15 files changed, 98 insertions, 73 deletions

diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 8c1b63a4337b..d2098b4d2945 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -780,6 +780,8 @@ static int genwqe_pin_mem(struct genwqe_file *cfile, struct genwqe_mem *m)
 
 	if ((m->addr == 0x0) || (m->size == 0))
 		return -EINVAL;
+	if (m->size > ULONG_MAX - PAGE_SIZE - (m->addr & ~PAGE_MASK))
+		return -EINVAL;
 
 	map_addr = (m->addr & PAGE_MASK);
 	map_size = round_up(m->size + (m->addr & ~PAGE_MASK), PAGE_SIZE);
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 89cff9d1012b..7571700abc6e 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -586,6 +586,10 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
 	/* determine space needed for page_list. */
 	data = (unsigned long)uaddr;
 	offs = offset_in_page(data);
+	if (size > ULONG_MAX - PAGE_SIZE - offs) {
+		m->size = 0;	/* mark unused and not added */
+		return -EINVAL;
+	}
 	m->nr_pages = DIV_ROUND_UP(offs + size, PAGE_SIZE);
 
 	m->page_list = kcalloc(m->nr_pages,
diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c
index 4804cdcf4c48..f4c92f110a72 100644
--- a/drivers/misc/habanalabs/context.c
+++ b/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);
 	}
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index a4447699ff4e..ba418aaa404c 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/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;
 
@@ -510,6 +500,7 @@ static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 {
 	struct hl_ctx *ctx = hdev->user_ctx;
 	u64 hop_addr, hop_pte_addr, hop_pte;
+	u64 offset_mask = HOP4_MASK | OFFSET_MASK;
 	int rc = 0;
 
 	if (!ctx) {
@@ -552,12 +543,14 @@ static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 			goto not_mapped;
 		hop_pte_addr = get_hop4_pte_addr(ctx, hop_addr, virt_addr);
 		hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+		offset_mask = OFFSET_MASK;
 	}
 
 	if (!(hop_pte & PAGE_PRESENT_MASK))
 		goto not_mapped;
 
-	*phys_addr = (hop_pte & PTE_PHYS_ADDR_MASK) | (virt_addr & OFFSET_MASK);
+	*phys_addr = (hop_pte & ~offset_mask) | (virt_addr & offset_mask);
 
 	goto out;
 
@@ -600,10 +593,8 @@ 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 +636,6 @@ 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 +650,8 @@ 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 +704,8 @@ 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 +794,9 @@ 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 +804,7 @@ 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)
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 91a9e47a3482..0b19d3eefb98 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/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);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index a582e29c1ee4..02d116b01a1a 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/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
 };
 
 /*
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index 14e216cb3668..c83cab0d641e 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/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);
diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c
index 1ac951f52d1e..d7ec7ad84cc6 100644
--- a/drivers/misc/habanalabs/goya/goya_coresight.c
+++ b/drivers/misc/habanalabs/goya/goya_coresight.c
@@ -425,8 +425,18 @@ static int goya_config_etr(struct hl_device *hdev,
 		WREG32(base_reg + 0x28, 0);
 		WREG32(base_reg + 0x304, 0);
 
-		if (params->output_size >= sizeof(u32))
-			*(u32 *) params->output = RREG32(base_reg + 0x18);
+		if (params->output_size >= sizeof(u64)) {
+			u32 rwp, rwphi;
+
+			/*
+			 * The trace buffer address is 40 bits wide. The end of
+			 * the buffer is set in the RWP register (lower 32
+			 * bits), and in the RWPHI register (upper 8 bits).
+			 */
+			rwp = RREG32(base_reg + 0x18);
+			rwphi = RREG32(base_reg + 0x3c) & 0xff;
+			*(u64 *) params->output = ((u64) rwphi << 32) | rwp;
+		}
 	}
 
 	return 0;
@@ -626,3 +636,20 @@ 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);
+}
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 71243b319920..adef7d9d7488 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/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);
 };
 
 
diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c
index d67d24c13efd..693877e37fd8 100644
--- a/drivers/misc/habanalabs/memory.c
+++ b/drivers/misc/habanalabs/memory.c
@@ -675,11 +675,6 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 
 		total_npages += npages;
 
-		if (first) {
-			first = false;
-			dma_addr &= PAGE_MASK_2MB;
-		}
-
 		if ((npages % PGS_IN_2MB_PAGE) ||
 					(dma_addr & (PAGE_SIZE_2MB - 1)))
 			is_huge_page_opt = false;
@@ -704,7 +699,6 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 	phys_pg_pack->total_size = total_npages * page_size;
 
 	j = 0;
-	first = true;
 	for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents, i) {
 		npages = get_sg_info(sg, &dma_addr);
 
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c
index 533d9315b6fb..10aee3141444 100644
--- a/drivers/misc/habanalabs/mmu.c
+++ b/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() */
 }
diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index 7eebbdfbcacd..17f839dee976 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -32,12 +32,20 @@ static int recur_count = REC_NUM_DEFAULT;
 
 static DEFINE_SPINLOCK(lock_me_up);
 
-static int recursive_loop(int remaining)
+/*
+ * Make sure compiler does not optimize this function or stack frame away:
+ * - function marked noinline
+ * - stack variables are marked volatile
+ * - stack variables are written (memset()) and read (pr_info())
+ * - function has external effects (pr_info())
+ * */
+static int noinline recursive_loop(int remaining)
 {
-	char buf[REC_STACK_SIZE];
+	volatile char buf[REC_STACK_SIZE];
 
-	/* Make sure compiler does not optimize this away. */
-	memset(buf, (remaining & 0xff) | 0x1, REC_STACK_SIZE);
+	memset((void *)buf, remaining & 0xFF, sizeof(buf));
+	pr_info("loop %d/%d ...\n", (int)buf[remaining % sizeof(buf)],
+		recur_count);
 	if (!remaining)
 		return 0;
 	else
@@ -81,9 +89,12 @@ void lkdtm_LOOP(void)
 		;
 }
 
-void lkdtm_OVERFLOW(void)
+void lkdtm_EXHAUST_STACK(void)
 {
-	(void) recursive_loop(recur_count);
+	pr_info("Calling function with %d frame size to depth %d ...\n",
+		REC_STACK_SIZE, recur_count);
+	recursive_loop(recur_count);
+	pr_info("FAIL: survived without exhausting stack?!\n");
 }
 
 static noinline void __lkdtm_CORRUPT_STACK(void *stack)
diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c
index 1972dad966f5..8a1428d4f138 100644
--- a/drivers/misc/lkdtm/core.c
+++ b/drivers/misc/lkdtm/core.c
@@ -106,12 +106,12 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(WARNING),
 	CRASHTYPE(EXCEPTION),
 	CRASHTYPE(LOOP),
-	CRASHTYPE(OVERFLOW),
+	CRASHTYPE(EXHAUST_STACK),
+	CRASHTYPE(CORRUPT_STACK),
+	CRASHTYPE(CORRUPT_STACK_STRONG),
 	CRASHTYPE(CORRUPT_LIST_ADD),
 	CRASHTYPE(CORRUPT_LIST_DEL),
 	CRASHTYPE(CORRUPT_USER_DS),
-	CRASHTYPE(CORRUPT_STACK),
-	CRASHTYPE(CORRUPT_STACK_STRONG),
 	CRASHTYPE(STACK_GUARD_PAGE_LEADING),
 	CRASHTYPE(STACK_GUARD_PAGE_TRAILING),
 	CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE),
diff --git a/drivers/misc/lkdtm/lkdtm.h b/drivers/misc/lkdtm/lkdtm.h
index b69ee004a3f7..23dc565b4307 100644
--- a/drivers/misc/lkdtm/lkdtm.h
+++ b/drivers/misc/lkdtm/lkdtm.h
@@ -13,7 +13,7 @@ void lkdtm_BUG(void);
 void lkdtm_WARNING(void);
 void lkdtm_EXCEPTION(void);
 void lkdtm_LOOP(void);
-void lkdtm_OVERFLOW(void);
+void lkdtm_EXHAUST_STACK(void);
 void lkdtm_CORRUPT_STACK(void);
 void lkdtm_CORRUPT_STACK_STRONG(void);
 void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void);
diff --git a/drivers/misc/lkdtm/usercopy.c b/drivers/misc/lkdtm/usercopy.c
index d5a0e7f1813b..e172719dd86d 100644
--- a/drivers/misc/lkdtm/usercopy.c
+++ b/drivers/misc/lkdtm/usercopy.c
@@ -324,14 +324,16 @@ free_user:
 
 void lkdtm_USERCOPY_KERNEL_DS(void)
 {
-	char __user *user_ptr = (char __user *)ERR_PTR(-EINVAL);
+	char __user *user_ptr =
+		(char __user *)(0xFUL << (sizeof(unsigned long) * 8 - 4));
 	mm_segment_t old_fs = get_fs();
 	char buf[10] = {0};
 
-	pr_info("attempting copy_to_user on unmapped kernel address\n");
+	pr_info("attempting copy_to_user() to noncanonical address: %px\n",
+		user_ptr);
 	set_fs(KERNEL_DS);
-	if (copy_to_user(user_ptr, buf, sizeof(buf)))
-		pr_info("copy_to_user un unmapped kernel address failed\n");
+	if (copy_to_user(user_ptr, buf, sizeof(buf)) == 0)
+		pr_err("copy_to_user() to noncanonical address succeeded!?\n");
 	set_fs(old_fs);
 }