64 len;
+
+ if (offset != prev_end || sg->length >= max_segment) {
+ if (st->nents)
+ sg = __sg_next(sg);
+
+ sg_dma_address(sg) = region_start + offset;
+ GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+ page_alignment));
+ sg_dma_len(sg) = 0;
+ sg->length = 0;
+ st->nents++;
+ }
+
+ len = min_t(u64, block_size, max_segment - sg->length);
+ sg->length += len;
+ sg_dma_len(sg) += len;
+
+ offset += len;
+ block_size -= len;
+
+ prev_end = offset;
+ }
+
+ sg_mark_end(sg);
+ i915_sg_trim(st);
+
+ return rsgt;
+}
+
+/**
+ * i915_rsgt_from_buddy_resource - Create a refcounted sg_table from a struct
+ * i915_buddy_block list
+ * @res: The struct i915_ttm_buddy_resource.
+ * @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
+ *
+ * Create a struct sg_table, initializing it from struct i915_buddy_block list,
+ * taking a maximum segment length into account, splitting into segments
+ * if necessary.
+ *
+ * Return: A pointer to a kmalloced struct i915_refct_sgts on success, negative
+ * error code cast to an error pointer on failure.
+ */
+struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
+ u64 region_start,
+ u32 page_alignment)
+{
+ struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
+ const u64 size = res->size;
+ const u32 max_segment = round_down(UINT_MAX, page_alignment);
+ struct drm_buddy *mm = bman_res->mm;
+ struct list_head *blocks = &bman_res->blocks;
+ struct drm_buddy_block *block;
+ struct i915_refct_sgt *rsgt;
+ struct scatterlist *sg;
+ struct sg_table *st;
+ resource_size_t prev_end;
+
+ GEM_BUG_ON(list_empty(blocks));
+ GEM_BUG_ON(!max_segment);
+
+ rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
+ if (!rsgt)
+ return ERR_PTR(-ENOMEM);
+
+ i915_refct_sgt_init(rsgt, size);
+ st = &rsgt->table;
+ if (sg_alloc_table(st, PFN_UP(res->size), GFP_KERNEL)) {
+ i915_refct_sgt_put(rsgt);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ sg = st->sgl;
+ st->nents = 0;
+ prev_end = (resource_size_t)-1;
+
+ list_for_each_entry(block, blocks, link) {
+ u64 block_size, offset;
+
+ block_size = min_t(u64, size, drm_buddy_block_size(mm, block));
+ offset = drm_buddy_block_offset(block);
+
+ while (block_size) {
+ u64 len;
+
+ if (offset != prev_end || sg->length >= max_segment) {
+ if (st->nents)
+ sg = __sg_next(sg);
+
+ sg_dma_address(sg) = region_start + offset;
+ GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+ page_alignment));
+ sg_dma_len(sg) = 0;
+ sg->length = 0;
+ st->nents++;
+ }
+
+ len = min_t(u64, block_size, max_segment - sg->length);
+ sg->length += len;
+ sg_dma_len(sg) += len;
+
+ offset += len;
+ block_size -= len;
+
+ prev_end = offset;
+ }
+ }
+
+ sg_mark_end(sg);
+ i915_sg_trim(st);
+
+ return rsgt;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/scatterlist.c"
+#endif