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, 477 insertions, 0 deletions

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
new file mode 100644
index 000000000..0cc1bf046
--- /dev/null
+++ b/arch/arm/mm/init.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/arch/arm/mm/init.c
+ *
+ *  Copyright (C) 1995-2005 Russell King
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/mman.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/export.h>
+#include <linux/nodemask.h>
+#include <linux/initrd.h>
+#include <linux/of_fdt.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/memblock.h>
+#include <linux/dma-map-ops.h>
+#include <linux/sizes.h>
+#include <linux/stop_machine.h>
+#include <linux/swiotlb.h>
+#include <linux/execmem.h>
+
+#include <asm/cp15.h>
+#include <asm/mach-types.h>
+#include <asm/memblock.h>
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/set_memory.h>
+#include <asm/system_info.h>
+#include <asm/tlb.h>
+#include <asm/fixmap.h>
+#include <asm/ptdump.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+
+#include "mm.h"
+
+#ifdef CONFIG_CPU_CP15_MMU
+unsigned long __init __clear_cr(unsigned long mask)
+{
+	cr_alignment = cr_alignment & ~mask;
+	return cr_alignment;
+}
+#endif
+
+#ifdef CONFIG_BLK_DEV_INITRD
+static int __init parse_tag_initrd(const struct tag *tag)
+{
+	pr_warn("ATAG_INITRD is deprecated; "
+		"please update your bootloader.\n");
+	phys_initrd_start = __virt_to_phys(tag->u.initrd.start);
+	phys_initrd_size = tag->u.initrd.size;
+	return 0;
+}
+
+__tagtable(ATAG_INITRD, parse_tag_initrd);
+
+static int __init parse_tag_initrd2(const struct tag *tag)
+{
+	phys_initrd_start = tag->u.initrd.start;
+	phys_initrd_size = tag->u.initrd.size;
+	return 0;
+}
+
+__tagtable(ATAG_INITRD2, parse_tag_initrd2);
+#endif
+
+static void __init find_limits(unsigned long *min, unsigned long *max_low,
+			       unsigned long *max_high)
+{
+	*max_low = PFN_DOWN(memblock_get_current_limit());
+	*min = PFN_UP(memblock_start_of_DRAM());
+	*max_high = PFN_DOWN(memblock_end_of_DRAM());
+}
+
+#ifdef CONFIG_ZONE_DMA
+
+phys_addr_t arm_dma_zone_size __read_mostly;
+EXPORT_SYMBOL(arm_dma_zone_size);
+
+/*
+ * The DMA mask corresponding to the maximum bus address allocatable
+ * using GFP_DMA.  The default here places no restriction on DMA
+ * allocations.  This must be the smallest DMA mask in the system,
+ * so a successful GFP_DMA allocation will always satisfy this.
+ */
+phys_addr_t arm_dma_limit;
+unsigned long arm_dma_pfn_limit;
+#endif
+
+void __init setup_dma_zone(const struct machine_desc *mdesc)
+{
+#ifdef CONFIG_ZONE_DMA
+	if (mdesc->dma_zone_size) {
+		arm_dma_zone_size = mdesc->dma_zone_size;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
+	} else
+		arm_dma_limit = 0xffffffff;
+	arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
+#endif
+}
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfn)
+{
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfn[ZONE_DMA] = min(arm_dma_pfn_limit, max_low_pfn);
+#endif
+	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfn[ZONE_HIGHMEM] = max_pfn;
+#endif
+}
+
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int pfn_valid(unsigned long pfn)
+{
+	phys_addr_t addr = __pfn_to_phys(pfn);
+	unsigned long pageblock_size = PAGE_SIZE * pageblock_nr_pages;
+
+	if (__phys_to_pfn(addr) != pfn)
+		return 0;
+
+	/*
+	 * If address less than pageblock_size bytes away from a present
+	 * memory chunk there still will be a memory map entry for it
+	 * because we round freed memory map to the pageblock boundaries.
+	 */
+	if (memblock_overlaps_region(&memblock.memory,
+				     ALIGN_DOWN(addr, pageblock_size),
+				     pageblock_size))
+		return 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(pfn_valid);
+#endif
+
+static bool arm_memblock_steal_permitted = true;
+
+phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
+{
+	phys_addr_t phys;
+
+	BUG_ON(!arm_memblock_steal_permitted);
+
+	phys = memblock_phys_alloc(size, align);
+	if (!phys)
+		panic("Failed to steal %pa bytes at %pS\n",
+		      &size, (void *)_RET_IP_);
+
+	memblock_phys_free(phys, size);
+	memblock_remove(phys, size);
+
+	return phys;
+}
+
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+void check_cpu_icache_size(int cpuid)
+{
+	u32 size, ctr;
+
+	asm("mrc p15, 0, %0, c0, c0, 1" : "=r" (ctr));
+
+	size = 1 << ((ctr & 0xf) + 2);
+	if (cpuid != 0 && icache_size != size)
+		pr_info("CPU%u: detected I-Cache line size mismatch, workaround enabled\n",
+			cpuid);
+	if (icache_size > size)
+		icache_size = size;
+}
+#endif
+
+void __init arm_memblock_init(const struct machine_desc *mdesc)
+{
+	/* Register the kernel text, kernel data and initrd with memblock. */
+	memblock_reserve(__pa(KERNEL_START), KERNEL_END - KERNEL_START);
+
+	reserve_initrd_mem();
+
+	arm_mm_memblock_reserve();
+
+	/* reserve any platform specific memblock areas */
+	if (mdesc->reserve)
+		mdesc->reserve();
+
+	early_init_fdt_scan_reserved_mem();
+
+	/* reserve memory for DMA contiguous allocations */
+	dma_contiguous_reserve(arm_dma_limit);
+
+	arm_memblock_steal_permitted = false;
+	memblock_dump_all();
+}
+
+void __init bootmem_init(void)
+{
+	memblock_allow_resize();
+
+	find_limits(&min_low_pfn, &max_low_pfn, &max_pfn);
+
+	early_memtest((phys_addr_t)min_low_pfn << PAGE_SHIFT,
+		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
+}
+
+/*
+ * Poison init memory with an undefined instruction (ARM) or a branch to an
+ * undefined instruction (Thumb).
+ */
+static inline void poison_init_mem(void *s, size_t count)
+{
+	u32 *p = (u32 *)s;
+	for (; count != 0; count -= 4)
+		*p++ = 0xe7fddef0;
+}
+
+void __init arch_mm_preinit(void)
+{
+#ifdef CONFIG_ARM_LPAE
+	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
+#endif
+
+#ifdef CONFIG_SA1111
+	/* now that our DMA memory is actually so designated, we can free it */
+	memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
+#endif
+
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#ifdef CONFIG_MMU
+	BUILD_BUG_ON(TASK_SIZE				> MODULES_VADDR);
+	BUG_ON(TASK_SIZE 				> MODULES_VADDR);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE > PAGE_OFFSET);
+	BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE	> PAGE_OFFSET);
+#endif
+}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+struct section_perm {
+	const char *name;
+	unsigned long start;
+	unsigned long end;
+	pmdval_t mask;
+	pmdval_t prot;
+	pmdval_t clear;
+};
+
+/* First section-aligned location at or after __start_rodata. */
+extern char __start_rodata_section_aligned[];
+
+static struct section_perm nx_perms[] = {
+	/* Make pages tables, etc before _stext RW (set NX). */
+	{
+		.name	= "pre-text NX",
+		.start	= PAGE_OFFSET,
+		.end	= (unsigned long)_stext,
+		.mask	= ~PMD_SECT_XN,
+		.prot	= PMD_SECT_XN,
+	},
+	/* Make init RW (set NX). */
+	{
+		.name	= "init NX",
+		.start	= (unsigned long)__init_begin,
+		.end	= (unsigned long)_sdata,
+		.mask	= ~PMD_SECT_XN,
+		.prot	= PMD_SECT_XN,
+	},
+	/* Make rodata NX (set RO in ro_perms below). */
+	{
+		.name	= "rodata NX",
+		.start  = (unsigned long)__start_rodata_section_aligned,
+		.end    = (unsigned long)__init_begin,
+		.mask   = ~PMD_SECT_XN,
+		.prot   = PMD_SECT_XN,
+	},
+};
+
+static struct section_perm ro_perms[] = {
+	/* Make kernel code and rodata RX (set RO). */
+	{
+		.name	= "text/rodata RO",
+		.start  = (unsigned long)_stext,
+		.end    = (unsigned long)__init_begin,
+#ifdef CONFIG_ARM_LPAE
+		.mask   = ~(L_PMD_SECT_RDONLY | PMD_SECT_AP2),
+		.prot   = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
+#else
+		.mask   = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
+		.prot   = PMD_SECT_APX | PMD_SECT_AP_WRITE,
+		.clear  = PMD_SECT_AP_WRITE,
+#endif
+	},
+};
+
+/*
+ * Updates section permissions only for the current mm (sections are
+ * copied into each mm). During startup, this is the init_mm. Is only
+ * safe to be called with preemption disabled, as under stop_machine().
+ */
+static inline void section_update(unsigned long addr, pmdval_t mask,
+				  pmdval_t prot, struct mm_struct *mm)
+{
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr);
+
+#ifdef CONFIG_ARM_LPAE
+	pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
+#else
+	if (addr & SECTION_SIZE)
+		pmd[1] = __pmd((pmd_val(pmd[1]) & mask) | prot);
+	else
+		pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
+#endif
+	flush_pmd_entry(pmd);
+	local_flush_tlb_kernel_range(addr, addr + SECTION_SIZE);
+}
+
+/* Make sure extended page tables are in use. */
+static inline bool arch_has_strict_perms(void)
+{
+	if (cpu_architecture() < CPU_ARCH_ARMv6)
+		return false;
+
+	return !!(get_cr() & CR_XP);
+}
+
+static void set_section_perms(struct section_perm *perms, int n, bool set,
+			      struct mm_struct *mm)
+{
+	size_t i;
+	unsigned long addr;
+
+	if (!arch_has_strict_perms())
+		return;
+
+	for (i = 0; i < n; i++) {
+		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||
+		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {
+			pr_err("BUG: %s section %lx-%lx not aligned to %lx\n",
+				perms[i].name, perms[i].start, perms[i].end,
+				SECTION_SIZE);
+			continue;
+		}
+
+		for (addr = perms[i].start;
+		     addr < perms[i].end;
+		     addr += SECTION_SIZE)
+			section_update(addr, perms[i].mask,
+				set ? perms[i].prot : perms[i].clear, mm);
+	}
+
+}
+
+/*
+ * update_sections_early intended to be called only through stop_machine
+ * framework and executed by only one CPU while all other CPUs will spin and
+ * wait, so no locking is required in this function.
+ */
+static void update_sections_early(struct section_perm perms[], int n)
+{
+	struct task_struct *t, *s;
+
+	for_each_process(t) {
+		if (t->flags & PF_KTHREAD)
+			continue;
+		for_each_thread(t, s)
+			if (s->mm)
+				set_section_perms(perms, n, true, s->mm);
+	}
+	set_section_perms(perms, n, true, current->active_mm);
+	set_section_perms(perms, n, true, &init_mm);
+}
+
+static int __fix_kernmem_perms(void *unused)
+{
+	update_sections_early(nx_perms, ARRAY_SIZE(nx_perms));
+	return 0;
+}
+
+static void fix_kernmem_perms(void)
+{
+	stop_machine(__fix_kernmem_perms, NULL, NULL);
+}
+
+static int __mark_rodata_ro(void *unused)
+{
+	update_sections_early(ro_perms, ARRAY_SIZE(ro_perms));
+	return 0;
+}
+
+void mark_rodata_ro(void)
+{
+	stop_machine(__mark_rodata_ro, NULL, NULL);
+	arm_debug_checkwx();
+}
+
+#else
+static inline void fix_kernmem_perms(void) { }
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
+void free_initmem(void)
+{
+	fix_kernmem_perms();
+
+	poison_init_mem(__init_begin, __init_end - __init_begin);
+	if (!machine_is_integrator() && !machine_is_cintegrator())
+		free_initmem_default(-1);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+	if (start == initrd_start)
+		start = round_down(start, PAGE_SIZE);
+	if (end == initrd_end)
+		end = round_up(end, PAGE_SIZE);
+
+	poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
+	free_reserved_area((void *)start, (void *)end, -1, "initrd");
+}
+#endif
+
+#ifdef CONFIG_EXECMEM
+
+#ifdef CONFIG_XIP_KERNEL
+/*
+ * The XIP kernel text is mapped in the module area for modules and
+ * some other stuff to work without any indirect relocations.
+ * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
+ * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
+ */
+#undef MODULES_VADDR
+#define MODULES_VADDR	(((unsigned long)_exiprom + ~PMD_MASK) & PMD_MASK)
+#endif
+
+#ifdef CONFIG_MMU
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	unsigned long fallback_start = 0, fallback_end = 0;
+
+	if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS)) {
+		fallback_start = VMALLOC_START;
+		fallback_end = VMALLOC_END;
+	}
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= MODULES_VADDR,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL_EXEC,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
+#endif /* CONFIG_MMU */
+
+#endif /* CONFIG_EXECMEM */