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, 464 insertions, 0 deletions

diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c
new file mode 100644
index 000000000..c8990e83a
--- /dev/null
+++ b/drivers/misc/sram.c
@@ -0,0 +1,464 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic on-chip SRAM allocation driver
+ *
+ * Copyright (C) 2012 Philipp Zabel, Pengutronix
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/genalloc.h>
+#include <linux/io.h>
+#include <linux/list_sort.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/mfd/syscon.h>
+#include <soc/at91/atmel-secumod.h>
+
+#include "sram.h"
+
+#define SRAM_GRANULARITY	32
+
+static ssize_t sram_read(struct file *filp, struct kobject *kobj,
+			 const struct bin_attribute *attr,
+			 char *buf, loff_t pos, size_t count)
+{
+	struct sram_partition *part;
+
+	/* Cast away the const as the attribute is part of a larger structure */
+	part = (struct sram_partition *)container_of(attr, struct sram_partition, battr);
+
+	mutex_lock(&part->lock);
+	memcpy_fromio(buf, part->base + pos, count);
+	mutex_unlock(&part->lock);
+
+	return count;
+}
+
+static ssize_t sram_write(struct file *filp, struct kobject *kobj,
+			  const struct bin_attribute *attr,
+			  char *buf, loff_t pos, size_t count)
+{
+	struct sram_partition *part;
+
+	/* Cast away the const as the attribute is part of a larger structure */
+	part = (struct sram_partition *)container_of(attr, struct sram_partition, battr);
+
+	mutex_lock(&part->lock);
+	memcpy_toio(part->base + pos, buf, count);
+	mutex_unlock(&part->lock);
+
+	return count;
+}
+
+static int sram_add_pool(struct sram_dev *sram, struct sram_reserve *block,
+			 phys_addr_t start, struct sram_partition *part)
+{
+	int ret;
+
+	part->pool = devm_gen_pool_create(sram->dev, ilog2(SRAM_GRANULARITY),
+					  NUMA_NO_NODE, block->label);
+	if (IS_ERR(part->pool))
+		return PTR_ERR(part->pool);
+
+	ret = gen_pool_add_virt(part->pool, (unsigned long)part->base, start,
+				block->size, NUMA_NO_NODE);
+	if (ret < 0) {
+		dev_err(sram->dev, "failed to register subpool: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int sram_add_export(struct sram_dev *sram, struct sram_reserve *block,
+			   phys_addr_t start, struct sram_partition *part)
+{
+	sysfs_bin_attr_init(&part->battr);
+	part->battr.attr.name = devm_kasprintf(sram->dev, GFP_KERNEL,
+					       "%llx.sram",
+					       (unsigned long long)start);
+	if (!part->battr.attr.name)
+		return -ENOMEM;
+
+	part->battr.attr.mode = S_IRUSR | S_IWUSR;
+	part->battr.read = sram_read;
+	part->battr.write = sram_write;
+	part->battr.size = block->size;
+
+	return device_create_bin_file(sram->dev, &part->battr);
+}
+
+static int sram_add_partition(struct sram_dev *sram, struct sram_reserve *block,
+			      phys_addr_t start)
+{
+	int ret;
+	struct sram_partition *part = &sram->partition[sram->partitions];
+
+	mutex_init(&part->lock);
+
+	if (sram->config && sram->config->map_only_reserved) {
+		void __iomem *virt_base;
+
+		if (sram->no_memory_wc)
+			virt_base = devm_ioremap_resource(sram->dev, &block->res);
+		else
+			virt_base = devm_ioremap_resource_wc(sram->dev, &block->res);
+
+		if (IS_ERR(virt_base)) {
+			dev_err(sram->dev, "could not map SRAM at %pr\n", &block->res);
+			return PTR_ERR(virt_base);
+		}
+
+		part->base = virt_base;
+	} else {
+		part->base = sram->virt_base + block->start;
+	}
+
+	if (block->pool) {
+		ret = sram_add_pool(sram, block, start, part);
+		if (ret)
+			return ret;
+	}
+	if (block->export) {
+		ret = sram_add_export(sram, block, start, part);
+		if (ret)
+			return ret;
+	}
+	if (block->protect_exec) {
+		ret = sram_check_protect_exec(sram, block, part);
+		if (ret)
+			return ret;
+
+		ret = sram_add_pool(sram, block, start, part);
+		if (ret)
+			return ret;
+
+		sram_add_protect_exec(part);
+	}
+
+	sram->partitions++;
+
+	return 0;
+}
+
+static void sram_free_partitions(struct sram_dev *sram)
+{
+	struct sram_partition *part;
+
+	if (!sram->partitions)
+		return;
+
+	part = &sram->partition[sram->partitions - 1];
+	for (; sram->partitions; sram->partitions--, part--) {
+		if (part->battr.size)
+			device_remove_bin_file(sram->dev, &part->battr);
+
+		if (part->pool &&
+		    gen_pool_avail(part->pool) < gen_pool_size(part->pool))
+			dev_err(sram->dev, "removed pool while SRAM allocated\n");
+	}
+}
+
+static int sram_reserve_cmp(void *priv, const struct list_head *a,
+					const struct list_head *b)
+{
+	const struct sram_reserve *ra = list_entry(a, struct sram_reserve, list);
+	const struct sram_reserve *rb = list_entry(b, struct sram_reserve, list);
+
+	return ra->start - rb->start;
+}
+
+static int sram_reserve_regions(struct sram_dev *sram, struct resource *res)
+{
+	struct device_node *np = sram->dev->of_node, *child;
+	unsigned long size, cur_start, cur_size;
+	struct sram_reserve *rblocks, *block;
+	struct list_head reserve_list;
+	unsigned int nblocks, exports = 0;
+	const char *label;
+	int ret = 0;
+
+	INIT_LIST_HEAD(&reserve_list);
+
+	size = resource_size(res);
+
+	/*
+	 * We need an additional block to mark the end of the memory region
+	 * after the reserved blocks from the dt are processed.
+	 */
+	nblocks = (np) ? of_get_available_child_count(np) + 1 : 1;
+	rblocks = kzalloc_objs(*rblocks, nblocks);
+	if (!rblocks)
+		return -ENOMEM;
+
+	block = &rblocks[0];
+	for_each_available_child_of_node(np, child) {
+		struct resource child_res;
+
+		ret = of_address_to_resource(child, 0, &child_res);
+		if (ret < 0) {
+			dev_err(sram->dev,
+				"could not get address for node %pOF\n",
+				child);
+			goto err_chunks;
+		}
+
+		if (child_res.start < res->start || child_res.end > res->end) {
+			dev_err(sram->dev,
+				"reserved block %pOF outside the sram area\n",
+				child);
+			ret = -EINVAL;
+			goto err_chunks;
+		}
+
+		block->start = child_res.start - res->start;
+		block->size = resource_size(&child_res);
+		block->res = child_res;
+		list_add_tail(&block->list, &reserve_list);
+
+		block->export = of_property_read_bool(child, "export");
+		block->pool = of_property_read_bool(child, "pool");
+		block->protect_exec = of_property_read_bool(child, "protect-exec");
+
+		if ((block->export || block->pool || block->protect_exec) &&
+		    block->size) {
+			exports++;
+
+			label = NULL;
+			ret = of_property_read_string(child, "label", &label);
+			if (ret && ret != -EINVAL) {
+				dev_err(sram->dev,
+					"%pOF has invalid label name\n",
+					child);
+				goto err_chunks;
+			}
+			if (!label)
+				block->label = devm_kasprintf(sram->dev, GFP_KERNEL,
+							      "%s", of_node_full_name(child));
+			else
+				block->label = devm_kstrdup(sram->dev,
+							    label, GFP_KERNEL);
+			if (!block->label) {
+				ret = -ENOMEM;
+				goto err_chunks;
+			}
+
+			dev_dbg(sram->dev, "found %sblock '%s' 0x%x-0x%x\n",
+				block->export ? "exported " : "", block->label,
+				block->start, block->start + block->size);
+		} else {
+			dev_dbg(sram->dev, "found reserved block 0x%x-0x%x\n",
+				block->start, block->start + block->size);
+		}
+
+		block++;
+	}
+	child = NULL;
+
+	/* the last chunk marks the end of the region */
+	rblocks[nblocks - 1].start = size;
+	rblocks[nblocks - 1].size = 0;
+	list_add_tail(&rblocks[nblocks - 1].list, &reserve_list);
+
+	list_sort(NULL, &reserve_list, sram_reserve_cmp);
+
+	if (exports) {
+		sram->partition = devm_kcalloc(sram->dev,
+				       exports, sizeof(*sram->partition),
+				       GFP_KERNEL);
+		if (!sram->partition) {
+			ret = -ENOMEM;
+			goto err_chunks;
+		}
+	}
+
+	cur_start = 0;
+	list_for_each_entry(block, &reserve_list, list) {
+		/* can only happen if sections overlap */
+		if (block->start < cur_start) {
+			dev_err(sram->dev,
+				"block at 0x%x starts after current offset 0x%lx\n",
+				block->start, cur_start);
+			ret = -EINVAL;
+			sram_free_partitions(sram);
+			goto err_chunks;
+		}
+
+		if ((block->export || block->pool || block->protect_exec) &&
+		    block->size) {
+			ret = sram_add_partition(sram, block,
+						 res->start + block->start);
+			if (ret) {
+				sram_free_partitions(sram);
+				goto err_chunks;
+			}
+		}
+
+		/* current start is in a reserved block, so continue after it */
+		if (block->start == cur_start) {
+			cur_start = block->start + block->size;
+			continue;
+		}
+
+		/*
+		 * allocate the space between the current starting
+		 * address and the following reserved block, or the
+		 * end of the region.
+		 */
+		cur_size = block->start - cur_start;
+
+		if (sram->pool) {
+			dev_dbg(sram->dev, "adding chunk 0x%lx-0x%lx\n",
+				cur_start, cur_start + cur_size);
+
+			ret = gen_pool_add_virt(sram->pool,
+					(unsigned long)sram->virt_base + cur_start,
+					res->start + cur_start, cur_size, -1);
+			if (ret < 0) {
+				sram_free_partitions(sram);
+				goto err_chunks;
+			}
+		}
+
+		/* next allocation after this reserved block */
+		cur_start = block->start + block->size;
+	}
+
+err_chunks:
+	of_node_put(child);
+	kfree(rblocks);
+
+	return ret;
+}
+
+static int atmel_securam_wait(void)
+{
+	struct regmap *regmap;
+	u32 val;
+
+	regmap = syscon_regmap_lookup_by_compatible("atmel,sama5d2-secumod");
+	if (IS_ERR(regmap))
+		return -ENODEV;
+
+	return regmap_read_poll_timeout(regmap, AT91_SECUMOD_RAMRDY, val,
+					val & AT91_SECUMOD_RAMRDY_READY,
+					10000, 500000);
+}
+
+static const struct sram_config atmel_securam_config = {
+	.init = atmel_securam_wait,
+};
+
+/*
+ * SYSRAM contains areas that are not accessible by the
+ * kernel, such as the first 256K that is reserved for TZ.
+ * Accesses to those areas (including speculative accesses)
+ * trigger SErrors. As such we must map only the areas of
+ * SYSRAM specified in the device tree.
+ */
+static const struct sram_config tegra_sysram_config = {
+	.map_only_reserved = true,
+};
+
+static const struct of_device_id sram_dt_ids[] = {
+	{ .compatible = "mmio-sram" },
+	{ .compatible = "atmel,sama5d2-securam", .data = &atmel_securam_config },
+	{ .compatible = "nvidia,tegra186-sysram", .data = &tegra_sysram_config },
+	{ .compatible = "nvidia,tegra194-sysram", .data = &tegra_sysram_config },
+	{ .compatible = "nvidia,tegra234-sysram", .data = &tegra_sysram_config },
+	{ }
+};
+
+static int sram_probe(struct platform_device *pdev)
+{
+	const struct sram_config *config;
+	struct sram_dev *sram;
+	int ret;
+	struct resource *res;
+	struct clk *clk;
+
+	config = of_device_get_match_data(&pdev->dev);
+
+	sram = devm_kzalloc(&pdev->dev, sizeof(*sram), GFP_KERNEL);
+	if (!sram)
+		return -ENOMEM;
+
+	sram->dev = &pdev->dev;
+	sram->no_memory_wc = of_property_read_bool(pdev->dev.of_node, "no-memory-wc");
+	sram->config = config;
+
+	if (!config || !config->map_only_reserved) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (sram->no_memory_wc)
+			sram->virt_base = devm_ioremap_resource(&pdev->dev, res);
+		else
+			sram->virt_base = devm_ioremap_resource_wc(&pdev->dev, res);
+		if (IS_ERR(sram->virt_base)) {
+			dev_err(&pdev->dev, "could not map SRAM registers\n");
+			return PTR_ERR(sram->virt_base);
+		}
+
+		sram->pool = devm_gen_pool_create(sram->dev, ilog2(SRAM_GRANULARITY),
+						  NUMA_NO_NODE, NULL);
+		if (IS_ERR(sram->pool))
+			return PTR_ERR(sram->pool);
+	}
+
+	clk = devm_clk_get_optional_enabled(sram->dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = sram_reserve_regions(sram,
+			platform_get_resource(pdev, IORESOURCE_MEM, 0));
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, sram);
+
+	if (config && config->init) {
+		ret = config->init();
+		if (ret)
+			goto err_free_partitions;
+	}
+
+	if (sram->pool)
+		dev_dbg(sram->dev, "SRAM pool: %zu KiB @ 0x%p\n",
+			gen_pool_size(sram->pool) / 1024, sram->virt_base);
+
+	return 0;
+
+err_free_partitions:
+	sram_free_partitions(sram);
+
+	return ret;
+}
+
+static void sram_remove(struct platform_device *pdev)
+{
+	struct sram_dev *sram = platform_get_drvdata(pdev);
+
+	sram_free_partitions(sram);
+
+	if (sram->pool && gen_pool_avail(sram->pool) < gen_pool_size(sram->pool))
+		dev_err(sram->dev, "removed while SRAM allocated\n");
+}
+
+static struct platform_driver sram_driver = {
+	.driver = {
+		.name = "sram",
+		.of_match_table = sram_dt_ids,
+	},
+	.probe = sram_probe,
+	.remove = sram_remove,
+};
+
+static int __init sram_init(void)
+{
+	return platform_driver_register(&sram_driver);
+}
+
+postcore_initcall(sram_init);