Merge branch 'akpm-current/current'

Documentation/admin-guide/cgroup-v2.rst

@@ -1301,6 +1301,11 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used to cache filesystem data,
 		including tmpfs and shared memory.
 
+	  kernel (npn)
+		Amount of total kernel memory, including
+		(kernel_stack, pagetables, percpu, vmalloc, slab) in
+		addition to other kernel memory use cases.
+
 	  kernel_stack
 		Amount of memory allocated to kernel stacks.
 

Documentation/admin-guide/kdump/kdump.rst

@@ -146,9 +146,9 @@ System kernel config options
 	CONFIG_SYSFS=y
 
    Note that "sysfs file system support" might not appear in the "Pseudo
-   filesystems" menu if "Configure standard kernel features (for small
-   systems)" is not enabled in "General Setup." In this case, check the
-   .config file itself to ensure that sysfs is turned on, as follows::
+   filesystems" menu if "Configure standard kernel features (expert users)"
+   is not enabled in "General Setup." In this case, check the .config file
+   itself to ensure that sysfs is turned on, as follows::
 
 	grep 'CONFIG_SYSFS' .config
 
@@ -533,6 +533,10 @@ the following command::
 
    cp /proc/vmcore <dump-file>
 
+or use scp to write out the dump file between hosts on a network, e.g::
+
+   scp /proc/vmcore remote_username@remote_ip:<dump-file>
+
 You can also use makedumpfile utility to write out the dump file
 with specified options to filter out unwanted contents, e.g::
 

Documentation/admin-guide/kernel-parameters.txt

@@ -1649,7 +1649,7 @@
 			[KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 			enabled.
 			Allows heavy hugetlb users to free up some more
-			memory (6 * PAGE_SIZE for each 2MB hugetlb page).
+			memory (7 * PAGE_SIZE for each 2MB hugetlb page).
 			Format: { on | off (default) }
 
 			on:  enable the feature
@@ -3765,6 +3765,7 @@
 			bit 3: print locks info if CONFIG_LOCKDEP is on
 			bit 4: print ftrace buffer
 			bit 5: print all printk messages in buffer
+			bit 6: print all CPUs backtrace (if available in the arch)
 
 	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
 			Format: <hex>[,nousertaint]

Documentation/admin-guide/mm/damon/usage.rst

@@ -108,19 +108,23 @@ In such cases, users can explicitly set the initial monitoring target regions
 as they want, by writing proper values to the ``init_regions`` file.  Each line
 of the input should represent one region in below form.::
 
-    <target id> <start address> <end address>
+    <target idx> <start address> <end address>
 
-The ``target id`` should already in ``target_ids`` file, and the regions should
-be passed in address order.  For example, below commands will set a couple of
-address ranges, ``1-100`` and ``100-200`` as the initial monitoring target
-region of process 42, and another couple of address ranges, ``20-40`` and
-``50-100`` as that of process 4242.::
+The ``target idx`` should be the index of the target in ``target_ids`` file,
+starting from ``0``, and the regions should be passed in address order.  For
+example, below commands will set a couple of address ranges, ``1-100`` and
+``100-200`` as the initial monitoring target region of pid 42, which is the
+first one (index ``0``) in ``target_ids``, and another couple of address
+ranges, ``20-40`` and ``50-100`` as that of pid 4242, which is the second one
+(index ``1``) in ``target_ids``.::
 
     # cd <debugfs>/damon
-    # echo "42   1       100
-            42   100     200
-            4242 20      40
-            4242 50      100" > init_regions
+    # cat target_ids
+    42 4242
+    # echo "0   1       100
+            0   100     200
+            1   20      40
+            1   50      100" > init_regions
 
 Note that this sets the initial monitoring target regions only.  In case of
 virtual memory monitoring, DAMON will automatically updates the boundary of the

Documentation/admin-guide/mm/zswap.rst

@@ -130,9 +130,25 @@ attribute, e.g.::
 	echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
 
 When zswap same-filled page identification is disabled at runtime, it will stop
-checking for the same-value filled pages during store operation. However, the
-existing pages which are marked as same-value filled pages remain stored
-unchanged in zswap until they are either loaded or invalidated.
+checking for the same-value filled pages during store operation.
+In other words, every page will be then considered non-same-value filled.
+However, the existing pages which are marked as same-value filled pages remain
+stored unchanged in zswap until they are either loaded or invalidated.
+
+In some circumstances it might be advantageous to make use of just the zswap
+ability to efficiently store same-filled pages without enabling the whole
+compressed page storage.
+In this case the handling of non-same-value pages by zswap (enabled by default)
+can be disabled by setting the ``non_same_filled_pages_enabled`` attribute
+to 0, e.g. ``zswap.non_same_filled_pages_enabled=0``.
+It can also be enabled and disabled at runtime using the sysfs
+``non_same_filled_pages_enabled`` attribute, e.g.::
+
+	echo 1 > /sys/module/zswap/parameters/non_same_filled_pages_enabled
+
+Disabling both ``zswap.same_filled_pages_enabled`` and
+``zswap.non_same_filled_pages_enabled`` effectively disables accepting any new
+pages by zswap.
 
 To prevent zswap from shrinking pool when zswap is full and there's a high
 pressure on swap (this will result in flipping pages in and out zswap pool

Documentation/admin-guide/sysctl/kernel.rst

@@ -595,22 +595,35 @@ Documentation/admin-guide/kernel-parameters.rst).
 numa_balancing
 ==============
 
-Enables/disables automatic page fault based NUMA memory
-balancing. Memory is moved automatically to nodes
-that access it often.
+Enables/disables and configures automatic page fault based NUMA memory
+balancing.  Memory is moved automatically to nodes that access it often. 
+The value to set can be the result of ORing the following:
 
-Enables/disables automatic NUMA memory balancing. On NUMA machines, there
-is a performance penalty if remote memory is accessed by a CPU. When this
-feature is enabled the kernel samples what task thread is accessing memory
-by periodically unmapping pages and later trapping a page fault. At the
-time of the page fault, it is determined if the data being accessed should
-be migrated to a local memory node.
+= =================================
+0 NUMA_BALANCING_DISABLED
+1 NUMA_BALANCING_NORMAL
+2 NUMA_BALANCING_MEMORY_TIERING
+= =================================
+
+Or NUMA_BALANCING_NORMAL to optimize page placement among different
+NUMA nodes to reduce remote accessing.  On NUMA machines, there is a
+performance penalty if remote memory is accessed by a CPU. When this
+feature is enabled the kernel samples what task thread is accessing
+memory by periodically unmapping pages and later trapping a page
+fault. At the time of the page fault, it is determined if the data
+being accessed should be migrated to a local memory node.
 
 The unmapping of pages and trapping faults incur additional overhead that
 ideally is offset by improved memory locality but there is no universal
 guarantee. If the target workload is already bound to NUMA nodes then this
 feature should be disabled.
 
+Or NUMA_BALANCING_MEMORY_TIERING to optimize page placement among
+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.
+
+
 oops_all_cpu_backtrace
 ======================
 
@@ -751,6 +764,8 @@ bit 1  print system memory info
 bit 2  print timer info
 bit 3  print locks info if ``CONFIG_LOCKDEP`` is on
 bit 4  print ftrace buffer
+bit 5  print all printk messages in buffer
+bit 6  print all CPUs backtrace (if available in the arch)
 =====  ============================================
 
 So for example to print tasks and memory info on panic, user can::

Documentation/dev-tools/kasan.rst

@@ -30,7 +30,7 @@ Software tag-based KASAN mode is only supported in Clang.
 
 The hardware KASAN mode (#3) relies on hardware to perform the checks but
 still requires a compiler version that supports memory tagging instructions.
-This mode is supported in GCC 10+ and Clang 11+.
+This mode is supported in GCC 10+ and Clang 12+.
 
 Both software KASAN modes work with SLUB and SLAB memory allocators,
 while the hardware tag-based KASAN currently only supports SLUB.
@@ -206,6 +206,9 @@ additional boot parameters that allow disabling KASAN or controlling features:
   Asymmetric mode: a bad access is detected synchronously on reads and
   asynchronously on writes.
 
+- ``kasan.vmalloc=off`` or ``=on`` disables or enables tagging of vmalloc
+  allocations (default: ``on``).
+
 - ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack
   traces collection (default: ``on``).
 
@@ -279,8 +282,8 @@ Software tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through
 pointers with the 0xFF pointer tag are not checked). The value 0xFE is currently
 reserved to tag freed memory regions.
 
-Software tag-based KASAN currently only supports tagging of slab and page_alloc
-memory.
+Software tag-based KASAN currently only supports tagging of slab, page_alloc,
+and vmalloc memory.
 
 Hardware tag-based KASAN
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -303,8 +306,8 @@ Hardware tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through
 pointers with the 0xFF pointer tag are not checked). The value 0xFE is currently
 reserved to tag freed memory regions.
 
-Hardware tag-based KASAN currently only supports tagging of slab and page_alloc
-memory.
+Hardware tag-based KASAN currently only supports tagging of slab, page_alloc,
+and VM_ALLOC-based vmalloc memory.
 
 If the hardware does not support MTE (pre ARMv8.5), hardware tag-based KASAN
 will not be enabled. In this case, all KASAN boot parameters are ignored.
@@ -319,6 +322,8 @@ checking gets disabled.
 Shadow memory
 -------------
 
+The contents of this section are only applicable to software KASAN modes.
+
 The kernel maps memory in several different parts of the address space.
 The range of kernel virtual addresses is large: there is not enough real
 memory to support a real shadow region for every address that could be
@@ -349,7 +354,7 @@ CONFIG_KASAN_VMALLOC
 
 With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the
 cost of greater memory usage. Currently, this is supported on x86,
-riscv, s390, and powerpc.
+arm64, riscv, s390, and powerpc.
 
 This works by hooking into vmalloc and vmap and dynamically
 allocating real shadow memory to back the mappings.

Documentation/vm/balance.rst

@@ -6,7 +6,7 @@ Memory Balancing
 
 Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
 
-Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
+Memory balancing is needed for !__GFP_HIGH and !__GFP_KSWAPD_RECLAIM as
 well as for non __GFP_IO allocations.
 
 The first reason why a caller may avoid reclaim is that the caller can not

Documentation/vm/page_owner.rst

@@ -89,22 +89,41 @@ Usage
 
 	Page allocated via order XXX, ...
 	PFN XXX ...
-	 // Detailed stack
+	// Detailed stack
 
 	Page allocated via order XXX, ...
 	PFN XXX ...
-	 // Detailed stack
+	// Detailed stack
 
    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
-   and pages of buf, and finally sorts them according to the times.
+   and pages of buf, and finally sorts them according to the parameter(s).
 
    See the result about who allocated each page
    in the ``sorted_page_owner.txt``. General output:
 
 	XXX times, XXX pages:
 	Page allocated via order XXX, ...
-	 // Detailed stack
+	// Detailed stack
 
    By default, ``page_owner_sort`` is sorted according to the times of buf.
-   If you want to sort by the pages nums of buf, use the ``-m`` parameter.
+   If you want to sort by the page nums of buf, use the ``-m`` parameter.
+   The detailed parameters are:
+
+   fundamental function:
+
+	Sort:
+		-a		Sort by memory allocation time.
+		-m		Sort by total memory.
+		-p		Sort by pid.
+		-r		Sort by memory release time.
+		-s		Sort by stack trace.
+		-t		Sort by times (default).
+
+   additional function:
+
+	Cull:
+		-c		Cull by comparing stacktrace instead of total block.
+
+	Filter:
+		-f		Filter out the information of blocks whose memory has not been released.

arch/arm/Kconfig

@@ -37,6 +37,7 @@ config ARM
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
+	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
@@ -1514,9 +1515,6 @@ config HW_PERF_EVENTS
 	def_bool y
 	depends on ARM_PMU
 
-config ARCH_WANT_GENERAL_HUGETLB
-	def_bool y
-
 config ARM_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES

arch/arm64/Kconfig

@@ -24,6 +24,7 @@ config ARM64
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
@@ -206,7 +207,7 @@ config ARM64
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
-	select KASAN_VMALLOC if KASAN_GENERIC
+	select KASAN_VMALLOC if KASAN
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
@@ -1253,9 +1254,6 @@ config HW_PERF_EVENTS
 	def_bool y
 	depends on ARM_PMU
 
-config ARCH_HAS_FILTER_PGPROT
-	def_bool y
-
 # Supported by clang >= 7.0
 config CC_HAVE_SHADOW_CALL_STACK
 	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)

arch/arm64/include/asm/vmalloc.h

@@ -25,4 +25,10 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot)
 
 #endif
 
+#define arch_vmap_pgprot_tagged arch_vmap_pgprot_tagged
+static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot)
+{
+	return pgprot_tagged(prot);
+}
+
 #endif /* _ASM_ARM64_VMALLOC_H */

arch/arm64/include/asm/vmap_stack.h

@@ -17,10 +17,13 @@
  */
 static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
 {
+	void *p;
+
 	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
 
-	return __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
+	p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
 			__builtin_return_address(0));
+	return kasan_reset_tag(p);
 }
 
 #endif /* __ASM_VMAP_STACK_H */

arch/arm64/kernel/module.c

@@ -58,12 +58,13 @@ void *module_alloc(unsigned long size)
 				PAGE_KERNEL, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 
-	if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) {
+	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
 		vfree(p);
 		return NULL;
 	}
 
-	return p;
+	/* Memory is intended to be executable, reset the pointer tag. */
+	return kasan_reset_tag(p);
 }
 
 enum aarch64_reloc_op {

arch/arm64/kernel/setup.c

@@ -406,9 +406,6 @@ static int __init topology_init(void)
 {
 	int i;
 
-	for_each_online_node(i)
-		register_one_node(i);
-
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = cpu_can_disable(i);

arch/arm64/mm/hugetlbpage.c

@@ -347,6 +347,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 {
 	size_t pagesize = 1UL << shift;
 
+	entry = pte_mkhuge(entry);
 	if (pagesize == CONT_PTE_SIZE) {
 		entry = pte_mkcont(entry);
 	} else if (pagesize == CONT_PMD_SIZE) {