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

Pull arm64 fixes from Catalin Marinas:
 "Nothing major, some left-overs from the recent merging window (MTE,
  coco) and some newly found issues like the ptrace() ones.

   - MTE/hugetlbfs:

      - Set VM_MTE_ALLOWED in the arch code and remove it from the core
        code for hugetlbfs mappings

      - Fix copy_highpage() warning when the source is a huge page but
        not MTE tagged, taking the wrong small page path

   - drivers/virt/coco:

      - Add the pKVM and Arm CCA drivers under the arm64 maintainership

      - Fix the pkvm driver to fall back to ioremap() (and warn) if the
        MMIO_GUARD hypercall fails

      - Keep the Arm CCA driver default 'n' rather than 'm'

   - A series of fixes for the arm64 ptrace() implementation,
     potentially leading to the kernel consuming uninitialised stack
     variables when PTRACE_SETREGSET is invoked with a length of 0

   - Fix zone_dma_limit calculation when RAM starts below 4GB and
     ZONE_DMA is capped to this limit

   - Fix early boot warning with CONFIG_DEBUG_VIRTUAL=y triggered by a
     call to page_to_phys() (from patch_map()) which checks pfn_valid()
     before vmemmap has been set up

   - Do not clobber bits 15:8 of the ASID used for TTBR1_EL1 and TLBI
     ops when the kernel assumes 8-bit ASIDs but running under a
     hypervisor on a system that implements 16-bit ASIDs (found running
     Linux under Parallels on Apple M4)

   - ACPI/IORT: Add PMCG platform information for HiSilicon HIP09A as it
     is using the same SMMU PMCG as HIP09 and suffers from the same
     errata

   - Add GCS to cpucap_is_possible(), missed in the recent merge"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: ptrace: fix partial SETREGSET for NT_ARM_GCS
  arm64: ptrace: fix partial SETREGSET for NT_ARM_POE
  arm64: ptrace: fix partial SETREGSET for NT_ARM_FPMR
  arm64: ptrace: fix partial SETREGSET for NT_ARM_TAGGED_ADDR_CTRL
  arm64: cpufeature: Add GCS to cpucap_is_possible()
  coco: virt: arm64: Do not enable cca guest driver by default
  arm64: mte: Fix copy_highpage() warning on hugetlb folios
  arm64: Ensure bits ASID[15:8] are masked out when the kernel uses 8-bit ASIDs
  ACPI/IORT: Add PMCG platform information for HiSilicon HIP09A
  MAINTAINERS: Add CCA and pKVM CoCO guest support to the ARM64 entry
  drivers/virt: pkvm: Don't fail ioremap() call if MMIO_GUARD fails
  arm64: patching: avoid early page_to_phys()
  arm64: mm: Fix zone_dma_limit calculation
  arm64: mte: set VM_MTE_ALLOWED for hugetlbfs at correct place

8 files changed, 60 insertions, 38 deletions

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 201a46efd918..cbbf70e0f204 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -44,6 +44,8 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
 	case ARM64_HAS_S1POE:
 		return IS_ENABLED(CONFIG_ARM64_POE);
+	case ARM64_HAS_GCS:
+		return IS_ENABLED(CONFIG_ARM64_GCS);
 	case ARM64_UNMAP_KERNEL_AT_EL0:
 		return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
 	case ARM64_WORKAROUND_843419:
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index b64e49bd9d10..8b4e5a3cd24c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -847,8 +847,7 @@ static inline bool system_supports_poe(void)
 
 static inline bool system_supports_gcs(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_GCS) &&
-		alternative_has_cap_unlikely(ARM64_HAS_GCS);
+	return alternative_has_cap_unlikely(ARM64_HAS_GCS);
 }
 
 static inline bool system_supports_haft(void)
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 1d53022fc7e1..21df8bbd2668 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -7,6 +7,7 @@
 #ifndef BUILD_VDSO
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/hugetlb.h>
 #include <linux/shmem_fs.h>
 #include <linux/types.h>
 
@@ -44,7 +45,7 @@ static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
 	if (system_supports_mte()) {
 		if (flags & (MAP_ANONYMOUS | MAP_HUGETLB))
 			return VM_MTE_ALLOWED;
-		if (shmem_file(file))
+		if (shmem_file(file) || is_file_hugepages(file))
 			return VM_MTE_ALLOWED;
 	}
 
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 7f99723fbb8c..1041bc67a3ee 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -30,20 +30,17 @@ static bool is_image_text(unsigned long addr)
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
-	unsigned long uintaddr = (uintptr_t) addr;
-	bool image = is_image_text(uintaddr);
-	struct page *page;
-
-	if (image)
-		page = phys_to_page(__pa_symbol(addr));
-	else if (IS_ENABLED(CONFIG_EXECMEM))
-		page = vmalloc_to_page(addr);
-	else
-		return addr;
-
-	BUG_ON(!page);
-	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
-			(uintaddr & ~PAGE_MASK));
+	phys_addr_t phys;
+
+	if (is_image_text((unsigned long)addr)) {
+		phys = __pa_symbol(addr);
+	} else {
+		struct page *page = vmalloc_to_page(addr);
+		BUG_ON(!page);
+		phys = page_to_phys(page) + offset_in_page(addr);
+	}
+
+	return (void *)set_fixmap_offset(fixmap, phys);
 }
 
 static void __kprobes patch_unmap(int fixmap)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e4437f62a2cd..f79b0d5f71ac 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -720,6 +720,8 @@ static int fpmr_set(struct task_struct *target, const struct user_regset *regset
 	if (!system_supports_fpmr())
 		return -EINVAL;
 
+	fpmr = target->thread.uw.fpmr;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count);
 	if (ret)
 		return ret;
@@ -1427,7 +1429,7 @@ static int tagged_addr_ctrl_get(struct task_struct *target,
 {
 	long ctrl = get_tagged_addr_ctrl(target);
 
-	if (IS_ERR_VALUE(ctrl))
+	if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
 		return ctrl;
 
 	return membuf_write(&to, &ctrl, sizeof(ctrl));
@@ -1441,6 +1443,10 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct
 	int ret;
 	long ctrl;
 
+	ctrl = get_tagged_addr_ctrl(target);
+	if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
+		return ctrl;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
 	if (ret)
 		return ret;
@@ -1472,6 +1478,8 @@ static int poe_set(struct task_struct *target, const struct
 	if (!system_supports_poe())
 		return -EINVAL;
 
+	ctrl = target->thread.por_el0;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
 	if (ret)
 		return ret;
@@ -1483,6 +1491,22 @@ static int poe_set(struct task_struct *target, const struct
 #endif
 
 #ifdef CONFIG_ARM64_GCS
+static void task_gcs_to_user(struct user_gcs *user_gcs,
+			     const struct task_struct *target)
+{
+	user_gcs->features_enabled = target->thread.gcs_el0_mode;
+	user_gcs->features_locked = target->thread.gcs_el0_locked;
+	user_gcs->gcspr_el0 = target->thread.gcspr_el0;
+}
+
+static void task_gcs_from_user(struct task_struct *target,
+			       const struct user_gcs *user_gcs)
+{
+	target->thread.gcs_el0_mode = user_gcs->features_enabled;
+	target->thread.gcs_el0_locked = user_gcs->features_locked;
+	target->thread.gcspr_el0 = user_gcs->gcspr_el0;
+}
+
 static int gcs_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   struct membuf to)
@@ -1495,9 +1519,7 @@ static int gcs_get(struct task_struct *target,
 	if (target == current)
 		gcs_preserve_current_state();
 
-	user_gcs.features_enabled = target->thread.gcs_el0_mode;
-	user_gcs.features_locked = target->thread.gcs_el0_locked;
-	user_gcs.gcspr_el0 = target->thread.gcspr_el0;
+	task_gcs_to_user(&user_gcs, target);
 
 	return membuf_write(&to, &user_gcs, sizeof(user_gcs));
 }
@@ -1513,6 +1535,8 @@ static int gcs_set(struct task_struct *target, const struct
 	if (!system_supports_gcs())
 		return -EINVAL;
 
+	task_gcs_to_user(&user_gcs, target);
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1);
 	if (ret)
 		return ret;
@@ -1520,9 +1544,7 @@ static int gcs_set(struct task_struct *target, const struct
 	if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
 		return -EINVAL;
 
-	target->thread.gcs_el0_mode = user_gcs.features_enabled;
-	target->thread.gcs_el0_locked = user_gcs.features_locked;
-	target->thread.gcspr_el0 = user_gcs.gcspr_el0;
+	task_gcs_from_user(target, &user_gcs);
 
 	return 0;
 }
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 188197590fc9..b2ac06246327 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -32,9 +32,9 @@ static unsigned long nr_pinned_asids;
 static unsigned long *pinned_asid_map;
 
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
-#define ASID_FIRST_VERSION	(1UL << asid_bits)
+#define ASID_FIRST_VERSION	(1UL << 16)
 
-#define NUM_USER_ASIDS		ASID_FIRST_VERSION
+#define NUM_USER_ASIDS		(1UL << asid_bits)
 #define ctxid2asid(asid)	((asid) & ~ASID_MASK)
 #define asid2ctxid(asid, genid)	((asid) | (genid))
 
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 87b3f1a25535..a86c897017df 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -30,11 +30,13 @@ void copy_highpage(struct page *to, struct page *from)
 	if (!system_supports_mte())
 		return;
 
-	if (folio_test_hugetlb(src) &&
-	    folio_test_hugetlb_mte_tagged(src)) {
-		if (!folio_try_hugetlb_mte_tagging(dst))
+	if (folio_test_hugetlb(src)) {
+		if (!folio_test_hugetlb_mte_tagged(src) ||
+		    from != folio_page(src, 0))
 			return;
 
+		WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst));
+
 		/*
 		 * Populate tags for all subpages.
 		 *
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d21f67d67cf5..ccdef53872a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -117,15 +117,6 @@ static void __init arch_reserve_crashkernel(void)
 
 static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
 {
-	/**
-	 * Information we get from firmware (e.g. DT dma-ranges) describe DMA
-	 * bus constraints. Devices using DMA might have their own limitations.
-	 * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
-	 * DMA zone on platforms that have RAM there.
-	 */
-	if (memblock_start_of_DRAM() < U32_MAX)
-		zone_limit = min(zone_limit, U32_MAX);
-
 	return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -141,6 +132,14 @@ static void __init zone_sizes_init(void)
 	acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
 	dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
 	zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
+	/*
+	 * Information we get from firmware (e.g. DT dma-ranges) describe DMA
+	 * bus constraints. Devices using DMA might have their own limitations.
+	 * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
+	 * DMA zone on platforms that have RAM there.
+	 */
+	if (memblock_start_of_DRAM() < U32_MAX)
+		zone_dma_limit = min(zone_dma_limit, U32_MAX);
 	arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif