Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Apart from the arm64-specific bits (core arch and perf, new arm64
  selftests), it touches the generic cow_user_page() (reviewed by
  Kirill) together with a macro for x86 to preserve the existing
  behaviour on this architecture.

  Summary:

   - On ARMv8 CPUs without hardware updates of the access flag, avoid
     failing cow_user_page() on PFN mappings if the pte is old. The
     patches introduce an arch_faults_on_old_pte() macro, defined as
     false on x86. When true, cow_user_page() makes the pte young before
     attempting __copy_from_user_inatomic().

   - Covert the synchronous exception handling paths in
     arch/arm64/kernel/entry.S to C.

   - FTRACE_WITH_REGS support for arm64.

   - ZONE_DMA re-introduced on arm64 to support Raspberry Pi 4

   - Several kselftest cases specific to arm64, together with a
     MAINTAINERS update for these files (moved to the ARM64 PORT entry).

   - Workaround for a Neoverse-N1 erratum where the CPU may fetch stale
     instructions under certain conditions.

   - Workaround for Cortex-A57 and A72 errata where the CPU may
     speculatively execute an AT instruction and associate a VMID with
     the wrong guest page tables (corrupting the TLB).

   - Perf updates for arm64: additional PMU topologies on HiSilicon
     platforms, support for CCN-512 interconnect, AXI ID filtering in
     the IMX8 DDR PMU, support for the CCPI2 uncore PMU in ThunderX2.

   - GICv3 optimisation to avoid a heavy barrier when accessing the
     ICC_PMR_EL1 register.

   - ELF HWCAP documentation updates and clean-up.

   - SMC calling convention conduit code clean-up.

   - KASLR diagnostics printed during boot

   - NVIDIA Carmel CPU added to the KPTI whitelist

   - Some arm64 mm clean-ups: use generic free_initrd_mem(), remove
     stale macro, simplify calculation in __create_pgd_mapping(), typos.

   - Kconfig clean-ups: CMDLINE_FORCE to depend on CMDLINE, choice for
     endinanness to help with allmodconfig"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (93 commits)
  arm64: Kconfig: add a choice for endianness
  kselftest: arm64: fix spelling mistake "contiguos" -> "contiguous"
  arm64: Kconfig: make CMDLINE_FORCE depend on CMDLINE
  MAINTAINERS: Add arm64 selftests to the ARM64 PORT entry
  arm64: kaslr: Check command line before looking for a seed
  arm64: kaslr: Announce KASLR status on boot
  kselftest: arm64: fake_sigreturn_misaligned_sp
  kselftest: arm64: fake_sigreturn_bad_size
  kselftest: arm64: fake_sigreturn_duplicated_fpsimd
  kselftest: arm64: fake_sigreturn_missing_fpsimd
  kselftest: arm64: fake_sigreturn_bad_size_for_magic0
  kselftest: arm64: fake_sigreturn_bad_magic
  kselftest: arm64: add helper get_current_context
  kselftest: arm64: extend test_init functionalities
  kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht]
  kselftest: arm64: mangle_pstate_invalid_daif_bits
  kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils
  kselftest: arm64: extend toplevel skeleton Makefile
  drivers/perf: hisi: update the sccl_id/ccl_id for certain HiSilicon platform
  arm64: mm: reserve CMA and crashkernel in ZONE_DMA32
  ...

1 files changed, 54 insertions, 37 deletions

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 45c00a54909c..be9481cdf3b9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -20,6 +20,7 @@
 #include <linux/sort.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
@@ -41,6 +42,8 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
+#define ARM64_ZONE_DMA_BITS	30
+
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
@@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset);
 struct page *vmemmap __ro_after_init;
 EXPORT_SYMBOL(vmemmap);
 
+/*
+ * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
+ * memory as some devices, namely the Raspberry Pi 4, have peripherals with
+ * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
+ * bit addressable memory area.
+ */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
+static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void)
 {
 }
 #endif /* CONFIG_CRASH_DUMP */
+
 /*
- * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
- * currently assumes that for memory starting above 4G, 32-bit devices will
- * use a DMA offset.
+ * Return the maximum physical address for a zone with a given address size
+ * limit. It currently assumes that for memory starting above 4G, 32-bit
+ * devices will use a DMA offset.
  */
-static phys_addr_t __init max_zone_dma_phys(void)
+static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
 {
-	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
-	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits);
+	return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_NUMA
@@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
+#endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max;
 
@@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma = min;
+	unsigned long max_dma32 = min;
+	unsigned long __maybe_unused max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-	/* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 	max_dma = PFN_DOWN(arm64_dma_phys_limit);
-	zone_size[ZONE_DMA32] = max_dma - min;
+	zone_size[ZONE_DMA] = max_dma - min;
+	max_dma32 = max_dma;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	max_dma32 = PFN_DOWN(arm64_dma32_phys_limit);
+	zone_size[ZONE_DMA32] = max_dma32 - max_dma;
 #endif
-	zone_size[ZONE_NORMAL] = max - max_dma;
+	zone_size[ZONE_NORMAL] = max - max_dma32;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 		if (start < max_dma) {
-			unsigned long dma_end = min(end, max_dma);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+			unsigned long dma_end = min_not_zero(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
 #endif
-		if (end > max_dma) {
+#ifdef CONFIG_ZONE_DMA32
+		if (start < max_dma32) {
+			unsigned long dma32_end = min(end, max_dma32);
+			unsigned long dma32_start = max(start, max_dma);
+			zhole_size[ZONE_DMA32] -= dma32_end - dma32_start;
+		}
+#endif
+		if (end > max_dma32) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma);
+			unsigned long normal_start = max(start, max_dma32);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -418,11 +443,15 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		zone_dma_bits = ARM64_ZONE_DMA_BITS;
+		arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS);
+	}
+
 	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma_phys_limit = max_zone_dma_phys();
+		arm64_dma32_phys_limit = max_zone_phys(32);
 	else
-		arm64_dma_phys_limit = PHYS_MASK + 1;
+		arm64_dma32_phys_limit = PHYS_MASK + 1;
 
 	reserve_crashkernel();
 
@@ -430,7 +459,7 @@ void __init arm64_memblock_init(void)
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
-	dma_contiguous_reserve(arm64_dma_phys_limit);
+	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -534,7 +563,7 @@ static void __init free_unused_memmap(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
@@ -571,7 +600,7 @@ void free_initmem(void)
 {
 	free_reserved_area(lm_alias(__init_begin),
 			   lm_alias(__init_end),
-			   0, "unused kernel");
+			   POISON_FREE_INITMEM, "unused kernel");
 	/*
 	 * Unmap the __init region but leave the VM area in place. This
 	 * prevents the region from being reused for kernel modules, which
@@ -580,18 +609,6 @@ void free_initmem(void)
 	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	unsigned long aligned_start, aligned_end;
-
-	aligned_start = __virt_to_phys(start) & PAGE_MASK;
-	aligned_end = PAGE_ALIGN(__virt_to_phys(end));
-	memblock_free(aligned_start, aligned_end - aligned_start);
-	free_reserved_area((void *)start, (void *)end, 0, "initrd");
-}
-#endif
-
 /*
  * Dump out memory limit information on panic.
  */