[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4DBAF40F.8030207@kernel.org>
Date: Fri, 29 Apr 2011 10:23:27 -0700
From: Yinghai Lu <yinghai@...nel.org>
To: Tejun Heo <tj@...nel.org>
CC: mingo@...hat.com, rientjes@...gle.com, tglx@...utronix.de,
hpa@...or.com, x86@...nel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 03/25] x86-64, NUMA: simplify nodedata allocation
On 04/29/2011 08:28 AM, Tejun Heo wrote:
> With top-down memblock allocation, the allocation range limits in
> ealry_node_mem() can be simplified - try node-local first, then any
> node but in any case don't allocate below DMA limit.
>
> Remove early_node_mem() and implement simplified allocation directly
> in setup_node_bootmem().
keep early_node_mem would be better?
Yinghai
>
> Signed-off-by: Tejun Heo <tj@...nel.org>
> Cc: Ingo Molnar <mingo@...hat.com>
> Cc: Yinghai Lu <yinghai@...nel.org>
> Cc: David Rientjes <rientjes@...gle.com>
> Cc: Thomas Gleixner <tglx@...utronix.de>
> Cc: "H. Peter Anvin" <hpa@...or.com>
> ---
> arch/x86/mm/numa_64.c | 53 +++++++++++++++---------------------------------
> 1 files changed, 17 insertions(+), 36 deletions(-)
>
> diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
> index 5e0dfc5..59d8a1c 100644
> --- a/arch/x86/mm/numa_64.c
> +++ b/arch/x86/mm/numa_64.c
> @@ -37,38 +37,6 @@ __initdata
> static int numa_distance_cnt;
> static u8 *numa_distance;
>
> -static void * __init early_node_mem(int nodeid, unsigned long start,
> - unsigned long end, unsigned long size,
> - unsigned long align)
> -{
> - unsigned long mem;
> -
> - /*
> - * put it on high as possible
> - * something will go with NODE_DATA
> - */
> - if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
> - start = MAX_DMA_PFN<<PAGE_SHIFT;
> - if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
> - end > (MAX_DMA32_PFN<<PAGE_SHIFT))
> - start = MAX_DMA32_PFN<<PAGE_SHIFT;
> - mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
> - if (mem != MEMBLOCK_ERROR)
> - return __va(mem);
> -
> - /* extend the search scope */
> - end = max_pfn_mapped << PAGE_SHIFT;
> - start = MAX_DMA_PFN << PAGE_SHIFT;
> - mem = memblock_find_in_range(start, end, size, align);
> - if (mem != MEMBLOCK_ERROR)
> - return __va(mem);
> -
> - printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
> - size, nodeid);
> -
> - return NULL;
> -}
> -
> static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
> struct numa_meminfo *mi)
> {
> @@ -130,6 +98,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
> void __init
> setup_node_bootmem(int nid, unsigned long start, unsigned long end)
> {
> + const u64 nd_low = (u64)MAX_DMA_PFN << PAGE_SHIFT;
> + const u64 nd_high = (u64)max_pfn_mapped << PAGE_SHIFT;
> const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
> unsigned long nd_pa;
> int tnid;
> @@ -146,18 +116,29 @@ setup_node_bootmem(int nid, unsigned long start, unsigned long end)
> printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n",
> nid, start, end);
>
> - node_data[nid] = early_node_mem(nid, start, end, nd_size,
> - SMP_CACHE_BYTES);
> - if (node_data[nid] == NULL)
> + /*
> + * Try to allocate node data on local node and then fall back to
> + * all nodes. Never allocate in DMA zone.
> + */
> + nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
> + nd_size, SMP_CACHE_BYTES);
> + if (nd_pa == MEMBLOCK_ERROR)
> + nd_pa = memblock_find_in_range(nd_low, nd_high,
> + nd_size, SMP_CACHE_BYTES);
> + if (nd_pa == MEMBLOCK_ERROR) {
> + pr_err("Cannot find %lu bytes in node %d\n", nd_size, nid);
> return;
> - nd_pa = __pa(node_data[nid]);
> + }
> memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
> +
> + /* report and initialize */
> printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n",
> nd_pa, nd_pa + nd_size - 1);
> tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
> if (tnid != nid)
> printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid);
>
> + node_data[nid] = __va(nd_pa);
> memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
> NODE_DATA(nid)->node_id = nid;
> NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists