[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.DEB.2.00.1002151343080.26927@chino.kir.corp.google.com>
Date: Mon, 15 Feb 2010 13:43:33 -0800 (PST)
From: David Rientjes <rientjes@...gle.com>
To: Ingo Molnar <mingo@...hat.com>, "H. Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>
cc: x86@...nel.org, linux-kernel@...r.kernel.org
Subject: [patch 3/3] x86: remove configurable node size support for numa
emulation
Now that numa=fake=<size>[MG] is implemented, it is possible to remove
configurable node size support. The command-line parsing was already
broken (numa=fake=*128, for example, would not work) and since fake nodes
are now interleaved over physical nodes, this support is no longer
required.
Signed-off-by: David Rientjes <rientjes@...gle.com>
---
Documentation/x86/x86_64/boot-options.txt | 16 +---
arch/x86/mm/numa_64.c | 160 +++--------------------------
2 files changed, 16 insertions(+), 160 deletions(-)
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -170,19 +170,9 @@ NUMA
If given as a memory unit, fills all system RAM with nodes of
size interleaved over physical nodes.
- numa=fake=CMDLINE
- If a number, fakes CMDLINE nodes and ignores NUMA setup of the
- actual machine. Otherwise, system memory is configured
- depending on the sizes and coefficients listed. For example:
- numa=fake=2*512,1024,4*256,*128
- gives two 512M nodes, a 1024M node, four 256M nodes, and the
- rest split into 128M chunks. If the last character of CMDLINE
- is a *, the remaining memory is divided up equally among its
- coefficient:
- numa=fake=2*512,2*
- gives two 512M nodes and the rest split into two nodes.
- Otherwise, the remaining system RAM is allocated to an
- additional node.
+ numa=fake=<N>
+ If given as an integer, fills all system RAM with N fake nodes
+ interleaved over physical nodes.
ACPI
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -598,172 +598,38 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
}
/*
- * Splits num_nodes nodes up equally starting at node_start. The return value
- * is the number of nodes split up and addr is adjusted to be at the end of the
- * last node allocated.
- */
-static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start,
- int num_nodes)
-{
- unsigned int big;
- u64 size;
- int i;
-
- if (num_nodes <= 0)
- return -1;
- if (num_nodes > MAX_NUMNODES)
- num_nodes = MAX_NUMNODES;
- size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) /
- num_nodes;
- /*
- * Calculate the number of big nodes that can be allocated as a result
- * of consolidating the leftovers.
- */
- big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * num_nodes) /
- FAKE_NODE_MIN_SIZE;
-
- /* Round down to nearest FAKE_NODE_MIN_SIZE. */
- size &= FAKE_NODE_MIN_HASH_MASK;
- if (!size) {
- printk(KERN_ERR "Not enough memory for each node. "
- "NUMA emulation disabled.\n");
- return -1;
- }
-
- for (i = node_start; i < num_nodes + node_start; i++) {
- u64 end = *addr + size;
-
- if (i < big)
- end += FAKE_NODE_MIN_SIZE;
- /*
- * The final node can have the remaining system RAM. Other
- * nodes receive roughly the same amount of available pages.
- */
- if (i == num_nodes + node_start - 1)
- end = max_addr;
- else
- end = find_end_of_node(*addr, max_addr, size);
- if (setup_node_range(i, addr, end - *addr, max_addr) < 0)
- break;
- }
- return i - node_start + 1;
-}
-
-/*
- * Splits the remaining system RAM into chunks of size. The remaining memory is
- * always assigned to a final node and can be asymmetric. Returns the number of
- * nodes split.
- */
-static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start,
- u64 size)
-{
- int i = node_start;
- size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
- while (!setup_node_range(i++, addr, size, max_addr))
- ;
- return i - node_start;
-}
-
-/*
* Sets up the system RAM area from start_pfn to last_pfn according to the
* numa=fake command-line option.
*/
static int __init numa_emulation(unsigned long start_pfn,
unsigned long last_pfn, int acpi, int k8)
{
- u64 size, addr = start_pfn << PAGE_SHIFT;
+ u64 addr = start_pfn << PAGE_SHIFT;
u64 max_addr = last_pfn << PAGE_SHIFT;
- int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i;
int num_phys_nodes;
+ int num_nodes;
+ int i;
num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
/*
* If the numa=fake command-line contains a 'M' or 'G', it represents
- * the fixed node size.
+ * the fixed node size. Otherwise, if it is just a single number N,
+ * split the system RAM into N fake nodes.
*/
if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) {
+ u64 size;
+
size = memparse(cmdline, &cmdline);
num_nodes = split_nodes_size_interleave(addr, max_addr, size);
- if (num_nodes < 0)
- return num_nodes;
- goto out;
- }
+ } else {
+ unsigned long n;
- /*
- * If the numa=fake command-line is just a single number N, split the
- * system RAM into N fake nodes.
- */
- if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
- long n = simple_strtol(cmdline, NULL, 0);
-
- num_nodes = split_nodes_interleave(addr, max_addr,
- num_phys_nodes, n);
- if (num_nodes < 0)
- return num_nodes;
- goto out;
+ n = simple_strtoul(cmdline, NULL, 0);
+ num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
}
- /* Parse the command line. */
- for (coeff_flag = 0; ; cmdline++) {
- if (*cmdline && isdigit(*cmdline)) {
- num = num * 10 + *cmdline - '0';
- continue;
- }
- if (*cmdline == '*') {
- if (num > 0)
- coeff = num;
- coeff_flag = 1;
- }
- if (!*cmdline || *cmdline == ',') {
- if (!coeff_flag)
- coeff = 1;
- /*
- * Round down to the nearest FAKE_NODE_MIN_SIZE.
- * Command-line coefficients are in megabytes.
- */
- size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK;
- if (size)
- for (i = 0; i < coeff; i++, num_nodes++)
- if (setup_node_range(num_nodes, &addr,
- size, max_addr) < 0)
- goto done;
- if (!*cmdline)
- break;
- coeff_flag = 0;
- coeff = -1;
- }
- num = 0;
- }
-done:
- if (!num_nodes)
- return -1;
- /* Fill remainder of system RAM, if appropriate. */
- if (addr < max_addr) {
- if (coeff_flag && coeff < 0) {
- /* Split remaining nodes into num-sized chunks */
- num_nodes += split_nodes_by_size(&addr, max_addr,
- num_nodes, num);
- goto out;
- }
- switch (*(cmdline - 1)) {
- case '*':
- /* Split remaining nodes into coeff chunks */
- if (coeff <= 0)
- break;
- num_nodes += split_nodes_equally(&addr, max_addr,
- num_nodes, coeff);
- break;
- case ',':
- /* Do not allocate remaining system RAM */
- break;
- default:
- /* Give one final node */
- setup_node_range(num_nodes, &addr, max_addr - addr,
- max_addr);
- num_nodes++;
- }
- }
-out:
+ if (num_nodes < 0)
+ return num_nodes;
memnode_shift = compute_hash_shift(nodes, num_nodes, NULL);
if (memnode_shift < 0) {
memnode_shift = 0;
--
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