From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c | 359 ++++++++++++++++++++++++++++++++ 1 file changed, 359 insertions(+) create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c new file mode 100644 index 000000000..0bb2466d5 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c @@ -0,0 +1,359 @@ +/* + * Copyright 2014 Advanced Micro Devices, Inc. + * + * 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 +#include "amdgpu.h" +#include "atom.h" +#include "atombios_encoders.h" +#include "amdgpu_pll.h" +#include +#include + +/** + * amdgpu_pll_reduce_ratio - fractional number reduction + * + * @nom: nominator + * @den: denominator + * @nom_min: minimum value for nominator + * @den_min: minimum value for denominator + * + * Find the greatest common divisor and apply it on both nominator and + * denominator, but make nominator and denominator are at least as large + * as their minimum values. + */ +static void amdgpu_pll_reduce_ratio(unsigned *nom, unsigned *den, + unsigned nom_min, unsigned den_min) +{ + unsigned tmp; + + /* reduce the numbers to a simpler ratio */ + tmp = gcd(*nom, *den); + *nom /= tmp; + *den /= tmp; + + /* make sure nominator is large enough */ + if (*nom < nom_min) { + tmp = DIV_ROUND_UP(nom_min, *nom); + *nom *= tmp; + *den *= tmp; + } + + /* make sure the denominator is large enough */ + if (*den < den_min) { + tmp = DIV_ROUND_UP(den_min, *den); + *nom *= tmp; + *den *= tmp; + } +} + +/** + * amdgpu_pll_get_fb_ref_div - feedback and ref divider calculation + * + * @adev: amdgpu_device pointer + * @nom: nominator + * @den: denominator + * @post_div: post divider + * @fb_div_max: feedback divider maximum + * @ref_div_max: reference divider maximum + * @fb_div: resulting feedback divider + * @ref_div: resulting reference divider + * + * Calculate feedback and reference divider for a given post divider. Makes + * sure we stay within the limits. + */ +static void amdgpu_pll_get_fb_ref_div(struct amdgpu_device *adev, unsigned int nom, + unsigned int den, unsigned int post_div, + unsigned int fb_div_max, unsigned int ref_div_max, + unsigned int *fb_div, unsigned int *ref_div) +{ + + /* limit reference * post divider to a maximum */ + if (adev->family == AMDGPU_FAMILY_SI) + ref_div_max = min(100 / post_div, ref_div_max); + else + ref_div_max = min(128 / post_div, ref_div_max); + + /* get matching reference and feedback divider */ + *ref_div = min(max(DIV_ROUND_CLOSEST(den, post_div), 1u), ref_div_max); + *fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den); + + /* limit fb divider to its maximum */ + if (*fb_div > fb_div_max) { + *ref_div = DIV_ROUND_CLOSEST(*ref_div * fb_div_max, *fb_div); + *fb_div = fb_div_max; + } +} + +/** + * amdgpu_pll_compute - compute PLL paramaters + * + * @adev: amdgpu_device pointer + * @pll: information about the PLL + * @freq: requested frequency + * @dot_clock_p: resulting pixel clock + * @fb_div_p: resulting feedback divider + * @frac_fb_div_p: fractional part of the feedback divider + * @ref_div_p: resulting reference divider + * @post_div_p: resulting reference divider + * + * Try to calculate the PLL parameters to generate the given frequency: + * dot_clock = (ref_freq * feedback_div) / (ref_div * post_div) + */ +void amdgpu_pll_compute(struct amdgpu_device *adev, + struct amdgpu_pll *pll, + u32 freq, + u32 *dot_clock_p, + u32 *fb_div_p, + u32 *frac_fb_div_p, + u32 *ref_div_p, + u32 *post_div_p) +{ + unsigned target_clock = pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV ? + freq : freq / 10; + + unsigned fb_div_min, fb_div_max, fb_div; + unsigned post_div_min, post_div_max, post_div; + unsigned ref_div_min, ref_div_max, ref_div; + unsigned post_div_best, diff_best; + unsigned nom, den; + + /* determine allowed feedback divider range */ + fb_div_min = pll->min_feedback_div; + fb_div_max = pll->max_feedback_div; + + if (pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV) { + fb_div_min *= 10; + fb_div_max *= 10; + } + + /* determine allowed ref divider range */ + if (pll->flags & AMDGPU_PLL_USE_REF_DIV) + ref_div_min = pll->reference_div; + else + ref_div_min = pll->min_ref_div; + + if (pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV && + pll->flags & AMDGPU_PLL_USE_REF_DIV) + ref_div_max = pll->reference_div; + else + ref_div_max = pll->max_ref_div; + + /* determine allowed post divider range */ + if (pll->flags & AMDGPU_PLL_USE_POST_DIV) { + post_div_min = pll->post_div; + post_div_max = pll->post_div; + } else { + unsigned vco_min, vco_max; + + if (pll->flags & AMDGPU_PLL_IS_LCD) { + vco_min = pll->lcd_pll_out_min; + vco_max = pll->lcd_pll_out_max; + } else { + vco_min = pll->pll_out_min; + vco_max = pll->pll_out_max; + } + + if (pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV) { + vco_min *= 10; + vco_max *= 10; + } + + post_div_min = vco_min / target_clock; + if ((target_clock * post_div_min) < vco_min) + ++post_div_min; + if (post_div_min < pll->min_post_div) + post_div_min = pll->min_post_div; + + post_div_max = vco_max / target_clock; + if ((target_clock * post_div_max) > vco_max) + --post_div_max; + if (post_div_max > pll->max_post_div) + post_div_max = pll->max_post_div; + } + + /* represent the searched ratio as fractional number */ + nom = target_clock; + den = pll->reference_freq; + + /* reduce the numbers to a simpler ratio */ + amdgpu_pll_reduce_ratio(&nom, &den, fb_div_min, post_div_min); + + /* now search for a post divider */ + if (pll->flags & AMDGPU_PLL_PREFER_MINM_OVER_MAXP) + post_div_best = post_div_min; + else + post_div_best = post_div_max; + diff_best = ~0; + + for (post_div = post_div_min; post_div <= post_div_max; ++post_div) { + unsigned diff; + amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max, + ref_div_max, &fb_div, &ref_div); + diff = abs(target_clock - (pll->reference_freq * fb_div) / + (ref_div * post_div)); + + if (diff < diff_best || (diff == diff_best && + !(pll->flags & AMDGPU_PLL_PREFER_MINM_OVER_MAXP))) { + + post_div_best = post_div; + diff_best = diff; + } + } + post_div = post_div_best; + + /* get the feedback and reference divider for the optimal value */ + amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max, ref_div_max, + &fb_div, &ref_div); + + /* reduce the numbers to a simpler ratio once more */ + /* this also makes sure that the reference divider is large enough */ + amdgpu_pll_reduce_ratio(&fb_div, &ref_div, fb_div_min, ref_div_min); + + /* avoid high jitter with small fractional dividers */ + if (pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV && (fb_div % 10)) { + fb_div_min = max(fb_div_min, (9 - (fb_div % 10)) * 20 + 60); + if (fb_div < fb_div_min) { + unsigned tmp = DIV_ROUND_UP(fb_div_min, fb_div); + fb_div *= tmp; + ref_div *= tmp; + } + } + + /* and finally save the result */ + if (pll->flags & AMDGPU_PLL_USE_FRAC_FB_DIV) { + *fb_div_p = fb_div / 10; + *frac_fb_div_p = fb_div % 10; + } else { + *fb_div_p = fb_div; + *frac_fb_div_p = 0; + } + + *dot_clock_p = ((pll->reference_freq * *fb_div_p * 10) + + (pll->reference_freq * *frac_fb_div_p)) / + (ref_div * post_div * 10); + *ref_div_p = ref_div; + *post_div_p = post_div; + + DRM_DEBUG_KMS("%d - %d, pll dividers - fb: %d.%d ref: %d, post %d\n", + freq, *dot_clock_p * 10, *fb_div_p, *frac_fb_div_p, + ref_div, post_div); +} + +/** + * amdgpu_pll_get_use_mask - look up a mask of which pplls are in use + * + * @crtc: drm crtc + * + * Returns the mask of which PPLLs (Pixel PLLs) are in use. + */ +u32 amdgpu_pll_get_use_mask(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_crtc *test_crtc; + struct amdgpu_crtc *test_amdgpu_crtc; + u32 pll_in_use = 0; + + list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { + if (crtc == test_crtc) + continue; + + test_amdgpu_crtc = to_amdgpu_crtc(test_crtc); + if (test_amdgpu_crtc->pll_id != ATOM_PPLL_INVALID) + pll_in_use |= (1 << test_amdgpu_crtc->pll_id); + } + return pll_in_use; +} + +/** + * amdgpu_pll_get_shared_dp_ppll - return the PPLL used by another crtc for DP + * + * @crtc: drm crtc + * + * Returns the PPLL (Pixel PLL) used by another crtc/encoder which is + * also in DP mode. For DP, a single PPLL can be used for all DP + * crtcs/encoders. + */ +int amdgpu_pll_get_shared_dp_ppll(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_crtc *test_crtc; + struct amdgpu_crtc *test_amdgpu_crtc; + + list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { + if (crtc == test_crtc) + continue; + test_amdgpu_crtc = to_amdgpu_crtc(test_crtc); + if (test_amdgpu_crtc->encoder && + ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(test_amdgpu_crtc->encoder))) { + /* for DP use the same PLL for all */ + if (test_amdgpu_crtc->pll_id != ATOM_PPLL_INVALID) + return test_amdgpu_crtc->pll_id; + } + } + return ATOM_PPLL_INVALID; +} + +/** + * amdgpu_pll_get_shared_nondp_ppll - return the PPLL used by another non-DP crtc + * + * @crtc: drm crtc + * + * Returns the PPLL (Pixel PLL) used by another non-DP crtc/encoder which can + * be shared (i.e., same clock). + */ +int amdgpu_pll_get_shared_nondp_ppll(struct drm_crtc *crtc) +{ + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + struct drm_device *dev = crtc->dev; + struct drm_crtc *test_crtc; + struct amdgpu_crtc *test_amdgpu_crtc; + u32 adjusted_clock, test_adjusted_clock; + + adjusted_clock = amdgpu_crtc->adjusted_clock; + + if (adjusted_clock == 0) + return ATOM_PPLL_INVALID; + + list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { + if (crtc == test_crtc) + continue; + test_amdgpu_crtc = to_amdgpu_crtc(test_crtc); + if (test_amdgpu_crtc->encoder && + !ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(test_amdgpu_crtc->encoder))) { + /* check if we are already driving this connector with another crtc */ + if (test_amdgpu_crtc->connector == amdgpu_crtc->connector) { + /* if we are, return that pll */ + if (test_amdgpu_crtc->pll_id != ATOM_PPLL_INVALID) + return test_amdgpu_crtc->pll_id; + } + /* for non-DP check the clock */ + test_adjusted_clock = test_amdgpu_crtc->adjusted_clock; + if ((crtc->mode.clock == test_crtc->mode.clock) && + (adjusted_clock == test_adjusted_clock) && + (amdgpu_crtc->ss_enabled == test_amdgpu_crtc->ss_enabled) && + (test_amdgpu_crtc->pll_id != ATOM_PPLL_INVALID)) + return test_amdgpu_crtc->pll_id; + } + } + return ATOM_PPLL_INVALID; +} -- cgit v1.2.3