arm64: mte: Dump the MTE tags in the core file

For each vma mapped with PROT_MTE (the VM_MTE flag set), generate a
PT_ARM_MEMTAG_MTE segment in the core file and dump the corresponding
tags. The in-file size for such segments is 128 bytes per page.

For pages in a VM_MTE vma which are not present in the user page tables
or don't have the PG_mte_tagged flag set (e.g. execute-only), just write
zeros in the core file.

An example of program headers for two vmas, one 2-page, the other 4-page
long:

  Type           Offset   VirtAddr           PhysAddr           FileSiz  MemSiz   Flg Align
  ...
  LOAD           0x030000 0x0000ffff80034000 0x0000000000000000 0x000000 0x002000 RW  0x1000
  LOAD           0x030000 0x0000ffff80036000 0x0000000000000000 0x004000 0x004000 RW  0x1000
  ...
  LOPROC+0x1     0x05b000 0x0000ffff80034000 0x0000000000000000 0x000100 0x002000     0
  LOPROC+0x1     0x05b100 0x0000ffff80036000 0x0000000000000000 0x000200 0x004000     0

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Luis Machado <luis.machado@linaro.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20220131165456.2160675-5-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

3 files changed, 125 insertions, 0 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cbcd42decb2a..b55c11796fad 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -10,6 +10,7 @@ config ARM64
 	select ACPI_SPCR_TABLE if ACPI
 	select ACPI_PPTT if ACPI
 	select ARCH_HAS_DEBUG_WX
+	select ARCH_BINFMT_ELF_EXTRA_PHDRS
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 88b3e2a21408..986837d7ec82 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 obj-$(CONFIG_PARAVIRT)			+= paravirt.o
 obj-$(CONFIG_RANDOMIZE_BASE)		+= kaslr.o
 obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
+obj-$(CONFIG_ELF_CORE)			+= elfcore.o
 obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
 obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o kexec_image.o
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
new file mode 100644
index 000000000000..3455ee4acc04
--- /dev/null
+++ b/arch/arm64/kernel/elfcore.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/coredump.h>
+#include <linux/elfcore.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+
+#include <asm/cpufeature.h>
+#include <asm/mte.h>
+
+#define for_each_mte_vma(tsk, vma)					\
+	if (system_supports_mte())					\
+		for (vma = tsk->mm->mmap; vma; vma = vma->vm_next)	\
+			if (vma->vm_flags & VM_MTE)
+
+static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_DONTDUMP)
+		return 0;
+
+	return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+}
+
+/* Derived from dump_user_range(); start/end must be page-aligned */
+static int mte_dump_tag_range(struct coredump_params *cprm,
+			      unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		char tags[MTE_PAGE_TAG_STORAGE];
+		struct page *page = get_dump_page(addr);
+
+		/*
+		 * get_dump_page() returns NULL when encountering an empty
+		 * page table entry that would otherwise have been filled with
+		 * the zero page. Skip the equivalent tag dump which would
+		 * have been all zeros.
+		 */
+		if (!page) {
+			dump_skip(cprm, MTE_PAGE_TAG_STORAGE);
+			continue;
+		}
+
+		/*
+		 * Pages mapped in user space as !pte_access_permitted() (e.g.
+		 * PROT_EXEC only) may not have the PG_mte_tagged flag set.
+		 */
+		if (!test_bit(PG_mte_tagged, &page->flags)) {
+			put_page(page);
+			dump_skip(cprm, MTE_PAGE_TAG_STORAGE);
+			continue;
+		}
+
+		mte_save_page_tags(page_address(page), tags);
+		put_page(page);
+		if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE))
+			return 0;
+	}
+
+	return 1;
+}
+
+Elf_Half elf_core_extra_phdrs(void)
+{
+	struct vm_area_struct *vma;
+	int vma_count = 0;
+
+	for_each_mte_vma(current, vma)
+		vma_count++;
+
+	return vma_count;
+}
+
+int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
+{
+	struct vm_area_struct *vma;
+
+	for_each_mte_vma(current, vma) {
+		struct elf_phdr phdr;
+
+		phdr.p_type = PT_ARM_MEMTAG_MTE;
+		phdr.p_offset = offset;
+		phdr.p_vaddr = vma->vm_start;
+		phdr.p_paddr = 0;
+		phdr.p_filesz = mte_vma_tag_dump_size(vma);
+		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		offset += phdr.p_filesz;
+		phdr.p_flags = 0;
+		phdr.p_align = 0;
+
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
+			return 0;
+	}
+
+	return 1;
+}
+
+size_t elf_core_extra_data_size(void)
+{
+	struct vm_area_struct *vma;
+	size_t data_size = 0;
+
+	for_each_mte_vma(current, vma)
+		data_size += mte_vma_tag_dump_size(vma);
+
+	return data_size;
+}
+
+int elf_core_write_extra_data(struct coredump_params *cprm)
+{
+	struct vm_area_struct *vma;
+
+	for_each_mte_vma(current, vma) {
+		if (vma->vm_flags & VM_DONTDUMP)
+			continue;
+
+		if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+			return 0;
+	}
+
+	return 1;
+}