Merge tag 'misc-habanalabs-fixes-2019-05-24' of git://people.freedesktop.org/~gabbayo/linux into char-misc-linus

Oded writes:

This tag contains the following fixes:

- Halt debug engines when user process closes the FD. We can't allow the
  device to issue transactions for a user which doesn't exists anymore.

- Fix various security holes in debugfs API.

- Add a new opcode to the DEBUG IOCTL API. The opcode is designed
  for setting the device into and out of debug mode. Although not a fix
  per-se, because this is a new IOCTL which is upstreamed in kernel 5.2, I
  think this is justified at this point because we won't be able to change
  the API later.

- Fix a bug where the code used an uninitialized mutex

* tag 'misc-habanalabs-fixes-2019-05-24' of git://people.freedesktop.org/~gabbayo/linux:
  habanalabs: Avoid using a non-initialized MMU cache mutex
  habanalabs: fix debugfs code
  uapi/habanalabs: add opcode for enable/disable device debug mode
  habanalabs: halt debug engines on user process close

drivers/misc/habanalabs/context.c

@@ -26,6 +26,12 @@ static void hl_ctx_fini(struct hl_ctx *ctx)
 		dma_fence_put(ctx->cs_pending[i]);
 
 	if (ctx->asid != HL_KERNEL_ASID_ID) {
+		/*
+		 * The engines are stopped as there is no executing CS, but the
+		 * Coresight might be still working by accessing addresses
+		 * related to the stopped engines. Hence stop it explicitly.
+		 */
+		hdev->asic_funcs->halt_coresight(hdev);
 		hl_vm_ctx_fini(ctx);
 		hl_asid_free(hdev, ctx->asid);
 	}

drivers/misc/habanalabs/debugfs.c

@@ -459,41 +459,31 @@ static ssize_t mmu_write(struct file *file, const char __user *buf,
 	struct hl_debugfs_entry *entry = s->private;
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
-	char kbuf[MMU_KBUF_SIZE], asid_kbuf[MMU_ASID_BUF_SIZE],
-		addr_kbuf[MMU_ADDR_BUF_SIZE];
+	char kbuf[MMU_KBUF_SIZE];
 	char *c;
 	ssize_t rc;
 
 	if (!hdev->mmu_enable)
 		return count;
 
-	memset(kbuf, 0, sizeof(kbuf));
-	memset(asid_kbuf, 0, sizeof(asid_kbuf));
-	memset(addr_kbuf, 0, sizeof(addr_kbuf));
-
+	if (count > sizeof(kbuf) - 1)
+		goto err;
 	if (copy_from_user(kbuf, buf, count))
 		goto err;
-
-	kbuf[MMU_KBUF_SIZE - 1] = 0;
+	kbuf[count] = 0;
 
 	c = strchr(kbuf, ' ');
 	if (!c)
 		goto err;
+	*c = '\0';
 
-	memcpy(asid_kbuf, kbuf, c - kbuf);
-
-	rc = kstrtouint(asid_kbuf, 10, &dev_entry->mmu_asid);
+	rc = kstrtouint(kbuf, 10, &dev_entry->mmu_asid);
 	if (rc)
 		goto err;
 
-	c = strstr(kbuf, " 0x");
-	if (!c)
+	if (strncmp(c+1, "0x", 2))
 		goto err;
-
-	c += 3;
-	memcpy(addr_kbuf, c, (kbuf + count) - c);
-
-	rc = kstrtoull(addr_kbuf, 16, &dev_entry->mmu_addr);
+	rc = kstrtoull(c+3, 16, &dev_entry->mmu_addr);
 	if (rc)
 		goto err;
 
@@ -600,10 +590,8 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf,
 	}
 
 	sprintf(tmp_buf, "0x%08x\n", val);
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
-			strlen(tmp_buf) + 1);
-
-	return rc;
+	return simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
 }
 
 static ssize_t hl_data_write32(struct file *f, const char __user *buf,
@@ -645,7 +633,6 @@ static ssize_t hl_get_power_state(struct file *f, char __user *buf,
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
 	char tmp_buf[200];
-	ssize_t rc;
 	int i;
 
 	if (*ppos)
@@ -660,10 +647,8 @@ static ssize_t hl_get_power_state(struct file *f, char __user *buf,
 
 	sprintf(tmp_buf,
 		"current power state: %d\n1 - D0\n2 - D3hot\n3 - Unknown\n", i);
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
-			strlen(tmp_buf) + 1);
-
-	return rc;
+	return simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
 }
 
 static ssize_t hl_set_power_state(struct file *f, const char __user *buf,
@@ -716,8 +701,8 @@ static ssize_t hl_i2c_data_read(struct file *f, char __user *buf,
 	}
 
 	sprintf(tmp_buf, "0x%02x\n", val);
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
-			strlen(tmp_buf) + 1);
+	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
 
 	return rc;
 }
@@ -806,18 +791,9 @@ static ssize_t hl_led2_write(struct file *f, const char __user *buf,
 static ssize_t hl_device_read(struct file *f, char __user *buf,
 					size_t count, loff_t *ppos)
 {
-	char tmp_buf[200];
-	ssize_t rc;
-
-	if (*ppos)
-		return 0;
-
-	sprintf(tmp_buf,
-		"Valid values: disable, enable, suspend, resume, cpu_timeout\n");
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
-			strlen(tmp_buf) + 1);
-
-	return rc;
+	static const char *help =
+		"Valid values: disable, enable, suspend, resume, cpu_timeout\n";
+	return simple_read_from_buffer(buf, count, ppos, help, strlen(help));
 }
 
 static ssize_t hl_device_write(struct file *f, const char __user *buf,
@@ -825,7 +801,7 @@ static ssize_t hl_device_write(struct file *f, const char __user *buf,
 {
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
-	char data[30];
+	char data[30] = {0};
 
 	/* don't allow partial writes */
 	if (*ppos != 0)

drivers/misc/habanalabs/device.c

@@ -231,6 +231,7 @@ static int device_early_init(struct hl_device *hdev)
 
 	mutex_init(&hdev->fd_open_cnt_lock);
 	mutex_init(&hdev->send_cpu_message_lock);
+	mutex_init(&hdev->mmu_cache_lock);
 	INIT_LIST_HEAD(&hdev->hw_queues_mirror_list);
 	spin_lock_init(&hdev->hw_queues_mirror_lock);
 	atomic_set(&hdev->in_reset, 0);
@@ -260,6 +261,7 @@ early_fini:
  */
 static void device_early_fini(struct hl_device *hdev)
 {
+	mutex_destroy(&hdev->mmu_cache_lock);
 	mutex_destroy(&hdev->send_cpu_message_lock);
 
 	hl_cb_mgr_fini(hdev, &hdev->kernel_cb_mgr);

drivers/misc/habanalabs/goya/goya.c

@@ -4819,7 +4819,8 @@ static const struct hl_asic_funcs goya_funcs = {
 	.set_dram_bar_base = goya_set_ddr_bar_base,
 	.init_iatu = goya_init_iatu,
 	.rreg = hl_rreg,
-	.wreg = hl_wreg
+	.wreg = hl_wreg,
+	.halt_coresight = goya_halt_coresight
 };
 
 /*

drivers/misc/habanalabs/goya/goyaP.h

@@ -202,6 +202,7 @@ void goya_add_device_attr(struct hl_device *hdev,
 			struct attribute_group *dev_attr_grp);
 int goya_armcp_info_get(struct hl_device *hdev);
 int goya_debug_coresight(struct hl_device *hdev, void *data);
+void goya_halt_coresight(struct hl_device *hdev);
 
 void goya_mmu_prepare(struct hl_device *hdev, u32 asid);
 int goya_mmu_clear_pgt_range(struct hl_device *hdev);

drivers/misc/habanalabs/goya/goya_coresight.c

@@ -626,3 +626,20 @@ int goya_debug_coresight(struct hl_device *hdev, void *data)
 
 	return rc;
 }
+
+void goya_halt_coresight(struct hl_device *hdev)
+{
+	struct hl_debug_params params = {};
+	int i, rc;
+
+	for (i = GOYA_ETF_FIRST ; i <= GOYA_ETF_LAST ; i++) {
+		params.reg_idx = i;
+		rc = goya_config_etf(hdev, &params);
+		if (rc)
+			dev_err(hdev->dev, "halt ETF failed, %d/%d\n", rc, i);
+	}
+
+	rc = goya_config_etr(hdev, &params);
+	if (rc)
+		dev_err(hdev->dev, "halt ETR failed, %d\n", rc);
+}

drivers/misc/habanalabs/habanalabs.h

@@ -501,6 +501,7 @@ enum hl_pll_frequency {
  * @init_iatu: Initialize the iATU unit inside the PCI controller.
  * @rreg: Read a register. Needed for simulator support.
  * @wreg: Write a register. Needed for simulator support.
+ * @halt_coresight: stop the ETF and ETR traces.
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -578,6 +579,7 @@ struct hl_asic_funcs {
 	int (*init_iatu)(struct hl_device *hdev);
 	u32 (*rreg)(struct hl_device *hdev, u32 reg);
 	void (*wreg)(struct hl_device *hdev, u32 reg, u32 val);
+	void (*halt_coresight)(struct hl_device *hdev);
 };
 
 

drivers/misc/habanalabs/mmu.c

@@ -404,15 +404,12 @@ int hl_mmu_init(struct hl_device *hdev)
 
 	/* MMU H/W init was already done in device hw_init() */
 
-	mutex_init(&hdev->mmu_cache_lock);
-
 	hdev->mmu_pgt_pool =
 			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);
 
 	if (!hdev->mmu_pgt_pool) {
 		dev_err(hdev->dev, "Failed to create page gen pool\n");
-		rc = -ENOMEM;
-		goto err_pool_create;
+		return -ENOMEM;
 	}
 
 	rc = gen_pool_add(hdev->mmu_pgt_pool, prop->mmu_pgt_addr +
@@ -436,8 +433,6 @@ int hl_mmu_init(struct hl_device *hdev)
 
 err_pool_add:
 	gen_pool_destroy(hdev->mmu_pgt_pool);
-err_pool_create:
-	mutex_destroy(&hdev->mmu_cache_lock);
 
 	return rc;
 }
@@ -459,7 +454,6 @@ void hl_mmu_fini(struct hl_device *hdev)
 
 	kvfree(hdev->mmu_shadow_hop0);
 	gen_pool_destroy(hdev->mmu_pgt_pool);
-	mutex_destroy(&hdev->mmu_cache_lock);
 
 	/* MMU H/W fini will be done in device hw_fini() */
 }

include/uapi/misc/habanalabs.h

@@ -413,6 +413,10 @@ struct hl_debug_params_spmu {
 #define HL_DEBUG_OP_SPMU	5
 /* Opcode for timestamp */
 #define HL_DEBUG_OP_TIMESTAMP	6
+/* Opcode for setting the device into or out of debug mode. The enable
+ * variable should be 1 for enabling debug mode and 0 for disabling it
+ */
+#define HL_DEBUG_OP_SET_MODE	7
 
 struct hl_debug_args {
 	/*
@@ -574,8 +578,22 @@ struct hl_debug_args {
  *
  * This IOCTL allows the user to get debug traces from the chip.
  *
- * The user needs to provide the register index and essential data such as
- * buffer address and size.
+ * Before the user can send configuration requests of the various
+ * debug/profile engines, it needs to set the device into debug mode.
+ * This is because the debug/profile infrastructure is shared component in the
+ * device and we can't allow multiple users to access it at the same time.
+ *
+ * Once a user set the device into debug mode, the driver won't allow other
+ * users to "work" with the device, i.e. open a FD. If there are multiple users
+ * opened on the device, the driver won't allow any user to debug the device.
+ *
+ * For each configuration request, the user needs to provide the register index
+ * and essential data such as buffer address and size.
+ *
+ * Once the user has finished using the debug/profile engines, he should
+ * set the device into non-debug mode, i.e. disable debug mode.
+ *
+ * The driver can decide to "kick out" the user if he abuses this interface.
  *
  */
 #define HL_IOCTL_DEBUG		\