From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To: linuxppc-dev@lists.ozlabs.org, mpe@ellerman.id.au
Cc: cam@neo-zeon.de, "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v2 1/4] powerpc/percpu: Update percpu bootmem allocator
Date: Mon, 8 Jun 2020 12:39:01 +0530 [thread overview]
Message-ID: <20200608070904.387440-1-aneesh.kumar@linux.ibm.com> (raw)
This update the ppc64 version to be closer to x86/sparc.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/kernel/setup_64.c | 45 ++++++++++++++++++++++++++++------
1 file changed, 37 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index bb47555d48a2..eaddd53a0e13 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -753,17 +753,46 @@ void __init emergency_stack_init(void)
}
#ifdef CONFIG_SMP
-#define PCPU_DYN_SIZE ()
-
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
+ size_t align)
{
- return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
- MEMBLOCK_ALLOC_ACCESSIBLE,
- early_cpu_to_node(cpu));
+ const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ int node = early_cpu_to_node(cpu);
+ void *ptr;
+ if (!node_online(node) || !NODE_DATA(node)) {
+ ptr = memblock_alloc_from(size, align, goal);
+ pr_info("cpu %d has no node %d or node-local memory\n",
+ cpu, node);
+ pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+ cpu, size, __pa(ptr));
+ } else {
+ ptr = memblock_alloc_try_nid(size, align, goal,
+ MEMBLOCK_ALLOC_ACCESSIBLE, node);
+ pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
+ "%016lx\n", cpu, size, node, __pa(ptr));
+ }
+ return ptr;
+#else
+ return memblock_alloc_from(size, align, goal);
+#endif
}
-static void __init pcpu_fc_free(void *ptr, size_t size)
+static void __init pcpu_free_bootmem(void *ptr, size_t size)
{
memblock_free(__pa(ptr), size);
}
@@ -798,7 +827,7 @@ void __init setup_per_cpu_areas(void)
atom_size = 1 << 20;
rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
- pcpu_fc_alloc, pcpu_fc_free);
+ pcpu_alloc_bootmem, pcpu_free_bootmem);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
--
2.26.2
next reply other threads:[~2020-06-08 7:13 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-08 7:09 Aneesh Kumar K.V [this message]
2020-06-08 7:09 ` [PATCH v2 2/4] powerpc/64/mm: implement page mapping percpu first chunk allocator Aneesh Kumar K.V
2020-06-08 7:12 ` Aneesh Kumar K.V
2020-06-08 7:09 ` [PATCH v2 3/4] powerpc/book3s64/hash/4k: Support large linear mapping range with 4K Aneesh Kumar K.V
2020-06-08 7:09 ` [PATCH v2 4/4] powerpc/mm/book3s: Split radix and hash MAX_PHYSMEM limit Aneesh Kumar K.V
2020-09-17 11:27 ` [PATCH v2 1/4] powerpc/percpu: Update percpu bootmem allocator Michael Ellerman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200608070904.387440-1-aneesh.kumar@linux.ibm.com \
--to=aneesh.kumar@linux.ibm.com \
--cc=cam@neo-zeon.de \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).