Hi Chen,
On Sat, Mar 7, 2020 at 4:36 PM Chen Zhou <chenzhou10@xxxxxxxxxx> wrote:
>
>
>
> On 2020/3/5 18:13, Prabhakar Kushwaha wrote:
> > On Mon, Dec 23, 2019 at 8:57 PM Chen Zhou <chenzhou10@xxxxxxxxxx> wrote:
> >>
> >> Crashkernel=X tries to reserve memory for the crash dump kernel under
> >> 4G. If crashkernel=X,low is specified simultaneously, reserve spcified
> >> size low memory for crash kdump kernel devices firstly and then reserve
> >> memory above 4G.
> >>
> >> Signed-off-by: Chen Zhou <chenzhou10@xxxxxxxxxx>
> >> ---
> >> arch/arm64/kernel/setup.c | 8 +++++++-
> >> arch/arm64/mm/init.c | 31 +++++++++++++++++++++++++++++--
> >> 2 files changed, 36 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> >> index 56f6645..04d1c87 100644
> >> --- a/arch/arm64/kernel/setup.c
> >> +++ b/arch/arm64/kernel/setup.c
> >> @@ -238,7 +238,13 @@ static void __init request_standard_resources(void)
> >> kernel_data.end <= res->end)
> >> request_resource(res, &kernel_data);
> >> #ifdef CONFIG_KEXEC_CORE
> >> - /* Userspace will find "Crash kernel" region in /proc/iomem. */
> >> + /*
> >> + * Userspace will find "Crash kernel" region in /proc/iomem.
> >> + * Note: the low region is renamed as Crash kernel (low).
> >> + */
> >> + if (crashk_low_res.end && crashk_low_res.start >= res->start &&
> >> + crashk_low_res.end <= res->end)
> >> + request_resource(res, &crashk_low_res);
> >> if (crashk_res.end && crashk_res.start >= res->start &&
> >> crashk_res.end <= res->end)
> >> request_resource(res, &crashk_res);
> >> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> >> index b65dffd..0d7afd5 100644
> >> --- a/arch/arm64/mm/init.c
> >> +++ b/arch/arm64/mm/init.c
> >> @@ -80,6 +80,7 @@ static void __init reserve_crashkernel(void)
> >> {
> >> unsigned long long crash_base, crash_size;
> >> int ret;
> >> + phys_addr_t crash_max = arm64_dma32_phys_limit;
> >>
> >> ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> >> &crash_size, &crash_base);
> >> @@ -87,12 +88,38 @@ static void __init reserve_crashkernel(void)
> >> if (ret || !crash_size)
> >> return;
> >>
> >> + ret = reserve_crashkernel_low();
> >> + if (!ret && crashk_low_res.end) {
> >> + /*
> >> + * If crashkernel=X,low specified, there may be two regions,
> >> + * we need to make some changes as follows:
> >> + *
> >> + * 1. rename the low region as "Crash kernel (low)"
> >> + * In order to distinct from the high region and make no effect
> >> + * to the use of existing kexec-tools, rename the low region as
> >> + * "Crash kernel (low)".
> >> + *
> >> + * 2. change the upper bound for crash memory
> >> + * Set MEMBLOCK_ALLOC_ACCESSIBLE upper bound for crash memory.
> >> + *
> >> + * 3. mark the low region as "nomap"
> >> + * The low region is intended to be used for crash dump kernel
> >> + * devices, just mark the low region as "nomap" simply.
> >> + */
> >> + const char *rename = "Crash kernel (low)";
> >> +
> >> + crashk_low_res.name = rename;
> >> + crash_max = MEMBLOCK_ALLOC_ACCESSIBLE;
> >> + memblock_mark_nomap(crashk_low_res.start,
> >> + resource_size(&crashk_low_res));
> >> + }
> >> +
> >> crash_size = PAGE_ALIGN(crash_size);
> >>
> >> if (crash_base == 0) {
> >> /* Current arm64 boot protocol requires 2MB alignment */
> >> - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
> >> - crash_size, SZ_2M);
> >> + crash_base = memblock_find_in_range(0, crash_max, crash_size,
> >> + SZ_2M);
> >> if (crash_base == 0) {
> >> pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
> >> crash_size);
> >> --
> >
> > I tested this patch series on ARM64-ThunderX2 with no issue with
> > bootargs crashkenel=X@Y crashkernel=250M,low
> >
> > $ dmesg | grep crash
> > [ 0.000000] crashkernel reserved: 0x0000000b81200000 -
> > 0x0000000c81200000 (4096 MB)
> > [ 0.000000] Kernel command line:
> > BOOT_IMAGE=/boot/vmlinuz-5.6.0-rc4+
> > root=UUID=866b8df3-14f4-4e11-95a1-74a90ee9b694 ro
> > crashkernel=4G@0xb81200000 crashkernel=250M,low nowatchdog earlycon
> > [ 29.310209] crashkernel=250M,low
> >
> > $ kexec -p -i /boot/vmlinuz-`uname -r`
> > --initrd=/boot/initrd.img-`uname -r` --reuse-cmdline
> > $ echo 1 > /proc/sys/kernel/sysrq ; echo c > /proc/sysrq-trigger
> >
> > But when i tried with crashkernel=4G crashkernel=250M,low as bootargs.
> > Kernel is not able to allocate memory.
> > [ 0.000000] cannot allocate crashkernel (size:0x100000000)
> > [ 0.000000] Kernel command line:
> > BOOT_IMAGE=/boot/vmlinuz-5.6.0-rc4+
> > root=UUID=866b8df3-14f4-4e11-95a1-74a90ee9b694 ro crashkernel=4G
> > crashkernel=250M,low nowatchdog
> > [ 29.332081] crashkernel=250M,low
> >
> > does crashkernel=X@Y mandatory to get allocated beyond 4G?
> > am I missing something?
>
> I can't reproduce the problem in my environment, can you test with other size,
> such as "crashkernel=1G crashkernel=250M,low", see if there is the same issue.
>
I tried 1G also. Same error, please find the logs
$ dmesg | grep crash
[ 0.000000] cannot allocate crashkernel (size:0x40000000)
[ 0.000000] Kernel command line:
BOOT_IMAGE=/boot/vmlinuz-5.6.0-rc4+
root=UUID=866b8df3-14f4-4e11-95a1-74a90ee9b694 ro nowatchdog earlycon
crashkernel=1G crashkernel=250M,low
[ 29.326916] crashkernel=250M,low
> Besides, crashkernel=X@Y isn't mandatory to get allocated beyond 4G,
this was my understanding also.
> can you show the whole file /proc/iomem.
>
$ cat /proc/iomem
00000000-00000000 : PCI ECAM
00000000-00000000 : PCI ECAM
00000000-00000000 : PCI Bus 0000:00
00000000-00000000 : PCI Bus 0000:0f
00000000-00000000 : PCI Bus 0000:10
00000000-00000000 : 0000:10:00.0
00000000-00000000 : 0000:10:00.0
00000000-00000000 : PCI Bus 0000:01
00000000-00000000 : 0000:01:00.0
00000000-00000000 : 0000:01:00.1
00000000-00000000 : PCI Bus 0000:05
00000000-00000000 : 0000:05:00.0
00000000-00000000 : 0000:05:00.1
00000000-00000000 : PCI Bus 0000:09
00000000-00000000 : 0000:09:00.0
00000000-00000000 : 0000:09:00.1
00000000-00000000 : 0000:00:10.0
00000000-00000000 : ahci
00000000-00000000 : 0000:00:10.1
00000000-00000000 : ahci
00000000-00000000 : PCI Bus 0000:80
00000000-00000000 : PCI Bus 0000:83
00000000-00000000 : 0000:83:00.0
00000000-00000000 : 0000:83:00.0
00000000-00000000 : nvme
00000000-00000000 : PCI Bus 0000:89
00000000-00000000 : 0000:89:00.0
00000000-00000000 : e1000e
00000000-00000000 : 0000:89:00.0
00000000-00000000 : 0000:89:00.0
00000000-00000000 : e1000e
00000000-00000000 : 0000:89:00.0
00000000-00000000 : e1000e
00000000-00000000 : PCI Bus 0000:8d
00000000-00000000 : 0000:8d:00.0
00000000-00000000 : 0000:8d:00.0
00000000-00000000 : mpt3sas
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : Kernel code
00000000-00000000 : reserved
00000000-00000000 : Kernel data
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : CAV901C:00
00000000-00000000 : CAV901D:00
00000000-00000000 : CAV901C:00
00000000-00000000 : CAV901E:00
00000000-00000000 : CAV901C:00
00000000-00000000 : CAV901F:00
00000000-00000000 : CAV901C:00
00000000-00000000 : CAV9006:00
00000000-00000000 : CAV9006:00
00000000-00000000 : ARMH0011:00
00000000-00000000 : ARMH0011:00
00000000-00000000 : arm-smmu-v3.0.auto
00000000-00000000 : arm-smmu-v3.0.auto
00000000-00000000 : arm-smmu-v3.1.auto
00000000-00000000 : arm-smmu-v3.1.auto
00000000-00000000 : arm-smmu-v3.2.auto
00000000-00000000 : arm-smmu-v3.2.auto
00000000-00000000 : CAV901C:01
00000000-00000000 : CAV901D:01
00000000-00000000 : CAV901C:01
00000000-00000000 : CAV901E:01
00000000-00000000 : CAV901C:01
00000000-00000000 : CAV901F:01
00000000-00000000 : CAV901C:01
00000000-00000000 : CAV9007:06
00000000-00000000 : CAV9007:06
00000000-00000000 : arm-smmu-v3.3.auto
00000000-00000000 : arm-smmu-v3.3.auto
00000000-00000000 : arm-smmu-v3.4.auto
00000000-00000000 : arm-smmu-v3.4.auto
00000000-00000000 : arm-smmu-v3.5.auto
00000000-00000000 : arm-smmu-v3.5.auto
00000000-00000000 : System RAM
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : System RAM
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : reserved
00000000-00000000 : PCI Bus 0000:00
00000000-00000000 : PCI Bus 0000:01
00000000-00000000 : 0000:01:00.0
00000000-00000000 : 0000:01:00.1
00000000-00000000 : 0000:01:00.0
00000000-00000000 : 0000:01:00.1
00000000-00000000 : 0000:01:00.0
00000000-00000000 : 0000:01:00.1
00000000-00000000 : PCI Bus 0000:05
00000000-00000000 : 0000:05:00.0
00000000-00000000 : bnx2x
00000000-00000000 : 0000:05:00.1
00000000-00000000 : bnx2x
00000000-00000000 : 0000:05:00.0
00000000-00000000 : bnx2x
00000000-00000000 : 0000:05:00.0
00000000-00000000 : bnx2x
00000000-00000000 : 0000:05:00.1
00000000-00000000 : bnx2x
00000000-00000000 : 0000:05:00.1
00000000-00000000 : bnx2x
00000000-00000000 : PCI Bus 0000:09
00000000-00000000 : 0000:09:00.0
00000000-00000000 : i40e
00000000-00000000 : 0000:09:00.1
00000000-00000000 : i40e
00000000-00000000 : 0000:09:00.0
00000000-00000000 : 0000:09:00.1
00000000-00000000 : 0000:09:00.0
00000000-00000000 : i40e
00000000-00000000 : 0000:09:00.1
00000000-00000000 : i40e
00000000-00000000 : 0000:09:00.0
00000000-00000000 : 0000:09:00.1
00000000-00000000 : 0000:00:0f.0
00000000-00000000 : xhci-hcd
00000000-00000000 : 0000:00:0f.0
00000000-00000000 : 0000:00:0f.1
00000000-00000000 : xhci-hcd
00000000-00000000 : 0000:00:0f.1
00000000-00000000 : 0000:00:10.0
00000000-00000000 : ahci
00000000-00000000 : 0000:00:10.1
00000000-00000000 : ahci
00000000-00000000 : PCI Bus 0000:80
--pk
