ef78e5ec92
The numa_slit variable used by node_distance is available to a module as long as it is linked at compile-time. However, it is not available to loadable modules. Leading to errors such as: ERROR: "numa_slit" [drivers/nvme/host/nvme-core.ko] undefined! The error above is caused by the nvme multipath code that makes use of node_distance for its path calculation. When the patch was added, the lightnvm subsystem would select nvme and always compile it in, leading to the node_distance call to always succeed. However, when this requirement was removed, nvme could be compiled in as a module, which exposed this bug. This patch extracts node_distance to a function and exports it. Since ACPI is depending on node_distance being a simple lookup to numa_slit, the previous behavior is exposed as slit_distance and its users updated. Fixes:f333444708"nvme: take node locality into account when selecting a path" Fixes:73569e1103"lightnvm: remove dependencies on BLK_DEV_NVME and PCI" Signed-off-by: Matias Bjøring <mb@lightnvm.io> Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
112 lines
2.9 KiB
C
112 lines
2.9 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* This file contains NUMA specific variables and functions which can
|
|
* be split away from DISCONTIGMEM and are used on NUMA machines with
|
|
* contiguous memory.
|
|
*
|
|
* 2002/08/07 Erich Focht <efocht@ess.nec.de>
|
|
*/
|
|
|
|
#include <linux/cpu.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/node.h>
|
|
#include <linux/init.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/module.h>
|
|
#include <asm/mmzone.h>
|
|
#include <asm/numa.h>
|
|
|
|
|
|
/*
|
|
* The following structures are usually initialized by ACPI or
|
|
* similar mechanisms and describe the NUMA characteristics of the machine.
|
|
*/
|
|
int num_node_memblks;
|
|
struct node_memblk_s node_memblk[NR_NODE_MEMBLKS];
|
|
struct node_cpuid_s node_cpuid[NR_CPUS] =
|
|
{ [0 ... NR_CPUS-1] = { .phys_id = 0, .nid = NUMA_NO_NODE } };
|
|
|
|
/*
|
|
* This is a matrix with "distances" between nodes, they should be
|
|
* proportional to the memory access latency ratios.
|
|
*/
|
|
u8 numa_slit[MAX_NUMNODES * MAX_NUMNODES];
|
|
|
|
int __node_distance(int from, int to)
|
|
{
|
|
return slit_distance(from, to);
|
|
}
|
|
EXPORT_SYMBOL(__node_distance);
|
|
|
|
/* Identify which cnode a physical address resides on */
|
|
int
|
|
paddr_to_nid(unsigned long paddr)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < num_node_memblks; i++)
|
|
if (paddr >= node_memblk[i].start_paddr &&
|
|
paddr < node_memblk[i].start_paddr + node_memblk[i].size)
|
|
break;
|
|
|
|
return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0);
|
|
}
|
|
|
|
#if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
|
|
/*
|
|
* Because of holes evaluate on section limits.
|
|
* If the section of memory exists, then return the node where the section
|
|
* resides. Otherwise return node 0 as the default. This is used by
|
|
* SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
|
|
* the section resides.
|
|
*/
|
|
int __meminit __early_pfn_to_nid(unsigned long pfn,
|
|
struct mminit_pfnnid_cache *state)
|
|
{
|
|
int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
|
|
|
|
if (section >= state->last_start && section < state->last_end)
|
|
return state->last_nid;
|
|
|
|
for (i = 0; i < num_node_memblks; i++) {
|
|
ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
|
|
esec = (node_memblk[i].start_paddr + node_memblk[i].size +
|
|
((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
|
|
if (section >= ssec && section < esec) {
|
|
state->last_start = ssec;
|
|
state->last_end = esec;
|
|
state->last_nid = node_memblk[i].nid;
|
|
return node_memblk[i].nid;
|
|
}
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
void numa_clear_node(int cpu)
|
|
{
|
|
unmap_cpu_from_node(cpu, NUMA_NO_NODE);
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
/*
|
|
* SRAT information is stored in node_memblk[], then we can use SRAT
|
|
* information at memory-hot-add if necessary.
|
|
*/
|
|
|
|
int memory_add_physaddr_to_nid(u64 addr)
|
|
{
|
|
int nid = paddr_to_nid(addr);
|
|
if (nid < 0)
|
|
return 0;
|
|
return nid;
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
|
|
#endif
|
|
#endif
|