aboutsummaryrefslogtreecommitdiff
path: root/drivers/misc/habanalabs/common/memory_mgr.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 /drivers/misc/habanalabs/common/memory_mgr.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 'drivers/misc/habanalabs/common/memory_mgr.c')
-rw-r--r--drivers/misc/habanalabs/common/memory_mgr.c349
1 files changed, 349 insertions, 0 deletions
diff --git a/drivers/misc/habanalabs/common/memory_mgr.c b/drivers/misc/habanalabs/common/memory_mgr.c
new file mode 100644
index 000000000..1936d6536
--- /dev/null
+++ b/drivers/misc/habanalabs/common/memory_mgr.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2022 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+/**
+ * hl_mmap_mem_buf_get - increase the buffer refcount and return a pointer to
+ * the buffer descriptor.
+ *
+ * @mmg: parent unified memory manager
+ * @handle: requested buffer handle
+ *
+ * Find the buffer in the store and return a pointer to its descriptor.
+ * Increase buffer refcount. If not found - return NULL.
+ */
+struct hl_mmap_mem_buf *hl_mmap_mem_buf_get(struct hl_mem_mgr *mmg, u64 handle)
+{
+ struct hl_mmap_mem_buf *buf;
+
+ spin_lock(&mmg->lock);
+ buf = idr_find(&mmg->handles, lower_32_bits(handle >> PAGE_SHIFT));
+ if (!buf) {
+ spin_unlock(&mmg->lock);
+ dev_warn(mmg->dev,
+ "Buff get failed, no match to handle %#llx\n", handle);
+ return NULL;
+ }
+ kref_get(&buf->refcount);
+ spin_unlock(&mmg->lock);
+ return buf;
+}
+
+/**
+ * hl_mmap_mem_buf_destroy - destroy the unused buffer
+ *
+ * @buf: memory manager buffer descriptor
+ *
+ * Internal function, used as a final step of buffer release. Shall be invoked
+ * only when the buffer is no longer in use (removed from idr). Will call the
+ * release callback (if applicable), and free the memory.
+ */
+static void hl_mmap_mem_buf_destroy(struct hl_mmap_mem_buf *buf)
+{
+ if (buf->behavior->release)
+ buf->behavior->release(buf);
+
+ kfree(buf);
+}
+
+/**
+ * hl_mmap_mem_buf_release - release buffer
+ *
+ * @kref: kref that reached 0.
+ *
+ * Internal function, used as a kref release callback, when the last user of
+ * the buffer is released. Shall be called from an interrupt context.
+ */
+static void hl_mmap_mem_buf_release(struct kref *kref)
+{
+ struct hl_mmap_mem_buf *buf =
+ container_of(kref, struct hl_mmap_mem_buf, refcount);
+
+ spin_lock(&buf->mmg->lock);
+ idr_remove(&buf->mmg->handles, lower_32_bits(buf->handle >> PAGE_SHIFT));
+ spin_unlock(&buf->mmg->lock);
+
+ hl_mmap_mem_buf_destroy(buf);
+}
+
+/**
+ * hl_mmap_mem_buf_remove_idr_locked - remove handle from idr
+ *
+ * @kref: kref that reached 0.
+ *
+ * Internal function, used for kref put by handle. Assumes mmg lock is taken.
+ * Will remove the buffer from idr, without destroying it.
+ */
+static void hl_mmap_mem_buf_remove_idr_locked(struct kref *kref)
+{
+ struct hl_mmap_mem_buf *buf =
+ container_of(kref, struct hl_mmap_mem_buf, refcount);
+
+ idr_remove(&buf->mmg->handles, lower_32_bits(buf->handle >> PAGE_SHIFT));
+}
+
+/**
+ * hl_mmap_mem_buf_put - decrease the reference to the buffer
+ *
+ * @buf: memory manager buffer descriptor
+ *
+ * Decrease the reference to the buffer, and release it if it was the last one.
+ * Shall be called from an interrupt context.
+ */
+int hl_mmap_mem_buf_put(struct hl_mmap_mem_buf *buf)
+{
+ return kref_put(&buf->refcount, hl_mmap_mem_buf_release);
+}
+
+/**
+ * hl_mmap_mem_buf_put_handle - decrease the reference to the buffer with the
+ * given handle.
+ *
+ * @mmg: parent unified memory manager
+ * @handle: requested buffer handle
+ *
+ * Decrease the reference to the buffer, and release it if it was the last one.
+ * Shall not be called from an interrupt context. Return -EINVAL if handle was
+ * not found, else return the put outcome (0 or 1).
+ */
+int hl_mmap_mem_buf_put_handle(struct hl_mem_mgr *mmg, u64 handle)
+{
+ struct hl_mmap_mem_buf *buf;
+
+ spin_lock(&mmg->lock);
+ buf = idr_find(&mmg->handles, lower_32_bits(handle >> PAGE_SHIFT));
+ if (!buf) {
+ spin_unlock(&mmg->lock);
+ dev_dbg(mmg->dev,
+ "Buff put failed, no match to handle %#llx\n", handle);
+ return -EINVAL;
+ }
+
+ if (kref_put(&buf->refcount, hl_mmap_mem_buf_remove_idr_locked)) {
+ spin_unlock(&mmg->lock);
+ hl_mmap_mem_buf_destroy(buf);
+ return 1;
+ }
+
+ spin_unlock(&mmg->lock);
+ return 0;
+}
+
+/**
+ * hl_mmap_mem_buf_alloc - allocate a new mappable buffer
+ *
+ * @mmg: parent unified memory manager
+ * @behavior: behavior object describing this buffer polymorphic behavior
+ * @gfp: gfp flags to use for the memory allocations
+ * @args: additional args passed to behavior->alloc
+ *
+ * Allocate and register a new memory buffer inside the give memory manager.
+ * Return the pointer to the new buffer on success or NULL on failure.
+ */
+struct hl_mmap_mem_buf *
+hl_mmap_mem_buf_alloc(struct hl_mem_mgr *mmg,
+ struct hl_mmap_mem_buf_behavior *behavior, gfp_t gfp,
+ void *args)
+{
+ struct hl_mmap_mem_buf *buf;
+ int rc;
+
+ buf = kzalloc(sizeof(*buf), gfp);
+ if (!buf)
+ return NULL;
+
+ spin_lock(&mmg->lock);
+ rc = idr_alloc(&mmg->handles, buf, 1, 0, GFP_ATOMIC);
+ spin_unlock(&mmg->lock);
+ if (rc < 0) {
+ dev_err(mmg->dev,
+ "%s: Failed to allocate IDR for a new buffer, rc=%d\n",
+ behavior->topic, rc);
+ goto free_buf;
+ }
+
+ buf->mmg = mmg;
+ buf->behavior = behavior;
+ buf->handle = (((u64)rc | buf->behavior->mem_id) << PAGE_SHIFT);
+ kref_init(&buf->refcount);
+
+ rc = buf->behavior->alloc(buf, gfp, args);
+ if (rc) {
+ dev_err(mmg->dev, "%s: Failure in buffer alloc callback %d\n",
+ behavior->topic, rc);
+ goto remove_idr;
+ }
+
+ return buf;
+
+remove_idr:
+ spin_lock(&mmg->lock);
+ idr_remove(&mmg->handles, lower_32_bits(buf->handle >> PAGE_SHIFT));
+ spin_unlock(&mmg->lock);
+free_buf:
+ kfree(buf);
+ return NULL;
+}
+
+/**
+ * hl_mmap_mem_buf_vm_close - handle mmap close
+ *
+ * @vma: the vma object for which mmap was closed.
+ *
+ * Put the memory buffer if it is no longer mapped.
+ */
+static void hl_mmap_mem_buf_vm_close(struct vm_area_struct *vma)
+{
+ struct hl_mmap_mem_buf *buf =
+ (struct hl_mmap_mem_buf *)vma->vm_private_data;
+ long new_mmap_size;
+
+ new_mmap_size = buf->real_mapped_size - (vma->vm_end - vma->vm_start);
+
+ if (new_mmap_size > 0) {
+ buf->real_mapped_size = new_mmap_size;
+ return;
+ }
+
+ atomic_set(&buf->mmap, 0);
+ hl_mmap_mem_buf_put(buf);
+ vma->vm_private_data = NULL;
+}
+
+static const struct vm_operations_struct hl_mmap_mem_buf_vm_ops = {
+ .close = hl_mmap_mem_buf_vm_close
+};
+
+/**
+ * hl_mem_mgr_mmap - map the given buffer to the user
+ *
+ * @mmg: unified memory manager
+ * @vma: the vma object for which mmap was closed.
+ * @args: additional args passed to behavior->mmap
+ *
+ * Map the buffer specified by the vma->vm_pgoff to the given vma.
+ */
+int hl_mem_mgr_mmap(struct hl_mem_mgr *mmg, struct vm_area_struct *vma,
+ void *args)
+{
+ struct hl_mmap_mem_buf *buf;
+ u64 user_mem_size;
+ u64 handle;
+ int rc;
+
+ /* We use the page offset to hold the idr and thus we need to clear
+ * it before doing the mmap itself
+ */
+ handle = vma->vm_pgoff << PAGE_SHIFT;
+ vma->vm_pgoff = 0;
+
+ /* Reference was taken here */
+ buf = hl_mmap_mem_buf_get(mmg, handle);
+ if (!buf) {
+ dev_err(mmg->dev,
+ "Memory mmap failed, no match to handle %#llx\n", handle);
+ return -EINVAL;
+ }
+
+ /* Validation check */
+ user_mem_size = vma->vm_end - vma->vm_start;
+ if (user_mem_size != ALIGN(buf->mappable_size, PAGE_SIZE)) {
+ dev_err(mmg->dev,
+ "%s: Memory mmap failed, mmap VM size 0x%llx != 0x%llx allocated physical mem size\n",
+ buf->behavior->topic, user_mem_size, buf->mappable_size);
+ rc = -EINVAL;
+ goto put_mem;
+ }
+
+#ifdef _HAS_TYPE_ARG_IN_ACCESS_OK
+ if (!access_ok(VERIFY_WRITE, (void __user *)(uintptr_t)vma->vm_start,
+ user_mem_size)) {
+#else
+ if (!access_ok((void __user *)(uintptr_t)vma->vm_start,
+ user_mem_size)) {
+#endif
+ dev_err(mmg->dev, "%s: User pointer is invalid - 0x%lx\n",
+ buf->behavior->topic, vma->vm_start);
+
+ rc = -EINVAL;
+ goto put_mem;
+ }
+
+ if (atomic_cmpxchg(&buf->mmap, 0, 1)) {
+ dev_err(mmg->dev,
+ "%s, Memory mmap failed, already mmaped to user\n",
+ buf->behavior->topic);
+ rc = -EINVAL;
+ goto put_mem;
+ }
+
+ vma->vm_ops = &hl_mmap_mem_buf_vm_ops;
+
+ /* Note: We're transferring the memory reference to vma->vm_private_data here. */
+
+ vma->vm_private_data = buf;
+
+ rc = buf->behavior->mmap(buf, vma, args);
+ if (rc) {
+ atomic_set(&buf->mmap, 0);
+ goto put_mem;
+ }
+
+ buf->real_mapped_size = buf->mappable_size;
+ vma->vm_pgoff = handle >> PAGE_SHIFT;
+
+ return 0;
+
+put_mem:
+ hl_mmap_mem_buf_put(buf);
+ return rc;
+}
+
+/**
+ * hl_mem_mgr_init - initialize unified memory manager
+ *
+ * @dev: owner device pointer
+ * @mmg: structure to initialize
+ *
+ * Initialize an instance of unified memory manager
+ */
+void hl_mem_mgr_init(struct device *dev, struct hl_mem_mgr *mmg)
+{
+ mmg->dev = dev;
+ spin_lock_init(&mmg->lock);
+ idr_init(&mmg->handles);
+}
+
+/**
+ * hl_mem_mgr_fini - release unified memory manager
+ *
+ * @mmg: parent unified memory manager
+ *
+ * Release the unified memory manager. Shall be called from an interrupt context.
+ */
+void hl_mem_mgr_fini(struct hl_mem_mgr *mmg)
+{
+ struct hl_mmap_mem_buf *buf;
+ struct idr *idp;
+ const char *topic;
+ u32 id;
+
+ idp = &mmg->handles;
+
+ idr_for_each_entry(idp, buf, id) {
+ topic = buf->behavior->topic;
+ if (hl_mmap_mem_buf_put(buf) != 1)
+ dev_err(mmg->dev,
+ "%s: Buff handle %u for CTX is still alive\n",
+ topic, id);
+ }
+
+ /* TODO: can it happen that some buffer is still in use at this point? */
+
+ idr_destroy(&mmg->handles);
+}