aboutsummaryrefslogtreecommitdiff
path: root/drivers/scsi/cxlflash/common.h
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/scsi/cxlflash/common.h
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/scsi/cxlflash/common.h')
-rw-r--r--drivers/scsi/cxlflash/common.h340
1 files changed, 340 insertions, 0 deletions
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
new file mode 100644
index 000000000..de6229e27
--- /dev/null
+++ b/drivers/scsi/cxlflash/common.h
@@ -0,0 +1,340 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CXL Flash Device Driver
+ *
+ * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
+ * Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
+ *
+ * Copyright (C) 2015 IBM Corporation
+ */
+
+#ifndef _CXLFLASH_COMMON_H
+#define _CXLFLASH_COMMON_H
+
+#include <linux/async.h>
+#include <linux/cdev.h>
+#include <linux/irq_poll.h>
+#include <linux/list.h>
+#include <linux/rwsem.h>
+#include <linux/types.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+
+#include "backend.h"
+
+extern const struct file_operations cxlflash_cxl_fops;
+
+#define MAX_CONTEXT CXLFLASH_MAX_CONTEXT /* num contexts per afu */
+#define MAX_FC_PORTS CXLFLASH_MAX_FC_PORTS /* max ports per AFU */
+#define LEGACY_FC_PORTS 2 /* legacy ports per AFU */
+
+#define CHAN2PORTBANK(_x) ((_x) >> ilog2(CXLFLASH_NUM_FC_PORTS_PER_BANK))
+#define CHAN2BANKPORT(_x) ((_x) & (CXLFLASH_NUM_FC_PORTS_PER_BANK - 1))
+
+#define CHAN2PORTMASK(_x) (1 << (_x)) /* channel to port mask */
+#define PORTMASK2CHAN(_x) (ilog2((_x))) /* port mask to channel */
+#define PORTNUM2CHAN(_x) ((_x) - 1) /* port number to channel */
+
+#define CXLFLASH_BLOCK_SIZE 4096 /* 4K blocks */
+#define CXLFLASH_MAX_XFER_SIZE 16777216 /* 16MB transfer */
+#define CXLFLASH_MAX_SECTORS (CXLFLASH_MAX_XFER_SIZE/512) /* SCSI wants
+ * max_sectors
+ * in units of
+ * 512 byte
+ * sectors
+ */
+
+#define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
+
+/* AFU command retry limit */
+#define MC_RETRY_CNT 5 /* Sufficient for SCSI and certain AFU errors */
+
+/* Command management definitions */
+#define CXLFLASH_MAX_CMDS 256
+#define CXLFLASH_MAX_CMDS_PER_LUN CXLFLASH_MAX_CMDS
+
+/* RRQ for master issued cmds */
+#define NUM_RRQ_ENTRY CXLFLASH_MAX_CMDS
+
+/* SQ for master issued cmds */
+#define NUM_SQ_ENTRY CXLFLASH_MAX_CMDS
+
+/* Hardware queue definitions */
+#define CXLFLASH_DEF_HWQS 1
+#define CXLFLASH_MAX_HWQS 8
+#define PRIMARY_HWQ 0
+
+
+static inline void check_sizes(void)
+{
+ BUILD_BUG_ON_NOT_POWER_OF_2(CXLFLASH_NUM_FC_PORTS_PER_BANK);
+ BUILD_BUG_ON_NOT_POWER_OF_2(CXLFLASH_MAX_CMDS);
+}
+
+/* AFU defines a fixed size of 4K for command buffers (borrow 4K page define) */
+#define CMD_BUFSIZE SIZE_4K
+
+enum cxlflash_lr_state {
+ LINK_RESET_INVALID,
+ LINK_RESET_REQUIRED,
+ LINK_RESET_COMPLETE
+};
+
+enum cxlflash_init_state {
+ INIT_STATE_NONE,
+ INIT_STATE_PCI,
+ INIT_STATE_AFU,
+ INIT_STATE_SCSI,
+ INIT_STATE_CDEV
+};
+
+enum cxlflash_state {
+ STATE_PROBING, /* Initial state during probe */
+ STATE_PROBED, /* Temporary state, probe completed but EEH occurred */
+ STATE_NORMAL, /* Normal running state, everything good */
+ STATE_RESET, /* Reset state, trying to reset/recover */
+ STATE_FAILTERM /* Failed/terminating state, error out users/threads */
+};
+
+enum cxlflash_hwq_mode {
+ HWQ_MODE_RR, /* Roundrobin (default) */
+ HWQ_MODE_TAG, /* Distribute based on block MQ tag */
+ HWQ_MODE_CPU, /* CPU affinity */
+ MAX_HWQ_MODE
+};
+
+/*
+ * Each context has its own set of resource handles that is visible
+ * only from that context.
+ */
+
+struct cxlflash_cfg {
+ struct afu *afu;
+
+ const struct cxlflash_backend_ops *ops;
+ struct pci_dev *dev;
+ struct pci_device_id *dev_id;
+ struct Scsi_Host *host;
+ int num_fc_ports;
+ struct cdev cdev;
+ struct device *chardev;
+
+ ulong cxlflash_regs_pci;
+
+ struct work_struct work_q;
+ enum cxlflash_init_state init_state;
+ enum cxlflash_lr_state lr_state;
+ int lr_port;
+ atomic_t scan_host_needed;
+
+ void *afu_cookie;
+
+ atomic_t recovery_threads;
+ struct mutex ctx_recovery_mutex;
+ struct mutex ctx_tbl_list_mutex;
+ struct rw_semaphore ioctl_rwsem;
+ struct ctx_info *ctx_tbl[MAX_CONTEXT];
+ struct list_head ctx_err_recovery; /* contexts w/ recovery pending */
+ struct file_operations cxl_fops;
+
+ /* Parameters that are LUN table related */
+ int last_lun_index[MAX_FC_PORTS];
+ int promote_lun_index;
+ struct list_head lluns; /* list of llun_info structs */
+
+ wait_queue_head_t tmf_waitq;
+ spinlock_t tmf_slock;
+ bool tmf_active;
+ bool ws_unmap; /* Write-same unmap supported */
+ wait_queue_head_t reset_waitq;
+ enum cxlflash_state state;
+ async_cookie_t async_reset_cookie;
+};
+
+struct afu_cmd {
+ struct sisl_ioarcb rcb; /* IOARCB (cache line aligned) */
+ struct sisl_ioasa sa; /* IOASA must follow IOARCB */
+ struct afu *parent;
+ struct scsi_cmnd *scp;
+ struct completion cevent;
+ struct list_head queue;
+ u32 hwq_index;
+
+ u8 cmd_tmf:1,
+ cmd_aborted:1;
+
+ struct list_head list; /* Pending commands link */
+
+ /* As per the SISLITE spec the IOARCB EA has to be 16-byte aligned.
+ * However for performance reasons the IOARCB/IOASA should be
+ * cache line aligned.
+ */
+} __aligned(cache_line_size());
+
+static inline struct afu_cmd *sc_to_afuc(struct scsi_cmnd *sc)
+{
+ return PTR_ALIGN(scsi_cmd_priv(sc), __alignof__(struct afu_cmd));
+}
+
+static inline struct afu_cmd *sc_to_afuci(struct scsi_cmnd *sc)
+{
+ struct afu_cmd *afuc = sc_to_afuc(sc);
+
+ INIT_LIST_HEAD(&afuc->queue);
+ return afuc;
+}
+
+static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
+{
+ struct afu_cmd *afuc = sc_to_afuc(sc);
+
+ memset(afuc, 0, sizeof(*afuc));
+ return sc_to_afuci(sc);
+}
+
+struct hwq {
+ /* Stuff requiring alignment go first. */
+ struct sisl_ioarcb sq[NUM_SQ_ENTRY]; /* 16K SQ */
+ u64 rrq_entry[NUM_RRQ_ENTRY]; /* 2K RRQ */
+
+ /* Beware of alignment till here. Preferably introduce new
+ * fields after this point
+ */
+ struct afu *afu;
+ void *ctx_cookie;
+ struct sisl_host_map __iomem *host_map; /* MC host map */
+ struct sisl_ctrl_map __iomem *ctrl_map; /* MC control map */
+ ctx_hndl_t ctx_hndl; /* master's context handle */
+ u32 index; /* Index of this hwq */
+ int num_irqs; /* Number of interrupts requested for context */
+ struct list_head pending_cmds; /* Commands pending completion */
+
+ atomic_t hsq_credits;
+ spinlock_t hsq_slock; /* Hardware send queue lock */
+ struct sisl_ioarcb *hsq_start;
+ struct sisl_ioarcb *hsq_end;
+ struct sisl_ioarcb *hsq_curr;
+ spinlock_t hrrq_slock;
+ u64 *hrrq_start;
+ u64 *hrrq_end;
+ u64 *hrrq_curr;
+ bool toggle;
+ bool hrrq_online;
+
+ s64 room;
+
+ struct irq_poll irqpoll;
+} __aligned(cache_line_size());
+
+struct afu {
+ struct hwq hwqs[CXLFLASH_MAX_HWQS];
+ int (*send_cmd)(struct afu *afu, struct afu_cmd *cmd);
+ int (*context_reset)(struct hwq *hwq);
+
+ /* AFU HW */
+ struct cxlflash_afu_map __iomem *afu_map; /* entire MMIO map */
+
+ atomic_t cmds_active; /* Number of currently active AFU commands */
+ struct mutex sync_active; /* Mutex to serialize AFU commands */
+ u64 hb;
+ u32 internal_lun; /* User-desired LUN mode for this AFU */
+
+ u32 num_hwqs; /* Number of hardware queues */
+ u32 desired_hwqs; /* Desired h/w queues, effective on AFU reset */
+ enum cxlflash_hwq_mode hwq_mode; /* Steering mode for h/w queues */
+ u32 hwq_rr_count; /* Count to distribute traffic for roundrobin */
+
+ char version[16];
+ u64 interface_version;
+
+ u32 irqpoll_weight;
+ struct cxlflash_cfg *parent; /* Pointer back to parent cxlflash_cfg */
+};
+
+static inline struct hwq *get_hwq(struct afu *afu, u32 index)
+{
+ WARN_ON(index >= CXLFLASH_MAX_HWQS);
+
+ return &afu->hwqs[index];
+}
+
+static inline bool afu_is_irqpoll_enabled(struct afu *afu)
+{
+ return !!afu->irqpoll_weight;
+}
+
+static inline bool afu_has_cap(struct afu *afu, u64 cap)
+{
+ u64 afu_cap = afu->interface_version >> SISL_INTVER_CAP_SHIFT;
+
+ return afu_cap & cap;
+}
+
+static inline bool afu_is_ocxl_lisn(struct afu *afu)
+{
+ return afu_has_cap(afu, SISL_INTVER_CAP_OCXL_LISN);
+}
+
+static inline bool afu_is_afu_debug(struct afu *afu)
+{
+ return afu_has_cap(afu, SISL_INTVER_CAP_AFU_DEBUG);
+}
+
+static inline bool afu_is_lun_provision(struct afu *afu)
+{
+ return afu_has_cap(afu, SISL_INTVER_CAP_LUN_PROVISION);
+}
+
+static inline bool afu_is_sq_cmd_mode(struct afu *afu)
+{
+ return afu_has_cap(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
+}
+
+static inline bool afu_is_ioarrin_cmd_mode(struct afu *afu)
+{
+ return afu_has_cap(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
+}
+
+static inline u64 lun_to_lunid(u64 lun)
+{
+ __be64 lun_id;
+
+ int_to_scsilun(lun, (struct scsi_lun *)&lun_id);
+ return be64_to_cpu(lun_id);
+}
+
+static inline struct fc_port_bank __iomem *get_fc_port_bank(
+ struct cxlflash_cfg *cfg, int i)
+{
+ struct afu *afu = cfg->afu;
+
+ return &afu->afu_map->global.bank[CHAN2PORTBANK(i)];
+}
+
+static inline __be64 __iomem *get_fc_port_regs(struct cxlflash_cfg *cfg, int i)
+{
+ struct fc_port_bank __iomem *fcpb = get_fc_port_bank(cfg, i);
+
+ return &fcpb->fc_port_regs[CHAN2BANKPORT(i)][0];
+}
+
+static inline __be64 __iomem *get_fc_port_luns(struct cxlflash_cfg *cfg, int i)
+{
+ struct fc_port_bank __iomem *fcpb = get_fc_port_bank(cfg, i);
+
+ return &fcpb->fc_port_luns[CHAN2BANKPORT(i)][0];
+}
+
+int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t c, res_hndl_t r, u8 mode);
+void cxlflash_list_init(void);
+void cxlflash_term_global_luns(void);
+void cxlflash_free_errpage(void);
+int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd,
+ void __user *arg);
+void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg);
+int cxlflash_mark_contexts_error(struct cxlflash_cfg *cfg);
+void cxlflash_term_local_luns(struct cxlflash_cfg *cfg);
+void cxlflash_restore_luntable(struct cxlflash_cfg *cfg);
+
+#endif /* ifndef _CXLFLASH_COMMON_H */