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/clk/clk-xgene.c | 746 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 746 insertions(+) create mode 100644 drivers/clk/clk-xgene.c (limited to 'drivers/clk/clk-xgene.c') diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c new file mode 100644 index 000000000..0c3d0cee9 --- /dev/null +++ b/drivers/clk/clk-xgene.c @@ -0,0 +1,746 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * clk-xgene.c - AppliedMicro X-Gene Clock Interface + * + * Copyright (c) 2013, Applied Micro Circuits Corporation + * Author: Loc Ho + */ +#include +#include +#include +#include +#include +#include +#include + +/* Register SCU_PCPPLL bit fields */ +#define N_DIV_RD(src) ((src) & 0x000001ff) +#define SC_N_DIV_RD(src) ((src) & 0x0000007f) +#define SC_OUTDIV2(src) (((src) & 0x00000100) >> 8) + +/* Register SCU_SOCPLL bit fields */ +#define CLKR_RD(src) (((src) & 0x07000000)>>24) +#define CLKOD_RD(src) (((src) & 0x00300000)>>20) +#define REGSPEC_RESET_F1_MASK 0x00010000 +#define CLKF_RD(src) (((src) & 0x000001ff)) + +#define XGENE_CLK_DRIVER_VER "0.1" + +static DEFINE_SPINLOCK(clk_lock); + +static inline u32 xgene_clk_read(void __iomem *csr) +{ + return readl_relaxed(csr); +} + +static inline void xgene_clk_write(u32 data, void __iomem *csr) +{ + writel_relaxed(data, csr); +} + +/* PLL Clock */ +enum xgene_pll_type { + PLL_TYPE_PCP = 0, + PLL_TYPE_SOC = 1, +}; + +struct xgene_clk_pll { + struct clk_hw hw; + void __iomem *reg; + spinlock_t *lock; + u32 pll_offset; + enum xgene_pll_type type; + int version; +}; + +#define to_xgene_clk_pll(_hw) container_of(_hw, struct xgene_clk_pll, hw) + +static int xgene_clk_pll_is_enabled(struct clk_hw *hw) +{ + struct xgene_clk_pll *pllclk = to_xgene_clk_pll(hw); + u32 data; + + data = xgene_clk_read(pllclk->reg + pllclk->pll_offset); + pr_debug("%s pll %s\n", clk_hw_get_name(hw), + data & REGSPEC_RESET_F1_MASK ? "disabled" : "enabled"); + + return data & REGSPEC_RESET_F1_MASK ? 0 : 1; +} + +static unsigned long xgene_clk_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct xgene_clk_pll *pllclk = to_xgene_clk_pll(hw); + unsigned long fref; + unsigned long fvco; + u32 pll; + u32 nref; + u32 nout; + u32 nfb; + + pll = xgene_clk_read(pllclk->reg + pllclk->pll_offset); + + if (pllclk->version <= 1) { + if (pllclk->type == PLL_TYPE_PCP) { + /* + * PLL VCO = Reference clock * NF + * PCP PLL = PLL_VCO / 2 + */ + nout = 2; + fvco = parent_rate * (N_DIV_RD(pll) + 4); + } else { + /* + * Fref = Reference Clock / NREF; + * Fvco = Fref * NFB; + * Fout = Fvco / NOUT; + */ + nref = CLKR_RD(pll) + 1; + nout = CLKOD_RD(pll) + 1; + nfb = CLKF_RD(pll); + fref = parent_rate / nref; + fvco = fref * nfb; + } + } else { + /* + * fvco = Reference clock * FBDIVC + * PLL freq = fvco / NOUT + */ + nout = SC_OUTDIV2(pll) ? 2 : 3; + fvco = parent_rate * SC_N_DIV_RD(pll); + } + pr_debug("%s pll recalc rate %ld parent %ld version %d\n", + clk_hw_get_name(hw), fvco / nout, parent_rate, + pllclk->version); + + return fvco / nout; +} + +static const struct clk_ops xgene_clk_pll_ops = { + .is_enabled = xgene_clk_pll_is_enabled, + .recalc_rate = xgene_clk_pll_recalc_rate, +}; + +static struct clk *xgene_register_clk_pll(struct device *dev, + const char *name, const char *parent_name, + unsigned long flags, void __iomem *reg, u32 pll_offset, + u32 type, spinlock_t *lock, int version) +{ + struct xgene_clk_pll *apmclk; + struct clk *clk; + struct clk_init_data init; + + /* allocate the APM clock structure */ + apmclk = kzalloc(sizeof(*apmclk), GFP_KERNEL); + if (!apmclk) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = &xgene_clk_pll_ops; + init.flags = flags; + init.parent_names = parent_name ? &parent_name : NULL; + init.num_parents = parent_name ? 1 : 0; + + apmclk->version = version; + apmclk->reg = reg; + apmclk->lock = lock; + apmclk->pll_offset = pll_offset; + apmclk->type = type; + apmclk->hw.init = &init; + + /* Register the clock */ + clk = clk_register(dev, &apmclk->hw); + if (IS_ERR(clk)) { + pr_err("%s: could not register clk %s\n", __func__, name); + kfree(apmclk); + return NULL; + } + return clk; +} + +static int xgene_pllclk_version(struct device_node *np) +{ + if (of_device_is_compatible(np, "apm,xgene-socpll-clock")) + return 1; + if (of_device_is_compatible(np, "apm,xgene-pcppll-clock")) + return 1; + return 2; +} + +static void xgene_pllclk_init(struct device_node *np, enum xgene_pll_type pll_type) +{ + const char *clk_name = np->full_name; + struct clk *clk; + void __iomem *reg; + int version = xgene_pllclk_version(np); + + reg = of_iomap(np, 0); + if (!reg) { + pr_err("Unable to map CSR register for %pOF\n", np); + return; + } + of_property_read_string(np, "clock-output-names", &clk_name); + clk = xgene_register_clk_pll(NULL, + clk_name, of_clk_get_parent_name(np, 0), + 0, reg, 0, pll_type, &clk_lock, + version); + if (!IS_ERR(clk)) { + of_clk_add_provider(np, of_clk_src_simple_get, clk); + clk_register_clkdev(clk, clk_name, NULL); + pr_debug("Add %s clock PLL\n", clk_name); + } +} + +static void xgene_socpllclk_init(struct device_node *np) +{ + xgene_pllclk_init(np, PLL_TYPE_SOC); +} + +static void xgene_pcppllclk_init(struct device_node *np) +{ + xgene_pllclk_init(np, PLL_TYPE_PCP); +} + +/** + * struct xgene_clk_pmd - PMD clock + * + * @hw: handle between common and hardware-specific interfaces + * @reg: register containing the fractional scale multiplier (scaler) + * @shift: shift to the unit bit field + * @mask: mask to the unit bit field + * @denom: 1/denominator unit + * @lock: register lock + * @flags: XGENE_CLK_PMD_SCALE_INVERTED - By default the scaler is the value read + * from the register plus one. For example, + * 0 for (0 + 1) / denom, + * 1 for (1 + 1) / denom and etc. + * If this flag is set, it is + * 0 for (denom - 0) / denom, + * 1 for (denom - 1) / denom and etc. + */ +struct xgene_clk_pmd { + struct clk_hw hw; + void __iomem *reg; + u8 shift; + u32 mask; + u64 denom; + u32 flags; + spinlock_t *lock; +}; + +#define to_xgene_clk_pmd(_hw) container_of(_hw, struct xgene_clk_pmd, hw) + +#define XGENE_CLK_PMD_SCALE_INVERTED BIT(0) +#define XGENE_CLK_PMD_SHIFT 8 +#define XGENE_CLK_PMD_WIDTH 3 + +static unsigned long xgene_clk_pmd_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct xgene_clk_pmd *fd = to_xgene_clk_pmd(hw); + unsigned long flags = 0; + u64 ret, scale; + u32 val; + + if (fd->lock) + spin_lock_irqsave(fd->lock, flags); + else + __acquire(fd->lock); + + val = readl(fd->reg); + + if (fd->lock) + spin_unlock_irqrestore(fd->lock, flags); + else + __release(fd->lock); + + ret = (u64)parent_rate; + + scale = (val & fd->mask) >> fd->shift; + if (fd->flags & XGENE_CLK_PMD_SCALE_INVERTED) + scale = fd->denom - scale; + else + scale++; + + /* freq = parent_rate * scaler / denom */ + do_div(ret, fd->denom); + ret *= scale; + if (ret == 0) + ret = (u64)parent_rate; + + return ret; +} + +static long xgene_clk_pmd_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + struct xgene_clk_pmd *fd = to_xgene_clk_pmd(hw); + u64 ret, scale; + + if (!rate || rate >= *parent_rate) + return *parent_rate; + + /* freq = parent_rate * scaler / denom */ + ret = rate * fd->denom; + scale = DIV_ROUND_UP_ULL(ret, *parent_rate); + + ret = (u64)*parent_rate * scale; + do_div(ret, fd->denom); + + return ret; +} + +static int xgene_clk_pmd_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct xgene_clk_pmd *fd = to_xgene_clk_pmd(hw); + unsigned long flags = 0; + u64 scale, ret; + u32 val; + + /* + * Compute the scaler: + * + * freq = parent_rate * scaler / denom, or + * scaler = freq * denom / parent_rate + */ + ret = rate * fd->denom; + scale = DIV_ROUND_UP_ULL(ret, (u64)parent_rate); + + /* Check if inverted */ + if (fd->flags & XGENE_CLK_PMD_SCALE_INVERTED) + scale = fd->denom - scale; + else + scale--; + + if (fd->lock) + spin_lock_irqsave(fd->lock, flags); + else + __acquire(fd->lock); + + val = readl(fd->reg); + val &= ~fd->mask; + val |= (scale << fd->shift); + writel(val, fd->reg); + + if (fd->lock) + spin_unlock_irqrestore(fd->lock, flags); + else + __release(fd->lock); + + return 0; +} + +static const struct clk_ops xgene_clk_pmd_ops = { + .recalc_rate = xgene_clk_pmd_recalc_rate, + .round_rate = xgene_clk_pmd_round_rate, + .set_rate = xgene_clk_pmd_set_rate, +}; + +static struct clk * +xgene_register_clk_pmd(struct device *dev, + const char *name, const char *parent_name, + unsigned long flags, void __iomem *reg, u8 shift, + u8 width, u64 denom, u32 clk_flags, spinlock_t *lock) +{ + struct xgene_clk_pmd *fd; + struct clk_init_data init; + struct clk *clk; + + fd = kzalloc(sizeof(*fd), GFP_KERNEL); + if (!fd) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = &xgene_clk_pmd_ops; + init.flags = flags; + init.parent_names = parent_name ? &parent_name : NULL; + init.num_parents = parent_name ? 1 : 0; + + fd->reg = reg; + fd->shift = shift; + fd->mask = (BIT(width) - 1) << shift; + fd->denom = denom; + fd->flags = clk_flags; + fd->lock = lock; + fd->hw.init = &init; + + clk = clk_register(dev, &fd->hw); + if (IS_ERR(clk)) { + pr_err("%s: could not register clk %s\n", __func__, name); + kfree(fd); + return NULL; + } + + return clk; +} + +static void xgene_pmdclk_init(struct device_node *np) +{ + const char *clk_name = np->full_name; + void __iomem *csr_reg; + struct resource res; + struct clk *clk; + u64 denom; + u32 flags = 0; + int rc; + + /* Check if the entry is disabled */ + if (!of_device_is_available(np)) + return; + + /* Parse the DTS register for resource */ + rc = of_address_to_resource(np, 0, &res); + if (rc != 0) { + pr_err("no DTS register for %pOF\n", np); + return; + } + csr_reg = of_iomap(np, 0); + if (!csr_reg) { + pr_err("Unable to map resource for %pOF\n", np); + return; + } + of_property_read_string(np, "clock-output-names", &clk_name); + + denom = BIT(XGENE_CLK_PMD_WIDTH); + flags |= XGENE_CLK_PMD_SCALE_INVERTED; + + clk = xgene_register_clk_pmd(NULL, clk_name, + of_clk_get_parent_name(np, 0), 0, + csr_reg, XGENE_CLK_PMD_SHIFT, + XGENE_CLK_PMD_WIDTH, denom, + flags, &clk_lock); + if (!IS_ERR(clk)) { + of_clk_add_provider(np, of_clk_src_simple_get, clk); + clk_register_clkdev(clk, clk_name, NULL); + pr_debug("Add %s clock\n", clk_name); + } else { + if (csr_reg) + iounmap(csr_reg); + } +} + +/* IP Clock */ +struct xgene_dev_parameters { + void __iomem *csr_reg; /* CSR for IP clock */ + u32 reg_clk_offset; /* Offset to clock enable CSR */ + u32 reg_clk_mask; /* Mask bit for clock enable */ + u32 reg_csr_offset; /* Offset to CSR reset */ + u32 reg_csr_mask; /* Mask bit for disable CSR reset */ + void __iomem *divider_reg; /* CSR for divider */ + u32 reg_divider_offset; /* Offset to divider register */ + u32 reg_divider_shift; /* Bit shift to divider field */ + u32 reg_divider_width; /* Width of the bit to divider field */ +}; + +struct xgene_clk { + struct clk_hw hw; + spinlock_t *lock; + struct xgene_dev_parameters param; +}; + +#define to_xgene_clk(_hw) container_of(_hw, struct xgene_clk, hw) + +static int xgene_clk_enable(struct clk_hw *hw) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + unsigned long flags = 0; + u32 data; + + if (pclk->lock) + spin_lock_irqsave(pclk->lock, flags); + + if (pclk->param.csr_reg) { + pr_debug("%s clock enabled\n", clk_hw_get_name(hw)); + /* First enable the clock */ + data = xgene_clk_read(pclk->param.csr_reg + + pclk->param.reg_clk_offset); + data |= pclk->param.reg_clk_mask; + xgene_clk_write(data, pclk->param.csr_reg + + pclk->param.reg_clk_offset); + pr_debug("%s clk offset 0x%08X mask 0x%08X value 0x%08X\n", + clk_hw_get_name(hw), + pclk->param.reg_clk_offset, pclk->param.reg_clk_mask, + data); + + /* Second enable the CSR */ + data = xgene_clk_read(pclk->param.csr_reg + + pclk->param.reg_csr_offset); + data &= ~pclk->param.reg_csr_mask; + xgene_clk_write(data, pclk->param.csr_reg + + pclk->param.reg_csr_offset); + pr_debug("%s csr offset 0x%08X mask 0x%08X value 0x%08X\n", + clk_hw_get_name(hw), + pclk->param.reg_csr_offset, pclk->param.reg_csr_mask, + data); + } + + if (pclk->lock) + spin_unlock_irqrestore(pclk->lock, flags); + + return 0; +} + +static void xgene_clk_disable(struct clk_hw *hw) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + unsigned long flags = 0; + u32 data; + + if (pclk->lock) + spin_lock_irqsave(pclk->lock, flags); + + if (pclk->param.csr_reg) { + pr_debug("%s clock disabled\n", clk_hw_get_name(hw)); + /* First put the CSR in reset */ + data = xgene_clk_read(pclk->param.csr_reg + + pclk->param.reg_csr_offset); + data |= pclk->param.reg_csr_mask; + xgene_clk_write(data, pclk->param.csr_reg + + pclk->param.reg_csr_offset); + + /* Second disable the clock */ + data = xgene_clk_read(pclk->param.csr_reg + + pclk->param.reg_clk_offset); + data &= ~pclk->param.reg_clk_mask; + xgene_clk_write(data, pclk->param.csr_reg + + pclk->param.reg_clk_offset); + } + + if (pclk->lock) + spin_unlock_irqrestore(pclk->lock, flags); +} + +static int xgene_clk_is_enabled(struct clk_hw *hw) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + u32 data = 0; + + if (pclk->param.csr_reg) { + pr_debug("%s clock checking\n", clk_hw_get_name(hw)); + data = xgene_clk_read(pclk->param.csr_reg + + pclk->param.reg_clk_offset); + pr_debug("%s clock is %s\n", clk_hw_get_name(hw), + data & pclk->param.reg_clk_mask ? "enabled" : + "disabled"); + } else { + return 1; + } + + return data & pclk->param.reg_clk_mask ? 1 : 0; +} + +static unsigned long xgene_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + u32 data; + + if (pclk->param.divider_reg) { + data = xgene_clk_read(pclk->param.divider_reg + + pclk->param.reg_divider_offset); + data >>= pclk->param.reg_divider_shift; + data &= (1 << pclk->param.reg_divider_width) - 1; + + pr_debug("%s clock recalc rate %ld parent %ld\n", + clk_hw_get_name(hw), + parent_rate / data, parent_rate); + + return parent_rate / data; + } else { + pr_debug("%s clock recalc rate %ld parent %ld\n", + clk_hw_get_name(hw), parent_rate, parent_rate); + return parent_rate; + } +} + +static int xgene_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + unsigned long flags = 0; + u32 data; + u32 divider; + u32 divider_save; + + if (pclk->lock) + spin_lock_irqsave(pclk->lock, flags); + + if (pclk->param.divider_reg) { + /* Let's compute the divider */ + if (rate > parent_rate) + rate = parent_rate; + divider_save = divider = parent_rate / rate; /* Rounded down */ + divider &= (1 << pclk->param.reg_divider_width) - 1; + divider <<= pclk->param.reg_divider_shift; + + /* Set new divider */ + data = xgene_clk_read(pclk->param.divider_reg + + pclk->param.reg_divider_offset); + data &= ~(((1 << pclk->param.reg_divider_width) - 1) + << pclk->param.reg_divider_shift); + data |= divider; + xgene_clk_write(data, pclk->param.divider_reg + + pclk->param.reg_divider_offset); + pr_debug("%s clock set rate %ld\n", clk_hw_get_name(hw), + parent_rate / divider_save); + } else { + divider_save = 1; + } + + if (pclk->lock) + spin_unlock_irqrestore(pclk->lock, flags); + + return parent_rate / divider_save; +} + +static long xgene_clk_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + struct xgene_clk *pclk = to_xgene_clk(hw); + unsigned long parent_rate = *prate; + u32 divider; + + if (pclk->param.divider_reg) { + /* Let's compute the divider */ + if (rate > parent_rate) + rate = parent_rate; + divider = parent_rate / rate; /* Rounded down */ + } else { + divider = 1; + } + + return parent_rate / divider; +} + +static const struct clk_ops xgene_clk_ops = { + .enable = xgene_clk_enable, + .disable = xgene_clk_disable, + .is_enabled = xgene_clk_is_enabled, + .recalc_rate = xgene_clk_recalc_rate, + .set_rate = xgene_clk_set_rate, + .round_rate = xgene_clk_round_rate, +}; + +static struct clk *xgene_register_clk(struct device *dev, + const char *name, const char *parent_name, + struct xgene_dev_parameters *parameters, spinlock_t *lock) +{ + struct xgene_clk *apmclk; + struct clk *clk; + struct clk_init_data init; + int rc; + + /* allocate the APM clock structure */ + apmclk = kzalloc(sizeof(*apmclk), GFP_KERNEL); + if (!apmclk) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = &xgene_clk_ops; + init.flags = 0; + init.parent_names = parent_name ? &parent_name : NULL; + init.num_parents = parent_name ? 1 : 0; + + apmclk->lock = lock; + apmclk->hw.init = &init; + apmclk->param = *parameters; + + /* Register the clock */ + clk = clk_register(dev, &apmclk->hw); + if (IS_ERR(clk)) { + pr_err("%s: could not register clk %s\n", __func__, name); + kfree(apmclk); + return clk; + } + + /* Register the clock for lookup */ + rc = clk_register_clkdev(clk, name, NULL); + if (rc != 0) { + pr_err("%s: could not register lookup clk %s\n", + __func__, name); + } + return clk; +} + +static void __init xgene_devclk_init(struct device_node *np) +{ + const char *clk_name = np->full_name; + struct clk *clk; + struct resource res; + int rc; + struct xgene_dev_parameters parameters; + int i; + + /* Check if the entry is disabled */ + if (!of_device_is_available(np)) + return; + + /* Parse the DTS register for resource */ + parameters.csr_reg = NULL; + parameters.divider_reg = NULL; + for (i = 0; i < 2; i++) { + void __iomem *map_res; + rc = of_address_to_resource(np, i, &res); + if (rc != 0) { + if (i == 0) { + pr_err("no DTS register for %pOF\n", np); + return; + } + break; + } + map_res = of_iomap(np, i); + if (!map_res) { + pr_err("Unable to map resource %d for %pOF\n", i, np); + goto err; + } + if (strcmp(res.name, "div-reg") == 0) + parameters.divider_reg = map_res; + else /* if (strcmp(res->name, "csr-reg") == 0) */ + parameters.csr_reg = map_res; + } + if (of_property_read_u32(np, "csr-offset", ¶meters.reg_csr_offset)) + parameters.reg_csr_offset = 0; + if (of_property_read_u32(np, "csr-mask", ¶meters.reg_csr_mask)) + parameters.reg_csr_mask = 0xF; + if (of_property_read_u32(np, "enable-offset", + ¶meters.reg_clk_offset)) + parameters.reg_clk_offset = 0x8; + if (of_property_read_u32(np, "enable-mask", ¶meters.reg_clk_mask)) + parameters.reg_clk_mask = 0xF; + if (of_property_read_u32(np, "divider-offset", + ¶meters.reg_divider_offset)) + parameters.reg_divider_offset = 0; + if (of_property_read_u32(np, "divider-width", + ¶meters.reg_divider_width)) + parameters.reg_divider_width = 0; + if (of_property_read_u32(np, "divider-shift", + ¶meters.reg_divider_shift)) + parameters.reg_divider_shift = 0; + of_property_read_string(np, "clock-output-names", &clk_name); + + clk = xgene_register_clk(NULL, clk_name, + of_clk_get_parent_name(np, 0), ¶meters, &clk_lock); + if (IS_ERR(clk)) + goto err; + pr_debug("Add %s clock\n", clk_name); + rc = of_clk_add_provider(np, of_clk_src_simple_get, clk); + if (rc != 0) + pr_err("%s: could register provider clk %pOF\n", __func__, np); + + return; + +err: + if (parameters.csr_reg) + iounmap(parameters.csr_reg); + if (parameters.divider_reg) + iounmap(parameters.divider_reg); +} + +CLK_OF_DECLARE(xgene_socpll_clock, "apm,xgene-socpll-clock", xgene_socpllclk_init); +CLK_OF_DECLARE(xgene_pcppll_clock, "apm,xgene-pcppll-clock", xgene_pcppllclk_init); +CLK_OF_DECLARE(xgene_pmd_clock, "apm,xgene-pmd-clock", xgene_pmdclk_init); +CLK_OF_DECLARE(xgene_socpll_v2_clock, "apm,xgene-socpll-v2-clock", + xgene_socpllclk_init); +CLK_OF_DECLARE(xgene_pcppll_v2_clock, "apm,xgene-pcppll-v2-clock", + xgene_pcppllclk_init); +CLK_OF_DECLARE(xgene_dev_clock, "apm,xgene-device-clock", xgene_devclk_init); -- cgit v1.2.3