Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

5 files changed, 730 insertions, 0 deletions

diff --git a/drivers/dibs/Kconfig b/drivers/dibs/Kconfig
new file mode 100644
index 000000000..8f41e5622
--- /dev/null
+++ b/drivers/dibs/Kconfig
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0
+config DIBS
+	tristate "Direct Internal Buffer Sharing support"
+	default n
+	help
+	  Direct Internal Buffer Sharing (DIBS) is a communication method that
+	  uses common physical (internal) memory for synchronous direct access
+	  into a remote buffer.
+
+	  Select this option to provide the abstraction layer between
+	  dibs devices and dibs clients like the SMC protocol.
+	  The module name is dibs.
+
+config DIBS_LO
+	bool "Intra-OS shortcut with dibs loopback"
+	depends on DIBS
+	default n
+	help
+	  DIBS_LO enables the creation of an software-emulated dibs device
+	  named lo which can be used for transferring data when communication
+	  occurs within the same OS. This helps in convenient testing of
+	  dibs clients, since dibs loopback is independent of architecture or
+	  hardware.
diff --git a/drivers/dibs/Makefile b/drivers/dibs/Makefile
new file mode 100644
index 000000000..85805490c
--- /dev/null
+++ b/drivers/dibs/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# DIBS class module
+#
+
+dibs-y += dibs_main.o
+obj-$(CONFIG_DIBS) += dibs.o
+dibs-$(CONFIG_DIBS_LO) += dibs_loopback.o
\ No newline at end of file
diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c
new file mode 100644
index 000000000..649e4e375
--- /dev/null
+++ b/drivers/dibs/dibs_loopback.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Functions for dibs loopback/loopback-ism device.
+ *
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: Wen Gu <guwen@linux.alibaba.com>
+ *          Tony Lu <tonylu@linux.alibaba.com>
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/dibs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "dibs_loopback.h"
+
+#define DIBS_LO_SUPPORT_NOCOPY	0x1
+#define DIBS_DMA_ADDR_INVALID	(~(dma_addr_t)0)
+
+static const char dibs_lo_dev_name[] = "lo";
+/* global loopback device */
+static struct dibs_lo_dev *lo_dev;
+
+static u16 dibs_lo_get_fabric_id(struct dibs_dev *dibs)
+{
+	return DIBS_LOOPBACK_FABRIC;
+}
+
+static int dibs_lo_query_rgid(struct dibs_dev *dibs, const uuid_t *rgid,
+			      u32 vid_valid, u32 vid)
+{
+	/* rgid should be the same as lgid */
+	if (!uuid_equal(rgid, &dibs->gid))
+		return -ENETUNREACH;
+	return 0;
+}
+
+static int dibs_lo_max_dmbs(void)
+{
+	return DIBS_LO_MAX_DMBS;
+}
+
+static int dibs_lo_register_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb,
+				struct dibs_client *client)
+{
+	struct dibs_lo_dmb_node *dmb_node, *tmp_node;
+	struct dibs_lo_dev *ldev;
+	struct folio *folio;
+	unsigned long flags;
+	int sba_idx, rc;
+
+	ldev = dibs->drv_priv;
+	sba_idx = dmb->idx;
+	/* check space for new dmb */
+	for_each_clear_bit(sba_idx, ldev->sba_idx_mask, DIBS_LO_MAX_DMBS) {
+		if (!test_and_set_bit(sba_idx, ldev->sba_idx_mask))
+			break;
+	}
+	if (sba_idx == DIBS_LO_MAX_DMBS)
+		return -ENOSPC;
+
+	dmb_node = kzalloc_obj(*dmb_node);
+	if (!dmb_node) {
+		rc = -ENOMEM;
+		goto err_bit;
+	}
+
+	dmb_node->sba_idx = sba_idx;
+	dmb_node->len = dmb->dmb_len;
+
+	/* not critical; fail under memory pressure and fallback to TCP */
+	folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC |
+			    __GFP_NORETRY | __GFP_ZERO,
+			    get_order(dmb_node->len));
+	if (!folio) {
+		rc = -ENOMEM;
+		goto err_node;
+	}
+	dmb_node->cpu_addr = folio_address(folio);
+	dmb_node->dma_addr = DIBS_DMA_ADDR_INVALID;
+	refcount_set(&dmb_node->refcnt, 1);
+
+again:
+	/* add new dmb into hash table */
+	get_random_bytes(&dmb_node->token, sizeof(dmb_node->token));
+	write_lock_bh(&ldev->dmb_ht_lock);
+	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_node->token) {
+		if (tmp_node->token == dmb_node->token) {
+			write_unlock_bh(&ldev->dmb_ht_lock);
+			goto again;
+		}
+	}
+	hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token);
+	write_unlock_bh(&ldev->dmb_ht_lock);
+	atomic_inc(&ldev->dmb_cnt);
+
+	dmb->idx = dmb_node->sba_idx;
+	dmb->dmb_tok = dmb_node->token;
+	dmb->cpu_addr = dmb_node->cpu_addr;
+	dmb->dma_addr = dmb_node->dma_addr;
+	dmb->dmb_len = dmb_node->len;
+
+	spin_lock_irqsave(&dibs->lock, flags);
+	dibs->dmb_clientid_arr[sba_idx] = client->id;
+	spin_unlock_irqrestore(&dibs->lock, flags);
+
+	return 0;
+
+err_node:
+	kfree(dmb_node);
+err_bit:
+	clear_bit(sba_idx, ldev->sba_idx_mask);
+	return rc;
+}
+
+static void dibs_lo_free_dmb(struct dibs_lo_dev *ldev,
+			     struct dibs_lo_dmb_node *dmb_node)
+{
+	clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask);
+	folio_put(virt_to_folio(dmb_node->cpu_addr));
+	kfree(dmb_node);
+
+	if (atomic_dec_and_test(&ldev->dmb_cnt))
+		wake_up(&ldev->ldev_release);
+}
+
+static int dibs_lo_unregister_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb)
+{
+	struct dibs_lo_dmb_node *dmb_node = NULL, *tmp_node;
+	struct dibs_lo_dev *ldev;
+	unsigned long flags;
+	bool last;
+
+	ldev = dibs->drv_priv;
+
+	/* find dmb from hash table */
+	write_lock_bh(&ldev->dmb_ht_lock);
+	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) {
+		if (tmp_node->token == dmb->dmb_tok) {
+			dmb_node = tmp_node;
+			break;
+		}
+	}
+	if (!dmb_node) {
+		write_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+	last = refcount_dec_and_test(&dmb_node->refcnt);
+	if (last)
+		hash_del(&dmb_node->list);
+	write_unlock_bh(&ldev->dmb_ht_lock);
+
+	if (last) {
+		spin_lock_irqsave(&dibs->lock, flags);
+		dibs->dmb_clientid_arr[dmb_node->sba_idx] = NO_DIBS_CLIENT;
+		spin_unlock_irqrestore(&dibs->lock, flags);
+
+		dibs_lo_free_dmb(ldev, dmb_node);
+	}
+	return 0;
+}
+
+static int dibs_lo_support_dmb_nocopy(struct dibs_dev *dibs)
+{
+	return DIBS_LO_SUPPORT_NOCOPY;
+}
+
+static int dibs_lo_attach_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb)
+{
+	struct dibs_lo_dmb_node *dmb_node = NULL, *tmp_node;
+	struct dibs_lo_dev *ldev;
+
+	ldev = dibs->drv_priv;
+
+	/* find dmb_node according to dmb->dmb_tok */
+	read_lock_bh(&ldev->dmb_ht_lock);
+	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) {
+		if (tmp_node->token == dmb->dmb_tok) {
+			dmb_node = tmp_node;
+			break;
+		}
+	}
+	if (!dmb_node) {
+		read_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+	refcount_inc(&dmb_node->refcnt);
+	read_unlock_bh(&ldev->dmb_ht_lock);
+
+	/* provide dmb information */
+	dmb->idx = dmb_node->sba_idx;
+	dmb->dmb_tok = dmb_node->token;
+	dmb->cpu_addr = dmb_node->cpu_addr;
+	dmb->dma_addr = dmb_node->dma_addr;
+	dmb->dmb_len = dmb_node->len;
+	return 0;
+}
+
+static int dibs_lo_detach_dmb(struct dibs_dev *dibs, u64 token)
+{
+	struct dibs_lo_dmb_node *dmb_node = NULL, *tmp_node;
+	struct dibs_lo_dev *ldev;
+	bool last;
+
+	ldev = dibs->drv_priv;
+
+	/* find dmb_node according to dmb->dmb_tok */
+	write_lock_bh(&ldev->dmb_ht_lock);
+	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, token) {
+		if (tmp_node->token == token) {
+			dmb_node = tmp_node;
+			break;
+		}
+	}
+	if (!dmb_node) {
+		write_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+	last = refcount_dec_and_test(&dmb_node->refcnt);
+	if (last)
+		hash_del(&dmb_node->list);
+	write_unlock_bh(&ldev->dmb_ht_lock);
+
+	if (last)
+		dibs_lo_free_dmb(ldev, dmb_node);
+
+	return 0;
+}
+
+static int dibs_lo_move_data(struct dibs_dev *dibs, u64 dmb_tok,
+			     unsigned int idx, bool sf, unsigned int offset,
+			     void *data, unsigned int size)
+{
+	struct dibs_lo_dmb_node *rmb_node = NULL, *tmp_node;
+	struct dibs_lo_dev *ldev;
+	u16 s_mask;
+	u8 client_id;
+	u32 sba_idx;
+
+	ldev = dibs->drv_priv;
+
+	read_lock_bh(&ldev->dmb_ht_lock);
+	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) {
+		if (tmp_node->token == dmb_tok) {
+			rmb_node = tmp_node;
+			break;
+		}
+	}
+	if (!rmb_node) {
+		read_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+	if ((u64)offset + size > rmb_node->len) {
+		read_unlock_bh(&ldev->dmb_ht_lock);
+		return -EINVAL;
+	}
+
+	memcpy((char *)rmb_node->cpu_addr + offset, data, size);
+	sba_idx = rmb_node->sba_idx;
+	read_unlock_bh(&ldev->dmb_ht_lock);
+
+	if (!sf)
+		return 0;
+
+	spin_lock(&dibs->lock);
+	client_id = dibs->dmb_clientid_arr[sba_idx];
+	s_mask = ror16(0x1000, idx);
+	if (likely(client_id != NO_DIBS_CLIENT && dibs->subs[client_id]))
+		dibs->subs[client_id]->ops->handle_irq(dibs, sba_idx, s_mask);
+	spin_unlock(&dibs->lock);
+
+	return 0;
+}
+
+static const struct dibs_dev_ops dibs_lo_ops = {
+	.get_fabric_id = dibs_lo_get_fabric_id,
+	.query_remote_gid = dibs_lo_query_rgid,
+	.max_dmbs = dibs_lo_max_dmbs,
+	.register_dmb = dibs_lo_register_dmb,
+	.unregister_dmb = dibs_lo_unregister_dmb,
+	.move_data = dibs_lo_move_data,
+	.support_mmapped_rdmb = dibs_lo_support_dmb_nocopy,
+	.attach_dmb = dibs_lo_attach_dmb,
+	.detach_dmb = dibs_lo_detach_dmb,
+};
+
+static void dibs_lo_dev_init(struct dibs_lo_dev *ldev)
+{
+	rwlock_init(&ldev->dmb_ht_lock);
+	hash_init(ldev->dmb_ht);
+	atomic_set(&ldev->dmb_cnt, 0);
+	init_waitqueue_head(&ldev->ldev_release);
+}
+
+static void dibs_lo_dev_exit(struct dibs_lo_dev *ldev)
+{
+	if (atomic_read(&ldev->dmb_cnt))
+		wait_event(ldev->ldev_release, !atomic_read(&ldev->dmb_cnt));
+}
+
+static int dibs_lo_dev_probe(void)
+{
+	struct dibs_lo_dev *ldev;
+	struct dibs_dev *dibs;
+	int ret;
+
+	ldev = kzalloc_obj(*ldev);
+	if (!ldev)
+		return -ENOMEM;
+
+	dibs = dibs_dev_alloc();
+	if (!dibs) {
+		kfree(ldev);
+		return -ENOMEM;
+	}
+
+	ldev->dibs = dibs;
+	dibs->drv_priv = ldev;
+	dibs_lo_dev_init(ldev);
+	uuid_gen(&dibs->gid);
+	dibs->ops = &dibs_lo_ops;
+
+	dibs->dev.parent = NULL;
+	dev_set_name(&dibs->dev, "%s", dibs_lo_dev_name);
+
+	ret = dibs_dev_add(dibs);
+	if (ret)
+		goto err_reg;
+	lo_dev = ldev;
+	return 0;
+
+err_reg:
+	/* pairs with dibs_dev_alloc() */
+	put_device(&dibs->dev);
+	kfree(ldev);
+
+	return ret;
+}
+
+static void dibs_lo_dev_remove(void)
+{
+	if (!lo_dev)
+		return;
+
+	dibs_dev_del(lo_dev->dibs);
+	dibs_lo_dev_exit(lo_dev);
+	/* pairs with dibs_dev_alloc() */
+	put_device(&lo_dev->dibs->dev);
+	kfree(lo_dev);
+	lo_dev = NULL;
+}
+
+int dibs_loopback_init(void)
+{
+	return dibs_lo_dev_probe();
+}
+
+void dibs_loopback_exit(void)
+{
+	dibs_lo_dev_remove();
+}
diff --git a/drivers/dibs/dibs_loopback.h b/drivers/dibs/dibs_loopback.h
new file mode 100644
index 000000000..0664f6a8e
--- /dev/null
+++ b/drivers/dibs/dibs_loopback.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  dibs loopback (aka loopback-ism) device structure definitions.
+ *
+ *  Copyright (c) 2024, Alibaba Inc.
+ *
+ *  Author: Wen Gu <guwen@linux.alibaba.com>
+ *          Tony Lu <tonylu@linux.alibaba.com>
+ *
+ */
+
+#ifndef _DIBS_LOOPBACK_H
+#define _DIBS_LOOPBACK_H
+
+#include <linux/dibs.h>
+#include <linux/hashtable.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#if IS_ENABLED(CONFIG_DIBS_LO)
+#define DIBS_LO_DMBS_HASH_BITS	12
+#define DIBS_LO_MAX_DMBS	5000
+
+struct dibs_lo_dmb_node {
+	struct hlist_node list;
+	u64 token;
+	u32 len;
+	u32 sba_idx;
+	void *cpu_addr;
+	dma_addr_t dma_addr;
+	refcount_t refcnt;
+};
+
+struct dibs_lo_dev {
+	struct dibs_dev *dibs;
+	atomic_t dmb_cnt;
+	rwlock_t dmb_ht_lock;
+	DECLARE_BITMAP(sba_idx_mask, DIBS_LO_MAX_DMBS);
+	DECLARE_HASHTABLE(dmb_ht, DIBS_LO_DMBS_HASH_BITS);
+	wait_queue_head_t ldev_release;
+};
+
+int dibs_loopback_init(void);
+void dibs_loopback_exit(void);
+#else
+static inline int dibs_loopback_init(void)
+{
+	return 0;
+}
+
+static inline void dibs_loopback_exit(void)
+{
+}
+#endif
+
+#endif /* _DIBS_LOOPBACK_H */
diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c
new file mode 100644
index 000000000..20c50997a
--- /dev/null
+++ b/drivers/dibs/dibs_main.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  DIBS - Direct Internal Buffer Sharing
+ *
+ *  Implementation of the DIBS class module
+ *
+ *  Copyright IBM Corp. 2025
+ */
+#define pr_fmt(fmt) "dibs: " fmt
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/dibs.h>
+
+#include "dibs_loopback.h"
+
+MODULE_DESCRIPTION("Direct Internal Buffer Sharing class");
+MODULE_LICENSE("GPL");
+
+static const struct class dibs_class = {
+	.name		= "dibs",
+};
+
+/* use an array rather a list for fast mapping: */
+static struct dibs_client *clients[MAX_DIBS_CLIENTS];
+static u8 max_client;
+static DEFINE_MUTEX(clients_lock);
+struct dibs_dev_list {
+	struct list_head list;
+	struct mutex mutex; /* protects dibs device list */
+};
+
+static struct dibs_dev_list dibs_dev_list = {
+	.list = LIST_HEAD_INIT(dibs_dev_list.list),
+	.mutex = __MUTEX_INITIALIZER(dibs_dev_list.mutex),
+};
+
+static void dibs_setup_forwarding(struct dibs_client *client,
+				  struct dibs_dev *dibs)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dibs->lock, flags);
+	dibs->subs[client->id] = client;
+	spin_unlock_irqrestore(&dibs->lock, flags);
+}
+
+int dibs_register_client(struct dibs_client *client)
+{
+	struct dibs_dev *dibs;
+	int i, rc = -ENOSPC;
+
+	mutex_lock(&dibs_dev_list.mutex);
+	mutex_lock(&clients_lock);
+	for (i = 0; i < MAX_DIBS_CLIENTS; ++i) {
+		if (!clients[i]) {
+			clients[i] = client;
+			client->id = i;
+			if (i == max_client)
+				max_client++;
+			rc = 0;
+			break;
+		}
+	}
+	mutex_unlock(&clients_lock);
+
+	if (i < MAX_DIBS_CLIENTS) {
+		/* initialize with all devices that we got so far */
+		list_for_each_entry(dibs, &dibs_dev_list.list, list) {
+			dibs->priv[i] = NULL;
+			client->ops->add_dev(dibs);
+			dibs_setup_forwarding(client, dibs);
+		}
+	}
+	mutex_unlock(&dibs_dev_list.mutex);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dibs_register_client);
+
+int dibs_unregister_client(struct dibs_client *client)
+{
+	struct dibs_dev *dibs;
+	unsigned long flags;
+	int max_dmbs;
+	int rc = 0;
+
+	mutex_lock(&dibs_dev_list.mutex);
+	list_for_each_entry(dibs, &dibs_dev_list.list, list) {
+		spin_lock_irqsave(&dibs->lock, flags);
+		max_dmbs = dibs->ops->max_dmbs();
+		for (int i = 0; i < max_dmbs; ++i) {
+			if (dibs->dmb_clientid_arr[i] == client->id) {
+				WARN(1, "%s: attempt to unregister '%s' with registered dmb(s)\n",
+				     __func__, client->name);
+				rc = -EBUSY;
+				goto err_reg_dmb;
+			}
+		}
+		/* Stop forwarding IRQs and events */
+		dibs->subs[client->id] = NULL;
+		spin_unlock_irqrestore(&dibs->lock, flags);
+		clients[client->id]->ops->del_dev(dibs);
+		dibs->priv[client->id] = NULL;
+	}
+
+	mutex_lock(&clients_lock);
+	clients[client->id] = NULL;
+	if (client->id + 1 == max_client)
+		max_client--;
+	mutex_unlock(&clients_lock);
+
+	mutex_unlock(&dibs_dev_list.mutex);
+	return rc;
+
+err_reg_dmb:
+	spin_unlock_irqrestore(&dibs->lock, flags);
+	mutex_unlock(&dibs_dev_list.mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dibs_unregister_client);
+
+static void dibs_dev_release(struct device *dev)
+{
+	struct dibs_dev *dibs;
+
+	dibs = container_of(dev, struct dibs_dev, dev);
+
+	kfree(dibs->dmb_clientid_arr);
+	kfree(dibs);
+}
+
+struct dibs_dev *dibs_dev_alloc(void)
+{
+	struct dibs_dev *dibs;
+
+	dibs = kzalloc_obj(*dibs);
+	if (!dibs)
+		return dibs;
+	spin_lock_init(&dibs->lock);
+	dibs->dev.release = dibs_dev_release;
+	dibs->dev.class = &dibs_class;
+	device_initialize(&dibs->dev);
+
+	return dibs;
+}
+EXPORT_SYMBOL_GPL(dibs_dev_alloc);
+
+static ssize_t gid_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct dibs_dev *dibs;
+
+	dibs = container_of(dev, struct dibs_dev, dev);
+
+	return sysfs_emit(buf, "%pUb\n", &dibs->gid);
+}
+static DEVICE_ATTR_RO(gid);
+
+static ssize_t fabric_id_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct dibs_dev *dibs;
+	u16 fabric_id;
+
+	dibs = container_of(dev, struct dibs_dev, dev);
+	fabric_id = dibs->ops->get_fabric_id(dibs);
+
+	return sysfs_emit(buf, "0x%04x\n", fabric_id);
+}
+static DEVICE_ATTR_RO(fabric_id);
+
+static struct attribute *dibs_dev_attrs[] = {
+	&dev_attr_gid.attr,
+	&dev_attr_fabric_id.attr,
+	NULL,
+};
+
+static const struct attribute_group dibs_dev_attr_group = {
+	.attrs = dibs_dev_attrs,
+};
+
+int dibs_dev_add(struct dibs_dev *dibs)
+{
+	int max_dmbs;
+	int i, ret;
+
+	max_dmbs = dibs->ops->max_dmbs();
+	dibs->dmb_clientid_arr = kzalloc(max_dmbs, GFP_KERNEL);
+	if (!dibs->dmb_clientid_arr)
+		return -ENOMEM;
+	memset(dibs->dmb_clientid_arr, NO_DIBS_CLIENT, max_dmbs);
+
+	ret = device_add(&dibs->dev);
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_group(&dibs->dev.kobj, &dibs_dev_attr_group);
+	if (ret) {
+		dev_err(&dibs->dev, "sysfs_create_group failed for dibs_dev\n");
+		device_del(&dibs->dev);
+		return ret;
+	}
+	mutex_lock(&dibs_dev_list.mutex);
+	mutex_lock(&clients_lock);
+	for (i = 0; i < max_client; ++i) {
+		if (clients[i]) {
+			clients[i]->ops->add_dev(dibs);
+			dibs_setup_forwarding(clients[i], dibs);
+		}
+	}
+	mutex_unlock(&clients_lock);
+	list_add(&dibs->list, &dibs_dev_list.list);
+	mutex_unlock(&dibs_dev_list.mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dibs_dev_add);
+
+void dibs_dev_del(struct dibs_dev *dibs)
+{
+	unsigned long flags;
+	int i;
+
+	sysfs_remove_group(&dibs->dev.kobj, &dibs_dev_attr_group);
+
+	spin_lock_irqsave(&dibs->lock, flags);
+	for (i = 0; i < MAX_DIBS_CLIENTS; ++i)
+		dibs->subs[i] = NULL;
+	spin_unlock_irqrestore(&dibs->lock, flags);
+
+	mutex_lock(&dibs_dev_list.mutex);
+	mutex_lock(&clients_lock);
+	for (i = 0; i < max_client; ++i) {
+		if (clients[i])
+			clients[i]->ops->del_dev(dibs);
+	}
+	mutex_unlock(&clients_lock);
+	list_del_init(&dibs->list);
+	mutex_unlock(&dibs_dev_list.mutex);
+
+	device_del(&dibs->dev);
+}
+EXPORT_SYMBOL_GPL(dibs_dev_del);
+
+static int __init dibs_init(void)
+{
+	int rc;
+
+	rc = class_register(&dibs_class);
+	if (rc)
+		goto err;
+
+	rc = dibs_loopback_init();
+	if (rc)
+		goto err_unregister;
+
+	return rc;
+
+err_unregister:
+	class_unregister(&dibs_class);
+err:
+	pr_err("%s fails with %d\n", __func__, rc);
+	return rc;
+}
+
+static void __exit dibs_exit(void)
+{
+	dibs_loopback_exit();
+	class_unregister(&dibs_class);
+}
+
+subsys_initcall(dibs_init);
+module_exit(dibs_exit);