From: Tejun Heo <tj@kernel.org>
Date: Fri, 14 Aug 2009 06:00:53 +0000 (+0900)
Subject: powerpc64: convert to dynamic percpu allocator
X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=c2a7e818019f20a5cf7fb26a6eb59e212e6c0cd8;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git

powerpc64: convert to dynamic percpu allocator

Now that percpu allows arbitrary embedding of the first chunk,
powerpc64 can easily be converted to dynamic percpu allocator.
Convert it.  powerpc supports several large page sizes.  Cap atom_size
at 1M.  There isn't much to gain by going above that anyway.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 61bbffa2fe60..2c42e1526d03 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -46,10 +46,10 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 	bool
 	default y
 
-config HAVE_LEGACY_PER_CPU_AREA
+config HAVE_SETUP_PER_CPU_AREA
 	def_bool PPC64
 
-config HAVE_SETUP_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool PPC64
 
 config IRQ_PER_CPU
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1f6816003ebe..aa6e4500635f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -57,6 +57,7 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
+#include <asm/mmu-hash64.h>
 #include <asm/firmware.h>
 #include <asm/xmon.h>
 #include <asm/udbg.h>
@@ -569,25 +570,53 @@ void cpu_die(void)
 }
 
 #ifdef CONFIG_SMP
-void __init setup_per_cpu_areas(void)
+#define PCPU_DYN_SIZE		()
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	int i;
-	unsigned long size;
-	char *ptr;
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE);
-#ifdef CONFIG_MODULES
-	if (size < PERCPU_ENOUGH_ROOM)
-		size = PERCPU_ENOUGH_ROOM;
-#endif
+	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+				    __pa(MAX_DMA_ADDRESS));
+}
 
-	for_each_possible_cpu(i) {
-		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	free_bootmem(__pa(ptr), size);
+}
 
-		paca[i].data_offset = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-	}
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	if (cpu_to_node(from) == cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
+	size_t atom_size;
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
+	 * to group units.  For larger mappings, use 1M atom which
+	 * should be large enough to contain a number of units.
+	 */
+	if (mmu_linear_psize == MMU_PAGE_4K)
+		atom_size = PAGE_SIZE;
+	else
+		atom_size = 1 << 20;
+
+	rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("cannot initialize percpu area (err=%d)", rc);
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		paca[cpu].data_offset = delta + pcpu_unit_offsets[cpu];
 }
 #endif