When tpm_get_random() was introduced, it defined the following API for the
return value:
1. A positive value tells how many bytes of random data was generated.
2. A negative value on error.
However, in the call sites the API was used incorrectly, i.e. as it would
only return negative values and otherwise zero. Returning he positive read
counts to the user space does not make any possible sense.
Fix this by returning -EIO when tpm_get_random() returns a positive value.
Fixes: 41ab999c80f1 ("tpm: Move tpm_get_random api into the TPM device driver")
Cc: Kent Yoder <key(a)linux.vnet.ibm.com>
Cc: David Howells <dhowells(a)redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley(a)HansenPartnership.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com>
---
security/keys/trusted-keys/trusted_tpm1.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c
index b9fe02e5f84f..0f2e893c6b5f 100644
--- a/security/keys/trusted-keys/trusted_tpm1.c
+++ b/security/keys/trusted-keys/trusted_tpm1.c
@@ -403,9 +403,12 @@ static int osap(struct tpm_buf *tb, struct osapsess *s,
int ret;
ret = tpm_get_random(chip, ononce, TPM_NONCE_SIZE);
- if (ret != TPM_NONCE_SIZE)
+ if (ret < 0)
return ret;
+ if (ret != TPM_NONCE_SIZE)
+ return -EIO;
+
tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OSAP);
tpm_buf_append_u16(tb, type);
tpm_buf_append_u32(tb, handle);
@@ -496,8 +499,12 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype,
goto out;
ret = tpm_get_random(chip, td->nonceodd, TPM_NONCE_SIZE);
+ if (ret < 0)
+ return ret;
+
if (ret != TPM_NONCE_SIZE)
- goto out;
+ return -EIO;
+
ordinal = htonl(TPM_ORD_SEAL);
datsize = htonl(datalen);
pcrsize = htonl(pcrinfosize);
@@ -601,6 +608,9 @@ static int tpm_unseal(struct tpm_buf *tb,
ordinal = htonl(TPM_ORD_UNSEAL);
ret = tpm_get_random(chip, nonceodd, TPM_NONCE_SIZE);
+ if (ret < 0)
+ return -EIO;
+
if (ret != TPM_NONCE_SIZE) {
pr_info("trusted_key: tpm_get_random failed (%d)\n", ret);
return ret;
@@ -1013,6 +1023,11 @@ static int trusted_instantiate(struct key *key,
case Opt_new:
key_len = payload->key_len;
ret = tpm_get_random(chip, payload->key, key_len);
+ if (ret < 0) {
+ ret = -EIO;
+ goto out;
+ }
+
if (ret != key_len) {
pr_info("trusted_key: key_create failed (%d)\n", ret);
goto out;
--
2.25.1
The patch below does not apply to the 5.8-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From f3cd4850504ff612d0ea77a0aaf29b66c98fcefe Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe(a)kernel.dk>
Date: Thu, 24 Sep 2020 14:55:54 -0600
Subject: [PATCH] io_uring: ensure open/openat2 name is cleaned on cancelation
If we cancel these requests, we'll leak the memory associated with the
filename. Add them to the table of ops that need cleaning, if
REQ_F_NEED_CLEANUP is set.
Cc: stable(a)vger.kernel.org
Fixes: e62753e4e292 ("io_uring: call statx directly")
Reviewed-by: Stefano Garzarella <sgarzare(a)redhat.com>
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e6004b92e553..0ab16df31288 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5671,6 +5671,11 @@ static void __io_clean_op(struct io_kiocb *req)
io_put_file(req, req->splice.file_in,
(req->splice.flags & SPLICE_F_FD_IN_FIXED));
break;
+ case IORING_OP_OPENAT:
+ case IORING_OP_OPENAT2:
+ if (req->open.filename)
+ putname(req->open.filename);
+ break;
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
We only allow persistent requests to remain on the GPU past the closure
of their containing context (and process) so long as they are continuously
checked for hangs or allow other requests to preempt them, as we need to
ensure forward progress of the system. If we allow persistent contexts
to remain on the system after the the hangcheck mechanism is disabled,
the system may grind to a halt. On disabling the mechanism, we sent a
pulse along the engine to remove all executing contexts from the engine
which would check for hung contexts -- but we did not prevent those
contexts from being resubmitted if they survived the final hangcheck.
Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs")
Testcase: igt/gem_ctx_persistence/heartbeat-stop
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com>
Cc: <stable(a)vger.kernel.org> # v5.7+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com>
---
drivers/gpu/drm/i915/gt/intel_engine.h | 9 +++++++++
drivers/gpu/drm/i915/i915_request.c | 5 +++++
2 files changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 08e2c000dcc3..7c3a1012e702 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -337,4 +337,13 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
return intel_engine_has_preemption(engine);
}
+static inline bool
+intel_engine_has_heartbeat(const struct intel_engine_cs *engine)
+{
+ if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL))
+ return false;
+
+ return READ_ONCE(engine->props.heartbeat_interval_ms);
+}
+
#endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 436ce368ddaa..0e813819b041 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -542,8 +542,13 @@ bool __i915_request_submit(struct i915_request *request)
if (i915_request_completed(request))
goto xfer;
+ if (unlikely(intel_context_is_closed(request->context) &&
+ !intel_engine_has_heartbeat(engine)))
+ intel_context_set_banned(request->context);
+
if (unlikely(intel_context_is_banned(request->context)))
i915_request_set_error_once(request, -EIO);
+
if (unlikely(fatal_error(request->fence.error)))
__i915_request_skip(request);
--
2.20.1
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour(a)linux.ibm.com>
Date: Fri, 25 Sep 2020 21:19:31 -0700
Subject: [PATCH] mm: don't rely on system state to detect hot-plug operations
In register_mem_sect_under_node() the system_state's value is checked to
detect whether the call is made during boot time or during an hot-plug
operation. Unfortunately, that check against SYSTEM_BOOTING is wrong
because regular memory is registered at SYSTEM_SCHEDULING state. In
addition, memory hot-plug operation can be triggered at this system
state by the ACPI [1]. So checking against the system state is not
enough.
The consequence is that on system with interleaved node's ranges like this:
Early memory node ranges
node 1: [mem 0x0000000000000000-0x000000011fffffff]
node 2: [mem 0x0000000120000000-0x000000014fffffff]
node 1: [mem 0x0000000150000000-0x00000001ffffffff]
node 0: [mem 0x0000000200000000-0x000000048fffffff]
node 2: [mem 0x0000000490000000-0x00000007ffffffff]
This can be seen on PowerPC LPAR after multiple memory hot-plug and
hot-unplug operations are done. At the next reboot the node's memory
ranges can be interleaved and since the call to link_mem_sections() is
made in topology_init() while the system is in the SYSTEM_SCHEDULING
state, the node's id is not checked, and the sections registered to
multiple nodes:
$ ls -l /sys/devices/system/memory/memory21/node*
total 0
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2
In that case, the system is able to boot but if later one of theses
memory blocks is hot-unplugged and then hot-plugged, the sysfs
inconsistency is detected and this is triggering a BUG_ON():
kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4
CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25
Call Trace:
add_memory_resource+0x23c/0x340 (unreliable)
__add_memory+0x5c/0xf0
dlpar_add_lmb+0x1b4/0x500
dlpar_memory+0x1f8/0xb80
handle_dlpar_errorlog+0xc0/0x190
dlpar_store+0x198/0x4a0
kobj_attr_store+0x30/0x50
sysfs_kf_write+0x64/0x90
kernfs_fop_write+0x1b0/0x290
vfs_write+0xe8/0x290
ksys_write+0xdc/0x130
system_call_exception+0x160/0x270
system_call_common+0xf0/0x27c
This patch addresses the root cause by not relying on the system_state
value to detect whether the call is due to a hot-plug operation. An
extra parameter is added to link_mem_sections() detailing whether the
operation is due to a hot-plug operation.
[1] According to Oscar Salvador, using this qemu command line, ACPI
memory hotplug operations are raised at SYSTEM_SCHEDULING state:
$QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \
-m size=$MEM,slots=255,maxmem=4294967296k \
-numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \
-object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \
-object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \
-object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \
-object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \
-object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \
-object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \
-object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \
Fixes: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()")
Signed-off-by: Laurent Dufour <ldufour(a)linux.ibm.com>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Reviewed-by: David Hildenbrand <david(a)redhat.com>
Reviewed-by: Oscar Salvador <osalvador(a)suse.de>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael(a)kernel.org>
Cc: Fenghua Yu <fenghua.yu(a)intel.com>
Cc: Nathan Lynch <nathanl(a)linux.ibm.com>
Cc: Scott Cheloha <cheloha(a)linux.ibm.com>
Cc: Tony Luck <tony.luck(a)intel.com>
Cc: <stable(a)vger.kernel.org>
Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..50af16e68d98 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
return pfn_to_nid(pfn);
}
+static int do_register_memory_block_under_node(int nid,
+ struct memory_block *mem_blk)
+{
+ int ret;
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node.
+ */
+ mem_blk->nid = nid;
+
+ ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+ &mem_blk->dev.kobj,
+ kobject_name(&mem_blk->dev.kobj));
+ if (ret)
+ return ret;
+
+ return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+ &node_devices[nid]->dev.kobj,
+ kobject_name(&node_devices[nid]->dev.kobj));
+}
+
/* register memory section under specified node if it spans that node */
-static int register_mem_sect_under_node(struct memory_block *mem_blk,
- void *arg)
+static int register_mem_block_under_node_early(struct memory_block *mem_blk,
+ void *arg)
{
unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
- int ret, nid = *(int *)arg;
+ int nid = *(int *)arg;
unsigned long pfn;
for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
@@ -785,38 +807,33 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
}
/*
- * We need to check if page belongs to nid only for the boot
- * case, during hotplug we know that all pages in the memory
- * block belong to the same node.
- */
- if (system_state == SYSTEM_BOOTING) {
- page_nid = get_nid_for_pfn(pfn);
- if (page_nid < 0)
- continue;
- if (page_nid != nid)
- continue;
- }
-
- /*
- * If this memory block spans multiple nodes, we only indicate
- * the last processed node.
+ * We need to check if page belongs to nid only at the boot
+ * case because node's ranges can be interleaved.
*/
- mem_blk->nid = nid;
-
- ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
- &mem_blk->dev.kobj,
- kobject_name(&mem_blk->dev.kobj));
- if (ret)
- return ret;
+ page_nid = get_nid_for_pfn(pfn);
+ if (page_nid < 0)
+ continue;
+ if (page_nid != nid)
+ continue;
- return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
- &node_devices[nid]->dev.kobj,
- kobject_name(&node_devices[nid]->dev.kobj));
+ return do_register_memory_block_under_node(nid, mem_blk);
}
/* mem section does not span the specified node */
return 0;
}
+/*
+ * During hotplug we know that all pages in the memory block belong to the same
+ * node.
+ */
+static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
+ void *arg)
+{
+ int nid = *(int *)arg;
+
+ return do_register_memory_block_under_node(nid, mem_blk);
+}
+
/*
* Unregister a memory block device under the node it spans. Memory blocks
* with multiple nodes cannot be offlined and therefore also never be removed.
@@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum meminit_context context)
{
+ walk_memory_blocks_func_t func;
+
+ if (context == MEMINIT_HOTPLUG)
+ func = register_mem_block_under_node_hotplug;
+ else
+ func = register_mem_block_under_node_early;
+
return walk_memory_blocks(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
- register_mem_sect_under_node);
+ func);
}
#ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/node.h b/include/linux/node.h
index 4866f32a02d8..014ba3ab2efd 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,11 +99,13 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn);
+int link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context);
#else
static inline int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn)
+ unsigned long end_pfn,
+ enum meminit_context context)
{
return 0;
}
@@ -128,7 +130,8 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, start_pfn, end_pfn);
+ error = link_mem_sections(nid, start_pfn, end_pfn,
+ MEMINIT_EARLY);
}
return error;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 345308a8bd15..ce3e73e3a5c1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
}
/* link memory sections under this node.*/
- ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
+ ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+ MEMINIT_HOTPLUG);
BUG_ON(ret);
/* create new memmap entry */
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour(a)linux.ibm.com>
Date: Fri, 25 Sep 2020 21:19:31 -0700
Subject: [PATCH] mm: don't rely on system state to detect hot-plug operations
In register_mem_sect_under_node() the system_state's value is checked to
detect whether the call is made during boot time or during an hot-plug
operation. Unfortunately, that check against SYSTEM_BOOTING is wrong
because regular memory is registered at SYSTEM_SCHEDULING state. In
addition, memory hot-plug operation can be triggered at this system
state by the ACPI [1]. So checking against the system state is not
enough.
The consequence is that on system with interleaved node's ranges like this:
Early memory node ranges
node 1: [mem 0x0000000000000000-0x000000011fffffff]
node 2: [mem 0x0000000120000000-0x000000014fffffff]
node 1: [mem 0x0000000150000000-0x00000001ffffffff]
node 0: [mem 0x0000000200000000-0x000000048fffffff]
node 2: [mem 0x0000000490000000-0x00000007ffffffff]
This can be seen on PowerPC LPAR after multiple memory hot-plug and
hot-unplug operations are done. At the next reboot the node's memory
ranges can be interleaved and since the call to link_mem_sections() is
made in topology_init() while the system is in the SYSTEM_SCHEDULING
state, the node's id is not checked, and the sections registered to
multiple nodes:
$ ls -l /sys/devices/system/memory/memory21/node*
total 0
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2
In that case, the system is able to boot but if later one of theses
memory blocks is hot-unplugged and then hot-plugged, the sysfs
inconsistency is detected and this is triggering a BUG_ON():
kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4
CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25
Call Trace:
add_memory_resource+0x23c/0x340 (unreliable)
__add_memory+0x5c/0xf0
dlpar_add_lmb+0x1b4/0x500
dlpar_memory+0x1f8/0xb80
handle_dlpar_errorlog+0xc0/0x190
dlpar_store+0x198/0x4a0
kobj_attr_store+0x30/0x50
sysfs_kf_write+0x64/0x90
kernfs_fop_write+0x1b0/0x290
vfs_write+0xe8/0x290
ksys_write+0xdc/0x130
system_call_exception+0x160/0x270
system_call_common+0xf0/0x27c
This patch addresses the root cause by not relying on the system_state
value to detect whether the call is due to a hot-plug operation. An
extra parameter is added to link_mem_sections() detailing whether the
operation is due to a hot-plug operation.
[1] According to Oscar Salvador, using this qemu command line, ACPI
memory hotplug operations are raised at SYSTEM_SCHEDULING state:
$QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \
-m size=$MEM,slots=255,maxmem=4294967296k \
-numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \
-object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \
-object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \
-object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \
-object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \
-object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \
-object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \
-object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \
Fixes: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()")
Signed-off-by: Laurent Dufour <ldufour(a)linux.ibm.com>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Reviewed-by: David Hildenbrand <david(a)redhat.com>
Reviewed-by: Oscar Salvador <osalvador(a)suse.de>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael(a)kernel.org>
Cc: Fenghua Yu <fenghua.yu(a)intel.com>
Cc: Nathan Lynch <nathanl(a)linux.ibm.com>
Cc: Scott Cheloha <cheloha(a)linux.ibm.com>
Cc: Tony Luck <tony.luck(a)intel.com>
Cc: <stable(a)vger.kernel.org>
Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..50af16e68d98 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
return pfn_to_nid(pfn);
}
+static int do_register_memory_block_under_node(int nid,
+ struct memory_block *mem_blk)
+{
+ int ret;
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node.
+ */
+ mem_blk->nid = nid;
+
+ ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+ &mem_blk->dev.kobj,
+ kobject_name(&mem_blk->dev.kobj));
+ if (ret)
+ return ret;
+
+ return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+ &node_devices[nid]->dev.kobj,
+ kobject_name(&node_devices[nid]->dev.kobj));
+}
+
/* register memory section under specified node if it spans that node */
-static int register_mem_sect_under_node(struct memory_block *mem_blk,
- void *arg)
+static int register_mem_block_under_node_early(struct memory_block *mem_blk,
+ void *arg)
{
unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
- int ret, nid = *(int *)arg;
+ int nid = *(int *)arg;
unsigned long pfn;
for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
@@ -785,38 +807,33 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
}
/*
- * We need to check if page belongs to nid only for the boot
- * case, during hotplug we know that all pages in the memory
- * block belong to the same node.
- */
- if (system_state == SYSTEM_BOOTING) {
- page_nid = get_nid_for_pfn(pfn);
- if (page_nid < 0)
- continue;
- if (page_nid != nid)
- continue;
- }
-
- /*
- * If this memory block spans multiple nodes, we only indicate
- * the last processed node.
+ * We need to check if page belongs to nid only at the boot
+ * case because node's ranges can be interleaved.
*/
- mem_blk->nid = nid;
-
- ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
- &mem_blk->dev.kobj,
- kobject_name(&mem_blk->dev.kobj));
- if (ret)
- return ret;
+ page_nid = get_nid_for_pfn(pfn);
+ if (page_nid < 0)
+ continue;
+ if (page_nid != nid)
+ continue;
- return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
- &node_devices[nid]->dev.kobj,
- kobject_name(&node_devices[nid]->dev.kobj));
+ return do_register_memory_block_under_node(nid, mem_blk);
}
/* mem section does not span the specified node */
return 0;
}
+/*
+ * During hotplug we know that all pages in the memory block belong to the same
+ * node.
+ */
+static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
+ void *arg)
+{
+ int nid = *(int *)arg;
+
+ return do_register_memory_block_under_node(nid, mem_blk);
+}
+
/*
* Unregister a memory block device under the node it spans. Memory blocks
* with multiple nodes cannot be offlined and therefore also never be removed.
@@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum meminit_context context)
{
+ walk_memory_blocks_func_t func;
+
+ if (context == MEMINIT_HOTPLUG)
+ func = register_mem_block_under_node_hotplug;
+ else
+ func = register_mem_block_under_node_early;
+
return walk_memory_blocks(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
- register_mem_sect_under_node);
+ func);
}
#ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/node.h b/include/linux/node.h
index 4866f32a02d8..014ba3ab2efd 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,11 +99,13 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn);
+int link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context);
#else
static inline int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn)
+ unsigned long end_pfn,
+ enum meminit_context context)
{
return 0;
}
@@ -128,7 +130,8 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, start_pfn, end_pfn);
+ error = link_mem_sections(nid, start_pfn, end_pfn,
+ MEMINIT_EARLY);
}
return error;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 345308a8bd15..ce3e73e3a5c1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
}
/* link memory sections under this node.*/
- ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
+ ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+ MEMINIT_HOTPLUG);
BUG_ON(ret);
/* create new memmap entry */