Skip to main content

Browse the archive

https://github.com/torvalds/linux
23 October 2021, 00:29:24 UTC
Revision c5c9f25b98a568451d665afe4aeefe17bf9f2995 authored by Nishanth Aravamudan on 24 November 2015, 16:55:05 UTC, committed by Jens Axboe on 24 November 2015, 22:05:51 UTC 
NVMe: default to 4k device page size
 
We received a bug report recently when DDW (64-bit direct DMA on Power)
is not enabled for NVMe devices. In that case, we fall back to 32-bit
DMA via the IOMMU, which is always done via 4K TCEs (Translation Control
Entries).

The NVMe device driver, though, assumes that the DMA alignment for the
PRP entries will match the device's page size, and that the DMA aligment
matches the kernel's page aligment. On Power, the the IOMMU page size,
as mentioned above, can be 4K, while the device can have a page size of
8K, while the kernel has a page size of 64K. This eventually trips the
BUG_ON in nvme_setup_prps(), as we have a 'dma_len' that is a multiple
of 4K but not 8K (e.g., 0xF000).

In this particular case of page sizes, we clearly want to use the
IOMMU's page size in the driver. And generally, the NVMe driver in this
function should be using the IOMMU's page size for the default device
page size, rather than the kernel's page size. There is not currently an
API to obtain the IOMMU's page size across all architectures and in the
interest of a stop-gap fix to this functional issue, default the NVMe
device page size to 4K, with the intent of adding such an API and
implementation across all architectures in the next merge window.

With the functionally equivalent v3 of this patch, our hardware test
exerciser survives when using 32-bit DMA; without the patch, the kernel
will BUG within a few minutes.

Signed-off-by: Nishanth Aravamudan <nacc at linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
1 parent 6ffeba9
Raw File
Tip revision: c5c9f25b98a568451d665afe4aeefe17bf9f2995 authored by Nishanth Aravamudan on 24 November 2015, 16:55:05 UTC
NVMe: default to 4k device page size
Tip revision: c5c9f25
mmzone.c 
/*
 * linux/mm/mmzone.c
 *
 * management codes for pgdats, zones and page flags
 */


#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/mmzone.h>

struct pglist_data *first_online_pgdat(void)
{
	return NODE_DATA(first_online_node);
}

struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
{
	int nid = next_online_node(pgdat->node_id);

	if (nid == MAX_NUMNODES)
		return NULL;
	return NODE_DATA(nid);
}

/*
 * next_zone - helper magic for for_each_zone()
 */
struct zone *next_zone(struct zone *zone)
{
	pg_data_t *pgdat = zone->zone_pgdat;

	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
		zone++;
	else {
		pgdat = next_online_pgdat(pgdat);
		if (pgdat)
			zone = pgdat->node_zones;
		else
			zone = NULL;
	}
	return zone;
}

static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
{
#ifdef CONFIG_NUMA
	return node_isset(zonelist_node_idx(zref), *nodes);
#else
	return 1;
#endif /* CONFIG_NUMA */
}

/* Returns the next zone at or below highest_zoneidx in a zonelist */
struct zoneref *next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes)
{
	/*
	 * Find the next suitable zone to use for the allocation.
	 * Only filter based on nodemask if it's set
	 */
	if (likely(nodes == NULL))
		while (zonelist_zone_idx(z) > highest_zoneidx)
			z++;
	else
		while (zonelist_zone_idx(z) > highest_zoneidx ||
				(z->zone && !zref_in_nodemask(z, nodes)))
			z++;

	return z;
}

#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
int memmap_valid_within(unsigned long pfn,
					struct page *page, struct zone *zone)
{
	if (page_to_pfn(page) != pfn)
		return 0;

	if (page_zone(page) != zone)
		return 0;

	return 1;
}
#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */

void lruvec_init(struct lruvec *lruvec)
{
	enum lru_list lru;

	memset(lruvec, 0, sizeof(struct lruvec));

	for_each_lru(lru)
		INIT_LIST_HEAD(&lruvec->lists[lru]);
}

#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
int page_cpupid_xchg_last(struct page *page, int cpupid)
{
	unsigned long old_flags, flags;
	int last_cpupid;

	do {
		old_flags = flags = page->flags;
		last_cpupid = page_cpupid_last(page);

		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));

	return last_cpupid;
}
#endif
back to top