Commit fc6daaf9 authored by Tony Luck's avatar Tony Luck Committed by Linus Torvalds
Browse files

mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute 



Some high end Intel Xeon systems report uncorrectable memory errors as a
recoverable machine check.  Linux has included code for some time to
process these and just signal the affected processes (or even recover
completely if the error was in a read only page that can be replaced by
reading from disk).

But we have no recovery path for errors encountered during kernel code
execution.  Except for some very specific cases were are unlikely to ever
be able to recover.

Enter memory mirroring. Actually 3rd generation of memory mirroing.

Gen1: All memory is mirrored
	Pro: No s/w enabling - h/w just gets good data from other side of the
	     mirror
	Con: Halves effective memory capacity available to OS/applications

Gen2: Partial memory mirror - just mirror memory begind some memory controllers
	Pro: Keep more of the capacity
	Con: Nightmare to enable. Have to choose between allocating from
	     mirrored memory for safety vs. NUMA local memory for performance

Gen3: Address range partial memory mirror - some mirror on each memory
      controller
	Pro: Can tune the amount of mirror and keep NUMA performance
	Con: I have to write memory management code to implement

The current plan is just to use mirrored memory for kernel allocations.
This has been broken into two phases:

1) This patch series - find the mirrored memory, use it for boot time
   allocations

2) Wade into mm/page_alloc.c and define a ZONE_MIRROR to pick up the
   unused mirrored memory from mm/memblock.c and only give it out to
   select kernel allocations (this is still being scoped because
   page_alloc.c is scary).

This patch (of 3):

Add extra "flags" to memblock to allow selection of memory based on
attribute.  No functional changes

Signed-off-by: default avatarTony Luck <tony.luck@intel.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Xiexiuqi <xiexiuqi@huawei.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 6afdb859

arch/s390/kernel/crash_dump.c

+3 −2
Original line number Diff line number Diff line
@@ -33,11 +33,12 @@ static struct memblock_type oldmem_type = { 
};



#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\

	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\

	for (i = 0, __next_mem_range(&i, nid, MEMBLOCK_NONE,		\

				     &memblock.physmem,			\

				     &oldmem_type, p_start,		\

				     p_end, p_nid);			\

	     i != (u64)ULLONG_MAX;					\

	     __next_mem_range(&i, nid, &memblock.physmem,		\

	     __next_mem_range(&i, nid, MEMBLOCK_NONE, &memblock.physmem,\

			      &oldmem_type,				\

			      p_start, p_end, p_nid))

arch/sparc/mm/init_64.c

+4 −2
Original line number Diff line number Diff line
@@ -1966,7 +1966,8 @@ static phys_addr_t __init available_memory(void) 
	phys_addr_t pa_start, pa_end;

	u64 i;



	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)

	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,

				&pa_end, NULL)

		available = available + (pa_end  - pa_start);



	return available;
@@ -1992,7 +1993,8 @@ static void __init reduce_memory(phys_addr_t limit_ram) 
	if (limit_ram >= avail_ram)

		return;



	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {

	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,

				&pa_end, NULL) {

		phys_addr_t region_size = pa_end - pa_start;

		phys_addr_t clip_start = pa_start;

arch/x86/kernel/check.c

+2 −1
Original line number Diff line number Diff line
@@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void) 


	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);



	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {

	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,

				NULL) {

		start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),

				PAGE_SIZE, corruption_check_size);

		end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),

arch/x86/kernel/e820.c

+2 −1
Original line number Diff line number Diff line
@@ -1123,7 +1123,8 @@ void __init memblock_find_dma_reserve(void) 
		nr_pages += end_pfn - start_pfn;

	}



	for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {

	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,

				NULL) {

		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);

		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);

		if (start_pfn < end_pfn)

arch/x86/mm/init_32.c

+1 −1
Original line number Diff line number Diff line
@@ -433,7 +433,7 @@ void __init add_highpages_with_active_regions(int nid, 
	phys_addr_t start, end;

	u64 i;



	for_each_free_mem_range(i, nid, &start, &end, NULL) {

	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) {

		unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),

					    start_pfn, end_pfn);

		unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),

CRA Git | Maintained and supported by SUSTech CRA and CCSE