aboutsummaryrefslogtreecommitdiff
path: root/lib/logic_iomem.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /lib/logic_iomem.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'lib/logic_iomem.c')
-rw-r--r--lib/logic_iomem.c321
1 files changed, 321 insertions, 0 deletions
diff --git a/lib/logic_iomem.c b/lib/logic_iomem.c
new file mode 100644
index 000000000..b247d412d
--- /dev/null
+++ b/lib/logic_iomem.c
@@ -0,0 +1,321 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Intel Corporation
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/logic_iomem.h>
+#include <asm/io.h>
+
+struct logic_iomem_region {
+ const struct resource *res;
+ const struct logic_iomem_region_ops *ops;
+ struct list_head list;
+};
+
+struct logic_iomem_area {
+ const struct logic_iomem_ops *ops;
+ void *priv;
+};
+
+#define AREA_SHIFT 24
+#define MAX_AREA_SIZE (1 << AREA_SHIFT)
+#define MAX_AREAS ((1U << 31) / MAX_AREA_SIZE)
+#define AREA_BITS ((MAX_AREAS - 1) << AREA_SHIFT)
+#define AREA_MASK (MAX_AREA_SIZE - 1)
+#ifdef CONFIG_64BIT
+#define IOREMAP_BIAS 0xDEAD000000000000UL
+#define IOREMAP_MASK 0xFFFFFFFF00000000UL
+#else
+#define IOREMAP_BIAS 0x80000000UL
+#define IOREMAP_MASK 0x80000000UL
+#endif
+
+static DEFINE_MUTEX(regions_mtx);
+static LIST_HEAD(regions_list);
+static struct logic_iomem_area mapped_areas[MAX_AREAS];
+
+int logic_iomem_add_region(struct resource *resource,
+ const struct logic_iomem_region_ops *ops)
+{
+ struct logic_iomem_region *rreg;
+ int err;
+
+ if (WARN_ON(!resource || !ops))
+ return -EINVAL;
+
+ if (WARN_ON((resource->flags & IORESOURCE_TYPE_BITS) != IORESOURCE_MEM))
+ return -EINVAL;
+
+ rreg = kzalloc(sizeof(*rreg), GFP_KERNEL);
+ if (!rreg)
+ return -ENOMEM;
+
+ err = request_resource(&iomem_resource, resource);
+ if (err) {
+ kfree(rreg);
+ return -ENOMEM;
+ }
+
+ mutex_lock(&regions_mtx);
+ rreg->res = resource;
+ rreg->ops = ops;
+ list_add_tail(&rreg->list, &regions_list);
+ mutex_unlock(&regions_mtx);
+
+ return 0;
+}
+EXPORT_SYMBOL(logic_iomem_add_region);
+
+#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK
+static void __iomem *real_ioremap(phys_addr_t offset, size_t size)
+{
+ WARN(1, "invalid ioremap(0x%llx, 0x%zx)\n",
+ (unsigned long long)offset, size);
+ return NULL;
+}
+
+static void real_iounmap(volatile void __iomem *addr)
+{
+ WARN(1, "invalid iounmap for addr 0x%llx\n",
+ (unsigned long long)(uintptr_t __force)addr);
+}
+#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */
+
+void __iomem *ioremap(phys_addr_t offset, size_t size)
+{
+ void __iomem *ret = NULL;
+ struct logic_iomem_region *rreg, *found = NULL;
+ int i;
+
+ mutex_lock(&regions_mtx);
+ list_for_each_entry(rreg, &regions_list, list) {
+ if (rreg->res->start > offset)
+ continue;
+ if (rreg->res->end < offset + size - 1)
+ continue;
+ found = rreg;
+ break;
+ }
+
+ if (!found)
+ goto out;
+
+ for (i = 0; i < MAX_AREAS; i++) {
+ long offs;
+
+ if (mapped_areas[i].ops)
+ continue;
+
+ offs = rreg->ops->map(offset - found->res->start,
+ size, &mapped_areas[i].ops,
+ &mapped_areas[i].priv);
+ if (offs < 0) {
+ mapped_areas[i].ops = NULL;
+ break;
+ }
+
+ if (WARN_ON(!mapped_areas[i].ops)) {
+ mapped_areas[i].ops = NULL;
+ break;
+ }
+
+ ret = (void __iomem *)(IOREMAP_BIAS + (i << AREA_SHIFT) + offs);
+ break;
+ }
+out:
+ mutex_unlock(&regions_mtx);
+ if (ret)
+ return ret;
+ return real_ioremap(offset, size);
+}
+EXPORT_SYMBOL(ioremap);
+
+static inline struct logic_iomem_area *
+get_area(const volatile void __iomem *addr)
+{
+ unsigned long a = (unsigned long)addr;
+ unsigned int idx;
+
+ if (WARN_ON((a & IOREMAP_MASK) != IOREMAP_BIAS))
+ return NULL;
+
+ idx = (a & AREA_BITS) >> AREA_SHIFT;
+
+ if (mapped_areas[idx].ops)
+ return &mapped_areas[idx];
+
+ return NULL;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+ struct logic_iomem_area *area = get_area(addr);
+
+ if (!area) {
+ real_iounmap(addr);
+ return;
+ }
+
+ if (area->ops->unmap)
+ area->ops->unmap(area->priv);
+
+ mutex_lock(&regions_mtx);
+ area->ops = NULL;
+ area->priv = NULL;
+ mutex_unlock(&regions_mtx);
+}
+EXPORT_SYMBOL(iounmap);
+
+#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK
+#define MAKE_FALLBACK(op, sz) \
+static u##sz real_raw_read ## op(const volatile void __iomem *addr) \
+{ \
+ WARN(1, "Invalid read" #op " at address %llx\n", \
+ (unsigned long long)(uintptr_t __force)addr); \
+ return (u ## sz)~0ULL; \
+} \
+ \
+static void real_raw_write ## op(u ## sz val, \
+ volatile void __iomem *addr) \
+{ \
+ WARN(1, "Invalid writeq" #op " of 0x%llx at address %llx\n", \
+ (unsigned long long)val, \
+ (unsigned long long)(uintptr_t __force)addr);\
+} \
+
+MAKE_FALLBACK(b, 8);
+MAKE_FALLBACK(w, 16);
+MAKE_FALLBACK(l, 32);
+#ifdef CONFIG_64BIT
+MAKE_FALLBACK(q, 64);
+#endif
+
+static void real_memset_io(volatile void __iomem *addr, int value, size_t size)
+{
+ WARN(1, "Invalid memset_io at address 0x%llx\n",
+ (unsigned long long)(uintptr_t __force)addr);
+}
+
+static void real_memcpy_fromio(void *buffer, const volatile void __iomem *addr,
+ size_t size)
+{
+ WARN(1, "Invalid memcpy_fromio at address 0x%llx\n",
+ (unsigned long long)(uintptr_t __force)addr);
+
+ memset(buffer, 0xff, size);
+}
+
+static void real_memcpy_toio(volatile void __iomem *addr, const void *buffer,
+ size_t size)
+{
+ WARN(1, "Invalid memcpy_toio at address 0x%llx\n",
+ (unsigned long long)(uintptr_t __force)addr);
+}
+#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */
+
+#define MAKE_OP(op, sz) \
+u##sz __raw_read ## op(const volatile void __iomem *addr) \
+{ \
+ struct logic_iomem_area *area = get_area(addr); \
+ \
+ if (!area) \
+ return real_raw_read ## op(addr); \
+ \
+ return (u ## sz) area->ops->read(area->priv, \
+ (unsigned long)addr & AREA_MASK,\
+ sz / 8); \
+} \
+EXPORT_SYMBOL(__raw_read ## op); \
+ \
+void __raw_write ## op(u ## sz val, volatile void __iomem *addr) \
+{ \
+ struct logic_iomem_area *area = get_area(addr); \
+ \
+ if (!area) { \
+ real_raw_write ## op(val, addr); \
+ return; \
+ } \
+ \
+ area->ops->write(area->priv, \
+ (unsigned long)addr & AREA_MASK, \
+ sz / 8, val); \
+} \
+EXPORT_SYMBOL(__raw_write ## op)
+
+MAKE_OP(b, 8);
+MAKE_OP(w, 16);
+MAKE_OP(l, 32);
+#ifdef CONFIG_64BIT
+MAKE_OP(q, 64);
+#endif
+
+void memset_io(volatile void __iomem *addr, int value, size_t size)
+{
+ struct logic_iomem_area *area = get_area(addr);
+ unsigned long offs, start;
+
+ if (!area) {
+ real_memset_io(addr, value, size);
+ return;
+ }
+
+ start = (unsigned long)addr & AREA_MASK;
+
+ if (area->ops->set) {
+ area->ops->set(area->priv, start, value, size);
+ return;
+ }
+
+ for (offs = 0; offs < size; offs++)
+ area->ops->write(area->priv, start + offs, 1, value);
+}
+EXPORT_SYMBOL(memset_io);
+
+void memcpy_fromio(void *buffer, const volatile void __iomem *addr,
+ size_t size)
+{
+ struct logic_iomem_area *area = get_area(addr);
+ u8 *buf = buffer;
+ unsigned long offs, start;
+
+ if (!area) {
+ real_memcpy_fromio(buffer, addr, size);
+ return;
+ }
+
+ start = (unsigned long)addr & AREA_MASK;
+
+ if (area->ops->copy_from) {
+ area->ops->copy_from(area->priv, buffer, start, size);
+ return;
+ }
+
+ for (offs = 0; offs < size; offs++)
+ buf[offs] = area->ops->read(area->priv, start + offs, 1);
+}
+EXPORT_SYMBOL(memcpy_fromio);
+
+void memcpy_toio(volatile void __iomem *addr, const void *buffer, size_t size)
+{
+ struct logic_iomem_area *area = get_area(addr);
+ const u8 *buf = buffer;
+ unsigned long offs, start;
+
+ if (!area) {
+ real_memcpy_toio(addr, buffer, size);
+ return;
+ }
+
+ start = (unsigned long)addr & AREA_MASK;
+
+ if (area->ops->copy_to) {
+ area->ops->copy_to(area->priv, start, buffer, size);
+ return;
+ }
+
+ for (offs = 0; offs < size; offs++)
+ area->ops->write(area->priv, start + offs, 1, buf[offs]);
+}
+EXPORT_SYMBOL(memcpy_toio);