Subject: powerpc/fadump: add reschedule point while releasing memory
From: Hari Bathini <hbathini@linux.vnet.ibm.com>

References: bsc#1040609
Patch-mainline: v4.13-rc1
Git-commit: 68fa6478e3b1fab7077d390070ed455aed93905c

Around 95% of memory is reserved by fadump/capture kernel. All this
memory is freed, one page at a time, on writing '1' to the node
/sys/kernel/fadump_release_mem. On systems with large memory, this
can take a long time to complete, leading to soft lockup warning
messages. To avoid this, add reschedule points at regular intervals.

Also, while memblock_reserve() implicitly takes care of holes in the
given memory range while reserving memory, those holes need to be
taken care of while releasing memory as memory is freed one page at
a time. Add support to skip holes while releasing memory.

Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/kernel/fadump.c | 65 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 54 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index a3568136ab28..3079518f2245 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1152,28 +1152,71 @@ void fadump_cleanup(void)
 	}
 }
 
+static void fadump_free_reserved_memory(unsigned long start_pfn,
+					unsigned long end_pfn)
+{
+	unsigned long pfn;
+	unsigned long time_limit = jiffies + HZ;
+
+	pr_info("freeing reserved memory (0x%llx - 0x%llx)\n",
+		PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		free_reserved_page(pfn_to_page(pfn));
+
+		if (time_after(jiffies, time_limit)) {
+			cond_resched();
+			time_limit = jiffies + HZ;
+		}
+	}
+}
+
+/*
+ * Skip memory holes and free memory that was actually reserved.
+ */
+static void fadump_release_reserved_area(unsigned long start, unsigned long end)
+{
+	struct memblock_region *reg;
+	unsigned long tstart, tend;
+	unsigned long start_pfn = PHYS_PFN(start);
+	unsigned long end_pfn = PHYS_PFN(end);
+
+	for_each_memblock(memory, reg) {
+		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
+		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+		if (tstart < tend) {
+			fadump_free_reserved_memory(tstart, tend);
+
+			if (tend == end_pfn)
+				break;
+
+			start_pfn = tend + 1;
+		}
+	}
+}
+
 /*
  * Release the memory that was reserved in early boot to preserve the memory
  * contents. The released memory will be available for general use.
  */
 static void fadump_release_memory(unsigned long begin, unsigned long end)
 {
-	unsigned long addr;
 	unsigned long ra_start, ra_end;
 
 	ra_start = fw_dump.reserve_dump_area_start;
 	ra_end = ra_start + fw_dump.reserve_dump_area_size;
 
-	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		/*
-		 * exclude the dump reserve area. Will reuse it for next
-		 * fadump registration.
-		 */
-		if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
-			continue;
-
-		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
-	}
+	/*
+	 * exclude the dump reserve area. Will reuse it for next
+	 * fadump registration.
+	 */
+	if (begin < ra_end && end > ra_start) {
+		if (begin < ra_start)
+			fadump_release_reserved_area(begin, ra_start);
+		if (end > ra_end)
+			fadump_release_reserved_area(ra_end, end);
+	} else
+		fadump_release_reserved_area(begin, end);
 }
 
 static void fadump_invalidate_release_mem(void)
-- 
2.10.2