If the memory reserved for crash dump kernel falled in ZONE_DMA32,
the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
enabled, otherwise, reserving in ZONE_DMA32.
Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
Signed-off-by: Chen Zhou <[email protected]>
---
arch/arm64/mm/init.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7b9809e39927..5074e945f1a6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -85,7 +85,8 @@ static void __init reserve_crashkernel(void)
if (crash_base == 0) {
/* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+ crash_base = memblock_find_in_range(0,
+ arm64_dma_phys_limit ? : arm64_dma32_phys_limit,
crash_size, SZ_2M);
if (crash_base == 0) {
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
--
2.20.1
Hi Chen, thanks for looking at this.
On Sat, 2020-12-26 at 11:35 +0800, Chen Zhou wrote:
> If the memory reserved for crash dump kernel falled in ZONE_DMA32,
> the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
>
> Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
> enabled, otherwise, reserving in ZONE_DMA32.
>
> Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
I'm not so sure this counts as a fix, if someone backports it it'll probably
break things as it depends on the series that dynamically sizes DMA zones.
> Signed-off-by: Chen Zhou <[email protected]>
> ---
Why not doing the same with CMA? You'll probably have to move the
dma_contiguous_reserve() call into bootmem_init() so as to make sure that
arm64_dma_phys_limit is populated.
Regards,
Nicolas
> arch/arm64/mm/init.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 7b9809e39927..5074e945f1a6 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -85,7 +85,8 @@ static void __init reserve_crashkernel(void)
>
>
> if (crash_base == 0) {
> /* Current arm64 boot protocol requires 2MB alignment */
> - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
> + crash_base = memblock_find_in_range(0,
> + arm64_dma_phys_limit ? : arm64_dma32_phys_limit,
> crash_size, SZ_2M);
> if (crash_base == 0) {
> pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
Hi Nicolas,
Thanks for your review.
On 2020/12/26 18:34, Nicolas Saenz Julienne wrote:
> Hi Chen, thanks for looking at this.
>
> On Sat, 2020-12-26 at 11:35 +0800, Chen Zhou wrote:
>> If the memory reserved for crash dump kernel falled in ZONE_DMA32,
>> the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
>>
>> Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
>> enabled, otherwise, reserving in ZONE_DMA32.
>>
>> Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
> I'm not so sure this counts as a fix, if someone backports it it'll probably
> break things as it depends on the series that dynamically sizes DMA zones.
I write this just because kdump is broken from this commit.
>
>> Signed-off-by: Chen Zhou <[email protected]>
>> ---
> Why not doing the same with CMA? You'll probably have to move the
> dma_contiguous_reserve() call into bootmem_init() so as to make sure that
> arm64_dma_phys_limit is populated.
You are right, CMA also need this. I will do this in next version.
Thanks,
Chen Zhou
>
> Regards,
> Nicolas
>
>> arch/arm64/mm/init.c | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
>> index 7b9809e39927..5074e945f1a6 100644
>> --- a/arch/arm64/mm/init.c
>> +++ b/arch/arm64/mm/init.c
>> @@ -85,7 +85,8 @@ static void __init reserve_crashkernel(void)
>>
>>
>> if (crash_base == 0) {
>> /* Current arm64 boot protocol requires 2MB alignment */
>> - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
>> + crash_base = memblock_find_in_range(0,
>> + arm64_dma_phys_limit ? : arm64_dma32_phys_limit,
>> crash_size, SZ_2M);
>> if (crash_base == 0) {
>> pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
>
On Sat, Dec 26, 2020 at 11:34:58AM +0100, Nicolas Saenz Julienne wrote:
> On Sat, 2020-12-26 at 11:35 +0800, Chen Zhou wrote:
> > If the memory reserved for crash dump kernel falled in ZONE_DMA32,
> > the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
> >
> > Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
> > enabled, otherwise, reserving in ZONE_DMA32.
> >
> > Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
>
> I'm not so sure this counts as a fix, if someone backports it it'll probably
> break things as it depends on the series that dynamically sizes DMA zones.
>
> > Signed-off-by: Chen Zhou <[email protected]>
> > ---
>
> Why not doing the same with CMA? You'll probably have to move the
> dma_contiguous_reserve() call into bootmem_init() so as to make sure that
> arm64_dma_phys_limit is populated.
Do we need the arm64_dma32_phys_limit at all? I can see the
(arm64_dma_phys_limit ? : arm64_dma32_phys_limit) pattern in several
places but I think we can just live with the arm64_dma_phys_limit.
Also, I don't think we need any early ARCH_LOW_ADDRESS_LIMIT. It's only
used by memblock_alloc_low() and that's called from swiotlb_init()
after arm64_dma_phys_limit was initialised.
What about something like below (on top of you ARCH_LOW_ADDRESS_LIMIT
fix but I can revert that)? I haven't tested it in all configurations
yet.
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
#endif /* CONFIG_ARM64_FORCE_52BIT */
extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
struct debug_info {
#ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7deddf56f7c3..596a94bf5ed6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -59,7 +59,6 @@ EXPORT_SYMBOL(memstart_addr);
* bit addressable memory area.
*/
phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
#ifdef CONFIG_KEXEC_CORE
/*
@@ -84,7 +83,7 @@ static void __init reserve_crashkernel(void)
if (crash_base == 0) {
/* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+ crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
crash_size, SZ_2M);
if (crash_base == 0) {
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +195,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
unsigned int __maybe_unused acpi_zone_dma_bits;
unsigned int __maybe_unused dt_zone_dma_bits;
+ phys_addr_t dma32_phys_limit = max_zone_phys(32);
#ifdef CONFIG_ZONE_DMA
acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +205,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = dma32_phys_limit;
#endif
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = PHYS_MASK + 1;
max_zone_pfns[ZONE_NORMAL] = max;
free_area_init(max_zone_pfns);
@@ -394,16 +398,9 @@ void __init arm64_memblock_init(void)
early_init_fdt_scan_reserved_mem();
- if (IS_ENABLED(CONFIG_ZONE_DMA32))
- arm64_dma32_phys_limit = max_zone_phys(32);
- else
- arm64_dma32_phys_limit = PHYS_MASK + 1;
-
reserve_elfcorehdr();
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
- dma_contiguous_reserve(arm64_dma32_phys_limit);
}
void __init bootmem_init(void)
@@ -438,6 +435,11 @@ void __init bootmem_init(void)
sparse_init();
zone_sizes_init(min, max);
+ /*
+ * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+ */
+ dma_contiguous_reserve(arm64_dma_phys_limit);
+
/*
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
@@ -455,7 +457,7 @@ void __init bootmem_init(void)
void __init mem_init(void)
{
if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+ max_pfn > PFN_DOWN(arm64_dma_phys_limit))
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
On Mon, Dec 28, 2020 at 03:32:35PM +0800, chenzhou wrote:
> On 2020/12/26 18:34, Nicolas Saenz Julienne wrote:
> > On Sat, 2020-12-26 at 11:35 +0800, Chen Zhou wrote:
> >> If the memory reserved for crash dump kernel falled in ZONE_DMA32,
> >> the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
> >>
> >> Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
> >> enabled, otherwise, reserving in ZONE_DMA32.
> >>
> >> Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
> > I'm not so sure this counts as a fix, if someone backports it it'll probably
> > break things as it depends on the series that dynamically sizes DMA zones.
>
> I write this just because kdump is broken from this commit.
Commit bff3b04460a8 actually fixed a regression introduced by the
limited 30-bit ZONE_DMA, under the assumption that RPi4 is the only
platform that cares about this. I agree a kdump kernel will fail to get
memory in the low zone but it's not clear to me whether the regression
you are seeing happened in 5.11-rc1 or you it's been around since 5.5.
We may have got away before because max_zone_phys() assumed an implicit
DMA offset equal to the start of the DRAM (well, power of two). This
assumption was removed in 5.11 by commit 791ab8b2e3db ("arm64: Ignore
any DMA offsets in the max_zone_phys() calculation").
So your patch or the clean-up I posted only makes sense with the dynamic
ZONE_DMA patches in 5.11-rc1. For any earlier version, I don't have any
suggestion other than not enabling CONFIG_ZONE_DMA in the kdump kernel
(or backporting all of Nicolas' patches).
I'll post my clean-up separately to go into 5.11 but won't have a fixes
tag for bff3b04460a8.
--
Catalin
On 2021/1/7 22:25, Catalin Marinas wrote:
> On Sat, Dec 26, 2020 at 11:34:58AM +0100, Nicolas Saenz Julienne wrote:
>> On Sat, 2020-12-26 at 11:35 +0800, Chen Zhou wrote:
>>> If the memory reserved for crash dump kernel falled in ZONE_DMA32,
>>> the devices in crash dump kernel need to use ZONE_DMA will alloc fail.
>>>
>>> Fix this by reserving low memory in ZONE_DMA if CONFIG_ZONE_DMA is
>>> enabled, otherwise, reserving in ZONE_DMA32.
>>>
>>> Fixes: bff3b04460a8 ("arm64: mm: reserve CMA and crashkernel in ZONE_DMA32")
>> I'm not so sure this counts as a fix, if someone backports it it'll probably
>> break things as it depends on the series that dynamically sizes DMA zones.
>>
>>> Signed-off-by: Chen Zhou <[email protected]>
>>> ---
>> Why not doing the same with CMA? You'll probably have to move the
>> dma_contiguous_reserve() call into bootmem_init() so as to make sure that
>> arm64_dma_phys_limit is populated.
> Do we need the arm64_dma32_phys_limit at all? I can see the
> (arm64_dma_phys_limit ? : arm64_dma32_phys_limit) pattern in several
> places but I think we can just live with the arm64_dma_phys_limit.
Yes, arm64_dma_phys_limit is enough.
>
> Also, I don't think we need any early ARCH_LOW_ADDRESS_LIMIT. It's only
> used by memblock_alloc_low() and that's called from swiotlb_init()
> after arm64_dma_phys_limit was initialised.
>
> What about something like below (on top of you ARCH_LOW_ADDRESS_LIMIT
> fix but I can revert that)? I haven't tested it in all configurations
> yet.
>
> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> index 69ad25fbeae4..ca2cd75d3286 100644
> --- a/arch/arm64/include/asm/processor.h
> +++ b/arch/arm64/include/asm/processor.h
> @@ -94,8 +94,7 @@
> #endif /* CONFIG_ARM64_FORCE_52BIT */
>
> extern phys_addr_t arm64_dma_phys_limit;
> -extern phys_addr_t arm64_dma32_phys_limit;
> -#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
> +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
>
> struct debug_info {
> #ifdef CONFIG_HAVE_HW_BREAKPOINT
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 7deddf56f7c3..596a94bf5ed6 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -59,7 +59,6 @@ EXPORT_SYMBOL(memstart_addr);
> * bit addressable memory area.
> */
> phys_addr_t arm64_dma_phys_limit __ro_after_init;
> -phys_addr_t arm64_dma32_phys_limit __ro_after_init;
>
> #ifdef CONFIG_KEXEC_CORE
> /*
> @@ -84,7 +83,7 @@ static void __init reserve_crashkernel(void)
>
> if (crash_base == 0) {
> /* Current arm64 boot protocol requires 2MB alignment */
> - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
> + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
> crash_size, SZ_2M);
> if (crash_base == 0) {
> pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
> @@ -196,6 +195,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
> unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
> unsigned int __maybe_unused acpi_zone_dma_bits;
> unsigned int __maybe_unused dt_zone_dma_bits;
> + phys_addr_t dma32_phys_limit = max_zone_phys(32);
>
> #ifdef CONFIG_ZONE_DMA
> acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
> @@ -205,8 +205,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
> max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
> #endif
> #ifdef CONFIG_ZONE_DMA32
> - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
> + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
> + if (!arm64_dma_phys_limit)
> + arm64_dma_phys_limit = dma32_phys_limit;
> #endif
> + if (!arm64_dma_phys_limit)
> + arm64_dma_phys_limit = PHYS_MASK + 1;
> max_zone_pfns[ZONE_NORMAL] = max;
>
> free_area_init(max_zone_pfns);
> @@ -394,16 +398,9 @@ void __init arm64_memblock_init(void)
>
> early_init_fdt_scan_reserved_mem();
>
> - if (IS_ENABLED(CONFIG_ZONE_DMA32))
> - arm64_dma32_phys_limit = max_zone_phys(32);
> - else
> - arm64_dma32_phys_limit = PHYS_MASK + 1;
> -
> reserve_elfcorehdr();
>
> high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
> -
> - dma_contiguous_reserve(arm64_dma32_phys_limit);
> }
>
> void __init bootmem_init(void)
> @@ -438,6 +435,11 @@ void __init bootmem_init(void)
> sparse_init();
> zone_sizes_init(min, max);
>
> + /*
> + * Reserve the CMA area after arm64_dma_phys_limit was initialised.
> + */
> + dma_contiguous_reserve(arm64_dma_phys_limit);
> +
> /*
> * request_standard_resources() depends on crashkernel's memory being
> * reserved, so do it here.
> @@ -455,7 +457,7 @@ void __init bootmem_init(void)
> void __init mem_init(void)
> {
> if (swiotlb_force == SWIOTLB_FORCE ||
> - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
> + max_pfn > PFN_DOWN(arm64_dma_phys_limit))
> swiotlb_init(1);
> else
> swiotlb_force = SWIOTLB_NO_FORCE;
> .
>