On Thu, 2020-10-15 at 08:56 +0200, Ard Biesheuvel wrote:

On Thu, 15 Oct 2020 at 00:03, Rob Herring [off-list ref] wrote:

quoted

On Wed, Oct 14, 2020 at 2:12 PM Nicolas Saenz Julienne
[off-list ref] wrote:

quoted

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 <redacted>

---

Changes since v2:
 - Use PHYS_ADDR_MAX
 - return phys_dma_t
 - Rename function
 - Correct subject
 - Add support to start parsing from an arbitrary device node in order
   for the function to work with unit tests

 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 eb9ab4f1e80b..b5a9695aaf82 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 system (or subtree when np is non-NULL). 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;

One issue with using phys_addr_t is it may be 32-bit even though the
DT is 64-bit addresses. LPAE capable system with LPAE disabled. Maybe
the truncation is fine here? Maybe not.

PHYS_ADDR_MAX is the max addressable CPU address on the system, and so
it makes sense to use it for the return type, and for the preliminary
return value: this is actually what /prevents/ truncation, because we
will only overwrite max_cpu_addr if the new u64 value is lower.

Actually I now see how things might go south.

quoted

quoted

+       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;

If cpu_end hits 0x1_00000000, it'll overflow to 0. This is possible on 32-bit
systems (LPAE or not). And something similar might happen on LPAE disabled
systems.

I could add some extra logic, something like:

	/* We overflowed */
	if (cpu_end < range.cpu_addr)
		cpu_end = PHYS_ADDR_MAX;

Which is not perfect but will cover most sensible cases.

Or simply deal internally in u64s, and upon returning, check if "max_cpu_addr"
falls higher than PHYS_ADDR_MAX.

quoted

quoted

+
+               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;
+}

Regards,
Nicolas