Merge tag 'arc-4.18-final' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC fixes from Vineet Gupta:
 "Another batch of fixes for ARC, this time mainly DMA API rework
  wreckage:

   - Fix software managed DMA wreckage after rework in 4.17 [Euginey]
      * missing cache flush
      * SMP_CACHE_BYTES vs cache_line_size

   - Fix allmodconfig build errors [Randy]

   - Maintainer update for Mellanox (EZChip) NPS platform"

* tag 'arc-4.18-final' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  arc: fix type warnings in arc/mm/cache.c
  arc: fix build errors in arc/include/asm/delay.h
  arc: [plat-eznps] fix printk warning in arc/plat-eznps/mtm.c
  arc: [plat-eznps] fix data type errors in platform headers
  ARC: [plat-eznps] Add missing struct nps_host_reg_aux_dpc
  ARC: add SMP_CACHE_BYTES value validate
  ARC: dma [non-IOC] setup SMP_CACHE_BYTES and cache_line_size
  ARC: dma [non IOC]: fix arc_dma_sync_single_for_(device|cpu)
  ARC: Add Ofer Levi as plat-eznps maintainer

8 files changed, 85 insertions, 8 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index f6a9b0842319..7cebd5bba8a8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5444,6 +5444,7 @@ F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
 M:	Vineet Gupta <vgupta@synopsys.com>
+M:	Ofer Levi <oferle@mellanox.com>
 S:	Supported
 F:	arch/arc/plat-eznps
 F:	arch/arc/boot/dts/eznps.dts
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 9cf59fc60eab..5151d81476a1 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -50,6 +50,9 @@ config ARC
 	select HAVE_KERNEL_LZMA
 	select ARCH_HAS_PTE_SPECIAL
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 config MIGHT_HAVE_PCI
 	bool
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 8486f328cc5d..ff7d3232764a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -48,7 +48,9 @@
 })
 
 /* Largest line length for either L1 or L2 is 128 bytes */
-#define ARCH_DMA_MINALIGN      128
+#define SMP_CACHE_BYTES		128
+#define cache_line_size()	SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
 
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index d5da2115d78a..03d6bb0f4e13 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -17,8 +17,11 @@
 #ifndef __ASM_ARC_UDELAY_H
 #define __ASM_ARC_UDELAY_H
 
+#include <asm-generic/types.h>
 #include <asm/param.h>		/* HZ */
 
+extern unsigned long loops_per_jiffy;
+
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9dbe645ee127..25c631942500 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
 		      unsigned long pfn)
 {
-	unsigned int paddr = pfn << PAGE_SHIFT;
+	phys_addr_t paddr = pfn << PAGE_SHIFT;
 
 	u_vaddr &= PAGE_MASK;
 
@@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page,
 		     unsigned long u_vaddr)
 {
 	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
+	__flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+	__flush_dcache_page((phys_addr_t)page_address(page),
+			    (phys_addr_t)page_address(page));
 
 }
 
@@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void)
 		}
 	}
 
+	/*
+	 * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+	 * or equal to any cache line length.
+	 */
+	BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+			 "SMP_CACHE_BYTES must be >= any cache line length");
+	if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+		panic("L2 Cache line [%d] > kernel Config [%d]\n",
+		      l2_line_sz, SMP_CACHE_BYTES);
+
 	/* Note that SLC disable not formally supported till HS 3.0 */
 	if (is_isa_arcv2() && l2_line_sz && !slc_enable)
 		arc_slc_disable();
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c1071840979..ec47e6079f5d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lkml.org/lkml/2018/5/18/979
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ *          |   map          ==  for_device     |   unmap     ==  for_cpu
+ *          |----------------------------------------------------------------
+ * TO_DEV   |   writeback        writeback      |   none          none
+ * FROM_DEV |   invalidate       invalidate     |   invalidate*   invalidate*
+ * BIDIR    |   writeback+inv    writeback+inv  |   invalidate    invalidate
+ *
+ *     [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_wback(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
 
 void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_inv(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index 0c7d11022d0f..4f6a1673b3a6 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -21,6 +21,7 @@
 #error "Incorrect ctop.h include"
 #endif
 
+#include <linux/types.h>
 #include <soc/nps/common.h>
 
 /* core auxiliary registers */
@@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst {
 };
 
 /* AUX registers definition */
+struct nps_host_reg_aux_dpc {
+	union {
+		struct {
+			u32 ien:1, men:1, hen:1, reserved:29;
+		};
+		u32 value;
+	};
+};
+
 struct nps_host_reg_aux_udmc {
 	union {
 		struct {
diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c
index 2388de3d09ef..ed0077ef666e 100644
--- a/arch/arc/plat-eznps/mtm.c
+++ b/arch/arc/plat-eznps/mtm.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/log2.h>
 #include <asm/arcregs.h>
@@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu)
 /* Verify and set the value of the mtm hs counter */
 static int __init set_mtm_hs_ctr(char *ctr_str)
 {
-	long hs_ctr;
+	int hs_ctr;
 	int ret;
 
-	ret = kstrtol(ctr_str, 0, &hs_ctr);
+	ret = kstrtoint(ctr_str, 0, &hs_ctr);
 
 	if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) {
 		pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n",