Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 316 insertions, 0 deletions

diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h
new file mode 100644
index 000000000..0e736846c
--- /dev/null
+++ b/include/net/libeth/rx.h
@@ -0,0 +1,316 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024-2025 Intel Corporation */
+
+#ifndef __LIBETH_RX_H
+#define __LIBETH_RX_H
+
+#include <linux/if_vlan.h>
+
+#include <net/page_pool/helpers.h>
+#include <net/xdp.h>
+
+/* Rx buffer management */
+
+/* Space reserved in front of each frame */
+#define LIBETH_SKB_HEADROOM	(NET_SKB_PAD + NET_IP_ALIGN)
+#define LIBETH_XDP_HEADROOM	(ALIGN(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
+				 NET_IP_ALIGN)
+/* Maximum headroom for worst-case calculations */
+#define LIBETH_MAX_HEADROOM	LIBETH_XDP_HEADROOM
+/* Link layer / L2 overhead: Ethernet, 2 VLAN tags (C + S), FCS */
+#define LIBETH_RX_LL_LEN	(ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN)
+/* Maximum supported L2-L4 header length */
+#define LIBETH_MAX_HEAD		roundup_pow_of_two(max(MAX_HEADER, 256))
+
+/* Always use order-0 pages */
+#define LIBETH_RX_PAGE_ORDER	0
+/* Pick a sane buffer stride and align to a cacheline boundary */
+#define LIBETH_RX_BUF_STRIDE	SKB_DATA_ALIGN(128)
+/* HW-writeable space in one buffer: truesize - headroom/tailroom, aligned */
+#define LIBETH_RX_PAGE_LEN(hr)						  \
+	ALIGN_DOWN(SKB_MAX_ORDER(hr, LIBETH_RX_PAGE_ORDER),		  \
+		   LIBETH_RX_BUF_STRIDE)
+
+/**
+ * struct libeth_fqe - structure representing an Rx buffer (fill queue element)
+ * @netmem: network memory reference holding the buffer
+ * @offset: offset from the page start (to the headroom)
+ * @truesize: total space occupied by the buffer (w/ headroom and tailroom)
+ *
+ * Depending on the MTU, API switches between one-page-per-frame and shared
+ * page model (to conserve memory on bigger-page platforms). In case of the
+ * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```.
+ */
+struct libeth_fqe {
+	netmem_ref		netmem;
+	u32			offset;
+	u32			truesize;
+} __aligned_largest;
+
+/**
+ * enum libeth_fqe_type - enum representing types of Rx buffers
+ * @LIBETH_FQE_MTU: buffer size is determined by MTU
+ * @LIBETH_FQE_SHORT: buffer size is smaller than MTU, for short frames
+ * @LIBETH_FQE_HDR: buffer size is ```LIBETH_MAX_HEAD```-sized, for headers
+ */
+enum libeth_fqe_type {
+	LIBETH_FQE_MTU		= 0U,
+	LIBETH_FQE_SHORT,
+	LIBETH_FQE_HDR,
+};
+
+/**
+ * struct libeth_fq - structure representing a buffer (fill) queue
+ * @fp: hotpath part of the structure
+ * @pp: &page_pool for buffer management
+ * @fqes: array of Rx buffers
+ * @truesize: size to allocate per buffer, w/overhead
+ * @count: number of descriptors/buffers the queue has
+ * @type: type of the buffers this queue has
+ * @hsplit: flag whether header split is enabled
+ * @xdp: flag indicating whether XDP is enabled
+ * @no_napi: the queue is not a data queue and does not have NAPI
+ * @buf_len: HW-writeable length per each buffer
+ * @nid: ID of the closest NUMA node with memory
+ */
+struct libeth_fq {
+	struct_group_tagged(libeth_fq_fp, fp,
+		struct page_pool	*pp;
+		struct libeth_fqe	*fqes;
+
+		u32			truesize;
+		u32			count;
+	);
+
+	/* Cold fields */
+	enum libeth_fqe_type	type:2;
+	bool			hsplit:1;
+	bool			xdp:1;
+	bool			no_napi:1;
+
+	u32			buf_len;
+	int			nid;
+};
+
+int libeth_rx_fq_create(struct libeth_fq *fq, void *napi_dev);
+void libeth_rx_fq_destroy(struct libeth_fq *fq);
+
+/**
+ * libeth_rx_alloc - allocate a new Rx buffer
+ * @fq: fill queue to allocate for
+ * @i: index of the buffer within the queue
+ *
+ * Return: DMA address to be passed to HW for Rx on successful allocation,
+ * ```DMA_MAPPING_ERROR``` otherwise.
+ */
+static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i)
+{
+	struct libeth_fqe *buf = &fq->fqes[i];
+
+	buf->truesize = fq->truesize;
+	buf->netmem = page_pool_dev_alloc_netmem(fq->pp, &buf->offset,
+						 &buf->truesize);
+	if (unlikely(!buf->netmem))
+		return DMA_MAPPING_ERROR;
+
+	return page_pool_get_dma_addr_netmem(buf->netmem) + buf->offset +
+	       fq->pp->p.offset;
+}
+
+void libeth_rx_recycle_slow(netmem_ref netmem);
+
+/**
+ * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
+ * @fqe: buffer to process
+ * @len: frame length from the descriptor
+ *
+ * Process the buffer after it's written by HW. The regular path is to
+ * synchronize DMA for CPU, but in case of no data it will be immediately
+ * recycled back to its PP.
+ *
+ * Return: true when there's data to process, false otherwise.
+ */
+static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe,
+					  u32 len)
+{
+	netmem_ref netmem = fqe->netmem;
+
+	/* Very rare, but possible case. The most common reason:
+	 * the last fragment contained FCS only, which was then
+	 * stripped by the HW.
+	 */
+	if (unlikely(!len)) {
+		libeth_rx_recycle_slow(netmem);
+		return false;
+	}
+
+	page_pool_dma_sync_netmem_for_cpu(netmem_get_pp(netmem), netmem,
+					  fqe->offset, len);
+
+	return true;
+}
+
+/* Converting abstract packet type numbers into a software structure with
+ * the packet parameters to do O(1) lookup on Rx.
+ */
+
+enum {
+	LIBETH_RX_PT_OUTER_L2			= 0U,
+	LIBETH_RX_PT_OUTER_IPV4,
+	LIBETH_RX_PT_OUTER_IPV6,
+};
+
+enum {
+	LIBETH_RX_PT_NOT_FRAG			= 0U,
+	LIBETH_RX_PT_FRAG,
+};
+
+enum {
+	LIBETH_RX_PT_TUNNEL_IP_NONE		= 0U,
+	LIBETH_RX_PT_TUNNEL_IP_IP,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC_VLAN,
+};
+
+enum {
+	LIBETH_RX_PT_TUNNEL_END_NONE		= 0U,
+	LIBETH_RX_PT_TUNNEL_END_IPV4,
+	LIBETH_RX_PT_TUNNEL_END_IPV6,
+};
+
+enum {
+	LIBETH_RX_PT_INNER_NONE			= 0U,
+	LIBETH_RX_PT_INNER_UDP,
+	LIBETH_RX_PT_INNER_TCP,
+	LIBETH_RX_PT_INNER_SCTP,
+	LIBETH_RX_PT_INNER_ICMP,
+	LIBETH_RX_PT_INNER_TIMESYNC,
+};
+
+#define LIBETH_RX_PT_PAYLOAD_NONE		PKT_HASH_TYPE_NONE
+#define LIBETH_RX_PT_PAYLOAD_L2			PKT_HASH_TYPE_L2
+#define LIBETH_RX_PT_PAYLOAD_L3			PKT_HASH_TYPE_L3
+#define LIBETH_RX_PT_PAYLOAD_L4			PKT_HASH_TYPE_L4
+
+struct libeth_rx_pt {
+	u32					outer_ip:2;
+	u32					outer_frag:1;
+	u32					tunnel_type:3;
+	u32					tunnel_end_prot:2;
+	u32					tunnel_end_frag:1;
+	u32					inner_prot:3;
+	enum pkt_hash_types			payload_layer:2;
+
+	u32					pad:2;
+	enum xdp_rss_hash_type			hash_type:16;
+};
+
+/**
+ * struct libeth_rx_csum - checksum offload bits decoded from the Rx descriptor
+ * @l3l4p: detectable L3 and L4 integrity check is processed by the hardware
+ * @ipe: IP checksum error
+ * @eipe: external (outermost) IP header (only for tunels)
+ * @eudpe: external (outermost) UDP checksum error (only for tunels)
+ * @ipv6exadd: IPv6 header with extension headers
+ * @l4e: L4 integrity error
+ * @pprs: set for packets that skip checksum calculation in the HW pre parser
+ * @nat: the packet is a UDP tunneled packet
+ * @raw_csum_valid: set if raw checksum is valid
+ * @pad: padding to naturally align raw_csum field
+ * @raw_csum: raw checksum
+ */
+struct libeth_rx_csum {
+	u32					l3l4p:1;
+	u32					ipe:1;
+	u32					eipe:1;
+	u32					eudpe:1;
+	u32					ipv6exadd:1;
+	u32					l4e:1;
+	u32					pprs:1;
+	u32					nat:1;
+
+	u32					raw_csum_valid:1;
+	u32					pad:7;
+	u32					raw_csum:16;
+};
+
+/**
+ * struct libeth_rqe_info - receive queue element info
+ * @len: packet length
+ * @ptype: packet type based on types programmed into the device
+ * @eop: whether it's the last fragment of the packet
+ * @rxe: MAC errors: CRC, Alignment, Oversize, Undersizes, Length error
+ * @vlan: C-VLAN or S-VLAN tag depending on the VLAN offload configuration
+ */
+struct libeth_rqe_info {
+	u32					len;
+
+	u32					ptype:14;
+	u32					eop:1;
+	u32					rxe:1;
+
+	u32					vlan:16;
+};
+
+void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt);
+
+/**
+ * libeth_rx_pt_get_ip_ver - get IP version from a packet type structure
+ * @pt: packet type params
+ *
+ * Wrapper to compile out the IPv6 code from the drivers when not supported
+ * by the kernel.
+ *
+ * Return: @pt.outer_ip or stub for IPv6 when not compiled-in.
+ */
+static inline u32 libeth_rx_pt_get_ip_ver(struct libeth_rx_pt pt)
+{
+#if !IS_ENABLED(CONFIG_IPV6)
+	switch (pt.outer_ip) {
+	case LIBETH_RX_PT_OUTER_IPV4:
+		return LIBETH_RX_PT_OUTER_IPV4;
+	default:
+		return LIBETH_RX_PT_OUTER_L2;
+	}
+#else
+	return pt.outer_ip;
+#endif
+}
+
+/* libeth_has_*() can be used to quickly check whether the HW metadata is
+ * available to avoid further expensive processing such as descriptor reads.
+ * They already check for the corresponding netdev feature to be enabled,
+ * thus can be used as drop-in replacements.
+ */
+
+static inline bool libeth_rx_pt_has_checksum(const struct net_device *dev,
+					     struct libeth_rx_pt pt)
+{
+	/* Non-zero _INNER* is only possible when _OUTER_IPV* is set,
+	 * it is enough to check only for the L4 type.
+	 */
+	return likely(pt.inner_prot > LIBETH_RX_PT_INNER_NONE &&
+		      (dev->features & NETIF_F_RXCSUM));
+}
+
+static inline bool libeth_rx_pt_has_hash(const struct net_device *dev,
+					 struct libeth_rx_pt pt)
+{
+	return likely(pt.payload_layer > LIBETH_RX_PT_PAYLOAD_NONE &&
+		      (dev->features & NETIF_F_RXHASH));
+}
+
+/**
+ * libeth_rx_pt_set_hash - fill in skb hash value basing on the PT
+ * @skb: skb to fill the hash in
+ * @hash: 32-bit hash value from the descriptor
+ * @pt: packet type
+ */
+static inline void libeth_rx_pt_set_hash(struct sk_buff *skb, u32 hash,
+					 struct libeth_rx_pt pt)
+{
+	skb_set_hash(skb, hash, pt.payload_layer);
+}
+
+#endif /* __LIBETH_RX_H */