diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | |
download | linux-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/iommu/arm/arm-smmu/arm-smmu-qcom.c')
-rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 549 |
1 files changed, 549 insertions, 0 deletions
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c new file mode 100644 index 000000000..91d404deb --- /dev/null +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019, The Linux Foundation. All rights reserved. + */ + +#include <linux/acpi.h> +#include <linux/adreno-smmu-priv.h> +#include <linux/delay.h> +#include <linux/of_device.h> +#include <linux/qcom_scm.h> + +#include "arm-smmu.h" +#include "arm-smmu-qcom.h" + +#define QCOM_DUMMY_VAL -1 + +static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu) +{ + return container_of(smmu, struct qcom_smmu, smmu); +} + +static void qcom_smmu_tlb_sync(struct arm_smmu_device *smmu, int page, + int sync, int status) +{ + unsigned int spin_cnt, delay; + u32 reg; + + arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL); + for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) { + for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) { + reg = arm_smmu_readl(smmu, page, status); + if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE)) + return; + cpu_relax(); + } + udelay(delay); + } + + qcom_smmu_tlb_sync_debug(smmu); +} + +static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx, + u32 reg) +{ + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + + /* + * On the GPU device we want to process subsequent transactions after a + * fault to keep the GPU from hanging + */ + reg |= ARM_SMMU_SCTLR_HUPCF; + + if (qsmmu->stall_enabled & BIT(idx)) + reg |= ARM_SMMU_SCTLR_CFCFG; + + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg); +} + +static void qcom_adreno_smmu_get_fault_info(const void *cookie, + struct adreno_smmu_fault_info *info) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + struct arm_smmu_device *smmu = smmu_domain->smmu; + + info->fsr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSR); + info->fsynr0 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSYNR0); + info->fsynr1 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSYNR1); + info->far = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_FAR); + info->cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx)); + info->ttbr0 = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_TTBR0); + info->contextidr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_CONTEXTIDR); +} + +static void qcom_adreno_smmu_set_stall(const void *cookie, bool enabled) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu_domain->smmu); + + if (enabled) + qsmmu->stall_enabled |= BIT(cfg->cbndx); + else + qsmmu->stall_enabled &= ~BIT(cfg->cbndx); +} + +static void qcom_adreno_smmu_resume_translation(const void *cookie, bool terminate) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + struct arm_smmu_device *smmu = smmu_domain->smmu; + u32 reg = 0; + + if (terminate) + reg |= ARM_SMMU_RESUME_TERMINATE; + + arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_RESUME, reg); +} + +#define QCOM_ADRENO_SMMU_GPU_SID 0 + +static bool qcom_adreno_smmu_is_gpu_device(struct device *dev) +{ + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + int i; + + /* + * The GPU will always use SID 0 so that is a handy way to uniquely + * identify it and configure it for per-instance pagetables + */ + for (i = 0; i < fwspec->num_ids; i++) { + u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]); + + if (sid == QCOM_ADRENO_SMMU_GPU_SID) + return true; + } + + return false; +} + +static const struct io_pgtable_cfg *qcom_adreno_smmu_get_ttbr1_cfg( + const void *cookie) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct io_pgtable *pgtable = + io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops); + return &pgtable->cfg; +} + +/* + * Local implementation to configure TTBR0 with the specified pagetable config. + * The GPU driver will call this to enable TTBR0 when per-instance pagetables + * are active + */ + +static int qcom_adreno_smmu_set_ttbr0_cfg(const void *cookie, + const struct io_pgtable_cfg *pgtbl_cfg) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct io_pgtable *pgtable = io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops); + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + struct arm_smmu_cb *cb = &smmu_domain->smmu->cbs[cfg->cbndx]; + + /* The domain must have split pagetables already enabled */ + if (cb->tcr[0] & ARM_SMMU_TCR_EPD1) + return -EINVAL; + + /* If the pagetable config is NULL, disable TTBR0 */ + if (!pgtbl_cfg) { + /* Do nothing if it is already disabled */ + if ((cb->tcr[0] & ARM_SMMU_TCR_EPD0)) + return -EINVAL; + + /* Set TCR to the original configuration */ + cb->tcr[0] = arm_smmu_lpae_tcr(&pgtable->cfg); + cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid); + } else { + u32 tcr = cb->tcr[0]; + + /* Don't call this again if TTBR0 is already enabled */ + if (!(cb->tcr[0] & ARM_SMMU_TCR_EPD0)) + return -EINVAL; + + tcr |= arm_smmu_lpae_tcr(pgtbl_cfg); + tcr &= ~(ARM_SMMU_TCR_EPD0 | ARM_SMMU_TCR_EPD1); + + cb->tcr[0] = tcr; + cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr; + cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid); + } + + arm_smmu_write_context_bank(smmu_domain->smmu, cb->cfg->cbndx); + + return 0; +} + +static int qcom_adreno_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_device *smmu, + struct device *dev, int start) +{ + int count; + + /* + * Assign context bank 0 to the GPU device so the GPU hardware can + * switch pagetables + */ + if (qcom_adreno_smmu_is_gpu_device(dev)) { + start = 0; + count = 1; + } else { + start = 1; + count = smmu->num_context_banks; + } + + return __arm_smmu_alloc_bitmap(smmu->context_map, start, count); +} + +static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu) +{ + const struct device_node *np = smmu->dev->of_node; + + if (of_device_is_compatible(np, "qcom,msm8996-smmu-v2")) + return false; + + return true; +} + +static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) +{ + struct adreno_smmu_priv *priv; + + smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + + /* Only enable split pagetables for the GPU device (SID 0) */ + if (!qcom_adreno_smmu_is_gpu_device(dev)) + return 0; + + /* + * All targets that use the qcom,adreno-smmu compatible string *should* + * be AARCH64 stage 1 but double check because the arm-smmu code assumes + * that is the case when the TTBR1 quirk is enabled + */ + if (qcom_adreno_can_do_ttbr1(smmu_domain->smmu) && + (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) && + (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64)) + pgtbl_cfg->quirks |= IO_PGTABLE_QUIRK_ARM_TTBR1; + + /* + * Initialize private interface with GPU: + */ + + priv = dev_get_drvdata(dev); + priv->cookie = smmu_domain; + priv->get_ttbr1_cfg = qcom_adreno_smmu_get_ttbr1_cfg; + priv->set_ttbr0_cfg = qcom_adreno_smmu_set_ttbr0_cfg; + priv->get_fault_info = qcom_adreno_smmu_get_fault_info; + priv->set_stall = qcom_adreno_smmu_set_stall; + priv->resume_translation = qcom_adreno_smmu_resume_translation; + + return 0; +} + +static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { + { .compatible = "qcom,adreno" }, + { .compatible = "qcom,mdp4" }, + { .compatible = "qcom,mdss" }, + { .compatible = "qcom,sc7180-mdss" }, + { .compatible = "qcom,sc7180-mss-pil" }, + { .compatible = "qcom,sc7280-mdss" }, + { .compatible = "qcom,sc7280-mss-pil" }, + { .compatible = "qcom,sc8180x-mdss" }, + { .compatible = "qcom,sm8250-mdss" }, + { .compatible = "qcom,sdm845-mdss" }, + { .compatible = "qcom,sdm845-mss-pil" }, + { } +}; + +static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) +{ + smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + + return 0; +} + +static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) +{ + unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + u32 reg; + u32 smr; + int i; + + /* + * With some firmware versions writes to S2CR of type FAULT are + * ignored, and writing BYPASS will end up written as FAULT in the + * register. Perform a write to S2CR to detect if this is the case and + * if so reserve a context bank to emulate bypass streams. + */ + reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, S2CR_TYPE_BYPASS) | + FIELD_PREP(ARM_SMMU_S2CR_CBNDX, 0xff) | + FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, S2CR_PRIVCFG_DEFAULT); + arm_smmu_gr0_write(smmu, last_s2cr, reg); + reg = arm_smmu_gr0_read(smmu, last_s2cr); + if (FIELD_GET(ARM_SMMU_S2CR_TYPE, reg) != S2CR_TYPE_BYPASS) { + qsmmu->bypass_quirk = true; + qsmmu->bypass_cbndx = smmu->num_context_banks - 1; + + set_bit(qsmmu->bypass_cbndx, smmu->context_map); + + arm_smmu_cb_write(smmu, qsmmu->bypass_cbndx, ARM_SMMU_CB_SCTLR, 0); + + reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS); + arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg); + } + + for (i = 0; i < smmu->num_mapping_groups; i++) { + smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i)); + + if (FIELD_GET(ARM_SMMU_SMR_VALID, smr)) { + /* Ignore valid bit for SMR mask extraction. */ + smr &= ~ARM_SMMU_SMR_VALID; + smmu->smrs[i].id = FIELD_GET(ARM_SMMU_SMR_ID, smr); + smmu->smrs[i].mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr); + smmu->smrs[i].valid = true; + + smmu->s2crs[i].type = S2CR_TYPE_BYPASS; + smmu->s2crs[i].privcfg = S2CR_PRIVCFG_DEFAULT; + smmu->s2crs[i].cbndx = 0xff; + } + } + + return 0; +} + +static void qcom_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx) +{ + struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + u32 cbndx = s2cr->cbndx; + u32 type = s2cr->type; + u32 reg; + + if (qsmmu->bypass_quirk) { + if (type == S2CR_TYPE_BYPASS) { + /* + * Firmware with quirky S2CR handling will substitute + * BYPASS writes with FAULT, so point the stream to the + * reserved context bank and ask for translation on the + * stream + */ + type = S2CR_TYPE_TRANS; + cbndx = qsmmu->bypass_cbndx; + } else if (type == S2CR_TYPE_FAULT) { + /* + * Firmware with quirky S2CR handling will ignore FAULT + * writes, so trick it to write FAULT by asking for a + * BYPASS. + */ + type = S2CR_TYPE_BYPASS; + cbndx = 0xff; + } + } + + reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, type) | + FIELD_PREP(ARM_SMMU_S2CR_CBNDX, cbndx) | + FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg); + arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg); +} + +static int qcom_smmu_def_domain_type(struct device *dev) +{ + const struct of_device_id *match = + of_match_device(qcom_smmu_client_of_match, dev); + + return match ? IOMMU_DOMAIN_IDENTITY : 0; +} + +static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu) +{ + int ret; + + arm_mmu500_reset(smmu); + + /* + * To address performance degradation in non-real time clients, + * such as USB and UFS, turn off wait-for-safe on sdm845 based boards, + * such as MTP and db845, whose firmwares implement secure monitor + * call handlers to turn on/off the wait-for-safe logic. + */ + ret = qcom_scm_qsmmu500_wait_safe_toggle(0); + if (ret) + dev_warn(smmu->dev, "Failed to turn off SAFE logic\n"); + + return ret; +} + +static const struct arm_smmu_impl qcom_smmu_v2_impl = { + .init_context = qcom_smmu_init_context, + .cfg_probe = qcom_smmu_cfg_probe, + .def_domain_type = qcom_smmu_def_domain_type, + .write_s2cr = qcom_smmu_write_s2cr, + .tlb_sync = qcom_smmu_tlb_sync, +}; + +static const struct arm_smmu_impl qcom_smmu_500_impl = { + .init_context = qcom_smmu_init_context, + .cfg_probe = qcom_smmu_cfg_probe, + .def_domain_type = qcom_smmu_def_domain_type, + .reset = arm_mmu500_reset, + .write_s2cr = qcom_smmu_write_s2cr, + .tlb_sync = qcom_smmu_tlb_sync, +}; + +static const struct arm_smmu_impl sdm845_smmu_500_impl = { + .init_context = qcom_smmu_init_context, + .cfg_probe = qcom_smmu_cfg_probe, + .def_domain_type = qcom_smmu_def_domain_type, + .reset = qcom_sdm845_smmu500_reset, + .write_s2cr = qcom_smmu_write_s2cr, + .tlb_sync = qcom_smmu_tlb_sync, +}; + +static const struct arm_smmu_impl qcom_adreno_smmu_v2_impl = { + .init_context = qcom_adreno_smmu_init_context, + .def_domain_type = qcom_smmu_def_domain_type, + .alloc_context_bank = qcom_adreno_smmu_alloc_context_bank, + .write_sctlr = qcom_adreno_smmu_write_sctlr, + .tlb_sync = qcom_smmu_tlb_sync, +}; + +static const struct arm_smmu_impl qcom_adreno_smmu_500_impl = { + .init_context = qcom_adreno_smmu_init_context, + .def_domain_type = qcom_smmu_def_domain_type, + .reset = arm_mmu500_reset, + .alloc_context_bank = qcom_adreno_smmu_alloc_context_bank, + .write_sctlr = qcom_adreno_smmu_write_sctlr, + .tlb_sync = qcom_smmu_tlb_sync, +}; + +static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu, + const struct qcom_smmu_match_data *data) +{ + const struct device_node *np = smmu->dev->of_node; + const struct arm_smmu_impl *impl; + struct qcom_smmu *qsmmu; + + if (!data) + return ERR_PTR(-EINVAL); + + if (np && of_device_is_compatible(np, "qcom,adreno-smmu")) + impl = data->adreno_impl; + else + impl = data->impl; + + if (!impl) + return smmu; + + /* Check to make sure qcom_scm has finished probing */ + if (!qcom_scm_is_available()) + return ERR_PTR(-EPROBE_DEFER); + + qsmmu = devm_krealloc(smmu->dev, smmu, sizeof(*qsmmu), GFP_KERNEL); + if (!qsmmu) + return ERR_PTR(-ENOMEM); + + qsmmu->smmu.impl = impl; + qsmmu->cfg = data->cfg; + + return &qsmmu->smmu; +} + +/* Implementation Defined Register Space 0 register offsets */ +static const u32 qcom_smmu_impl0_reg_offset[] = { + [QCOM_SMMU_TBU_PWR_STATUS] = 0x2204, + [QCOM_SMMU_STATS_SYNC_INV_TBU_ACK] = 0x25dc, + [QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR] = 0x2670, +}; + +static const struct qcom_smmu_config qcom_smmu_impl0_cfg = { + .reg_offset = qcom_smmu_impl0_reg_offset, +}; + +/* + * It is not yet possible to use MDP SMMU with the bypass quirk on the msm8996, + * there are not enough context banks. + */ +static const struct qcom_smmu_match_data msm8996_smmu_data = { + .impl = NULL, + .adreno_impl = &qcom_adreno_smmu_v2_impl, +}; + +static const struct qcom_smmu_match_data qcom_smmu_v2_data = { + .impl = &qcom_smmu_v2_impl, + .adreno_impl = &qcom_adreno_smmu_v2_impl, +}; + +static const struct qcom_smmu_match_data sdm845_smmu_500_data = { + .impl = &sdm845_smmu_500_impl, + /* + * No need for adreno impl here. On sdm845 the Adreno SMMU is handled + * by the separate sdm845-smmu-v2 device. + */ + /* Also no debug configuration. */ +}; + +static const struct qcom_smmu_match_data qcom_smmu_500_impl0_data = { + .impl = &qcom_smmu_500_impl, + .adreno_impl = &qcom_adreno_smmu_500_impl, + .cfg = &qcom_smmu_impl0_cfg, +}; + +/* + * Do not add any more qcom,SOC-smmu-500 entries to this list, unless they need + * special handling and can not be covered by the qcom,smmu-500 entry. + */ +static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { + { .compatible = "qcom,msm8996-smmu-v2", .data = &msm8996_smmu_data }, + { .compatible = "qcom,msm8998-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,qcm2290-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,qdu1000-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7180-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7280-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sdm630-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,sdm845-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,sdm845-smmu-500", .data = &sdm845_smmu_500_data }, + { .compatible = "qcom,sm6115-smmu-500", .data = &qcom_smmu_500_impl0_data}, + { .compatible = "qcom,sm6125-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm6350-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,sm6350-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm6375-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm8150-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm8250-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm8350-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sm8450-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,smmu-500", .data = &qcom_smmu_500_impl0_data }, + { } +}; + +#ifdef CONFIG_ACPI +static struct acpi_platform_list qcom_acpi_platlist[] = { + { "LENOVO", "CB-01 ", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" }, + { "QCOM ", "QCOMEDK2", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" }, + { } +}; +#endif + +struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) +{ + const struct device_node *np = smmu->dev->of_node; + const struct of_device_id *match; + +#ifdef CONFIG_ACPI + if (np == NULL) { + /* Match platform for ACPI boot */ + if (acpi_match_platform_list(qcom_acpi_platlist) >= 0) + return qcom_smmu_create(smmu, &qcom_smmu_500_impl0_data); + } +#endif + + match = of_match_node(qcom_smmu_impl_of_match, np); + if (match) + return qcom_smmu_create(smmu, match->data); + + return smmu; +} |