Re: [PATCH v2] memblock: make memblock_find_in_range method private

From: Rob Herring
Date: Mon Aug 02 2021 - 10:56:25 EST

On Mon, Aug 2, 2021 at 12:37 AM Mike Rapoport <rppt@xxxxxxxxxx> wrote:
>
> From: Mike Rapoport <rppt@xxxxxxxxxxxxx>
>
> There are a lot of uses of memblock_find_in_range() along with
> memblock_reserve() from the times memblock allocation APIs did not exist.
>
> memblock_find_in_range() is the very core of memblock allocations, so any
> future changes to its internal behaviour would mandate updates of all the
> users outside memblock.
>
> Replace the calls to memblock_find_in_range() with an equivalent calls to
> memblock_phys_alloc() and memblock_phys_alloc_range() and make
> memblock_find_in_range() private method of memblock.
>
> This simplifies the callers, ensures that (unlikely) errors in
> memblock_reserve() are handled and improves maintainability of
> memblock_find_in_range().
>
> Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
> ---
> v2: don't change error message in arm::reserve_crashkernel(), per Russell
> v1: https://lore.kernel.org/lkml/20210730104039.7047-1-rppt@xxxxxxxxxx
>
> arch/arm/kernel/setup.c | 18 +++++--------
> arch/arm64/kvm/hyp/reserved_mem.c | 9 +++----
> arch/arm64/mm/init.c | 36 ++++++++-----------------
> arch/mips/kernel/setup.c | 14 +++++-----
> arch/riscv/mm/init.c | 44 ++++++++++---------------------
> arch/s390/kernel/setup.c | 10 ++++---
> arch/x86/kernel/aperture_64.c | 5 ++--
> arch/x86/mm/init.c | 21 +++++++++------
> arch/x86/mm/numa.c | 5 ++--
> arch/x86/mm/numa_emulation.c | 5 ++--
> arch/x86/realmode/init.c | 2 +-
> drivers/acpi/tables.c | 5 ++--
> drivers/base/arch_numa.c | 5 +---
> drivers/of/of_reserved_mem.c | 12 ++++++---
> include/linux/memblock.h | 2 --
> mm/memblock.c | 2 +-
> 16 files changed, 78 insertions(+), 117 deletions(-)
>
> diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
> index f97eb2371672..67f5421b2af7 100644
> --- a/arch/arm/kernel/setup.c
> +++ b/arch/arm/kernel/setup.c
> @@ -1012,31 +1012,25 @@ static void __init reserve_crashkernel(void)
> unsigned long long lowmem_max = __pa(high_memory - 1) + 1;
> if (crash_max > lowmem_max)
> crash_max = lowmem_max;
> - crash_base = memblock_find_in_range(CRASH_ALIGN, crash_max,
> - crash_size, CRASH_ALIGN);
> +
> + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN,
> + CRASH_ALIGN, crash_max);
> if (!crash_base) {
> pr_err("crashkernel reservation failed - No suitable area found.\n");
> return;
> }
> } else {
> + unsigned long long crash_max = crash_base + crash_size;
> unsigned long long start;
>
> - start = memblock_find_in_range(crash_base,
> - crash_base + crash_size,
> - crash_size, SECTION_SIZE);
> + start = memblock_phys_alloc_range(crash_size, SECTION_SIZE,
> + crash_base, crash_max);
> if (start != crash_base) {

If this is true and start is non-zero, then you need an
memblock_free(). However, since the range is equal to the size, then
that can never happen and just checking !start is sufficient.

> pr_err("crashkernel reservation failed - memory is in use.\n");
> return;
> }
> }
>
> - ret = memblock_reserve(crash_base, crash_size);
> - if (ret < 0) {
> - pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n",
> - (unsigned long)crash_base);
> - return;
> - }
> -
> pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
> (unsigned long)(crash_size >> 20),
> (unsigned long)(crash_base >> 20),
> diff --git a/arch/arm64/kvm/hyp/reserved_mem.c b/arch/arm64/kvm/hyp/reserved_mem.c
> index d654921dd09b..578670e3f608 100644
> --- a/arch/arm64/kvm/hyp/reserved_mem.c
> +++ b/arch/arm64/kvm/hyp/reserved_mem.c
> @@ -92,12 +92,10 @@ void __init kvm_hyp_reserve(void)
> * this is unmapped from the host stage-2, and fallback to PAGE_SIZE.
> */
> hyp_mem_size = hyp_mem_pages << PAGE_SHIFT;
> - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(),
> - ALIGN(hyp_mem_size, PMD_SIZE),
> - PMD_SIZE);
> + hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE),
> + PMD_SIZE);
> if (!hyp_mem_base)
> - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(),
> - hyp_mem_size, PAGE_SIZE);
> + hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE);
> else
> hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE);
>
> @@ -105,7 +103,6 @@ void __init kvm_hyp_reserve(void)
> kvm_err("Failed to reserve hyp memory\n");
> return;
> }
> - memblock_reserve(hyp_mem_base, hyp_mem_size);
>
> kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20,
> hyp_mem_base);
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 8490ed2917ff..d566478a06dd 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -74,6 +74,7 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init;
> static void __init reserve_crashkernel(void)
> {
> unsigned long long crash_base, crash_size;
> + unsigned long crash_max = arm64_dma_phys_limit;

It all works out to the same size, but it doesn't make sense that
crash_base and crash_size are long long and crash_max is long.

> int ret;
>
> ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> @@ -84,33 +85,18 @@ static void __init reserve_crashkernel(void)
>
> crash_size = PAGE_ALIGN(crash_size);
>
> - if (crash_base == 0) {
> - /* Current arm64 boot protocol requires 2MB alignment */
> - 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",
> - crash_size);
> - return;
> - }
> - } else {
> - /* User specifies base address explicitly. */
> - if (!memblock_is_region_memory(crash_base, crash_size)) {
> - pr_warn("cannot reserve crashkernel: region is not memory\n");
> - return;
> - }
> + /* User specifies base address explicitly. */
> + if (crash_base)
> + crash_max = crash_base + crash_size;
>
> - if (memblock_is_region_reserved(crash_base, crash_size)) {
> - pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
> - return;
> - }
> -
> - if (!IS_ALIGNED(crash_base, SZ_2M)) {
> - pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
> - return;

We've lost the alignment check.

Perhaps memblock_phys_alloc_range() should check that the start
matches the alignment. That would simplify the return handling as it
seems NULL is not the only error case.

> - }
> + /* Current arm64 boot protocol requires 2MB alignment */
> + crash_base = memblock_phys_alloc_range(crash_size, SZ_2M,
> + crash_base, crash_max);
> + if (!crash_base) {
> + pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
> + crash_size);
> + return;
> }
> - memblock_reserve(crash_base, crash_size);
>
> pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
> crash_base, crash_base + crash_size, crash_size >> 20);

[...]

> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
> index 6534c92d0f83..31b5856010cb 100644
> --- a/arch/x86/realmode/init.c
> +++ b/arch/x86/realmode/init.c
> @@ -28,7 +28,7 @@ void __init reserve_real_mode(void)
> WARN_ON(slab_is_available());
>
> /* Has to be under 1M so we can execute real-mode AP code. */
> - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
> + mem = memblock_phys_alloc_range(size, PAGE_SIZE, 0, 1<<20);
> if (!mem)
> pr_info("No sub-1M memory is available for the trampoline\n");
> else

Don't you need to drop the memblock_reserve() after this?