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, 218 insertions, 0 deletions

diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c
new file mode 100644
index 000000000..5edbffd4e
--- /dev/null
+++ b/drivers/firmware/efi/memattr.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#define pr_fmt(fmt)	"efi: memattr: " fmt
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+
+#include <asm/early_ioremap.h>
+
+static int __initdata tbl_size;
+unsigned long __ro_after_init efi_mem_attr_table = EFI_INVALID_TABLE_ADDR;
+
+/*
+ * Reserve the memory associated with the Memory Attributes configuration
+ * table, if it exists.
+ */
+void __init efi_memattr_init(void)
+{
+	efi_memory_attributes_table_t *tbl;
+
+	if (efi_mem_attr_table == EFI_INVALID_TABLE_ADDR)
+		return;
+
+	tbl = early_memremap(efi_mem_attr_table, sizeof(*tbl));
+	if (!tbl) {
+		pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n",
+		       efi_mem_attr_table);
+		return;
+	}
+
+	if (tbl->version > 2) {
+		pr_warn("Unexpected EFI Memory Attributes table version %d\n",
+			tbl->version);
+		goto unmap;
+	}
+
+	/*
+	 * The EFI memory attributes table descriptors might potentially be
+	 * smaller than those used by the EFI memory map, as long as they can
+	 * fit a efi_memory_desc_t. However, a larger descriptor size makes no
+	 * sense, and might be an indication that the table is corrupted.
+	 *
+	 * The only exception is kexec_load(), where the EFI memory map is
+	 * reconstructed by user space, and may use a smaller descriptor size
+	 * than the original. Given that, ignoring this companion table is
+	 * still the right thing to do here, but don't complain too loudly when
+	 * this happens.
+	 */
+	if (tbl->desc_size < sizeof(efi_memory_desc_t) ||
+	    tbl->desc_size > efi.memmap.desc_size) {
+		pr_warn("Unexpected EFI Memory Attributes descriptor size %u (expected: %lu)\n",
+			tbl->desc_size, efi.memmap.desc_size);
+		goto unmap;
+	}
+
+	/*
+	 * Sanity check: the Memory Attributes Table contains multiple entries
+	 * for each EFI runtime services code or data region in the EFI memory
+	 * map, each with the permission attributes that may be applied when
+	 * mapping the region.  There is no upper bound for the number of
+	 * entries, as it could conceivably contain more entries than the EFI
+	 * memory map itself. So pick an arbitrary limit of 64k, which is
+	 * ludicrously high. This prevents a corrupted table from eating all
+	 * system RAM.
+	 */
+	if (tbl->num_entries > SZ_64K) {
+		pr_warn(FW_BUG "Corrupted EFI Memory Attributes Table detected! (version == %u, desc_size == %u, num_entries == %u)\n",
+			tbl->version, tbl->desc_size, tbl->num_entries);
+		goto unmap;
+	}
+
+	tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size;
+	memblock_reserve(efi_mem_attr_table, tbl_size);
+	set_bit(EFI_MEM_ATTR, &efi.flags);
+
+unmap:
+	early_memunmap(tbl, sizeof(*tbl));
+}
+
+/*
+ * Returns a copy @out of the UEFI memory descriptor @in if it is covered
+ * entirely by a UEFI memory map entry with matching attributes. The virtual
+ * address of @out is set according to the matching entry that was found.
+ */
+static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out)
+{
+	u64 in_paddr = in->phys_addr;
+	u64 in_size = in->num_pages << EFI_PAGE_SHIFT;
+	efi_memory_desc_t *md;
+
+	*out = *in;
+
+	if (in->type != EFI_RUNTIME_SERVICES_CODE &&
+	    in->type != EFI_RUNTIME_SERVICES_DATA) {
+		pr_warn("Entry type should be RuntimeServiceCode/Data\n");
+		return false;
+	}
+
+	if (PAGE_SIZE > EFI_PAGE_SIZE &&
+	    (!PAGE_ALIGNED(in->phys_addr) ||
+	     !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) {
+		/*
+		 * Since arm64 may execute with page sizes of up to 64 KB, the
+		 * UEFI spec mandates that RuntimeServices memory regions must
+		 * be 64 KB aligned. We need to validate this here since we will
+		 * not be able to tighten permissions on such regions without
+		 * affecting adjacent regions.
+		 */
+		pr_warn("Entry address region misaligned\n");
+		return false;
+	}
+
+	for_each_efi_memory_desc(md) {
+		u64 md_paddr = md->phys_addr;
+		u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0 && md->phys_addr != 0) {
+			/* no virtual mapping has been installed by the stub */
+			break;
+		}
+
+		if (md_paddr > in_paddr || (in_paddr - md_paddr) >= md_size)
+			continue;
+
+		/*
+		 * This entry covers the start of @in, check whether
+		 * it covers the end as well.
+		 */
+		if (md_paddr + md_size < in_paddr + in_size) {
+			pr_warn("Entry covers multiple EFI memory map regions\n");
+			return false;
+		}
+
+		if (md->type != in->type) {
+			pr_warn("Entry type deviates from EFI memory map region type\n");
+			return false;
+		}
+
+		out->virt_addr = in_paddr + (md->virt_addr - md_paddr);
+
+		return true;
+	}
+
+	pr_warn("No matching entry found in the EFI memory map\n");
+	return false;
+}
+
+/*
+ * To be called after the EFI page tables have been populated. If a memory
+ * attributes table is available, its contents will be used to update the
+ * mappings with tightened permissions as described by the table.
+ * This requires the UEFI memory map to have already been populated with
+ * virtual addresses.
+ */
+int __init efi_memattr_apply_permissions(struct mm_struct *mm,
+					 efi_memattr_perm_setter fn)
+{
+	efi_memory_attributes_table_t *tbl;
+	bool has_bti = false;
+	int i, ret;
+
+	if (tbl_size <= sizeof(*tbl))
+		return 0;
+
+	/*
+	 * We need the EFI memory map to be setup so we can use it to
+	 * lookup the virtual addresses of all entries in the  of EFI
+	 * Memory Attributes table. If it isn't available, this
+	 * function should not be called.
+	 */
+	if (WARN_ON(!efi_enabled(EFI_MEMMAP)))
+		return 0;
+
+	tbl = memremap(efi_mem_attr_table, tbl_size, MEMREMAP_WB);
+	if (!tbl) {
+		pr_err("Failed to map EFI Memory Attributes table @ 0x%lx\n",
+		       efi_mem_attr_table);
+		return -ENOMEM;
+	}
+
+	if (tbl->version > 1 &&
+	    (tbl->flags & EFI_MEMORY_ATTRIBUTES_FLAGS_RT_FORWARD_CONTROL_FLOW_GUARD))
+		has_bti = true;
+
+	if (efi_enabled(EFI_DBG))
+		pr_info("Processing EFI Memory Attributes table:\n");
+
+	for (i = ret = 0; ret == 0 && i < tbl->num_entries; i++) {
+		efi_memory_desc_t md;
+		unsigned long size;
+		bool valid;
+		char buf[64];
+
+		valid = entry_is_valid(efi_memdesc_ptr(tbl->entry, tbl->desc_size, i),
+				       &md);
+		size = md.num_pages << EFI_PAGE_SHIFT;
+		if (efi_enabled(EFI_DBG) || !valid)
+			pr_info("%s 0x%012llx-0x%012llx %s\n",
+				valid ? "" : "!", md.phys_addr,
+				md.phys_addr + size - 1,
+				efi_md_typeattr_format(buf, sizeof(buf), &md));
+
+		if (valid) {
+			ret = fn(mm, &md, has_bti);
+			if (ret)
+				pr_err("Error updating mappings, skipping subsequent md's\n");
+		}
+	}
+	memunmap(tbl);
+	return ret;
+}