riscv: implement Zicbom-based CMO instructions + the t-head variant

This series is based on the alternatives changes done in my svpbmt
series and thus also depends on Atish's isa-extension parsing series.

It implements using the cache-management instructions from the  Zicbom-
extension to handle cache flush, etc actions on platforms needing them.

SoCs using cpu cores from T-Head like the Allwinne D1 implement a
different set of cache instructions. But while they are different,
instructions they provide the same functionality, so a variant can easly
hook into the existing alternatives mechanism on those.

[Palmer:  Some minor fixups, including a RISCV_ISA_ZICBOM dependency on
MMU that's probably not strictly necessary.  The Zicbom support will
trip up sparse for users that have new toolchains, I just sent a patch.]

Link: https://lore.kernel.org/all/20220706231536.2041855-1-heiko@sntech.de/
Link: https://lore.kernel.org/linux-sparse/20220811033138.20676-1-palmer@rivosinc.com/T/#u
* palmer/riscv-zicbom:
  riscv: implement cache-management errata for T-Head SoCs
  riscv: Add support for non-coherent devices using zicbom extension
  dt-bindings: riscv: document cbom-block-size
  of: also handle dma-noncoherent in of_dma_is_coherent()

diff --cc arch/riscv/Kconfig
index 5c52a82,897ae28..3d49317
--- 1/arch/riscv/Kconfig
--- 2/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@@ -392,6 -385,28 +401,28 @@@ config RISCV_ISA_SVPBM
  
           If you don't know what to do here, say Y.
  
 -      depends on !XIP_KERNEL
+ config CC_HAS_ZICBOM
+       bool
+       default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+       default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+ 
+ config RISCV_ISA_ZICBOM
+       bool "Zicbom extension support for non-coherent DMA operation"
+       depends on CC_HAS_ZICBOM
++      depends on !XIP_KERNEL && MMU
+       select RISCV_DMA_NONCOHERENT
+       select RISCV_ALTERNATIVE
+       default y
+       help
+          Adds support to dynamically detect the presence of the ZICBOM
+          extension (Cache Block Management Operations) and enable its
+          usage.
+ 
+          The Zicbom extension can be used to handle for example
+          non-coherent DMA support on devices that need it.
+ 
+          If you don't know what to do here, say Y.
+ 
  config FPU
        bool "FPU support"
        default y

diff --cc arch/riscv/Kconfig.erratas
index f62b628,3223e53..6850e93
--- 1/arch/riscv/Kconfig.erratas
--- 2/arch/riscv/Kconfig.erratas
+++ b/arch/riscv/Kconfig.erratas
@@@ -55,4 -55,15 +55,15 @@@ config ERRATA_THEAD_PBM
  
          If you don't know what to do here, say "Y".
  
 -endmenu
+ config ERRATA_THEAD_CMO
+       bool "Apply T-Head cache management errata"
+       depends on ERRATA_THEAD
+       select RISCV_DMA_NONCOHERENT
+       default y
+       help
+         This will apply the cache management errata to handle the
+         non-standard handling on non-coherent operations on T-Head SoCs.
+ 
+         If you don't know what to do here, say "Y".
+ 
 +endmenu # "CPU errata selection"

diff --cc arch/riscv/Makefile
Simple merge

diff --cc arch/riscv/include/asm/errata_list.h
Simple merge

diff --cc arch/riscv/kernel/cpu.c
Simple merge

diff --cc arch/riscv/kernel/cpufeature.c
Simple merge

diff --cc arch/riscv/mm/dma-noncoherent.c
index 0000000,a8dc0bd..cd22253
mode 000000,100644..100644
--- /dev/null
--- 2/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@@ -1,0 -1,112 +1,116 @@@
 -              int hartid = riscv_of_processor_hartid(node);
+ // SPDX-License-Identifier: GPL-2.0-only
+ /*
+  * RISC-V specific functions to support DMA for non-coherent devices
+  *
+  * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+  */
+ 
+ #include <linux/dma-direct.h>
+ #include <linux/dma-map-ops.h>
+ #include <linux/mm.h>
+ #include <linux/of.h>
+ #include <linux/of_device.h>
+ #include <asm/cacheflush.h>
+ 
+ static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES;
+ static bool noncoherent_supported;
+ 
+ void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+                             enum dma_data_direction dir)
+ {
+       void *vaddr = phys_to_virt(paddr);
+ 
+       switch (dir) {
+       case DMA_TO_DEVICE:
+               ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+               break;
+       case DMA_FROM_DEVICE:
+               ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+               break;
+       case DMA_BIDIRECTIONAL:
+               ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+               break;
+       default:
+               break;
+       }
+ }
+ 
+ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+                          enum dma_data_direction dir)
+ {
+       void *vaddr = phys_to_virt(paddr);
+ 
+       switch (dir) {
+       case DMA_TO_DEVICE:
+               break;
+       case DMA_FROM_DEVICE:
+       case DMA_BIDIRECTIONAL:
+               ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+               break;
+       default:
+               break;
+       }
+ }
+ 
+ void arch_dma_prep_coherent(struct page *page, size_t size)
+ {
+       void *flush_addr = page_address(page);
+ 
+       ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
+ }
+ 
+ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+               const struct iommu_ops *iommu, bool coherent)
+ {
+       WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
+                  TAINT_CPU_OUT_OF_SPEC,
+                  "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)",
+                  dev_driver_string(dev), dev_name(dev),
+                  ARCH_DMA_MINALIGN, riscv_cbom_block_size);
+ 
+       WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC,
+                  "%s %s: device non-coherent but no non-coherent operations supported",
+                  dev_driver_string(dev), dev_name(dev));
+ 
+       dev->dma_coherent = coherent;
+ }
+ 
+ #ifdef CONFIG_RISCV_ISA_ZICBOM
+ void riscv_init_cbom_blocksize(void)
+ {
+       struct device_node *node;
+       int ret;
+       u32 val;
+ 
+       for_each_of_cpu_node(node) {
 -                              pr_warn("cbom-block-size mismatched between harts %d and %d\n",
++              unsigned long hartid;
+               int cbom_hartid;
+ 
++              ret = riscv_of_processor_hartid(node, &hartid);
++              if (ret)
++                      continue;
++
+               if (hartid < 0)
+                       continue;
+ 
+               /* set block-size for cbom extension if available */
+               ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+               if (ret)
+                       continue;
+ 
+               if (!riscv_cbom_block_size) {
+                       riscv_cbom_block_size = val;
+                       cbom_hartid = hartid;
+               } else {
+                       if (riscv_cbom_block_size != val)
++                              pr_warn("cbom-block-size mismatched between harts %d and %lu\n",
+                                       cbom_hartid, hartid);
+               }
+       }
+ }
+ #endif
+ 
+ void riscv_noncoherent_supported(void)
+ {
+       noncoherent_supported = true;
+ }