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
  ...

1 files changed, 892 insertions, 0 deletions

diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c
new file mode 100644
index 000000000..2d86f6110
--- /dev/null
+++ b/drivers/dma/fsl_raid.c
@@ -0,0 +1,892 @@
+/*
+ * drivers/dma/fsl_raid.c
+ *
+ * Freescale RAID Engine device driver
+ *
+ * Author:
+ *	Harninder Rai <harninder.rai@freescale.com>
+ *	Naveen Burmi <naveenburmi@freescale.com>
+ *
+ * Rewrite:
+ *	Xuelin Shi <xuelin.shi@freescale.com>
+ *
+ * Copyright (c) 2010-2014 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Theory of operation:
+ *
+ * General capabilities:
+ *	RAID Engine (RE) block is capable of offloading XOR, memcpy and P/Q
+ *	calculations required in RAID5 and RAID6 operations. RE driver
+ *	registers with Linux's ASYNC layer as dma driver. RE hardware
+ *	maintains strict ordering of the requests through chained
+ *	command queueing.
+ *
+ * Data flow:
+ *	Software RAID layer of Linux (MD layer) maintains RAID partitions,
+ *	strips, stripes etc. It sends requests to the underlying ASYNC layer
+ *	which further passes it to RE driver. ASYNC layer decides which request
+ *	goes to which job ring of RE hardware. For every request processed by
+ *	RAID Engine, driver gets an interrupt unless coalescing is set. The
+ *	per job ring interrupt handler checks the status register for errors,
+ *	clears the interrupt and leave the post interrupt processing to the irq
+ *	thread.
+ */
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/dmaengine.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+
+#include "dmaengine.h"
+#include "fsl_raid.h"
+
+#define FSL_RE_MAX_XOR_SRCS	16
+#define FSL_RE_MAX_PQ_SRCS	16
+#define FSL_RE_MIN_DESCS	256
+#define FSL_RE_MAX_DESCS	(4 * FSL_RE_MIN_DESCS)
+#define FSL_RE_FRAME_FORMAT	0x1
+#define FSL_RE_MAX_DATA_LEN	(1024*1024)
+
+#define to_fsl_re_dma_desc(tx) container_of(tx, struct fsl_re_desc, async_tx)
+
+/* Add descriptors into per chan software queue - submit_q */
+static dma_cookie_t fsl_re_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct fsl_re_desc *desc;
+	struct fsl_re_chan *re_chan;
+	dma_cookie_t cookie;
+	unsigned long flags;
+
+	desc = to_fsl_re_dma_desc(tx);
+	re_chan = container_of(tx->chan, struct fsl_re_chan, chan);
+
+	spin_lock_irqsave(&re_chan->desc_lock, flags);
+	cookie = dma_cookie_assign(tx);
+	list_add_tail(&desc->node, &re_chan->submit_q);
+	spin_unlock_irqrestore(&re_chan->desc_lock, flags);
+
+	return cookie;
+}
+
+/* Copy descriptor from per chan software queue into hardware job ring */
+static void fsl_re_issue_pending(struct dma_chan *chan)
+{
+	struct fsl_re_chan *re_chan;
+	int avail;
+	struct fsl_re_desc *desc, *_desc;
+	unsigned long flags;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+
+	spin_lock_irqsave(&re_chan->desc_lock, flags);
+	avail = FSL_RE_SLOT_AVAIL(
+		in_be32(&re_chan->jrregs->inbring_slot_avail));
+
+	list_for_each_entry_safe(desc, _desc, &re_chan->submit_q, node) {
+		if (!avail)
+			break;
+
+		list_move_tail(&desc->node, &re_chan->active_q);
+
+		memcpy(&re_chan->inb_ring_virt_addr[re_chan->inb_count],
+		       &desc->hwdesc, sizeof(struct fsl_re_hw_desc));
+
+		re_chan->inb_count = (re_chan->inb_count + 1) &
+						FSL_RE_RING_SIZE_MASK;
+		out_be32(&re_chan->jrregs->inbring_add_job, FSL_RE_ADD_JOB(1));
+		avail--;
+	}
+	spin_unlock_irqrestore(&re_chan->desc_lock, flags);
+}
+
+static void fsl_re_desc_done(struct fsl_re_desc *desc)
+{
+	dma_cookie_complete(&desc->async_tx);
+	dma_descriptor_unmap(&desc->async_tx);
+	dmaengine_desc_get_callback_invoke(&desc->async_tx, NULL);
+}
+
+static void fsl_re_cleanup_descs(struct fsl_re_chan *re_chan)
+{
+	struct fsl_re_desc *desc, *_desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&re_chan->desc_lock, flags);
+	list_for_each_entry_safe(desc, _desc, &re_chan->ack_q, node) {
+		if (async_tx_test_ack(&desc->async_tx))
+			list_move_tail(&desc->node, &re_chan->free_q);
+	}
+	spin_unlock_irqrestore(&re_chan->desc_lock, flags);
+
+	fsl_re_issue_pending(&re_chan->chan);
+}
+
+static void fsl_re_dequeue(struct tasklet_struct *t)
+{
+	struct fsl_re_chan *re_chan = from_tasklet(re_chan, t, irqtask);
+	struct fsl_re_desc *desc, *_desc;
+	struct fsl_re_hw_desc *hwdesc;
+	unsigned long flags;
+	unsigned int count, oub_count;
+	int found;
+
+	fsl_re_cleanup_descs(re_chan);
+
+	spin_lock_irqsave(&re_chan->desc_lock, flags);
+	count =	FSL_RE_SLOT_FULL(in_be32(&re_chan->jrregs->oubring_slot_full));
+	while (count--) {
+		found = 0;
+		hwdesc = &re_chan->oub_ring_virt_addr[re_chan->oub_count];
+		list_for_each_entry_safe(desc, _desc, &re_chan->active_q,
+					 node) {
+			/* compare the hw dma addr to find the completed */
+			if (desc->hwdesc.lbea32 == hwdesc->lbea32 &&
+			    desc->hwdesc.addr_low == hwdesc->addr_low) {
+				found = 1;
+				break;
+			}
+		}
+
+		if (found) {
+			fsl_re_desc_done(desc);
+			list_move_tail(&desc->node, &re_chan->ack_q);
+		} else {
+			dev_err(re_chan->dev,
+				"found hwdesc not in sw queue, discard it\n");
+		}
+
+		oub_count = (re_chan->oub_count + 1) & FSL_RE_RING_SIZE_MASK;
+		re_chan->oub_count = oub_count;
+
+		out_be32(&re_chan->jrregs->oubring_job_rmvd,
+			 FSL_RE_RMVD_JOB(1));
+	}
+	spin_unlock_irqrestore(&re_chan->desc_lock, flags);
+}
+
+/* Per Job Ring interrupt handler */
+static irqreturn_t fsl_re_isr(int irq, void *data)
+{
+	struct fsl_re_chan *re_chan;
+	u32 irqstate, status;
+
+	re_chan = dev_get_drvdata((struct device *)data);
+
+	irqstate = in_be32(&re_chan->jrregs->jr_interrupt_status);
+	if (!irqstate)
+		return IRQ_NONE;
+
+	/*
+	 * There's no way in upper layer (read MD layer) to recover from
+	 * error conditions except restart everything. In long term we
+	 * need to do something more than just crashing
+	 */
+	if (irqstate & FSL_RE_ERROR) {
+		status = in_be32(&re_chan->jrregs->jr_status);
+		dev_err(re_chan->dev, "chan error irqstate: %x, status: %x\n",
+			irqstate, status);
+	}
+
+	/* Clear interrupt */
+	out_be32(&re_chan->jrregs->jr_interrupt_status, FSL_RE_CLR_INTR);
+
+	tasklet_schedule(&re_chan->irqtask);
+
+	return IRQ_HANDLED;
+}
+
+static enum dma_status fsl_re_tx_status(struct dma_chan *chan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(chan, cookie, txstate);
+}
+
+static void fill_cfd_frame(struct fsl_re_cmpnd_frame *cf, u8 index,
+			   size_t length, dma_addr_t addr, bool final)
+{
+	u32 efrl = length & FSL_RE_CF_LENGTH_MASK;
+
+	efrl |= final << FSL_RE_CF_FINAL_SHIFT;
+	cf[index].efrl32 = cpu_to_be32(efrl);
+	cf[index].addr_high = cpu_to_be32(upper_32_bits(addr));
+	cf[index].addr_low = cpu_to_be32(lower_32_bits(addr));
+}
+
+static struct fsl_re_desc *fsl_re_init_desc(struct fsl_re_chan *re_chan,
+					    struct fsl_re_desc *desc,
+					    void *cf, dma_addr_t paddr)
+{
+	desc->re_chan = re_chan;
+	desc->async_tx.tx_submit = fsl_re_tx_submit;
+	dma_async_tx_descriptor_init(&desc->async_tx, &re_chan->chan);
+	INIT_LIST_HEAD(&desc->node);
+
+	desc->hwdesc.fmt32 = cpu_to_be32(FSL_RE_FRAME_FORMAT <<
+					  FSL_RE_HWDESC_FMT_SHIFT);
+	desc->hwdesc.lbea32 = cpu_to_be32(upper_32_bits(paddr));
+	desc->hwdesc.addr_low = cpu_to_be32(lower_32_bits(paddr));
+	desc->cf_addr = cf;
+	desc->cf_paddr = paddr;
+
+	desc->cdb_addr = (void *)(cf + FSL_RE_CF_DESC_SIZE);
+	desc->cdb_paddr = paddr + FSL_RE_CF_DESC_SIZE;
+
+	return desc;
+}
+
+static struct fsl_re_desc *fsl_re_chan_alloc_desc(struct fsl_re_chan *re_chan,
+						  unsigned long flags)
+{
+	struct fsl_re_desc *desc = NULL;
+	void *cf;
+	dma_addr_t paddr;
+	unsigned long lock_flag;
+
+	fsl_re_cleanup_descs(re_chan);
+
+	spin_lock_irqsave(&re_chan->desc_lock, lock_flag);
+	if (!list_empty(&re_chan->free_q)) {
+		/* take one desc from free_q */
+		desc = list_first_entry(&re_chan->free_q,
+					struct fsl_re_desc, node);
+		list_del(&desc->node);
+
+		desc->async_tx.flags = flags;
+	}
+	spin_unlock_irqrestore(&re_chan->desc_lock, lock_flag);
+
+	if (!desc) {
+		desc = kzalloc_obj(*desc, GFP_NOWAIT);
+		if (!desc)
+			return NULL;
+
+		cf = dma_pool_alloc(re_chan->re_dev->cf_desc_pool, GFP_NOWAIT,
+				    &paddr);
+		if (!cf) {
+			kfree(desc);
+			return NULL;
+		}
+
+		desc = fsl_re_init_desc(re_chan, desc, cf, paddr);
+		desc->async_tx.flags = flags;
+
+		spin_lock_irqsave(&re_chan->desc_lock, lock_flag);
+		re_chan->alloc_count++;
+		spin_unlock_irqrestore(&re_chan->desc_lock, lock_flag);
+	}
+
+	return desc;
+}
+
+static struct dma_async_tx_descriptor *fsl_re_prep_dma_genq(
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+		unsigned int src_cnt, const unsigned char *scf, size_t len,
+		unsigned long flags)
+{
+	struct fsl_re_chan *re_chan;
+	struct fsl_re_desc *desc;
+	struct fsl_re_xor_cdb *xor;
+	struct fsl_re_cmpnd_frame *cf;
+	u32 cdb;
+	unsigned int i, j;
+	unsigned int save_src_cnt = src_cnt;
+	int cont_q = 0;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+	if (len > FSL_RE_MAX_DATA_LEN) {
+		dev_err(re_chan->dev, "genq tx length %zu, max length %d\n",
+			len, FSL_RE_MAX_DATA_LEN);
+		return NULL;
+	}
+
+	desc = fsl_re_chan_alloc_desc(re_chan, flags);
+	if (desc <= 0)
+		return NULL;
+
+	if (scf && (flags & DMA_PREP_CONTINUE)) {
+		cont_q = 1;
+		src_cnt += 1;
+	}
+
+	/* Filling xor CDB */
+	cdb = FSL_RE_XOR_OPCODE << FSL_RE_CDB_OPCODE_SHIFT;
+	cdb |= (src_cnt - 1) << FSL_RE_CDB_NRCS_SHIFT;
+	cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT;
+	cdb |= FSL_RE_INTR_ON_ERROR << FSL_RE_CDB_ERROR_SHIFT;
+	cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT;
+	xor = desc->cdb_addr;
+	xor->cdb32 = cdb;
+
+	if (scf) {
+		/* compute q = src0*coef0^src1*coef1^..., * is GF(8) mult */
+		for (i = 0; i < save_src_cnt; i++)
+			xor->gfm[i] = scf[i];
+		if (cont_q)
+			xor->gfm[i++] = 1;
+	} else {
+		/* compute P, that is XOR all srcs */
+		for (i = 0; i < src_cnt; i++)
+			xor->gfm[i] = 1;
+	}
+
+	/* Filling frame 0 of compound frame descriptor with CDB */
+	cf = desc->cf_addr;
+	fill_cfd_frame(cf, 0, sizeof(*xor), desc->cdb_paddr, 0);
+
+	/* Fill CFD's 1st frame with dest buffer */
+	fill_cfd_frame(cf, 1, len, dest, 0);
+
+	/* Fill CFD's rest of the frames with source buffers */
+	for (i = 2, j = 0; j < save_src_cnt; i++, j++)
+		fill_cfd_frame(cf, i, len, src[j], 0);
+
+	/* Fill the last frame and mark it final */
+	if (cont_q)
+		fill_cfd_frame(cf, i, len, dest, 1);
+	else
+		fill_cfd_frame(cf, i - 1, len, src[j - 1], 1);
+
+	return &desc->async_tx;
+}
+
+/*
+ * Prep function for P parity calculation.In RAID Engine terminology,
+ * XOR calculation is called GenQ calculation done through GenQ command
+ */
+static struct dma_async_tx_descriptor *fsl_re_prep_dma_xor(
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+		unsigned int src_cnt, size_t len, unsigned long flags)
+{
+	/* NULL let genq take all coef as 1 */
+	return fsl_re_prep_dma_genq(chan, dest, src, src_cnt, NULL, len, flags);
+}
+
+/*
+ * Prep function for P/Q parity calculation.In RAID Engine terminology,
+ * P/Q calculation is called GenQQ done through GenQQ command
+ */
+static struct dma_async_tx_descriptor *fsl_re_prep_dma_pq(
+		struct dma_chan *chan, dma_addr_t *dest, dma_addr_t *src,
+		unsigned int src_cnt, const unsigned char *scf, size_t len,
+		unsigned long flags)
+{
+	struct fsl_re_chan *re_chan;
+	struct fsl_re_desc *desc;
+	struct fsl_re_pq_cdb *pq;
+	struct fsl_re_cmpnd_frame *cf;
+	u32 cdb;
+	u8 *p;
+	int gfmq_len, i, j;
+	unsigned int save_src_cnt = src_cnt;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+	if (len > FSL_RE_MAX_DATA_LEN) {
+		dev_err(re_chan->dev, "pq tx length is %zu, max length is %d\n",
+			len, FSL_RE_MAX_DATA_LEN);
+		return NULL;
+	}
+
+	/*
+	 * RE requires at least 2 sources, if given only one source, we pass the
+	 * second source same as the first one.
+	 * With only one source, generating P is meaningless, only generate Q.
+	 */
+	if (src_cnt == 1) {
+		struct dma_async_tx_descriptor *tx;
+		dma_addr_t dma_src[2];
+		unsigned char coef[2];
+
+		dma_src[0] = *src;
+		coef[0] = *scf;
+		dma_src[1] = *src;
+		coef[1] = 0;
+		tx = fsl_re_prep_dma_genq(chan, dest[1], dma_src, 2, coef, len,
+					  flags);
+		if (tx)
+			desc = to_fsl_re_dma_desc(tx);
+
+		return tx;
+	}
+
+	/*
+	 * During RAID6 array creation, Linux's MD layer gets P and Q
+	 * calculated separately in two steps. But our RAID Engine has
+	 * the capability to calculate both P and Q with a single command
+	 * Hence to merge well with MD layer, we need to provide a hook
+	 * here and call re_jq_prep_dma_genq() function
+	 */
+
+	if (flags & DMA_PREP_PQ_DISABLE_P)
+		return fsl_re_prep_dma_genq(chan, dest[1], src, src_cnt,
+				scf, len, flags);
+
+	if (flags & DMA_PREP_CONTINUE)
+		src_cnt += 3;
+
+	desc = fsl_re_chan_alloc_desc(re_chan, flags);
+	if (desc <= 0)
+		return NULL;
+
+	/* Filling GenQQ CDB */
+	cdb = FSL_RE_PQ_OPCODE << FSL_RE_CDB_OPCODE_SHIFT;
+	cdb |= (src_cnt - 1) << FSL_RE_CDB_NRCS_SHIFT;
+	cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT;
+	cdb |= FSL_RE_BUFFER_OUTPUT << FSL_RE_CDB_BUFFER_SHIFT;
+	cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT;
+
+	pq = desc->cdb_addr;
+	pq->cdb32 = cdb;
+
+	p = pq->gfm_q1;
+	/* Init gfm_q1[] */
+	for (i = 0; i < src_cnt; i++)
+		p[i] = 1;
+
+	/* Align gfm[] to 32bit */
+	gfmq_len = ALIGN(src_cnt, 4);
+
+	/* Init gfm_q2[] */
+	p += gfmq_len;
+	for (i = 0; i < src_cnt; i++)
+		p[i] = scf[i];
+
+	/* Filling frame 0 of compound frame descriptor with CDB */
+	cf = desc->cf_addr;
+	fill_cfd_frame(cf, 0, sizeof(struct fsl_re_pq_cdb), desc->cdb_paddr, 0);
+
+	/* Fill CFD's 1st & 2nd frame with dest buffers */
+	for (i = 1, j = 0; i < 3; i++, j++)
+		fill_cfd_frame(cf, i, len, dest[j], 0);
+
+	/* Fill CFD's rest of the frames with source buffers */
+	for (i = 3, j = 0; j < save_src_cnt; i++, j++)
+		fill_cfd_frame(cf, i, len, src[j], 0);
+
+	/* PQ computation continuation */
+	if (flags & DMA_PREP_CONTINUE) {
+		if (src_cnt - save_src_cnt == 3) {
+			p[save_src_cnt] = 0;
+			p[save_src_cnt + 1] = 0;
+			p[save_src_cnt + 2] = 1;
+			fill_cfd_frame(cf, i++, len, dest[0], 0);
+			fill_cfd_frame(cf, i++, len, dest[1], 0);
+			fill_cfd_frame(cf, i++, len, dest[1], 1);
+		} else {
+			dev_err(re_chan->dev, "PQ tx continuation error!\n");
+			return NULL;
+		}
+	} else {
+		/* Mark the last source buffer frame final */
+		fill_cfd_frame(cf, i - 1, len, src[j - 1], 1);
+	}
+
+	return &desc->async_tx;
+}
+
+/*
+ * Prep function for memcpy. In RAID Engine, memcpy is done through MOVE
+ * command. Logic of this function will need to be modified once multipage
+ * support is added in Linux's MD/ASYNC Layer
+ */
+static struct dma_async_tx_descriptor *fsl_re_prep_dma_memcpy(
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct fsl_re_chan *re_chan;
+	struct fsl_re_desc *desc;
+	size_t length;
+	struct fsl_re_cmpnd_frame *cf;
+	struct fsl_re_move_cdb *move;
+	u32 cdb;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+
+	if (len > FSL_RE_MAX_DATA_LEN) {
+		dev_err(re_chan->dev, "cp tx length is %zu, max length is %d\n",
+			len, FSL_RE_MAX_DATA_LEN);
+		return NULL;
+	}
+
+	desc = fsl_re_chan_alloc_desc(re_chan, flags);
+	if (desc <= 0)
+		return NULL;
+
+	/* Filling move CDB */
+	cdb = FSL_RE_MOVE_OPCODE << FSL_RE_CDB_OPCODE_SHIFT;
+	cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT;
+	cdb |= FSL_RE_INTR_ON_ERROR << FSL_RE_CDB_ERROR_SHIFT;
+	cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT;
+
+	move = desc->cdb_addr;
+	move->cdb32 = cdb;
+
+	/* Filling frame 0 of CFD with move CDB */
+	cf = desc->cf_addr;
+	fill_cfd_frame(cf, 0, sizeof(*move), desc->cdb_paddr, 0);
+
+	length = min_t(size_t, len, FSL_RE_MAX_DATA_LEN);
+
+	/* Fill CFD's 1st frame with dest buffer */
+	fill_cfd_frame(cf, 1, length, dest, 0);
+
+	/* Fill CFD's 2nd frame with src buffer */
+	fill_cfd_frame(cf, 2, length, src, 1);
+
+	return &desc->async_tx;
+}
+
+static int fsl_re_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_re_chan *re_chan;
+	struct fsl_re_desc *desc;
+	void *cf;
+	dma_addr_t paddr;
+	int i;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+	for (i = 0; i < FSL_RE_MIN_DESCS; i++) {
+		desc = kzalloc_obj(*desc);
+		if (!desc)
+			break;
+
+		cf = dma_pool_alloc(re_chan->re_dev->cf_desc_pool, GFP_KERNEL,
+				    &paddr);
+		if (!cf) {
+			kfree(desc);
+			break;
+		}
+
+		INIT_LIST_HEAD(&desc->node);
+		fsl_re_init_desc(re_chan, desc, cf, paddr);
+
+		list_add_tail(&desc->node, &re_chan->free_q);
+		re_chan->alloc_count++;
+	}
+	return re_chan->alloc_count;
+}
+
+static void fsl_re_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_re_chan *re_chan;
+	struct fsl_re_desc *desc;
+
+	re_chan = container_of(chan, struct fsl_re_chan, chan);
+	while (re_chan->alloc_count--) {
+		desc = list_first_entry(&re_chan->free_q,
+					struct fsl_re_desc,
+					node);
+
+		list_del(&desc->node);
+		dma_pool_free(re_chan->re_dev->cf_desc_pool, desc->cf_addr,
+			      desc->cf_paddr);
+		kfree(desc);
+	}
+
+	if (!list_empty(&re_chan->free_q))
+		dev_err(re_chan->dev, "chan resource cannot be cleaned!\n");
+}
+
+static int fsl_re_chan_probe(struct platform_device *ofdev,
+		      struct device_node *np, u8 q, u32 off)
+{
+	struct device *dev, *chandev;
+	struct fsl_re_drv_private *re_priv;
+	struct fsl_re_chan *chan;
+	struct dma_device *dma_dev;
+	u32 ptr;
+	u32 status;
+	int ret = 0, rc;
+	struct platform_device *chan_ofdev;
+
+	dev = &ofdev->dev;
+	re_priv = dev_get_drvdata(dev);
+	dma_dev = &re_priv->dma_dev;
+
+	chan = devm_kzalloc(dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+
+	/* create platform device for chan node */
+	chan_ofdev = of_platform_device_create(np, NULL, dev);
+	if (!chan_ofdev) {
+		dev_err(dev, "Not able to create ofdev for jr %d\n", q);
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	/* read reg property from dts */
+	rc = of_property_read_u32(np, "reg", &ptr);
+	if (rc) {
+		dev_err(dev, "Reg property not found in jr %d\n", q);
+		ret = -ENODEV;
+		goto err_free;
+	}
+
+	chan->jrregs = re_priv->base + off + ptr;
+
+	/* read irq property from dts */
+	chan->irq = irq_of_parse_and_map(np, 0);
+	if (!chan->irq) {
+		dev_err(dev, "No IRQ defined for JR %d\n", q);
+		ret = -ENODEV;
+		goto err_free;
+	}
+
+	snprintf(chan->name, sizeof(chan->name), "re_jr%02d", q);
+
+	chandev = &chan_ofdev->dev;
+	tasklet_setup(&chan->irqtask, fsl_re_dequeue);
+
+	ret = request_irq(chan->irq, fsl_re_isr, 0, chan->name, chandev);
+	if (ret) {
+		dev_err(dev, "Unable to register interrupt for JR %d\n", q);
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	re_priv->re_jrs[q] = chan;
+	chan->chan.device = dma_dev;
+	chan->chan.private = chan;
+	chan->dev = chandev;
+	chan->re_dev = re_priv;
+
+	spin_lock_init(&chan->desc_lock);
+	INIT_LIST_HEAD(&chan->ack_q);
+	INIT_LIST_HEAD(&chan->active_q);
+	INIT_LIST_HEAD(&chan->submit_q);
+	INIT_LIST_HEAD(&chan->free_q);
+
+	chan->inb_ring_virt_addr = dma_pool_alloc(chan->re_dev->hw_desc_pool,
+		GFP_KERNEL, &chan->inb_phys_addr);
+	if (!chan->inb_ring_virt_addr) {
+		dev_err(dev, "No dma memory for inb_ring_virt_addr\n");
+		ret = -ENOMEM;
+		goto err_free;
+	}
+
+	chan->oub_ring_virt_addr = dma_pool_alloc(chan->re_dev->hw_desc_pool,
+		GFP_KERNEL, &chan->oub_phys_addr);
+	if (!chan->oub_ring_virt_addr) {
+		dev_err(dev, "No dma memory for oub_ring_virt_addr\n");
+		ret = -ENOMEM;
+		goto err_free_1;
+	}
+
+	/* Program the Inbound/Outbound ring base addresses and size */
+	out_be32(&chan->jrregs->inbring_base_h,
+		 chan->inb_phys_addr & FSL_RE_ADDR_BIT_MASK);
+	out_be32(&chan->jrregs->oubring_base_h,
+		 chan->oub_phys_addr & FSL_RE_ADDR_BIT_MASK);
+	out_be32(&chan->jrregs->inbring_base_l,
+		 chan->inb_phys_addr >> FSL_RE_ADDR_BIT_SHIFT);
+	out_be32(&chan->jrregs->oubring_base_l,
+		 chan->oub_phys_addr >> FSL_RE_ADDR_BIT_SHIFT);
+	out_be32(&chan->jrregs->inbring_size,
+		 FSL_RE_RING_SIZE << FSL_RE_RING_SIZE_SHIFT);
+	out_be32(&chan->jrregs->oubring_size,
+		 FSL_RE_RING_SIZE << FSL_RE_RING_SIZE_SHIFT);
+
+	/* Read LIODN value from u-boot */
+	status = in_be32(&chan->jrregs->jr_config_1) & FSL_RE_REG_LIODN_MASK;
+
+	/* Program the CFG reg */
+	out_be32(&chan->jrregs->jr_config_1,
+		 FSL_RE_CFG1_CBSI | FSL_RE_CFG1_CBS0 | status);
+
+	dev_set_drvdata(chandev, chan);
+
+	/* Enable RE/CHAN */
+	out_be32(&chan->jrregs->jr_command, FSL_RE_ENABLE);
+
+	return 0;
+
+err_free_1:
+	dma_pool_free(chan->re_dev->hw_desc_pool, chan->inb_ring_virt_addr,
+		      chan->inb_phys_addr);
+err_free:
+	return ret;
+}
+
+/* Probe function for RAID Engine */
+static int fsl_re_probe(struct platform_device *ofdev)
+{
+	struct fsl_re_ctrl __iomem *re_regs;
+	struct fsl_re_drv_private *re_priv;
+	struct device_node *child;
+	u32 off;
+	u8 ridx = 0;
+	struct dma_device *dma_dev;
+	int rc;
+	struct device *dev = &ofdev->dev;
+
+	/* IOMAP the entire RAID Engine region */
+	re_regs = devm_platform_ioremap_resource(ofdev, 0);
+	if (IS_ERR(re_regs))
+		return PTR_ERR(re_regs);
+
+	re_priv = devm_kzalloc(dev, sizeof(*re_priv), GFP_KERNEL);
+	if (!re_priv)
+		return -ENOMEM;
+
+	re_priv->base = re_regs;
+
+	/* Program the RE mode */
+	out_be32(&re_regs->global_config, FSL_RE_NON_DPAA_MODE);
+
+	/* Program Galois Field polynomial */
+	out_be32(&re_regs->galois_field_config, FSL_RE_GFM_POLY);
+
+	dev_info(dev, "version %x, mode %x, gfp %x\n",
+		 in_be32(&re_regs->re_version_id),
+		 in_be32(&re_regs->global_config),
+		 in_be32(&re_regs->galois_field_config));
+
+	dma_dev = &re_priv->dma_dev;
+	dma_dev->dev = dev;
+	INIT_LIST_HEAD(&dma_dev->channels);
+	dma_set_mask(dev, DMA_BIT_MASK(40));
+
+	dma_dev->device_alloc_chan_resources = fsl_re_alloc_chan_resources;
+	dma_dev->device_tx_status = fsl_re_tx_status;
+	dma_dev->device_issue_pending = fsl_re_issue_pending;
+
+	dma_dev->max_xor = FSL_RE_MAX_XOR_SRCS;
+	dma_dev->device_prep_dma_xor = fsl_re_prep_dma_xor;
+	dma_cap_set(DMA_XOR, dma_dev->cap_mask);
+
+	dma_dev->max_pq = FSL_RE_MAX_PQ_SRCS;
+	dma_dev->device_prep_dma_pq = fsl_re_prep_dma_pq;
+	dma_cap_set(DMA_PQ, dma_dev->cap_mask);
+
+	dma_dev->device_prep_dma_memcpy = fsl_re_prep_dma_memcpy;
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+
+	dma_dev->device_free_chan_resources = fsl_re_free_chan_resources;
+
+	re_priv->total_chans = 0;
+
+	re_priv->cf_desc_pool = dmam_pool_create("fsl_re_cf_desc_pool", dev,
+					FSL_RE_CF_CDB_SIZE,
+					FSL_RE_CF_CDB_ALIGN, 0);
+
+	if (!re_priv->cf_desc_pool) {
+		dev_err(dev, "No memory for fsl re_cf desc pool\n");
+		return -ENOMEM;
+	}
+
+	re_priv->hw_desc_pool = dmam_pool_create("fsl_re_hw_desc_pool", dev,
+			sizeof(struct fsl_re_hw_desc) * FSL_RE_RING_SIZE,
+			FSL_RE_FRAME_ALIGN, 0);
+	if (!re_priv->hw_desc_pool) {
+		dev_err(dev, "No memory for fsl re_hw desc pool\n");
+		return -ENOMEM;
+	}
+
+	dev_set_drvdata(dev, re_priv);
+
+	/* Parse Device tree to find out the total number of JQs present */
+	for_each_compatible_node_scoped(np, NULL, "fsl,raideng-v1.0-job-queue") {
+		rc = of_property_read_u32(np, "reg", &off);
+		if (rc) {
+			dev_err(dev, "Reg property not found in JQ node\n");
+			return -ENODEV;
+		}
+		/* Find out the Job Rings present under each JQ */
+		for_each_child_of_node(np, child) {
+			rc = of_device_is_compatible(child,
+					     "fsl,raideng-v1.0-job-ring");
+			if (rc) {
+				fsl_re_chan_probe(ofdev, child, ridx++, off);
+				re_priv->total_chans++;
+			}
+		}
+	}
+
+	dma_async_device_register(dma_dev);
+
+	return 0;
+}
+
+static void fsl_re_remove_chan(struct fsl_re_chan *chan)
+{
+	tasklet_kill(&chan->irqtask);
+
+	dma_pool_free(chan->re_dev->hw_desc_pool, chan->inb_ring_virt_addr,
+		      chan->inb_phys_addr);
+
+	dma_pool_free(chan->re_dev->hw_desc_pool, chan->oub_ring_virt_addr,
+		      chan->oub_phys_addr);
+}
+
+static void fsl_re_remove(struct platform_device *ofdev)
+{
+	struct fsl_re_drv_private *re_priv;
+	struct device *dev;
+	int i;
+
+	dev = &ofdev->dev;
+	re_priv = dev_get_drvdata(dev);
+
+	/* Cleanup chan related memory areas */
+	for (i = 0; i < re_priv->total_chans; i++)
+		fsl_re_remove_chan(re_priv->re_jrs[i]);
+
+	/* Unregister the driver */
+	dma_async_device_unregister(&re_priv->dma_dev);
+}
+
+static const struct of_device_id fsl_re_ids[] = {
+	{ .compatible = "fsl,raideng-v1.0", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, fsl_re_ids);
+
+static struct platform_driver fsl_re_driver = {
+	.driver = {
+		.name = "fsl-raideng",
+		.of_match_table = fsl_re_ids,
+	},
+	.probe = fsl_re_probe,
+	.remove = fsl_re_remove,
+};
+
+module_platform_driver(fsl_re_driver);
+
+MODULE_AUTHOR("Harninder Rai <harninder.rai@freescale.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Freescale RAID Engine Device Driver");