[PATCH v6] lib: sbi: Set the scratch allocation to alignment to cacheline size.
Samuel Holland
samuel.holland at sifive.com
Wed Apr 23 18:17:33 PDT 2025
Hi Raj,
On 2025-04-23 5:50 PM, Raj Vishwanathan wrote:
> We set the scratch allocation alignment to cacheline size,specified by
> riscv,cbom-block-size in the dts file to avoid two atomic variables from
> the same cache line causing livelock on some platforms. If the cacheline
> is not specified, we set it a default value.
>
> Signed-off-by: Raj Vishwanathan <Raj.Vishwanathan at gmail.com>
> --
> Changes in V6:
> Add assert for assert_member_offset for cbom_block_size
> Update the subject line
> Changes in V5:
> Formatting issues
> Changes in V4:
> Pickup the cacheline size from the dts file
> Changes in V3:
> Remove platform specific references to 64 Bytes.
> Changes in V2:
> Added a new configuration to get the alignment size.
> Change in V1:
> Original Patch
> ---
> include/sbi/sbi_platform.h | 5 +++++
> include/sbi_utils/fdt/fdt_helper.h | 2 ++
> lib/sbi/sbi_scratch.c | 26 ++++++++++++++++++++++++--
> lib/utils/fdt/fdt_helper.c | 24 ++++++++++++++++++++++++
> platform/generic/platform.c | 9 +++++++++
> 5 files changed, 64 insertions(+), 2 deletions(-)
>
> diff --git a/include/sbi/sbi_platform.h b/include/sbi/sbi_platform.h
> index 82840ae..08ece32 100644
> --- a/include/sbi/sbi_platform.h
> +++ b/include/sbi/sbi_platform.h
> @@ -39,6 +39,8 @@
> #define SBI_PLATFORM_FIRMWARE_CONTEXT_OFFSET (0x60 + __SIZEOF_POINTER__)
> /** Offset of hart_index2id in struct sbi_platform */
> #define SBI_PLATFORM_HART_INDEX2ID_OFFSET (0x60 + (__SIZEOF_POINTER__ * 2))
> +/** Offset of cbom_block_size in struct sbi_platform */
> +#define SBI_PLATFORM_CBOM_BLOCK_SIZE_OFFSET (0x60 + (__SIZEOF_POINTER__ * 3))
>
> #define SBI_PLATFORM_TLB_RANGE_FLUSH_LIMIT_DEFAULT (1UL << 12)
>
> @@ -190,6 +192,8 @@ struct sbi_platform {
> * hart_index2id[<abc>] = <abc>
> */
> const u32 *hart_index2id;
> + /** Allocation alignment for Scratch */
> + unsigned long cbom_block_size;
> };
>
> /**
> @@ -207,6 +211,7 @@ assert_member_offset(struct sbi_platform, reserved, SBI_PLATFORM_RESERVED_OFFSET
> assert_member_offset(struct sbi_platform, platform_ops_addr, SBI_PLATFORM_OPS_OFFSET);
> assert_member_offset(struct sbi_platform, firmware_context, SBI_PLATFORM_FIRMWARE_CONTEXT_OFFSET);
> assert_member_offset(struct sbi_platform, hart_index2id, SBI_PLATFORM_HART_INDEX2ID_OFFSET);
> +assert_member_offset(struct sbi_platform, cbom_block_size, SBI_PLATFORM_CBOM_BLOCK_SIZE_OFFSET);
>
> /** Get pointer to sbi_platform for sbi_scratch pointer */
> #define sbi_platform_ptr(__s) \
> diff --git a/include/sbi_utils/fdt/fdt_helper.h b/include/sbi_utils/fdt/fdt_helper.h
> index 5875880..04c850c 100644
> --- a/include/sbi_utils/fdt/fdt_helper.h
> +++ b/include/sbi_utils/fdt/fdt_helper.h
> @@ -50,6 +50,8 @@ int fdt_parse_hart_id(const void *fdt, int cpu_offset, u32 *hartid);
>
> int fdt_parse_max_enabled_hart_id(const void *fdt, u32 *max_hartid);
>
> +int fdt_parse_cbom_block_size(const void *fdt, int cpu_offset, unsigned long *cbom_block_size);
> +
> int fdt_parse_timebase_frequency(const void *fdt, unsigned long *freq);
>
> int fdt_parse_isa_extensions(const void *fdt, unsigned int hartid,
> diff --git a/lib/sbi/sbi_scratch.c b/lib/sbi/sbi_scratch.c
> index 8c7eeaf..916f283 100644
> --- a/lib/sbi/sbi_scratch.c
> +++ b/lib/sbi/sbi_scratch.c
> @@ -14,6 +14,8 @@
> #include <sbi/sbi_scratch.h>
> #include <sbi/sbi_string.h>
>
> +#define DEFAULT_SCRATCH_ALLOC_ALIGN __SIZEOF_POINTER__
> +
> u32 sbi_scratch_hart_count;
> u32 hartindex_to_hartid_table[SBI_HARTMASK_MAX_BITS] = { [0 ... SBI_HARTMASK_MAX_BITS-1] = -1U };
> struct sbi_scratch *hartindex_to_scratch_table[SBI_HARTMASK_MAX_BITS];
> @@ -21,6 +23,19 @@ struct sbi_scratch *hartindex_to_scratch_table[SBI_HARTMASK_MAX_BITS];
> static spinlock_t extra_lock = SPIN_LOCK_INITIALIZER;
> static unsigned long extra_offset = SBI_SCRATCH_EXTRA_SPACE_OFFSET;
>
> +static unsigned long sbi_get_scratch_alloc_align(void)
> +{
> + const struct sbi_platform *plat;
> + /*
> + * Get the alignment size. We will return DEFAULT_SCRATCH_ALLOC_ALIGNMENT
> + * or riscv,cbom_block_size
> + */
> + plat = sbi_platform_thishart_ptr();
> + if (!plat || !plat->cbom_block_size)
> + return DEFAULT_SCRATCH_ALLOC_ALIGN;
> + return plat->cbom_block_size;
> +}
> +
> u32 sbi_hartid_to_hartindex(u32 hartid)
> {
> sbi_for_each_hartindex(i)
> @@ -57,6 +72,7 @@ unsigned long sbi_scratch_alloc_offset(unsigned long size)
> void *ptr;
> unsigned long ret = 0;
> struct sbi_scratch *rscratch;
> + unsigned long scratch_alloc_align = 0;
This variable is unconditionally assigned below, so it doesn't need to be
initialized here.
>
> /*
> * We have a simple brain-dead allocator which never expects
> @@ -70,8 +86,14 @@ unsigned long sbi_scratch_alloc_offset(unsigned long size)
> if (!size)
> return 0;
>
> - size += __SIZEOF_POINTER__ - 1;
> - size &= ~((unsigned long)__SIZEOF_POINTER__ - 1);
> + scratch_alloc_align = sbi_get_scratch_alloc_align();
> +
> + /*
> + * We let the allocation align to cacheline bytes to avoid livelock on
> + * certain platforms due to atomic variables from the same cache line.
> + */
> + size += scratch_alloc_align - 1;
> + size &= ~(scratch_alloc_align - 1);
>
> spin_lock(&extra_lock);
>
> diff --git a/lib/utils/fdt/fdt_helper.c b/lib/utils/fdt/fdt_helper.c
> index 79e59dd..b2d91fd 100644
> --- a/lib/utils/fdt/fdt_helper.c
> +++ b/lib/utils/fdt/fdt_helper.c
> @@ -246,6 +246,30 @@ int fdt_parse_hart_id(const void *fdt, int cpu_offset, u32 *hartid)
> return 0;
> }
>
> +int fdt_parse_cbom_block_size(const void *fdt, int cpu_offset, unsigned long *cbom_block_size)
> +{
> + int len;
> + const void *prop;
> + const fdt32_t *val;
> +
> + if (!fdt || cpu_offset < 0)
> + return SBI_EINVAL;
> +
> + prop = fdt_getprop(fdt, cpu_offset, "device_type", &len);
> + if (!prop || !len)
> + return SBI_EINVAL;
> + if (strncmp (prop, "cpu", strlen ("cpu")))
> + return SBI_EINVAL;
> +
> + val = fdt_getprop(fdt, cpu_offset, "riscv,cbom-block-size", &len);
> + if (!val || len < sizeof(fdt32_t))
> + return SBI_EINVAL;
> +
> + if (cbom_block_size)
> + *cbom_block_size = fdt32_to_cpu(*val);
> + return 0;
> +}
> +
> int fdt_parse_max_enabled_hart_id(const void *fdt, u32 *max_hartid)
> {
> u32 hartid;
> diff --git a/platform/generic/platform.c b/platform/generic/platform.c
> index f3072be..2b1b949 100644
> --- a/platform/generic/platform.c
> +++ b/platform/generic/platform.c
> @@ -147,6 +147,9 @@ unsigned long fw_platform_init(unsigned long arg0, unsigned long arg1,
> const void *fdt = (void *)arg1;
> u32 hartid, hart_count = 0;
> int rc, root_offset, cpus_offset, cpu_offset, len;
> + unsigned long cbom_block_size = 0;
> + unsigned long tmp = 0;
> +
>
Extra blank line here. These are trivial issues, so:
Reviewed-by: Samuel Holland <samuel.holland at sifive.com>
> root_offset = fdt_path_offset(fdt, "/");
> if (root_offset < 0)
> @@ -174,11 +177,17 @@ unsigned long fw_platform_init(unsigned long arg0, unsigned long arg1,
> continue;
>
> generic_hart_index2id[hart_count++] = hartid;
> +
> + rc = fdt_parse_cbom_block_size(fdt, cpu_offset, &tmp);
> + if (rc)
> + continue;
> + cbom_block_size = MAX(tmp, cbom_block_size);
> }
>
> platform.hart_count = hart_count;
> platform.heap_size = fw_platform_get_heap_size(fdt, hart_count);
> platform_has_mlevel_imsic = fdt_check_imsic_mlevel(fdt);
> + platform.cbom_block_size = cbom_block_size;
>
> fw_platform_coldboot_harts_init(fdt);
>
More information about the opensbi
mailing list