Message ID | 20190902141043.27210-4-nsaenzjulienne@suse.de (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | Raspberry Pi 4 DMA addressing support | expand |
On Mon, Sep 02, 2019 at 04:10:41PM +0200, Nicolas Saenz Julienne wrote: > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 8956c22634dd..f02a4945aeac 100644 > --- a/arch/arm64/mm/init.c > +++ b/arch/arm64/mm/init.c > @@ -50,6 +50,13 @@ > s64 memstart_addr __ro_after_init = -1; > EXPORT_SYMBOL(memstart_addr); > > +/* > + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of > + * memory as some devices, namely the Raspberry Pi 4, have peripherals with > + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 > + * 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 > @@ -164,9 +171,9 @@ static void __init reserve_elfcorehdr(void) > } > #endif /* CONFIG_CRASH_DUMP */ > /* > - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It > - * currently assumes that for memory starting above 4G, 32-bit devices will > - * use a DMA offset. > + * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)) and > + * ZONE_DMA (DMA_BIT_MASK(30)) respectively. It currently assumes that for > + * memory starting above 4G, 32-bit devices will use a DMA offset. > */ > static phys_addr_t __init max_zone_dma32_phys(void) > { > @@ -174,12 +181,23 @@ static phys_addr_t __init max_zone_dma32_phys(void) > return min(offset + (1ULL << 32), memblock_end_of_DRAM()); > } > > +static phys_addr_t __init max_zone_dma_phys(void) > +{ > + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); > + > + return min(offset + (1ULL << ARCH_ZONE_DMA_BITS), > + memblock_end_of_DRAM()); > +} I think we could squash these two functions into a single one with a "bits" argument that is either 32 or ARCH_ZONE_DMA_BITS. > + > #ifdef CONFIG_NUMA > > static void __init zone_sizes_init(unsigned long min, unsigned long max) > { > unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; > > +#ifdef CONFIG_ZONE_DMA > + 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); > #endif > @@ -195,13 +213,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) > struct memblock_region *reg; > unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; > unsigned long max_dma32 = min; > + unsigned long max_dma = min; > > memset(zone_size, 0, sizeof(zone_size)); > > - /* 4GB maximum for 32-bit only capable devices */ > +#ifdef CONFIG_ZONE_DMA > + max_dma = PFN_DOWN(arm64_dma_phys_limit); > + zone_size[ZONE_DMA] = max_dma - min; > +#endif > #ifdef CONFIG_ZONE_DMA32 > max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); > - zone_size[ZONE_DMA32] = max_dma32 - min; > + zone_size[ZONE_DMA32] = max_dma32 - max_dma; > #endif > zone_size[ZONE_NORMAL] = max - max_dma32; Does this still work if we have ZONE_DMA32 disabled but ZONE_DMA enabled? You could use a max(max_dma32, max_dma) or just update max_dma32 to max_dma in the CONFIG_ZONE_DMA block. > @@ -213,11 +235,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) > > if (start >= max) > continue; > - > +#ifdef CONFIG_ZONE_DMA > + if (start < max_dma) { > + unsigned long dma_end = min_not_zero(end, max_dma); > + zhole_size[ZONE_DMA] -= dma_end - start; > + } > +#endif > #ifdef CONFIG_ZONE_DMA32 > if (start < max_dma32) { > - unsigned long dma_end = min(end, max_dma32); > - zhole_size[ZONE_DMA32] -= dma_end - start; > + unsigned long dma32_end = min(end, max_dma32); > + unsigned long dma32_start = max(start, max_dma); > + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; > } > #endif > if (end > max_dma32) { Similar comment here.
On Thu, 2019-09-05 at 18:19 +0100, Catalin Marinas wrote: > On Mon, Sep 02, 2019 at 04:10:41PM +0200, Nicolas Saenz Julienne wrote: > > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > > index 8956c22634dd..f02a4945aeac 100644 > > --- a/arch/arm64/mm/init.c > > +++ b/arch/arm64/mm/init.c > > @@ -50,6 +50,13 @@ > > s64 memstart_addr __ro_after_init = -1; > > EXPORT_SYMBOL(memstart_addr); > > > > +/* > > + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of > > + * memory as some devices, namely the Raspberry Pi 4, have peripherals with > > + * this limited view of the memory. ZONE_DMA32 will cover the rest of the > > 32 > > + * 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 > > @@ -164,9 +171,9 @@ static void __init reserve_elfcorehdr(void) > > } > > #endif /* CONFIG_CRASH_DUMP */ > > /* > > - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). > > It > > - * currently assumes that for memory starting above 4G, 32-bit devices will > > - * use a DMA offset. > > + * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)) > > and > > + * ZONE_DMA (DMA_BIT_MASK(30)) respectively. It currently assumes that for > > + * memory starting above 4G, 32-bit devices will use a DMA offset. > > */ > > static phys_addr_t __init max_zone_dma32_phys(void) > > { > > @@ -174,12 +181,23 @@ static phys_addr_t __init max_zone_dma32_phys(void) > > return min(offset + (1ULL << 32), memblock_end_of_DRAM()); > > } > > > > +static phys_addr_t __init max_zone_dma_phys(void) > > +{ > > + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); > > + > > + return min(offset + (1ULL << ARCH_ZONE_DMA_BITS), > > + memblock_end_of_DRAM()); > > +} > > I think we could squash these two functions into a single one with a > "bits" argument that is either 32 or ARCH_ZONE_DMA_BITS. Hi Catalin, thanks for the review. Agree, it'll look nicer. > > + > > #ifdef CONFIG_NUMA > > > > static void __init zone_sizes_init(unsigned long min, unsigned long max) > > { > > unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; > > > > +#ifdef CONFIG_ZONE_DMA > > + 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); > > #endif > > @@ -195,13 +213,17 @@ static void __init zone_sizes_init(unsigned long min, > > unsigned long max) > > struct memblock_region *reg; > > unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; > > unsigned long max_dma32 = min; > > + unsigned long max_dma = min; > > > > memset(zone_size, 0, sizeof(zone_size)); > > > > - /* 4GB maximum for 32-bit only capable devices */ > > +#ifdef CONFIG_ZONE_DMA > > + max_dma = PFN_DOWN(arm64_dma_phys_limit); > > + zone_size[ZONE_DMA] = max_dma - min; > > +#endifmax_dma32 > > #ifdef CONFIG_ZONE_DMA32 > > max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); > > - zone_size[ZONE_DMA32] = max_dma32 - min; > > + zone_size[ZONE_DMA32] = max_dma32 - max_dma; > > #endif > > zone_size[ZONE_NORMAL] = max - max_dma32; > > Does this still work if we have ZONE_DMA32 disabled but ZONE_DMA > enabled? You could use a max(max_dma32, max_dma) or just update > max_dma32 to max_dma in the CONFIG_ZONE_DMA block. You're right, I missed that scenario. I'll fix it and give it a test for the next series. Regards, Nicolas
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3adcec05b1f6..a9fd71d3bc8e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -266,6 +266,10 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y +config ZONE_DMA + bool "Support DMA zone" if EXPERT + default y + config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index d39ddb258a04..7b8c98830101 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -38,4 +38,6 @@ extern int pfn_valid(unsigned long); #include <asm-generic/getorder.h> +#define ARCH_ZONE_DMA_BITS 30 + #endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8956c22634dd..f02a4945aeac 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -50,6 +50,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); +/* + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of + * memory as some devices, namely the Raspberry Pi 4, have peripherals with + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 + * 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 @@ -164,9 +171,9 @@ static void __init reserve_elfcorehdr(void) } #endif /* CONFIG_CRASH_DUMP */ /* - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It - * currently assumes that for memory starting above 4G, 32-bit devices will - * use a DMA offset. + * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)) and + * ZONE_DMA (DMA_BIT_MASK(30)) respectively. It currently assumes that for + * memory starting above 4G, 32-bit devices will use a DMA offset. */ static phys_addr_t __init max_zone_dma32_phys(void) { @@ -174,12 +181,23 @@ static phys_addr_t __init max_zone_dma32_phys(void) return min(offset + (1ULL << 32), memblock_end_of_DRAM()); } +static phys_addr_t __init max_zone_dma_phys(void) +{ + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); + + return min(offset + (1ULL << ARCH_ZONE_DMA_BITS), + memblock_end_of_DRAM()); +} + #ifdef CONFIG_NUMA static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; +#ifdef CONFIG_ZONE_DMA + 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); #endif @@ -195,13 +213,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) struct memblock_region *reg; unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; unsigned long max_dma32 = min; + unsigned long max_dma = min; memset(zone_size, 0, sizeof(zone_size)); - /* 4GB maximum for 32-bit only capable devices */ +#ifdef CONFIG_ZONE_DMA + max_dma = PFN_DOWN(arm64_dma_phys_limit); + zone_size[ZONE_DMA] = max_dma - min; +#endif #ifdef CONFIG_ZONE_DMA32 max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); - zone_size[ZONE_DMA32] = max_dma32 - min; + zone_size[ZONE_DMA32] = max_dma32 - max_dma; #endif zone_size[ZONE_NORMAL] = max - max_dma32; @@ -213,11 +235,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - +#ifdef CONFIG_ZONE_DMA + if (start < max_dma) { + unsigned long dma_end = min_not_zero(end, max_dma); + zhole_size[ZONE_DMA] -= dma_end - start; + } +#endif #ifdef CONFIG_ZONE_DMA32 if (start < max_dma32) { - unsigned long dma_end = min(end, max_dma32); - zhole_size[ZONE_DMA32] -= dma_end - start; + unsigned long dma32_end = min(end, max_dma32); + unsigned long dma32_start = max(start, max_dma); + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; } #endif if (end > max_dma32) { @@ -405,7 +433,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + arm64_dma_phys_limit = max_zone_dma_phys(); + if (IS_ENABLED(CONFIG_ZONE_DMA32)) arm64_dma32_phys_limit = max_zone_dma32_phys(); else @@ -417,7 +447,7 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - dma_contiguous_reserve(arm64_dma32_phys_limit); + dma_contiguous_reserve(arm64_dma_phys_limit ? : arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -521,6 +551,7 @@ static void __init free_unused_memmap(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || + max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT) || max_pfn > (arm64_dma32_phys_limit >> PAGE_SHIFT)) swiotlb_init(1); else
So far all arm64 devices have supported 32 bit DMA masks for their peripherals. This is not true anymore for the Raspberry Pi 4 as most of it's peripherals can only address the first GB of memory on a total of up to 4 GB. This goes against ZONE_DMA32's intent, as it's expected for ZONE_DMA32 to be addressable with a 32 bit mask. So it was decided to re-introduce ZONE_DMA in arm64. ZONE_DMA will contain the lower 1G of memory, which is currently the memory area addressable by any peripheral on an arm64 device. ZONE_DMA32 will contain the rest of the 32 bit addressable memory. Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de> --- Changes in v3: - Used fixed size ZONE_DMA - Fix check befor swiotlb_init() Changes in v2: - Update comment to reflect new zones split - ZONE_DMA will never be left empty arch/arm64/Kconfig | 4 +++ arch/arm64/include/asm/page.h | 2 ++ arch/arm64/mm/init.c | 51 ++++++++++++++++++++++++++++------- 3 files changed, 47 insertions(+), 10 deletions(-)