Merge branch 'mm-stable' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/akpm/mm
mariux64 · Sep 16, 2022 · 818ae0d · 818ae0d
2 parents 7fcb7bf + 088b8aa
commit 818ae0d
Show file tree

Hide file tree

Showing 147 changed files with 2,603 additions and 1,625 deletions.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
@@ -1469,6 +1469,14 @@
 			Permit 'security.evm' to be updated regardless of
 			current integrity status.
 
+	early_page_ext [KNL] Enforces page_ext initialization to earlier
+			stages so cover more early boot allocations.
+			Please note that as side effect some optimizations
+			might be disabled to achieve that (e.g. parallelized
+			memory initialization is disabled) so the boot process
+			might take longer, especially on systems with a lot of
+			memory. Available with CONFIG_PAGE_EXTENSION=y.
+
 	failslab=
 	fail_usercopy=
 	fail_page_alloc=

diff --git a/Documentation/admin-guide/mm/cma_debugfs.rst b/Documentation/admin-guide/mm/cma_debugfs.rst
@@ -5,10 +5,10 @@ CMA Debugfs Interface
 The CMA debugfs interface is useful to retrieve basic information out of the
 different CMA areas and to test allocation/release in each of the areas.
 
-Each CMA zone represents a directory under <debugfs>/cma/, indexed by the
-kernel's CMA index. So the first CMA zone would be:
+Each CMA area represents a directory under <debugfs>/cma/, represented by
+its CMA name like below:
 
-	<debugfs>/cma/cma-0
+	<debugfs>/cma/<cma_name>
 
 The structure of the files created under that directory is as follows:
 
@@ -18,8 +18,8 @@ The structure of the files created under that directory is as follows:
  - [RO] bitmap: The bitmap of page states in the zone.
  - [WO] alloc: Allocate N pages from that CMA area. For example::
 
-	echo 5 > <debugfs>/cma/cma-2/alloc
+	echo 5 > <debugfs>/cma/<cma_name>/alloc
 
-would try to allocate 5 pages from the cma-2 area.
+would try to allocate 5 pages from the 'cma_name' area.
 
  - [WO] free: Free N pages from that CMA area, similar to the above.
diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -17,7 +17,10 @@ of the ``PROT_NONE+SIGSEGV`` trick.
 Design
 ======
 
-Userfaults are delivered and resolved through the ``userfaultfd`` syscall.
+Userspace creates a new userfaultfd, initializes it, and registers one or more
+regions of virtual memory with it. Then, any page faults which occur within the
+region(s) result in a message being delivered to the userfaultfd, notifying
+userspace of the fault.
 
 The ``userfaultfd`` (aside from registering and unregistering virtual
 memory ranges) provides two primary functionalities:
@@ -34,12 +37,11 @@ The real advantage of userfaults if compared to regular virtual memory
 management of mremap/mprotect is that the userfaults in all their
 operations never involve heavyweight structures like vmas (in fact the
 ``userfaultfd`` runtime load never takes the mmap_lock for writing).
-
 Vmas are not suitable for page- (or hugepage) granular fault tracking
 when dealing with virtual address spaces that could span
 Terabytes. Too many vmas would be needed for that.
 
-The ``userfaultfd`` once opened by invoking the syscall, can also be
+The ``userfaultfd``, once created, can also be
 passed using unix domain sockets to a manager process, so the same
 manager process could handle the userfaults of a multitude of
 different processes without them being aware about what is going on
@@ -50,6 +52,39 @@ is a corner case that would currently return ``-EBUSY``).
 API
 ===
 
+Creating a userfaultfd
+----------------------
+
+There are two ways to create a new userfaultfd, each of which provide ways to
+restrict access to this functionality (since historically userfaultfds which
+handle kernel page faults have been a useful tool for exploiting the kernel).
+
+The first way, supported since userfaultfd was introduced, is the
+userfaultfd(2) syscall. Access to this is controlled in several ways:
+
+- Any user can always create a userfaultfd which traps userspace page faults
+  only. Such a userfaultfd can be created using the userfaultfd(2) syscall
+  with the flag UFFD_USER_MODE_ONLY.
+
+- In order to also trap kernel page faults for the address space, either the
+  process needs the CAP_SYS_PTRACE capability, or the system must have
+  vm.unprivileged_userfaultfd set to 1. By default, vm.unprivileged_userfaultfd
+  is set to 0.
+
+The second way, added to the kernel more recently, is by opening
+/dev/userfaultfd and issuing a USERFAULTFD_IOC_NEW ioctl to it. This method
+yields equivalent userfaultfds to the userfaultfd(2) syscall.
+
+Unlike userfaultfd(2), access to /dev/userfaultfd is controlled via normal
+filesystem permissions (user/group/mode), which gives fine grained access to
+userfaultfd specifically, without also granting other unrelated privileges at
+the same time (as e.g. granting CAP_SYS_PTRACE would do). Users who have access
+to /dev/userfaultfd can always create userfaultfds that trap kernel page faults;
+vm.unprivileged_userfaultfd is not considered.
+
+Initializing a userfaultfd
+--------------------------
+
 When first opened the ``userfaultfd`` must be enabled invoking the
 ``UFFDIO_API`` ioctl specifying a ``uffdio_api.api`` value set to ``UFFD_API`` (or
 a later API version) which will specify the ``read/POLLIN`` protocol

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
@@ -635,6 +635,17 @@ different types of memory (represented as different NUMA nodes) to
 place the hot pages in the fast memory.  This is implemented based on
 unmapping and page fault too.
 
+numa_balancing_promote_rate_limit_MBps
+======================================
+
+Too high promotion/demotion throughput between different memory types
+may hurt application latency.  This can be used to rate limit the
+promotion throughput.  The per-node max promotion throughput in MB/s
+will be limited to be no more than the set value.
+
+A rule of thumb is to set this to less than 1/10 of the PMEM node
+write bandwidth.
+
 oops_all_cpu_backtrace
 ======================
 

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
@@ -926,6 +926,9 @@ calls without any restrictions.
 
 The default value is 0.
 
+Another way to control permissions for userfaultfd is to use
+/dev/userfaultfd instead of userfaultfd(2). See
+Documentation/admin-guide/mm/userfaultfd.rst.
 
 user_reserve_kbytes
 ===================

diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst
@@ -94,6 +94,11 @@ Usage
 	Page allocated via order XXX, ...
 	PFN XXX ...
 	// Detailed stack
+    By default, it will do full pfn dump, to start with a given pfn,
+    page_owner supports fseek.
+
+    FILE *fp = fopen("/sys/kernel/debug/page_owner", "r");
+    fseek(fp, pfn_start, SEEK_SET);
 
    The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows
    in buf, uses regexp to extract the page order value, counts the times

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
@@ -76,6 +76,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
@@ -554,7 +554,7 @@ config ARC_BUILTIN_DTB_NAME
 
 endmenu	 # "ARC Architecture Configuration"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "12" if ARC_HUGEPAGE_16M
 	default "11"

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
@@ -1362,7 +1362,7 @@ config ARM_MODULE_PLTS
 	  Disabling this is usually safe for small single-platform
 	  configurations. If unsure, say y.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "12" if SOC_AM33XX
 	default "9" if SA1111

diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
@@ -31,7 +31,7 @@ CONFIG_SOC_VF610=y
 CONFIG_SMP=y
 CONFIG_ARM_PSCI=y
 CONFIG_HIGHMEM=y
-CONFIG_FORCE_MAX_ZONEORDER=14
+CONFIG_ARCH_FORCE_MAX_ORDER=14
 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y

diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -26,7 +26,7 @@ CONFIG_THUMB2_KERNEL=y
 # CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 CONFIG_HIGHMEM=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
 CONFIG_EFI=y

diff --git a/arch/arm/configs/oxnas_v6_defconfig b/arch/arm/configs/oxnas_v6_defconfig
@@ -12,7 +12,7 @@ CONFIG_ARCH_OXNAS=y
 CONFIG_MACH_OX820=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_SECCOMP=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y

diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
@@ -21,7 +21,7 @@ CONFIG_MACH_AKITA=y
 CONFIG_MACH_BORZOI=y
 CONFIG_PXA_SYSTEMS_CPLDS=y
 CONFIG_AEABI=y
-CONFIG_FORCE_MAX_ZONEORDER=9
+CONFIG_ARCH_FORCE_MAX_ORDER=9
 CONFIG_CMDLINE="root=/dev/ram0 ro"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y

diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
@@ -19,7 +19,7 @@ CONFIG_ATMEL_CLOCKSOURCE_TCB=y
 # CONFIG_CACHE_L2X0 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 # CONFIG_CPU_SW_DOMAIN_PAN is not set
-CONFIG_FORCE_MAX_ZONEORDER=15
+CONFIG_ARCH_FORCE_MAX_ORDER=15
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
 CONFIG_CMDLINE="console=ttyS0,115200 earlyprintk ignore_loglevel"

diff --git a/arch/arm/configs/sp7021_defconfig b/arch/arm/configs/sp7021_defconfig
@@ -17,7 +17,7 @@ CONFIG_ARCH_SUNPLUS=y
 # CONFIG_VDSO is not set
 CONFIG_SMP=y
 CONFIG_THUMB2_KERNEL=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_MODULES=y

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
@@ -1418,7 +1418,7 @@ config XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int
 	default "14" if ARM64_64K_PAGES
 	default "12" if ARM64_16K_PAGES

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
@@ -332,7 +332,7 @@ config HIGHMEM
 	select KMAP_LOCAL
 	default y
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "11"
 

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
@@ -200,7 +200,7 @@ config IA64_CYCLONE
 	  Say Y here to enable support for IBM EXA Cyclone time source.
 	  If you're unsure, answer N.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "MAX_ORDER (11 - 17)"  if !HUGETLB_PAGE
 	range 11 17  if !HUGETLB_PAGE
 	default "17" if HUGETLB_PAGE

diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
@@ -11,10 +11,10 @@
 
 #define SECTION_SIZE_BITS	(30)
 #define MAX_PHYSMEM_BITS	(50)
-#ifdef CONFIG_FORCE_MAX_ZONEORDER
-#if ((CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
+#ifdef CONFIG_ARCH_FORCE_MAX_ORDER
+#if ((CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
 #undef SECTION_SIZE_BITS
-#define SECTION_SIZE_BITS (CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT)
+#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT)
 #endif
 #endif
 

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
@@ -381,7 +381,7 @@ config NODES_SHIFT
 	default "6"
 	depends on NUMA
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 14 64 if PAGE_SIZE_64KB
 	default "14" if PAGE_SIZE_64KB

diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
@@ -397,7 +397,7 @@ config SINGLE_MEMORY_CHUNK
 	  order" to save memory that could be wasted for unused memory map.
 	  Say N if not sure.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order" if ADVANCED
 	depends on !SINGLE_MEMORY_CHUNK
 	default "11"

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
@@ -2140,7 +2140,7 @@ config PAGE_SIZE_64KB
 
 endchoice
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
 	default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB

diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
@@ -103,6 +103,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
@@ -44,7 +44,7 @@ menu "Kernel features"
 
 source "kernel/Kconfig.hz"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 9 20
 	default "11"

diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
@@ -70,6 +70,8 @@
 #define MADV_WIPEONFORK 71		/* Zero memory on fork, child only */
 #define MADV_KEEPONFORK 72		/* Undo MADV_WIPEONFORK */
 
+#define MADV_COLLAPSE	73		/* Synchronous hugepage collapse */
+
 #define MADV_HWPOISON     100		/* poison a page for testing */
 #define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
 

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
@@ -845,7 +845,7 @@ config DATA_SHIFT
 	  in that case. If PIN_TLB is selected, it must be aligned to 8M as
 	  8M pages will be pinned.
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 8 9 if PPC64 && PPC_64K_PAGES
 	default "9" if PPC64 && PPC_64K_PAGES

diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -30,7 +30,7 @@ CONFIG_PREEMPT=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
-CONFIG_FORCE_MAX_ZONEORDER=17
+CONFIG_ARCH_FORCE_MAX_ORDER=17
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MSI=y

diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -41,7 +41,7 @@ CONFIG_FIXED_PHY=y
 CONFIG_FONT_8x16=y
 CONFIG_FONT_8x8=y
 CONFIG_FONTS=y
-CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_ARCH_FORCE_MAX_ORDER=13
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAME_WARN=1024
 CONFIG_FTL=y

diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
@@ -237,16 +237,6 @@ int pud_huge(pud_t pud)
 	return pud_large(pud);
 }
 
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int flags)
-{
-	if (flags & FOLL_GET)
-		return NULL;
-
-	return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)

diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
@@ -8,7 +8,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_CPU_SUBTYPE_SH7724=y
-CONFIG_FORCE_MAX_ZONEORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=12
 CONFIG_MEMORY_SIZE=0x10000000
 CONFIG_FLATMEM_MANUAL=y
 CONFIG_SH_ECOVEC=y

diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
@@ -18,7 +18,7 @@ config PAGE_OFFSET
 	default "0x80000000" if MMU
 	default "0x00000000"
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	range 9 64 if PAGE_SIZE_16KB
 	default "9" if PAGE_SIZE_16KB

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
@@ -269,7 +269,7 @@ config ARCH_SPARSEMEM_ENABLE
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y if SPARC64
 
-config FORCE_MAX_ZONEORDER
+config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "13"
 	help