early_res: Add free_early_partial()

To free partial areas in pcpu_setup...

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
LKML-Reference: <4B85E245.5030001@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 62 insertions, 3 deletions

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 35abcb8b00e9..ef6370b00e70 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -137,7 +137,13 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	u64 start = __pa(ptr);
+	u64 end = start + size;
+	free_early_partial(start, end);
+#else
 	free_bootmem(__pa(ptr), size);
+#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
index 50f7663bb8b1..29c09f57a13c 100644
--- a/include/linux/early_res.h
+++ b/include/linux/early_res.h
@@ -5,6 +5,7 @@
 extern void reserve_early(u64 start, u64 end, char *name);
 extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
 extern void free_early(u64 start, u64 end);
+void free_early_partial(u64 start, u64 end);
 extern void early_res_to_bootmem(u64 start, u64 end);
 
 void reserve_early_without_check(u64 start, u64 end, char *name);
diff --git a/kernel/early_res.c b/kernel/early_res.c
index aa5494ac4462..9ab11cd84853 100644
--- a/kernel/early_res.c
+++ b/kernel/early_res.c
@@ -61,6 +61,40 @@ static void __init drop_range(int i)
 	early_res_count--;
 }
 
+static void __init drop_range_partial(int i, u64 start, u64 end)
+{
+	u64 common_start, common_end;
+	u64 old_start, old_end;
+
+	old_start = early_res[i].start;
+	old_end = early_res[i].end;
+	common_start = max(old_start, start);
+	common_end = min(old_end, end);
+
+	/* no overlap ? */
+	if (common_start >= common_end)
+		return;
+
+	if (old_start < common_start) {
+		/* make head segment */
+		early_res[i].end = common_start;
+		if (old_end > common_end) {
+			/* add another for left over on tail */
+			reserve_early_without_check(common_end, old_end,
+					 early_res[i].name);
+		}
+		return;
+	} else {
+		if (old_end > common_end) {
+			/* reuse the entry for tail left */
+			early_res[i].start = common_end;
+			return;
+		}
+		/* all covered */
+		drop_range(i);
+	}
+}
+
 /*
  * Split any existing ranges that:
  *  1) are marked 'overlap_ok', and
@@ -284,6 +318,27 @@ void __init free_early(u64 start, u64 end)
 	drop_range(i);
 }
 
+void __init free_early_partial(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+try_next:
+	i = find_overlapped_early(start, end);
+	if (i >= max_early_res)
+		return;
+
+	r = &early_res[i];
+	/* hole ? */
+	if (r->end >= end && r->start <= start) {
+		drop_range_partial(i, start, end);
+		return;
+	}
+
+	drop_range_partial(i, start, end);
+	goto try_next;
+}
+
 #ifdef CONFIG_NO_BOOTMEM
 static void __init subtract_early_res(struct range *range, int az)
 {
diff --git a/mm/percpu.c b/mm/percpu.c
index 841defeeef86..083e7c91e5f6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1929,10 +1929,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
 			}
 			/* copy and return the unused part */
 			memcpy(ptr, __per_cpu_load, ai->static_size);
-#ifndef CONFIG_NO_BOOTMEM
-			/* fix partial free ! */
 			free_fn(ptr + size_sum, ai->unit_size - size_sum);
-#endif
 		}
 	}