Merge branch 'akpm-current/current'

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
@@ -3739,6 +3739,7 @@
 			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

@@ -795,6 +795,8 @@ 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/kernel/setup.c

@@ -973,7 +973,6 @@ static int __init init_machine_late(void)
 }
 late_initcall(init_machine_late);
 
-#ifdef CONFIG_KEXEC
 /*
  * The crash region must be aligned to 128MB to avoid
  * zImage relocating below the reserved region.
@@ -1001,6 +1000,9 @@ static void __init reserve_crashkernel(void)
 	unsigned long long total_mem;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
 	total_mem = get_total_mem();
 	ret = parse_crashkernel(boot_command_line, total_mem,
 				&crash_size, &crash_base);
@@ -1056,9 +1058,6 @@ static void __init reserve_crashkernel(void)
 		insert_resource(&iomem_resource, &crashk_boot_res);
 	}
 }
-#else
-static inline void reserve_crashkernel(void) {}
-#endif /* CONFIG_KEXEC */
 
 void __init hyp_mode_check(void)
 {

arch/arm64/Kconfig

@@ -23,6 +23,7 @@ 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
@@ -205,7 +206,7 @@ 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
@@ -1225,9 +1226,6 @@ 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/mm/init.c

@@ -64,7 +64,6 @@ EXPORT_SYMBOL(memstart_addr);
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
-#ifdef CONFIG_KEXEC_CORE
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -78,6 +77,9 @@ static void __init reserve_crashkernel(void)
 	unsigned long long crash_max = arm64_dma_phys_limit;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
 	/* no crashkernel= or invalid value specified */
@@ -110,11 +112,6 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
-#else
-static void __init reserve_crashkernel(void)
-{
-}
-#endif /* CONFIG_KEXEC_CORE */
 
 /*
  * Return the maximum physical address for a zone accessible by the given bits

arch/arm64/mm/pageattr.c

@@ -85,7 +85,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 	 */
 	area = find_vm_area((void *)addr);
 	if (!area ||
-	    end > (unsigned long)area->addr + area->size ||
+	    end > (unsigned long)kasan_reset_tag(area->addr) + area->size ||
 	    !(area->flags & VM_ALLOC))
 		return -EINVAL;
 

arch/arm64/net/bpf_jit_comp.c

@@ -1150,7 +1150,8 @@ u64 bpf_jit_alloc_exec_limit(void)
 
 void *bpf_jit_alloc_exec(unsigned long size)
 {
-	return vmalloc(size);
+	/* Memory is intended to be executable, reset the pointer tag. */
+	return kasan_reset_tag(vmalloc(size));
 }
 
 void bpf_jit_free_exec(void *addr)

arch/ia64/Kconfig

@@ -318,7 +318,7 @@ config ARCH_PROC_KCORE_TEXT
 	depends on PROC_KCORE
 
 config IA64_MCA_RECOVERY
-	tristate "MCA recovery from errors other than TLB."
+	bool "MCA recovery from errors other than TLB."
 
 config IA64_PALINFO
 	tristate "/proc/pal support"

arch/powerpc/kernel/fadump.c

@@ -112,6 +112,12 @@ static int __init fadump_cma_init(void)
 		return 1;
 	}
 
+	/*
+	 *  If CMA activation fails, keep the pages reserved, instead of
+	 *  exposing them to buddy allocator. Same as 'fadump=nocma' case.
+	 */
+	cma_reserve_pages_on_error(fadump_cma);
+
 	/*
 	 * So we now have successfully initialized cma area for fadump.
 	 */