Merge branch 'akpm' (patches from Andrew)
Pull yet more updates from Andrew Morton:
"54 patches.
Subsystems affected by this patch series: lib, mm (slub, secretmem,
cleanups, init, pagemap, and mremap), and debug"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (54 commits)
powerpc/mm: enable HAVE_MOVE_PMD support
powerpc/book3s64/mm: update flush_tlb_range to flush page walk cache
mm/mremap: allow arch runtime override
mm/mremap: hold the rmap lock in write mode when moving page table entries.
mm/mremap: use pmd/pud_poplulate to update page table entries
mm/mremap: don't enable optimized PUD move if page table levels is 2
mm/mremap: convert huge PUD move to separate helper
selftest/mremap_test: avoid crash with static build
selftest/mremap_test: update the test to handle pagesize other than 4K
mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t *
mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t *
kdump: use vmlinux_build_id to simplify
buildid: fix kernel-doc notation
buildid: mark some arguments const
scripts/decode_stacktrace.sh: indicate 'auto' can be used for base path
scripts/decode_stacktrace.sh: silence stderr messages from addr2line/nm
scripts/decode_stacktrace.sh: support debuginfod
x86/dumpstack: use %pSb/%pBb for backtrace printing
arm64: stacktrace: use %pSb for backtrace printing
module: add printk formats to add module build ID to stacktraces
...
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index 4346ae1..d941717 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -125,6 +125,17 @@
consideration the effect of compiler optimisations which may occur
when tail-calls are used and marked with the noreturn GCC attribute.
+If the pointer is within a module, the module name and optionally build ID is
+printed after the symbol name with an extra ``b`` appended to the end of the
+specifier.
+
+::
+ %pS versatile_init+0x0/0x110 [module_name]
+ %pSb versatile_init+0x0/0x110 [module_name ed5019fdf5e53be37cb1ba7899292d7e143b259e]
+ %pSRb versatile_init+0x9/0x110 [module_name ed5019fdf5e53be37cb1ba7899292d7e143b259e]
+ (with __builtin_extract_return_addr() translation)
+ %pBb prev_fn_of_versatile_init+0x88/0x88 [module_name ed5019fdf5e53be37cb1ba7899292d7e143b259e]
+
Probed Pointers from BPF / tracing
----------------------------------
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index ff69084..02f0429 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -236,8 +236,10 @@
#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> 32))
#define pud_page(pud) (pfn_to_page(pud_val(pud) >> 32))
-extern inline unsigned long pud_page_vaddr(pud_t pgd)
-{ return PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); }
+extern inline pmd_t *pud_pgtable(pud_t pgd)
+{
+ return (pmd_t *)(PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)));
+}
extern inline int pte_none(pte_t pte) { return !pte_val(pte); }
extern inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_VALID; }
@@ -287,7 +289,7 @@
/* Find an entry in the second-level page table.. */
extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
{
- pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
+ pmd_t *ret = pud_pgtable(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
smp_rmb(); /* see above */
return ret;
}
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index abfeef7..c083bf6 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -89,10 +89,7 @@
{
unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
- init_mm.start_code = (unsigned long)_text;
- init_mm.end_code = (unsigned long)_etext;
- init_mm.end_data = (unsigned long)_edata;
- init_mm.brk = (unsigned long)_end;
+ setup_initial_init_mm(_text, _etext, _edata, _end);
/* first page of system - kernel .vector starts here */
min_low_pfn = virt_to_pfn(CONFIG_LINUX_RAM_BASE);
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index d4edab5..eabe72f 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -130,7 +130,7 @@
flush_pmd_entry(pudp); \
} while (0)
-static inline pmd_t *pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7693a1f..f97eb23 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1130,10 +1130,7 @@
if (mdesc->reboot_mode != REBOOT_HARD)
reboot_mode = mdesc->reboot_mode;
- init_mm.start_code = (unsigned long) _text;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_text, _etext, _edata, _end);
/* populate cmd_line too for later use, preserving boot_command_line */
strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 26889db..6420201 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -3,7 +3,6 @@
generic-y += mcs_spinlock.h
generic-y += qrwlock.h
generic-y += qspinlock.h
-generic-y += set_memory.h
generic-y += user.h
generated-y += cpucaps.h
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 543c997..5a228e2 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -144,12 +144,6 @@
dsb(ish);
}
-int set_memory_valid(unsigned long addr, int numpages, int enable);
-
-int set_direct_map_invalid_noflush(struct page *page);
-int set_direct_map_default_noflush(struct page *page);
-bool kernel_page_present(struct page *page);
-
#include <asm-generic/cacheflush.h>
#endif /* __ASM_CACHEFLUSH_H */
diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h
index d061176..aa855c6 100644
--- a/arch/arm64/include/asm/kfence.h
+++ b/arch/arm64/include/asm/kfence.h
@@ -8,7 +8,7 @@
#ifndef __ASM_KFENCE_H
#define __ASM_KFENCE_H
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
static inline bool arch_kfence_init_pool(void) { return true; }
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 508c7ff..f09bf5c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -649,9 +649,9 @@
return __pud_to_phys(pud);
}
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
- return (unsigned long)__va(pud_page_paddr(pud));
+ return (pmd_t *)__va(pud_page_paddr(pud));
}
/* Find an entry in the second-level page table. */
@@ -710,9 +710,9 @@
return __p4d_to_phys(p4d);
}
-static inline unsigned long p4d_page_vaddr(p4d_t p4d)
+static inline pud_t *p4d_pgtable(p4d_t p4d)
{
- return (unsigned long)__va(p4d_page_paddr(p4d));
+ return (pud_t *)__va(p4d_page_paddr(p4d));
}
/* Find an entry in the frst-level page table. */
diff --git a/arch/arm64/include/asm/set_memory.h b/arch/arm64/include/asm/set_memory.h
new file mode 100644
index 0000000..0f740b7
--- /dev/null
+++ b/arch/arm64/include/asm/set_memory.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARM64_SET_MEMORY_H
+#define _ASM_ARM64_SET_MEMORY_H
+
+#include <asm-generic/set_memory.h>
+
+bool can_set_direct_map(void);
+#define can_set_direct_map can_set_direct_map
+
+int set_memory_valid(unsigned long addr, int numpages, int enable);
+
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
+
+#endif /* _ASM_ARM64_SET_MEMORY_H */
diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h
index f83a70e..ce2ee8f 100644
--- a/arch/arm64/include/uapi/asm/unistd.h
+++ b/arch/arm64/include/uapi/asm/unistd.h
@@ -20,5 +20,6 @@
#define __ARCH_WANT_SET_GET_RLIMIT
#define __ARCH_WANT_TIME32_SYSCALLS
#define __ARCH_WANT_SYS_CLONE3
+#define __ARCH_WANT_MEMFD_SECRET
#include <asm-generic/unistd.h>
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 03ceabe..213d56c 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/kexec.h>
#include <linux/page-flags.h>
+#include <linux/set_memory.h>
#include <linux/smp.h>
#include <asm/cacheflush.h>
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 880f40b..be5f85b 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -293,10 +293,7 @@
void __init __no_sanitize_address setup_arch(char **cmdline_p)
{
- init_mm.start_code = (unsigned long) _stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
*cmdline_p = boot_command_line;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index b189de5..b83c8d9119 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -153,7 +153,7 @@
static void dump_backtrace_entry(unsigned long where, const char *loglvl)
{
- printk("%s %pS\n", loglvl, (void *)where);
+ printk("%s %pSb\n", loglvl, (void *)where);
}
void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 595fde9..d745865 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -22,6 +22,7 @@
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
+#include <linux/set_memory.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
@@ -515,8 +516,7 @@
*/
BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
- if (rodata_full || crash_mem_map || debug_pagealloc_enabled() ||
- IS_ENABLED(CONFIG_KFENCE))
+ if (can_set_direct_map() || crash_mem_map || IS_ENABLED(CONFIG_KFENCE))
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
@@ -1489,8 +1489,7 @@
* KFENCE requires linear map to be mapped at page granularity, so that
* it is possible to protect/unprotect single pages in the KFENCE pool.
*/
- if (rodata_full || debug_pagealloc_enabled() ||
- IS_ENABLED(CONFIG_KFENCE))
+ if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 92eccaf..a3bacd7 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -19,6 +19,11 @@
bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED);
+bool can_set_direct_map(void)
+{
+ return rodata_full || debug_pagealloc_enabled();
+}
+
static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
{
struct page_change_data *cdata = data;
@@ -155,7 +160,7 @@
.clear_mask = __pgprot(PTE_VALID),
};
- if (!debug_pagealloc_enabled() && !rodata_full)
+ if (!can_set_direct_map())
return 0;
return apply_to_page_range(&init_mm,
@@ -170,7 +175,7 @@
.clear_mask = __pgprot(PTE_RDONLY),
};
- if (!debug_pagealloc_enabled() && !rodata_full)
+ if (!can_set_direct_map())
return 0;
return apply_to_page_range(&init_mm,
@@ -181,7 +186,7 @@
#ifdef CONFIG_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
- if (!debug_pagealloc_enabled() && !rodata_full)
+ if (!can_set_direct_map())
return;
set_memory_valid((unsigned long)page_address(page), numpages, enable);
@@ -206,7 +211,7 @@
pte_t *ptep;
unsigned long addr = (unsigned long)page_address(page);
- if (!debug_pagealloc_enabled() && !rodata_full)
+ if (!can_set_direct_map())
return true;
pgdp = pgd_offset_k(addr);
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index e93bc6f..c64e7be 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -78,10 +78,7 @@
pr_info("Phys. mem: %ldMB\n",
(unsigned long) memblock_phys_mem_size()/1024/1024);
- init_mm.start_code = (unsigned long) _stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
parse_early_param();
diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c
index c3590b2..61091a7 100644
--- a/arch/h8300/kernel/setup.c
+++ b/arch/h8300/kernel/setup.c
@@ -95,10 +95,7 @@
{
unflatten_and_copy_device_tree();
- init_mm.start_code = (unsigned long) _stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) 0;
+ setup_initial_init_mm(_stext, _etext, _edata, NULL);
pr_notice("\r\n\nuClinux " CPU "\n");
pr_notice("Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n");
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 44a4099..e5a8520 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -30,6 +30,7 @@
select MODULES_USE_ELF_RELA
select GENERIC_CPU_DEVICES
select SET_FS
+ select ARCH_WANT_LD_ORPHAN_WARN
help
Qualcomm Hexagon is a processor architecture designed for high
performance and low power across a wide variety of applications.
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 35b18e5..57465bf 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -38,6 +38,8 @@
.text : AT(ADDR(.text)) {
_text = .;
TEXT_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
@@ -59,14 +61,9 @@
_end = .;
- /DISCARD/ : {
- EXIT_TEXT
- EXIT_DATA
- EXIT_CALL
- }
-
STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
+ DISCARDS
}
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 3f5dbbd..9584b2c 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -273,7 +273,7 @@
#define pud_bad(pud) (!ia64_phys_addr_valid(pud_val(pud)))
#define pud_present(pud) (pud_val(pud) != 0UL)
#define pud_clear(pudp) (pud_val(*(pudp)) = 0UL)
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & _PFN_MASK))
+#define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & _PFN_MASK))
#define pud_page(pud) virt_to_page((pud_val(pud) + PAGE_OFFSET))
#if CONFIG_PGTABLE_LEVELS == 4
@@ -281,7 +281,7 @@
#define p4d_bad(p4d) (!ia64_phys_addr_valid(p4d_val(p4d)))
#define p4d_present(p4d) (p4d_val(p4d) != 0UL)
#define p4d_clear(p4dp) (p4d_val(*(p4dp)) = 0UL)
-#define p4d_page_vaddr(p4d) ((unsigned long) __va(p4d_val(p4d) & _PFN_MASK))
+#define p4d_pgtable(p4d) ((pud_t *) __va(p4d_val(p4d) & _PFN_MASK))
#define p4d_page(p4d) virt_to_page((p4d_val(p4d) + PAGE_OFFSET))
#endif
diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h
index a290816..022c3ab 100644
--- a/arch/m68k/include/asm/motorola_pgtable.h
+++ b/arch/m68k/include/asm/motorola_pgtable.h
@@ -131,7 +131,7 @@
#define __pte_page(pte) ((unsigned long)__va(pte_val(pte) & PAGE_MASK))
#define pmd_page_vaddr(pmd) ((unsigned long)__va(pmd_val(pmd) & _TABLE_MASK))
-#define pud_page_vaddr(pud) ((unsigned long)__va(pud_val(pud) & _TABLE_MASK))
+#define pud_pgtable(pud) ((pmd_t *)__va(pud_val(pud) & _TABLE_MASK))
#define pte_none(pte) (!pte_val(pte))
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 017bac3..4b51bfd 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -258,10 +258,7 @@
}
}
- init_mm.start_code = PAGE_OFFSET;
- init_mm.end_code = (unsigned long)_etext;
- init_mm.end_data = (unsigned long)_edata;
- init_mm.brk = (unsigned long)_end;
+ setup_initial_init_mm((void *)PAGE_OFFSET, _etext, _edata, _end);
#if defined(CONFIG_BOOTPARAM)
strncpy(m68k_command_line, CONFIG_BOOTPARAM_STRING, CL_SIZE);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index d1b7988..5e4104f 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -87,10 +87,7 @@
memory_start = PAGE_ALIGN(_ramstart);
memory_end = _ramend;
- init_mm.start_code = (unsigned long) &_stext;
- init_mm.end_code = (unsigned long) &_etext;
- init_mm.end_data = (unsigned long) &_edata;
- init_mm.brk = (unsigned long) 0;
+ setup_initial_init_mm(_stext, _etext, _edata, NULL);
config_BSP(&command_line[0], sizeof(command_line));
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 0464659..41921ac 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -209,9 +209,9 @@
p4d_val(*p4dp) = (unsigned long)invalid_pud_table;
}
-static inline unsigned long p4d_page_vaddr(p4d_t p4d)
+static inline pud_t *p4d_pgtable(p4d_t p4d)
{
- return p4d_val(p4d);
+ return (pud_t *)p4d_val(p4d);
}
#define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d))
@@ -313,9 +313,9 @@
#endif
#ifndef __PAGETABLE_PMD_FOLDED
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
- return pud_val(pud);
+ return (pmd_t *)pud_val(pud);
}
#define pud_phys(pud) virt_to_phys((void *)pud_val(pud))
#define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT))
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index af82e99..41725ea 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -294,10 +294,7 @@
setup_cpuinfo();
- init_mm.start_code = (unsigned long)&_stext;
- init_mm.end_code = (unsigned long)&_etext;
- init_mm.end_data = (unsigned long)&_edata;
- init_mm.brk = (unsigned long)&_end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
/* setup bootmem allocator */
setup_memory();
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index d2f2195..cf8d687 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -156,10 +156,7 @@
memory_start = memblock_start_of_DRAM();
memory_end = memblock_end_of_DRAM();
- init_mm.start_code = (unsigned long) _stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
init_task.thread.kregs = &fake_regs;
/* Keep a copy of command line */
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index c6f9e7b..8ae2da6 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -293,10 +293,7 @@
#endif
/* process 1's initial memory region is the kernel code/data */
- init_mm.start_code = (unsigned long)_stext;
- init_mm.end_code = (unsigned long)_etext;
- init_mm.end_data = (unsigned long)_edata;
- init_mm.brk = (unsigned long)_end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start == initrd_end) {
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 7f33c29..43937af 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -322,8 +322,8 @@
#if CONFIG_PGTABLE_LEVELS == 3
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_address(pud)))
-#define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud))
+#define pud_pgtable(pud) ((pmd_t *) __va(pud_address(pud)))
+#define pud_page(pud) virt_to_page((void *)pud_pgtable(pud))
/* For 64 bit we have three level tables */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 4d9941b..5d34a86 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1051,8 +1051,15 @@
/* Pointers in the page table tree are physical addresses */
#define __pgtable_ptr_val(ptr) __pa(ptr)
-#define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS)
-#define p4d_page_vaddr(p4d) __va(p4d_val(p4d) & ~P4D_MASKED_BITS)
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+ return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS);
+}
+
+static inline pmd_t *pud_pgtable(pud_t pud)
+{
+ return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS);
+}
#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index a46fd37..77797a2 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -64,6 +64,8 @@
unsigned long start, unsigned long end);
extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
unsigned long end, int psize);
+void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
+ unsigned long end, int psize);
extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index fe2f4c9..10f5cf4 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -56,10 +56,14 @@
#define p4d_none(p4d) (!p4d_val(p4d))
#define p4d_bad(p4d) (p4d_val(p4d) == 0)
#define p4d_present(p4d) (p4d_val(p4d) != 0)
-#define p4d_page_vaddr(p4d) (p4d_val(p4d) & ~P4D_MASKED_BITS)
#ifndef __ASSEMBLY__
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+ return (pud_t *) (p4d_val(p4d) & ~P4D_MASKED_BITS);
+}
+
static inline void p4d_clear(p4d_t *p4dp)
{
*p4dp = __p4d(0);
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 53fbfdf..d081704 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -162,7 +162,11 @@
#define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \
|| (pud_val(pud) & PUD_BAD_BITS))
#define pud_present(pud) (pud_val(pud) != 0)
-#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS)
+
+static inline pmd_t *pud_pgtable(pud_t pud)
+{
+ return (pmd_t *)(pud_val(pud) & ~PUD_MASKED_BITS);
+}
extern struct page *pud_page(pud_t pud);
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 160422a..09a9ae5 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -83,5 +83,11 @@
}
#endif
+#define arch_supports_page_table_move arch_supports_page_table_move
+static inline bool arch_supports_page_table_move(void)
+{
+ return radix_enabled();
+}
+
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_TLB_H */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 26328fd..aa9c2d0 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -926,10 +926,7 @@
klp_init_thread_info(&init_task);
- init_mm.start_code = (unsigned long)_stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long)_end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
mm_iommu_init(&init_mm);
irqstack_early_init();
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index cb91071..23d3e08 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -32,7 +32,13 @@
struct hstate *hstate = hstate_file(vma->vm_file);
psize = hstate_get_psize(hstate);
- radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
+ /*
+ * Flush PWC even if we get PUD_SIZE hugetlb invalidate to keep this simpler.
+ */
+ if (end - start >= PUD_SIZE)
+ radix__flush_tlb_pwc_range_psize(vma->vm_mm, start, end, psize);
+ else
+ radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
}
/*
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 2176a5f..e50ddf1 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -820,7 +820,7 @@
continue;
}
- pmd_base = (pmd_t *)pud_page_vaddr(*pud);
+ pmd_base = pud_pgtable(*pud);
remove_pmd_table(pmd_base, addr, next);
free_pmd_table(pmd_base, pud);
}
@@ -854,7 +854,7 @@
continue;
}
- pud_base = (pud_t *)p4d_page_vaddr(*p4d);
+ pud_base = p4d_pgtable(*p4d);
remove_pud_table(pud_base, addr, next);
free_pud_table(pud_base, p4d);
}
@@ -1105,7 +1105,7 @@
pmd_t *pmd;
int i;
- pmd = (pmd_t *)pud_page_vaddr(*pud);
+ pmd = pud_pgtable(*pud);
pud_clear(pud);
flush_tlb_kernel_range(addr, addr + PUD_SIZE);
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index ae12fb5..aefc100 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1111,14 +1111,13 @@
static inline void __radix__flush_tlb_range(struct mm_struct *mm,
unsigned long start, unsigned long end)
-
{
unsigned long pid;
unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
unsigned long page_size = 1UL << page_shift;
unsigned long nr_pages = (end - start) >> page_shift;
bool fullmm = (end == TLB_FLUSH_ALL);
- bool flush_pid;
+ bool flush_pid, flush_pwc = false;
enum tlb_flush_type type;
pid = mm->context.id;
@@ -1137,8 +1136,16 @@
flush_pid = nr_pages > tlb_single_page_flush_ceiling;
else
flush_pid = nr_pages > tlb_local_single_page_flush_ceiling;
+ /*
+ * full pid flush already does the PWC flush. if it is not full pid
+ * flush check the range is more than PMD and force a pwc flush
+ * mremap() depends on this behaviour.
+ */
+ if (!flush_pid && (end - start) >= PMD_SIZE)
+ flush_pwc = true;
if (!mmu_has_feature(MMU_FTR_GTSE) && type == FLUSH_TYPE_GLOBAL) {
+ unsigned long type = H_RPTI_TYPE_TLB;
unsigned long tgt = H_RPTI_TARGET_CMMU;
unsigned long pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize);
@@ -1146,19 +1153,20 @@
pg_sizes |= psize_to_rpti_pgsize(MMU_PAGE_2M);
if (atomic_read(&mm->context.copros) > 0)
tgt |= H_RPTI_TARGET_NMMU;
- pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, pg_sizes,
- start, end);
+ if (flush_pwc)
+ type |= H_RPTI_TYPE_PWC;
+ pseries_rpt_invalidate(pid, tgt, type, pg_sizes, start, end);
} else if (flush_pid) {
+ /*
+ * We are now flushing a range larger than PMD size force a RIC_FLUSH_ALL
+ */
if (type == FLUSH_TYPE_LOCAL) {
- _tlbiel_pid(pid, RIC_FLUSH_TLB);
+ _tlbiel_pid(pid, RIC_FLUSH_ALL);
} else {
if (cputlb_use_tlbie()) {
- if (mm_needs_flush_escalation(mm))
- _tlbie_pid(pid, RIC_FLUSH_ALL);
- else
- _tlbie_pid(pid, RIC_FLUSH_TLB);
+ _tlbie_pid(pid, RIC_FLUSH_ALL);
} else {
- _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
+ _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
}
}
} else {
@@ -1174,6 +1182,9 @@
if (type == FLUSH_TYPE_LOCAL) {
asm volatile("ptesync": : :"memory");
+ if (flush_pwc)
+ /* For PWC, only one flush is needed */
+ __tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbiel_va_range(hstart, hend, pid,
@@ -1181,6 +1192,8 @@
ppc_after_tlbiel_barrier();
} else if (cputlb_use_tlbie()) {
asm volatile("ptesync": : :"memory");
+ if (flush_pwc)
+ __tlbie_pid(pid, RIC_FLUSH_PWC);
__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbie_va_range(hstart, hend, pid,
@@ -1188,10 +1201,10 @@
asm volatile("eieio; tlbsync; ptesync": : :"memory");
} else {
_tlbiel_va_range_multicast(mm,
- start, end, pid, page_size, mmu_virtual_psize, false);
+ start, end, pid, page_size, mmu_virtual_psize, flush_pwc);
if (hflush)
_tlbiel_va_range_multicast(mm,
- hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false);
+ hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, flush_pwc);
}
}
out:
@@ -1265,9 +1278,6 @@
_tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
}
-static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
- unsigned long end, int psize);
-
void radix__tlb_flush(struct mmu_gather *tlb)
{
int psize = 0;
@@ -1374,8 +1384,8 @@
return __radix__flush_tlb_range_psize(mm, start, end, psize, false);
}
-static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
- unsigned long end, int psize)
+void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
+ unsigned long end, int psize)
{
__radix__flush_tlb_range_psize(mm, start, end, psize, true);
}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index cc6e2f9..78c8cf0 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -105,7 +105,7 @@
VM_WARN_ON(!p4d_huge(p4d));
return pte_page(p4d_pte(p4d));
}
- return virt_to_page(p4d_page_vaddr(p4d));
+ return virt_to_page(p4d_pgtable(p4d));
}
#endif
@@ -115,7 +115,7 @@
VM_WARN_ON(!pud_huge(pud));
return pte_page(pud_pte(pud));
}
- return virt_to_page(pud_page_vaddr(pud));
+ return virt_to_page(pud_pgtable(pud));
}
/*
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 0e1bb1c..6794145 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -102,6 +102,8 @@
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_NUMA_BALANCING
+ select HAVE_MOVE_PMD
+ select HAVE_MOVE_PUD
select IRQ_WORK
select PPC_MM_SLICES
select PPC_HAVE_KUEP
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 469a70b..c711ccd 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -26,8 +26,8 @@
select ARCH_HAS_KCOV
select ARCH_HAS_MMIOWB
select ARCH_HAS_PTE_SPECIAL
- select ARCH_HAS_SET_DIRECT_MAP
- select ARCH_HAS_SET_MEMORY
+ select ARCH_HAS_SET_DIRECT_MAP if MMU
+ select ARCH_HAS_SET_MEMORY if MMU
select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index f3b0da6..0e863f3 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -60,9 +60,9 @@
set_pud(pudp, __pud(0));
}
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
- return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
+ return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
}
static inline struct page *pud_page(pud_t pud)
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index 977ee61..6c31609 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -9,6 +9,7 @@
*/
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_MEMFD_SECRET
#include <uapi/asm/unistd.h>
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 9a1b7a0..8e318f2 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -264,10 +264,7 @@
void __init setup_arch(char **cmdline_p)
{
parse_dtb();
- init_mm.start_code = (unsigned long) _stext;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
*cmdline_p = boot_command_line;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index b58ee83..5486d82 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1028,10 +1028,7 @@
ROOT_DEV = Root_RAM0;
- init_mm.start_code = (unsigned long) _text;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_text, _etext, _edata, _end);
if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
nospec_auto_detect();
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index 82d7447..56bf35c 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -32,9 +32,9 @@
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) } )
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
- return pud_val(pud);
+ return (pmd_t *)pud_val(pud);
}
/* only used by the stubbed out hugetlb gup code, should never be called */
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 4144be6..1fcb665 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -294,10 +294,7 @@
if (!MOUNT_ROOT_RDONLY)
root_mountflags &= ~MS_RDONLY;
- init_mm.start_code = (unsigned long) _text;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = (unsigned long) _end;
+ setup_initial_init_mm(_text, _etext, _edata, _end);
code_resource.start = virt_to_phys(_text);
code_resource.end = virt_to_phys(_etext)-1;
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index ebaf374..ffccfe3 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -151,13 +151,13 @@
return (unsigned long)__nocache_va(v << 4);
}
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
if (srmmu_device_memory(pud_val(pud))) {
- return ~0;
+ return (pmd_t *)~0;
} else {
unsigned long v = pud_val(pud) & SRMMU_PTD_PMASK;
- return (unsigned long)__nocache_va(v << 4);
+ return (pmd_t *)__nocache_va(v << 4);
}
}
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index e0ee48e..4679e45 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -841,23 +841,23 @@
return ((unsigned long) __va(pfn << PAGE_SHIFT));
}
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
pte_t pte = __pte(pud_val(pud));
unsigned long pfn;
pfn = pte_pfn(pte);
- return ((unsigned long) __va(pfn << PAGE_SHIFT));
+ return ((pmd_t *) __va(pfn << PAGE_SHIFT));
}
#define pmd_page(pmd) virt_to_page((void *)pmd_page_vaddr(pmd))
-#define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud))
+#define pud_page(pud) virt_to_page((void *)pud_pgtable(pud))
#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL)
#define pud_present(pud) (pud_val(pud) != 0U)
#define pud_clear(pudp) (pud_val(*(pudp)) = 0UL)
-#define p4d_page_vaddr(p4d) \
- ((unsigned long) __va(p4d_val(p4d)))
+#define p4d_pgtable(p4d) \
+ ((pud_t *) __va(p4d_val(p4d)))
#define p4d_present(p4d) (p4d_val(p4d) != 0U)
#define p4d_clear(p4dp) (p4d_val(*(p4dp)) = 0UL)
diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h
index 9289a86..cb896e6 100644
--- a/arch/um/include/asm/pgtable-3level.h
+++ b/arch/um/include/asm/pgtable-3level.h
@@ -83,7 +83,7 @@
}
#define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK)
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+#define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & PAGE_MASK))
static inline unsigned long pte_pfn(pte_t pte)
{
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index fba2f61..ce763a1 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -451,3 +451,4 @@
444 i386 landlock_create_ruleset sys_landlock_create_ruleset
445 i386 landlock_add_rule sys_landlock_add_rule
446 i386 landlock_restrict_self sys_landlock_restrict_self
+447 i386 memfd_secret sys_memfd_secret
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index af973e4..f6b5779 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -368,6 +368,7 @@
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+447 common memfd_secret sys_memfd_secret
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index ec0d8e1..448cd01 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -836,9 +836,9 @@
return pud_flags(pud) & _PAGE_PRESENT;
}
-static inline unsigned long pud_page_vaddr(pud_t pud)
+static inline pmd_t *pud_pgtable(pud_t pud)
{
- return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud));
+ return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud));
}
/*
@@ -877,9 +877,9 @@
return p4d_flags(p4d) & _PAGE_PRESENT;
}
-static inline unsigned long p4d_page_vaddr(p4d_t p4d)
+static inline pud_t *p4d_pgtable(p4d_t p4d)
{
- return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(p4d));
+ return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d));
}
/*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 299c20f..ea4fe19 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -69,7 +69,7 @@
const char *log_lvl)
{
touch_nmi_watchdog();
- printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
+ printk("%s %s%pBb\n", log_lvl, reliable ? "" : "? ", (void *)address);
}
static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9f1d921..bff3a78 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -847,10 +847,7 @@
if (!boot_params.hdr.root_flags)
root_mountflags &= ~MS_RDONLY;
- init_mm.start_code = (unsigned long) _text;
- init_mm.end_code = (unsigned long) _etext;
- init_mm.end_data = (unsigned long) _edata;
- init_mm.brk = _brk_end;
+ setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end);
code_resource.start = __pa_symbol(_text);
code_resource.end = __pa_symbol(_etext)-1;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 65ea585..ddeaba9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -194,8 +194,8 @@
spin_lock(pgt_lock);
if (!p4d_none(*p4d_ref) && !p4d_none(*p4d))
- BUG_ON(p4d_page_vaddr(*p4d)
- != p4d_page_vaddr(*p4d_ref));
+ BUG_ON(p4d_pgtable(*p4d)
+ != p4d_pgtable(*p4d_ref));
if (p4d_none(*p4d))
set_p4d(p4d, *p4d_ref);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 156cd235..ad8a5c5 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1134,7 +1134,7 @@
unsigned long start, unsigned long end)
{
if (unmap_pte_range(pmd, start, end))
- if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+ if (try_to_free_pmd_page(pud_pgtable(*pud)))
pud_clear(pud);
}
@@ -1178,7 +1178,7 @@
* Try again to free the PMD page if haven't succeeded above.
*/
if (!pud_none(*pud))
- if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+ if (try_to_free_pmd_page(pud_pgtable(*pud)))
pud_clear(pud);
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1303ff6..3364fe6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -801,7 +801,7 @@
pte_t *pte;
int i;
- pmd = (pmd_t *)pud_page_vaddr(*pud);
+ pmd = pud_pgtable(*pud);
pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
if (!pmd_sv)
return 0;
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index 2f6b1be..03b7dae 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -41,7 +41,7 @@
#define __p4d(x) ((p4d_t) { __pgd(x) })
#define pgd_page(pgd) (p4d_page((p4d_t){ pgd }))
-#define pgd_page_vaddr(pgd) (p4d_page_vaddr((p4d_t){ pgd }))
+#define pgd_page_vaddr(pgd) ((unsigned long)(p4d_pgtable((p4d_t){ pgd })))
/*
* allocating and freeing a p4d is trivial: the 1-entry p4d is
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index 3e13acd0..10789cf 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -51,7 +51,7 @@
#define __pmd(x) ((pmd_t) { __pud(x) } )
#define pud_page(pud) (pmd_page((pmd_t){ pud }))
-#define pud_page_vaddr(pud) (pmd_page_vaddr((pmd_t){ pud }))
+#define pud_pgtable(pud) ((pmd_t *)(pmd_page_vaddr((pmd_t){ pud })))
/*
* allocating and freeing a pmd is trivial: the 1-entry pmd is
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index a9d751f..eb70c6d 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -49,7 +49,7 @@
#define __pud(x) ((pud_t) { __p4d(x) })
#define p4d_page(p4d) (pud_page((pud_t){ p4d }))
-#define p4d_page_vaddr(p4d) (pud_page_vaddr((pud_t){ p4d }))
+#define p4d_pgtable(p4d) ((pud_t *)(pud_pgtable((pud_t){ p4d })))
/*
* allocating and freeing a pud is trivial: the 1-entry pud is
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 6bdd94c..abe089c 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -214,10 +214,10 @@
* @value: Iterated value of array entry.
*
* Iterate array entries of given @key under @node. Each array entry node
- * is stroed to @anode and @value. If the @node doesn't have @key node,
+ * is stored to @anode and @value. If the @node doesn't have @key node,
* it does nothing.
* Note that even if the found key node has only one value (not array)
- * this executes block once. Hoever, if the found key node has no value
+ * this executes block once. However, if the found key node has no value
* (key-only node), this does nothing. So don't use this for testing the
* key-value pair existence.
*/
diff --git a/include/linux/buildid.h b/include/linux/buildid.h
index 40232f9..3b7a0ff 100644
--- a/include/linux/buildid.h
+++ b/include/linux/buildid.h
@@ -8,5 +8,13 @@
int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id,
__u32 *size);
+int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size);
+
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE)
+extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX];
+void init_vmlinux_build_id(void);
+#else
+static inline void init_vmlinux_build_id(void) { }
+#endif
#endif
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 4221888..c24098c 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -35,12 +35,12 @@
COMPACT_CONTINUE,
/*
- * The full zone was compacted scanned but wasn't successfull to compact
+ * The full zone was compacted scanned but wasn't successful to compact
* suitable pages.
*/
COMPACT_COMPLETE,
/*
- * direct compaction has scanned part of the zone but wasn't successfull
+ * direct compaction has scanned part of the zone but wasn't successful
* to compact suitable pages.
*/
COMPACT_PARTIAL_SKIPPED,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index bfc4690..f3689a5 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -259,7 +259,7 @@
/**
* for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
* @cpu: the (optionally unsigned) integer iterator
- * @mask: the cpumask poiter
+ * @mask: the cpumask pointer
* @start: the start location
*
* The implementation does not assume any bit in @mask is set (including @start).
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 206bde8..de62a72 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -38,8 +38,12 @@
#define VMCOREINFO_OSRELEASE(value) \
vmcoreinfo_append_str("OSRELEASE=%s\n", value)
-#define VMCOREINFO_BUILD_ID(value) \
- vmcoreinfo_append_str("BUILD-ID=%s\n", value)
+#define VMCOREINFO_BUILD_ID() \
+ ({ \
+ static_assert(sizeof(vmlinux_build_id) == 20); \
+ vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \
+ })
+
#define VMCOREINFO_PAGESIZE(value) \
vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
#define VMCOREINFO_SYMBOL(name) \
@@ -69,10 +73,6 @@
extern size_t vmcoreinfo_size;
extern u32 *vmcoreinfo_note;
-/* raw contents of kernel .notes section */
-extern const void __start_notes __weak;
-extern const void __stop_notes __weak;
-
Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
void *data, size_t data_len);
void final_note(Elf_Word *buf);
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 8d2dde2..3244468 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -18,7 +18,7 @@
struct debug_obj_descr;
/**
- * struct debug_obj - representaion of an tracked object
+ * struct debug_obj - representation of an tracked object
* @node: hlist node to link the object into the tracker list
* @state: tracked object state
* @astate: current active state
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 866a0fa..2fd2e91 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -113,7 +113,7 @@
* HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
*
* When waiting for mmu notifiers we need some kind of time out otherwise we
- * could potentialy wait for ever, 1000ms ie 1s sounds like a long time to
+ * could potentially wait for ever, 1000ms ie 1s sounds like a long time to
* wait already.
*/
#define HMM_RANGE_DEFAULT_TIMEOUT 1000
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8e0f32f..f7ca1a3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -51,7 +51,7 @@
long count;
long max_hpages; /* Maximum huge pages or -1 if no maximum. */
long used_hpages; /* Used count against maximum, includes */
- /* both alloced and reserved pages. */
+ /* both allocated and reserved pages. */
struct hstate *hstate;
long min_hpages; /* Minimum huge pages or -1 if no minimum. */
long rsv_hpages; /* Pages reserved against global pool to */
@@ -85,7 +85,7 @@
* by a resv_map's lock. The set of regions within the resv_map represent
* reservations for huge pages, or huge pages that have already been
* instantiated within the map. The from and to elements are huge page
- * indicies into the associated mapping. from indicates the starting index
+ * indices into the associated mapping. from indicates the starting index
* of the region. to represents the first index past the end of the region.
*
* For example, a file region structure with from == 0 and to == 4 represents
@@ -797,7 +797,7 @@
* It determines whether or not a huge page should be placed on
* movable zone or not. Movability of any huge page should be
* required only if huge page size is supported for migration.
- * There wont be any reason for the huge page to be movable if
+ * There won't be any reason for the huge page to be movable if
* it is not migratable to start with. Also the size of the huge
* page should be large enough to be placed under a movable zone
* and still feasible enough to be migratable. Just the presence
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index 465060a..a1d6fc8 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -7,6 +7,7 @@
#define _LINUX_KALLSYMS_H
#include <linux/errno.h>
+#include <linux/buildid.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/mm.h>
@@ -15,8 +16,10 @@
#include <asm/sections.h>
#define KSYM_NAME_LEN 128
-#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
- 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
+#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \
+ (KSYM_NAME_LEN - 1) + \
+ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \
+ (BUILD_ID_SIZE_MAX * 2) + 1)
struct cred;
struct module;
@@ -91,8 +94,10 @@
/* Look up a kernel symbol and return it in a text buffer. */
extern int sprint_symbol(char *buffer, unsigned long address);
+extern int sprint_symbol_build_id(char *buffer, unsigned long address);
extern int sprint_symbol_no_offset(char *buffer, unsigned long address);
extern int sprint_backtrace(char *buffer, unsigned long address);
+extern int sprint_backtrace_build_id(char *buffer, unsigned long address);
int lookup_symbol_name(unsigned long addr, char *symname);
int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
@@ -128,6 +133,12 @@
return 0;
}
+static inline int sprint_symbol_build_id(char *buffer, unsigned long address)
+{
+ *buffer = '\0';
+ return 0;
+}
+
static inline int sprint_symbol_no_offset(char *buffer, unsigned long addr)
{
*buffer = '\0';
@@ -140,6 +151,12 @@
return 0;
}
+static inline int sprint_backtrace_build_id(char *buffer, unsigned long addr)
+{
+ *buffer = '\0';
+ return 0;
+}
+
static inline int lookup_symbol_name(unsigned long addr, char *symname)
{
return -ERANGE;
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 9dcaa3e..1b5fceb 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -146,7 +146,7 @@
* @lru: the lru pointer.
* @nid: the node id to scan from.
* @memcg: the cgroup to scan from.
- * @isolate: callback function that is resposible for deciding what to do with
+ * @isolate: callback function that is responsible for deciding what to do with
* the item currently being scanned
* @cb_arg: opaque type that will be passed to @isolate
* @nr_to_walk: how many items to scan.
@@ -172,7 +172,7 @@
* @lru: the lru pointer.
* @nid: the node id to scan from.
* @memcg: the cgroup to scan from.
- * @isolate: callback function that is resposible for deciding what to do with
+ * @isolate: callback function that is responsible for deciding what to do with
* the item currently being scanned
* @cb_arg: opaque type that will be passed to @isolate
* @nr_to_walk: how many items to scan.
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 429d67d..07add78 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -32,7 +32,7 @@
Because of this later property, it is called "lru_cache".
As it actually Tracks Objects in an Active SeT, we could also call it
toast (incidentally that is what may happen to the data on the
- backend storage uppon next resync, if we don't get it right).
+ backend storage upon next resync, if we don't get it right).
What for?
@@ -152,7 +152,7 @@
* for paranoia, and for "lc_element_to_index" */
unsigned lc_index;
/* if we want to track a larger set of objects,
- * it needs to become arch independend u64 */
+ * it needs to become an architecture independent u64 */
unsigned lc_number;
/* special label when on free list */
#define LC_FREE (~0U)
@@ -263,7 +263,7 @@
*
* Allows (expects) the set to be "dirty". Note that the reference counts and
* order on the active and lru lists may still change. Used to serialize
- * changing transactions. Returns true if we aquired the lock.
+ * changing transactions. Returns true if we acquired the lock.
*/
static inline int lc_try_lock_for_transaction(struct lru_cache *lc)
{
@@ -275,7 +275,7 @@
* @lc: the lru cache to operate on
*
* Note that the reference counts and order on the active and lru lists may
- * still change. Only works on a "clean" set. Returns true if we aquired the
+ * still change. Only works on a "clean" set. Returns true if we acquired the
* lock, which means there are no pending changes, and any further attempt to
* change the set will not succeed until the next lc_unlock().
*/
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 788a0b1..57453db 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -238,6 +238,9 @@
#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
+void setup_initial_init_mm(void *start_code, void *end_code,
+ void *end_data, void *brk);
+
/*
* Linux kernel virtual memory manager primitives.
* The idea being to have a "virtual" mm in the same way
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 6692da8..45fc2c8 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -33,7 +33,7 @@
*
* @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same
* access flags). User should soft dirty the page in the end callback to make
- * sure that anyone relying on soft dirtyness catch pages that might be written
+ * sure that anyone relying on soft dirtiness catch pages that might be written
* through non CPU mappings.
*
* @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
@@ -167,7 +167,7 @@
* decrease the refcount. If the refcount is decreased on
* invalidate_range_start() then the VM can free pages as page
* table entries are removed. If the refcount is only
- * droppped on invalidate_range_end() then the driver itself
+ * dropped on invalidate_range_end() then the driver itself
* will drop the last refcount but it must take care to flush
* any secondary tlb before doing the final free on the
* page. Pages will no longer be referenced by the linux
@@ -196,7 +196,7 @@
* If invalidate_range() is used to manage a non-CPU TLB with
* shared page-tables, it not necessary to implement the
* invalidate_range_start()/end() notifiers, as
- * invalidate_range() alread catches the points in time when an
+ * invalidate_range() already catches the points in time when an
* external TLB range needs to be flushed. For more in depth
* discussion on this see Documentation/vm/mmu_notifier.rst
*
@@ -369,7 +369,7 @@
* mmu_interval_read_retry() will return true.
*
* False is not reliable and only suggests a collision may not have
- * occured. It can be called many times and does not have to hold the user
+ * occurred. It can be called many times and does not have to hold the user
* provided lock.
*
* This call can be used as part of loops and other expensive operations to
diff --git a/include/linux/module.h b/include/linux/module.h
index 8100bb4..8a298d8 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -11,6 +11,7 @@
#include <linux/list.h>
#include <linux/stat.h>
+#include <linux/buildid.h>
#include <linux/compiler.h>
#include <linux/cache.h>
#include <linux/kmod.h>
@@ -369,6 +370,11 @@
/* Unique handle for this module */
char name[MODULE_NAME_LEN];
+#ifdef CONFIG_STACKTRACE_BUILD_ID
+ /* Module build ID */
+ unsigned char build_id[BUILD_ID_SIZE_MAX];
+#endif
+
/* Sysfs stuff. */
struct module_kobject mkobj;
struct module_attribute *modinfo_attrs;
@@ -636,7 +642,7 @@
const char *module_address_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
- char **modname,
+ char **modname, const unsigned char **modbuildid,
char *namebuf);
int lookup_module_symbol_name(unsigned long addr, char *symname);
int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
@@ -740,6 +746,7 @@
unsigned long *symbolsize,
unsigned long *offset,
char **modname,
+ const unsigned char **modbuildid,
char *namebuf)
{
return NULL;
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index ac398e1..567c3dd 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -119,7 +119,7 @@
* The inline keyword gives the compiler room to decide to inline, or
* not inline a function as it sees best. However, as these functions
* are called in both __init and non-__init functions, if they are not
- * inlined we will end up with a section mis-match error (of the type of
+ * inlined we will end up with a section mismatch error (of the type of
* freeable items not being freed). So we must use __always_inline here
* to fix the problem. If other functions in the future also end up in
* this situation they will also need to be annotated as __always_inline
@@ -515,7 +515,7 @@
#define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
/*
- * For nodemask scrach area.
+ * For nodemask scratch area.
* NODEMASK_ALLOC(type, name) allocates an object with a specified type and
* name.
*/
@@ -528,7 +528,7 @@
#define NODEMASK_FREE(m) do {} while (0)
#endif
-/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */
+/* Example structure for using NODEMASK_ALLOC, used in mempolicy. */
struct nodemask_scratch {
nodemask_t mask1;
nodemask_t mask2;
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index dff7040..af10715 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -412,7 +412,7 @@
* instead.
*
* If there is no other protection through preempt disable and/or disabling
- * interupts then one of these RMW operations can show unexpected behavior
+ * interrupts then one of these RMW operations can show unexpected behavior
* because the execution thread was rescheduled on another processor or an
* interrupt occurred and the same percpu variable was modified from the
* interrupt context.
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 16c35a7..ae16a98 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -213,7 +213,7 @@
* percpu_ref_get - increment a percpu refcount
* @ref: percpu_ref to get
*
- * Analagous to atomic_long_inc().
+ * Analogous to atomic_long_inc().
*
* This function is safe to call as long as @ref is between init and exit.
*/
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e82660f..d147480 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -106,7 +106,7 @@
#ifndef pmd_offset
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
- return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
+ return pud_pgtable(*pud) + pmd_index(address);
}
#define pmd_offset pmd_offset
#endif
@@ -114,7 +114,7 @@
#ifndef pud_offset
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
- return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address);
+ return p4d_pgtable(*p4d) + pud_index(address);
}
#define pud_offset pud_offset
#endif
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 6f70572..ecf8748 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -474,7 +474,7 @@
* Iterates over sg entries mapping page-by-page. On each successful
* iteration, @miter->page points to the mapped page and
* @miter->length bytes of data can be accessed at @miter->addr. As
- * long as an interation is enclosed between start and stop, the user
+ * long as an iteration is enclosed between start and stop, the user
* is free to choose control structure and when to stop.
*
* @miter->consumed is set to @miter->length on each iteration. It
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
new file mode 100644
index 0000000..21c3771
--- /dev/null
+++ b/include/linux/secretmem.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SECRETMEM_H
+#define _LINUX_SECRETMEM_H
+
+#ifdef CONFIG_SECRETMEM
+
+extern const struct address_space_operations secretmem_aops;
+
+static inline bool page_is_secretmem(struct page *page)
+{
+ struct address_space *mapping;
+
+ /*
+ * Using page_mapping() is quite slow because of the actual call
+ * instruction and repeated compound_head(page) inside the
+ * page_mapping() function.
+ * We know that secretmem pages are not compound and LRU so we can
+ * save a couple of cycles here.
+ */
+ if (PageCompound(page) || !PageLRU(page))
+ return false;
+
+ mapping = (struct address_space *)
+ ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
+
+ if (mapping != page->mapping)
+ return false;
+
+ return mapping->a_ops == &secretmem_aops;
+}
+
+bool vma_is_secretmem(struct vm_area_struct *vma);
+bool secretmem_active(void);
+
+#else
+
+static inline bool vma_is_secretmem(struct vm_area_struct *vma)
+{
+ return false;
+}
+
+static inline bool page_is_secretmem(struct page *page)
+{
+ return false;
+}
+
+static inline bool secretmem_active(void)
+{
+ return false;
+}
+
+#endif /* CONFIG_SECRETMEM */
+
+#endif /* _LINUX_SECRETMEM_H */
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index fe1aa4e..f36be51 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -28,7 +28,19 @@
{
return true;
}
+#else /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
+/*
+ * Some architectures, e.g. ARM64 can disable direct map modifications at
+ * boot time. Let them overrive this query.
+ */
+#ifndef can_set_direct_map
+static inline bool can_set_direct_map(void)
+{
+ return true;
+}
+#define can_set_direct_map can_set_direct_map
#endif
+#endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
#ifndef set_mce_nospec
static inline int set_mce_nospec(unsigned long pfn, bool unmap)
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 1eac79c..9814fff 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -4,7 +4,7 @@
/*
* This struct is used to pass information from page reclaim to the shrinkers.
- * We consolidate the values for easier extention later.
+ * We consolidate the values for easier extension later.
*
* The 'gfpmask' refers to the allocation we are currently trying to
* fulfil.
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 586128d..69c9a70 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1050,6 +1050,7 @@
asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type,
const void __user *rule_attr, __u32 flags);
asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags);
+asmlinkage long sys_memfd_secret(unsigned int flags);
/*
* Architecture-specific system calls
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 1dabd6f..2644425 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -29,7 +29,7 @@
#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */
/*
- * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
+ * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC.
*
* If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after
* shadow memory has been mapped. It's used to handle allocation errors so that
@@ -247,7 +247,7 @@
extern long vread(char *buf, char *addr, unsigned long count);
/*
- * Internals. Dont't use..
+ * Internals. Don't use..
*/
extern struct list_head vmap_area_list;
extern __init void vm_area_add_early(struct vm_struct *vm);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f211961..a9d6fcd 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -873,8 +873,13 @@
#define __NR_landlock_restrict_self 446
__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+#ifdef __ARCH_WANT_MEMFD_SECRET
+#define __NR_memfd_secret 447
+__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
+#endif
+
#undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 448
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index f3956fc..35687dc 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -97,5 +97,6 @@
#define DEVMEM_MAGIC 0x454d444d /* "DMEM" */
#define Z3FOLD_MAGIC 0x33
#define PPC_CMM_MAGIC 0xc7571590
+#define SECRETMEM_MAGIC 0x5345434d /* "SECM" */
#endif /* __LINUX_MAGIC_H__ */
diff --git a/init/Kconfig b/init/Kconfig
index 55f9f77..bb0d6e6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1847,6 +1847,7 @@
default y
bool "Enable SLUB debugging support" if EXPERT
depends on SLUB && SYSFS
+ select STACKDEPOT if STACKTRACE_SUPPORT
help
SLUB has extensive debug support features. Disabling these can
result in significant savings in code size. This also disables
diff --git a/init/main.c b/init/main.c
index af521b3..f5b8246 100644
--- a/init/main.c
+++ b/init/main.c
@@ -45,6 +45,7 @@
#include <linux/srcu.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
+#include <linux/buildid.h>
#include <linux/writeback.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
@@ -913,6 +914,7 @@
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
+ init_vmlinux_build_id();
cgroup_init_early();
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index da449c1..eb53f5e 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -4,6 +4,7 @@
* Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
*/
+#include <linux/buildid.h>
#include <linux/crash_core.h>
#include <linux/utsname.h>
#include <linux/vmalloc.h>
@@ -378,53 +379,6 @@
}
EXPORT_SYMBOL(paddr_vmcoreinfo_note);
-#define NOTES_SIZE (&__stop_notes - &__start_notes)
-#define BUILD_ID_MAX SHA1_DIGEST_SIZE
-#define NT_GNU_BUILD_ID 3
-
-struct elf_note_section {
- struct elf_note n_hdr;
- u8 n_data[];
-};
-
-/*
- * Add build ID from .notes section as generated by the GNU ld(1)
- * or LLVM lld(1) --build-id option.
- */
-static void add_build_id_vmcoreinfo(void)
-{
- char build_id[BUILD_ID_MAX * 2 + 1];
- int n_remain = NOTES_SIZE;
-
- while (n_remain >= sizeof(struct elf_note)) {
- const struct elf_note_section *note_sec =
- &__start_notes + NOTES_SIZE - n_remain;
- const u32 n_namesz = note_sec->n_hdr.n_namesz;
-
- if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID &&
- n_namesz != 0 &&
- !strcmp((char *)¬e_sec->n_data[0], "GNU")) {
- if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) {
- const u32 n_descsz = note_sec->n_hdr.n_descsz;
- const u8 *s = ¬e_sec->n_data[n_namesz];
-
- s = PTR_ALIGN(s, 4);
- bin2hex(build_id, s, n_descsz);
- build_id[2 * n_descsz] = '\0';
- VMCOREINFO_BUILD_ID(build_id);
- return;
- }
- pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n",
- note_sec->n_hdr.n_descsz,
- BUILD_ID_MAX);
- return;
- }
- n_remain -= sizeof(struct elf_note) +
- ALIGN(note_sec->n_hdr.n_namesz, 4) +
- ALIGN(note_sec->n_hdr.n_descsz, 4);
- }
-}
-
static int __init crash_save_vmcoreinfo_init(void)
{
vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
@@ -443,7 +397,7 @@
}
VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
- add_build_id_vmcoreinfo();
+ VMCOREINFO_BUILD_ID();
VMCOREINFO_PAGESIZE(PAGE_SIZE);
VMCOREINFO_SYMBOL(init_uts_ns);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index c851ca0..0ba87982 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -25,7 +25,10 @@
#include <linux/filter.h>
#include <linux/ftrace.h>
#include <linux/kprobes.h>
+#include <linux/build_bug.h>
#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
/*
* These will be re-linked against their real values
@@ -297,21 +300,14 @@
get_symbol_pos(addr, symbolsize, offset);
return 1;
}
- return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
+ return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) ||
!!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
}
-/*
- * Lookup an address
- * - modname is set to NULL if it's in the kernel.
- * - We guarantee that the returned name is valid until we reschedule even if.
- * It resides in a module.
- * - We also guarantee that modname will be valid until rescheduled.
- */
-const char *kallsyms_lookup(unsigned long addr,
- unsigned long *symbolsize,
- unsigned long *offset,
- char **modname, char *namebuf)
+static const char *kallsyms_lookup_buildid(unsigned long addr,
+ unsigned long *symbolsize,
+ unsigned long *offset, char **modname,
+ const unsigned char **modbuildid, char *namebuf)
{
const char *ret;
@@ -327,6 +323,8 @@
namebuf, KSYM_NAME_LEN);
if (modname)
*modname = NULL;
+ if (modbuildid)
+ *modbuildid = NULL;
ret = namebuf;
goto found;
@@ -334,7 +332,7 @@
/* See if it's in a module or a BPF JITed image. */
ret = module_address_lookup(addr, symbolsize, offset,
- modname, namebuf);
+ modname, modbuildid, namebuf);
if (!ret)
ret = bpf_address_lookup(addr, symbolsize,
offset, modname, namebuf);
@@ -348,6 +346,22 @@
return ret;
}
+/*
+ * Lookup an address
+ * - modname is set to NULL if it's in the kernel.
+ * - We guarantee that the returned name is valid until we reschedule even if.
+ * It resides in a module.
+ * - We also guarantee that modname will be valid until rescheduled.
+ */
+const char *kallsyms_lookup(unsigned long addr,
+ unsigned long *symbolsize,
+ unsigned long *offset,
+ char **modname, char *namebuf)
+{
+ return kallsyms_lookup_buildid(addr, symbolsize, offset, modname,
+ NULL, namebuf);
+}
+
int lookup_symbol_name(unsigned long addr, char *symname)
{
int res;
@@ -404,15 +418,17 @@
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
- int symbol_offset, int add_offset)
+ int symbol_offset, int add_offset, int add_buildid)
{
char *modname;
+ const unsigned char *buildid;
const char *name;
unsigned long offset, size;
int len;
address += symbol_offset;
- name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
+ name = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid,
+ buffer);
if (!name)
return sprintf(buffer, "0x%lx", address - symbol_offset);
@@ -424,8 +440,19 @@
if (add_offset)
len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
- if (modname)
- len += sprintf(buffer + len, " [%s]", modname);
+ if (modname) {
+ len += sprintf(buffer + len, " [%s", modname);
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+ if (add_buildid && buildid) {
+ /* build ID should match length of sprintf */
+#if IS_ENABLED(CONFIG_MODULES)
+ static_assert(sizeof(typeof_member(struct module, build_id)) == 20);
+#endif
+ len += sprintf(buffer + len, " %20phN", buildid);
+ }
+#endif
+ len += sprintf(buffer + len, "]");
+ }
return len;
}
@@ -443,11 +470,28 @@
*/
int sprint_symbol(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0, 1);
+ return __sprint_symbol(buffer, address, 0, 1, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol);
/**
+ * sprint_symbol_build_id - Look up a kernel symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function looks up a kernel symbol with @address and stores its name,
+ * offset, size, module name and module build ID to @buffer if possible. If no
+ * symbol was found, just saves its @address as is.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_symbol_build_id(char *buffer, unsigned long address)
+{
+ return __sprint_symbol(buffer, address, 0, 1, 1);
+}
+EXPORT_SYMBOL_GPL(sprint_symbol_build_id);
+
+/**
* sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
@@ -460,7 +504,7 @@
*/
int sprint_symbol_no_offset(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0, 0);
+ return __sprint_symbol(buffer, address, 0, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
@@ -480,7 +524,27 @@
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, -1, 1);
+ return __sprint_symbol(buffer, address, -1, 1, 0);
+}
+
+/**
+ * sprint_backtrace_build_id - Look up a backtrace symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function is for stack backtrace and does the same thing as
+ * sprint_symbol() but with modified/decreased @address. If there is a
+ * tail-call to the function marked "noreturn", gcc optimized out code after
+ * the call so that the stack-saved return address could point outside of the
+ * caller. This function ensures that kallsyms will find the original caller
+ * by decreasing @address. This function also appends the module build ID to
+ * the @buffer if @address is within a kernel module.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_backtrace_build_id(char *buffer, unsigned long address)
+{
+ return __sprint_symbol(buffer, address, -1, 1, 1);
}
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
diff --git a/kernel/module.c b/kernel/module.c
index 64bd61b..ed13917 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -13,6 +13,7 @@
#include <linux/trace_events.h>
#include <linux/init.h>
#include <linux/kallsyms.h>
+#include <linux/buildid.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
@@ -1465,6 +1466,13 @@
return ksym;
}
+#ifdef CONFIG_KALLSYMS
+static inline bool sect_empty(const Elf_Shdr *sect)
+{
+ return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
+}
+#endif
+
/*
* /sys/module/foo/sections stuff
* J. Corbet <corbet@lwn.net>
@@ -1472,11 +1480,6 @@
#ifdef CONFIG_SYSFS
#ifdef CONFIG_KALLSYMS
-static inline bool sect_empty(const Elf_Shdr *sect)
-{
- return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
-}
-
struct module_sect_attr {
struct bin_attribute battr;
unsigned long address;
@@ -2797,6 +2800,26 @@
}
#endif /* CONFIG_KALLSYMS */
+#if IS_ENABLED(CONFIG_KALLSYMS) && IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+static void init_build_id(struct module *mod, const struct load_info *info)
+{
+ const Elf_Shdr *sechdr;
+ unsigned int i;
+
+ for (i = 0; i < info->hdr->e_shnum; i++) {
+ sechdr = &info->sechdrs[i];
+ if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE &&
+ !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id,
+ sechdr->sh_size))
+ break;
+ }
+}
+#else
+static void init_build_id(struct module *mod, const struct load_info *info)
+{
+}
+#endif
+
static void dynamic_debug_setup(struct module *mod, struct _ddebug *debug, unsigned int num)
{
if (!debug)
@@ -4021,6 +4044,7 @@
goto free_arch_cleanup;
}
+ init_build_id(mod, info);
dynamic_debug_setup(mod, info->debug, info->num_debug);
/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
@@ -4254,6 +4278,7 @@
unsigned long *size,
unsigned long *offset,
char **modname,
+ const unsigned char **modbuildid,
char *namebuf)
{
const char *ret = NULL;
@@ -4264,6 +4289,13 @@
if (mod) {
if (modname)
*modname = mod->name;
+ if (modbuildid) {
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+ *modbuildid = mod->build_id;
+#else
+ *modbuildid = NULL;
+#endif
+ }
ret = find_kallsyms_symbol(mod, addr, size, offset);
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index da0b419..559acef 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -31,6 +31,7 @@
#include <linux/genhd.h>
#include <linux/ktime.h>
#include <linux/security.h>
+#include <linux/secretmem.h>
#include <trace/events/power.h>
#include "power.h"
@@ -81,7 +82,9 @@
bool hibernation_available(void)
{
- return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION);
+ return nohibernate == 0 &&
+ !security_locked_down(LOCKDOWN_HIBERNATION) &&
+ !secretmem_active();
}
/**
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index dad4d99..30971b1 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -358,6 +358,8 @@
COND_SYSCALL(pkey_alloc);
COND_SYSCALL(pkey_free);
+/* memfd_secret */
+COND_SYSCALL(memfd_secret);
/*
* Architecture specific weak syscall entries.
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8acc01d..2987925 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -35,6 +35,17 @@
no option to enable/disable at the kernel command line parameter or
sysfs interface.
+config STACKTRACE_BUILD_ID
+ bool "Show build ID information in stacktraces"
+ depends on PRINTK
+ help
+ Selecting this option adds build ID information for symbols in
+ stacktraces printed with the printk format '%p[SR]b'.
+
+ This option is intended for distros where debuginfo is not easily
+ accessible but can be downloaded given the build ID of the vmlinux or
+ kernel module where the function is located.
+
config CONSOLE_LOGLEVEL_DEFAULT
int "Default console loglevel (1-15)"
range 1 15
@@ -1282,7 +1293,7 @@
option expect lockdep splats until these problems have been fully
addressed which is work in progress. This config switch allows to
identify and analyze these problems. It will be removed and the
- check permanentely enabled once the main issues have been fixed.
+ check permanently enabled once the main issues have been fixed.
If unsure, select N.
@@ -1448,7 +1459,7 @@
Say Y here if you want the kernel to run a short self-test during
bootup. The self-test checks whether common types of locking bugs
are detected by debugging mechanisms or not. (if you disable
- lock debugging then those bugs wont be detected of course.)
+ lock debugging then those bugs won't be detected of course.)
The following locking APIs are covered: spinlocks, rwlocks,
mutexes and rwsems.
@@ -1928,7 +1939,7 @@
thus exercising the error handling.
Only works with drivers that use the generic timeout handling,
- for others it wont do anything.
+ for others it won't do anything.
config FAIL_FUTEX
bool "Fault-injection capability for futexes"
diff --git a/lib/asn1_encoder.c b/lib/asn1_encoder.c
index 41e71aa..27bbe89 100644
--- a/lib/asn1_encoder.c
+++ b/lib/asn1_encoder.c
@@ -181,7 +181,7 @@
/**
* asn1_encode_length() - encode a length to follow an ASN.1 tag
* @data: pointer to encode at
- * @data_len: pointer to remaning length (adjusted by routine)
+ * @data_len: pointer to remaining length (adjusted by routine)
* @len: length to encode
*
* This routine can encode lengths up to 65535 using the ASN.1 rules.
diff --git a/lib/buildid.c b/lib/buildid.c
index 6156997..dfc6262 100644
--- a/lib/buildid.c
+++ b/lib/buildid.c
@@ -1,36 +1,31 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/buildid.h>
+#include <linux/cache.h>
#include <linux/elf.h>
+#include <linux/kernel.h>
#include <linux/pagemap.h>
#define BUILD_ID 3
+
/*
* Parse build id from the note segment. This logic can be shared between
* 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
* identical.
*/
-static inline int parse_build_id(void *page_addr,
- unsigned char *build_id,
- __u32 *size,
- void *note_start,
- Elf32_Word note_size)
+static int parse_build_id_buf(unsigned char *build_id,
+ __u32 *size,
+ const void *note_start,
+ Elf32_Word note_size)
{
Elf32_Word note_offs = 0, new_offs;
- /* check for overflow */
- if (note_start < page_addr || note_start + note_size < note_start)
- return -EINVAL;
-
- /* only supports note that fits in the first page */
- if (note_start + note_size > page_addr + PAGE_SIZE)
- return -EINVAL;
-
while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
if (nhdr->n_type == BUILD_ID &&
nhdr->n_namesz == sizeof("GNU") &&
+ !strcmp((char *)(nhdr + 1), "GNU") &&
nhdr->n_descsz > 0 &&
nhdr->n_descsz <= BUILD_ID_SIZE_MAX) {
memcpy(build_id,
@@ -49,11 +44,29 @@
break;
note_offs = new_offs;
}
+
return -EINVAL;
}
+static inline int parse_build_id(const void *page_addr,
+ unsigned char *build_id,
+ __u32 *size,
+ const void *note_start,
+ Elf32_Word note_size)
+{
+ /* check for overflow */
+ if (note_start < page_addr || note_start + note_size < note_start)
+ return -EINVAL;
+
+ /* only supports note that fits in the first page */
+ if (note_start + note_size > page_addr + PAGE_SIZE)
+ return -EINVAL;
+
+ return parse_build_id_buf(build_id, size, note_start, note_size);
+}
+
/* Parse build ID from 32-bit ELF */
-static int get_build_id_32(void *page_addr, unsigned char *build_id,
+static int get_build_id_32(const void *page_addr, unsigned char *build_id,
__u32 *size)
{
Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
@@ -78,7 +91,7 @@
}
/* Parse build ID from 64-bit ELF */
-static int get_build_id_64(void *page_addr, unsigned char *build_id,
+static int get_build_id_64(const void *page_addr, unsigned char *build_id,
__u32 *size)
{
Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
@@ -108,7 +121,7 @@
* @build_id: buffer to store build id, at least BUILD_ID_SIZE long
* @size: returns actual build id size in case of success
*
- * Returns 0 on success, otherwise error (< 0).
+ * Return: 0 on success, -EINVAL otherwise
*/
int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id,
__u32 *size)
@@ -147,3 +160,32 @@
put_page(page);
return ret;
}
+
+/**
+ * build_id_parse_buf - Get build ID from a buffer
+ * @buf: Elf note section(s) to parse
+ * @buf_size: Size of @buf in bytes
+ * @build_id: Build ID parsed from @buf, at least BUILD_ID_SIZE_MAX long
+ *
+ * Return: 0 on success, -EINVAL otherwise
+ */
+int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size)
+{
+ return parse_build_id_buf(build_id, NULL, buf, buf_size);
+}
+
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE)
+unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX] __ro_after_init;
+
+/**
+ * init_vmlinux_build_id - Compute and stash the running kernel's build ID
+ */
+void __init init_vmlinux_build_id(void)
+{
+ extern const void __start_notes __weak;
+ extern const void __stop_notes __weak;
+ unsigned int size = &__stop_notes - &__start_notes;
+
+ build_id_parse_buf(&__start_notes, vmlinux_build_id, size);
+}
+#endif
diff --git a/lib/devres.c b/lib/devres.c
index bdb0689..b0e1c67 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -355,7 +355,7 @@
* detach.
*
* This function might sleep when the table is first allocated but can
- * be safely called without context and guaranteed to succed once
+ * be safely called without context and guaranteed to succeed once
* allocated.
*/
void __iomem * const *pcim_iomap_table(struct pci_dev *pdev)
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 27f1687..cd3387b 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -5,6 +5,7 @@
*/
#include <linux/kernel.h>
+#include <linux/buildid.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
@@ -36,6 +37,14 @@
va_end(args);
}
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+#define BUILD_ID_FMT " %20phN"
+#define BUILD_ID_VAL vmlinux_build_id
+#else
+#define BUILD_ID_FMT "%s"
+#define BUILD_ID_VAL ""
+#endif
+
/**
* dump_stack_print_info - print generic debug info for dump_stack()
* @log_lvl: log level
@@ -45,13 +54,13 @@
*/
void dump_stack_print_info(const char *log_lvl)
{
- printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s\n",
+ printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n",
log_lvl, raw_smp_processor_id(), current->pid, current->comm,
kexec_crash_loaded() ? "Kdump: loaded " : "",
print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
- init_utsname()->version);
+ init_utsname()->version, BUILD_ID_VAL);
if (dump_stack_arch_desc_str[0] != '\0')
printk("%sHardware name: %s\n",
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index d3ce782..cb5abb4 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -991,7 +991,7 @@
ddebug_exec_queries((val ? val : "+p"), modname);
- return 0; /* query failure shouldnt stop module load */
+ return 0; /* query failure shouldn't stop module load */
}
/* handle both dyndbg and $module.dyndbg params at boot */
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index b1678ed..ae98ca1 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -3,7 +3,7 @@
/* */
/* Font file generated by cpi2fnt */
/* ------------------------------ */
-/* Combined with the alpha-numeric */
+/* Combined with the alphanumeric */
/* portion of Greg Harp's old PEARL */
/* font (from earlier versions of */
/* linux-m86k) by John Shifflett */
diff --git a/lib/kfifo.c b/lib/kfifo.c
index 70dab9ac..12f5a34 100644
--- a/lib/kfifo.c
+++ b/lib/kfifo.c
@@ -415,7 +415,7 @@
)
/*
- * __kfifo_poke_n internal helper function for storeing the length of
+ * __kfifo_poke_n internal helper function for storing the length of
* the record into the fifo
*/
static void __kfifo_poke_n(struct __kfifo *fifo, unsigned int n, size_t recsize)
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 1e1e377..0fb59e9 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -104,7 +104,7 @@
* @head: the list to sort
* @cmp: the elements comparison function
*
- * The comparison funtion @cmp must return > 0 if @a should sort after
+ * The comparison function @cmp must return > 0 if @a should sort after
* @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should
* sort before @b *or* their original order should be preserved. It is
* always called with the element that came first in the input in @a,
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 1d051ef..86029ad 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -619,7 +619,7 @@
* Validates all attributes in the specified attribute stream against the
* specified policy. Validation depends on the validate flags passed, see
* &enum netlink_validation for more details on that.
- * See documenation of struct nla_policy for more details.
+ * See documentation of struct nla_policy for more details.
*
* Returns 0 on success or a negative error code.
*/
@@ -633,7 +633,7 @@
EXPORT_SYMBOL(__nla_validate);
/**
- * nla_policy_len - Determin the max. length of a policy
+ * nla_policy_len - Determine the max. length of a policy
* @policy: policy to use
* @n: number of policies
*
diff --git a/lib/oid_registry.c b/lib/oid_registry.c
index 3dfaa83..e592d48 100644
--- a/lib/oid_registry.c
+++ b/lib/oid_registry.c
@@ -124,7 +124,7 @@
* @bufsize: The size of the buffer
*
* The OID is rendered into the buffer in "a.b.c.d" format and the number of
- * bytes is returned. -EBADMSG is returned if the data could not be intepreted
+ * bytes is returned. -EBADMSG is returned if the data could not be interpreted
* and -ENOBUFS if the buffer was too small.
*/
int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize)
diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c
index e5d4b3b..6e77eb6 100644
--- a/lib/pldmfw/pldmfw.c
+++ b/lib/pldmfw/pldmfw.c
@@ -82,7 +82,7 @@
* @bytes_to_move: number of bytes to move the offset forward by
*
* Check that there is enough space past the current offset, and then move the
- * offset forward by this ammount.
+ * offset forward by this amount.
*
* Returns: zero on success, or -EFAULT if the image is too small to fit the
* expected length.
diff --git a/lib/reed_solomon/test_rslib.c b/lib/reed_solomon/test_rslib.c
index 4eb29f3..d9d1c33 100644
--- a/lib/reed_solomon/test_rslib.c
+++ b/lib/reed_solomon/test_rslib.c
@@ -385,7 +385,7 @@
/*
* We check that the returned word is actually a
- * codeword. The obious way to do this would be to
+ * codeword. The obvious way to do this would be to
* compute the syndrome, but we don't want to replicate
* that code here. However, all the codes are in
* systematic form, and therefore we can encode the
diff --git a/lib/refcount.c b/lib/refcount.c
index ebac8b7..a207a8f 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -164,7 +164,7 @@
* @flags: saved IRQ-flags if the is acquired
*
* Same as refcount_dec_and_lock() above except that the spinlock is acquired
- * with disabled interupts.
+ * with disabled interrupts.
*
* Return: true and hold spinlock if able to decrement refcount to 0, false
* otherwise
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index c949c1e..e12bbfb 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -703,7 +703,7 @@
*
* Returns zero if successful.
*
- * Returns -EAGAIN if resize event occured. Note that the iterator
+ * Returns -EAGAIN if resize event occurred. Note that the iterator
* will rewind back to the beginning and you may use it immediately
* by calling rhashtable_walk_next.
*
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 47b3691..b25db9b 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -583,7 +583,7 @@
/*
* Once the clear bit is set, the bit may be allocated out.
*
- * Orders READ/WRITE on the asssociated instance(such as request
+ * Orders READ/WRITE on the associated instance(such as request
* of blk_mq) by this bit for avoiding race with re-allocation,
* and its pair is the memory barrier implied in __sbitmap_get_word.
*
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index a597789..27efa61 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -38,7 +38,7 @@
* @sg: The scatterlist
*
* Description:
- * Allows to know how many entries are in sg, taking into acount
+ * Allows to know how many entries are in sg, taking into account
* chaining as well
*
**/
@@ -59,7 +59,7 @@
*
* Description:
* Determines the number of entries in sg that are required to meet
- * the supplied length, taking into acount chaining as well
+ * the supplied length, taking into account chaining as well
*
* Returns:
* the number of sg entries needed, negative error on failure
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 6dafde8..0a68f7a 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -289,7 +289,7 @@
}
/**
- * seq_buf_to_user - copy the squence buffer to user space
+ * seq_buf_to_user - copy the sequence buffer to user space
* @s: seq_buf descriptor
* @ubuf: The userspace memory location to copy to
* @cnt: The amount to copy
diff --git a/lib/sort.c b/lib/sort.c
index 3ad4544..aa18153 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -51,7 +51,7 @@
* which basically all CPUs have, to minimize loop overhead computations.
*
* For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
- * bottom of the loop, even though the zero flag is stil valid from the
+ * bottom of the loop, even though the zero flag is still valid from the
* subtract (since the intervening mov instructions don't alter the flags).
* Gcc 8.1.0 doesn't have that problem.
*/
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index df9179f..0a2e417 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -11,7 +11,7 @@
* Instead, stack depot maintains a hashtable of unique stacktraces. Since alloc
* and free stacks repeat a lot, we save about 100x space.
* Stacks are never removed from depot, so we store them contiguously one after
- * another in a contiguos memory allocation.
+ * another in a contiguous memory allocation.
*
* Author: Alexander Potapenko <glider@google.com>
* Copyright (C) 2016 Google, Inc.
diff --git a/lib/test_bitops.c b/lib/test_bitops.c
index 471141d..3b7bcbe 100644
--- a/lib/test_bitops.c
+++ b/lib/test_bitops.c
@@ -15,7 +15,7 @@
* get_count_order/long
*/
-/* use an enum because thats the most common BITMAP usage */
+/* use an enum because that's the most common BITMAP usage */
enum bitops_fun {
BITOPS_4 = 4,
BITOPS_7 = 7,
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 4dc4dcb..d500320 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -1095,7 +1095,7 @@
{
"RET_A",
.u.insns = {
- /* check that unitialized X and A contain zeros */
+ /* check that uninitialized X and A contain zeros */
BPF_STMT(BPF_MISC | BPF_TXA, 0),
BPF_STMT(BPF_RET | BPF_A, 0)
},
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index f5f5476..8f7b0b2 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -651,7 +651,7 @@
{
/*
* Deliberate out-of-bounds access. To prevent CONFIG_UBSAN_LOCAL_BOUNDS
- * from failing here and panicing the kernel, access the array via a
+ * from failing here and panicking the kernel, access the array via a
* volatile pointer, which will prevent the compiler from being able to
* determine the array bounds.
*
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index 38c250f..ce15893 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -286,7 +286,7 @@
* If this ran it means *all* tasks were created fine and we
* are now just collecting results.
*
- * Only propagate errors, do not override with a subsequent sucess case.
+ * Only propagate errors, do not override with a subsequent success case.
*/
static void tally_up_work(struct kmod_test_device *test_dev)
{
@@ -543,7 +543,7 @@
* wrong with the setup of the test. If the test setup went fine
* then userspace must just check the result of config->test_result.
* One issue with relying on the return from a call in the kernel
- * is if the kernel returns a possitive value using this trigger
+ * is if the kernel returns a positive value using this trigger
* will not return the value to userspace, it would be lost.
*
* By not relying on capturing the return value of tests we are using
@@ -585,7 +585,7 @@
* Note: any return > 0 will be treated as success
* and the error value will not be available to userspace.
* Do not rely on trying to send to userspace a test value
- * return value as possitive return errors will be lost.
+ * return value as positive return errors will be lost.
*/
if (WARN_ON(ret > 0))
return -EINVAL;
diff --git a/lib/test_scanf.c b/lib/test_scanf.c
index 48ff574..84fe09e 100644
--- a/lib/test_scanf.c
+++ b/lib/test_scanf.c
@@ -600,7 +600,7 @@
/*
* 0x prefix in a field of width 2 using %i conversion: first field
* converts to 0. Next field scan starts at the character after "0x",
- * which will convert if can be intepreted as decimal but will fail
+ * which will convert if can be interpreted as decimal but will fail
* if it contains any hex digits (since no 0x prefix).
*/
test_number_prefix(long long, "0x67", "%2lli%lli", 0, 67, 2, check_ll);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 2926cc2..26c8394 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -993,8 +993,12 @@
value = (unsigned long)ptr;
#ifdef CONFIG_KALLSYMS
- if (*fmt == 'B')
+ if (*fmt == 'B' && fmt[1] == 'b')
+ sprint_backtrace_build_id(sym, value);
+ else if (*fmt == 'B')
sprint_backtrace(sym, value);
+ else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b')))
+ sprint_symbol_build_id(sym, value);
else if (*fmt != 's')
sprint_symbol(sym, value);
else
@@ -2263,9 +2267,11 @@
* - 'S' For symbolic direct pointers (or function descriptors) with offset
* - 's' For symbolic direct pointers (or function descriptors) without offset
* - '[Ss]R' as above with __builtin_extract_return_addr() translation
+ * - 'S[R]b' as above with module build ID (for use in backtraces)
* - '[Ff]' %pf and %pF were obsoleted and later removed in favor of
* %ps and %pS. Be careful when re-using these specifiers.
* - 'B' For backtraced symbolic direct pointers with offset
+ * - 'Bb' as above with module build ID (for use in backtraces)
* - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref]
* - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201]
* - 'b[l]' For a bitmap, the number of bits is determined by the field
@@ -3417,7 +3423,7 @@
while (*fmt) {
/* skip any white space in format */
- /* white space in format matchs any amount of
+ /* white space in format matches any amount of
* white space, including none, in the input.
*/
if (isspace(*fmt)) {
diff --git a/mm/Kconfig b/mm/Kconfig
index a02498c..40a9bfc 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -885,4 +885,8 @@
# struct io_mapping based helper. Selected by drivers that need them
config IO_MAPPING
bool
+
+config SECRETMEM
+ def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 74b47c3..e343674 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -113,6 +113,7 @@
obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
+obj-$(CONFIG_SECRETMEM) += secretmem.o
obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
diff --git a/mm/gup.c b/mm/gup.c
index 728d996..42b8b1f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -10,6 +10,7 @@
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/secretmem.h>
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
@@ -855,6 +856,9 @@
struct follow_page_context ctx = { NULL };
struct page *page;
+ if (vma_is_secretmem(vma))
+ return NULL;
+
page = follow_page_mask(vma, address, foll_flags, &ctx);
if (ctx.pgmap)
put_dev_pagemap(ctx.pgmap);
@@ -988,6 +992,9 @@
if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
return -EOPNOTSUPP;
+ if (vma_is_secretmem(vma))
+ return -EFAULT;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
@@ -2170,6 +2177,11 @@
if (!head)
goto pte_unmap;
+ if (unlikely(page_is_secretmem(page))) {
+ put_compound_head(head, 1, flags);
+ goto pte_unmap;
+ }
+
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
put_compound_head(head, 1, flags);
goto pte_unmap;
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 15316266..b4a6f38 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -40,3 +40,12 @@
.cpu_bitmap = CPU_BITS_NONE,
INIT_MM_CONTEXT(init_mm)
};
+
+void setup_initial_init_mm(void *start_code, void *end_code,
+ void *end_data, void *brk)
+{
+ init_mm.start_code = (unsigned long)start_code;
+ init_mm.end_code = (unsigned long)end_code;
+ init_mm.end_data = (unsigned long)end_data;
+ init_mm.brk = (unsigned long)brk;
+}
diff --git a/mm/internal.h b/mm/internal.h
index 2d7c9a2..31ff935 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -360,6 +360,9 @@
extern void mlock_vma_page(struct page *page);
extern unsigned int munlock_vma_page(struct page *page);
+extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
+ unsigned long len);
+
/*
* Clear the page's PageMlocked(). This can be useful in a situation where
* we want to unconditionally remove a page from the pagecache -- e.g.,
diff --git a/mm/mlock.c b/mm/mlock.c
index 0d639bf4..16d2ee1 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -23,6 +23,7 @@
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
+#include <linux/secretmem.h>
#include "internal.h"
@@ -503,7 +504,7 @@
if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
- vma_is_dax(vma))
+ vma_is_dax(vma) || vma_is_secretmem(vma))
/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
goto out;
diff --git a/mm/mmap.c b/mm/mmap.c
index aa9de98..ca54d36 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1352,9 +1352,8 @@
return hint;
}
-static inline int mlock_future_check(struct mm_struct *mm,
- unsigned long flags,
- unsigned long len)
+int mlock_future_check(struct mm_struct *mm, unsigned long flags,
+ unsigned long len)
{
unsigned long locked, lock_limit;
diff --git a/mm/mremap.c b/mm/mremap.c
index a369a61..5989d39 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -25,7 +25,8 @@
#include <linux/userfaultfd_k.h>
#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/pgalloc.h>
#include "internal.h"
@@ -209,6 +210,15 @@
drop_rmap_locks(vma);
}
+#ifndef arch_supports_page_table_move
+#define arch_supports_page_table_move arch_supports_page_table_move
+static inline bool arch_supports_page_table_move(void)
+{
+ return IS_ENABLED(CONFIG_HAVE_MOVE_PMD) ||
+ IS_ENABLED(CONFIG_HAVE_MOVE_PUD);
+}
+#endif
+
#ifdef CONFIG_HAVE_MOVE_PMD
static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
@@ -217,6 +227,8 @@
struct mm_struct *mm = vma->vm_mm;
pmd_t pmd;
+ if (!arch_supports_page_table_move())
+ return false;
/*
* The destination pmd shouldn't be established, free_pgtables()
* should have released it.
@@ -258,8 +270,7 @@
VM_BUG_ON(!pmd_none(*new_pmd));
- /* Set the new pmd */
- set_pmd_at(mm, new_addr, new_pmd, pmd);
+ pmd_populate(mm, new_pmd, pmd_pgtable(pmd));
flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
@@ -276,7 +287,7 @@
}
#endif
-#ifdef CONFIG_HAVE_MOVE_PUD
+#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_HAVE_MOVE_PUD)
static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
{
@@ -284,6 +295,55 @@
struct mm_struct *mm = vma->vm_mm;
pud_t pud;
+ if (!arch_supports_page_table_move())
+ return false;
+ /*
+ * The destination pud shouldn't be established, free_pgtables()
+ * should have released it.
+ */
+ if (WARN_ON_ONCE(!pud_none(*new_pud)))
+ return false;
+
+ /*
+ * We don't have to worry about the ordering of src and dst
+ * ptlocks because exclusive mmap_lock prevents deadlock.
+ */
+ old_ptl = pud_lock(vma->vm_mm, old_pud);
+ new_ptl = pud_lockptr(mm, new_pud);
+ if (new_ptl != old_ptl)
+ spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+
+ /* Clear the pud */
+ pud = *old_pud;
+ pud_clear(old_pud);
+
+ VM_BUG_ON(!pud_none(*new_pud));
+
+ pud_populate(mm, new_pud, pud_pgtable(pud));
+ flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
+ if (new_ptl != old_ptl)
+ spin_unlock(new_ptl);
+ spin_unlock(old_ptl);
+
+ return true;
+}
+#else
+static inline bool move_normal_pud(struct vm_area_struct *vma,
+ unsigned long old_addr, unsigned long new_addr, pud_t *old_pud,
+ pud_t *new_pud)
+{
+ return false;
+}
+#endif
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static bool move_huge_pud(struct vm_area_struct *vma, unsigned long old_addr,
+ unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
+{
+ spinlock_t *old_ptl, *new_ptl;
+ struct mm_struct *mm = vma->vm_mm;
+ pud_t pud;
+
/*
* The destination pud shouldn't be established, free_pgtables()
* should have released it.
@@ -307,8 +367,9 @@
VM_BUG_ON(!pud_none(*new_pud));
/* Set the new pud */
+ /* mark soft_ditry when we add pud level soft dirty support */
set_pud_at(mm, new_addr, new_pud, pud);
- flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
+ flush_pud_tlb_range(vma, old_addr, old_addr + HPAGE_PUD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
@@ -316,11 +377,12 @@
return true;
}
#else
-static inline bool move_normal_pud(struct vm_area_struct *vma,
- unsigned long old_addr, unsigned long new_addr, pud_t *old_pud,
- pud_t *new_pud)
+static bool move_huge_pud(struct vm_area_struct *vma, unsigned long old_addr,
+ unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
{
+ WARN_ON_ONCE(1);
return false;
+
}
#endif
@@ -328,6 +390,7 @@
NORMAL_PMD,
HPAGE_PMD,
NORMAL_PUD,
+ HPAGE_PUD,
};
/*
@@ -347,6 +410,7 @@
mask = PMD_MASK;
size = PMD_SIZE;
break;
+ case HPAGE_PUD:
case NORMAL_PUD:
mask = PUD_MASK;
size = PUD_SIZE;
@@ -395,6 +459,12 @@
move_huge_pmd(vma, old_addr, new_addr, old_entry,
new_entry);
break;
+ case HPAGE_PUD:
+ moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+ move_huge_pud(vma, old_addr, new_addr, old_entry,
+ new_entry);
+ break;
+
default:
WARN_ON_ONCE(1);
break;
@@ -414,6 +484,7 @@
unsigned long extent, old_end;
struct mmu_notifier_range range;
pmd_t *old_pmd, *new_pmd;
+ pud_t *old_pud, *new_pud;
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
@@ -429,17 +500,24 @@
* PUD level if possible.
*/
extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr);
- if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD) && extent == PUD_SIZE) {
- pud_t *old_pud, *new_pud;
- old_pud = get_old_pud(vma->vm_mm, old_addr);
- if (!old_pud)
+ old_pud = get_old_pud(vma->vm_mm, old_addr);
+ if (!old_pud)
+ continue;
+ new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
+ if (!new_pud)
+ break;
+ if (pud_trans_huge(*old_pud) || pud_devmap(*old_pud)) {
+ if (extent == HPAGE_PUD_SIZE) {
+ move_pgt_entry(HPAGE_PUD, vma, old_addr, new_addr,
+ old_pud, new_pud, need_rmap_locks);
+ /* We ignore and continue on error? */
continue;
- new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
- if (!new_pud)
- break;
+ }
+ } else if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD) && extent == PUD_SIZE) {
+
if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr,
- old_pud, new_pud, need_rmap_locks))
+ old_pud, new_pud, true))
continue;
}
@@ -466,7 +544,7 @@
* moving at the PMD level if possible.
*/
if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr,
- old_pmd, new_pmd, need_rmap_locks))
+ old_pmd, new_pmd, true))
continue;
}
diff --git a/mm/secretmem.c b/mm/secretmem.c
new file mode 100644
index 0000000..f77d254
--- /dev/null
+++ b/mm/secretmem.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2021
+ *
+ * Author: Mike Rapoport <rppt@linux.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/swap.h>
+#include <linux/mount.h>
+#include <linux/memfd.h>
+#include <linux/bitops.h>
+#include <linux/printk.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/pseudo_fs.h>
+#include <linux/secretmem.h>
+#include <linux/set_memory.h>
+#include <linux/sched/signal.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "secretmem: " fmt
+
+/*
+ * Define mode and flag masks to allow validation of the system call
+ * parameters.
+ */
+#define SECRETMEM_MODE_MASK (0x0)
+#define SECRETMEM_FLAGS_MASK SECRETMEM_MODE_MASK
+
+static bool secretmem_enable __ro_after_init;
+module_param_named(enable, secretmem_enable, bool, 0400);
+MODULE_PARM_DESC(secretmem_enable,
+ "Enable secretmem and memfd_secret(2) system call");
+
+static atomic_t secretmem_users;
+
+bool secretmem_active(void)
+{
+ return !!atomic_read(&secretmem_users);
+}
+
+static vm_fault_t secretmem_fault(struct vm_fault *vmf)
+{
+ struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ pgoff_t offset = vmf->pgoff;
+ gfp_t gfp = vmf->gfp_mask;
+ unsigned long addr;
+ struct page *page;
+ int err;
+
+ if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+ return vmf_error(-EINVAL);
+
+retry:
+ page = find_lock_page(mapping, offset);
+ if (!page) {
+ page = alloc_page(gfp | __GFP_ZERO);
+ if (!page)
+ return VM_FAULT_OOM;
+
+ err = set_direct_map_invalid_noflush(page);
+ if (err) {
+ put_page(page);
+ return vmf_error(err);
+ }
+
+ __SetPageUptodate(page);
+ err = add_to_page_cache_lru(page, mapping, offset, gfp);
+ if (unlikely(err)) {
+ put_page(page);
+ /*
+ * If a split of large page was required, it
+ * already happened when we marked the page invalid
+ * which guarantees that this call won't fail
+ */
+ set_direct_map_default_noflush(page);
+ if (err == -EEXIST)
+ goto retry;
+
+ return vmf_error(err);
+ }
+
+ addr = (unsigned long)page_address(page);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ }
+
+ vmf->page = page;
+ return VM_FAULT_LOCKED;
+}
+
+static const struct vm_operations_struct secretmem_vm_ops = {
+ .fault = secretmem_fault,
+};
+
+static int secretmem_release(struct inode *inode, struct file *file)
+{
+ atomic_dec(&secretmem_users);
+ return 0;
+}
+
+static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ unsigned long len = vma->vm_end - vma->vm_start;
+
+ if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+ return -EINVAL;
+
+ if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
+ return -EAGAIN;
+
+ vma->vm_flags |= VM_LOCKED | VM_DONTDUMP;
+ vma->vm_ops = &secretmem_vm_ops;
+
+ return 0;
+}
+
+bool vma_is_secretmem(struct vm_area_struct *vma)
+{
+ return vma->vm_ops == &secretmem_vm_ops;
+}
+
+static const struct file_operations secretmem_fops = {
+ .release = secretmem_release,
+ .mmap = secretmem_mmap,
+};
+
+static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
+{
+ return false;
+}
+
+static int secretmem_migratepage(struct address_space *mapping,
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
+{
+ return -EBUSY;
+}
+
+static void secretmem_freepage(struct page *page)
+{
+ set_direct_map_default_noflush(page);
+ clear_highpage(page);
+}
+
+const struct address_space_operations secretmem_aops = {
+ .freepage = secretmem_freepage,
+ .migratepage = secretmem_migratepage,
+ .isolate_page = secretmem_isolate_page,
+};
+
+static struct vfsmount *secretmem_mnt;
+
+static struct file *secretmem_file_create(unsigned long flags)
+{
+ struct file *file = ERR_PTR(-ENOMEM);
+ struct inode *inode;
+
+ inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+
+ file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
+ O_RDWR, &secretmem_fops);
+ if (IS_ERR(file))
+ goto err_free_inode;
+
+ mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+ mapping_set_unevictable(inode->i_mapping);
+
+ inode->i_mapping->a_ops = &secretmem_aops;
+
+ /* pretend we are a normal file with zero size */
+ inode->i_mode |= S_IFREG;
+ inode->i_size = 0;
+
+ return file;
+
+err_free_inode:
+ iput(inode);
+ return file;
+}
+
+SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
+{
+ struct file *file;
+ int fd, err;
+
+ /* make sure local flags do not confict with global fcntl.h */
+ BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC);
+
+ if (!secretmem_enable)
+ return -ENOSYS;
+
+ if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC))
+ return -EINVAL;
+
+ fd = get_unused_fd_flags(flags & O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = secretmem_file_create(flags);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ goto err_put_fd;
+ }
+
+ file->f_flags |= O_LARGEFILE;
+
+ fd_install(fd, file);
+ atomic_inc(&secretmem_users);
+ return fd;
+
+err_put_fd:
+ put_unused_fd(fd);
+ return err;
+}
+
+static int secretmem_init_fs_context(struct fs_context *fc)
+{
+ return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type secretmem_fs = {
+ .name = "secretmem",
+ .init_fs_context = secretmem_init_fs_context,
+ .kill_sb = kill_anon_super,
+};
+
+static int secretmem_init(void)
+{
+ int ret = 0;
+
+ if (!secretmem_enable)
+ return ret;
+
+ secretmem_mnt = kern_mount(&secretmem_fs);
+ if (IS_ERR(secretmem_mnt))
+ ret = PTR_ERR(secretmem_mnt);
+
+ /* prevent secretmem mappings from ever getting PROT_EXEC */
+ secretmem_mnt->mnt_flags |= MNT_NOEXEC;
+
+ return ret;
+}
+fs_initcall(secretmem_init);
diff --git a/mm/slub.c b/mm/slub.c
index 2ee43ff..dc863c1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -26,6 +26,7 @@
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
+#include <linux/stackdepot.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/kfence.h>
@@ -220,8 +221,8 @@
#define TRACK_ADDRS_COUNT 16
struct track {
unsigned long addr; /* Called from address */
-#ifdef CONFIG_STACKTRACE
- unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */
+#ifdef CONFIG_STACKDEPOT
+ depot_stack_handle_t handle;
#endif
int cpu; /* Was running on cpu */
int pid; /* Pid context */
@@ -625,22 +626,27 @@
return kasan_reset_tag(p + alloc);
}
+#ifdef CONFIG_STACKDEPOT
+static depot_stack_handle_t save_stack_depot_trace(gfp_t flags)
+{
+ unsigned long entries[TRACK_ADDRS_COUNT];
+ depot_stack_handle_t handle;
+ unsigned int nr_entries;
+
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 4);
+ handle = stack_depot_save(entries, nr_entries, flags);
+ return handle;
+}
+#endif
+
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
struct track *p = get_track(s, object, alloc);
if (addr) {
-#ifdef CONFIG_STACKTRACE
- unsigned int nr_entries;
-
- metadata_access_enable();
- nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
- TRACK_ADDRS_COUNT, 3);
- metadata_access_disable();
-
- if (nr_entries < TRACK_ADDRS_COUNT)
- p->addrs[nr_entries] = 0;
+#ifdef CONFIG_STACKDEPOT
+ p->handle = save_stack_depot_trace(GFP_NOWAIT);
#endif
p->addr = addr;
p->cpu = smp_processor_id();
@@ -667,14 +673,19 @@
pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
-#ifdef CONFIG_STACKTRACE
+#ifdef CONFIG_STACKDEPOT
{
- int i;
- for (i = 0; i < TRACK_ADDRS_COUNT; i++)
- if (t->addrs[i])
- pr_err("\t%pS\n", (void *)t->addrs[i]);
- else
- break;
+ depot_stack_handle_t handle;
+ unsigned long *entries;
+ unsigned int nr_entries;
+
+ handle = READ_ONCE(t->handle);
+ if (!handle) {
+ pr_err("object allocation/free stack trace missing\n");
+ } else {
+ nr_entries = stack_depot_fetch(handle, &entries);
+ stack_trace_print(entries, nr_entries, 0);
+ }
}
#endif
}
@@ -4048,18 +4059,26 @@
objp = fixup_red_left(s, objp);
trackp = get_track(s, objp, TRACK_ALLOC);
kpp->kp_ret = (void *)trackp->addr;
-#ifdef CONFIG_STACKTRACE
- for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
- kpp->kp_stack[i] = (void *)trackp->addrs[i];
- if (!kpp->kp_stack[i])
- break;
- }
+#ifdef CONFIG_STACKDEPOT
+ {
+ depot_stack_handle_t handle;
+ unsigned long *entries;
+ unsigned int nr_entries;
- trackp = get_track(s, objp, TRACK_FREE);
- for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
- kpp->kp_free_stack[i] = (void *)trackp->addrs[i];
- if (!kpp->kp_free_stack[i])
- break;
+ handle = READ_ONCE(trackp->handle);
+ if (handle) {
+ nr_entries = stack_depot_fetch(handle, &entries);
+ for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
+ kpp->kp_stack[i] = (void *)entries[i];
+ }
+
+ trackp = get_track(s, objp, TRACK_FREE);
+ handle = READ_ONCE(trackp->handle);
+ if (handle) {
+ nr_entries = stack_depot_fetch(handle, &entries);
+ for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
+ kpp->kp_free_stack[i] = (void *)entries[i];
+ }
}
#endif
#endif
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index a18b476..b760995 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -40,6 +40,10 @@
#define __IGNORE_setrlimit /* setrlimit */
#endif
+#ifndef __ARCH_WANT_MEMFD_SECRET
+#define __IGNORE_memfd_secret
+#endif
+
/* Missing flags argument */
#define __IGNORE_renameat /* renameat2 */
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 9039834..5fbad61 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -3,11 +3,10 @@
# (c) 2014, Sasha Levin <sasha.levin@oracle.com>
#set -x
-if [[ $# < 1 ]]; then
+usage() {
echo "Usage:"
- echo " $0 -r <release> | <vmlinux> [base path] [modules path]"
- exit 1
-fi
+ echo " $0 -r <release> | <vmlinux> [<base path>|auto] [<modules path>]"
+}
if [[ $1 == "-r" ]] ; then
vmlinux=""
@@ -24,6 +23,7 @@
if [[ $vmlinux == "" ]] ; then
echo "ERROR! vmlinux image for release $release is not found" >&2
+ usage
exit 2
fi
else
@@ -31,12 +31,35 @@
basepath=${2-auto}
modpath=$3
release=""
+ debuginfod=
+
+ # Can we use debuginfod-find?
+ if type debuginfod-find >/dev/null 2>&1 ; then
+ debuginfod=${1-only}
+ fi
+
+ if [[ $vmlinux == "" && -z $debuginfod ]] ; then
+ echo "ERROR! vmlinux image must be specified" >&2
+ usage
+ exit 1
+ fi
fi
declare -A cache
declare -A modcache
find_module() {
+ if [[ -n $debuginfod ]] ; then
+ if [[ -n $modbuildid ]] ; then
+ debuginfod-find debuginfo $modbuildid && return
+ fi
+
+ # Only using debuginfod so don't try to find vmlinux module path
+ if [[ $debuginfod == "only" ]] ; then
+ return
+ fi
+ fi
+
if [[ "$modpath" != "" ]] ; then
for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do
if readelf -WS "$fn" | grep -qwF .debug_line ; then
@@ -51,7 +74,7 @@
find_module && return
if [[ $release == "" ]] ; then
- release=$(gdb -ex 'print init_uts_ns.name.release' -ex 'quit' -quiet -batch "$vmlinux" | sed -n 's/\$1 = "\(.*\)".*/\1/p')
+ release=$(gdb -ex 'print init_uts_ns.name.release' -ex 'quit' -quiet -batch "$vmlinux" 2>/dev/null | sed -n 's/\$1 = "\(.*\)".*/\1/p')
fi
for dn in {/usr/lib/debug,}/lib/modules/$release ; do
@@ -105,7 +128,7 @@
if [[ "${cache[$module,$name]+isset}" == "isset" ]]; then
local base_addr=${cache[$module,$name]}
else
- local base_addr=$(nm "$objfile" | awk '$3 == "'$name'" && ($2 == "t" || $2 == "T") {print $1; exit}')
+ local base_addr=$(nm "$objfile" 2>/dev/null | awk '$3 == "'$name'" && ($2 == "t" || $2 == "T") {print $1; exit}')
if [[ $base_addr == "" ]] ; then
# address not found
return
@@ -129,7 +152,7 @@
if [[ "${cache[$module,$address]+isset}" == "isset" ]]; then
local code=${cache[$module,$address]}
else
- local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address")
+ local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address" 2>/dev/null)
cache[$module,$address]=$code
fi
@@ -150,6 +173,27 @@
symbol="$segment$name ($code)"
}
+debuginfod_get_vmlinux() {
+ local vmlinux_buildid=${1##* }
+
+ if [[ $vmlinux != "" ]]; then
+ return
+ fi
+
+ if [[ $vmlinux_buildid =~ ^[0-9a-f]+ ]]; then
+ vmlinux=$(debuginfod-find debuginfo $vmlinux_buildid)
+ if [[ $? -ne 0 ]] ; then
+ echo "ERROR! vmlinux image not found via debuginfod-find" >&2
+ usage
+ exit 2
+ fi
+ return
+ fi
+ echo "ERROR! Build ID for vmlinux not found. Try passing -r or specifying vmlinux" >&2
+ usage
+ exit 2
+}
+
decode_code() {
local scripts=`dirname "${BASH_SOURCE[0]}"`
@@ -157,6 +201,14 @@
}
handle_line() {
+ if [[ $basepath == "auto" && $vmlinux != "" ]] ; then
+ module=""
+ symbol="kernel_init+0x0/0x0"
+ parse_symbol
+ basepath=${symbol#kernel_init (}
+ basepath=${basepath%/init/main.c:*)}
+ fi
+
local words
# Tokenize
@@ -182,16 +234,28 @@
fi
done
+ if [[ ${words[$last]} =~ ^[0-9a-f]+\] ]]; then
+ words[$last-1]="${words[$last-1]} ${words[$last]}"
+ unset words[$last]
+ last=$(( $last - 1 ))
+ fi
+
if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then
module=${words[$last]}
module=${module#\[}
module=${module%\]}
+ modbuildid=${module#* }
+ module=${module% *}
+ if [[ $modbuildid == $module ]]; then
+ modbuildid=
+ fi
symbol=${words[$last-1]}
unset words[$last-1]
else
# The symbol is the last element, process it
symbol=${words[$last]}
module=
+ modbuildid=
fi
unset words[$last]
@@ -201,14 +265,6 @@
echo "${words[@]}" "$symbol $module"
}
-if [[ $basepath == "auto" ]] ; then
- module=""
- symbol="kernel_init+0x0/0x0"
- parse_symbol
- basepath=${symbol#kernel_init (}
- basepath=${basepath%/init/main.c:*)}
-fi
-
while read line; do
# Let's see if we have an address in the line
if [[ $line =~ \[\<([^]]+)\>\] ]] ||
@@ -218,6 +274,9 @@
# Is it a code line?
elif [[ $line == *Code:* ]]; then
decode_code "$line"
+ # Is it a version line?
+ elif [[ -n $debuginfod && $line =~ PID:\ [0-9]+\ Comm: ]]; then
+ debuginfod_get_vmlinux "$line"
else
# Nothing special in this line, show it as is
echo "$line"
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index d683a49..f0fd80e 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -24,5 +24,6 @@
map_fixed_noreplace
write_to_hugetlbfs
hmm-tests
+memfd_secret
local_config.*
split_huge_page_test
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 812bc03..5212437 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -35,6 +35,7 @@
TEST_GEN_FILES += map_fixed_noreplace
TEST_GEN_FILES += map_hugetlb
TEST_GEN_FILES += map_populate
+TEST_GEN_FILES += memfd_secret
TEST_GEN_FILES += mlock-random-test
TEST_GEN_FILES += mlock2-tests
TEST_GEN_FILES += mremap_dontunmap
@@ -135,7 +136,7 @@
endif
endif
-$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
+$(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap
$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c
new file mode 100644
index 0000000..93e7e7f
--- /dev/null
+++ b/tools/testing/selftests/vm/memfd_secret.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2021
+ *
+ * Author: Mike Rapoport <rppt@linux.ibm.com>
+ */
+
+#define _GNU_SOURCE
+#include <sys/uio.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <sys/types.h>
+#include <sys/ptrace.h>
+#include <sys/syscall.h>
+#include <sys/resource.h>
+#include <sys/capability.h>
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+
+#include "../kselftest.h"
+
+#define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__)
+#define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__)
+#define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__)
+
+#ifdef __NR_memfd_secret
+
+#define PATTERN 0x55
+
+static const int prot = PROT_READ | PROT_WRITE;
+static const int mode = MAP_SHARED;
+
+static unsigned long page_size;
+static unsigned long mlock_limit_cur;
+static unsigned long mlock_limit_max;
+
+static int memfd_secret(unsigned int flags)
+{
+ return syscall(__NR_memfd_secret, flags);
+}
+
+static void test_file_apis(int fd)
+{
+ char buf[64];
+
+ if ((read(fd, buf, sizeof(buf)) >= 0) ||
+ (write(fd, buf, sizeof(buf)) >= 0) ||
+ (pread(fd, buf, sizeof(buf), 0) >= 0) ||
+ (pwrite(fd, buf, sizeof(buf), 0) >= 0))
+ fail("unexpected file IO\n");
+ else
+ pass("file IO is blocked as expected\n");
+}
+
+static void test_mlock_limit(int fd)
+{
+ size_t len;
+ char *mem;
+
+ len = mlock_limit_cur;
+ mem = mmap(NULL, len, prot, mode, fd, 0);
+ if (mem == MAP_FAILED) {
+ fail("unable to mmap secret memory\n");
+ return;
+ }
+ munmap(mem, len);
+
+ len = mlock_limit_max * 2;
+ mem = mmap(NULL, len, prot, mode, fd, 0);
+ if (mem != MAP_FAILED) {
+ fail("unexpected mlock limit violation\n");
+ munmap(mem, len);
+ return;
+ }
+
+ pass("mlock limit is respected\n");
+}
+
+static void try_process_vm_read(int fd, int pipefd[2])
+{
+ struct iovec liov, riov;
+ char buf[64];
+ char *mem;
+
+ if (read(pipefd[0], &mem, sizeof(mem)) < 0) {
+ fail("pipe write: %s\n", strerror(errno));
+ exit(KSFT_FAIL);
+ }
+
+ liov.iov_len = riov.iov_len = sizeof(buf);
+ liov.iov_base = buf;
+ riov.iov_base = mem;
+
+ if (process_vm_readv(getppid(), &liov, 1, &riov, 1, 0) < 0) {
+ if (errno == ENOSYS)
+ exit(KSFT_SKIP);
+ exit(KSFT_PASS);
+ }
+
+ exit(KSFT_FAIL);
+}
+
+static void try_ptrace(int fd, int pipefd[2])
+{
+ pid_t ppid = getppid();
+ int status;
+ char *mem;
+ long ret;
+
+ if (read(pipefd[0], &mem, sizeof(mem)) < 0) {
+ perror("pipe write");
+ exit(KSFT_FAIL);
+ }
+
+ ret = ptrace(PTRACE_ATTACH, ppid, 0, 0);
+ if (ret) {
+ perror("ptrace_attach");
+ exit(KSFT_FAIL);
+ }
+
+ ret = waitpid(ppid, &status, WUNTRACED);
+ if ((ret != ppid) || !(WIFSTOPPED(status))) {
+ fprintf(stderr, "weird waitppid result %ld stat %x\n",
+ ret, status);
+ exit(KSFT_FAIL);
+ }
+
+ if (ptrace(PTRACE_PEEKDATA, ppid, mem, 0))
+ exit(KSFT_PASS);
+
+ exit(KSFT_FAIL);
+}
+
+static void check_child_status(pid_t pid, const char *name)
+{
+ int status;
+
+ waitpid(pid, &status, 0);
+
+ if (WIFEXITED(status) && WEXITSTATUS(status) == KSFT_SKIP) {
+ skip("%s is not supported\n", name);
+ return;
+ }
+
+ if ((WIFEXITED(status) && WEXITSTATUS(status) == KSFT_PASS) ||
+ WIFSIGNALED(status)) {
+ pass("%s is blocked as expected\n", name);
+ return;
+ }
+
+ fail("%s: unexpected memory access\n", name);
+}
+
+static void test_remote_access(int fd, const char *name,
+ void (*func)(int fd, int pipefd[2]))
+{
+ int pipefd[2];
+ pid_t pid;
+ char *mem;
+
+ if (pipe(pipefd)) {
+ fail("pipe failed: %s\n", strerror(errno));
+ return;
+ }
+
+ pid = fork();
+ if (pid < 0) {
+ fail("fork failed: %s\n", strerror(errno));
+ return;
+ }
+
+ if (pid == 0) {
+ func(fd, pipefd);
+ return;
+ }
+
+ mem = mmap(NULL, page_size, prot, mode, fd, 0);
+ if (mem == MAP_FAILED) {
+ fail("Unable to mmap secret memory\n");
+ return;
+ }
+
+ ftruncate(fd, page_size);
+ memset(mem, PATTERN, page_size);
+
+ if (write(pipefd[1], &mem, sizeof(mem)) < 0) {
+ fail("pipe write: %s\n", strerror(errno));
+ return;
+ }
+
+ check_child_status(pid, name);
+}
+
+static void test_process_vm_read(int fd)
+{
+ test_remote_access(fd, "process_vm_read", try_process_vm_read);
+}
+
+static void test_ptrace(int fd)
+{
+ test_remote_access(fd, "ptrace", try_ptrace);
+}
+
+static int set_cap_limits(rlim_t max)
+{
+ struct rlimit new;
+ cap_t cap = cap_init();
+
+ new.rlim_cur = max;
+ new.rlim_max = max;
+ if (setrlimit(RLIMIT_MEMLOCK, &new)) {
+ perror("setrlimit() returns error");
+ return -1;
+ }
+
+ /* drop capabilities including CAP_IPC_LOCK */
+ if (cap_set_proc(cap)) {
+ perror("cap_set_proc() returns error");
+ return -2;
+ }
+
+ return 0;
+}
+
+static void prepare(void)
+{
+ struct rlimit rlim;
+
+ page_size = sysconf(_SC_PAGE_SIZE);
+ if (!page_size)
+ ksft_exit_fail_msg("Failed to get page size %s\n",
+ strerror(errno));
+
+ if (getrlimit(RLIMIT_MEMLOCK, &rlim))
+ ksft_exit_fail_msg("Unable to detect mlock limit: %s\n",
+ strerror(errno));
+
+ mlock_limit_cur = rlim.rlim_cur;
+ mlock_limit_max = rlim.rlim_max;
+
+ printf("page_size: %ld, mlock.soft: %ld, mlock.hard: %ld\n",
+ page_size, mlock_limit_cur, mlock_limit_max);
+
+ if (page_size > mlock_limit_cur)
+ mlock_limit_cur = page_size;
+ if (page_size > mlock_limit_max)
+ mlock_limit_max = page_size;
+
+ if (set_cap_limits(mlock_limit_max))
+ ksft_exit_fail_msg("Unable to set mlock limit: %s\n",
+ strerror(errno));
+}
+
+#define NUM_TESTS 4
+
+int main(int argc, char *argv[])
+{
+ int fd;
+
+ prepare();
+
+ ksft_print_header();
+ ksft_set_plan(NUM_TESTS);
+
+ fd = memfd_secret(0);
+ if (fd < 0) {
+ if (errno == ENOSYS)
+ ksft_exit_skip("memfd_secret is not supported\n");
+ else
+ ksft_exit_fail_msg("memfd_secret failed: %s\n",
+ strerror(errno));
+ }
+
+ test_mlock_limit(fd);
+ test_file_apis(fd);
+ test_process_vm_read(fd);
+ test_ptrace(fd);
+
+ close(fd);
+
+ ksft_exit(!ksft_get_fail_cnt());
+}
+
+#else /* __NR_memfd_secret */
+
+int main(int argc, char *argv[])
+{
+ printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n");
+ return KSFT_SKIP;
+}
+
+#endif /* __NR_memfd_secret */
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index 9c391d0..0624d1b 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -45,14 +45,15 @@
_4MB = 4ULL << 20,
_1GB = 1ULL << 30,
_2GB = 2ULL << 30,
- PTE = _4KB,
PMD = _2MB,
PUD = _1GB,
};
+#define PTE page_size
+
#define MAKE_TEST(source_align, destination_align, size, \
overlaps, should_fail, test_name) \
-{ \
+(struct test){ \
.name = test_name, \
.config = { \
.src_alignment = source_align, \
@@ -74,9 +75,10 @@
retry:
addr += c.src_alignment;
src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+ MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+ -1, 0);
if (src_addr == MAP_FAILED) {
- if (errno == EPERM)
+ if (errno == EPERM || errno == EEXIST)
goto retry;
goto error;
}
@@ -252,12 +254,17 @@
return 0;
}
+#define MAX_TEST 13
+#define MAX_PERF_TEST 3
int main(int argc, char **argv)
{
int failures = 0;
int i, run_perf_tests;
unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD;
unsigned int pattern_seed;
+ struct test test_cases[MAX_TEST];
+ struct test perf_test_cases[MAX_PERF_TEST];
+ int page_size;
time_t t;
pattern_seed = (unsigned int) time(&t);
@@ -268,56 +275,59 @@
ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n",
threshold_mb, pattern_seed);
- struct test test_cases[] = {
- /* Expected mremap failures */
- MAKE_TEST(_4KB, _4KB, _4KB, OVERLAPPING, EXPECT_FAILURE,
- "mremap - Source and Destination Regions Overlapping"),
- MAKE_TEST(_4KB, _1KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
- "mremap - Destination Address Misaligned (1KB-aligned)"),
- MAKE_TEST(_1KB, _4KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
- "mremap - Source Address Misaligned (1KB-aligned)"),
+ page_size = sysconf(_SC_PAGESIZE);
- /* Src addr PTE aligned */
- MAKE_TEST(PTE, PTE, _8KB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "8KB mremap - Source PTE-aligned, Destination PTE-aligned"),
+ /* Expected mremap failures */
+ test_cases[0] = MAKE_TEST(page_size, page_size, page_size,
+ OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Source and Destination Regions Overlapping");
- /* Src addr 1MB aligned */
- MAKE_TEST(_1MB, PTE, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2MB mremap - Source 1MB-aligned, Destination PTE-aligned"),
- MAKE_TEST(_1MB, _1MB, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2MB mremap - Source 1MB-aligned, Destination 1MB-aligned"),
+ test_cases[1] = MAKE_TEST(page_size, page_size/4, page_size,
+ NON_OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Destination Address Misaligned (1KB-aligned)");
+ test_cases[2] = MAKE_TEST(page_size/4, page_size, page_size,
+ NON_OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Source Address Misaligned (1KB-aligned)");
- /* Src addr PMD aligned */
- MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "4MB mremap - Source PMD-aligned, Destination PTE-aligned"),
- MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "4MB mremap - Source PMD-aligned, Destination 1MB-aligned"),
- MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "4MB mremap - Source PMD-aligned, Destination PMD-aligned"),
+ /* Src addr PTE aligned */
+ test_cases[3] = MAKE_TEST(PTE, PTE, PTE * 2,
+ NON_OVERLAPPING, EXPECT_SUCCESS,
+ "8KB mremap - Source PTE-aligned, Destination PTE-aligned");
- /* Src addr PUD aligned */
- MAKE_TEST(PUD, PTE, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2GB mremap - Source PUD-aligned, Destination PTE-aligned"),
- MAKE_TEST(PUD, _1MB, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2GB mremap - Source PUD-aligned, Destination 1MB-aligned"),
- MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2GB mremap - Source PUD-aligned, Destination PMD-aligned"),
- MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "2GB mremap - Source PUD-aligned, Destination PUD-aligned"),
- };
+ /* Src addr 1MB aligned */
+ test_cases[4] = MAKE_TEST(_1MB, PTE, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2MB mremap - Source 1MB-aligned, Destination PTE-aligned");
+ test_cases[5] = MAKE_TEST(_1MB, _1MB, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2MB mremap - Source 1MB-aligned, Destination 1MB-aligned");
- struct test perf_test_cases[] = {
- /*
- * mremap 1GB region - Page table level aligned time
- * comparison.
- */
- MAKE_TEST(PTE, PTE, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "1GB mremap - Source PTE-aligned, Destination PTE-aligned"),
- MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "1GB mremap - Source PMD-aligned, Destination PMD-aligned"),
- MAKE_TEST(PUD, PUD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
- "1GB mremap - Source PUD-aligned, Destination PUD-aligned"),
- };
+ /* Src addr PMD aligned */
+ test_cases[6] = MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination PTE-aligned");
+ test_cases[7] = MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination 1MB-aligned");
+ test_cases[8] = MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination PMD-aligned");
+
+ /* Src addr PUD aligned */
+ test_cases[9] = MAKE_TEST(PUD, PTE, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PTE-aligned");
+ test_cases[10] = MAKE_TEST(PUD, _1MB, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination 1MB-aligned");
+ test_cases[11] = MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PMD-aligned");
+ test_cases[12] = MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PUD-aligned");
+
+ perf_test_cases[0] = MAKE_TEST(page_size, page_size, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PTE-aligned, Destination PTE-aligned");
+ /*
+ * mremap 1GB region - Page table level aligned time
+ * comparison.
+ */
+ perf_test_cases[1] = MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PMD-aligned, Destination PMD-aligned");
+ perf_test_cases[2] = MAKE_TEST(PUD, PUD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PUD-aligned, Destination PUD-aligned");
run_perf_tests = (threshold_mb == VALIDATION_NO_THRESHOLD) ||
(threshold_mb * _1MB >= _1GB);
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 955782d..d09a6b7 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -362,4 +362,21 @@
exitcode=1
fi
+echo "running memfd_secret test"
+echo "------------------------------------"
+./memfd_secret
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+ echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+ echo "[SKIP]"
+ exitcode=$ksft_skip
+else
+ echo "[FAIL]"
+ exitcode=1
+fi
+
+exit $exitcode
+
exit $exitcode
