Merge tag 'memblock-v5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock

Pull memblock updates from Mike Rapoport:
 "Test suite and a small cleanup:

   - A small cleanup of unused variable in __next_mem_pfn_range_in_zone

   - Initial test suite to simulate memblock behaviour in userspace"

* tag 'memblock-v5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock: (27 commits)
  memblock tests: Add TODO and README files
  memblock tests: Add memblock_alloc_try_nid tests for bottom up
  memblock tests: Add memblock_alloc_try_nid tests for top down
  memblock tests: Add memblock_alloc_from tests for bottom up
  memblock tests: Add memblock_alloc_from tests for top down
  memblock tests: Add memblock_alloc tests for bottom up
  memblock tests: Add memblock_alloc tests for top down
  memblock tests: Add simulation of physical memory
  memblock tests: Split up reset_memblock function
  memblock tests: Fix testing with 32-bit physical addresses
  memblock: __next_mem_pfn_range_in_zone: remove unneeded local variable nid
  memblock tests: Add memblock_free tests
  memblock tests: Add memblock_add_node test
  memblock tests: Add memblock_remove tests
  memblock tests: Add memblock_reserve tests
  memblock tests: Add memblock_add tests
  memblock tests: Add memblock reset function
  memblock tests: Add skeleton of the memblock simulator
  tools/include: Add debugfs.h stub
  tools/include: Add pfn.h stub
  ...

MAINTAINERS

@@ -12550,6 +12550,7 @@ S:	Maintained
 F:	Documentation/core-api/boot-time-mm.rst
 F:	include/linux/memblock.h
 F:	mm/memblock.c
+F:	tools/testing/memblock/
 
 MEMORY CONTROLLER DRIVERS
 M:	Krzysztof Kozlowski <krzk@kernel.org>

mm/memblock.c

@@ -1284,11 +1284,10 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 {
 	int zone_nid = zone_to_nid(zone);
 	phys_addr_t spa, epa;
-	int nid;
 
 	__next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
 			 &memblock.memory, &memblock.reserved,
-			 &spa, &epa, &nid);
+			 &spa, &epa, NULL);
 
 	while (*idx != U64_MAX) {
 		unsigned long epfn = PFN_DOWN(epa);
@@ -1315,7 +1314,7 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 
 		__next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
 				 &memblock.memory, &memblock.reserved,
-				 &spa, &epa, &nid);
+				 &spa, &epa, NULL);
 	}
 
 	/* signal end of iteration */

tools/include/linux/atomic.h

@@ -4,6 +4,8 @@
 
 #include <asm/atomic.h>
 
+void atomic_long_set(atomic_long_t *v, long i);
+
 /* atomic_cmpxchg_relaxed */
 #ifndef atomic_cmpxchg_relaxed
 #define  atomic_cmpxchg_relaxed		atomic_cmpxchg

tools/include/linux/cache.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_CACHE_H
+#define _TOOLS_LINUX_CACHE_H
+
+#define L1_CACHE_SHIFT		5
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define SMP_CACHE_BYTES L1_CACHE_BYTES
+
+#endif

tools/include/linux/debugfs.h

@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_DEBUGFS_H
+#define _TOOLS_DEBUGFS_H
+
+#endif

tools/include/linux/gfp.h

@@ -1,4 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_INCLUDE_LINUX_GFP_H
 #define _TOOLS_INCLUDE_LINUX_GFP_H
 
+#include <linux/types.h>
+
+#define __GFP_BITS_SHIFT 26
+#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
+
+#define __GFP_HIGH		0x20u
+#define __GFP_IO		0x40u
+#define __GFP_FS		0x80u
+#define __GFP_NOWARN		0x200u
+#define __GFP_ZERO		0x8000u
+#define __GFP_ATOMIC		0x80000u
+#define __GFP_ACCOUNT		0x100000u
+#define __GFP_DIRECT_RECLAIM	0x400000u
+#define __GFP_KSWAPD_RECLAIM	0x2000000u
+
+#define __GFP_RECLAIM	(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM)
+
+#define GFP_ZONEMASK	0x0fu
+#define GFP_ATOMIC	(__GFP_HIGH | __GFP_ATOMIC | __GFP_KSWAPD_RECLAIM)
+#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+
+static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
+{
+	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
+}
+
 #endif /* _TOOLS_INCLUDE_LINUX_GFP_H */

tools/include/linux/io.h

@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_IO_H
+#define _TOOLS_IO_H
+
+#endif

tools/include/linux/kernel.h

@@ -15,6 +15,8 @@
 #define UINT_MAX	(~0U)
 #endif
 
+#define _RET_IP_		((unsigned long)__builtin_return_address(0))
+
 #define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
 #define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
@@ -51,6 +53,10 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
+#define max_t(type, x, y)	max((type)x, (type)y)
+#define min_t(type, x, y)	min((type)x, (type)y)
+#define clamp(val, lo, hi)	min((typeof(val))max(val, lo), hi)
+
 #ifndef BUG_ON
 #ifdef NDEBUG
 #define BUG_ON(cond) do { if (cond) {} } while (0)

tools/include/linux/mm.h

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_MM_H
+#define _TOOLS_LINUX_MM_H
+
+#include <linux/mmzone.h>
+#include <uapi/linux/const.h>
+
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE - 1))
+
+#define PHYS_ADDR_MAX	(~(phys_addr_t)0)
+
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+#define ALIGN(x, a)			__ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a)		__ALIGN_KERNEL((x) - ((a) - 1), (a))
+
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
+#define __va(x) ((void *)((unsigned long)(x)))
+#define __pa(x) ((unsigned long)(x))
+
+#define pfn_to_page(pfn) ((void *)((pfn) * PAGE_SIZE))
+
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+
+void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
+
+static inline void totalram_pages_inc(void)
+{
+}
+
+static inline void totalram_pages_add(long count)
+{
+}
+
+#endif

tools/include/linux/pfn.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PFN_H_
+#define _TOOLS_LINUX_PFN_H_
+
+#include <linux/mm.h>
+
+#define PFN_UP(x)	(((x) + PAGE_SIZE - 1) >> PAGE_SHIFT)
+#define PFN_DOWN(x)	((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x)	((phys_addr_t)(x) << PAGE_SHIFT)
+#endif

tools/include/linux/slab.h

@@ -1,20 +1,31 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef SLAB_H
-#define SLAB_H
+#ifndef _TOOLS_SLAB_H
+#define _TOOLS_SLAB_H
 
 #include <linux/types.h>
 #include <linux/gfp.h>
 
-#define SLAB_HWCACHE_ALIGN 1
 #define SLAB_PANIC 2
 #define SLAB_RECLAIM_ACCOUNT    0x00020000UL            /* Objects are reclaimable */
 
-void *kmalloc(size_t size, gfp_t);
-void kfree(void *);
+#define kzalloc_node(size, flags, node) kmalloc(size, flags)
+
+void *kmalloc(size_t size, gfp_t gfp);
+void kfree(void *p);
+
+bool slab_is_available(void);
+
+enum slab_state {
+	DOWN,
+	PARTIAL,
+	PARTIAL_NODE,
+	UP,
+	FULL
+};
 
 static inline void *kzalloc(size_t size, gfp_t gfp)
 {
-        return kmalloc(size, gfp | __GFP_ZERO);
+	return kmalloc(size, gfp | __GFP_ZERO);
 }
 
 void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
@@ -24,4 +35,4 @@ struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
 			unsigned int align, unsigned int flags,
 			void (*ctor)(void *));
 
-#endif		/* SLAB_H */
+#endif		/* _TOOLS_SLAB_H */

tools/include/linux/types.h

@@ -63,10 +63,20 @@ typedef __u64 __bitwise __be64;
 typedef __u16 __bitwise __sum16;
 typedef __u32 __bitwise __wsum;
 
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+typedef u64 phys_addr_t;
+#else
+typedef u32 phys_addr_t;
+#endif
+
 typedef struct {
 	int counter;
 } atomic_t;
 
+typedef struct {
+	long counter;
+} atomic_long_t;
+
 #ifndef __aligned_u64
 # define __aligned_u64 __u64 __attribute__((aligned(8)))
 #endif

tools/lib/slab.c

@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+
+#include <urcu/uatomic.h>
+#include <linux/slab.h>
+#include <malloc.h>
+#include <linux/gfp.h>
+
+int kmalloc_nr_allocated;
+int kmalloc_verbose;
+
+void *kmalloc(size_t size, gfp_t gfp)
+{
+	void *ret;
+
+	if (!(gfp & __GFP_DIRECT_RECLAIM))
+		return NULL;
+
+	ret = malloc(size);
+	uatomic_inc(&kmalloc_nr_allocated);
+	if (kmalloc_verbose)
+		printf("Allocating %p from malloc\n", ret);
+	if (gfp & __GFP_ZERO)
+		memset(ret, 0, size);
+	return ret;
+}
+
+void kfree(void *p)
+{
+	if (!p)
+		return;
+	uatomic_dec(&kmalloc_nr_allocated);
+	if (kmalloc_verbose)
+		printf("Freeing %p to malloc\n", p);
+	free(p);
+}

tools/testing/memblock/.gitignore

@@ -0,0 +1,4 @@
+main
+memblock.c
+linux/memblock.h
+asm/cmpxchg.h

tools/testing/memblock/Makefile

@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Memblock simulator requires AddressSanitizer (libasan) and liburcu development
+# packages installed
+CFLAGS += -I. -I../../include -Wall -O2 -fsanitize=address \
+	  -fsanitize=undefined -D CONFIG_PHYS_ADDR_T_64BIT
+LDFLAGS += -fsanitize=address -fsanitize=undefined
+TARGETS = main
+TEST_OFILES = tests/alloc_nid_api.o tests/alloc_helpers_api.o tests/alloc_api.o \
+		  tests/basic_api.o tests/common.o
+DEP_OFILES = memblock.o lib/slab.o mmzone.o slab.o
+OFILES = main.o $(DEP_OFILES) $(TEST_OFILES)
+EXTR_SRC = ../../../mm/memblock.c
+
+ifeq ($(BUILD), 32)
+	CFLAGS += -m32
+	LDFLAGS += -m32
+endif
+
+# Process user parameters
+include scripts/Makefile.include
+
+main: $(OFILES)
+
+$(OFILES): include
+
+include: ../../../include/linux/memblock.h ../../include/linux/*.h \
+	../../include/asm/*.h
+
+	@mkdir -p linux
+	test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h
+	test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h
+
+memblock.c: $(EXTR_SRC)
+	test -L memblock.c || ln -s $(EXTR_SRC) memblock.c
+
+clean:
+	$(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h
+
+help:
+	@echo  'Memblock simulator'
+	@echo  ''
+	@echo  'Available targets:'
+	@echo  '  main		  - Build the memblock simulator'
+	@echo  '  clean		  - Remove generated files and symlinks in the directory'
+	@echo  ''
+	@echo  'Configuration:'
+	@echo  '  make NUMA=1               - simulate enabled NUMA'
+	@echo  '  make MOVABLE_NODE=1       - override `movable_node_is_enabled`'
+	@echo  '                              definition to simulate movable NUMA nodes'
+	@echo  '  make 32BIT_PHYS_ADDR_T=1  - Use 32 bit physical addresses'
+
+vpath %.c ../../lib
+
+.PHONY: clean include help

tools/testing/memblock/README

@@ -0,0 +1,107 @@
+==================
+Memblock simulator
+==================
+
+Introduction
+============
+
+Memblock is a boot time memory allocator[1] that manages memory regions before
+the actual memory management is initialized. Its APIs allow to register physical
+memory regions, mark them as available or reserved, allocate a block of memory
+within the requested range and/or in specific NUMA node, and many more.
+
+Because it is used so early in the booting process, testing and debugging it is
+difficult. This test suite, usually referred as memblock simulator, is
+an attempt at testing the memblock mechanism. It runs one monolithic test that
+consist of a series of checks that exercise both the basic operations and
+allocation functionalities of memblock. The main data structure of the boot time
+memory allocator is initialized at the build time, so the checks here reuse its
+instance throughout the duration of the test. To ensure that tests don't affect
+each other, region arrays are reset in between.
+
+As this project uses the actual memblock code and has to run in user space,
+some of the kernel definitions were stubbed by the initial commit that
+introduced memblock simulator (commit 16802e55dea9 ("memblock tests: Add
+skeleton of the memblock simulator")) and a few preparation commits just
+before it. Most of them don't match the kernel implementation, so one should
+consult them first before making any significant changes to the project.
+
+Usage
+=====
+
+To run the tests, build the main target and run it:
+
+$ make && ./main
+
+A successful run produces no output. It is also possible to override different
+configuration parameters. For example, to simulate enabled NUMA, use:
+
+$ make NUMA=1
+
+For the full list of options, see `make help`.
+
+Project structure
+=================
+
+The project has one target, main, which calls a group of checks for basic and
+allocation functions. Tests for each group are defined in dedicated files, as it
+can be seen here:
+
+memblock
+|-- asm       ------------------,
+|-- lib                         |-- implement function and struct stubs
+|-- linux     ------------------'
+|-- scripts
+|    |-- Makefile.include        -- handles `make` parameters
+|-- tests
+|    |-- alloc_api.(c|h)         -- memblock_alloc tests
+|    |-- alloc_helpers_api.(c|h) -- memblock_alloc_from tests
+|    |-- alloc_nid_api.(c|h)     -- memblock_alloc_try_nid tests
+|    |-- basic_api.(c|h)         -- memblock_add/memblock_reserve/... tests
+|    |-- common.(c|h)            -- helper functions for resetting memblock;
+|-- main.c        --------------.   dummy physical memory definition
+|-- Makefile                     `- test runner
+|-- README
+|-- TODO
+|-- .gitignore
+
+Simulating physical memory
+==========================
+
+Some allocation functions clear the memory in the process, so it is required for
+memblock to track valid memory ranges. To achieve this, the test suite registers
+with memblock memory stored by test_memory struct. It is a small wrapper that
+points to a block of memory allocated via malloc. For each group of allocation
+tests, dummy physical memory is allocated, added to memblock, and then released
+at the end of the test run. The structure of a test runner checking allocation
+functions is as follows:
+
+int memblock_alloc_foo_checks(void)
+{
+	reset_memblock_attributes();     /* data structure reset */
+	dummy_physical_memory_init();    /* allocate and register memory */
+
+	(...allocation checks...)
+
+	dummy_physical_memory_cleanup(); /* free the memory */
+}
+
+There's no need to explicitly free the dummy memory from memblock via
+memblock_free() call. The entry will be erased by reset_memblock_regions(),
+called at the beginning of each test.
+
+Known issues
+============
+
+1. Requesting a specific NUMA node via memblock_alloc_node() does not work as
+   intended. Once the fix is in place, tests for this function can be added.
+
+2. Tests for memblock_alloc_low() can't be easily implemented. The function uses
+   ARCH_LOW_ADDRESS_LIMIT marco, which can't be changed to point at the low
+   memory of the memory_block.
+
+References
+==========
+
+1. Boot time memory management documentation page:
+   https://www.kernel.org/doc/html/latest/core-api/boot-time-mm.html

tools/testing/memblock/TODO

@@ -0,0 +1,28 @@
+TODO
+=====
+
+1. Add verbose output (e.g., what is being tested and how many tests cases are
+   passing)
+
+2. Add flags to Makefile:
+   + verbosity level
+   + enable memblock_dbg() messages (i.e. pass "-D CONFIG_DEBUG_MEMORY_INIT"
+     flag)
+
+3. Add tests trying to memblock_add() or memblock_reserve() 129th region.
+   This will trigger memblock_double_array(), make sure it succeeds.
+   *Important:* These tests require valid memory ranges, use dummy physical
+                memory block from common.c to implement them. It is also very
+                likely that the current MEM_SIZE won't be enough for these
+                test cases. Use realloc to adjust the size accordingly.
+
+4. Add test cases using this functions (implement them for both directions):
+   + memblock_alloc_raw()
+   + memblock_alloc_exact_nid_raw()
+   + memblock_alloc_try_nid_raw()
+
+5. Add tests for memblock_alloc_node() to check if the correct NUMA node is set
+   for the new region
+
+6. Update comments in tests/basic_api.c to match the style used in
+   tests/alloc_*.c

tools/testing/memblock/asm/dma.h

@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_DMA_H
+#define _TOOLS_DMA_H
+
+#endif

tools/testing/memblock/internal.h

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _MM_INTERNAL_H
+#define _MM_INTERNAL_H
+
+struct page {};
+
+void memblock_free_pages(struct page *page, unsigned long pfn,
+			 unsigned int order)
+{
+}
+
+#endif

tools/testing/memblock/lib/slab.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/slab.h>
+
+enum slab_state slab_state;
+
+bool slab_is_available(void)
+{
+	return slab_state >= UP;
+}