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, 451 insertions, 0 deletions

diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c
new file mode 100644
index 000000000..96ca0b87b
--- /dev/null
+++ b/drivers/soc/qcom/ocmem.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/firmware/qcom/qcom_scm.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <soc/qcom/ocmem.h>
+
+enum region_mode {
+	WIDE_MODE = 0x0,
+	THIN_MODE,
+	MODE_DEFAULT = WIDE_MODE,
+};
+
+enum ocmem_macro_state {
+	PASSTHROUGH = 0,
+	PERI_ON = 1,
+	CORE_ON = 2,
+	CLK_OFF = 4,
+};
+
+struct ocmem_region {
+	bool interleaved;
+	enum region_mode mode;
+	unsigned int num_macros;
+	enum ocmem_macro_state macro_state[4];
+	unsigned long macro_size;
+	unsigned long region_size;
+};
+
+struct ocmem_config {
+	uint8_t num_regions;
+	unsigned long macro_size;
+};
+
+struct ocmem {
+	struct device *dev;
+	const struct ocmem_config *config;
+	struct resource *memory;
+	void __iomem *mmio;
+	struct clk *core_clk;
+	struct clk *iface_clk;
+	unsigned int num_ports;
+	unsigned int num_macros;
+	bool interleaved;
+	struct ocmem_region *regions;
+	unsigned long active_allocations;
+};
+
+#define OCMEM_MIN_ALIGN				SZ_64K
+#define OCMEM_MIN_ALLOC				SZ_64K
+
+#define OCMEM_REG_HW_VERSION			0x00000000
+#define OCMEM_REG_HW_PROFILE			0x00000004
+
+#define OCMEM_REG_REGION_MODE_CTL		0x00001000
+#define OCMEM_REGION_MODE_CTL_REG0_THIN		0x00000001
+#define OCMEM_REGION_MODE_CTL_REG1_THIN		0x00000002
+#define OCMEM_REGION_MODE_CTL_REG2_THIN		0x00000004
+#define OCMEM_REGION_MODE_CTL_REG3_THIN		0x00000008
+
+#define OCMEM_REG_GFX_MPU_START			0x00001004
+#define OCMEM_REG_GFX_MPU_END			0x00001008
+
+#define OCMEM_HW_VERSION_MAJOR(val)		FIELD_GET(GENMASK(31, 28), val)
+#define OCMEM_HW_VERSION_MINOR(val)		FIELD_GET(GENMASK(27, 16), val)
+#define OCMEM_HW_VERSION_STEP(val)		FIELD_GET(GENMASK(15, 0), val)
+
+#define OCMEM_HW_PROFILE_NUM_PORTS(val)		FIELD_GET(0x0000000f, (val))
+#define OCMEM_HW_PROFILE_NUM_MACROS(val)	FIELD_GET(0x00003f00, (val))
+
+#define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE	0x00010000
+#define OCMEM_HW_PROFILE_INTERLEAVING		0x00020000
+#define OCMEM_REG_GEN_STATUS			0x0000000c
+
+#define OCMEM_REG_PSGSC_STATUS			0x00000038
+#define OCMEM_REG_PSGSC_CTL(i0)			(0x0000003c + 0x1*(i0))
+
+#define OCMEM_PSGSC_CTL_MACRO0_MODE(val)	FIELD_PREP(0x00000007, (val))
+#define OCMEM_PSGSC_CTL_MACRO1_MODE(val)	FIELD_PREP(0x00000070, (val))
+#define OCMEM_PSGSC_CTL_MACRO2_MODE(val)	FIELD_PREP(0x00000700, (val))
+#define OCMEM_PSGSC_CTL_MACRO3_MODE(val)	FIELD_PREP(0x00007000, (val))
+
+static inline void ocmem_write(struct ocmem *ocmem, u32 reg, u32 data)
+{
+	writel(data, ocmem->mmio + reg);
+}
+
+static inline u32 ocmem_read(struct ocmem *ocmem, u32 reg)
+{
+	return readl(ocmem->mmio + reg);
+}
+
+static void update_ocmem(struct ocmem *ocmem)
+{
+	uint32_t region_mode_ctrl = 0x0;
+	int i;
+
+	if (!qcom_scm_ocmem_lock_available()) {
+		for (i = 0; i < ocmem->config->num_regions; i++) {
+			struct ocmem_region *region = &ocmem->regions[i];
+
+			if (region->mode == THIN_MODE)
+				region_mode_ctrl |= BIT(i);
+		}
+
+		dev_dbg(ocmem->dev, "ocmem_region_mode_control %x\n",
+			region_mode_ctrl);
+		ocmem_write(ocmem, OCMEM_REG_REGION_MODE_CTL, region_mode_ctrl);
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+		u32 data;
+
+		data = OCMEM_PSGSC_CTL_MACRO0_MODE(region->macro_state[0]) |
+			OCMEM_PSGSC_CTL_MACRO1_MODE(region->macro_state[1]) |
+			OCMEM_PSGSC_CTL_MACRO2_MODE(region->macro_state[2]) |
+			OCMEM_PSGSC_CTL_MACRO3_MODE(region->macro_state[3]);
+
+		ocmem_write(ocmem, OCMEM_REG_PSGSC_CTL(i), data);
+	}
+}
+
+static unsigned long phys_to_offset(struct ocmem *ocmem,
+				    unsigned long addr)
+{
+	if (addr < ocmem->memory->start || addr >= ocmem->memory->end)
+		return 0;
+
+	return addr - ocmem->memory->start;
+}
+
+static unsigned long device_address(struct ocmem *ocmem,
+				    enum ocmem_client client,
+				    unsigned long addr)
+{
+	WARN_ON(client != OCMEM_GRAPHICS);
+
+	/* TODO: gpu uses phys_to_offset, but others do not.. */
+	return phys_to_offset(ocmem, addr);
+}
+
+static void update_range(struct ocmem *ocmem, struct ocmem_buf *buf,
+			 enum ocmem_macro_state mstate, enum region_mode rmode)
+{
+	unsigned long offset = 0;
+	int i, j;
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (buf->offset <= offset && offset < buf->offset + buf->len)
+			region->mode = rmode;
+
+		for (j = 0; j < region->num_macros; j++) {
+			if (buf->offset <= offset &&
+			    offset < buf->offset + buf->len)
+				region->macro_state[j] = mstate;
+
+			offset += region->macro_size;
+		}
+	}
+
+	update_ocmem(ocmem);
+}
+
+struct ocmem *of_get_ocmem(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct ocmem *ocmem;
+
+	struct device_node *devnode __free(device_node) = of_parse_phandle(dev->of_node,
+									   "sram", 0);
+	if (!devnode || !devnode->parent) {
+		dev_err(dev, "Cannot look up sram phandle\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	pdev = of_find_device_by_node(devnode->parent);
+	if (!pdev)
+		return dev_err_ptr_probe(dev, -EPROBE_DEFER,
+					 "Cannot find device node %s\n",
+					 devnode->name);
+
+	ocmem = platform_get_drvdata(pdev);
+	put_device(&pdev->dev);
+	if (!ocmem)
+		return dev_err_ptr_probe(dev, -EPROBE_DEFER, "Cannot get ocmem\n");
+
+	return ocmem;
+}
+EXPORT_SYMBOL_GPL(of_get_ocmem);
+
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size)
+{
+	int ret;
+
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return ERR_PTR(-ENODEV);
+
+	if (size < OCMEM_MIN_ALLOC || !IS_ALIGNED(size, OCMEM_MIN_ALIGN))
+		return ERR_PTR(-EINVAL);
+
+	if (test_and_set_bit_lock(BIT(client), &ocmem->active_allocations))
+		return ERR_PTR(-EBUSY);
+
+	struct ocmem_buf *buf __free(kfree) = kzalloc_obj(*buf);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	buf->offset = 0;
+	buf->addr = device_address(ocmem, client, buf->offset);
+	buf->len = size;
+
+	update_range(ocmem, buf, CORE_ON, WIDE_MODE);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		ret = qcom_scm_ocmem_lock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					  buf->offset, buf->len, WIDE_MODE);
+		if (ret) {
+			dev_err(ocmem->dev, "could not lock: %d\n", ret);
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, buf->offset);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END,
+			    buf->offset + buf->len);
+	}
+
+	dev_dbg(ocmem->dev, "using %ldK of OCMEM at 0x%08lx for client %d\n",
+		size / 1024, buf->addr, client);
+
+	return_ptr(buf);
+
+err_unlock:
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(ocmem_allocate);
+
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf)
+{
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return;
+
+	update_range(ocmem, buf, CLK_OFF, MODE_DEFAULT);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		int ret;
+
+		ret = qcom_scm_ocmem_unlock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					    buf->offset, buf->len);
+		if (ret)
+			dev_err(ocmem->dev, "could not unlock: %d\n", ret);
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, 0x0);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, 0x0);
+	}
+
+	kfree(buf);
+
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+}
+EXPORT_SYMBOL_GPL(ocmem_free);
+
+static int ocmem_dev_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned long reg, region_size;
+	int i, j, ret, num_banks;
+	struct ocmem *ocmem;
+
+	if (!qcom_scm_is_available())
+		return -EPROBE_DEFER;
+
+	ocmem = devm_kzalloc(dev, sizeof(*ocmem), GFP_KERNEL);
+	if (!ocmem)
+		return -ENOMEM;
+
+	ocmem->dev = dev;
+	ocmem->config = device_get_match_data(dev);
+
+	ocmem->core_clk = devm_clk_get_optional(dev, "core");
+	if (IS_ERR(ocmem->core_clk))
+		return dev_err_probe(dev, PTR_ERR(ocmem->core_clk),
+				     "Unable to get core clock\n");
+
+	ocmem->iface_clk = devm_clk_get_optional(dev, "iface");
+	if (IS_ERR(ocmem->iface_clk))
+		return dev_err_probe(dev, PTR_ERR(ocmem->iface_clk),
+				     "Unable to get iface clock\n");
+
+	ocmem->mmio = devm_platform_ioremap_resource_byname(pdev, "ctrl");
+	if (IS_ERR(ocmem->mmio))
+		return dev_err_probe(&pdev->dev, PTR_ERR(ocmem->mmio),
+				     "Failed to ioremap ocmem_ctrl resource\n");
+
+	ocmem->memory = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						     "mem");
+	if (!ocmem->memory) {
+		dev_err(dev, "Could not get mem region\n");
+		return -ENXIO;
+	}
+
+	/* The core clock is synchronous with graphics */
+	WARN_ON(clk_set_rate(ocmem->core_clk, 1000) < 0);
+
+	ret = clk_prepare_enable(ocmem->core_clk);
+	if (ret)
+		return dev_err_probe(ocmem->dev, ret, "Failed to enable core clock\n");
+
+	ret = clk_prepare_enable(ocmem->iface_clk);
+	if (ret) {
+		clk_disable_unprepare(ocmem->core_clk);
+		return dev_err_probe(ocmem->dev, ret, "Failed to enable iface clock\n");
+	}
+
+	if (qcom_scm_restore_sec_cfg_available()) {
+		dev_dbg(dev, "configuring scm\n");
+		ret = qcom_scm_restore_sec_cfg(QCOM_SCM_OCMEM_DEV_ID, 0);
+		if (ret) {
+			dev_err_probe(dev, ret, "Could not enable secure configuration\n");
+			goto err_clk_disable;
+		}
+	}
+
+	reg = ocmem_read(ocmem, OCMEM_REG_HW_VERSION);
+	dev_dbg(dev, "OCMEM hardware version: %lu.%lu.%lu\n",
+		OCMEM_HW_VERSION_MAJOR(reg),
+		OCMEM_HW_VERSION_MINOR(reg),
+		OCMEM_HW_VERSION_STEP(reg));
+
+	reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE);
+	ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg);
+	ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg);
+	ocmem->interleaved = !!(reg & OCMEM_HW_PROFILE_INTERLEAVING);
+
+	num_banks = ocmem->num_ports / 2;
+	region_size = ocmem->config->macro_size * num_banks;
+
+	dev_info(dev, "%u ports, %u regions, %u macros, %sinterleaved\n",
+		 ocmem->num_ports, ocmem->config->num_regions,
+		 ocmem->num_macros, ocmem->interleaved ? "" : "not ");
+
+	ocmem->regions = devm_kcalloc(dev, ocmem->config->num_regions,
+				      sizeof(struct ocmem_region), GFP_KERNEL);
+	if (!ocmem->regions) {
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (WARN_ON(num_banks > ARRAY_SIZE(region->macro_state))) {
+			ret = -EINVAL;
+			goto err_clk_disable;
+		}
+
+		region->mode = MODE_DEFAULT;
+		region->num_macros = num_banks;
+
+		if (i == (ocmem->config->num_regions - 1) &&
+		    reg & OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE) {
+			region->macro_size = ocmem->config->macro_size / 2;
+			region->region_size = region_size / 2;
+		} else {
+			region->macro_size = ocmem->config->macro_size;
+			region->region_size = region_size;
+		}
+
+		for (j = 0; j < ARRAY_SIZE(region->macro_state); j++)
+			region->macro_state[j] = CLK_OFF;
+	}
+
+	platform_set_drvdata(pdev, ocmem);
+
+	return 0;
+
+err_clk_disable:
+	clk_disable_unprepare(ocmem->core_clk);
+	clk_disable_unprepare(ocmem->iface_clk);
+	return ret;
+}
+
+static void ocmem_dev_remove(struct platform_device *pdev)
+{
+	struct ocmem *ocmem = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(ocmem->core_clk);
+	clk_disable_unprepare(ocmem->iface_clk);
+}
+
+static const struct ocmem_config ocmem_8226_config = {
+	.num_regions = 1,
+	.macro_size = SZ_128K,
+};
+
+static const struct ocmem_config ocmem_8974_config = {
+	.num_regions = 3,
+	.macro_size = SZ_128K,
+};
+
+static const struct of_device_id ocmem_of_match[] = {
+	{ .compatible = "qcom,msm8226-ocmem", .data = &ocmem_8226_config },
+	{ .compatible = "qcom,msm8974-ocmem", .data = &ocmem_8974_config },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, ocmem_of_match);
+
+static struct platform_driver ocmem_driver = {
+	.probe = ocmem_dev_probe,
+	.remove = ocmem_dev_remove,
+	.driver = {
+		.name = "ocmem",
+		.of_match_table = ocmem_of_match,
+	},
+};
+
+module_platform_driver(ocmem_driver);
+
+MODULE_DESCRIPTION("On Chip Memory (OCMEM) allocator for some Snapdragon SoCs");
+MODULE_LICENSE("GPL v2");