aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/selftests/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/selftests/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/selftests/scatterlist.c')
-rw-r--r--drivers/gpu/drm/i915/selftests/scatterlist.c380
1 files changed, 380 insertions, 0 deletions
diff --git a/drivers/gpu/drm/i915/selftests/scatterlist.c b/drivers/gpu/drm/i915/selftests/scatterlist.c
new file mode 100644
index 000000000..d599186d5
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/scatterlist.c
@@ -0,0 +1,380 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/prime_numbers.h>
+#include <linux/random.h>
+
+#include "i915_selftest.h"
+#include "i915_utils.h"
+
+#define PFN_BIAS (1 << 10)
+
+struct pfn_table {
+ struct sg_table st;
+ unsigned long start, end;
+};
+
+typedef unsigned int (*npages_fn_t)(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd);
+
+static noinline int expect_pfn_sg(struct pfn_table *pt,
+ npages_fn_t npages_fn,
+ struct rnd_state *rnd,
+ const char *who,
+ unsigned long timeout)
+{
+ struct scatterlist *sg;
+ unsigned long pfn, n;
+
+ pfn = pt->start;
+ for_each_sg(pt->st.sgl, sg, pt->st.nents, n) {
+ struct page *page = sg_page(sg);
+ unsigned int npages = npages_fn(n, pt->st.nents, rnd);
+
+ if (page_to_pfn(page) != pfn) {
+ pr_err("%s: %s left pages out of order, expected pfn %lu, found pfn %lu (using for_each_sg)\n",
+ __func__, who, pfn, page_to_pfn(page));
+ return -EINVAL;
+ }
+
+ if (sg->length != npages * PAGE_SIZE) {
+ pr_err("%s: %s copied wrong sg length, expected size %lu, found %u (using for_each_sg)\n",
+ __func__, who, npages * PAGE_SIZE, sg->length);
+ return -EINVAL;
+ }
+
+ if (igt_timeout(timeout, "%s timed out\n", who))
+ return -EINTR;
+
+ pfn += npages;
+ }
+ if (pfn != pt->end) {
+ pr_err("%s: %s finished on wrong pfn, expected %lu, found %lu\n",
+ __func__, who, pt->end, pfn);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static noinline int expect_pfn_sg_page_iter(struct pfn_table *pt,
+ const char *who,
+ unsigned long timeout)
+{
+ struct sg_page_iter sgiter;
+ unsigned long pfn;
+
+ pfn = pt->start;
+ for_each_sg_page(pt->st.sgl, &sgiter, pt->st.nents, 0) {
+ struct page *page = sg_page_iter_page(&sgiter);
+
+ if (page != pfn_to_page(pfn)) {
+ pr_err("%s: %s left pages out of order, expected pfn %lu, found pfn %lu (using for_each_sg_page)\n",
+ __func__, who, pfn, page_to_pfn(page));
+ return -EINVAL;
+ }
+
+ if (igt_timeout(timeout, "%s timed out\n", who))
+ return -EINTR;
+
+ pfn++;
+ }
+ if (pfn != pt->end) {
+ pr_err("%s: %s finished on wrong pfn, expected %lu, found %lu\n",
+ __func__, who, pt->end, pfn);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static noinline int expect_pfn_sgtiter(struct pfn_table *pt,
+ const char *who,
+ unsigned long timeout)
+{
+ struct sgt_iter sgt;
+ struct page *page;
+ unsigned long pfn;
+
+ pfn = pt->start;
+ for_each_sgt_page(page, sgt, &pt->st) {
+ if (page != pfn_to_page(pfn)) {
+ pr_err("%s: %s left pages out of order, expected pfn %lu, found pfn %lu (using for_each_sgt_page)\n",
+ __func__, who, pfn, page_to_pfn(page));
+ return -EINVAL;
+ }
+
+ if (igt_timeout(timeout, "%s timed out\n", who))
+ return -EINTR;
+
+ pfn++;
+ }
+ if (pfn != pt->end) {
+ pr_err("%s: %s finished on wrong pfn, expected %lu, found %lu\n",
+ __func__, who, pt->end, pfn);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int expect_pfn_sgtable(struct pfn_table *pt,
+ npages_fn_t npages_fn,
+ struct rnd_state *rnd,
+ const char *who,
+ unsigned long timeout)
+{
+ int err;
+
+ err = expect_pfn_sg(pt, npages_fn, rnd, who, timeout);
+ if (err)
+ return err;
+
+ err = expect_pfn_sg_page_iter(pt, who, timeout);
+ if (err)
+ return err;
+
+ err = expect_pfn_sgtiter(pt, who, timeout);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static unsigned int one(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd)
+{
+ return 1;
+}
+
+static unsigned int grow(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd)
+{
+ return n + 1;
+}
+
+static unsigned int shrink(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd)
+{
+ return count - n;
+}
+
+static unsigned int random(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd)
+{
+ return 1 + (prandom_u32_state(rnd) % 1024);
+}
+
+static unsigned int random_page_size_pages(unsigned long n,
+ unsigned long count,
+ struct rnd_state *rnd)
+{
+ /* 4K, 64K, 2M */
+ static unsigned int page_count[] = {
+ BIT(12) >> PAGE_SHIFT,
+ BIT(16) >> PAGE_SHIFT,
+ BIT(21) >> PAGE_SHIFT,
+ };
+
+ return page_count[(prandom_u32_state(rnd) % 3)];
+}
+
+static inline bool page_contiguous(struct page *first,
+ struct page *last,
+ unsigned long npages)
+{
+ return first + npages == last;
+}
+
+static int alloc_table(struct pfn_table *pt,
+ unsigned long count, unsigned long max,
+ npages_fn_t npages_fn,
+ struct rnd_state *rnd,
+ int alloc_error)
+{
+ struct scatterlist *sg;
+ unsigned long n, pfn;
+
+ if (sg_alloc_table(&pt->st, max,
+ GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN))
+ return alloc_error;
+
+ /* count should be less than 20 to prevent overflowing sg->length */
+ GEM_BUG_ON(overflows_type(count * PAGE_SIZE, sg->length));
+
+ /* Construct a table where each scatterlist contains different number
+ * of entries. The idea is to check that we can iterate the individual
+ * pages from inside the coalesced lists.
+ */
+ pt->start = PFN_BIAS;
+ pfn = pt->start;
+ sg = pt->st.sgl;
+ for (n = 0; n < count; n++) {
+ unsigned long npages = npages_fn(n, count, rnd);
+
+ /* Nobody expects the Sparse Memmap! */
+ if (!page_contiguous(pfn_to_page(pfn),
+ pfn_to_page(pfn + npages),
+ npages)) {
+ sg_free_table(&pt->st);
+ return -ENOSPC;
+ }
+
+ if (n)
+ sg = sg_next(sg);
+ sg_set_page(sg, pfn_to_page(pfn), npages * PAGE_SIZE, 0);
+
+ GEM_BUG_ON(page_to_pfn(sg_page(sg)) != pfn);
+ GEM_BUG_ON(sg->length != npages * PAGE_SIZE);
+ GEM_BUG_ON(sg->offset != 0);
+
+ pfn += npages;
+ }
+ sg_mark_end(sg);
+ pt->st.nents = n;
+ pt->end = pfn;
+
+ return 0;
+}
+
+static const npages_fn_t npages_funcs[] = {
+ one,
+ grow,
+ shrink,
+ random,
+ random_page_size_pages,
+ NULL,
+};
+
+static int igt_sg_alloc(void *ignored)
+{
+ IGT_TIMEOUT(end_time);
+ const unsigned long max_order = 20; /* approximating a 4GiB object */
+ struct rnd_state prng;
+ unsigned long prime;
+ int alloc_error = -ENOMEM;
+
+ for_each_prime_number(prime, max_order) {
+ unsigned long size = BIT(prime);
+ int offset;
+
+ for (offset = -1; offset <= 1; offset++) {
+ unsigned long sz = size + offset;
+ const npages_fn_t *npages;
+ struct pfn_table pt;
+ int err;
+
+ for (npages = npages_funcs; *npages; npages++) {
+ prandom_seed_state(&prng,
+ i915_selftest.random_seed);
+ err = alloc_table(&pt, sz, sz, *npages, &prng,
+ alloc_error);
+ if (err == -ENOSPC)
+ break;
+ if (err)
+ return err;
+
+ prandom_seed_state(&prng,
+ i915_selftest.random_seed);
+ err = expect_pfn_sgtable(&pt, *npages, &prng,
+ "sg_alloc_table",
+ end_time);
+ sg_free_table(&pt.st);
+ if (err)
+ return err;
+ }
+ }
+
+ /* Test at least one continuation before accepting oom */
+ if (size > SG_MAX_SINGLE_ALLOC)
+ alloc_error = -ENOSPC;
+ }
+
+ return 0;
+}
+
+static int igt_sg_trim(void *ignored)
+{
+ IGT_TIMEOUT(end_time);
+ const unsigned long max = PAGE_SIZE; /* not prime! */
+ struct pfn_table pt;
+ unsigned long prime;
+ int alloc_error = -ENOMEM;
+
+ for_each_prime_number(prime, max) {
+ const npages_fn_t *npages;
+ int err;
+
+ for (npages = npages_funcs; *npages; npages++) {
+ struct rnd_state prng;
+
+ prandom_seed_state(&prng, i915_selftest.random_seed);
+ err = alloc_table(&pt, prime, max, *npages, &prng,
+ alloc_error);
+ if (err == -ENOSPC)
+ break;
+ if (err)
+ return err;
+
+ if (i915_sg_trim(&pt.st)) {
+ if (pt.st.orig_nents != prime ||
+ pt.st.nents != prime) {
+ pr_err("i915_sg_trim failed (nents %u, orig_nents %u), expected %lu\n",
+ pt.st.nents, pt.st.orig_nents, prime);
+ err = -EINVAL;
+ } else {
+ prandom_seed_state(&prng,
+ i915_selftest.random_seed);
+ err = expect_pfn_sgtable(&pt,
+ *npages, &prng,
+ "i915_sg_trim",
+ end_time);
+ }
+ }
+ sg_free_table(&pt.st);
+ if (err)
+ return err;
+ }
+
+ /* Test at least one continuation before accepting oom */
+ if (prime > SG_MAX_SINGLE_ALLOC)
+ alloc_error = -ENOSPC;
+ }
+
+ return 0;
+}
+
+int scatterlist_mock_selftests(void)
+{
+ static const struct i915_subtest tests[] = {
+ SUBTEST(igt_sg_alloc),
+ SUBTEST(igt_sg_trim),
+ };
+
+ return i915_subtests(tests, NULL);
+}