Merge patch series "riscv: mm: Extend mappable memory up to hint address"

Charlie Jenkins <charlie@rivosinc.com> says:

On riscv, mmap currently returns an address from the largest address
space that can fit entirely inside of the hint address. This makes it
such that the hint address is almost never returned. This patch raises
the mappable area up to and including the hint address. This allows mmap
to often return the hint address, which allows a performance improvement
over searching for a valid address as well as making the behavior more
similar to other architectures.

Note that a previous patch introduced stronger semantics compared to
other architectures for riscv mmap. On riscv, mmap will not use bits in
the upper bits of the virtual address depending on the hint address. On
other architectures, a random address is returned in the address space
requested. On all architectures the hint address will be returned if it
is available. This allows riscv applications to configure how many bits
in the virtual address should be left empty. This has the two benefits
of being able to request address spaces that are smaller than the
default and doesn't require the application to know the page table
layout of riscv.

* b4-shazam-merge:
  docs: riscv: Define behavior of mmap
  selftests: riscv: Generalize mm selftests
  riscv: mm: Use hint address in mmap if available

Link: https://lore.kernel.org/r/20240130-use_mmap_hint_address-v3-0-8a655cfa8bcb@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

5 files changed, 83 insertions, 113 deletions

diff --git a/Documentation/arch/riscv/vm-layout.rst b/Documentation/arch/riscv/vm-layout.rst
index 69ff6da1dbf8f..e476b4386bd9d 100644
--- a/Documentation/arch/riscv/vm-layout.rst
+++ b/Documentation/arch/riscv/vm-layout.rst
@@ -144,14 +144,8 @@ passing 0 into the hint address parameter of mmap. On CPUs with an address space
 smaller than sv48, the CPU maximum supported address space will be the default.
 
 Software can "opt-in" to receiving VAs from another VA space by providing
-a hint address to mmap. A hint address passed to mmap will cause the largest
-address space that fits entirely into the hint to be used, unless there is no
-space left in the address space. If there is no space available in the requested
-address space, an address in the next smallest available address space will be
-returned.
-
-For example, in order to obtain 48-bit VA space, a hint address greater than
-:code:`1 << 47` must be provided. Note that this is 47 due to sv48 userspace
-ending at :code:`1 << 47` and the addresses beyond this are reserved for the
-kernel. Similarly, to obtain 57-bit VA space addresses, a hint address greater
-than or equal to :code:`1 << 56` must be provided.
+a hint address to mmap. When a hint address is passed to mmap, the returned
+address will never use more bits than the hint address. For example, if a hint
+address of `1 << 40` is passed to mmap, a valid returned address will never use
+bits 41 through 63. If no mappable addresses are available in that range, mmap
+will return `MAP_FAILED`.
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index a8509cc31ab25..0d13b4497b017 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -14,22 +14,16 @@
 
 #include <asm/ptrace.h>
 
-#ifdef CONFIG_64BIT
-#define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
-#define STACK_TOP_MAX		TASK_SIZE
-
 #define arch_get_mmap_end(addr, len, flags)			\
 ({								\
 	unsigned long mmap_end;					\
 	typeof(addr) _addr = (addr);				\
-	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+	if ((_addr) == 0 ||					\
+	    (IS_ENABLED(CONFIG_COMPAT) && is_compat_task()) ||	\
+	    ((_addr + len) > BIT(VA_BITS - 1)))			\
 		mmap_end = STACK_TOP_MAX;			\
-	else if ((_addr) >= VA_USER_SV57)			\
-		mmap_end = STACK_TOP_MAX;			\
-	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
-		mmap_end = VA_USER_SV48;			\
 	else							\
-		mmap_end = VA_USER_SV39;			\
+		mmap_end = (_addr + len);			\
 	mmap_end;						\
 })
 
@@ -39,17 +33,18 @@
 	typeof(addr) _addr = (addr);				\
 	typeof(base) _base = (base);				\
 	unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base);	\
-	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+	if ((_addr) == 0 ||					\
+	    (IS_ENABLED(CONFIG_COMPAT) && is_compat_task()) ||	\
+	    ((_addr + len) > BIT(VA_BITS - 1)))			\
 		mmap_base = (_base);				\
-	else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) \
-		mmap_base = VA_USER_SV57 - rnd_gap;		\
-	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
-		mmap_base = VA_USER_SV48 - rnd_gap;		\
 	else							\
-		mmap_base = VA_USER_SV39 - rnd_gap;		\
+		mmap_base = (_addr + len) - rnd_gap;		\
 	mmap_base;						\
 })
 
+#ifdef CONFIG_64BIT
+#define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
+#define STACK_TOP_MAX		TASK_SIZE_64
 #else
 #define DEFAULT_MAP_WINDOW	TASK_SIZE
 #define STACK_TOP_MAX		TASK_SIZE
diff --git a/tools/testing/selftests/riscv/mm/mmap_bottomup.c b/tools/testing/selftests/riscv/mm/mmap_bottomup.c
index 1757d19ca89b1..7f7d3eb8b9c92 100644
--- a/tools/testing/selftests/riscv/mm/mmap_bottomup.c
+++ b/tools/testing/selftests/riscv/mm/mmap_bottomup.c
@@ -6,30 +6,9 @@
 
 TEST(infinite_rlimit)
 {
-// Only works on 64 bit
-#if __riscv_xlen == 64
-	struct addresses mmap_addresses;
-
 	EXPECT_EQ(BOTTOM_UP, memory_layout());
 
-	do_mmaps(&mmap_addresses);
-
-	EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr);
-
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr);
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr);
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr);
-	EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr);
-#endif
+	TEST_MMAPS;
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/riscv/mm/mmap_default.c b/tools/testing/selftests/riscv/mm/mmap_default.c
index c63c60b9397e7..2ba3ec9900064 100644
--- a/tools/testing/selftests/riscv/mm/mmap_default.c
+++ b/tools/testing/selftests/riscv/mm/mmap_default.c
@@ -6,30 +6,9 @@
 
 TEST(default_rlimit)
 {
-// Only works on 64 bit
-#if __riscv_xlen == 64
-	struct addresses mmap_addresses;
-
 	EXPECT_EQ(TOP_DOWN, memory_layout());
 
-	do_mmaps(&mmap_addresses);
-
-	EXPECT_NE(MAP_FAILED, mmap_addresses.no_hint);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_37_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_38_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_46_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_47_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_55_addr);
-	EXPECT_NE(MAP_FAILED, mmap_addresses.on_56_addr);
-
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.no_hint);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_37_addr);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_38_addr);
-	EXPECT_GT(1UL << 38, (unsigned long)mmap_addresses.on_46_addr);
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_47_addr);
-	EXPECT_GT(1UL << 47, (unsigned long)mmap_addresses.on_55_addr);
-	EXPECT_GT(1UL << 56, (unsigned long)mmap_addresses.on_56_addr);
-#endif
+	TEST_MMAPS;
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h
index 2e0db9c5be6c3..3b29ca3bb3d40 100644
--- a/tools/testing/selftests/riscv/mm/mmap_test.h
+++ b/tools/testing/selftests/riscv/mm/mmap_test.h
@@ -4,63 +4,86 @@
 #include <sys/mman.h>
 #include <sys/resource.h>
 #include <stddef.h>
+#include <strings.h>
+#include "../../kselftest_harness.h"
 
 #define TOP_DOWN 0
 #define BOTTOM_UP 1
 
-struct addresses {
-	int *no_hint;
-	int *on_37_addr;
-	int *on_38_addr;
-	int *on_46_addr;
-	int *on_47_addr;
-	int *on_55_addr;
-	int *on_56_addr;
+#if __riscv_xlen == 64
+uint64_t random_addresses[] = {
+	0x19764f0d73b3a9f0, 0x016049584cecef59, 0x3580bdd3562f4acd,
+	0x1164219f20b17da0, 0x07d97fcb40ff2373, 0x76ec528921272ee7,
+	0x4dd48c38a3de3f70, 0x2e11415055f6997d, 0x14b43334ac476c02,
+	0x375a60795aff19f6, 0x47f3051725b8ee1a, 0x4e697cf240494a9f,
+	0x456b59b5c2f9e9d1, 0x101724379d63cb96, 0x7fe9ad31619528c1,
+	0x2f417247c495c2ea, 0x329a5a5b82943a5e, 0x06d7a9d6adcd3827,
+	0x327b0b9ee37f62d5, 0x17c7b1851dfd9b76, 0x006ebb6456ec2cd9,
+	0x00836cd14146a134, 0x00e5c4dcde7126db, 0x004c29feadf75753,
+	0x00d8b20149ed930c, 0x00d71574c269387a, 0x0006ebe4a82acb7a,
+	0x0016135df51f471b, 0x00758bdb55455160, 0x00d0bdd949b13b32,
+	0x00ecea01e7c5f54b, 0x00e37b071b9948b1, 0x0011fdd00ff57ab3,
+	0x00e407294b52f5ea, 0x00567748c200ed20, 0x000d073084651046,
+	0x00ac896f4365463c, 0x00eb0d49a0b26216, 0x0066a2564a982a31,
+	0x002e0d20237784ae, 0x0000554ff8a77a76, 0x00006ce07a54c012,
+	0x000009570516d799, 0x00000954ca15b84d, 0x0000684f0d453379,
+	0x00002ae5816302b5, 0x0000042403fb54bf, 0x00004bad7392bf30,
+	0x00003e73bfa4b5e3, 0x00005442c29978e0, 0x00002803f11286b6,
+	0x000073875d745fc6, 0x00007cede9cb8240, 0x000027df84cc6a4f,
+	0x00006d7e0e74242a, 0x00004afd0b836e02, 0x000047d0e837cd82,
+	0x00003b42405efeda, 0x00001531bafa4c95, 0x00007172cae34ac4,
+};
+#else
+uint32_t random_addresses[] = {
+	0x8dc302e0, 0x929ab1e0, 0xb47683ba, 0xea519c73, 0xa19f1c90, 0xc49ba213,
+	0x8f57c625, 0xadfe5137, 0x874d4d95, 0xaa20f09d, 0xcf21ebfc, 0xda7737f1,
+	0xcedf392a, 0x83026c14, 0xccedca52, 0xc6ccf826, 0xe0cd9415, 0x997472ca,
+	0xa21a44c1, 0xe82196f5, 0xa23fd66b, 0xc28d5590, 0xd009cdce, 0xcf0be646,
+	0x8fc8c7ff, 0xe2a85984, 0xa3d3236b, 0x89a0619d, 0xc03db924, 0xb5d4cc1b,
+	0xb96ee04c, 0xd191da48, 0xb432a000, 0xaa2bebbc, 0xa2fcb289, 0xb0cca89b,
+	0xb0c18d6a, 0x88f58deb, 0xa4d42d1c, 0xe4d74e86, 0x99902b09, 0x8f786d31,
+	0xbec5e381, 0x9a727e65, 0xa9a65040, 0xa880d789, 0x8f1b335e, 0xfc821c1e,
+	0x97e34be4, 0xbbef84ed, 0xf447d197, 0xfd7ceee2, 0xe632348d, 0xee4590f4,
+	0x958992a5, 0xd57e05d6, 0xfd240970, 0xc5b0dcff, 0xd96da2c2, 0xa7ae041d,
 };
+#endif
 
 // Only works on 64 bit
 #if __riscv_xlen == 64
-static inline void do_mmaps(struct addresses *mmap_addresses)
-{
-	/*
-	 * Place all of the hint addresses on the boundaries of mmap
-	 * sv39, sv48, sv57
-	 * User addresses end at 1<<38, 1<<47, 1<<56 respectively
-	 */
-	void *on_37_bits = (void *)(1UL << 37);
-	void *on_38_bits = (void *)(1UL << 38);
-	void *on_46_bits = (void *)(1UL << 46);
-	void *on_47_bits = (void *)(1UL << 47);
-	void *on_55_bits = (void *)(1UL << 55);
-	void *on_56_bits = (void *)(1UL << 56);
+#define PROT (PROT_READ | PROT_WRITE)
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS)
 
-	int prot = PROT_READ | PROT_WRITE;
-	int flags = MAP_PRIVATE | MAP_ANONYMOUS;
+/* mmap must return a value that doesn't use more bits than the hint address. */
+static inline unsigned long get_max_value(unsigned long input)
+{
+	unsigned long max_bit = (1UL << (((sizeof(unsigned long) * 8) - 1 -
+					  __builtin_clzl(input))));
 
-	mmap_addresses->no_hint =
-		mmap(NULL, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_37_addr =
-		mmap(on_37_bits, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_38_addr =
-		mmap(on_38_bits, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_46_addr =
-		mmap(on_46_bits, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_47_addr =
-		mmap(on_47_bits, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_55_addr =
-		mmap(on_55_bits, 5 * sizeof(int), prot, flags, 0, 0);
-	mmap_addresses->on_56_addr =
-		mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0);
+	return max_bit + (max_bit - 1);
 }
+
+#define TEST_MMAPS                                                            \
+	({                                                                    \
+		void *mmap_addr;                                              \
+		for (int i = 0; i < ARRAY_SIZE(random_addresses); i++) {      \
+			mmap_addr = mmap((void *)random_addresses[i],         \
+					 5 * sizeof(int), PROT, FLAGS, 0, 0); \
+			EXPECT_NE(MAP_FAILED, mmap_addr);                     \
+			EXPECT_GE((void *)get_max_value(random_addresses[i]), \
+				  mmap_addr);                                 \
+			mmap_addr = mmap((void *)random_addresses[i],         \
+					 5 * sizeof(int), PROT, FLAGS, 0, 0); \
+			EXPECT_NE(MAP_FAILED, mmap_addr);                     \
+			EXPECT_GE((void *)get_max_value(random_addresses[i]), \
+				  mmap_addr);                                 \
+		}                                                             \
+	})
 #endif /* __riscv_xlen == 64 */
 
 static inline int memory_layout(void)
 {
-	int prot = PROT_READ | PROT_WRITE;
-	int flags = MAP_PRIVATE | MAP_ANONYMOUS;
-
-	void *value1 = mmap(NULL, sizeof(int), prot, flags, 0, 0);
-	void *value2 = mmap(NULL, sizeof(int), prot, flags, 0, 0);
+	void *value1 = mmap(NULL, sizeof(int), PROT, FLAGS, 0, 0);
+	void *value2 = mmap(NULL, sizeof(int), PROT, FLAGS, 0, 0);
 
 	return value2 > value1;
 }