Using two distinct DMA zones turned out to be problematic. Here's an
attempt go back to a saner default.
Ard Biesheuvel (1):
arm64: mm: Set ZONE_DMA size based on early IORT scan
Nicolas Saenz Julienne (6):
arm64: mm: Move reserve_crashkernel() into mem_init()
arm64: mm: Move zone_dma_bits initialization into zone_sizes_init()
of/address: Introduce of_dma_get_max_cpu_address()
of: unittest: Add test for of_dma_get_max_cpu_address()
arm64: mm: Set ZONE_DMA size based on devicetree's dma-ranges
mm: Remove examples from enum zone_type comment
arch/arm64/mm/init.c | 22 +++++++++-------
drivers/acpi/arm64/iort.c | 55 +++++++++++++++++++++++++++++++++++++++
drivers/of/address.c | 42 ++++++++++++++++++++++++++++++
drivers/of/unittest.c | 18 +++++++++++++
include/linux/acpi_iort.h | 4 +++
include/linux/mmzone.h | 20 --------------
include/linux/of.h | 7 +++++
7 files changed, 139 insertions(+), 29 deletions(-)
--
2.25.1
From: Nicolas Saenz Julienne <[email protected]>
commit 9804f8c69b04a39d0ba41d19e6bdc6aa91c19725 upstream
zone_dma_bits's initialization happens earlier that it's actually
needed, in arm64_memblock_init(). So move it into the more suitable
zone_sizes_init().
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
Tested-by: Jeremy Linton <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
Cc: <[email protected]>
Signed-off-by: Jing Xiangfeng <[email protected]>
---
arch/arm64/mm/init.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 686653e33250..7da912bf4222 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -190,6 +190,8 @@ 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
+ zone_dma_bits = ARM64_ZONE_DMA_BITS;
+ arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
@@ -376,11 +378,6 @@ void __init arm64_memblock_init(void)
early_init_fdt_scan_reserved_mem();
- if (IS_ENABLED(CONFIG_ZONE_DMA)) {
- zone_dma_bits = ARM64_ZONE_DMA_BITS;
- arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS);
- }
-
if (IS_ENABLED(CONFIG_ZONE_DMA32))
arm64_dma32_phys_limit = max_zone_phys(32);
else
--
2.25.1
From: Nicolas Saenz Julienne <[email protected]>
commit 07d13a1d6120d453c3c1f020578693d072deded5 upstream
Introduce a test for of_dma_get_max_cup_address(), it uses the same DT
data as the rest of dma-ranges unit tests.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
Reviewed-by: Rob Herring <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
Cc: <[email protected]>
Signed-off-by: Jing Xiangfeng <[email protected]>
---
drivers/of/unittest.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 06cc988faf78..98cc0163301b 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -869,6 +869,23 @@ static void __init of_unittest_changeset(void)
#endif
}
+static void __init of_unittest_dma_get_max_cpu_address(void)
+{
+ struct device_node *np;
+ phys_addr_t cpu_addr;
+
+ np = of_find_node_by_path("/testcase-data/address-tests");
+ if (!np) {
+ pr_err("missing testcase data\n");
+ return;
+ }
+
+ cpu_addr = of_dma_get_max_cpu_address(np);
+ unittest(cpu_addr == 0x4fffffff,
+ "of_dma_get_max_cpu_address: wrong CPU addr %pad (expecting %x)\n",
+ &cpu_addr, 0x4fffffff);
+}
+
static void __init of_unittest_dma_ranges_one(const char *path,
u64 expect_dma_addr, u64 expect_paddr)
{
@@ -3266,6 +3283,7 @@ static int __init of_unittest(void)
of_unittest_changeset();
of_unittest_parse_interrupts();
of_unittest_parse_interrupts_extended();
+ of_unittest_dma_get_max_cpu_address();
of_unittest_parse_dma_ranges();
of_unittest_pci_dma_ranges();
of_unittest_match_node();
--
2.25.1
From: Nicolas Saenz Julienne <[email protected]>
commit 8424ecdde7df99d5426e1a1fd9f0fb36f4183032 upstream
We recently introduced a 1 GB sized ZONE_DMA to cater for platforms
incorporating masters that can address less than 32 bits of DMA, in
particular the Raspberry Pi 4, which has 4 or 8 GB of DRAM, but has
peripherals that can only address up to 1 GB (and its PCIe host
bridge can only access the bottom 3 GB)
The DMA layer also needs to be able to allocate memory that is
guaranteed to meet those DMA constraints, for bounce buffering as well
as allocating the backing for consistent mappings. This is why the 1 GB
ZONE_DMA was introduced recently. Unfortunately, it turns out the having
a 1 GB ZONE_DMA as well as a ZONE_DMA32 causes problems with kdump, and
potentially in other places where allocations cannot cross zone
boundaries. Therefore, we should avoid having two separate DMA zones
when possible.
So, with the help of of_dma_get_max_cpu_address() get the topmost
physical address accessible to all DMA masters in system and use that
information to fine-tune ZONE_DMA's size. In the absence of addressing
limited masters ZONE_DMA will span the whole 32-bit address space,
otherwise, in the case of the Raspberry Pi 4 it'll only span the 30-bit
address space, and have ZONE_DMA32 cover the rest of the 32-bit address
space.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
Cc: <[email protected]>
Signed-off-by: Jing Xiangfeng <[email protected]>
---
arch/arm64/mm/init.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7da912bf4222..05a1c2773629 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -42,8 +42,6 @@
#include <asm/tlb.h>
#include <asm/alternative.h>
-#define ARM64_ZONE_DMA_BITS 30
-
/*
* We need to be able to catch inadvertent references to memstart_addr
* that occur (potentially in generic code) before arm64_memblock_init()
@@ -188,9 +186,11 @@ static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
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 dt_zone_dma_bits;
#ifdef CONFIG_ZONE_DMA
- zone_dma_bits = ARM64_ZONE_DMA_BITS;
+ dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
+ zone_dma_bits = min(32U, dt_zone_dma_bits);
arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
--
2.25.1
From: Nicolas Saenz Julienne <[email protected]>
commit 964db79d6c186cc2ecc6ae46f98eed7e0ea8cf71 upstream
Introduce of_dma_get_max_cpu_address(), which provides the highest CPU
physical address addressable by all DMA masters in the system. It's
specially useful for setting memory zones sizes at early boot time.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
Reviewed-by: Rob Herring <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>
Cc: <[email protected]>
Signed-off-by: Jing Xiangfeng <[email protected]>
---
drivers/of/address.c | 42 ++++++++++++++++++++++++++++++++++++++++++
include/linux/of.h | 7 +++++++
2 files changed, 49 insertions(+)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 1c3257a2d4e3..73ddf2540f3f 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -1024,6 +1024,48 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
}
#endif /* CONFIG_HAS_DMA */
+/**
+ * of_dma_get_max_cpu_address - Gets highest CPU address suitable for DMA
+ * @np: The node to start searching from or NULL to start from the root
+ *
+ * Gets the highest CPU physical address that is addressable by all DMA masters
+ * in the sub-tree pointed by np, or the whole tree if NULL is passed. If no
+ * DMA constrained device is found, it returns PHYS_ADDR_MAX.
+ */
+phys_addr_t __init of_dma_get_max_cpu_address(struct device_node *np)
+{
+ phys_addr_t max_cpu_addr = PHYS_ADDR_MAX;
+ struct of_range_parser parser;
+ phys_addr_t subtree_max_addr;
+ struct device_node *child;
+ struct of_range range;
+ const __be32 *ranges;
+ u64 cpu_end = 0;
+ int len;
+
+ if (!np)
+ np = of_root;
+
+ ranges = of_get_property(np, "dma-ranges", &len);
+ if (ranges && len) {
+ of_dma_range_parser_init(&parser, np);
+ for_each_of_range(&parser, &range)
+ if (range.cpu_addr + range.size > cpu_end)
+ cpu_end = range.cpu_addr + range.size - 1;
+
+ if (max_cpu_addr > cpu_end)
+ max_cpu_addr = cpu_end;
+ }
+
+ for_each_available_child_of_node(np, child) {
+ subtree_max_addr = of_dma_get_max_cpu_address(child);
+ if (max_cpu_addr > subtree_max_addr)
+ max_cpu_addr = subtree_max_addr;
+ }
+
+ return max_cpu_addr;
+}
+
/**
* of_dma_is_coherent - Check if device is coherent
* @np: device node
diff --git a/include/linux/of.h b/include/linux/of.h
index af655d264f10..0f4e81e6fb23 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -558,6 +558,8 @@ int of_map_id(struct device_node *np, u32 id,
const char *map_name, const char *map_mask_name,
struct device_node **target, u32 *id_out);
+phys_addr_t of_dma_get_max_cpu_address(struct device_node *np);
+
#else /* CONFIG_OF */
static inline void of_core_init(void)
@@ -995,6 +997,11 @@ static inline int of_map_id(struct device_node *np, u32 id,
return -EINVAL;
}
+static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np)
+{
+ return PHYS_ADDR_MAX;
+}
+
#define of_match_ptr(_ptr) NULL
#define of_match_node(_matches, _node) NULL
#endif /* CONFIG_OF */
--
2.25.1