Hi Sasha,
I noticed build error on latest stable-rc/queue/5.4 branch:
util/parse-events.c: In function 'parse_events_add_pmu':
util/parse-events.c:1373:11: error: 'struct perf_evsel_config_term'
has no member named 'free_str'
if (pos->free_str)
^~
In file included from util/parse-events.c:4:
util/parse-events.c:1374:20: error: 'union <anonymous>' has no member
named 'str'
zfree(&pos->val.str);
^
/<<PKGBUILDDIR>>/tools/include/linux/zalloc.h:10:38: note: in
definition of macro 'zfree'
#define zfree(ptr) __zfree((void **)(ptr))
revert both
d6ac1bd91161 ("perf parse-events: Fix incorrect conversion of 'if ()
free()' to 'zfree()'")
b6f48cb0c18b ("perf parse-events: Fix memory leaks found on parse_events")
Fixed the problem.
Thanks!
--
Jinpu Wang
Linux Kernel Developer
Application Support (IONOS Cloud)
1&1 IONOS SE | Greifswalder Str. 207 | 10405 Berlin | Germany
Phone:
E-mail: jinpu.wang(a)cloud.ionos.com | Web: www.ionos.de
Hauptsitz Montabaur, Amtsgericht Montabaur, HRB 24498
Vorstand: Dr. Christian Böing, Hüseyin Dogan, Dr. Martin Endreß,
Hans-Henning Kettler, Arthur Mai, Matthias Steinberg, Achim Weiß
Aufsichtsratsvorsitzender: Markus Kadelke
Member of United Internet
Diese E-Mail kann vertrauliche und/oder gesetzlich geschützte
Informationen enthalten. Wenn Sie nicht der bestimmungsgemäße Adressat
sind oder diese E-Mail irrtümlich erhalten haben, unterrichten Sie
bitte den Absender und vernichten Sie diese E-Mail. Anderen als dem
bestimmungsgemäßen Adressaten ist untersagt, diese E-Mail zu
speichern, weiterzuleiten oder ihren Inhalt auf welche Weise auch
immer zu verwenden.
This e-mail may contain confidential and/or privileged information. If
you are not the intended recipient of this e-mail, you are hereby
notified that saving, distribution or use of the content of this
e-mail in any way is prohibited. If you have received this e-mail in
error, please notify the sender and delete the e-mail.
From: Jia He <justin.he(a)arm.com>
[ Upstream commit 83d116c53058d505ddef051e90ab27f57015b025 ]
When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there
will be a double page fault in __copy_from_user_inatomic of cow_user_page.
To reproduce the bug, the cmd is as follows after you deployed everything:
make -C src/test/vmmalloc_fork/ TEST_TIME=60m check
Below call trace is from arm64 do_page_fault for debugging purpose:
[ 110.016195] Call trace:
[ 110.016826] do_page_fault+0x5a4/0x690
[ 110.017812] do_mem_abort+0x50/0xb0
[ 110.018726] el1_da+0x20/0xc4
[ 110.019492] __arch_copy_from_user+0x180/0x280
[ 110.020646] do_wp_page+0xb0/0x860
[ 110.021517] __handle_mm_fault+0x994/0x1338
[ 110.022606] handle_mm_fault+0xe8/0x180
[ 110.023584] do_page_fault+0x240/0x690
[ 110.024535] do_mem_abort+0x50/0xb0
[ 110.025423] el0_da+0x20/0x24
The pte info before __copy_from_user_inatomic is (PTE_AF is cleared):
[ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003,
pmd=000000023d4b3003, pte=360000298607bd3
As told by Catalin: "On arm64 without hardware Access Flag, copying from
user will fail because the pte is old and cannot be marked young. So we
always end up with zeroed page after fork() + CoW for pfn mappings. we
don't always have a hardware-managed access flag on arm64."
This patch fixes it by calling pte_mkyoung. Also, the parameter is
changed because vmf should be passed to cow_user_page()
Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error
in case there can be some obscure use-case (by Kirill).
[1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork
Signed-off-by: Jia He <justin.he(a)arm.com>
Reported-by: Yibo Cai <Yibo.Cai(a)arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
mm/memory.c | 104 ++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 89 insertions(+), 15 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index e9bce27bc18c3..07188929a30a1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -117,6 +117,18 @@ int randomize_va_space __read_mostly =
2;
#endif
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+ /*
+ * Those arches which don't have hw access flag feature need to
+ * implement their own helper. By default, "true" means pagefault
+ * will be hit on old pte.
+ */
+ return true;
+}
+#endif
+
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
@@ -2324,32 +2336,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
return same;
}
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+ struct vm_fault *vmf)
{
+ bool ret;
+ void *kaddr;
+ void __user *uaddr;
+ bool force_mkyoung;
+ struct vm_area_struct *vma = vmf->vma;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long addr = vmf->address;
+
debug_dma_assert_idle(src);
+ if (likely(src)) {
+ copy_user_highpage(dst, src, addr, vma);
+ return true;
+ }
+
/*
* If the source page was a PFN mapping, we don't have
* a "struct page" for it. We do a best-effort copy by
* just copying from the original user address. If that
* fails, we just zero-fill it. Live with it.
*/
- if (unlikely(!src)) {
- void *kaddr = kmap_atomic(dst);
- void __user *uaddr = (void __user *)(va & PAGE_MASK);
+ kaddr = kmap_atomic(dst);
+ uaddr = (void __user *)(addr & PAGE_MASK);
+
+ /*
+ * On architectures with software "accessed" bits, we would
+ * take a double page fault, so mark it accessed here.
+ */
+ force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte);
+ if (force_mkyoung) {
+ pte_t entry;
+
+ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+ if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+ /*
+ * Other thread has already handled the fault
+ * and we don't need to do anything. If it's
+ * not the case, the fault will be triggered
+ * again on the same address.
+ */
+ ret = false;
+ goto pte_unlock;
+ }
+ entry = pte_mkyoung(vmf->orig_pte);
+ if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
+ update_mmu_cache(vma, addr, vmf->pte);
+ }
+
+ /*
+ * This really shouldn't fail, because the page is there
+ * in the page tables. But it might just be unreadable,
+ * in which case we just give up and fill the result with
+ * zeroes.
+ */
+ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
/*
- * This really shouldn't fail, because the page is there
- * in the page tables. But it might just be unreadable,
- * in which case we just give up and fill the result with
- * zeroes.
+ * Give a warn in case there can be some obscure
+ * use-case
*/
- if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
- clear_page(kaddr);
- kunmap_atomic(kaddr);
- flush_dcache_page(dst);
- } else
- copy_user_highpage(dst, src, va, vma);
+ WARN_ON_ONCE(1);
+ clear_page(kaddr);
+ }
+
+ ret = true;
+
+pte_unlock:
+ if (force_mkyoung)
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ kunmap_atomic(kaddr);
+ flush_dcache_page(dst);
+
+ return ret;
}
static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2503,7 +2565,19 @@ static int wp_page_copy(struct vm_fault *vmf)
vmf->address);
if (!new_page)
goto oom;
- cow_user_page(new_page, old_page, vmf->address, vma);
+
+ if (!cow_user_page(new_page, old_page, vmf)) {
+ /*
+ * COW failed, if the fault was solved by other,
+ * it's fine. If not, userspace would re-fault on
+ * the same address and we will handle the fault
+ * from the second attempt.
+ */
+ put_page(new_page);
+ if (old_page)
+ put_page(old_page);
+ return 0;
+ }
}
if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
--
2.25.1
Hello,
We ran automated tests on a recent commit from this kernel tree:
Kernel repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Commit: 3df2b9c0d66b - lib/string.c: implement stpcpy
The results of these automated tests are provided below.
Overall result: PASSED
Merge: OK
Compile: OK
Tests: OK
All kernel binaries, config files, and logs are available for download here:
https://arr-cki-prod-datawarehouse-public.s3.amazonaws.com/index.html?prefi…
Please reply to this email if you have any questions about the tests that we
ran or if you have any suggestions on how to make future tests more effective.
,-. ,-.
( C ) ( K ) Continuous
`-',-.`-' Kernel
( I ) Integration
`-'
______________________________________________________________________________
Compile testing
---------------
We compiled the kernel for 4 architectures:
aarch64:
make options: make -j30 INSTALL_MOD_STRIP=1 targz-pkg
ppc64le:
make options: make -j30 INSTALL_MOD_STRIP=1 targz-pkg
s390x:
make options: make -j30 INSTALL_MOD_STRIP=1 targz-pkg
x86_64:
make options: make -j30 INSTALL_MOD_STRIP=1 targz-pkg
Hardware testing
----------------
We booted each kernel and ran the following tests:
aarch64:
Host 1:
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
✅ stress: stress-ng
🚧 ✅ xfstests - btrfs
🚧 ✅ IPMI driver test
🚧 ✅ IPMItool loop stress test
🚧 ✅ Storage blktests
🚧 ❌ Storage nvme - tcp
Host 2:
✅ Boot test
✅ ACPI table test
✅ ACPI enabled test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory: fork_mem
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking: igmp conformance test
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
✅ storage: SCSI VPD
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ Firmware test suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
🚧 ✅ kdump - kexec_boot
ppc64le:
Host 1:
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
🚧 ✅ xfstests - btrfs
🚧 ✅ IPMI driver test
🚧 ✅ IPMItool loop stress test
🚧 ✅ Storage blktests
🚧 ✅ Storage nvme - tcp
Host 2:
✅ Boot test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory: fork_mem
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
Host 3:
⚡ Internal infrastructure issues prevented one or more tests (marked
with ⚡⚡⚡) from running on this architecture.
This is not the fault of the kernel that was tested.
⚡⚡⚡ Boot test
🚧 ⚡⚡⚡ kdump - sysrq-c
Host 4:
✅ Boot test
🚧 ✅ kdump - sysrq-c
s390x:
Host 1:
✅ Boot test
✅ selinux-policy: serge-testsuite
✅ stress: stress-ng
🚧 ✅ Storage blktests
🚧 ✅ Storage nvme - tcp
Host 2:
✅ Boot test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory: fork_mem
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
x86_64:
Host 1:
⚡ Internal infrastructure issues prevented one or more tests (marked
with ⚡⚡⚡) from running on this architecture.
This is not the fault of the kernel that was tested.
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
✅ stress: stress-ng
🚧 ❌ CPU: Frequency Driver Test
🚧 ✅ xfstests - btrfs
🚧 ⚡⚡⚡ IOMMU boot test
🚧 ⚡⚡⚡ IPMI driver test
🚧 ⚡⚡⚡ IPMItool loop stress test
🚧 ⚡⚡⚡ power-management: cpupower/sanity test
🚧 ⚡⚡⚡ Storage blktests
🚧 ⚡⚡⚡ Storage nvme - tcp
Host 2:
✅ Boot test
✅ ACPI table test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory: fork_mem
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking: igmp conformance test
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: sanity smoke test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
✅ storage: SCSI VPD
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ Firmware test suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
🚧 ✅ kdump - kexec_boot
Host 3:
✅ Boot test
🚧 ✅ kdump - sysrq-c
🚧 ✅ kdump - file-load
Test sources: https://gitlab.com/cki-project/kernel-tests
💚 Pull requests are welcome for new tests or improvements to existing tests!
Aborted tests
-------------
Tests that didn't complete running successfully are marked with ⚡⚡⚡.
If this was caused by an infrastructure issue, we try to mark that
explicitly in the report.
Waived tests
------------
If the test run included waived tests, they are marked with 🚧. Such tests are
executed but their results are not taken into account. Tests are waived when
their results are not reliable enough, e.g. when they're just introduced or are
being fixed.
Testing timeout
---------------
We aim to provide a report within reasonable timeframe. Tests that haven't
finished running yet are marked with ⏱.
The patch titled
Subject: mm: don't rely on system state to detect hot-plug operations
has been removed from the -mm tree. Its filename was
mm-dont-rely-on-system-state-to-detect-hot-plug-operations.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Laurent Dufour <ldufour(a)linux.ibm.com>
Subject: 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():
------------[ cut here ]------------
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
NIP: c000000000403f34 LR: c000000000403f2c CTR: 0000000000000000
REGS: c0000004876e3660 TRAP: 0700 Not tainted (5.9.0-rc1+)
MSR: 800000000282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 24000448 XER: 20040000
CFAR: c000000000846d20 IRQMASK: 0
GPR00: c000000000403f2c c0000004876e38f0 c0000000012f6f00 ffffffffffffffef
GPR04: 0000000000000227 c0000004805ae680 0000000000000000 00000004886f0000
GPR08: 0000000000000226 0000000000000003 0000000000000002 fffffffffffffffd
GPR12: 0000000088000484 c00000001ec96280 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000004 0000000000000003
GPR20: c00000047814ffe0 c0000007ffff7c08 0000000000000010 c0000000013332c8
GPR24: 0000000000000000 c0000000011f6cc0 0000000000000000 0000000000000000
GPR28: ffffffffffffffef 0000000000000001 0000000150000000 0000000010000000
NIP [c000000000403f34] add_memory_resource+0x244/0x340
LR [c000000000403f2c] add_memory_resource+0x23c/0x340
Call Trace:
[c0000004876e38f0] [c000000000403f2c] add_memory_resource+0x23c/0x340 (unreliable)
[c0000004876e39c0] [c00000000040408c] __add_memory+0x5c/0xf0
[c0000004876e39f0] [c0000000000e2b94] dlpar_add_lmb+0x1b4/0x500
[c0000004876e3ad0] [c0000000000e3888] dlpar_memory+0x1f8/0xb80
[c0000004876e3b60] [c0000000000dc0d0] handle_dlpar_errorlog+0xc0/0x190
[c0000004876e3bd0] [c0000000000dc398] dlpar_store+0x198/0x4a0
[c0000004876e3c90] [c00000000072e630] kobj_attr_store+0x30/0x50
[c0000004876e3cb0] [c00000000051f954] sysfs_kf_write+0x64/0x90
[c0000004876e3cd0] [c00000000051ee40] kernfs_fop_write+0x1b0/0x290
[c0000004876e3d20] [c000000000438dd8] vfs_write+0xe8/0x290
[c0000004876e3d70] [c0000000004391ac] ksys_write+0xdc/0x130
[c0000004876e3dc0] [c000000000034e40] system_call_exception+0x160/0x270
[c0000004876e3e20] [c00000000000d740] system_call_common+0xf0/0x27c
Instruction dump:
48442e35 60000000 0b030000 3cbe0001 7fa3eb78 7bc48402 38a5fffe 7ca5fa14
78a58402 48442db1 60000000 7c7c1b78 <0b030000> 7f23cb78 4bda371d 60000000
---[ end trace 562fd6c109cd0fb2 ]---
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 \
Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com
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>
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>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
drivers/base/node.c | 85 ++++++++++++++++++++++++++---------------
include/linux/node.h | 11 +++--
mm/memory_hotplug.c | 3 -
3 files changed, 64 insertions(+), 35 deletions(-)
--- a/drivers/base/node.c~mm-dont-rely-on-system-state-to-detect-hot-plug-operations
+++ a/drivers/base/node.c
@@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigne
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++) {
@@ -785,39 +807,34 @@ static int register_mem_sect_under_node(
}
/*
- * 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
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
--- a/include/linux/node.h~mm-dont-rely-on-system-state-to-detect-hot-plug-operations
+++ a/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
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;
--- a/mm/memory_hotplug.c~mm-dont-rely-on-system-state-to-detect-hot-plug-operations
+++ a/mm/memory_hotplug.c
@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, s
}
/* 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 */
_
Patches currently in -mm which might be from ldufour(a)linux.ibm.com are
mm-dont-panic-when-links-cant-be-created-in-sysfs.patch