NVIDIA: SAUCE: iommu/arm-smmu-v3: Allow default substream bypass with…

Documentation/admin-guide/kernel-parameters.txt

@@ -4572,6 +4572,38 @@
 				bridges without forcing it upstream. Note:
 				this removes isolation between devices and
 				may put more devices in an IOMMU group.
+		config_acs=
+				Format:
+				<ACS flags>@<pci_dev>[; ...]
+				Specify one or more PCI devices (in the format
+				specified above) optionally prepended with flags
+				and separated by semicolons. The respective
+				capabilities will be enabled, disabled or
+				unchanged based on what is specified in
+				flags.
+
+				ACS Flags is defined as follows:
+				  bit-0 : ACS Source Validation
+				  bit-1 : ACS Translation Blocking
+				  bit-2 : ACS P2P Request Redirect
+				  bit-3 : ACS P2P Completion Redirect
+				  bit-4 : ACS Upstream Forwarding
+				  bit-5 : ACS P2P Egress Control
+				  bit-6 : ACS Direct Translated P2P
+				Each bit can be marked as:
+				  '0' – force disabled
+				  '1' – force enabled
+				  'x' – unchanged
+				For example,
+				  pci=config_acs=10x
+				would configure all devices that support
+				ACS to enable P2P Request Redirect, disable
+				Translation Blocking, and leave Source
+				Validation unchanged from whatever power-up
+				or firmware set it to.
+
+				Note: this may remove isolation between devices
+				and may put more devices in an IOMMU group.
 		force_floating	[S390] Force usage of floating interrupts.
 		nomio		[S390] Do not use MIO instructions.
 		norid		[S390] ignore the RID field and force use of

Ubuntu.md

@@ -1,8 +1,8 @@
-Name:    linux
-Version: 6.1.0
-Series:  23.04 (lunar)
+Name:    linux-nvidia
+Version: 6.8.0
+Series:  24.04 (noble)
 Description:
-    This is the source code for the Ubuntu linux kernel for the 23.04 series. This
-    source tree is used to produce the flavours: generic, generic-64k, generic-lpae.
+    This is the source code for the Ubuntu linux kernel for the 24.04 series. This
+    source tree is used to produce the flavours: nvidia, nvidia-64k.
     This kernel is configured to support the widest range of desktop, laptop and
     server configurations.

arch/arm/include/asm/pgtable.h

@@ -209,6 +209,8 @@ static inline void __sync_icache_dcache(pte_t pteval)
 extern void __sync_icache_dcache(pte_t pteval);
 #endif
 
+#define PFN_PTE_SHIFT		PAGE_SHIFT
+
 void set_ptes(struct mm_struct *mm, unsigned long addr,
 		      pte_t *ptep, pte_t pteval, unsigned int nr);
 #define set_ptes set_ptes

arch/arm/mm/mmu.c

@@ -1814,6 +1814,6 @@ void set_ptes(struct mm_struct *mm, unsigned long addr,
 		if (--nr == 0)
 			break;
 		ptep++;
-		pte_val(pteval) += PAGE_SIZE;
+		pteval = pte_next_pfn(pteval);
 	}
 }

arch/arm64/Kconfig

@@ -2229,6 +2229,15 @@ config UNWIND_PATCH_PAC_INTO_SCS
 	select UNWIND_TABLES
 	select DYNAMIC_SCS
 
+config ARM64_CONTPTE
+	bool "Contiguous PTE mappings for user memory" if EXPERT
+	depends on TRANSPARENT_HUGEPAGE
+	default y
+	help
+	  When enabled, user mappings are configured using the PTE contiguous
+	  bit, for any mappings that meet the size and alignment requirements.
+	  This reduces TLB pressure and improves performance.
+
 endmenu # "Kernel Features"
 
 menu "Boot options"

arch/arm64/include/asm/io.h

@@ -135,6 +135,138 @@ extern void __memset_io(volatile void __iomem *, int, size_t);
 #define memcpy_fromio(a,c,l)	__memcpy_fromio((a),(c),(l))
 #define memcpy_toio(c,a,l)	__memcpy_toio((c),(a),(l))
 
+/*
+ * The ARM64 iowrite implementation is intended to support drivers that want to
+ * use write combining. For instance PCI drivers using write combining with a 64
+ * byte __iowrite64_copy() expect to get a 64 byte MemWr TLP on the PCIe bus.
+ *
+ * Newer ARM core have sensitive write combining buffers, it is important that
+ * the stores be contiguous blocks of store instructions. Normal memcpy
+ * approaches have a very low chance to generate write combining.
+ *
+ * Since this is the only API on ARM64 that should be used with write combining
+ * it also integrates the DGH hint which is supposed to lower the latency to
+ * emit the large TLP from the CPU.
+ */
+
+static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to,
+						 const u32 *from, size_t count)
+{
+	switch (count) {
+	case 8:
+		asm volatile("str %w0, [%8, #4 * 0]\n"
+			     "str %w1, [%8, #4 * 1]\n"
+			     "str %w2, [%8, #4 * 2]\n"
+			     "str %w3, [%8, #4 * 3]\n"
+			     "str %w4, [%8, #4 * 4]\n"
+			     "str %w5, [%8, #4 * 5]\n"
+			     "str %w6, [%8, #4 * 6]\n"
+			     "str %w7, [%8, #4 * 7]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]),
+			       "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]),
+			       "rZ"(from[6]), "rZ"(from[7]), "r"(to));
+		break;
+	case 4:
+		asm volatile("str %w0, [%4, #4 * 0]\n"
+			     "str %w1, [%4, #4 * 1]\n"
+			     "str %w2, [%4, #4 * 2]\n"
+			     "str %w3, [%4, #4 * 3]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]),
+			       "rZ"(from[3]), "r"(to));
+		break;
+	case 2:
+		asm volatile("str %w0, [%2, #4 * 0]\n"
+			     "str %w1, [%2, #4 * 1]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "r"(to));
+		break;
+	case 1:
+		__raw_writel(*from, to);
+		break;
+	default:
+		BUILD_BUG();
+	}
+}
+
+void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count);
+
+static inline void __const_iowrite32_copy(void __iomem *to, const void *from,
+					  size_t count)
+{
+	if (count == 8 || count == 4 || count == 2 || count == 1) {
+		__const_memcpy_toio_aligned32(to, from, count);
+		dgh();
+	} else {
+		__iowrite32_copy_full(to, from, count);
+	}
+}
+
+#define __iowrite32_copy(to, from, count)                  \
+	(__builtin_constant_p(count) ?                     \
+		 __const_iowrite32_copy(to, from, count) : \
+		 __iowrite32_copy_full(to, from, count))
+
+static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to,
+						 const u64 *from, size_t count)
+{
+	switch (count) {
+	case 8:
+		asm volatile("str %x0, [%8, #8 * 0]\n"
+			     "str %x1, [%8, #8 * 1]\n"
+			     "str %x2, [%8, #8 * 2]\n"
+			     "str %x3, [%8, #8 * 3]\n"
+			     "str %x4, [%8, #8 * 4]\n"
+			     "str %x5, [%8, #8 * 5]\n"
+			     "str %x6, [%8, #8 * 6]\n"
+			     "str %x7, [%8, #8 * 7]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]),
+			       "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]),
+			       "rZ"(from[6]), "rZ"(from[7]), "r"(to));
+		break;
+	case 4:
+		asm volatile("str %x0, [%4, #8 * 0]\n"
+			     "str %x1, [%4, #8 * 1]\n"
+			     "str %x2, [%4, #8 * 2]\n"
+			     "str %x3, [%4, #8 * 3]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]),
+			       "rZ"(from[3]), "r"(to));
+		break;
+	case 2:
+		asm volatile("str %x0, [%2, #8 * 0]\n"
+			     "str %x1, [%2, #8 * 1]\n"
+			     :
+			     : "rZ"(from[0]), "rZ"(from[1]), "r"(to));
+		break;
+	case 1:
+		__raw_writeq(*from, to);
+		break;
+	default:
+		BUILD_BUG();
+	}
+}
+
+void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count);
+
+static inline void __const_iowrite64_copy(void __iomem *to, const void *from,
+					  size_t count)
+{
+	if (count == 8 || count == 4 || count == 2 || count == 1) {
+		__const_memcpy_toio_aligned64(to, from, count);
+		dgh();
+	} else {
+		__iowrite64_copy_full(to, from, count);
+	}
+}
+
+#define __iowrite64_copy(to, from, count)                  \
+	(__builtin_constant_p(count) ?                     \
+		 __const_iowrite64_copy(to, from, count) : \
+		 __iowrite64_copy_full(to, from, count))
+
 /*
  * I/O memory mapping functions.
  */