Merge d5660df4a5 ("Merge branch 'akpm' (patches from Andrew)") into android-mainline

steps on the way to 5.10-rc1

Change-Id: Iddc84c25b6a9d71fa8542b927d6f69c364131c3d
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

.clang-format

@@ -203,11 +203,13 @@ ForEachMacros:
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
   - 'for_each_member'
-  - 'for_each_memblock'
+  - 'for_each_mem_region'
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
+  - '__for_each_mem_range'
   - 'for_each_mem_range'
+  - '__for_each_mem_range_rev'
   - 'for_each_mem_range_rev'
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
@@ -271,6 +273,7 @@ ForEachMacros:
   - 'for_each_registered_fb'
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
+  - 'for_each_reserved_mem_range'
   - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'

Documentation/ABI/obsolete/sysfs-selinux-checkreqprot

@@ -15,7 +15,7 @@ Description:
 	actual protection), and Android and Linux distributions have been
 	explicitly writing a "0" to /sys/fs/selinux/checkreqprot during
 	initialization for some time.  Support for setting checkreqprot to 1
-	will be	removed in a future kernel release, at which point the kernel
+	will be	removed no sooner than June 2021, at which point the kernel
 	will always cease using checkreqprot internally and will always
 	check the actual protections being applied upon mmap/mprotect calls.
 	The checkreqprot selinuxfs node will remain for backward compatibility

Documentation/admin-guide/cgroup-v2.rst

@@ -1259,6 +1259,10 @@ PAGE_SIZE multiple when read back.
 	can show up in the middle. Don't rely on items remaining in a
 	fixed position; use the keys to look up specific values!
 
+	If the entry has no per-node counter(or not show in the
+	mempry.numa_stat). We use 'npn'(non-per-node) as the tag
+	to indicate that it will not show in the mempry.numa_stat.
+
 	  anon
 		Amount of memory used in anonymous mappings such as
 		brk(), sbrk(), and mmap(MAP_ANONYMOUS)
@@ -1270,15 +1274,11 @@ PAGE_SIZE multiple when read back.
 	  kernel_stack
 		Amount of memory allocated to kernel stacks.
 
-	  slab
+	  percpu(npn)
-		Amount of memory used for storing in-kernel data
-		structures.
-
-	  percpu
 		Amount of memory used for storing per-cpu kernel
 		data structures.
 
-	  sock
+	  sock(npn)
 		Amount of memory used in network transmission buffers
 
 	  shmem
@@ -1318,11 +1318,9 @@ PAGE_SIZE multiple when read back.
 		Part of "slab" that cannot be reclaimed on memory
 		pressure.
 
-	  pgfault
+	  slab(npn)
-		Total number of page faults incurred
+		Amount of memory used for storing in-kernel data
-
+		structures.
-	  pgmajfault
-		Number of major page faults incurred
 
 	  workingset_refault_anon
 		Number of refaults of previously evicted anonymous pages.
@@ -1348,37 +1346,68 @@ PAGE_SIZE multiple when read back.
 	  workingset_nodereclaim
 		Number of times a shadow node has been reclaimed
 
-	  pgrefill
+	  pgfault(npn)
+		Total number of page faults incurred
+
+	  pgmajfault(npn)
+		Number of major page faults incurred
+
+	  pgrefill(npn)
 		Amount of scanned pages (in an active LRU list)
 
-	  pgscan
+	  pgscan(npn)
 		Amount of scanned pages (in an inactive LRU list)
 
-	  pgsteal
+	  pgsteal(npn)
 		Amount of reclaimed pages
 
-	  pgactivate
+	  pgactivate(npn)
 		Amount of pages moved to the active LRU list
 
-	  pgdeactivate
+	  pgdeactivate(npn)
 		Amount of pages moved to the inactive LRU list
 
-	  pglazyfree
+	  pglazyfree(npn)
 		Amount of pages postponed to be freed under memory pressure
 
-	  pglazyfreed
+	  pglazyfreed(npn)
 		Amount of reclaimed lazyfree pages
 
-	  thp_fault_alloc
+	  thp_fault_alloc(npn)
 		Number of transparent hugepages which were allocated to satisfy
 		a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE
                 is not set.
 
-	  thp_collapse_alloc
+	  thp_collapse_alloc(npn)
 		Number of transparent hugepages which were allocated to allow
 		collapsing an existing range of pages. This counter is not
 		present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
 
+  memory.numa_stat
+	A read-only nested-keyed file which exists on non-root cgroups.
+
+	This breaks down the cgroup's memory footprint into different
+	types of memory, type-specific details, and other information
+	per node on the state of the memory management system.
+
+	This is useful for providing visibility into the NUMA locality
+	information within an memcg since the pages are allowed to be
+	allocated from any physical node. One of the use case is evaluating
+	application performance by combining this information with the
+	application's CPU allocation.
+
+	All memory amounts are in bytes.
+
+	The output format of memory.numa_stat is::
+
+	  type N0=<bytes in node 0> N1=<bytes in node 1> ...
+
+	The entries are ordered to be human readable, and new entries
+	can show up in the middle. Don't rely on items remaining in a
+	fixed position; use the keys to look up specific values!
+
+	The entries can refer to the memory.stat.
+
   memory.swap.current
 	A read-only single value file which exists on non-root
 	cgroups.

Documentation/admin-guide/kdump/gdbmacros.txt

@@ -170,57 +170,82 @@ document trapinfo
 	address the kernel panicked.
 end
 
-define dump_log_idx
+define dump_record
-	set $idx = $arg0
+	set var $desc = $arg0
-	if ($argc > 1)
+	set var $info = $arg1
-		set $prev_flags = $arg1
+	if ($argc > 2)
+		set var $prev_flags = $arg2
 	else
-		set $prev_flags = 0
+		set var $prev_flags = 0
-	end
-	set $msg = ((struct printk_log *) (log_buf + $idx))
-	set $prefix = 1
-	set $newline = 1
-	set $log = log_buf + $idx + sizeof(*$msg)
-
-	# prev & LOG_CONT && !(msg->flags & LOG_PREIX)
-	if (($prev_flags & 8) && !($msg->flags & 4))
-		set $prefix = 0
 	end
 
-	# msg->flags & LOG_CONT
+	set var $prefix = 1
-	if ($msg->flags & 8)
+	set var $newline = 1
+
+	set var $begin = $desc->text_blk_lpos.begin % (1U << prb->text_data_ring.size_bits)
+	set var $next = $desc->text_blk_lpos.next % (1U << prb->text_data_ring.size_bits)
+
+	# handle data-less record
+	if ($begin & 1)
+		set var $text_len = 0
+		set var $log = ""
+	else
+		# handle wrapping data block
+		if ($begin > $next)
+			set var $begin = 0
+		end
+
+		# skip over descriptor id
+		set var $begin = $begin + sizeof(long)
+
+		# handle truncated message
+		if ($next - $begin < $info->text_len)
+			set var $text_len = $next - $begin
+		else
+			set var $text_len = $info->text_len
+		end
+
+		set var $log = &prb->text_data_ring.data[$begin]
+	end
+
+	# prev & LOG_CONT && !(info->flags & LOG_PREIX)
+	if (($prev_flags & 8) && !($info->flags & 4))
+		set var $prefix = 0
+	end
+
+	# info->flags & LOG_CONT
+	if ($info->flags & 8)
 		# (prev & LOG_CONT && !(prev & LOG_NEWLINE))
 		if (($prev_flags & 8) && !($prev_flags & 2))
-			set $prefix = 0
+			set var $prefix = 0
 		end
-		# (!(msg->flags & LOG_NEWLINE))
+		# (!(info->flags & LOG_NEWLINE))
-		if (!($msg->flags & 2))
+		if (!($info->flags & 2))
-			set $newline = 0
+			set var $newline = 0
 		end
 	end
 
 	if ($prefix)
-		printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+		printf "[%5lu.%06lu] ", $info->ts_nsec / 1000000000, $info->ts_nsec % 1000000000
 	end
-	if ($msg->text_len != 0)
+	if ($text_len)
-		eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+		eval "printf \"%%%d.%ds\", $log", $text_len, $text_len
 	end
 	if ($newline)
 		printf "\n"
 	end
-	if ($msg->dict_len > 0)
+
-		set $dict = $log + $msg->text_len
+	# handle dictionary data
-		set $idx = 0
+
-		set $line = 1
+	set var $dict = &$info->dev_info.subsystem[0]
-		while ($idx < $msg->dict_len)
+	set var $dict_len = sizeof($info->dev_info.subsystem)
-			if ($line)
+	if ($dict[0] != '\0')
-				printf " "
+		printf " SUBSYSTEM="
-				set $line = 0
+		set var $idx = 0
-			end
+		while ($idx < $dict_len)
-			set $c = $dict[$idx]
+			set var $c = $dict[$idx]
 			if ($c == '\0')
-				printf "\n"
+				loop_break
-				set $line = 1
 			else
 				if ($c < ' ' || $c >= 127 || $c == '\\')
 					printf "\\x%02x", $c
@@ -228,33 +253,67 @@ define dump_log_idx
 					printf "%c", $c
 				end
 			end
-			set $idx = $idx + 1
+			set var $idx = $idx + 1
+		end
+		printf "\n"
+	end
+
+	set var $dict = &$info->dev_info.device[0]
+	set var $dict_len = sizeof($info->dev_info.device)
+	if ($dict[0] != '\0')
+		printf " DEVICE="
+		set var $idx = 0
+		while ($idx < $dict_len)
+			set var $c = $dict[$idx]
+			if ($c == '\0')
+				loop_break
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set var $idx = $idx + 1
 		end
 		printf "\n"
 	end
 end
-document dump_log_idx
+document dump_record
-	Dump a single log given its index in the log buffer.  The first
+	Dump a single record. The first parameter is the descriptor,
-	parameter is the index into log_buf, the second is optional and
+	the second parameter is the info, the third parameter is
-	specified the previous log buffer's flags, used for properly
+	optional and specifies the previous record's flags, used for
-	formatting continued lines.
+	properly formatting continued lines.
 end
 
 define dmesg
-	set $i = log_first_idx
+	# definitions from kernel/printk/printk_ringbuffer.h
-	set $end_idx = log_first_idx
+	set var $desc_committed = 1
-	set $prev_flags = 0
+	set var $desc_finalized = 2
+	set var $desc_sv_bits = sizeof(long) * 8
+	set var $desc_flags_shift = $desc_sv_bits - 2
+	set var $desc_flags_mask = 3 << $desc_flags_shift
+	set var $id_mask = ~$desc_flags_mask
+
+	set var $desc_count = 1U << prb->desc_ring.count_bits
+	set var $prev_flags = 0
+
+	set var $id = prb->desc_ring.tail_id.counter
+	set var $end_id = prb->desc_ring.head_id.counter
 
 	while (1)
-		set $msg = ((struct printk_log *) (log_buf + $i))
+		set var $desc = &prb->desc_ring.descs[$id % $desc_count]
-		if ($msg->len == 0)
+		set var $info = &prb->desc_ring.infos[$id % $desc_count]
-			set $i = 0
+
-		else
+		# skip non-committed record
-			dump_log_idx $i $prev_flags
+		set var $state = 3 & ($desc->state_var.counter >> $desc_flags_shift)
-			set $i = $i + $msg->len
+		if ($state == $desc_committed || $state == $desc_finalized)
-			set $prev_flags = $msg->flags
+			dump_record $desc $info $prev_flags
+			set var $prev_flags = $info->flags
 		end
-		if ($i == $end_idx)
+
+		set var $id = ($id + 1) & $id_mask
+		if ($id == $end_id)
 			loop_break
 		end
 	end

Documentation/admin-guide/kdump/vmcoreinfo.rst

@@ -189,50 +189,123 @@ from this.
 Free areas descriptor. User-space tools use this value to iterate the
 free_area ranges. MAX_ORDER is used by the zone buddy allocator.
 
-log_first_idx
+prb
--------------
+---
 
-Index of the first record stored in the buffer log_buf. Used by
+A pointer to the printk ringbuffer (struct printk_ringbuffer). This
-user-space tools to read the strings in the log_buf.
+may be pointing to the static boot ringbuffer or the dynamically
+allocated ringbuffer, depending on when the the core dump occurred.
+Used by user-space tools to read the active kernel log buffer.
 
-log_buf
+printk_rb_static
--------
+----------------
 
-Console output is written to the ring buffer log_buf at index
+A pointer to the static boot printk ringbuffer. If @prb has a
-log_first_idx. Used to get the kernel log.
+different value, this is useful for viewing the initial boot messages,
+which may have been overwritten in the dynamically allocated
+ringbuffer.
 
-log_buf_len
+clear_seq
------------
-
-log_buf's length.
-
-clear_idx
 ---------
 
-The index that the next printk() record to read after the last clear
+The sequence number of the printk() record after the last clear
-command. It indicates the first record after the last SYSLOG_ACTION
+command. It indicates the first record after the last
-_CLEAR, like issued by 'dmesg -c'. Used by user-space tools to dump
+SYSLOG_ACTION_CLEAR, like issued by 'dmesg -c'. Used by user-space
-the dmesg log.
+tools to dump a subset of the dmesg log.
 
-log_next_idx
+printk_ringbuffer
-------------
+-----------------
 
-The index of the next record to store in the buffer log_buf. Used to
+The size of a printk_ringbuffer structure. This structure contains all
-compute the index of the current buffer position.
+information required for accessing the various components of the
+kernel log buffer.
 
-printk_log
+(printk_ringbuffer, desc_ring|text_data_ring|dict_data_ring|fail)
-----------
+-----------------------------------------------------------------
 
-The size of a structure printk_log. Used to compute the size of
+Offsets for the various components of the printk ringbuffer. Used by
-messages, and extract dmesg log. It encapsulates header information for
+user-space tools to view the kernel log buffer without requiring the
-log_buf, such as timestamp, syslog level, etc.
+declaration of the structure.
 
-(printk_log, ts_nsec|len|text_len|dict_len)
+prb_desc_ring
--------------------------------------------
+-------------
 
-It represents field offsets in struct printk_log. User space tools
+The size of the prb_desc_ring structure. This structure contains
-parse it and check whether the values of printk_log's members have been
+information about the set of record descriptors.
-changed.
+
+(prb_desc_ring, count_bits|descs|head_id|tail_id)
+-------------------------------------------------
+
+Offsets for the fields describing the set of record descriptors. Used
+by user-space tools to be able to traverse the descriptors without
+requiring the declaration of the structure.
+
+prb_desc
+--------
+
+The size of the prb_desc structure. This structure contains
+information about a single record descriptor.
+
+(prb_desc, info|state_var|text_blk_lpos|dict_blk_lpos)
+------------------------------------------------------
+
+Offsets for the fields describing a record descriptors. Used by
+user-space tools to be able to read descriptors without requiring
+the declaration of the structure.
+
+prb_data_blk_lpos
+-----------------
+
+The size of the prb_data_blk_lpos structure. This structure contains
+information about where the text or dictionary data (data block) is
+located within the respective data ring.
+
+(prb_data_blk_lpos, begin|next)
+-------------------------------
+
+Offsets for the fields describing the location of a data block. Used
+by user-space tools to be able to locate data blocks without
+requiring the declaration of the structure.
+
+printk_info
+-----------
+
+The size of the printk_info structure. This structure contains all
+the meta-data for a record.
+
+(printk_info, seq|ts_nsec|text_len|dict_len|caller_id)
+------------------------------------------------------
+
+Offsets for the fields providing the meta-data for a record. Used by
+user-space tools to be able to read the information without requiring
+the declaration of the structure.
+
+prb_data_ring
+-------------
+
+The size of the prb_data_ring structure. This structure contains
+information about a set of data blocks.
+
+(prb_data_ring, size_bits|data|head_lpos|tail_lpos)
+---------------------------------------------------
+
+Offsets for the fields describing a set of data blocks. Used by
+user-space tools to be able to access the data blocks without
+requiring the declaration of the structure.
+
+atomic_long_t
+-------------
+
+The size of the atomic_long_t structure. Used by user-space tools to
+be able to copy the full structure, regardless of its
+architecture-specific implementation.
+
+(atomic_long_t, counter)
+------------------------
+
+Offset for the long value of an atomic_long_t variable. Used by
+user-space tools to access the long value without requiring the
+architecture-specific declaration.
 
 (free_area.free_list, MIGRATE_TYPES)
 ------------------------------------

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -131,7 +131,7 @@ hugepages
 	parameter is preceded by an invalid hugepagesz parameter, it will
 	be ignored.
 default_hugepagesz
-	pecify the default huge page size.  This parameter can
+	Specify the default huge page size.  This parameter can
 	only be specified once on the command line.  default_hugepagesz can
 	optionally be followed by the hugepages parameter to preallocate a
 	specific number of huge pages of default size.  The number of default

Documentation/dev-tools/kasan.rst

@@ -13,10 +13,10 @@ KASAN uses compile-time instrumentation to insert validity checks before every
 memory access, and therefore requires a compiler version that supports that.
 
 Generic KASAN is supported in both GCC and Clang. With GCC it requires version
-8.3.0 or later. With Clang it requires version 7.0.0 or later, but detection of
+8.3.0 or later. Any supported Clang version is compatible, but detection of
 out-of-bounds accesses for global variables is only supported since Clang 11.
 
-Tag-based KASAN is only supported in Clang and requires version 7.0.0 or later.
+Tag-based KASAN is only supported in Clang.
 
 Currently generic KASAN is supported for the x86_64, arm64, xtensa, s390 and
 riscv architectures, and tag-based KASAN is supported only for arm64.
@@ -281,3 +281,73 @@ unmapped. This will require changes in arch-specific code.
 
 This allows ``VMAP_STACK`` support on x86, and can simplify support of
 architectures that do not have a fixed module region.
+
+CONFIG_KASAN_KUNIT_TEST & CONFIG_TEST_KASAN_MODULE
+--------------------------------------------------
+
+``CONFIG_KASAN_KUNIT_TEST`` utilizes the KUnit Test Framework for testing.
+This means each test focuses on a small unit of functionality and
+there are a few ways these tests can be run.
+
+Each test will print the KASAN report if an error is detected and then
+print the number of the test and the status of the test:
+
+pass::
+
+        ok 28 - kmalloc_double_kzfree
+or, if kmalloc failed::
+
+        # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
+        Expected ptr is not null, but is
+        not ok 4 - kmalloc_large_oob_right
+or, if a KASAN report was expected, but not found::
+
+        # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
+        Expected kasan_data->report_expected == kasan_data->report_found, but
+        kasan_data->report_expected == 1
+        kasan_data->report_found == 0
+        not ok 28 - kmalloc_double_kzfree
+
+All test statuses are tracked as they run and an overall status will
+be printed at the end::
+
+        ok 1 - kasan
+
+or::
+
+        not ok 1 - kasan
+
+(1) Loadable Module
+~~~~~~~~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` enabled, ``CONFIG_KASAN_KUNIT_TEST`` can be built as
+a loadable module and run on any architecture that supports KASAN
+using something like insmod or modprobe. The module is called ``test_kasan``.
+
+(2) Built-In
+~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` built-in, ``CONFIG_KASAN_KUNIT_TEST`` can be built-in
+on any architecure that supports KASAN. These and any other KUnit
+tests enabled will run and print the results at boot as a late-init
+call.
+
+(3) Using kunit_tool
+~~~~~~~~~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` and ``CONFIG_KASAN_KUNIT_TEST`` built-in, we can also
+use kunit_tool to see the results of these along with other KUnit
+tests in a more readable way. This will not print the KASAN reports
+of tests that passed. Use `KUnit documentation <https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html>`_ for more up-to-date
+information on kunit_tool.
+
+.. _KUnit: https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html
+
+``CONFIG_TEST_KASAN_MODULE`` is a set of KASAN tests that could not be
+converted to KUnit. These tests can be run only as a module with
+``CONFIG_TEST_KASAN_MODULE`` built as a loadable module and
+``CONFIG_KASAN`` built-in. The type of error expected and the
+function being run is printed before the expression expected to give
+an error. Then the error is printed, if found, and that test
+should be interpretted to pass only if the error was the one expected
+by the test.

Documentation/dev-tools/kmemleak.rst

@@ -229,7 +229,7 @@ Testing with kmemleak-test
 
 To check if you have all set up to use kmemleak, you can use the kmemleak-test
 module, a module that deliberately leaks memory. Set CONFIG_DEBUG_KMEMLEAK_TEST
-as module (it can't be used as bult-in) and boot the kernel with kmemleak
+as module (it can't be used as built-in) and boot the kernel with kmemleak
 enabled. Load the module and perform a scan with::
 
         # modprobe kmemleak-test

Documentation/kbuild/makefiles.rst

@@ -21,6 +21,7 @@ This document describes the Linux kernel Makefiles.
 	   --- 3.10 Special Rules
 	   --- 3.11 $(CC) support functions
 	   --- 3.12 $(LD) support functions
+	   --- 3.13 Script Invocation
 
 	=== 4 Host Program support
 	   --- 4.1 Simple Host Program
@@ -605,6 +606,25 @@ more details, with real examples.
 		#Makefile
 		LDFLAGS_vmlinux += $(call ld-option, -X)
 
+3.13 Script invocation
+----------------------
+
+	Make rules may invoke scripts to build the kernel. The rules shall
+	always provide the appropriate interpreter to execute the script. They
+	shall not rely on the execute bits being set, and shall not invoke the
+	script directly. For the convenience of manual script invocation, such
+	as invoking ./scripts/checkpatch.pl, it is recommended to set execute
+	bits on the scripts nonetheless.
+
+	Kbuild provides variables $(CONFIG_SHELL), $(AWK), $(PERL),
+	$(PYTHON) and $(PYTHON3) to refer to interpreters for the respective
+	scripts.
+
+	Example::
+
+		#Makefile
+		cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \
+			     $(KERNELRELEASE)
 
 4 Host Program support
 ======================

Documentation/vm/active_mm.rst

@@ -64,7 +64,7 @@ Active MM
  actually get cases where you have a address space that is _only_ used by
  lazy users. That is often a short-lived state, because once that thread
  gets scheduled away in favour of a real thread, the "zombie" mm gets
- released because "mm_users" becomes zero.
+ released because "mm_count" becomes zero.
 
  Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
  more. "init_mm" should be considered just a "lazy context when no other

Documentation/x86/x86_64/boot-options.rst

@@ -173,6 +173,10 @@ NUMA
   numa=noacpi
     Don't parse the SRAT table for NUMA setup
 
+  numa=nohmat
+    Don't parse the HMAT table for NUMA setup, or soft-reserved memory
+    partitioning.
+
   numa=fake=<size>[MG]
     If given as a memory unit, fills all system RAM with nodes of
     size interleaved over physical nodes.

MAINTAINERS

@@ -9734,8 +9734,8 @@ M:	Catalin Marinas <catalin.marinas@arm.com>
 S:	Maintained
 F:	Documentation/dev-tools/kmemleak.rst
 F:	include/linux/kmemleak.h
-F:	mm/kmemleak-test.c
 F:	mm/kmemleak.c
+F:	samples/kmemleak/kmemleak-test.c
 
 KMOD KERNEL MODULE LOADER - USERMODE HELPER
 M:	Luis Chamberlain <mcgrof@kernel.org>
@@ -13983,6 +13983,7 @@ PRINTK
 M:	Petr Mladek <pmladek@suse.com>
 M:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
 R:	Steven Rostedt <rostedt@goodmis.org>
+R:	John Ogness <john.ogness@linutronix.de>
 S:	Maintained
 F:	include/linux/printk.h
 F:	kernel/printk/
@@ -15633,6 +15634,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
 F:	Documentation/ABI/obsolete/sysfs-selinux-checkreqprot
 F:	Documentation/ABI/obsolete/sysfs-selinux-disable
 F:	Documentation/admin-guide/LSM/SELinux.rst
+F:	include/trace/events/avc.h
 F:	include/uapi/linux/selinux_netlink.h
 F:	scripts/selinux/
 F:	security/selinux/

Makefile

@@ -926,15 +926,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
-# clang sets -fmerge-all-constants by default as optimization, but this
-# is non-conforming behavior for C and in fact breaks the kernel, so we
-# need to disable it here generally.
-KBUILD_CFLAGS	+= $(call cc-option,-fno-merge-all-constants)
-
-# for gcc -fno-merge-all-constants disables everything, but it is fine
-# to have actual conforming behavior enabled.
-KBUILD_CFLAGS	+= $(call cc-option,-fmerge-constants)
-
 # Make sure -fstack-check isn't enabled (like gentoo apparently did)
 KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
 

arch/Kconfig

@@ -450,10 +450,23 @@ config ARCH_WANT_OLD_COMPAT_IPC
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
-config HAVE_ARCH_SECCOMP_FILTER
+config HAVE_ARCH_SECCOMP
 	bool
+	help
+	  An arch should select this symbol to support seccomp mode 1 (the fixed
+	  syscall policy), and must provide an overrides for __NR_seccomp_sigreturn,
+	  and compat syscalls if the asm-generic/seccomp.h defaults need adjustment:
+	  - __NR_seccomp_read_32
+	  - __NR_seccomp_write_32
+	  - __NR_seccomp_exit_32
+	  - __NR_seccomp_sigreturn_32
+
+config HAVE_ARCH_SECCOMP_FILTER
+	bool
+	select HAVE_ARCH_SECCOMP
 	help
 	  An arch should select this symbol if it provides all of these things:
+	  - all the requirements for HAVE_ARCH_SECCOMP
 	  - syscall_get_arch()
 	  - syscall_get_arguments()
 	  - syscall_rollback()
@@ -464,6 +477,23 @@ config HAVE_ARCH_SECCOMP_FILTER
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
 
+config SECCOMP
+	prompt "Enable seccomp to safely execute untrusted bytecode"
+	def_bool y
+	depends on HAVE_ARCH_SECCOMP
+	help
+	  This kernel feature is useful for number crunching applications
+	  that may need to handle untrusted bytecode during their
+	  execution. By using pipes or other transports made available
+	  to the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in their
+	  own address space using seccomp. Once seccomp is enabled via
+	  prctl(PR_SET_SECCOMP) or the seccomp() syscall, it cannot be
+	  disabled and the task is only allowed to execute a few safe
+	  syscalls defined by each seccomp mode.
+
+	  If unsure, say Y.
+
 config SECCOMP_FILTER
 	def_bool y
 	depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET

arch/arm/Kconfig

@@ -68,6 +68,7 @@ config ARM
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
@@ -84,7 +85,7 @@ config ARM
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && (CC_IS_GCC || CLANG_VERSION >= 100000)
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_IDE if PCI || ISA || PCMCIA
@@ -1618,20 +1619,6 @@ config UACCESS_WITH_MEMCPY
 	  However, if the CPU data cache is using a write-allocate mode,
 	  this option is unlikely to provide any performance gain.
 
-config SECCOMP
-	bool
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config PARAVIRT
 	bool "Enable paravirtualization code"
 	help

arch/arm/include/asm/tlb.h

@@ -59,6 +59,7 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
 	struct page *page = virt_to_page(pmdp);
 
+	pgtable_pmd_page_dtor(page);
 	tlb_remove_table(tlb, page);
 #endif
 }

arch/arm/kernel/setup.c

@@ -843,19 +843,25 @@ early_param("mem", early_mem);
 
 static void __init request_standard_resources(const struct machine_desc *mdesc)
 {
-	struct memblock_region *region;
+	phys_addr_t start, end, res_end;
 	struct resource *res;
+	u64 i;
 
 	kernel_code.start   = virt_to_phys(_text);
 	kernel_code.end     = virt_to_phys(__init_begin - 1);
 	kernel_data.start   = virt_to_phys(_sdata);
 	kernel_data.end     = virt_to_phys(_end - 1);
 
-	for_each_memblock(memory, region) {
+	for_each_mem_range(i, &start, &end) {
-		phys_addr_t start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
-		phys_addr_t end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
 		unsigned long boot_alias_start;
 
+		/*
+		 * In memblock, end points to the first byte after the
+		 * range while in resourses, end points to the last byte in
+		 * the range.
+		 */
+		res_end = end - 1;
+
 		/*
 		 * Some systems have a special memory alias which is only
 		 * used for booting.  We need to advertise this region to
@@ -869,7 +875,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 				      __func__, sizeof(*res));
 			res->name = "System RAM (boot alias)";
 			res->start = boot_alias_start;
-			res->end = phys_to_idmap(end);
+			res->end = phys_to_idmap(res_end);
 			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 			request_resource(&iomem_resource, res);
 		}
@@ -880,7 +886,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 			      sizeof(*res));
 		res->name  = "System RAM";
 		res->start = start;
-		res->end = end;
+		res->end = res_end;
 		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);

arch/arm/mm/init.c

@@ -299,16 +299,14 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
  */
 static void __init free_unused_memmap(void)
 {
-	unsigned long start, prev_end = 0;
+	unsigned long start, end, prev_end = 0;
-	struct memblock_region *reg;
+	int i;
 
 	/*
 	 * This relies on each bank being in address order.
 	 * The banks are sorted previously in bootmem_init().
 	 */
-	for_each_memblock(memory, reg) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		start = memblock_region_memory_base_pfn(reg);
-
 #ifdef CONFIG_SPARSEMEM
 		/*
 		 * Take care not to free memmap entries that don't exist
@@ -336,8 +334,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(memblock_region_memory_end_pfn(reg),
+		prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
-				 MAX_ORDER_NR_PAGES);
 	}
 
 #ifdef CONFIG_SPARSEMEM
@@ -347,61 +344,29 @@ static void __init free_unused_memmap(void)
 #endif
 }
 
-#ifdef CONFIG_HIGHMEM
-static inline void free_area_high(unsigned long pfn, unsigned long end)
-{
-	for (; pfn < end; pfn++)
-		free_highmem_page(pfn_to_page(pfn));
-}
-#endif
-
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
 	unsigned long max_low = max_low_pfn;
-	struct memblock_region *mem, *res;
+	phys_addr_t range_start, range_end;
+	u64 i;
 
 	/* set highmem page free */
-	for_each_memblock(memory, mem) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
-		unsigned long start = memblock_region_memory_base_pfn(mem);
+				&range_start, &range_end, NULL) {
-		unsigned long end = memblock_region_memory_end_pfn(mem);
+		unsigned long start = PHYS_PFN(range_start);
+		unsigned long end = PHYS_PFN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)
 			continue;
 
-		if (memblock_is_nomap(mem))
-			continue;
-
 		/* Truncate partial highmem entries */
 		if (start < max_low)
 			start = max_low;
 
-		/* Find and exclude any reserved regions */
+		for (; start < end; start++)
-		for_each_memblock(reserved, res) {
+			free_highmem_page(pfn_to_page(start));
-			unsigned long res_start, res_end;
-
-			res_start = memblock_region_reserved_base_pfn(res);
-			res_end = memblock_region_reserved_end_pfn(res);
-
-			if (res_end < start)
-				continue;
-			if (res_start < start)
-				res_start = start;
-			if (res_start > end)
-				res_start = end;
-			if (res_end > end)
-				res_end = end;
-			if (res_start != start)
-				free_area_high(start, res_start);
-			start = res_end;
-			if (start == end)
-				break;
-		}
-
-		/* And now free anything which remains */
-		if (start < end)
-			free_area_high(start, end);
 	}
 #endif
 }

arch/arm/mm/mmu.c

@@ -1154,9 +1154,8 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 
 void __init adjust_lowmem_bounds(void)
 {
-	phys_addr_t memblock_limit = 0;
+	phys_addr_t block_start, block_end, memblock_limit = 0;
-	u64 vmalloc_limit;
+	u64 vmalloc_limit, i;
-	struct memblock_region *reg;
 	phys_addr_t lowmem_limit = 0;
 
 	/*
@@ -1172,26 +1171,18 @@ void __init adjust_lowmem_bounds(void)
 	 * The first usable region must be PMD aligned. Mark its start
 	 * as MEMBLOCK_NOMAP if it isn't
 	 */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &block_start, &block_end) {
-		if (!memblock_is_nomap(reg)) {
+		if (!IS_ALIGNED(block_start, PMD_SIZE)) {
-			if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
+			phys_addr_t len;
-				phys_addr_t len;
 
-				len = round_up(reg->base, PMD_SIZE) - reg->base;
+			len = round_up(block_start, PMD_SIZE) - block_start;
-				memblock_mark_nomap(reg->base, len);
+			memblock_mark_nomap(block_start, len);
-			}
-			break;
 		}
+		break;
 	}
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &block_start, &block_end) {
-		phys_addr_t block_start = reg->base;
+		if (block_start < vmalloc_limit) {
-		phys_addr_t block_end = reg->base + reg->size;
-
-		if (memblock_is_nomap(reg))
-			continue;
-
-		if (reg->base < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*
 				 * Compare as u64 to ensure vmalloc_limit does
@@ -1440,19 +1431,15 @@ static void __init kmap_init(void)
 
 static void __init map_lowmem(void)
 {
-	struct memblock_region *reg;
 	phys_addr_t kernel_x_start = round_down(__pa(KERNEL_START), SECTION_SIZE);
 	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	phys_addr_t start, end;
+	u64 i;
 
 	/* Map all the lowmem memory banks. */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		phys_addr_t start = reg->base;
-		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
-		if (memblock_is_nomap(reg))
-			continue;
-
 		if (end > arm_lowmem_limit)
 			end = arm_lowmem_limit;
 		if (start >= end)

arch/arm/mm/pmsa-v7.c

@@ -231,12 +231,12 @@ static int __init allocate_region(phys_addr_t base, phys_addr_t size,
 void __init pmsav7_adjust_lowmem_bounds(void)
 {
 	phys_addr_t  specified_mem_size = 0, total_mem_size = 0;
-	struct memblock_region *reg;
-	bool first = true;
 	phys_addr_t mem_start;
 	phys_addr_t mem_end;
+	phys_addr_t reg_start, reg_end;
 	unsigned int mem_max_regions;
-	int num, i;
+	int num;
+	u64 i;
 
 	/* Free-up PMSAv7_PROBE_REGION */
 	mpu_min_region_order = __mpu_min_region_order();
@@ -262,20 +262,19 @@ void __init pmsav7_adjust_lowmem_bounds(void)
 	mem_max_regions -= num;
 #endif
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
-		if (first) {
+		if (i == 0) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
 			 * Initially only use memory continuous from
 			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
+			if (reg_start != phys_offset)
 				panic("First memory bank must be contiguous from PHYS_OFFSET");
 
-			mem_start = reg->base;
+			mem_start = reg_start;
-			mem_end = reg->base + reg->size;
+			mem_end = reg_end;
-			specified_mem_size = reg->size;
+			specified_mem_size = mem_end - mem_start;
-			first = false;
 		} else {
 			/*
 			 * memblock auto merges contiguous blocks, remove
@@ -283,8 +282,8 @@ void __init pmsav7_adjust_lowmem_bounds(void)
 			 * blocks separately while iterating)
 			 */
 			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
-				  &mem_end, &reg->base);
+				  &mem_end, &reg_start);
-			memblock_remove(reg->base, 0 - reg->base);
+			memblock_remove(reg_start, 0 - reg_start);
 			break;
 		}
 	}

arch/arm/mm/pmsa-v8.c

@@ -94,20 +94,19 @@ static __init bool is_region_fixed(int number)
 void __init pmsav8_adjust_lowmem_bounds(void)
 {
 	phys_addr_t mem_end;
-	struct memblock_region *reg;
+	phys_addr_t reg_start, reg_end;
-	bool first = true;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
-		if (first) {
+		if (i == 0) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
 			 * Initially only use memory continuous from
 			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
+			if (reg_start != phys_offset)
 				panic("First memory bank must be contiguous from PHYS_OFFSET");
-			mem_end = reg->base + reg->size;
+			mem_end = reg_end;
-			first = false;
 		} else {
 			/*
 			 * memblock auto merges contiguous blocks, remove
@@ -115,8 +114,8 @@ void __init pmsav8_adjust_lowmem_bounds(void)
 			 * blocks separately while iterating)
 			 */
 			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
-				  &mem_end, &reg->base);
+				  &mem_end, &reg_start);
-			memblock_remove(reg->base, 0 - reg->base);
+			memblock_remove(reg_start, 0 - reg_start);
 			break;
 		}
 	}

arch/arm/xen/mm.c

@@ -25,11 +25,12 @@
 
 unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 {
-	struct memblock_region *reg;
+	phys_addr_t base;
 	gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &base, NULL) {
-		if (reg->base < (phys_addr_t)0xffffffff) {
+		if (base < (phys_addr_t)0xffffffff) {
 			if (IS_ENABLED(CONFIG_ZONE_DMA32))
 				flags |= __GFP_DMA32;
 			else

arch/arm64/Kconfig

@@ -1041,19 +1041,6 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 config CC_HAVE_SHADOW_CALL_STACK
 	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config PARAVIRT
 	bool "Enable paravirtualization code"
 	help
@@ -1612,8 +1599,6 @@ config ARM64_BTI_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
-	# https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55
-	depends on !CC_IS_CLANG || CLANG_VERSION >= 100001
 	depends on !(CC_IS_CLANG && GCOV_KERNEL)
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help

arch/arm64/kernel/machine_kexec_file.c

@@ -215,8 +215,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 	phys_addr_t start, end;
 
 	nr_ranges = 1; /* for exclusion of crashkernel region */
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+	for_each_mem_range(i, &start, &end)
-					MEMBLOCK_NONE, &start, &end, NULL)
 		nr_ranges++;
 
 	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
@@ -225,8 +224,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 
 	cmem->max_nr_ranges = nr_ranges;
 	cmem->nr_ranges = 0;
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+	for_each_mem_range(i, &start, &end) {
-					MEMBLOCK_NONE, &start, &end, NULL) {
 		cmem->ranges[cmem->nr_ranges].start = start;
 		cmem->ranges[cmem->nr_ranges].end = end - 1;
 		cmem->nr_ranges++;

arch/arm64/kernel/setup.c

@@ -217,7 +217,7 @@ static void __init request_standard_resources(void)
 	if (!standard_resources)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		res = &standard_resources[i++];
 		if (memblock_is_nomap(region)) {
 			res->name  = "reserved";
@@ -257,7 +257,7 @@ static int __init reserve_memblock_reserved_regions(void)
 		if (!memblock_is_region_reserved(mem->start, mem_size))
 			continue;
 
-		for_each_reserved_mem_region(j, &r_start, &r_end) {
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
 			resource_size_t start, end;
 
 			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);

arch/arm64/kernel/vdso/Makefile

@@ -43,13 +43,6 @@ ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
 endif
 
-# Clang versions less than 8 do not support -mcmodel=tiny
-ifeq ($(CONFIG_CC_IS_CLANG), y)
-  ifeq ($(shell test $(CONFIG_CLANG_VERSION) -lt 80000; echo $$?),0)
-    CFLAGS_REMOVE_vgettimeofday.o += -mcmodel=tiny
-  endif
-endif
-
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 

arch/arm64/mm/init.c

@@ -471,12 +471,10 @@ static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)
  */
 static void __init free_unused_memmap(void)
 {
-	unsigned long start, prev_end = 0;
+	unsigned long start, end, prev_end = 0;
-	struct memblock_region *reg;
+	int i;
-
-	for_each_memblock(memory, reg) {
-		start = __phys_to_pfn(reg->base);
 
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
 #ifdef CONFIG_SPARSEMEM
 		/*
 		 * Take care not to free memmap entries that don't exist due
@@ -496,8 +494,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
+		prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
-				 MAX_ORDER_NR_PAGES);
 	}
 
 #ifdef CONFIG_SPARSEMEM

arch/arm64/mm/kasan_init.c

@@ -212,8 +212,8 @@ void __init kasan_init(void)
 {
 	u64 kimg_shadow_start, kimg_shadow_end;
 	u64 mod_shadow_start, mod_shadow_end;
-	struct memblock_region *reg;
+	phys_addr_t pa_start, pa_end;
-	int i;
+	u64 i;
 
 	kimg_shadow_start = (u64)kasan_mem_to_shadow(_text) & PAGE_MASK;
 	kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(_end));
@@ -246,9 +246,9 @@ void __init kasan_init(void)
 		kasan_populate_early_shadow((void *)mod_shadow_end,
 					    (void *)kimg_shadow_start);
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &pa_start, &pa_end) {
-		void *start = (void *)__phys_to_virt(reg->base);
+		void *start = (void *)__phys_to_virt(pa_start);
-		void *end = (void *)__phys_to_virt(reg->base + reg->size);
+		void *end = (void *)__phys_to_virt(pa_end);
 
 		if (start >= end)
 			break;

arch/arm64/mm/mmu.c

@@ -473,8 +473,9 @@ static void __init map_mem(pgd_t *pgdp)
 {
 	phys_addr_t kernel_start = __pa_symbol(_text);
 	phys_addr_t kernel_end = __pa_symbol(__init_begin);
-	struct memblock_region *reg;
+	phys_addr_t start, end;
 	int flags = 0;
+	u64 i;
 
 	if (rodata_full || debug_pagealloc_enabled())
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
@@ -493,15 +494,9 @@ static void __init map_mem(pgd_t *pgdp)
 #endif
 
 	/* map all the memory banks */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		phys_addr_t start = reg->base;
-		phys_addr_t end = start + reg->size;
-
 		if (start >= end)
 			break;
-		if (memblock_is_nomap(reg))
-			continue;
-
 		/*
 		 * The linear map must allow allocation tags reading/writing
 		 * if MTE is present. Otherwise, it has the same attributes as

arch/arm64/mm/numa.c

@@ -354,7 +354,7 @@ static int __init numa_register_nodes(void)
 	struct memblock_region *mblk;
 
 	/* Check that valid nid is set to memblks */
-	for_each_memblock(memory, mblk) {
+	for_each_mem_region(mblk) {
 		int mblk_nid = memblock_get_region_node(mblk);
 
 		if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) {
@@ -427,19 +427,16 @@ out_free_distance:
  */
 static int __init dummy_numa_init(void)
 {
+	phys_addr_t start = memblock_start_of_DRAM();
+	phys_addr_t end = memblock_end_of_DRAM();
 	int ret;
-	struct memblock_region *mblk;
 
 	if (numa_off)
 		pr_info("NUMA disabled\n"); /* Forced off on command line. */
-	pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+	pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", start, end - 1);
-		memblock_start_of_DRAM(), memblock_end_of_DRAM() - 1);
-
-	for_each_memblock(memory, mblk) {
-		ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
-		if (!ret)
-			continue;
 
+	ret = numa_add_memblk(0, start, end);
+	if (ret) {
 		pr_err("NUMA init failed\n");
 		return ret;
 	}

arch/c6x/kernel/setup.c

@@ -287,7 +287,8 @@ notrace void __init machine_init(unsigned long dt_ptr)
 
 void __init setup_arch(char **cmdline_p)
 {
-	struct memblock_region *reg;
+	phys_addr_t start, end;
+	u64 i;
 
 	printk(KERN_INFO "Initializing kernel\n");
 
@@ -351,9 +352,9 @@ void __init setup_arch(char **cmdline_p)
 	disable_caching(ram_start, ram_end - 1);
 
 	/* Set caching of external RAM used by Linux */
-	for_each_memblock(memory, reg)
+	for_each_mem_range(i, &start, &end)
-		enable_caching(CACHE_REGION_START(reg->base),
+		enable_caching(CACHE_REGION_START(start),
-			       CACHE_REGION_START(reg->base + reg->size - 1));
+			       CACHE_REGION_START(end - 1));
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/*

arch/csky/Kconfig

@@ -309,16 +309,3 @@ endmenu
 source "arch/csky/Kconfig.platforms"
 
 source "kernel/Kconfig.hz"
-
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.

arch/h8300/kernel/setup.c

@@ -74,17 +74,15 @@ static void __init bootmem_init(void)
 	memory_end = memory_start = 0;
 
 	/* Find main memory where is the kernel */
-	for_each_memblock(memory, region) {
+	memory_start = memblock_start_of_DRAM();
-		memory_start = region->base;
+	memory_end = memblock_end_of_DRAM();
-		memory_end = region->base + region->size;
-	}
 
 	if (!memory_end)
 		panic("No memory!");
 
 	/* setup bootmem globals (we use no_bootmem, but mm still depends on this) */
 	min_low_pfn = PFN_UP(memory_start);
-	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_low_pfn = PFN_DOWN(memory_end);
 	max_pfn = max_low_pfn;
 
 	memblock_reserve(__pa(_stext), _end - _stext);

arch/microblaze/Kconfig

@@ -26,6 +26,7 @@ config MICROBLAZE
 	select GENERIC_SCHED_CLOCK
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
@@ -120,23 +121,6 @@ config CMDLINE_FORCE
 	  Set this to have arguments from the default kernel command string
 	  override those passed by the boot loader.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 endmenu
 
 menu "Kernel features"

arch/microblaze/mm/init.c

@@ -108,15 +108,15 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-	struct memblock_region *reg;
-
 #ifndef CONFIG_MMU
 	u32 kernel_align_start, kernel_align_size;
+	phys_addr_t start, end;
+	u64 i;
 
 	/* Find main memory where is the kernel */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		memory_start = (u32)reg->base;
+		memory_start = start;
-		lowmem_size = reg->size;
+		lowmem_size = end - start;
 		if ((memory_start <= (u32)_text) &&
 			((u32)_text <= (memory_start + lowmem_size - 1))) {
 			memory_size = lowmem_size;
@@ -164,17 +164,6 @@ void __init setup_memory(void)
 	pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
 	pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn);
 
-	/* Add active regions with valid PFNs */
-	for_each_memblock(memory, reg) {
-		unsigned long start_pfn, end_pfn;
-
-		start_pfn = memblock_region_memory_base_pfn(reg);
-		end_pfn = memblock_region_memory_end_pfn(reg);
-		memblock_set_node(start_pfn << PAGE_SHIFT,
-				  (end_pfn - start_pfn) << PAGE_SHIFT,
-				  &memblock.memory, 0);
-	}
-
 	paging_init();
 }
 

arch/mips/Kconfig

@@ -3006,23 +3006,6 @@ config PHYSICAL_START
 	  specified in the "crashkernel=YM@XM" command line boot parameter
 	  passed to the panic-ed kernel).
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 config MIPS_O32_FP64_SUPPORT
 	bool "Support for O32 binaries using 64-bit FP" if !CPU_MIPSR6
 	depends on 32BIT || MIPS32_O32

arch/mips/cavium-octeon/dma-octeon.c

@@ -190,25 +190,25 @@ char *octeon_swiotlb;
 
 void __init plat_swiotlb_setup(void)
 {
-	struct memblock_region *mem;
+	phys_addr_t start, end;
 	phys_addr_t max_addr;
 	phys_addr_t addr_size;
 	size_t swiotlbsize;
 	unsigned long swiotlb_nslabs;
+	u64 i;
 
 	max_addr = 0;
 	addr_size = 0;
 
-	for_each_memblock(memory, mem) {
+	for_each_mem_range(i, &start, &end) {
 		/* These addresses map low for PCI. */
-		if (mem->base > 0x410000000ull && !OCTEON_IS_OCTEON2())
+		if (start > 0x410000000ull && !OCTEON_IS_OCTEON2())
 			continue;
 
-		addr_size += mem->size;
+		addr_size += (end - start);
-
-		if (max_addr < mem->base + mem->size)
-			max_addr = mem->base + mem->size;
 
+		if (max_addr < end)
+			max_addr = end;
 	}
 
 	swiotlbsize = PAGE_SIZE;

arch/mips/kernel/setup.c

@@ -300,8 +300,9 @@ static void __init bootmem_init(void)
 
 static void __init bootmem_init(void)
 {
-	struct memblock_region *mem;
 	phys_addr_t ramstart, ramend;
+	phys_addr_t start, end;
+	u64 i;
 
 	ramstart = memblock_start_of_DRAM();
 	ramend = memblock_end_of_DRAM();
@@ -338,18 +339,13 @@ static void __init bootmem_init(void)
 
 	min_low_pfn = ARCH_PFN_OFFSET;
 	max_pfn = PFN_DOWN(ramend);
-	for_each_memblock(memory, mem) {
+	for_each_mem_range(i, &start, &end) {
-		unsigned long start = memblock_region_memory_base_pfn(mem);
-		unsigned long end = memblock_region_memory_end_pfn(mem);
-
 		/*
 		 * Skip highmem here so we get an accurate max_low_pfn if low
 		 * memory stops short of high memory.
 		 * If the region overlaps HIGHMEM_START, end is clipped so
 		 * max_pfn excludes the highmem portion.
 		 */
-		if (memblock_is_nomap(mem))
-			continue;
 		if (start >= PFN_DOWN(HIGHMEM_START))
 			continue;
 		if (end > PFN_DOWN(HIGHMEM_START))
@@ -450,13 +446,12 @@ early_param("memmap", early_parse_memmap);
 unsigned long setup_elfcorehdr, setup_elfcorehdr_size;
 static int __init early_parse_elfcorehdr(char *p)
 {
-	struct memblock_region *mem;
+	phys_addr_t start, end;
+	u64 i;
 
 	setup_elfcorehdr = memparse(p, &p);
 
-	 for_each_memblock(memory, mem) {
+	for_each_mem_range(i, &start, &end) {
-		unsigned long start = mem->base;
-		unsigned long end = start + mem->size;
 		if (setup_elfcorehdr >= start && setup_elfcorehdr < end) {
 			/*
 			 * Reserve from the elf core header to the end of
@@ -720,7 +715,8 @@ static void __init arch_mem_init(char **cmdline_p)
 
 static void __init resource_init(void)
 {
-	struct memblock_region *region;
+	phys_addr_t start, end;
+	u64 i;
 
 	if (UNCAC_BASE != IO_BASE)
 		return;
@@ -732,9 +728,7 @@ static void __init resource_init(void)
 	bss_resource.start = __pa_symbol(&__bss_start);
 	bss_resource.end = __pa_symbol(&__bss_stop) - 1;
 
-	for_each_memblock(memory, region) {
+	for_each_mem_range(i, &start, &end) {
-		phys_addr_t start = PFN_PHYS(memblock_region_memory_base_pfn(region));
-		phys_addr_t end = PFN_PHYS(memblock_region_memory_end_pfn(region)) - 1;
 		struct resource *res;
 
 		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
@@ -743,7 +737,12 @@ static void __init resource_init(void)
 			      sizeof(struct resource));
 
 		res->start = start;
-		res->end = end;
+		/*
+		 * In memblock, end points to the first byte after the
+		 * range while in resourses, end points to the last byte in
+		 * the range.
+		 */
+		res->end = end - 1;
 		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 		res->name = "System RAM";
 

arch/mips/netlogic/xlp/setup.c

@@ -70,7 +70,7 @@ static void nlm_fixup_mem(void)
 	const int pref_backup = 512;
 	struct memblock_region *mem;
 
-	for_each_memblock(memory, mem) {
+	for_each_mem_region(mem) {
 		memblock_remove(mem->base + mem->size - pref_backup,
 			pref_backup);
 	}

arch/nds32/kernel/setup.c

@@ -249,12 +249,8 @@ static void __init setup_memory(void)
 	memory_end = memory_start = 0;
 
 	/* Find main memory where is the kernel */
-	for_each_memblock(memory, region) {
+	memory_start = memblock_start_of_DRAM();
-		memory_start = region->base;
+	memory_end = memblock_end_of_DRAM();
-		memory_end = region->base + region->size;
-		pr_info("%s: Memory: 0x%x-0x%x\n", __func__,
-			memory_start, memory_end);
-	}
 
 	if (!memory_end) {
 		panic("No memory!");

arch/openrisc/kernel/setup.c

@@ -48,17 +48,12 @@ static void __init setup_memory(void)
 	unsigned long ram_start_pfn;
 	unsigned long ram_end_pfn;
 	phys_addr_t memory_start, memory_end;
-	struct memblock_region *region;
 
 	memory_end = memory_start = 0;
 
 	/* Find main memory where is the kernel, we assume its the only one */
-	for_each_memblock(memory, region) {
+	memory_start = memblock_start_of_DRAM();
-		memory_start = region->base;
+	memory_end = memblock_end_of_DRAM();
-		memory_end = region->base + region->size;
-		printk(KERN_INFO "%s: Memory: 0x%x-0x%x\n", __func__,
-		       memory_start, memory_end);
-	}
 
 	if (!memory_end) {
 		panic("No memory!");

arch/openrisc/mm/init.c

@@ -64,6 +64,7 @@ extern const char _s_kernel_ro[], _e_kernel_ro[];
  */
 static void __init map_ram(void)
 {
+	phys_addr_t start, end;
 	unsigned long v, p, e;
 	pgprot_t prot;
 	pgd_t *pge;
@@ -71,6 +72,7 @@ static void __init map_ram(void)
 	pud_t *pue;
 	pmd_t *pme;
 	pte_t *pte;
+	u64 i;
 	/* These mark extents of read-only kernel pages...
 	 * ...from vmlinux.lds.S
 	 */
@@ -78,9 +80,9 @@ static void __init map_ram(void)
 
 	v = PAGE_OFFSET;
 
-	for_each_memblock(memory, region) {
+	for_each_mem_range(i, &start, &end) {
-		p = (u32) region->base & PAGE_MASK;
+		p = (u32) start & PAGE_MASK;
-		e = p + (u32) region->size;
+		e = (u32) end;
 
 		v = (u32) __va(p);
 		pge = pgd_offset_k(v);

arch/parisc/Kconfig

@@ -378,19 +378,3 @@ endmenu
 
 
 source "drivers/parisc/Kconfig"
-
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.

arch/powerpc/Kconfig

@@ -946,23 +946,6 @@ config ARCH_WANTS_FREEZER_CONTROL
 
 source "kernel/power/Kconfig"
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 config PPC_MEM_KEYS
 	prompt "PowerPC Memory Protection Keys"
 	def_bool y

arch/powerpc/kernel/fadump.c

@@ -191,13 +191,13 @@ int is_fadump_active(void)
  */
 static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
 {
-	struct memblock_region *reg;
+	phys_addr_t reg_start, reg_end;
 	bool ret = false;
-	u64 start, end;
+	u64 i, start, end;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
-		start = max_t(u64, d_start, reg->base);
+		start = max_t(u64, d_start, reg_start);
-		end = min_t(u64, d_end, (reg->base + reg->size));
+		end = min_t(u64, d_end, reg_end);
 		if (d_start < end) {
 			/* Memory hole from d_start to start */
 			if (start > d_start)
@@ -422,34 +422,34 @@ static int __init add_boot_mem_regions(unsigned long mstart,
 
 static int __init fadump_get_boot_mem_regions(void)
 {
-	unsigned long base, size, cur_size, hole_size, last_end;
+	unsigned long size, cur_size, hole_size, last_end;
 	unsigned long mem_size = fw_dump.boot_memory_size;
-	struct memblock_region *reg;
+	phys_addr_t reg_start, reg_end;
 	int ret = 1;
+	u64 i;
 
 	fw_dump.boot_mem_regs_cnt = 0;
 
 	last_end = 0;
 	hole_size = 0;
 	cur_size = 0;
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
-		base = reg->base;
+		size = reg_end - reg_start;
-		size = reg->size;
+		hole_size += (reg_start - last_end);
-		hole_size += (base - last_end);
 
 		if ((cur_size + size) >= mem_size) {
 			size = (mem_size - cur_size);
-			ret = add_boot_mem_regions(base, size);
+			ret = add_boot_mem_regions(reg_start, size);
 			break;
 		}
 
 		mem_size -= size;
 		cur_size += size;
-		ret = add_boot_mem_regions(base, size);
+		ret = add_boot_mem_regions(reg_start, size);
 		if (!ret)
 			break;
 
-		last_end = base + size;
+		last_end = reg_end;
 	}
 	fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size);
 
@@ -985,9 +985,8 @@ static int fadump_init_elfcore_header(char *bufp)
  */
 static int fadump_setup_crash_memory_ranges(void)
 {
-	struct memblock_region *reg;
+	u64 i, start, end;
-	u64 start, end;
+	int ret;
-	int i, ret;
 
 	pr_debug("Setup crash memory ranges.\n");
 	crash_mrange_info.mem_range_cnt = 0;
@@ -1005,10 +1004,7 @@ static int fadump_setup_crash_memory_ranges(void)
 			return ret;
 	}
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		start = (u64)reg->base;
-		end = start + (u64)reg->size;
-
 		/*
 		 * skip the memory chunk that is already added
 		 * (0 through boot_memory_top).
@@ -1242,14 +1238,17 @@ static void fadump_free_reserved_memory(unsigned long start_pfn,
  */
 static void fadump_release_reserved_area(u64 start, u64 end)
 {
+	unsigned long reg_spfn, reg_epfn;
 	u64 tstart, tend, spfn, epfn;
-	struct memblock_region *reg;
+	int i;
 
 	spfn = PHYS_PFN(start);
 	epfn = PHYS_PFN(end);
-	for_each_memblock(memory, reg) {
+
-		tstart = max_t(u64, spfn, memblock_region_memory_base_pfn(reg));
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &reg_spfn, &reg_epfn, NULL) {
-		tend   = min_t(u64, epfn, memblock_region_memory_end_pfn(reg));
+		tstart = max_t(u64, spfn, reg_spfn);
+		tend   = min_t(u64, epfn, reg_epfn);
+
 		if (tstart < tend) {
 			fadump_free_reserved_memory(tstart, tend);
 
@@ -1684,12 +1683,10 @@ int __init fadump_reserve_mem(void)
 /* Preserve everything above the base address */
 static void __init fadump_reserve_crash_area(u64 base)
 {
-	struct memblock_region *reg;
+	u64 i, mstart, mend, msize;
-	u64 mstart, msize;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &mstart, &mend) {
-		mstart = reg->base;
+		msize  = mend - mstart;
-		msize  = reg->size;
 
 		if ((mstart + msize) < base)
 			continue;

arch/powerpc/kexec/file_load_64.c

@@ -138,15 +138,13 @@ out:
  */
 static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
 {
-	struct memblock_region *reg;
+	phys_addr_t base, end;
 	struct crash_mem *tmem;
+	u64 i;
 	int ret;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &base, &end) {
-		u64 base, size;
+		u64 size = end - base;
-
-		base = (u64)reg->base;
-		size = (u64)reg->size;
 
 		/* Skip backup memory region, which needs a separate entry */
 		if (base == BACKUP_SRC_START) {
@@ -250,8 +248,7 @@ static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE,
+	for_each_mem_range_rev(i, &start, &end) {
-			       MEMBLOCK_NONE, &start, &end, NULL) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the
@@ -350,8 +347,7 @@ static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+	for_each_mem_range(i, &start, &end) {
-			   MEMBLOCK_NONE, &start, &end, NULL) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -95,23 +95,15 @@ EXPORT_SYMBOL_GPL(kvm_free_hpt_cma);
 void __init kvm_cma_reserve(void)
 {
 	unsigned long align_size;
-	struct memblock_region *reg;
+	phys_addr_t selected_size;
-	phys_addr_t selected_size = 0;
 
 	/*
 	 * We need CMA reservation only when we are in HV mode
 	 */
 	if (!cpu_has_feature(CPU_FTR_HVMODE))
 		return;
-	/*
-	 * We cannot use memblock_phys_mem_size() here, because
-	 * memblock_analyze() has not been called yet.
-	 */
-	for_each_memblock(memory, reg)
-		selected_size += memblock_region_memory_end_pfn(reg) -
-				 memblock_region_memory_base_pfn(reg);
 
-	selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
+	selected_size = PAGE_ALIGN(memblock_phys_mem_size() * kvm_cma_resv_ratio / 100);
 	if (selected_size) {
 		pr_info("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -687,9 +687,9 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn_last, pfn_first;
 
-	pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT;
+	pfn_first = kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT;
 	pfn_last = pfn_first +
-		   (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT);
+		   (range_len(&kvmppc_uvmem_pgmap.range) >> PAGE_SHIFT);
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
 	bit = find_first_zero_bit(kvmppc_uvmem_bitmap,
@@ -1007,7 +1007,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 static void kvmppc_uvmem_page_free(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page) -
-			(kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT);
+			(kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT);
 	struct kvmppc_uvmem_page_pvt *pvt;
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
@@ -1170,7 +1170,9 @@ int kvmppc_uvmem_init(void)
 	}
 
 	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
-	kvmppc_uvmem_pgmap.res = *res;
+	kvmppc_uvmem_pgmap.range.start = res->start;
+	kvmppc_uvmem_pgmap.range.end = res->end;
+	kvmppc_uvmem_pgmap.nr_range = 1;
 	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
 	/* just one global instance: */
 	kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
@@ -1205,7 +1207,7 @@ void kvmppc_uvmem_free(void)
 		return;
 
 	memunmap_pages(&kvmppc_uvmem_pgmap);
-	release_mem_region(kvmppc_uvmem_pgmap.res.start,
+	release_mem_region(kvmppc_uvmem_pgmap.range.start,
-			   resource_size(&kvmppc_uvmem_pgmap.res));
+			   range_len(&kvmppc_uvmem_pgmap.range));
 	kfree(kvmppc_uvmem_bitmap);
 }

arch/powerpc/mm/book3s64/hash_utils.c

@@ -7,7 +7,7 @@
  *
  * SMP scalability work:
  *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
- * 
+ *
  *    Module name: htab.c
  *
  *    Description:
@@ -867,8 +867,8 @@ static void __init htab_initialize(void)
 	unsigned long table;
 	unsigned long pteg_count;
 	unsigned long prot;
-	unsigned long base = 0, size = 0;
+	phys_addr_t base = 0, size = 0, end;
-	struct memblock_region *reg;
+	u64 i;
 
 	DBG(" -> htab_initialize()\n");
 
@@ -884,7 +884,7 @@ static void __init htab_initialize(void)
 	/*
 	 * Calculate the required size of the htab.  We want the number of
 	 * PTEGs to equal one half the number of real pages.
-	 */ 
+	 */
 	htab_size_bytes = htab_get_table_size();
 	pteg_count = htab_size_bytes >> 7;
 
@@ -894,7 +894,7 @@ static void __init htab_initialize(void)
 	    firmware_has_feature(FW_FEATURE_PS3_LV1)) {
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
-		_SDR1 = 0; 
+		_SDR1 = 0;
 #ifdef CONFIG_FA_DUMP
 		/*
 		 * If firmware assisted dump is active firmware preserves
@@ -960,9 +960,9 @@ static void __init htab_initialize(void)
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
 	/* create bolted the linear mapping in the hash table */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &base, &end) {
-		base = (unsigned long)__va(reg->base);
+		size = end - base;
-		size = reg->size;
+		base = (unsigned long)__va(base);
 
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -329,7 +329,8 @@ static int __meminit create_physical_mapping(unsigned long start,
 static void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
-	struct memblock_region *reg;
+	phys_addr_t start, end;
+	u64 i;
 
 	/* We don't support slb for radix */
 	mmu_slb_size = 0;
@@ -337,20 +338,19 @@ static void __init radix_init_pgtable(void)
 	/*
 	 * Create the linear mapping
 	 */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
 		/*
 		 * The memblock allocator  is up at this point, so the
 		 * page tables will be allocated within the range. No
 		 * need or a node (which we don't have yet).
 		 */
 
-		if ((reg->base + reg->size) >= RADIX_VMALLOC_START) {
+		if (end >= RADIX_VMALLOC_START) {
 			pr_warn("Outside the supported range\n");
 			continue;
 		}
 
-		WARN_ON(create_physical_mapping(reg->base,
+		WARN_ON(create_physical_mapping(start, end,
-						reg->base + reg->size,
 						radix_mem_block_size,
 						-1, PAGE_KERNEL));
 	}

arch/powerpc/mm/kasan/kasan_init_32.c

@@ -138,11 +138,11 @@ void __init kasan_mmu_init(void)
 
 void __init kasan_init(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t base, end;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &base, &end) {
-		phys_addr_t base = reg->base;
+		phys_addr_t top = min(end, total_lowmem);
-		phys_addr_t top = min(base + reg->size, total_lowmem);
 		int ret;
 
 		if (base >= top)

arch/powerpc/mm/mem.c

@@ -184,15 +184,16 @@ void __init initmem_init(void)
 /* mark pages that don't exist as nosave */
 static int __init mark_nonram_nosave(void)
 {
-	struct memblock_region *reg, *prev = NULL;
+	unsigned long spfn, epfn, prev = 0;
+	int i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &spfn, &epfn, NULL) {
-		if (prev &&
+		if (prev && prev < spfn)
-		    memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg))
+			register_nosave_region(prev, spfn);
-			register_nosave_region(memblock_region_memory_end_pfn(prev),
+
-					       memblock_region_memory_base_pfn(reg));
+		prev = epfn;
-		prev = reg;
 	}
+
 	return 0;
 }
 #else /* CONFIG_NEED_MULTIPLE_NODES */
@@ -584,20 +585,24 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
  */
 static int __init add_system_ram_resources(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t start, end;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
 		struct resource *res;
-		unsigned long base = reg->base;
-		unsigned long size = reg->size;
 
 		res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 		WARN_ON(!res);
 
 		if (res) {
 			res->name = "System RAM";
-			res->start = base;
+			res->start = start;
-			res->end = base + size - 1;
+			/*
+			 * In memblock, end points to the first byte after
+			 * the range while in resourses, end points to the
+			 * last byte in the range.
+			 */
+			res->end = end - 1;
 			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 			WARN_ON(request_resource(&iomem_resource, res) < 0);
 		}

arch/powerpc/mm/numa.c

@@ -804,17 +804,14 @@ static void __init setup_nonnuma(void)
 	unsigned long total_ram = memblock_phys_mem_size();
 	unsigned long start_pfn, end_pfn;
 	unsigned int nid = 0;
-	struct memblock_region *reg;
+	int i;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-		start_pfn = memblock_region_memory_base_pfn(reg);
-		end_pfn = memblock_region_memory_end_pfn(reg);
-
 		fake_numa_create_new_node(end_pfn, &nid);
 		memblock_set_node(PFN_PHYS(start_pfn),
 				  PFN_PHYS(end_pfn - start_pfn),

arch/powerpc/mm/pgtable_32.c

@@ -123,11 +123,11 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 
 void __init mapin_ram(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t base, end;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &base, &end) {
-		phys_addr_t base = reg->base;
+		phys_addr_t top = min(end, total_lowmem);
-		phys_addr_t top = min(base + reg->size, total_lowmem);
 
 		if (base >= top)
 			continue;

arch/riscv/Kconfig

@@ -334,19 +334,6 @@ menu "Kernel features"
 
 source "kernel/Kconfig.hz"
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config RISCV_SBI_V01
 	bool "SBI v0.1 support"
 	default y

arch/riscv/mm/init.c

@@ -145,21 +145,21 @@ static phys_addr_t dtb_early_pa __initdata;
 
 void __init setup_bootmem(void)
 {
-	struct memblock_region *reg;
 	phys_addr_t mem_size = 0;
 	phys_addr_t total_mem = 0;
-	phys_addr_t mem_start, end = 0;
+	phys_addr_t mem_start, start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
+	u64 i;
 
 	/* Find the memory region containing the kernel */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		end = reg->base + reg->size;
+		phys_addr_t size = end - start;
 		if (!total_mem)
-			mem_start = reg->base;
+			mem_start = start;
-		if (reg->base <= vmlinux_start && vmlinux_end <= end)
+		if (start <= vmlinux_start && vmlinux_end <= end)
-			BUG_ON(reg->size == 0);
+			BUG_ON(size == 0);
-		total_mem = total_mem + reg->size;
+		total_mem = total_mem + size;
 	}
 
 	/*
@@ -191,15 +191,6 @@ void __init setup_bootmem(void)
 	early_init_fdt_scan_reserved_mem();
 	memblock_allow_resize();
 	memblock_dump_all();
-
-	for_each_memblock(memory, reg) {
-		unsigned long start_pfn = memblock_region_memory_base_pfn(reg);
-		unsigned long end_pfn = memblock_region_memory_end_pfn(reg);
-
-		memblock_set_node(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn),
-				  &memblock.memory, 0);
-	}
 }
 
 #ifdef CONFIG_MMU
@@ -464,7 +455,7 @@ static void __init setup_vm_final(void)
 {
 	uintptr_t va, map_size;
 	phys_addr_t pa, start, end;
-	struct memblock_region *reg;
+	u64 i;
 
 	/* Set mmu_enabled flag */
 	mmu_enabled = true;
@@ -475,14 +466,9 @@ static void __init setup_vm_final(void)
 			   PGDIR_SIZE, PAGE_TABLE);
 
 	/* Map all memory banks */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		start = reg->base;
-		end = start + reg->size;
-
 		if (start >= end)
 			break;
-		if (memblock_is_nomap(reg))
-			continue;
 		if (start <= __pa(PAGE_OFFSET) &&
 		    __pa(PAGE_OFFSET) < end)
 			start = __pa(PAGE_OFFSET);
@@ -545,7 +531,7 @@ static void __init resource_init(void)
 {
 	struct memblock_region *region;
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		struct resource *res;
 
 		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);

arch/riscv/mm/kasan_init.c

@@ -85,16 +85,16 @@ static void __init populate(void *start, void *end)
 
 void __init kasan_init(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t _start, _end;
-	unsigned long i;
+	u64 i;
 
 	kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
 				    (void *)kasan_mem_to_shadow((void *)
 								VMALLOC_END));
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &_start, &_end) {
-		void *start = (void *)__va(reg->base);
+		void *start = (void *)_start;
-		void *end = (void *)__va(reg->base + reg->size);
+		void *end = (void *)_end;
 
 		if (start >= end)
 			break;

arch/s390/Kconfig

@@ -792,23 +792,6 @@ config CRASH_DUMP
 
 endmenu
 
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y.
-
 config CCW
 	def_bool y
 

arch/s390/kernel/setup.c

@@ -484,8 +484,9 @@ static struct resource __initdata *standard_resources[] = {
 static void __init setup_resources(void)
 {
 	struct resource *res, *std_res, *sub_res;
-	struct memblock_region *reg;
+	phys_addr_t start, end;
 	int j;
+	u64 i;
 
 	code_resource.start = (unsigned long) _text;
 	code_resource.end = (unsigned long) _etext - 1;
@@ -494,7 +495,7 @@ static void __init setup_resources(void)
 	bss_resource.start = (unsigned long) __bss_start;
 	bss_resource.end = (unsigned long) __bss_stop - 1;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
 		res = memblock_alloc(sizeof(*res), 8);
 		if (!res)
 			panic("%s: Failed to allocate %zu bytes align=0x%x\n",
@@ -502,8 +503,13 @@ static void __init setup_resources(void)
 		res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 
 		res->name = "System RAM";
-		res->start = reg->base;
+		res->start = start;
-		res->end = reg->base + reg->size - 1;
+		/*
+		 * In memblock, end points to the first byte after the
+		 * range while in resourses, end points to the last byte in
+		 * the range.
+		 */
+		res->end = end - 1;
 		request_resource(&iomem_resource, res);
 
 		for (j = 0; j < ARRAY_SIZE(standard_resources); j++) {
@@ -776,8 +782,8 @@ static void __init memblock_add_mem_detect_info(void)
 	unsigned long start, end;
 	int i;
 
-	memblock_dbg("physmem info source: %s (%hhd)\n",
+	pr_debug("physmem info source: %s (%hhd)\n",
-		     get_mem_info_source(), mem_detect.info_source);
+		 get_mem_info_source(), mem_detect.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
 	for_each_mem_detect_block(i, &start, &end) {
@@ -819,14 +825,15 @@ static void __init reserve_kernel(void)
 
 static void __init setup_memory(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t start, end;
+	u64 i;
 
 	/*
 	 * Init storage key for present memory
 	 */
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end)
-		storage_key_init_range(reg->base, reg->base + reg->size);
+		storage_key_init_range(start, end);
-	}
+
 	psw_set_key(PAGE_DEFAULT_KEY);
 
 	/* Only cosmetics */

arch/s390/mm/page-states.c

@@ -183,9 +183,9 @@ static void mark_kernel_pgd(void)
 
 void __init cmma_init_nodat(void)
 {
-	struct memblock_region *reg;
 	struct page *page;
 	unsigned long start, end, ix;
+	int i;
 
 	if (cmma_flag < 2)
 		return;
@@ -193,9 +193,7 @@ void __init cmma_init_nodat(void)
 	mark_kernel_pgd();
 
 	/* Set all kernel pages not used for page tables to stable/no-dat */
-	for_each_memblock(memory, reg) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		start = memblock_region_memory_base_pfn(reg);
-		end = memblock_region_memory_end_pfn(reg);
 		page = pfn_to_page(start);
 		for (ix = start; ix < end; ix++, page++) {
 			if (__test_and_clear_bit(PG_arch_1, &page->flags))

arch/s390/mm/vmem.c

@@ -555,10 +555,11 @@ int vmem_add_mapping(unsigned long start, unsigned long size)
  */
 void __init vmem_map_init(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t base, end;
+	u64 i;
 
-	for_each_memblock(memory, reg)
+	for_each_mem_range(i, &base, &end)
-		vmem_add_range(reg->base, reg->size);
+		vmem_add_range(base, end - base);
 	__set_memory((unsigned long)_stext,
 		     (unsigned long)(_etext - _stext) >> PAGE_SHIFT,
 		     SET_MEMORY_RO | SET_MEMORY_X);

arch/sh/Kconfig

@@ -600,22 +600,6 @@ config PHYSICAL_START
 	  where the fail safe kernel needs to run at a different address
 	  than the panic-ed kernel.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl, it cannot be disabled and the task is only
-	  allowed to execute a few safe syscalls defined by each seccomp
-	  mode.
-
-	  If unsure, say N.
-
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP

arch/sh/mm/init.c

@@ -226,15 +226,12 @@ void __init allocate_pgdat(unsigned int nid)
 
 static void __init do_init_bootmem(void)
 {
-	struct memblock_region *reg;
+	unsigned long start_pfn, end_pfn;
+	int i;
 
 	/* Add active regions with valid PFNs. */
-	for_each_memblock(memory, reg) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL)
-		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock_region_memory_base_pfn(reg);
-		end_pfn = memblock_region_memory_end_pfn(reg);
 		__add_active_range(0, start_pfn, end_pfn);
-	}
 
 	/* All of system RAM sits in node 0 for the non-NUMA case */
 	allocate_pgdat(0);

arch/sparc/Kconfig

@@ -23,6 +23,7 @@ config SPARC
 	select HAVE_OPROFILE
 	select HAVE_ARCH_KGDB if !SMP || SPARC64
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_SECCOMP if SPARC64
 	select HAVE_EXIT_THREAD
 	select HAVE_PCI
 	select SYSCTL_EXCEPTION_TRACE
@@ -227,23 +228,6 @@ config EARLYFB
 	help
 	  Say Y here to enable a faster early framebuffer boot console.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on SPARC64 && PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SPARC64 && SMP

arch/sparc/mm/init_64.c

@@ -1192,18 +1192,14 @@ int of_node_to_nid(struct device_node *dp)
 
 static void __init add_node_ranges(void)
 {
-	struct memblock_region *reg;
+	phys_addr_t start, end;
 	unsigned long prev_max;
+	u64 i;
 
 memblock_resized:
 	prev_max = memblock.memory.max;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &start, &end) {
-		unsigned long size = reg->size;
-		unsigned long start, end;
-
-		start = reg->base;
-		end = start + size;
 		while (start < end) {
 			unsigned long this_end;
 			int nid;
@@ -1211,7 +1207,7 @@ memblock_resized:
 			this_end = memblock_nid_range(start, end, &nid);
 
 			numadbg("Setting memblock NUMA node nid[%d] "
-				"start[%lx] end[%lx]\n",
+				"start[%llx] end[%lx]\n",
 				nid, start, this_end);
 
 			memblock_set_node(start, this_end - start,

arch/um/Kconfig

@@ -173,22 +173,6 @@ config PGTABLE_LEVELS
 	default 3 if 3_LEVEL_PGTABLES
 	default 2
 
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y.
-
 config UML_TIME_TRAVEL_SUPPORT
 	bool
 	prompt "Support time-travel mode (e.g. for test execution)"

arch/x86/Kconfig

@@ -1970,22 +1970,6 @@ config EFI_MIXED
 
 	   If unsure, say N.
 
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 source "kernel/Kconfig.hz"
 
 config KEXEC

arch/x86/boot/compressed/pgtable_64.c

@@ -5,15 +5,6 @@
 #include "pgtable.h"
 #include "../string.h"
 
-/*
- * __force_order is used by special_insns.h asm code to force instruction
- * serialization.
- *
- * It is not referenced from the code, but GCC < 5 with -fPIE would fail
- * due to an undefined symbol. Define it to make these ancient GCCs work.
- */
-unsigned long __force_order;
-
 #define BIOS_START_MIN		0x20000U	/* 128K, less than this is insane */
 #define BIOS_START_MAX		0x9f000U	/* 640K, absolute maximum */
 

arch/x86/include/asm/numa.h

@@ -3,6 +3,7 @@
 #define _ASM_X86_NUMA_H
 
 #include <linux/nodemask.h>
+#include <linux/errno.h>
 
 #include <asm/topology.h>
 #include <asm/apicdef.h>
@@ -77,7 +78,12 @@ void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
-void numa_emu_cmdline(char *);
+int numa_emu_cmdline(char *str);
+#else /* CONFIG_NUMA_EMU */
+static inline int numa_emu_cmdline(char *str)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_NUMA_EMU */
 
 #endif	/* _ASM_X86_NUMA_H */

arch/x86/include/asm/special_insns.h

@@ -11,45 +11,47 @@
 #include <linux/jump_label.h>
 
 /*
- * Volatile isn't enough to prevent the compiler from reordering the
+ * The compiler should not reorder volatile asm statements with respect to each
- * read/write functions for the control registers and messing everything up.
+ * other: they should execute in program order. However GCC 4.9.x and 5.x have
- * A memory clobber would solve the problem, but would prevent reordering of
+ * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
- * all loads stores around it, which can hurt performance. Solution is to
+ * volatile asm. The write functions are not affected since they have memory
- * use a variable and mimic reads and writes to it to enforce serialization
+ * clobbers preventing reordering. To prevent reads from being reordered with
+ * respect to writes, use a dummy memory operand.
  */
-extern unsigned long __force_order;
+
+#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
 
 void native_write_cr0(unsigned long val);
 
 static inline unsigned long native_read_cr0(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static __always_inline unsigned long native_read_cr2(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static __always_inline void native_write_cr2(unsigned long val)
 {
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
 static inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static inline void native_write_cr3(unsigned long val)
 {
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
 
 static inline unsigned long native_read_cr4(void)
@@ -64,10 +66,10 @@ static inline unsigned long native_read_cr4(void)
 	asm volatile("1: mov %%cr4, %0\n"
 		     "2:\n"
 		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
+		     : "=r" (val) : "0" (0), __FORCE_ORDER);
 #else
 	/* CR4 always exists on x86_64. */
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 #endif
 	return val;
 }

arch/x86/include/asm/uaccess.h

@@ -418,7 +418,7 @@ do {									\
 		     "2:\n"						\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %[efault],%[errout]\n"		\
-		     "	xor"itype" %[output],%[output]\n"		\
+		     "	xorl %k[output],%k[output]\n"			\
 		     "	jmp 2b\n"					\
 		     ".previous\n"					\
 		     _ASM_EXTABLE_UA(1b, 3b)				\

arch/x86/kernel/cpu/common.c

@@ -360,7 +360,7 @@ void native_write_cr0(unsigned long val)
 	unsigned long bits_missing = 0;
 
 set_register:
-	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
+	asm volatile("mov %0,%%cr0": "+r" (val) : : "memory");
 
 	if (static_branch_likely(&cr_pinning)) {
 		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
@@ -379,7 +379,7 @@ void native_write_cr4(unsigned long val)
 	unsigned long bits_changed = 0;
 
 set_register:
-	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
+	asm volatile("mov %0,%%cr4": "+r" (val) : : "memory");
 
 	if (static_branch_likely(&cr_pinning)) {
 		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {

arch/x86/kernel/e820.c

@@ -305,6 +305,20 @@ static int __init cpcompare(const void *a, const void *b)
 	return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr);
 }
 
+static bool e820_nomerge(enum e820_type type)
+{
+	/*
+	 * These types may indicate distinct platform ranges aligned to
+	 * numa node, protection domain, performance domain, or other
+	 * boundaries. Do not merge them.
+	 */
+	if (type == E820_TYPE_PRAM)
+		return true;
+	if (type == E820_TYPE_SOFT_RESERVED)
+		return true;
+	return false;
+}
+
 int __init e820__update_table(struct e820_table *table)
 {
 	struct e820_entry *entries = table->entries;
@@ -380,7 +394,7 @@ int __init e820__update_table(struct e820_table *table)
 		}
 
 		/* Continue building up new map based on this information: */
-		if (current_type != last_type || current_type == E820_TYPE_PRAM) {
+		if (current_type != last_type || e820_nomerge(current_type)) {
 			if (last_type != 0)	 {
 				new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr;
 				/* Move forward only if the new size was non-zero: */

arch/x86/kernel/setup.c

@@ -264,16 +264,12 @@ static void __init relocate_initrd(void)
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 
 	/* We need to move the initrd down into directly mapped mem */
-	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+	relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
-						   area_size, PAGE_SIZE);
+						      PFN_PHYS(max_pfn_mapped));
-
 	if (!relocated_ramdisk)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 		      ramdisk_size);
 
-	/* Note: this includes all the mem currently occupied by
-	   the initrd, we rely on that fact to keep the data intact. */
-	memblock_reserve(relocated_ramdisk, area_size);
 	initrd_start = relocated_ramdisk + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
@@ -300,13 +296,13 @@ static void __init early_reserve_initrd(void)
 
 	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
 }
+
 static void __init reserve_initrd(void)
 {
 	/* Assume only end is not page aligned */
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-	u64 mapped_size;
 
 	if (!boot_params.hdr.type_of_loader ||
 	    !ramdisk_image || !ramdisk_size)
@@ -314,12 +310,6 @@ static void __init reserve_initrd(void)
 
 	initrd_start = 0;
 
-	mapped_size = memblock_mem_size(max_pfn_mapped);
-	if (ramdisk_size >= (mapped_size>>1))
-		panic("initrd too large to handle, "
-		       "disabling initrd (%lld needed, %lld available)\n",
-		       ramdisk_size, mapped_size>>1);
-
 	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
 			ramdisk_end - 1);
 
@@ -431,13 +421,13 @@ static int __init reserve_crashkernel_low(void)
 {
 #ifdef CONFIG_X86_64
 	unsigned long long base, low_base = 0, low_size = 0;
-	unsigned long total_low_mem;
+	unsigned long low_mem_limit;
 	int ret;
 
-	total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT));
+	low_mem_limit = min(memblock_phys_mem_size(), CRASH_ADDR_LOW_MAX);
 
 	/* crashkernel=Y,low */
-	ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base);
+	ret = parse_crashkernel_low(boot_command_line, low_mem_limit, &low_size, &base);
 	if (ret) {
 		/*
 		 * two parts from kernel/dma/swiotlb.c:
@@ -455,23 +445,17 @@ static int __init reserve_crashkernel_low(void)
 			return 0;
 	}
 
-	low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN);
+	low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX);
 	if (!low_base) {
 		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
 		       (unsigned long)(low_size >> 20));
 		return -ENOMEM;
 	}
 
-	ret = memblock_reserve(low_base, low_size);
+	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (low RAM limit: %ldMB)\n",
-	if (ret) {
-		pr_err("%s: Error reserving crashkernel low memblock.\n", __func__);
-		return ret;
-	}
-
-	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
 		(unsigned long)(low_size >> 20),
 		(unsigned long)(low_base >> 20),
-		(unsigned long)(total_low_mem >> 20));
+		(unsigned long)(low_mem_limit >> 20));
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
@@ -515,13 +499,13 @@ static void __init reserve_crashkernel(void)
 		 * unless "crashkernel=size[KMG],high" is specified.
 		 */
 		if (!high)
-			crash_base = memblock_find_in_range(CRASH_ALIGN,
+			crash_base = memblock_phys_alloc_range(crash_size,
-						CRASH_ADDR_LOW_MAX,
+						CRASH_ALIGN, CRASH_ALIGN,
-						crash_size, CRASH_ALIGN);
+						CRASH_ADDR_LOW_MAX);
 		if (!crash_base)
-			crash_base = memblock_find_in_range(CRASH_ALIGN,
+			crash_base = memblock_phys_alloc_range(crash_size,
-						CRASH_ADDR_HIGH_MAX,
+						CRASH_ALIGN, CRASH_ALIGN,
-						crash_size, CRASH_ALIGN);
+						CRASH_ADDR_HIGH_MAX);
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
@@ -529,19 +513,13 @@ static void __init reserve_crashkernel(void)
 	} else {
 		unsigned long long start;
 
-		start = memblock_find_in_range(crash_base,
+		start = memblock_phys_alloc_range(crash_size, SZ_1M, crash_base,
-					       crash_base + crash_size,
+						  crash_base + crash_size);
-					       crash_size, 1 << 20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
-	ret = memblock_reserve(crash_base, crash_size);
-	if (ret) {
-		pr_err("%s: Error reserving crashkernel memblock.\n", __func__);
-		return;
-	}
 
 	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
 		memblock_free(crash_base, crash_size);

arch/x86/mm/numa.c

@@ -37,14 +37,12 @@ static __init int numa_setup(char *opt)
 		return -EINVAL;
 	if (!strncmp(opt, "off", 3))
 		numa_off = 1;
-#ifdef CONFIG_NUMA_EMU
 	if (!strncmp(opt, "fake=", 5))
-		numa_emu_cmdline(opt + 5);
+		return numa_emu_cmdline(opt + 5);
-#endif
-#ifdef CONFIG_ACPI_NUMA
 	if (!strncmp(opt, "noacpi", 6))
-		acpi_numa = -1;
+		disable_srat();
-#endif
+	if (!strncmp(opt, "nohmat", 6))
+		disable_hmat();
 	return 0;
 }
 early_param("numa", numa_setup);
@@ -516,7 +514,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	 *   memory ranges, because quirks such as trim_snb_memory()
 	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, mb_region) {
+	for_each_reserved_mem_region(mb_region) {
 		int nid = memblock_get_region_node(mb_region);
 
 		if (nid != MAX_NUMNODES)
@@ -919,7 +917,6 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
-EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {

arch/x86/mm/numa_emulation.c

@@ -13,9 +13,10 @@
 static int emu_nid_to_phys[MAX_NUMNODES];
 static char *emu_cmdline __initdata;
 
-void __init numa_emu_cmdline(char *str)
+int __init numa_emu_cmdline(char *str)
 {
 	emu_cmdline = str;
+	return 0;
 }
 
 static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)

arch/x86/xen/enlighten_pv.c

@@ -1300,7 +1300,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * any NUMA information the kernel tries to get from ACPI will
 	 * be meaningless.  Prevent it from trying.
 	 */
-	acpi_numa = -1;
+	disable_srat();
 #endif
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
 

arch/xtensa/Kconfig

@@ -217,20 +217,6 @@ config HOTPLUG_CPU
 
 	  Say N if you want to disable CPU hotplug.
 
-config SECCOMP
-	bool
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config FAST_SYSCALL_XTENSA
 	bool "Enable fast atomic syscalls"
 	default n

arch/xtensa/mm/init.c

@@ -79,67 +79,32 @@ void __init zones_init(void)
 	free_area_init(max_zone_pfn);
 }
 
-#ifdef CONFIG_HIGHMEM
-static void __init free_area_high(unsigned long pfn, unsigned long end)
-{
-	for (; pfn < end; pfn++)
-		free_highmem_page(pfn_to_page(pfn));
-}
-
 static void __init free_highpages(void)
 {
+#ifdef CONFIG_HIGHMEM
 	unsigned long max_low = max_low_pfn;
-	struct memblock_region *mem, *res;
+	phys_addr_t range_start, range_end;
+	u64 i;
 
-	reset_all_zones_managed_pages();
 	/* set highmem page free */
-	for_each_memblock(memory, mem) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
-		unsigned long start = memblock_region_memory_base_pfn(mem);
+				&range_start, &range_end, NULL) {
-		unsigned long end = memblock_region_memory_end_pfn(mem);
+		unsigned long start = PHYS_PFN(range_start);
+		unsigned long end = PHYS_PFN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)
 			continue;
 
-		if (memblock_is_nomap(mem))
-			continue;
-
 		/* Truncate partial highmem entries */
 		if (start < max_low)
 			start = max_low;
 
-		/* Find and exclude any reserved regions */
+		for (; start < end; start++)
-		for_each_memblock(reserved, res) {
+			free_highmem_page(pfn_to_page(start));
-			unsigned long res_start, res_end;
-
-			res_start = memblock_region_reserved_base_pfn(res);
-			res_end = memblock_region_reserved_end_pfn(res);
-
-			if (res_end < start)
-				continue;
-			if (res_start < start)
-				res_start = start;
-			if (res_start > end)
-				res_start = end;
-			if (res_end > end)
-				res_end = end;
-			if (res_start != start)
-				free_area_high(start, res_start);
-			start = res_end;
-			if (start == end)
-				break;
-		}
-
-		/* And now free anything which remains */
-		if (start < end)
-			free_area_high(start, end);
 	}
-}
-#else
-static void __init free_highpages(void)
-{
-}
 #endif
+}
 
 /*
  * Initialize memory pages.

drivers/acpi/numa/hmat.c

@@ -24,8 +24,15 @@
 #include <linux/mutex.h>
 #include <linux/node.h>
 #include <linux/sysfs.h>
+#include <linux/dax.h>
 
 static u8 hmat_revision;
+static int hmat_disable __initdata;
+
+void __init disable_hmat(void)
+{
+	hmat_disable = 1;
+}
 
 static LIST_HEAD(targets);
 static LIST_HEAD(initiators);
@@ -634,66 +641,6 @@ static void hmat_register_target_perf(struct memory_target *target)
 	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
 }
 
-static void hmat_register_target_device(struct memory_target *target,
-		struct resource *r)
-{
-	/* define a clean / non-busy resource for the platform device */
-	struct resource res = {
-		.start = r->start,
-		.end = r->end,
-		.flags = IORESOURCE_MEM,
-	};
-	struct platform_device *pdev;
-	struct memregion_info info;
-	int rc, id;
-
-	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
-			IORES_DESC_SOFT_RESERVED);
-	if (rc != REGION_INTERSECTS)
-		return;
-
-	id = memregion_alloc(GFP_KERNEL);
-	if (id < 0) {
-		pr_err("memregion allocation failure for %pr\n", &res);
-		return;
-	}
-
-	pdev = platform_device_alloc("hmem", id);
-	if (!pdev) {
-		pr_err("hmem device allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
-	info = (struct memregion_info) {
-		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
-	};
-	rc = platform_device_add_data(pdev, &info, sizeof(info));
-	if (rc < 0) {
-		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	rc = platform_device_add_resources(pdev, &res, 1);
-	if (rc < 0) {
-		pr_err("hmem resource allocation failure for %pr\n", &res);
-		goto out_resource;
-	}
-
-	rc = platform_device_add(pdev);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
-		goto out_resource;
-	}
-
-	return;
-
-out_resource:
-	put_device(&pdev->dev);
-out_pdev:
-	memregion_free(id);
-}
-
 static void hmat_register_target_devices(struct memory_target *target)
 {
 	struct resource *res;
@@ -705,8 +652,11 @@ static void hmat_register_target_devices(struct memory_target *target)
 	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
 		return;
 
-	for (res = target->memregions.child; res; res = res->sibling)
+	for (res = target->memregions.child; res; res = res->sibling) {
-		hmat_register_target_device(target, res);
+		int target_nid = acpi_map_pxm_to_node(target->memory_pxm);
+
+		hmem_register_device(target_nid, res);
+	}
 }
 
 static void hmat_register_target(struct memory_target *target)
@@ -814,7 +764,7 @@ static __init int hmat_init(void)
 	enum acpi_hmat_type i;
 	acpi_status status;
 
-	if (srat_disabled())
+	if (srat_disabled() || hmat_disable)
 		return 0;
 
 	status = acpi_get_table(ACPI_SIG_SRAT, 0, &tbl);

drivers/acpi/numa/srat.c

@@ -27,7 +27,12 @@ static int node_to_pxm_map[MAX_NUMNODES]
 			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
 
 unsigned char acpi_srat_revision __initdata;
-int acpi_numa __initdata;
+static int acpi_numa __initdata;
+
+void __init disable_srat(void)
+{
+	acpi_numa = -1;
+}
 
 int pxm_to_node(int pxm)
 {
@@ -163,7 +168,7 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 void __init bad_srat(void)
 {
 	pr_err("SRAT: SRAT not used.\n");
-	acpi_numa = -1;
+	disable_srat();
 }
 
 int __init srat_disabled(void)

drivers/base/core.c

@@ -3324,7 +3324,7 @@ struct device *device_find_child_by_name(struct device *parent,
 
 	klist_iter_init(&parent->p->klist_children, &i);
 	while ((child = next_device(&i)))
-		if (!strcmp(dev_name(child), name) && get_device(child))
+		if (sysfs_streq(dev_name(child), name) && get_device(child))
 			break;
 	klist_iter_exit(&i);
 	return child;
@@ -4061,22 +4061,21 @@ void device_shutdown(void)
  */
 
 #ifdef CONFIG_PRINTK
-static int
+static void
-create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
+set_dev_info(const struct device *dev, struct dev_printk_info *dev_info)
 {
 	const char *subsys;
-	size_t pos = 0;
+
+	memset(dev_info, 0, sizeof(*dev_info));
 
 	if (dev->class)
 		subsys = dev->class->name;
 	else if (dev->bus)
 		subsys = dev->bus->name;
 	else
-		return 0;
+		return;
 
-	pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys);
+	strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem));
-	if (pos >= hdrlen)
-		goto overflow;
 
 	/*
 	 * Add device identifier DEVICE=:
@@ -4092,41 +4091,28 @@ create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
 			c = 'b';
 		else
 			c = 'c';
-		pos++;
+
-		pos += snprintf(hdr + pos, hdrlen - pos,
+		snprintf(dev_info->device, sizeof(dev_info->device),
-				"DEVICE=%c%u:%u",
+			 "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt));
-				c, MAJOR(dev->devt), MINOR(dev->devt));
 	} else if (strcmp(subsys, "net") == 0) {
 		struct net_device *net = to_net_dev(dev);
 
-		pos++;
+		snprintf(dev_info->device, sizeof(dev_info->device),
-		pos += snprintf(hdr + pos, hdrlen - pos,
+			 "n%u", net->ifindex);
-				"DEVICE=n%u", net->ifindex);
 	} else {
-		pos++;
+		snprintf(dev_info->device, sizeof(dev_info->device),
-		pos += snprintf(hdr + pos, hdrlen - pos,
+			 "+%s:%s", subsys, dev_name(dev));
-				"DEVICE=+%s:%s", subsys, dev_name(dev));
 	}
-
-	if (pos >= hdrlen)
-		goto overflow;
-
-	return pos;
-
-overflow:
-	dev_WARN(dev, "device/subsystem name too long");
-	return 0;
 }
 
 int dev_vprintk_emit(int level, const struct device *dev,
 		     const char *fmt, va_list args)
 {
-	char hdr[128];
+	struct dev_printk_info dev_info;
-	size_t hdrlen;
 
-	hdrlen = create_syslog_header(dev, hdr, sizeof(hdr));
+	set_dev_info(dev, &dev_info);
 
-	return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args);
+	return vprintk_emit(0, level, &dev_info, fmt, args);
 }
 EXPORT_SYMBOL(dev_vprintk_emit);
 

drivers/bus/mvebu-mbus.c

@@ -610,23 +610,23 @@ static unsigned int armada_xp_mbus_win_remap_offset(int win)
 static void __init
 mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
 {
-	struct memblock_region *r;
+	phys_addr_t reg_start, reg_end;
-	uint64_t s = 0;
+	uint64_t i, s = 0;
 
-	for_each_memblock(memory, r) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
 		/*
 		 * This part of the memory is above 4 GB, so we don't
 		 * care for the MBus bridge hole.
 		 */
-		if (r->base >= 0x100000000ULL)
+		if (reg_start >= 0x100000000ULL)
 			continue;
 
 		/*
 		 * The MBus bridge hole is at the end of the RAM under
 		 * the 4 GB limit.
 		 */
-		if (r->base + r->size > s)
+		if (reg_end > s)
-			s = r->base + r->size;
+			s = reg_end;
 	}
 
 	*start = s;

drivers/dax/Kconfig

@@ -35,6 +35,7 @@ config DEV_DAX_PMEM
 config DEV_DAX_HMEM
 	tristate "HMEM DAX: direct access to 'specific purpose' memory"
 	depends on EFI_SOFT_RESERVE
+	select NUMA_KEEP_MEMINFO if (NUMA && X86)
 	default DEV_DAX
 	help
 	  EFI 2.8 platforms, and others, may advertise 'specific purpose'
@@ -48,6 +49,11 @@ config DEV_DAX_HMEM
 
 	  Say M if unsure.
 
+config DEV_DAX_HMEM_DEVICES
+	depends on NUMA_KEEP_MEMINFO # for phys_to_target_node()
+	depends on DEV_DAX_HMEM && DAX=y
+	def_bool y
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX

drivers/dax/Makefile

@@ -2,11 +2,10 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
-obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
-dax_hmem-y := hmem.o
 
 obj-y += pmem/
+obj-y += hmem/

drivers/dax/bus.h

@@ -3,29 +3,33 @@
 #ifndef __DAX_BUS_H__
 #define __DAX_BUS_H__
 #include <linux/device.h>
+#include <linux/range.h>
 
 struct dev_dax;
 struct resource;
 struct dax_device;
 struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
+
+#define IORESOURCE_DAX_STATIC (1UL << 0)
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, int target_node, unsigned int align,
+		struct range *range, int target_node, unsigned int align,
-		unsigned long long flags);
+		unsigned long flags);
 
 enum dev_dax_subsys {
-	DEV_DAX_BUS,
+	DEV_DAX_BUS = 0, /* zeroed dev_dax_data picks this by default */
 	DEV_DAX_CLASS,
 };
 
-struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
+struct dev_dax_data {
-		struct dev_pagemap *pgmap, enum dev_dax_subsys subsys);
+	struct dax_region *dax_region;
+	struct dev_pagemap *pgmap;
+	enum dev_dax_subsys subsys;
+	resource_size_t size;
+	int id;
+};
 
-static inline struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region,
+struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
-		int id, struct dev_pagemap *pgmap)
-{
-	return __devm_create_dev_dax(dax_region, id, pgmap, DEV_DAX_BUS);
-}
 
 /* to be deleted when DEV_DAX_CLASS is removed */
 struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys);
@@ -34,6 +38,8 @@ struct dax_device_driver {
 	struct device_driver drv;
 	struct list_head ids;
 	int match_always;
+	int (*probe)(struct dev_dax *dev);
+	int (*remove)(struct dev_dax *dev);
 };
 
 int __dax_driver_register(struct dax_device_driver *dax_drv,
@@ -44,7 +50,7 @@ void dax_driver_unregister(struct dax_device_driver *dax_drv);
 void kill_dev_dax(struct dev_dax *dev_dax);
 
 #if IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)
-int dev_dax_probe(struct device *dev);
+int dev_dax_probe(struct dev_dax *dev_dax);
 #endif
 
 /*

drivers/dax/dax-private.h

@@ -7,6 +7,7 @@
 
 #include <linux/device.h>
 #include <linux/cdev.h>
+#include <linux/idr.h>
 
 /* private routines between core files */
 struct dax_device;
@@ -22,8 +23,10 @@ void dax_bus_exit(void);
  * @kref: to pin while other agents have a need to do lookups
  * @dev: parent device backing this region
  * @align: allocation and mapping alignment for child dax devices
- * @res: physical address range of the region
+ * @ida: instance id allocator
- * @pfn_flags: identify whether the pfns are paged back or not
+ * @res: resource tree to track instance allocations
+ * @seed: allow userspace to find the first unbound seed device
+ * @youngest: allow userspace to find the most recently created device
  */
 struct dax_region {
 	int id;
@@ -31,8 +34,16 @@ struct dax_region {
 	struct kref kref;
 	struct device *dev;
 	unsigned int align;
+	struct ida ida;
 	struct resource res;
-	unsigned long long pfn_flags;
+	struct device *seed;
+	struct device *youngest;
+};
+
+struct dax_mapping {
+	struct device dev;
+	int range_id;
+	int id;
 };
 
 /**
@@ -41,22 +52,57 @@ struct dax_region {
  * @region - parent region
  * @dax_dev - core dax functionality
  * @target_node: effective numa node if dev_dax memory range is onlined
+ * @id: ida allocated id
+ * @ida: mapping id allocator
  * @dev - device core
  * @pgmap - pgmap for memmap setup / lifetime (driver owned)
- * @dax_mem_res: physical address range of hotadded DAX memory
+ * @nr_range: size of @ranges
- * @dax_mem_name: name for hotadded DAX memory via add_memory_driver_managed()
+ * @ranges: resource-span + pgoff tuples for the instance
  */
 struct dev_dax {
 	struct dax_region *region;
 	struct dax_device *dax_dev;
+	unsigned int align;
 	int target_node;
+	int id;
+	struct ida ida;
 	struct device dev;
-	struct dev_pagemap pgmap;
+	struct dev_pagemap *pgmap;
-	struct resource *dax_kmem_res;
+	int nr_range;
+	struct dev_dax_range {
+		unsigned long pgoff;
+		struct range range;
+		struct dax_mapping *mapping;
+	} *ranges;
 };
 
 static inline struct dev_dax *to_dev_dax(struct device *dev)
 {
 	return container_of(dev, struct dev_dax, dev);
 }
+
+static inline struct dax_mapping *to_dax_mapping(struct device *dev)
+{
+	return container_of(dev, struct dax_mapping, dev);
+}
+
+phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, unsigned long size);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline bool dax_align_valid(unsigned long align)
+{
+	if (align == PUD_SIZE && IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+		return true;
+	if (align == PMD_SIZE && has_transparent_hugepage())
+		return true;
+	if (align == PAGE_SIZE)
+		return true;
+	return false;
+}
+#else
+static inline bool dax_align_valid(unsigned long align)
+{
+	return align == PAGE_SIZE;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif

drivers/dax/device.c

@@ -17,7 +17,6 @@
 static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 		const char *func)
 {
-	struct dax_region *dax_region = dev_dax->region;
 	struct device *dev = &dev_dax->dev;
 	unsigned long mask;
 
@@ -32,7 +31,7 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 		return -EINVAL;
 	}
 
-	mask = dax_region->align - 1;
+	mask = dev_dax->align - 1;
 	if (vma->vm_start & mask || vma->vm_end & mask) {
 		dev_info_ratelimited(dev,
 				"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
@@ -41,14 +40,6 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 		return -EINVAL;
 	}
 
-	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
-			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
-		dev_info_ratelimited(dev,
-				"%s: %s: fail, dax range requires MADV_DONTFORK\n",
-				current->comm, func);
-		return -EINVAL;
-	}
-
 	if (!vma_is_dax(vma)) {
 		dev_info_ratelimited(dev,
 				"%s: %s: fail, vma is not DAX capable\n",
@@ -63,15 +54,22 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
-	struct resource *res = &dev_dax->region->res;
+	int i;
-	phys_addr_t phys;
 
-	phys = pgoff * PAGE_SIZE + res->start;
+	for (i = 0; i < dev_dax->nr_range; i++) {
-	if (phys >= res->start && phys <= res->end) {
+		struct dev_dax_range *dax_range = &dev_dax->ranges[i];
-		if (phys + size - 1 <= res->end)
+		struct range *range = &dax_range->range;
+		unsigned long long pgoff_end;
+		phys_addr_t phys;
+
+		pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
+		if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
+			continue;
+		phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
+		if (phys + size - 1 <= range->end)
 			return phys;
+		break;
 	}
-
 	return -1;
 }
 
@@ -79,21 +77,19 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 				struct vm_fault *vmf, pfn_t *pfn)
 {
 	struct device *dev = &dev_dax->dev;
-	struct dax_region *dax_region;
 	phys_addr_t phys;
 	unsigned int fault_size = PAGE_SIZE;
 
 	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dev_dax->region;
+	if (dev_dax->align > PAGE_SIZE) {
-	if (dax_region->align > PAGE_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
-	if (fault_size != dax_region->align)
+	if (fault_size != dev_dax->align)
 		return VM_FAULT_SIGBUS;
 
 	phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
@@ -102,7 +98,7 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
 	return vmf_insert_mixed(vmf->vma, vmf->address, *pfn);
 }
@@ -112,7 +108,6 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 {
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dev_dax->dev;
-	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	unsigned int fault_size = PMD_SIZE;
@@ -120,22 +115,15 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dev_dax->region;
+	if (dev_dax->align > PMD_SIZE) {
-	if (dax_region->align > PMD_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
-	/* dax pmd mappings require pfn_t_devmap() */
+	if (fault_size < dev_dax->align)
-	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
-		dev_dbg(dev, "region lacks devmap flags\n");
 		return VM_FAULT_SIGBUS;
-	}
+	else if (fault_size > dev_dax->align)
-
-	if (fault_size < dax_region->align)
-		return VM_FAULT_SIGBUS;
-	else if (fault_size > dax_region->align)
 		return VM_FAULT_FALLBACK;
 
 	/* if we are outside of the VMA */
@@ -150,7 +138,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
 	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
 }
@@ -161,7 +149,6 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 {
 	unsigned long pud_addr = vmf->address & PUD_MASK;
 	struct device *dev = &dev_dax->dev;
-	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	unsigned int fault_size = PUD_SIZE;
@@ -170,22 +157,15 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dev_dax->region;
+	if (dev_dax->align > PUD_SIZE) {
-	if (dax_region->align > PUD_SIZE) {
 		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
-			dax_region->align, fault_size);
+			dev_dax->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
-	/* dax pud mappings require pfn_t_devmap() */
+	if (fault_size < dev_dax->align)
-	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
-		dev_dbg(dev, "region lacks devmap flags\n");
 		return VM_FAULT_SIGBUS;
-	}
+	else if (fault_size > dev_dax->align)
-
-	if (fault_size < dax_region->align)
-		return VM_FAULT_SIGBUS;
-	else if (fault_size > dax_region->align)
 		return VM_FAULT_FALLBACK;
 
 	/* if we are outside of the VMA */
@@ -200,7 +180,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
 	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
 }
@@ -280,9 +260,8 @@ static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct file *filp = vma->vm_file;
 	struct dev_dax *dev_dax = filp->private_data;
-	struct dax_region *dax_region = dev_dax->region;
 
-	if (!IS_ALIGNED(addr, dax_region->align))
+	if (!IS_ALIGNED(addr, dev_dax->align))
 		return -EINVAL;
 	return 0;
 }
@@ -291,9 +270,8 @@ static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
 {
 	struct file *filp = vma->vm_file;
 	struct dev_dax *dev_dax = filp->private_data;
-	struct dax_region *dax_region = dev_dax->region;
 
-	return dax_region->align;
+	return dev_dax->align;
 }
 
 static const struct vm_operations_struct dax_vm_ops = {
@@ -332,13 +310,11 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 {
 	unsigned long off, off_end, off_align, len_align, addr_align, align;
 	struct dev_dax *dev_dax = filp ? filp->private_data : NULL;
-	struct dax_region *dax_region;
 
 	if (!dev_dax || addr)
 		goto out;
 
-	dax_region = dev_dax->region;
+	align = dev_dax->align;
-	align = dax_region->align;
 	off = pgoff << PAGE_SHIFT;
 	off_end = off + len;
 	off_align = round_up(off, align);
@@ -412,25 +388,45 @@ static void dev_dax_kill(void *dev_dax)
 	kill_dev_dax(dev_dax);
 }
 
-int dev_dax_probe(struct device *dev)
+int dev_dax_probe(struct dev_dax *dev_dax)
 {
-	struct dev_dax *dev_dax = to_dev_dax(dev);
 	struct dax_device *dax_dev = dev_dax->dax_dev;
-	struct resource *res = &dev_dax->region->res;
+	struct device *dev = &dev_dax->dev;
+	struct dev_pagemap *pgmap;
 	struct inode *inode;
 	struct cdev *cdev;
 	void *addr;
-	int rc;
+	int rc, i;
 
-	/* 1:1 map region resource range to device-dax instance range */
+	pgmap = dev_dax->pgmap;
-	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+	if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1,
-				dev_name(dev))) {
+			"static pgmap / multi-range device conflict\n"))
-		dev_warn(dev, "could not reserve region %pR\n", res);
+		return -EINVAL;
-		return -EBUSY;
+
+	if (!pgmap) {
+		pgmap = devm_kzalloc(dev, sizeof(*pgmap) + sizeof(struct range)
+				* (dev_dax->nr_range - 1), GFP_KERNEL);
+		if (!pgmap)
+			return -ENOMEM;
+		pgmap->nr_range = dev_dax->nr_range;
 	}
 
-	dev_dax->pgmap.type = MEMORY_DEVICE_GENERIC;
+	for (i = 0; i < dev_dax->nr_range; i++) {
-	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
+		struct range *range = &dev_dax->ranges[i].range;
+
+		if (!devm_request_mem_region(dev, range->start,
+					range_len(range), dev_name(dev))) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve range\n",
+					i, range->start, range->end);
+			return -EBUSY;
+		}
+		/* don't update the range for static pgmap */
+		if (!dev_dax->pgmap)
+			pgmap->ranges[i] = *range;
+	}
+
+	pgmap->type = MEMORY_DEVICE_GENERIC;
+	addr = devm_memremap_pages(dev, pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
 
@@ -456,17 +452,15 @@ int dev_dax_probe(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_dax_probe);
 
-static int dev_dax_remove(struct device *dev)
+static int dev_dax_remove(struct dev_dax *dev_dax)
 {
 	/* all probe actions are unwound by devm */
 	return 0;
 }
 
 static struct dax_device_driver device_dax_driver = {
-	.drv = {
+	.probe = dev_dax_probe,
-		.probe = dev_dax_probe,
+	.remove = dev_dax_remove,
-		.remove = dev_dax_remove,
-	},
 	.match_always = 1,
 };
 

drivers/dax/hmem/Makefile

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
+obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device_hmem.o
+
+device_hmem-y := device.o
+dax_hmem-y := hmem.o

drivers/dax/hmem/device.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/dax.h>
+#include <linux/mm.h>
+
+static bool nohmem;
+module_param_named(disable, nohmem, bool, 0444);
+
+void hmem_register_device(int target_nid, struct resource *r)
+{
+	/* define a clean / non-busy resource for the platform device */
+	struct resource res = {
+		.start = r->start,
+		.end = r->end,
+		.flags = IORESOURCE_MEM,
+	};
+	struct platform_device *pdev;
+	struct memregion_info info;
+	int rc, id;
+
+	if (nohmem)
+		return;
+
+	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+			IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
+		return;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		pr_err("memregion allocation failure for %pr\n", &res);
+		return;
+	}
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		pr_err("hmem device allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
+	info = (struct memregion_info) {
+		.target_node = target_nid,
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	rc = platform_device_add_resources(pdev, &res, 1);
+	if (rc < 0) {
+		pr_err("hmem resource allocation failure for %pr\n", &res);
+		goto out_resource;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+		goto out_resource;
+	}
+
+	return;
+
+out_resource:
+	put_device(&pdev->dev);
+out_pdev:
+	memregion_free(id);
+}
+
+static __init int hmem_register_one(struct resource *res, void *data)
+{
+	/*
+	 * If the resource is not a top-level resource it was already
+	 * assigned to a device by the HMAT parsing.
+	 */
+	if (res->parent != &iomem_resource) {
+		pr_info("HMEM: skip %pr, already claimed\n", res);
+		return 0;
+	}
+
+	hmem_register_device(phys_to_target_node(res->start), res);
+
+	return 0;
+}
+
+static __init int hmem_init(void)
+{
+	walk_iomem_res_desc(IORES_DESC_SOFT_RESERVED,
+			IORESOURCE_MEM, 0, -1, NULL, hmem_register_one);
+	return 0;
+}
+
+/*
+ * As this is a fallback for address ranges unclaimed by the ACPI HMAT
+ * parsing it must be at an initcall level greater than hmat_init().
+ */
+late_initcall(hmem_init);

drivers/dax/hmem/hmem.c

@@ -3,30 +3,39 @@
 #include <linux/memregion.h>
 #include <linux/module.h>
 #include <linux/pfn_t.h>
-#include "bus.h"
+#include "../bus.h"
+
+static bool region_idle;
+module_param_named(region_idle, region_idle, bool, 0644);
 
 static int dax_hmem_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct dev_pagemap pgmap = { };
 	struct dax_region *dax_region;
 	struct memregion_info *mri;
+	struct dev_dax_data data;
 	struct dev_dax *dev_dax;
 	struct resource *res;
+	struct range range;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENOMEM;
 
 	mri = dev->platform_data;
-	memcpy(&pgmap.res, res, sizeof(*res));
+	range.start = res->start;
-
+	range.end = res->end;
-	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+	dax_region = alloc_dax_region(dev, pdev->id, &range, mri->target_node,
-			PMD_SIZE, PFN_DEV|PFN_MAP);
+			PMD_SIZE, 0);
 	if (!dax_region)
 		return -ENOMEM;
 
-	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+	data = (struct dev_dax_data) {
+		.dax_region = dax_region,
+		.id = -1,
+		.size = region_idle ? 0 : resource_size(res),
+	};
+	dev_dax = devm_create_dev_dax(&data);
 	if (IS_ERR(dev_dax))
 		return PTR_ERR(dev_dax);
 

drivers/dax/kmem.c

@@ -19,17 +19,28 @@ static const char *kmem_name;
 /* Set if any memory will remain added when the driver will be unloaded. */
 static bool any_hotremove_failed;
 
-int dev_dax_kmem_probe(struct device *dev)
+static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
 {
-	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct dev_dax_range *dax_range = &dev_dax->ranges[i];
-	struct resource *res = &dev_dax->region->res;
+	struct range *range = &dax_range->range;
-	resource_size_t kmem_start;
+
-	resource_size_t kmem_size;
+	/* memory-block align the hotplug range */
-	resource_size_t kmem_end;
+	r->start = ALIGN(range->start, memory_block_size_bytes());
-	struct resource *new_res;
+	r->end = ALIGN_DOWN(range->end + 1, memory_block_size_bytes()) - 1;
-	const char *new_res_name;
+	if (r->start >= r->end) {
+		r->start = range->start;
+		r->end = range->end;
+		return -ENOSPC;
+	}
+	return 0;
+}
+
+static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
+{
+	struct device *dev = &dev_dax->dev;
+	int i, mapped = 0;
+	char *res_name;
 	int numa_node;
-	int rc;
 
 	/*
 	 * Ensure good NUMA information for the persistent memory.
@@ -39,68 +50,80 @@ int dev_dax_kmem_probe(struct device *dev)
 	 */
 	numa_node = dev_dax->target_node;
 	if (numa_node < 0) {
-		dev_warn(dev, "rejecting DAX region %pR with invalid node: %d\n",
+		dev_warn(dev, "rejecting DAX region with invalid node: %d\n",
-			 res, numa_node);
+				numa_node);
 		return -EINVAL;
 	}
 
-	/* Hotplug starting at the beginning of the next block: */
+	res_name = kstrdup(dev_name(dev), GFP_KERNEL);
-	kmem_start = ALIGN(res->start, memory_block_size_bytes());
+	if (!res_name)
-
-	kmem_size = resource_size(res);
-	/* Adjust the size down to compensate for moving up kmem_start: */
-	kmem_size -= kmem_start - res->start;
-	/* Align the size down to cover only complete blocks: */
-	kmem_size &= ~(memory_block_size_bytes() - 1);
-	kmem_end = kmem_start + kmem_size;
-
-	new_res_name = kstrdup(dev_name(dev), GFP_KERNEL);
-	if (!new_res_name)
 		return -ENOMEM;
 
-	/* Region is permanently reserved if hotremove fails. */
+	for (i = 0; i < dev_dax->nr_range; i++) {
-	new_res = request_mem_region(kmem_start, kmem_size, new_res_name);
+		struct resource *res;
-	if (!new_res) {
+		struct range range;
-		dev_warn(dev, "could not reserve region [%pa-%pa]\n",
+		int rc;
-			 &kmem_start, &kmem_end);
+
-		kfree(new_res_name);
+		rc = dax_kmem_range(dev_dax, i, &range);
-		return -EBUSY;
+		if (rc) {
+			dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
+					i, range.start, range.end);
+			continue;
+		}
+
+		/* Region is permanently reserved if hotremove fails. */
+		res = request_mem_region(range.start, range_len(&range), res_name);
+		if (!res) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
+					i, range.start, range.end);
+			/*
+			 * Once some memory has been onlined we can't
+			 * assume that it can be un-onlined safely.
+			 */
+			if (mapped)
+				continue;
+			kfree(res_name);
+			return -EBUSY;
+		}
+
+		/*
+		 * Set flags appropriate for System RAM.  Leave ..._BUSY clear
+		 * so that add_memory() can add a child resource.  Do not
+		 * inherit flags from the parent since it may set new flags
+		 * unknown to us that will break add_memory() below.
+		 */
+		res->flags = IORESOURCE_SYSTEM_RAM;
+
+		/*
+		 * Ensure that future kexec'd kernels will not treat
+		 * this as RAM automatically.
+		 */
+		rc = add_memory_driver_managed(numa_node, range.start,
+				range_len(&range), kmem_name);
+
+		if (rc) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
+					i, range.start, range.end);
+			release_mem_region(range.start, range_len(&range));
+			if (mapped)
+				continue;
+			kfree(res_name);
+			return rc;
+		}
+		mapped++;
 	}
 
-	/*
+	dev_set_drvdata(dev, res_name);
-	 * Set flags appropriate for System RAM.  Leave ..._BUSY clear
-	 * so that add_memory() can add a child resource.  Do not
-	 * inherit flags from the parent since it may set new flags
-	 * unknown to us that will break add_memory() below.
-	 */
-	new_res->flags = IORESOURCE_SYSTEM_RAM;
-
-	/*
-	 * Ensure that future kexec'd kernels will not treat this as RAM
-	 * automatically.
-	 */
-	rc = add_memory_driver_managed(numa_node, new_res->start,
-				       resource_size(new_res), kmem_name);
-	if (rc) {
-		release_resource(new_res);
-		kfree(new_res);
-		kfree(new_res_name);
-		return rc;
-	}
-	dev_dax->dax_kmem_res = new_res;
 
 	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int dev_dax_kmem_remove(struct device *dev)
+static int dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
-	struct dev_dax *dev_dax = to_dev_dax(dev);
+	int i, success = 0;
-	struct resource *res = dev_dax->dax_kmem_res;
+	struct device *dev = &dev_dax->dev;
-	resource_size_t kmem_start = res->start;
+	const char *res_name = dev_get_drvdata(dev);
-	resource_size_t kmem_size = resource_size(res);
-	const char *res_name = res->name;
-	int rc;
 
 	/*
 	 * We have one shot for removing memory, if some memory blocks were not
@@ -108,25 +131,36 @@ static int dev_dax_kmem_remove(struct device *dev)
 	 * there is no way to hotremove this memory until reboot because device
 	 * unbind will succeed even if we return failure.
 	 */
-	rc = remove_memory(dev_dax->target_node, kmem_start, kmem_size);
+	for (i = 0; i < dev_dax->nr_range; i++) {
-	if (rc) {
+		struct range range;
+		int rc;
+
+		rc = dax_kmem_range(dev_dax, i, &range);
+		if (rc)
+			continue;
+
+		rc = remove_memory(dev_dax->target_node, range.start,
+				range_len(&range));
+		if (rc == 0) {
+			release_mem_region(range.start, range_len(&range));
+			success++;
+			continue;
+		}
 		any_hotremove_failed = true;
 		dev_err(dev,
-			"DAX region %pR cannot be hotremoved until the next reboot\n",
+			"mapping%d: %#llx-%#llx cannot be hotremoved until the next reboot\n",
-			res);
+				i, range.start, range.end);
-		return rc;
 	}
 
-	/* Release and free dax resources */
+	if (success >= dev_dax->nr_range) {
-	release_resource(res);
+		kfree(res_name);
-	kfree(res);
+		dev_set_drvdata(dev, NULL);
-	kfree(res_name);
+	}
-	dev_dax->dax_kmem_res = NULL;
 
 	return 0;
 }
 #else
-static int dev_dax_kmem_remove(struct device *dev)
+static int dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
 	/*
 	 * Without hotremove purposely leak the request_mem_region() for the
@@ -141,10 +175,8 @@ static int dev_dax_kmem_remove(struct device *dev)
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 static struct dax_device_driver device_dax_kmem_driver = {
-	.drv = {
+	.probe = dev_dax_kmem_probe,
-		.probe = dev_dax_kmem_probe,
+	.remove = dev_dax_kmem_remove,
-		.remove = dev_dax_kmem_remove,
-	},
 };
 
 static int __init dax_kmem_init(void)

drivers/dax/pmem/compat.c

@@ -22,7 +22,7 @@ static int dax_pmem_compat_probe(struct device *dev)
 		return -ENOMEM;
 
 	device_lock(&dev_dax->dev);
-	rc = dev_dax_probe(&dev_dax->dev);
+	rc = dev_dax_probe(dev_dax);
 	device_unlock(&dev_dax->dev);
 
 	devres_close_group(&dev_dax->dev, dev_dax);

drivers/dax/pmem/core.c

@@ -9,11 +9,12 @@
 
 struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 {
-	struct resource res;
+	struct range range;
 	int rc, id, region_id;
 	resource_size_t offset;
 	struct nd_pfn_sb *pfn_sb;
 	struct dev_dax *dev_dax;
+	struct dev_dax_data data;
 	struct nd_namespace_io *nsio;
 	struct dax_region *dax_region;
 	struct dev_pagemap pgmap = { };
@@ -49,16 +50,23 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 	if (rc != 2)
 		return ERR_PTR(-EINVAL);
 
-	/* adjust the dax_region resource to the start of data */
+	/* adjust the dax_region range to the start of data */
-	memcpy(&res, &pgmap.res, sizeof(res));
+	range = pgmap.range;
-	res.start += offset;
+	range.start += offset,
-	dax_region = alloc_dax_region(dev, region_id, &res,
+	dax_region = alloc_dax_region(dev, region_id, &range,
 			nd_region->target_node, le32_to_cpu(pfn_sb->align),
-			PFN_DEV|PFN_MAP);
+			IORESOURCE_DAX_STATIC);
 	if (!dax_region)
 		return ERR_PTR(-ENOMEM);
 
-	dev_dax = __devm_create_dev_dax(dax_region, id, &pgmap, subsys);
+	data = (struct dev_dax_data) {
+		.dax_region = dax_region,
+		.id = id,
+		.pgmap = &pgmap,
+		.subsys = subsys,
+		.size = range_len(&range),
+	};
+	dev_dax = devm_create_dev_dax(&data);
 
 	/* child dev_dax instances now own the lifetime of the dax_region */
 	dax_region_put(dax_region);

drivers/firmware/efi/x86_fake_mem.c

@@ -38,7 +38,7 @@ void __init efi_fake_memmap_early(void)
 		m_start = mem->range.start;
 		m_end = mem->range.end;
 		for_each_efi_memory_desc(md) {
-			u64 start, end;
+			u64 start, end, size;
 
 			if (md->type != EFI_CONVENTIONAL_MEMORY)
 				continue;
@@ -58,11 +58,17 @@ void __init efi_fake_memmap_early(void)
 			 */
 			start = max(start, m_start);
 			end = min(end, m_end);
+			size = end - start + 1;
 
 			if (end <= start)
 				continue;
-			e820__range_update(start, end - start + 1, E820_TYPE_RAM,
+
-					E820_TYPE_SOFT_RESERVED);
+			/*
+			 * Ensure each efi_fake_mem instance results in
+			 * a unique e820 resource
+			 */
+			e820__range_remove(start, size, E820_TYPE_RAM, 1);
+			e820__range_add(start, size, E820_TYPE_SOFT_RESERVED);
 			e820__update_table(e820_table);
 		}
 	}

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -258,8 +258,8 @@ shmem_writeback(struct drm_i915_gem_object *obj)
 	for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) {
 		struct page *page;
 
-		page = find_lock_entry(mapping, i);
+		page = find_lock_page(mapping, i);
-		if (!page || xa_is_value(page))
+		if (!page)
 			continue;
 
 		if (!page_mapped(page) && clear_page_dirty_for_io(page)) {

drivers/gpu/drm/nouveau/nouveau_dmem.c

@@ -101,7 +101,7 @@ unsigned long nouveau_dmem_page_addr(struct page *page)
 {
 	struct nouveau_dmem_chunk *chunk = nouveau_page_to_chunk(page);
 	unsigned long off = (page_to_pfn(page) << PAGE_SHIFT) -
-				chunk->pagemap.res.start;
+				chunk->pagemap.range.start;
 
 	return chunk->bo->offset + off;
 }
@@ -249,7 +249,9 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 
 	chunk->drm = drm;
 	chunk->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	chunk->pagemap.res = *res;
+	chunk->pagemap.range.start = res->start;
+	chunk->pagemap.range.end = res->end;
+	chunk->pagemap.nr_range = 1;
 	chunk->pagemap.ops = &nouveau_dmem_pagemap_ops;
 	chunk->pagemap.owner = drm->dev;
 
@@ -273,7 +275,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	list_add(&chunk->list, &drm->dmem->chunks);
 	mutex_unlock(&drm->dmem->mutex);
 
-	pfn_first = chunk->pagemap.res.start >> PAGE_SHIFT;
+	pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT;
 	page = pfn_to_page(pfn_first);
 	spin_lock(&drm->dmem->lock);
 	for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) {
@@ -294,8 +296,7 @@ out_bo_unpin:
 out_bo_free:
 	nouveau_bo_ref(NULL, &chunk->bo);
 out_release:
-	release_mem_region(chunk->pagemap.res.start,
+	release_mem_region(chunk->pagemap.range.start, range_len(&chunk->pagemap.range));
-			   resource_size(&chunk->pagemap.res));
 out_free:
 	kfree(chunk);
 out:
@@ -382,8 +383,8 @@ nouveau_dmem_fini(struct nouveau_drm *drm)
 		nouveau_bo_ref(NULL, &chunk->bo);
 		list_del(&chunk->list);
 		memunmap_pages(&chunk->pagemap);
-		release_mem_region(chunk->pagemap.res.start,
+		release_mem_region(chunk->pagemap.range.start,
-				   resource_size(&chunk->pagemap.res));
+				   range_len(&chunk->pagemap.range));
 		kfree(chunk);
 	}
 

drivers/irqchip/irq-gic-v3-its.c

@@ -2198,7 +2198,7 @@ static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
 
 	addr_end = addr + size - 1;
 
-	for_each_reserved_mem_region(i, &start, &end) {
+	for_each_reserved_mem_range(i, &start, &end) {
 		if (addr >= start && addr_end <= end)
 			return true;
 	}

drivers/nvdimm/badrange.c

@@ -211,7 +211,7 @@ static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
 }
 
 static void badblocks_populate(struct badrange *badrange,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct badrange_entry *bre;
 
@@ -222,34 +222,34 @@ static void badblocks_populate(struct badrange *badrange,
 		u64 bre_end = bre->start + bre->length - 1;
 
 		/* Discard intervals with no intersection */
-		if (bre_end < res->start)
+		if (bre_end < range->start)
 			continue;
-		if (bre->start >  res->end)
+		if (bre->start > range->end)
 			continue;
 		/* Deal with any overlap after start of the namespace */
-		if (bre->start >= res->start) {
+		if (bre->start >= range->start) {
 			u64 start = bre->start;
 			u64 len;
 
-			if (bre_end <= res->end)
+			if (bre_end <= range->end)
 				len = bre->length;
 			else
-				len = res->start + resource_size(res)
+				len = range->start + range_len(range)
 					- bre->start;
-			__add_badblock_range(bb, start - res->start, len);
+			__add_badblock_range(bb, start - range->start, len);
 			continue;
 		}
 		/*
 		 * Deal with overlap for badrange starting before
 		 * the namespace.
 		 */
-		if (bre->start < res->start) {
+		if (bre->start < range->start) {
 			u64 len;
 
-			if (bre_end < res->end)
+			if (bre_end < range->end)
-				len = bre->start + bre->length - res->start;
+				len = bre->start + bre->length - range->start;
 			else
-				len = resource_size(res);
+				len = range_len(range);
 			__add_badblock_range(bb, 0, len);
 		}
 	}
@@ -267,7 +267,7 @@ static void badblocks_populate(struct badrange *badrange,
  * and add badblocks entries for all matching sub-ranges
  */
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct nvdimm_bus *nvdimm_bus;
 
@@ -279,7 +279,7 @@ void nvdimm_badblocks_populate(struct nd_region *nd_region,
 	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
 
 	nvdimm_bus_lock(&nvdimm_bus->dev);
-	badblocks_populate(&nvdimm_bus->badrange, bb, res);
+	badblocks_populate(&nvdimm_bus->badrange, bb, range);
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
 }
 EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);