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, 333 insertions, 0 deletions

diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c
new file mode 100644
index 000000000..5d3c0ae6b
--- /dev/null
+++ b/drivers/dma/ioat/dca.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel I/OAT DMA Linux driver
+ * Copyright(c) 2007 - 2009 Intel Corporation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/dca.h>
+
+#include <asm/cpuid/api.h>
+
+/* either a kernel change is needed, or we need something like this in kernel */
+#ifndef CONFIG_SMP
+#include <asm/smp.h>
+#undef cpu_physical_id
+#define cpu_physical_id(cpu) (cpuid_ebx(1) >> 24)
+#endif
+
+#include "dma.h"
+#include "registers.h"
+
+/*
+ * Bit 7 of a tag map entry is the "valid" bit, if it is set then bits 0:6
+ * contain the bit number of the APIC ID to map into the DCA tag.  If the valid
+ * bit is not set, then the value must be 0 or 1 and defines the bit in the tag.
+ */
+#define DCA_TAG_MAP_VALID 0x80
+
+#define DCA3_TAG_MAP_BIT_TO_INV 0x80
+#define DCA3_TAG_MAP_BIT_TO_SEL 0x40
+#define DCA3_TAG_MAP_LITERAL_VAL 0x1
+
+#define DCA_TAG_MAP_MASK 0xDF
+
+/* expected tag map bytes for I/OAT ver.2 */
+#define DCA2_TAG_MAP_BYTE0 0x80
+#define DCA2_TAG_MAP_BYTE1 0x0
+#define DCA2_TAG_MAP_BYTE2 0x81
+#define DCA2_TAG_MAP_BYTE3 0x82
+#define DCA2_TAG_MAP_BYTE4 0x82
+
+/*
+ * "Legacy" DCA systems do not implement the DCA register set in the
+ * I/OAT device.  Software needs direct support for their tag mappings.
+ */
+
+#define APICID_BIT(x)		(DCA_TAG_MAP_VALID | (x))
+#define IOAT_TAG_MAP_LEN	8
+
+/* pack PCI B/D/F into a u16 */
+static inline u16 dcaid_from_pcidev(struct pci_dev *pci)
+{
+	return pci_dev_id(pci);
+}
+
+static int dca_enabled_in_bios(struct pci_dev *pdev)
+{
+	/* CPUID level 9 returns DCA configuration */
+	/* Bit 0 indicates DCA enabled by the BIOS */
+	u32 eax;
+	int res;
+
+	eax = cpuid_eax(CPUID_LEAF_DCA);
+	res = eax & BIT(0);
+	if (!res)
+		dev_dbg(&pdev->dev, "DCA is disabled in BIOS\n");
+
+	return res;
+}
+
+int system_has_dca_enabled(struct pci_dev *pdev)
+{
+	if (boot_cpu_has(X86_FEATURE_DCA))
+		return dca_enabled_in_bios(pdev);
+
+	dev_dbg(&pdev->dev, "boot cpu doesn't have X86_FEATURE_DCA\n");
+	return 0;
+}
+
+struct ioat_dca_slot {
+	struct pci_dev *pdev;	/* requester device */
+	u16 rid;		/* requester id, as used by IOAT */
+};
+
+#define IOAT_DCA_MAX_REQ 6
+#define IOAT3_DCA_MAX_REQ 2
+
+struct ioat_dca_priv {
+	void __iomem		*iobase;
+	void __iomem		*dca_base;
+	int			 max_requesters;
+	int			 requester_count;
+	u8			 tag_map[IOAT_TAG_MAP_LEN];
+	struct ioat_dca_slot	 req_slots[];
+};
+
+static int ioat_dca_dev_managed(struct dca_provider *dca,
+				struct device *dev)
+{
+	struct ioat_dca_priv *ioatdca = dca_priv(dca);
+	struct pci_dev *pdev;
+	int i;
+
+	pdev = to_pci_dev(dev);
+	for (i = 0; i < ioatdca->max_requesters; i++) {
+		if (ioatdca->req_slots[i].pdev == pdev)
+			return 1;
+	}
+	return 0;
+}
+
+static int ioat_dca_add_requester(struct dca_provider *dca, struct device *dev)
+{
+	struct ioat_dca_priv *ioatdca = dca_priv(dca);
+	struct pci_dev *pdev;
+	int i;
+	u16 id;
+	u16 global_req_table;
+
+	/* This implementation only supports PCI-Express */
+	if (!dev_is_pci(dev))
+		return -ENODEV;
+	pdev = to_pci_dev(dev);
+	id = dcaid_from_pcidev(pdev);
+
+	if (ioatdca->requester_count == ioatdca->max_requesters)
+		return -ENODEV;
+
+	for (i = 0; i < ioatdca->max_requesters; i++) {
+		if (ioatdca->req_slots[i].pdev == NULL) {
+			/* found an empty slot */
+			ioatdca->requester_count++;
+			ioatdca->req_slots[i].pdev = pdev;
+			ioatdca->req_slots[i].rid = id;
+			global_req_table =
+			      readw(ioatdca->dca_base + IOAT3_DCA_GREQID_OFFSET);
+			writel(id | IOAT_DCA_GREQID_VALID,
+			       ioatdca->iobase + global_req_table + (i * 4));
+			return i;
+		}
+	}
+	/* Error, ioatdma->requester_count is out of whack */
+	return -EFAULT;
+}
+
+static int ioat_dca_remove_requester(struct dca_provider *dca,
+				      struct device *dev)
+{
+	struct ioat_dca_priv *ioatdca = dca_priv(dca);
+	struct pci_dev *pdev;
+	int i;
+	u16 global_req_table;
+
+	/* This implementation only supports PCI-Express */
+	if (!dev_is_pci(dev))
+		return -ENODEV;
+	pdev = to_pci_dev(dev);
+
+	for (i = 0; i < ioatdca->max_requesters; i++) {
+		if (ioatdca->req_slots[i].pdev == pdev) {
+			global_req_table =
+			      readw(ioatdca->dca_base + IOAT3_DCA_GREQID_OFFSET);
+			writel(0, ioatdca->iobase + global_req_table + (i * 4));
+			ioatdca->req_slots[i].pdev = NULL;
+			ioatdca->req_slots[i].rid = 0;
+			ioatdca->requester_count--;
+			return i;
+		}
+	}
+	return -ENODEV;
+}
+
+static u8 ioat_dca_get_tag(struct dca_provider *dca,
+			    struct device *dev,
+			    int cpu)
+{
+	u8 tag;
+
+	struct ioat_dca_priv *ioatdca = dca_priv(dca);
+	int i, apic_id, bit, value;
+	u8 entry;
+
+	tag = 0;
+	apic_id = cpu_physical_id(cpu);
+
+	for (i = 0; i < IOAT_TAG_MAP_LEN; i++) {
+		entry = ioatdca->tag_map[i];
+		if (entry & DCA3_TAG_MAP_BIT_TO_SEL) {
+			bit = entry &
+				~(DCA3_TAG_MAP_BIT_TO_SEL | DCA3_TAG_MAP_BIT_TO_INV);
+			value = (apic_id & (1 << bit)) ? 1 : 0;
+		} else if (entry & DCA3_TAG_MAP_BIT_TO_INV) {
+			bit = entry & ~DCA3_TAG_MAP_BIT_TO_INV;
+			value = (apic_id & (1 << bit)) ? 0 : 1;
+		} else {
+			value = (entry & DCA3_TAG_MAP_LITERAL_VAL) ? 1 : 0;
+		}
+		tag |= (value << i);
+	}
+
+	return tag;
+}
+
+static const struct dca_ops ioat_dca_ops = {
+	.add_requester		= ioat_dca_add_requester,
+	.remove_requester	= ioat_dca_remove_requester,
+	.get_tag		= ioat_dca_get_tag,
+	.dev_managed		= ioat_dca_dev_managed,
+};
+
+static int ioat_dca_count_dca_slots(void *iobase, u16 dca_offset)
+{
+	int slots = 0;
+	u32 req;
+	u16 global_req_table;
+
+	global_req_table = readw(iobase + dca_offset + IOAT3_DCA_GREQID_OFFSET);
+	if (global_req_table == 0)
+		return 0;
+
+	do {
+		req = readl(iobase + global_req_table + (slots * sizeof(u32)));
+		slots++;
+	} while ((req & IOAT_DCA_GREQID_LASTID) == 0);
+
+	return slots;
+}
+
+static inline int dca3_tag_map_invalid(u8 *tag_map)
+{
+	/*
+	 * If the tag map is not programmed by the BIOS the default is:
+	 * 0x80 0x80 0x80 0x80 0x80 0x00 0x00 0x00
+	 *
+	 * This an invalid map and will result in only 2 possible tags
+	 * 0x1F and 0x00.  0x00 is an invalid DCA tag so we know that
+	 * this entire definition is invalid.
+	 */
+	return ((tag_map[0] == DCA_TAG_MAP_VALID) &&
+		(tag_map[1] == DCA_TAG_MAP_VALID) &&
+		(tag_map[2] == DCA_TAG_MAP_VALID) &&
+		(tag_map[3] == DCA_TAG_MAP_VALID) &&
+		(tag_map[4] == DCA_TAG_MAP_VALID));
+}
+
+struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
+{
+	struct dca_provider *dca;
+	struct ioat_dca_priv *ioatdca;
+	int slots;
+	int i;
+	int err;
+	u16 dca_offset;
+	u16 csi_fsb_control;
+	u16 pcie_control;
+	u8 bit;
+
+	union {
+		u64 full;
+		struct {
+			u32 low;
+			u32 high;
+		};
+	} tag_map;
+
+	if (!system_has_dca_enabled(pdev))
+		return NULL;
+
+	dca_offset = readw(iobase + IOAT_DCAOFFSET_OFFSET);
+	if (dca_offset == 0)
+		return NULL;
+
+	slots = ioat_dca_count_dca_slots(iobase, dca_offset);
+	if (slots == 0)
+		return NULL;
+
+	dca = alloc_dca_provider(&ioat_dca_ops,
+				 struct_size(ioatdca, req_slots, slots));
+	if (!dca)
+		return NULL;
+
+	ioatdca = dca_priv(dca);
+	ioatdca->iobase = iobase;
+	ioatdca->dca_base = iobase + dca_offset;
+	ioatdca->max_requesters = slots;
+
+	/* some bios might not know to turn these on */
+	csi_fsb_control = readw(ioatdca->dca_base + IOAT3_CSI_CONTROL_OFFSET);
+	if ((csi_fsb_control & IOAT3_CSI_CONTROL_PREFETCH) == 0) {
+		csi_fsb_control |= IOAT3_CSI_CONTROL_PREFETCH;
+		writew(csi_fsb_control,
+		       ioatdca->dca_base + IOAT3_CSI_CONTROL_OFFSET);
+	}
+	pcie_control = readw(ioatdca->dca_base + IOAT3_PCI_CONTROL_OFFSET);
+	if ((pcie_control & IOAT3_PCI_CONTROL_MEMWR) == 0) {
+		pcie_control |= IOAT3_PCI_CONTROL_MEMWR;
+		writew(pcie_control,
+		       ioatdca->dca_base + IOAT3_PCI_CONTROL_OFFSET);
+	}
+
+
+	/* TODO version, compatibility and configuration checks */
+
+	/* copy out the APIC to DCA tag map */
+	tag_map.low =
+		readl(ioatdca->dca_base + IOAT3_APICID_TAG_MAP_OFFSET_LOW);
+	tag_map.high =
+		readl(ioatdca->dca_base + IOAT3_APICID_TAG_MAP_OFFSET_HIGH);
+	for (i = 0; i < 8; i++) {
+		bit = tag_map.full >> (8 * i);
+		ioatdca->tag_map[i] = bit & DCA_TAG_MAP_MASK;
+	}
+
+	if (dca3_tag_map_invalid(ioatdca->tag_map)) {
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		pr_warn_once("%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n",
+			     dev_driver_string(&pdev->dev),
+			     dev_name(&pdev->dev));
+		free_dca_provider(dca);
+		return NULL;
+	}
+
+	err = register_dca_provider(dca, &pdev->dev);
+	if (err) {
+		free_dca_provider(dca);
+		return NULL;
+	}
+
+	return dca;
+}