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, 283 insertions, 0 deletions

diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
new file mode 100644
index 000000000..99bb2b916
--- /dev/null
+++ b/arch/powerpc/sysdev/i8259.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * i8259 interrupt controller driver.
+ */
+#undef DEBUG
+
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <asm/io.h>
+#include <asm/i8259.h>
+
+static volatile void __iomem *pci_intack; /* RO, gives us the irq vector */
+
+static unsigned char cached_8259[2] = { 0xff, 0xff };
+#define cached_A1 (cached_8259[0])
+#define cached_21 (cached_8259[1])
+
+static DEFINE_RAW_SPINLOCK(i8259_lock);
+
+static struct irq_domain *i8259_host;
+
+/*
+ * Acknowledge the IRQ using either the PCI host bridge's interrupt
+ * acknowledge feature or poll.  How i8259_init() is called determines
+ * which is called.  It should be noted that polling is broken on some
+ * IBM and Motorola PReP boxes so we must use the int-ack feature on them.
+ */
+unsigned int i8259_irq(void)
+{
+	int irq;
+	int lock = 0;
+
+	/* Either int-ack or poll for the IRQ */
+	if (pci_intack)
+		irq = readb(pci_intack);
+	else {
+		raw_spin_lock(&i8259_lock);
+		lock = 1;
+
+		/* Perform an interrupt acknowledge cycle on controller 1. */
+		outb(0x0C, 0x20);		/* prepare for poll */
+		irq = inb(0x20) & 7;
+		if (irq == 2 ) {
+			/*
+			 * Interrupt is cascaded so perform interrupt
+			 * acknowledge on controller 2.
+			 */
+			outb(0x0C, 0xA0);	/* prepare for poll */
+			irq = (inb(0xA0) & 7) + 8;
+		}
+	}
+
+	if (irq == 7) {
+		/*
+		 * This may be a spurious interrupt.
+		 *
+		 * Read the interrupt status register (ISR). If the most
+		 * significant bit is not set then there is no valid
+		 * interrupt.
+		 */
+		if (!pci_intack)
+			outb(0x0B, 0x20);	/* ISR register */
+		if(~inb(0x20) & 0x80)
+			irq = 0;
+	} else if (irq == 0xff)
+		irq = 0;
+
+	if (lock)
+		raw_spin_unlock(&i8259_lock);
+	return irq;
+}
+
+static void i8259_mask_and_ack_irq(struct irq_data *d)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&i8259_lock, flags);
+	if (d->irq > 7) {
+		cached_A1 |= 1 << (d->irq-8);
+		inb(0xA1); 	/* DUMMY */
+		outb(cached_A1, 0xA1);
+		outb(0x20, 0xA0);	/* Non-specific EOI */
+		outb(0x20, 0x20);	/* Non-specific EOI to cascade */
+	} else {
+		cached_21 |= 1 << d->irq;
+		inb(0x21); 	/* DUMMY */
+		outb(cached_21, 0x21);
+		outb(0x20, 0x20);	/* Non-specific EOI */
+	}
+	raw_spin_unlock_irqrestore(&i8259_lock, flags);
+}
+
+static void i8259_set_irq_mask(int irq_nr)
+{
+	outb(cached_A1,0xA1);
+	outb(cached_21,0x21);
+}
+
+static void i8259_mask_irq(struct irq_data *d)
+{
+	unsigned long flags;
+
+	pr_debug("i8259_mask_irq(%d)\n", d->irq);
+
+	raw_spin_lock_irqsave(&i8259_lock, flags);
+	if (d->irq < 8)
+		cached_21 |= 1 << d->irq;
+	else
+		cached_A1 |= 1 << (d->irq-8);
+	i8259_set_irq_mask(d->irq);
+	raw_spin_unlock_irqrestore(&i8259_lock, flags);
+}
+
+static void i8259_unmask_irq(struct irq_data *d)
+{
+	unsigned long flags;
+
+	pr_debug("i8259_unmask_irq(%d)\n", d->irq);
+
+	raw_spin_lock_irqsave(&i8259_lock, flags);
+	if (d->irq < 8)
+		cached_21 &= ~(1 << d->irq);
+	else
+		cached_A1 &= ~(1 << (d->irq-8));
+	i8259_set_irq_mask(d->irq);
+	raw_spin_unlock_irqrestore(&i8259_lock, flags);
+}
+
+static struct irq_chip i8259_pic = {
+	.name		= "i8259",
+	.irq_mask	= i8259_mask_irq,
+	.irq_disable	= i8259_mask_irq,
+	.irq_unmask	= i8259_unmask_irq,
+	.irq_mask_ack	= i8259_mask_and_ack_irq,
+};
+
+static struct resource pic1_iores = {
+	.name = "8259 (master)",
+	.start = 0x20,
+	.end = 0x21,
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static struct resource pic2_iores = {
+	.name = "8259 (slave)",
+	.start = 0xa0,
+	.end = 0xa1,
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static struct resource pic_edgectrl_iores = {
+	.name = "8259 edge control",
+	.start = 0x4d0,
+	.end = 0x4d1,
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static int i8259_host_match(struct irq_domain *h, struct device_node *node,
+			    enum irq_domain_bus_token bus_token)
+{
+	struct device_node *of_node = irq_domain_get_of_node(h);
+	return of_node == NULL || of_node == node;
+}
+
+static int i8259_host_map(struct irq_domain *h, unsigned int virq,
+			  irq_hw_number_t hw)
+{
+	pr_debug("i8259_host_map(%d, 0x%lx)\n", virq, hw);
+
+	/* We block the internal cascade */
+	if (hw == 2)
+		irq_set_status_flags(virq, IRQ_NOREQUEST);
+
+	/* We use the level handler only for now, we might want to
+	 * be more cautious here but that works for now
+	 */
+	irq_set_status_flags(virq, IRQ_LEVEL);
+	irq_set_chip_and_handler(virq, &i8259_pic, handle_level_irq);
+	return 0;
+}
+
+static int i8259_host_xlate(struct irq_domain *h, struct device_node *ct,
+			    const u32 *intspec, unsigned int intsize,
+			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
+{
+	static unsigned char map_isa_senses[4] = {
+		IRQ_TYPE_LEVEL_LOW,
+		IRQ_TYPE_LEVEL_HIGH,
+		IRQ_TYPE_EDGE_FALLING,
+		IRQ_TYPE_EDGE_RISING,
+	};
+
+	*out_hwirq = intspec[0];
+	if (intsize > 1 && intspec[1] < 4)
+		*out_flags = map_isa_senses[intspec[1]];
+	else
+		*out_flags = IRQ_TYPE_NONE;
+
+	return 0;
+}
+
+static const struct irq_domain_ops i8259_host_ops = {
+	.match = i8259_host_match,
+	.map = i8259_host_map,
+	.xlate = i8259_host_xlate,
+};
+
+struct irq_domain *__init i8259_get_host(void)
+{
+	return i8259_host;
+}
+
+/**
+ * i8259_init - Initialize the legacy controller
+ * @node: device node of the legacy PIC (can be NULL, but then, it will match
+ *        all interrupts, so beware)
+ * @intack_addr: PCI interrupt acknowledge (real) address which will return
+ *             	 the active irq from the 8259
+ */
+void i8259_init(struct device_node *node, unsigned long intack_addr)
+{
+	unsigned long flags;
+
+	/* initialize the controller */
+	raw_spin_lock_irqsave(&i8259_lock, flags);
+
+	/* Mask all first */
+	outb(0xff, 0xA1);
+	outb(0xff, 0x21);
+
+	/* init master interrupt controller */
+	outb(0x11, 0x20); /* Start init sequence */
+	outb(0x00, 0x21); /* Vector base */
+	outb(0x04, 0x21); /* edge triggered, Cascade (slave) on IRQ2 */
+	outb(0x01, 0x21); /* Select 8086 mode */
+
+	/* init slave interrupt controller */
+	outb(0x11, 0xA0); /* Start init sequence */
+	outb(0x08, 0xA1); /* Vector base */
+	outb(0x02, 0xA1); /* edge triggered, Cascade (slave) on IRQ2 */
+	outb(0x01, 0xA1); /* Select 8086 mode */
+
+	/* That thing is slow */
+	udelay(100);
+
+	/* always read ISR */
+	outb(0x0B, 0x20);
+	outb(0x0B, 0xA0);
+
+	/* Unmask the internal cascade */
+	cached_21 &= ~(1 << 2);
+
+	/* Set interrupt masks */
+	outb(cached_A1, 0xA1);
+	outb(cached_21, 0x21);
+
+	raw_spin_unlock_irqrestore(&i8259_lock, flags);
+
+	/* create a legacy host */
+	i8259_host = irq_domain_create_legacy(of_fwnode_handle(node), NR_IRQS_LEGACY, 0, 0,
+					      &i8259_host_ops, NULL);
+	if (i8259_host == NULL) {
+		printk(KERN_ERR "i8259: failed to allocate irq host !\n");
+		return;
+	}
+
+	/* reserve our resources */
+	/* XXX should we continue doing that ? it seems to cause problems
+	 * with further requesting of PCI IO resources for that range...
+	 * need to look into it.
+	 */
+	request_resource(&ioport_resource, &pic1_iores);
+	request_resource(&ioport_resource, &pic2_iores);
+	request_resource(&ioport_resource, &pic_edgectrl_iores);
+
+	if (intack_addr != 0)
+		pci_intack = ioremap(intack_addr, 1);
+
+	printk(KERN_INFO "i8259 legacy interrupt controller initialized\n");
+}