Commit 7c21d533 authored Sep 16, 2014 by bob picco Committed by David S. Miller Sep 16, 2014

sparc64: mem boot option correction



The "mem" boot option can result in many unexpected consequences. This patch
attempts to prevent boot hangs which have been experienced on T4-4 and T5-8.
Basically the boot loader allocates vmlinuz and initrd higher in available
OBP physical memory. For example, on a 2Tb T5-8 it isn't possible to boot
with mem=20G.

The patch utilizes memblock to avoid reserved regions and trim memory which
is only free. Other improvements are possible for a multi-node machine.

This is a snippet of the boot log with mem=20G on T5-8 with the patch applied:
MEMBLOCK configuration:	<- before memory reduction
 memory size = 0x1ffad6ce000 reserved size = 0xa1adf44
 memory.cnt  = 0xb
 memory[0x0]    [0x00000030400000-0x00003fdde47fff], 0x3fada48000 bytes
 memory[0x1]    [0x00003fdde4e000-0x00003fdde4ffff], 0x2000 bytes
 memory[0x2]    [0x00080000000000-0x00083fffffffff], 0x4000000000 bytes
 memory[0x3]    [0x00100000000000-0x00103fffffffff], 0x4000000000 bytes
 memory[0x4]    [0x00180000000000-0x00183fffffffff], 0x4000000000 bytes
 memory[0x5]    [0x00200000000000-0x00203fffffffff], 0x4000000000 bytes
 memory[0x6]    [0x00280000000000-0x00283fffffffff], 0x4000000000 bytes
 memory[0x7]    [0x00300000000000-0x00303fffffffff], 0x4000000000 bytes
 memory[0x8]    [0x00380000000000-0x00383fffc71fff], 0x3fffc72000 bytes
 memory[0x9]    [0x00383fffc92000-0x00383fffca1fff], 0x10000 bytes
 memory[0xa]    [0x00383fffcb4000-0x00383fffcb5fff], 0x2000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 reserved[0x1]  [0x00380004000000-0x0038000d02f74a], 0x902f74b bytes
...
MEMBLOCK configuration:	<- after reduction of memory
 memory size = 0x50a1adf44 reserved size = 0xa1adf44
 memory.cnt  = 0x4
 memory[0x0]    [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 memory[0x1]    [0x00380004000000-0x0038050d01d74a], 0x50901d74b bytes
 memory[0x2]    [0x00383fffc92000-0x00383fffca1fff], 0x10000 bytes
 memory[0x3]    [0x00383fffcb4000-0x00383fffcb5fff], 0x2000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 reserved[0x1]  [0x00380004000000-0x0038000d02f74a], 0x902f74b bytes
...
Early memory node ranges
  node   7: [mem 0x380000000000-0x38000117dfff]
  node   7: [mem 0x380004000000-0x380f0d01bfff]
  node   7: [mem 0x383fffc92000-0x383fffca1fff]
  node   7: [mem 0x383fffcb4000-0x383fffcb5fff]
Could not find start_pfn for node 0
Could not find start_pfn for node 1
Could not find start_pfn for node 2
Could not find start_pfn for node 3
Could not find start_pfn for node 4
Could not find start_pfn for node 5
Could not find start_pfn for node 6
.

The patch was tested on T4-1, T5-8 and Jalap?no.

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent 3dee9df5

arch/sparc/kernel/setup_64.c

+3 −15

Original line number	Original line	Diff line number	Diff line
	@@ -141,21 +141,9 @@ static void __init boot_flags_init(char *commands)
	process_switch(*commands++);		process_switch(*commands++);
	continue;		continue;
	}		}
	if (!strncmp(commands, "mem=", 4)) {		if (!strncmp(commands, "mem=", 4))
	/*		cmdline_memory_size = memparse(commands + 4, &commands);
	* "mem=XXX[kKmM]" overrides the PROM-reported
	* memory size.
	*/
	cmdline_memory_size = simple_strtoul(commands + 4,
	&commands, 0);
	if (commands == 'K' \|\| commands == 'k') {
	cmdline_memory_size <<= 10;
	commands++;
	} else if (commands=='M' \|\| commands=='m') {
	cmdline_memory_size <<= 20;
	commands++;
	}
	}
	while (commands && commands != ' ')		while (commands && commands != ' ')
	commands++;		commands++;
	}		}

arch/sparc/mm/init_64.c

+48 −1

Original line number	Original line	Diff line number	Diff line
	@@ -1861,6 +1861,52 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD];
	static void sun4u_pgprot_init(void);		static void sun4u_pgprot_init(void);
	static void sun4v_pgprot_init(void);		static void sun4v_pgprot_init(void);

			static phys_addr_t __init available_memory(void)
			{
			phys_addr_t available = 0ULL;
			phys_addr_t pa_start, pa_end;
			u64 i;

			for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)
			available = available + (pa_end - pa_start);

			return available;
			}

			/* We need to exclude reserved regions. This exclusion will include
			* vmlinux and initrd. To be more precise the initrd size could be used to
			* compute a new lower limit because it is freed later during initialization.
			*/
			static void __init reduce_memory(phys_addr_t limit_ram)
			{
			phys_addr_t avail_ram = available_memory();
			phys_addr_t pa_start, pa_end;
			u64 i;

			if (limit_ram >= avail_ram)
			return;

			for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {
			phys_addr_t region_size = pa_end - pa_start;
			phys_addr_t clip_start = pa_start;

			avail_ram = avail_ram - region_size;
			/* Are we consuming too much? */
			if (avail_ram < limit_ram) {
			phys_addr_t give_back = limit_ram - avail_ram;

			region_size = region_size - give_back;
			clip_start = clip_start + give_back;
			}

			memblock_remove(clip_start, region_size);

			if (avail_ram <= limit_ram)
			break;
			i = 0UL;
			}
			}

	void __init paging_init(void)		void __init paging_init(void)
	{		{
	unsigned long end_pfn, shift, phys_base;		unsigned long end_pfn, shift, phys_base;
	@@ -1940,7 +1986,8 @@ void __init paging_init(void)

	find_ramdisk(phys_base);		find_ramdisk(phys_base);

	memblock_enforce_memory_limit(cmdline_memory_size);		if (cmdline_memory_size)
			reduce_memory(cmdline_memory_size);

	memblock_allow_resize();		memblock_allow_resize();
	memblock_dump_all();		memblock_dump_all();