[RFC PATCH 2/2] arm64: Implement vmalloc based thread_info allocator

[Jungseok Lee]

Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
since system memory is fragmented.

This patch tries to solve the problem as allocating thread_info memory
from vmalloc space, not 1:1 mapping one. The downside is one additional
page allocation in case of vmalloc. However, vmalloc space is large enough,
around 240GB, under a combination of 39-bit VA and 4KB page. Thus, it is
not a big tradeoff for fork-routine service.

Suggested-by: Sungjinn Chung <barami97 at gmail.com>
Signed-off-by: Jungseok Lee <jungseoklee85 at gmail.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Cc: Will Deacon <will.deacon at arm.com>
Cc: linux-kernel at vger.kernel.org
Cc: linux-mm at kvack.org
---
 arch/arm64/Kconfig                   | 12 ++++++++++++
 arch/arm64/include/asm/thread_info.h |  9 +++++++++
 arch/arm64/kernel/process.c          |  7 +++++++
 3 files changed, 28 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 99930cf..93c236a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -536,6 +536,18 @@ config ARCH_SELECT_MEMORY_MODEL
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
+config ARCH_THREAD_INFO_ALLOCATOR
+	bool "Enable vmalloc based thread_info allocator (EXPERIMENTAL)"
+	depends on ARM64_4K_PAGES
+	default n
+	help
+	  This feature enables vmalloc based thread_info allocator. It
+	  prevents fork-routine from begin failed to obtain physically
+	  contiguour region due to memory fragmentation on low system
+	  memory platforms.
+
+	  If unsure, say N
+
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
 	depends on PERF_EVENTS
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index dcd06d1..e753e59 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -61,6 +61,15 @@ struct thread_info {
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
+#ifdef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#define alloc_thread_info_node(tsk, node)				\
+({									\
+	__vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, VMALLOC_START,	\
+			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL, 0,	\
+			NUMA_NO_NODE, __builtin_return_address(0));	\
+})
+#define free_thread_info(ti)	vfree(ti)
+#endif
 /*
  * how to get the current stack pointer from C
  */
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c506bee..c4b6aae 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -238,6 +238,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+struct page *arch_thread_info_to_page(struct thread_info *ti)
+{
+	return vmalloc_to_page(ti);
+}
+#endif
+
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
 int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-- 
1.9.1