[PATCH v22 1/8] arm64: kdump: reserve memory for crash dump kernel

From: takahiro.akashi@linaro.org (AKASHI Takahiro)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v22 1/8] arm64: kdump: reserve memory for crash dump kernel
Date: Wed, 20 Jul 2016 08:34:54 +0900	[thread overview]
Message-ID: <20160719233452.GG20774@linaro.org> (raw)
In-Reply-To: <1468932537.27473.6.camel@redhat.com>

On Tue, Jul 19, 2016 at 08:48:57AM -0400, Mark Salter wrote:
> On Tue, 2016-07-19 at 18:41 +0800, Dennis Chen wrote:
> > On Tue, Jul 19, 2016 at 07:28:16PM +0900, AKASHI Takahiro wrote:
> > > 
> > > On Tue, Jul 19, 2016 at 05:39:07PM +0800, Dennis Chen wrote:
> > > > 
> > > > Hello AKASHI,
> > > > 
> > > > On Tue, Jul 12, 2016 at 02:05:07PM +0900, AKASHI Takahiro wrote:
> > > > > 
> > > > > On the startup of primary kernel, the memory region used by crash dump
> > > > > kernel must be specified by "crashkernel=" kernel parameter.
> > > > > reserve_crashkernel() will allocate and reserve the region for later use.
> > > > > 
> > > > > User space tools, like kexec-tools, will be able to find that region as
> > > > > ????????????- "Crash kernel" in /proc/iomem, or
> > > > > ????????????- "linux,crashkernel-base" and "linux,crashkernel-size" under
> > > > > ????????????????/sys/firmware/devicetree/base/chosen
> > > > > 
> > > > > Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> > > > > Signed-off-by: Mark Salter <msalter@redhat.com>
> > > > > Signed-off-by: Pratyush Anand <panand@redhat.com>
> > > > > Reviewed-by: James Morse <james.morse@arm.com>
> > > > > ---
> > > > > ??arch/arm64/kernel/setup.c |??????7 ++-
> > > > > ??arch/arm64/mm/init.c????????????| 115 ++++++++++++++++++++++++++++++++++++++++++++++
> > > > > ??2 files changed, 121 insertions(+), 1 deletion(-)
> > > > > 
> > > > > diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> > > > > index c1509e6..cb5eee0 100644
> > > > > --- a/arch/arm64/kernel/setup.c
> > > > > +++ b/arch/arm64/kernel/setup.c
> > > > > @@ -31,7 +31,6 @@
> > > > > ??#include <linux/screen_info.h>
> > > > > ??#include <linux/init.h>
> > > > > ??#include <linux/kexec.h>
> > > > > -#include <linux/crash_dump.h>
> > > > > ??#include <linux/root_dev.h>
> > > > > ??#include <linux/cpu.h>
> > > > > ??#include <linux/interrupt.h>
> > > > > @@ -222,6 +221,12 @@ static void __init request_standard_resources(void)
> > > > > ????????????????????????????????????kernel_data.end <= res->end)
> > > > > ????????????????????????????????????????????request_resource(res, &kernel_data);
> > > > > ????????????}
> > > > > +
> > > > > +#ifdef CONFIG_KEXEC_CORE
> > > > > +??????????/* User space tools will find "Crash kernel" region in /proc/iomem. */
> > > > > +??????????if (crashk_res.end)
> > > > > +??????????????????????????insert_resource(&iomem_resource, &crashk_res);
> > > > > +#endif
> > > > > ??}
> > > > > 
> > > > > ??u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
> > > > > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> > > > > index 2ade7a6..51b1302 100644
> > > > > --- a/arch/arm64/mm/init.c
> > > > > +++ b/arch/arm64/mm/init.c
> > > > > @@ -29,11 +29,13 @@
> > > > > ??#include <linux/gfp.h>
> > > > > ??#include <linux/memblock.h>
> > > > > ??#include <linux/sort.h>
> > > > > +#include <linux/of.h>
> > > > > ??#include <linux/of_fdt.h>
> > > > > ??#include <linux/dma-mapping.h>
> > > > > ??#include <linux/dma-contiguous.h>
> > > > > ??#include <linux/efi.h>
> > > > > ??#include <linux/swiotlb.h>
> > > > > +#include <linux/kexec.h>
> > > > > 
> > > > > ??#include <asm/boot.h>
> > > > > ??#include <asm/fixmap.h>
> > > > > @@ -76,6 +78,117 @@ static int __init early_initrd(char *p)
> > > > > ??early_param("initrd", early_initrd);
> > > > > ??#endif
> > > > > 
> > > > > +#ifdef CONFIG_KEXEC_CORE
> > > > > +static unsigned long long crash_size, crash_base;
> > > > > +static struct property crash_base_prop = {
> > > > > +??????????.name = "linux,crashkernel-base",
> > > > > +??????????.length = sizeof(u64),
> > > > > +??????????.value = &crash_base
> > > > > +};
> > > > > +static struct property crash_size_prop = {
> > > > > +??????????.name = "linux,crashkernel-size",
> > > > > +??????????.length = sizeof(u64),
> > > > > +??????????.value = &crash_size,
> > > > > +};
> > > > > +
> > > > > +static int __init export_crashkernel(void)
> > > > > +{
> > > > > +??????????struct device_node *node;
> > > > > +??????????int ret;
> > > > > +
> > > > > +??????????if (!crashk_res.end)
> > > > > +??????????????????????????return 0;
> > > > > +
> > > > > +??????????crash_base = cpu_to_be64(crashk_res.start);
> > > > > +??????????crash_size = cpu_to_be64(crashk_res.end - crashk_res.start + 1);
> > > > > +
> > > > > +??????????/* Add /chosen/linux,crashkernel-* properties */
> > > > > +??????????node = of_find_node_by_path("/chosen");
> > > > > +??????????if (!node)
> > > > > +??????????????????????????return -ENOENT;
> > > > > +
> > > > > +??????????/*
> > > > > +????????????* There might be existing crash kernel properties, but we can't
> > > > > +????????????* be sure what's in them, so remove them.
> > > > > +????????????*/
> > > > > +??????????of_remove_property(node, of_find_property(node,
> > > > > +??????????????????????????????????????????????????????????"linux,crashkernel-base", NULL));
> > > > > +??????????of_remove_property(node, of_find_property(node,
> > > > > +??????????????????????????????????????????????????????????"linux,crashkernel-size", NULL));
> > > > > +
> > > > > +??????????ret = of_add_property(node, &crash_base_prop);
> > > > > +??????????if (ret)
> > > > > +??????????????????????????goto ret_err;
> > > > > +
> > > > > +??????????ret = of_add_property(node, &crash_size_prop);
> > > > > +??????????if (ret)
> > > > > +??????????????????????????goto ret_err;
> > > > > +
> > > > > +??????????return 0;
> > > > > +
> > > > > +ret_err:
> > > > > +??????????pr_warn("Exporting crashkernel region to device tree failed\n");
> > > > > +??????????return ret;
> > > > > +}
> > > > > +late_initcall(export_crashkernel);
> > > > > +
> > > > > +/*
> > > > > + * reserve_crashkernel() - reserves memory for crash kernel
> > > > > + *
> > > > > + * This function reserves memory area given in "crashkernel=" kernel command
> > > > > + * line parameter. The memory reserved is used by dump capture kernel when
> > > > > + * primary kernel is crashing.
> > > > > + */
> > > > > +static void __init reserve_crashkernel(void)
> > > > > +{
> > > > > +??????????int ret;
> > > > > +
> > > > > +??????????ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> > > > > +??????????????????????????????????????????????????????????&crash_size, &crash_base);
> > > > > +??????????/* no crashkernel= or invalid value specified */
> > > > > +??????????if (ret || !crash_size)
> > > > > +??????????????????????????return;
> > > > > +
> > > > > +??????????if (crash_base == 0) {
> > > > > +??????????????????????????/* Current arm64 boot protocol requires 2MB alignment */
> > > > > +??????????????????????????crash_base = memblock_find_in_range(0,
> > > > > +??????????????????????????????????????????????????????????MEMBLOCK_ALLOC_ACCESSIBLE, crash_size, SZ_2M);
> > > > > +??????????????????????????if (crash_base == 0) {
> > > > > +??????????????????????????????????????????pr_warn("Unable to allocate crashkernel (size:%llx)\n",
> > > > > +??????????????????????????????????????????????????????????crash_size);
> > > > > +??????????????????????????????????????????return;
> > > > > +??????????????????????????}
> > > > > +??????????????????????????memblock_reserve(crash_base, crash_size);
> > > > > 
> > > > I am not pretty sure the context here, but
> > > > can we use below code piece instead of the above lines?
> > > > ????????????????if (crash_base == 0)
> > > > ????????????????????????????????memblock_alloc(crash_size, SZ_2M);
> > > Either would be fine here.
> > > 
> > Hello AKASHI, maybe you can succeed to find the base with memblock_find_in_range(),??
> > but that doesn't mean you will also succeed to reserve them with memblock_reserve followed.
> 
> We avoid memblock_alloc() here because it panics on failure. This could happen

Thank you for pointing this out. I forgot it.

> if user asks for an unusually large crashkernel size. Better to print a message
> and keep booting. Checking the return value of memblock_reserve() seems like a
> good thing to do though.

Yeah, but it is unlikely that the function fails in this context (just
after find_in_range at early boot time) and nobody in arm64/mm/*.c checks
a return value of memblock_reserve() as well.
So I want to keep the code unchanged.

Thanks,
-Takahiro AKASHI

> 
> > 
> > Thanks,
> > Dennis
> > > 
> > > 
> > > Thanks,
> > > -Takahiro AKASHI
> > > 
> > > > 
> > > > Thanks,
> > > > Dennis
> > > > 
> > > > > 
> > > > > +
> > > > > +??????????} else {
> > > > > +??????????????????????????/* User specifies base address explicitly. */
> > > > > +??????????????????????????if (!memblock_is_region_memory(crash_base, crash_size) ||
> > > > > +??????????????????????????????????????????memblock_is_region_reserved(crash_base, crash_size)) {
> > > > > +??????????????????????????????????????????pr_warn("crashkernel has wrong address or size\n");
> > > > > +??????????????????????????????????????????return;
> > > > > +??????????????????????????}
> > > > > +
> > > > > +??????????????????????????if (!IS_ALIGNED(crash_base, SZ_2M)) {
> > > > > +??????????????????????????????????????????pr_warn("crashkernel base address is not 2MB aligned\n");
> > > > > +??????????????????????????????????????????return;
> > > > > +??????????????????????????}
> > > > > +
> > > > > +??????????????????????????memblock_reserve(crash_base, crash_size);
> > > > > +??????????}
> > > > > +
> > > > > +??????????pr_info("Reserving %lldMB of memory at %lldMB for crashkernel\n",
> > > > > +??????????????????????????crash_size >> 20, crash_base >> 20);
> > > > > +
> > > > > +??????????crashk_res.start = crash_base;
> > > > > +??????????crashk_res.end = crash_base + crash_size - 1;
> > > > > +}
> > > > > +#else
> > > > > +static void __init reserve_crashkernel(void)
> > > > > +{
> > > > > +??????????;
> > > > > +}
> > > > > +#endif /* CONFIG_KEXEC_CORE */
> > > > > +
> > > > > ??/*
> > > > > ?? * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
> > > > > ?? * currently assumes that for memory starting above 4G, 32-bit devices will
> > > > > @@ -289,6 +402,8 @@ void __init arm64_memblock_init(void)
> > > > > ????????????}
> > > > > ??#endif
> > > > > 
> > > > > +??????????reserve_crashkernel();
> > > > > +
> > > > > ????????????early_init_fdt_scan_reserved_mem();
> > > > > 
> > > > > ????????????/* 4GB maximum for 32-bit only capable devices */
> > > > > --
> > > > > 2.9.0
> > > > > 
> > > > > 
> > > > > _______________________________________________
> > > > > linux-arm-kernel mailing list
> > > > > linux-arm-kernel at lists.infradead.org
> > > > > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
> > > > > 
> 