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, 278 insertions, 0 deletions

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
new file mode 100644
index 000000000..6103b1a08
--- /dev/null
+++ b/drivers/firmware/efi/efi-init.c
@@ -0,0 +1,278 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013 - 2015 Linaro Ltd.
+ */
+
+#define pr_fmt(fmt)	"efi: " fmt
+
+#include <linux/efi.h>
+#include <linux/fwnode.h>
+#include <linux/init.h>
+#include <linux/kexec_handover.h>
+#include <linux/memblock.h>
+#include <linux/mm_types.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
+#include <linux/platform_device.h>
+#include <linux/sysfb.h>
+
+#include <asm/efi.h>
+
+unsigned long __initdata primary_display_table = EFI_INVALID_TABLE_ADDR;
+
+static int __init is_memory(efi_memory_desc_t *md)
+{
+	if (md->attribute & (EFI_MEMORY_WB|EFI_MEMORY_WT|EFI_MEMORY_WC))
+		return 1;
+	return 0;
+}
+
+/*
+ * Translate a EFI virtual address into a physical address: this is necessary,
+ * as some data members of the EFI system table are virtually remapped after
+ * SetVirtualAddressMap() has been called.
+ */
+static phys_addr_t __init efi_to_phys(unsigned long addr)
+{
+	efi_memory_desc_t *md;
+
+	for_each_efi_memory_desc(md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0)
+			/* no virtual mapping has been installed by the stub */
+			break;
+		if (md->virt_addr <= addr &&
+		    (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
+			return md->phys_addr + addr - md->virt_addr;
+	}
+	return addr;
+}
+
+extern __weak const efi_config_table_type_t efi_arch_tables[];
+
+/*
+ * x86 defines its own instance of sysfb_primary_display and uses
+ * it even without EFI, everything else can get them from here.
+ */
+#if !defined(CONFIG_X86) && (defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_FIRMWARE_EDID))
+struct sysfb_display_info sysfb_primary_display __section(".data");
+EXPORT_SYMBOL_GPL(sysfb_primary_display);
+#endif
+
+static void __init init_primary_display(void)
+{
+	struct sysfb_display_info *dpy;
+
+	if (primary_display_table != EFI_INVALID_TABLE_ADDR) {
+		dpy = early_memremap(primary_display_table, sizeof(*dpy));
+		if (!dpy) {
+			pr_err("Could not map primary_display config table\n");
+			return;
+		}
+		sysfb_primary_display = *dpy;
+		memset(dpy, 0, sizeof(*dpy));
+		early_memunmap(dpy, sizeof(*dpy));
+
+		if (memblock_is_map_memory(sysfb_primary_display.screen.lfb_base))
+			memblock_mark_nomap(sysfb_primary_display.screen.lfb_base,
+					    sysfb_primary_display.screen.lfb_size);
+
+		if (IS_ENABLED(CONFIG_EFI_EARLYCON))
+			efi_earlycon_reprobe();
+	}
+}
+
+static int __init uefi_init(u64 efi_system_table)
+{
+	efi_config_table_t *config_tables;
+	efi_system_table_t *systab;
+	size_t table_size;
+	int retval;
+
+	systab = early_memremap_ro(efi_system_table, sizeof(efi_system_table_t));
+	if (systab == NULL) {
+		pr_warn("Unable to map EFI system table.\n");
+		return -ENOMEM;
+	}
+
+	set_bit(EFI_BOOT, &efi.flags);
+	if (IS_ENABLED(CONFIG_64BIT))
+		set_bit(EFI_64BIT, &efi.flags);
+
+	retval = efi_systab_check_header(&systab->hdr);
+	if (retval)
+		goto out;
+
+	efi.runtime = systab->runtime;
+	efi.runtime_version = systab->hdr.revision;
+
+	efi_systab_report_header(&systab->hdr, efi_to_phys(systab->fw_vendor));
+
+	table_size = sizeof(efi_config_table_t) * systab->nr_tables;
+	config_tables = early_memremap_ro(efi_to_phys(systab->tables),
+					  table_size);
+	if (config_tables == NULL) {
+		pr_warn("Unable to map EFI config table array.\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+	retval = efi_config_parse_tables(config_tables, systab->nr_tables,
+					 efi_arch_tables);
+
+	early_memunmap(config_tables, table_size);
+out:
+	early_memunmap(systab, sizeof(efi_system_table_t));
+	return retval;
+}
+
+/*
+ * Return true for regions that can be used as System RAM.
+ */
+static __init int is_usable_memory(efi_memory_desc_t *md)
+{
+	switch (md->type) {
+	case EFI_LOADER_CODE:
+	case EFI_LOADER_DATA:
+	case EFI_ACPI_RECLAIM_MEMORY:
+	case EFI_BOOT_SERVICES_CODE:
+	case EFI_BOOT_SERVICES_DATA:
+	case EFI_CONVENTIONAL_MEMORY:
+	case EFI_PERSISTENT_MEMORY:
+		/*
+		 * According to the spec, these regions are no longer reserved
+		 * after calling ExitBootServices(). However, we can only use
+		 * them as System RAM if they can be mapped writeback cacheable.
+		 */
+		return (md->attribute & EFI_MEMORY_WB);
+	default:
+		break;
+	}
+	return false;
+}
+
+static __init void reserve_regions(void)
+{
+	efi_memory_desc_t *md;
+	u64 paddr, npages, size;
+
+	if (efi_enabled(EFI_DBG))
+		pr_info("Processing EFI memory map:\n");
+
+	/*
+	 * Discard memblocks discovered so far except for KHO scratch
+	 * regions. Most memblocks at this point originate from memory nodes
+	 * in the DT and UEFI uses its own memory map instead. However, if
+	 * KHO is enabled, scratch regions, which are good known memory
+	 * must be preserved.
+	 */
+	memblock_dump_all();
+
+	if (is_kho_boot()) {
+		struct memblock_region *r;
+
+		/* Remove all non-KHO regions */
+		for_each_mem_region(r) {
+			if (!memblock_is_kho_scratch(r)) {
+				memblock_remove(r->base, r->size);
+				r--;
+			}
+		}
+	} else {
+		/*
+		 * KHO is disabled. Discard memblocks discovered so far:
+		 * if there are any at this point, they originate from memory
+		 * nodes in the DT, and UEFI uses its own memory map instead.
+		 */
+		memblock_remove(0, PHYS_ADDR_MAX);
+	}
+
+	for_each_efi_memory_desc(md) {
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+
+		if (efi_enabled(EFI_DBG)) {
+			char buf[64];
+
+			pr_info("  0x%012llx-0x%012llx %s\n",
+				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
+				efi_md_typeattr_format(buf, sizeof(buf), md));
+		}
+
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+
+		if (is_memory(md)) {
+			/*
+			 * Special purpose memory is 'soft reserved', which
+			 * means it is set aside initially. Don't add a memblock
+			 * for it now so that it can be hotplugged back in or
+			 * be assigned to the dax driver after boot.
+			 */
+			if (efi_soft_reserve_enabled() &&
+			    (md->attribute & EFI_MEMORY_SP))
+				continue;
+
+			early_init_dt_add_memory_arch(paddr, size);
+
+			if (!is_usable_memory(md))
+				memblock_mark_nomap(paddr, size);
+
+			/* keep ACPI reclaim memory intact for kexec etc. */
+			if (md->type == EFI_ACPI_RECLAIM_MEMORY)
+				memblock_reserve(paddr, size);
+		}
+	}
+}
+
+void __init efi_init(void)
+{
+	struct efi_memory_map_data data;
+	u64 efi_system_table;
+
+	/* Grab UEFI information placed in FDT by stub */
+	efi_system_table = efi_get_fdt_params(&data);
+	if (!efi_system_table)
+		return;
+
+	if (efi_memmap_init_early(&data) < 0) {
+		/*
+		* If we are booting via UEFI, the UEFI memory map is the only
+		* description of memory we have, so there is little point in
+		* proceeding if we cannot access it.
+		*/
+		panic("Unable to map EFI memory map.\n");
+	}
+
+	WARN(efi.memmap.desc_version != 1,
+	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
+	      efi.memmap.desc_version);
+
+	if (uefi_init(efi_system_table) < 0) {
+		efi_memmap_unmap();
+		return;
+	}
+
+	reserve_regions();
+	/*
+	 * For memblock manipulation, the cap should come after the memblock_add().
+	 * And now, memblock is fully populated, it is time to do capping.
+	 */
+	early_init_dt_check_for_usable_mem_range();
+	efi_find_mirror();
+	efi_esrt_init();
+	efi_mokvar_table_init();
+
+	memblock_reserve(data.phys_map & PAGE_MASK,
+			 PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
+
+	if (IS_ENABLED(CONFIG_X86) ||
+	    IS_ENABLED(CONFIG_SYSFB) ||
+	    IS_ENABLED(CONFIG_EFI_EARLYCON))
+		init_primary_display();
+}