From 25b92693a1b67a47b0c64a3410009d09e9658412 Mon Sep 17 00:00:00 2001
From: Mark Rutland
Date: Thu, 13 Feb 2020 12:14:52 +0000
Subject: arm64: mm: convert cpu_do_switch_mm() to C

There's no reason that cpu_do_switch_mm() needs to be written as an
assembly function, and having it as a C function would make it easier to
maintain.

This patch converts cpu_do_switch_mm() to C, removing code that this
change makes redundant (e.g. the mmid macro). Since the header comment
was stale and the prototype now implies all the necessary information,
this comment is removed. The 'pgd_phys' argument is made a phys_addr_t
to match the return type of virt_to_phys().

At the same time, post_ttbr_update_workaround() is updated to use
IS_ENABLED(), which allows the compiler to figure out it can elide calls
for !CONFIG_CAVIUM_ERRATUM_27456 builds.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
[catalin.marinas@arm.com: change comments from asm-style to C-style]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/assembler.h   | 6 ------
 arch/arm64/include/asm/mmu_context.h | 2 ++
 arch/arm64/include/asm/proc-fns.h    | 2 --
 3 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aca337d79d12..af03001293c6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -256,12 +256,6 @@ alternative_endif
 	ldr	\rd, [\rn, #VMA_VM_MM]
 	.endm
 
-/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldr	\rd, [\rn, #MM_CONTEXT_ID]
-	.endm
 /*
  * read_ctr - read CTR_EL0. If the system has mismatched register fields,
  * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3827ff4040a3..ab46187c6300 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -46,6 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
 	isb();
 }
 
+void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+
 static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 {
 	BUG_ON(pgd == swapper_pg_dir);
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index a2ce65a0c1fa..0d5d1f0525eb 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -13,11 +13,9 @@
 
 #include <asm/page.h>
 
-struct mm_struct;
 struct cpu_suspend_ctx;
 
 extern void cpu_do_idle(void);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
-- 
cgit v1.2.3


From 90765f745b08fdf069e4562f6985bdba0fefad8d Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Fri, 28 Feb 2020 12:43:55 +0000
Subject: arm64: Update comment for ASID() macro

Commit 25b92693a1b6 ("arm64: mm: convert cpu_do_switch_mm() to C") added
a new use of the ASID() macro, so update the comment in asm/mmu.h which
reasons about why an atomic reload of 'mm->context.id.counter' is not
required.

Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/mmu.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index e4d862420bb4..21a4bcfdb378 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -23,9 +23,9 @@ typedef struct {
 } mm_context_t;
 
 /*
- * This macro is only used by the TLBI code, which cannot race with an
- * ASID change and therefore doesn't need to reload the counter using
- * atomic64_read.
+ * This macro is only used by the TLBI and low-level switch_mm() code,
+ * neither of which can race with an ASID change. We therefore don't
+ * need to reload the counter using atomic64_read().
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
-- 
cgit v1.2.3


From bbd6ec605c0fc286c3f8ce60b4ed44635361d58b Mon Sep 17 00:00:00 2001
From: Anshuman Khandual
Date: Wed, 4 Mar 2020 09:58:43 +0530
Subject: arm64/mm: Enable memory hot remove

The arch code for hot-remove must tear down portions of the linear map and
vmemmap corresponding to memory being removed. In both cases the page
tables mapping these regions must be freed, and when sparse vmemmap is in
use the memory backing the vmemmap must also be freed.

This patch adds unmap_hotplug_range() and free_empty_tables() helpers which
can be used to tear down either region and calls it from vmemmap_free() and
___remove_pgd_mapping(). The free_mapped argument determines whether the
backing memory will be freed.

It makes two distinct passes over the kernel page table. In the first pass
with unmap_hotplug_range() it unmaps, invalidates applicable TLB cache and
frees backing memory if required (vmemmap) for each mapped leaf entry. In
the second pass with free_empty_tables() it looks for empty page table
sections whose page table page can be unmapped, TLB invalidated and freed.

While freeing intermediate level page table pages bail out if any of its
entries are still valid. This can happen for partially filled kernel page
table either from a previously attempted failed memory hot add or while
removing an address range which does not span the entire page table page
range.

The vmemmap region may share levels of table with the vmalloc region.
There can be conflicts between hot remove freeing page table pages with
a concurrent vmalloc() walking the kernel page table. This conflict can
not just be solved by taking the init_mm ptl because of existing locking
scheme in vmalloc(). So free_empty_tables() implements a floor and ceiling
method which is borrowed from user page table tear with free_pgd_range()
which skips freeing page table pages if intermediate address range is not
aligned or maximum floor-ceiling might not own the entire page table page.

Boot memory on arm64 cannot be removed. Hence this registers a new memory
hotplug notifier which prevents boot memory offlining and it's removal.

While here update arch_add_memory() to handle __add_pages() failures by
just unmapping recently added kernel linear mapping. Now enable memory hot
remove on arm64 platforms by default with ARCH_ENABLE_MEMORY_HOTREMOVE.

This implementation is overall inspired from kernel page table tear down
procedure on X86 architecture and user page table tear down method.

[Mike and Catalin added P4D page table level support]

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig              |   3 +
 arch/arm64/include/asm/memory.h |   1 +
 arch/arm64/mm/mmu.c             | 379 +++++++++++++++++++++++++++++++++++++++-
 3 files changed, 374 insertions(+), 9 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0b30e884e088..8fb0ba221a26 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -281,6 +281,9 @@ config ZONE_DMA32
 config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+	def_bool y
+
 config SMP
 	def_bool y
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 4d94676e5a8b..2be67b232499 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -54,6 +54,7 @@
 #define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(-VMEMMAP_SIZE - SZ_2M)
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 128f70852bf3..9b08f7c7e6f0 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,6 +17,7 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
+#include <linux/memory.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
@@ -724,6 +725,312 @@ int kern_addr_valid(unsigned long addr)
 
 	return pfn_valid(pte_pfn(pte));
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size)
+{
+	WARN_ON(PageReserved(page));
+	free_pages((unsigned long)page_address(page), get_order(size));
+}
+
+static void free_hotplug_pgtable_page(struct page *page)
+{
+	free_hotplug_page_range(page, PAGE_SIZE);
+}
+
+static bool pgtable_range_aligned(unsigned long start, unsigned long end,
+				  unsigned long floor, unsigned long ceiling,
+				  unsigned long mask)
+{
+	start &= mask;
+	if (start < floor)
+		return false;
+
+	if (ceiling) {
+		ceiling &= mask;
+		if (!ceiling)
+			return false;
+	}
+
+	if (end - 1 > ceiling - 1)
+		return false;
+	return true;
+}
+
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+				    unsigned long end, bool free_mapped)
+{
+	pte_t *ptep, pte;
+
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+		if (pte_none(pte))
+			continue;
+
+		WARN_ON(!pte_present(pte));
+		pte_clear(&init_mm, addr, ptep);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+		if (free_mapped)
+			free_hotplug_page_range(pte_page(pte), PAGE_SIZE);
+	} while (addr += PAGE_SIZE, addr < end);
+}
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+				    unsigned long end, bool free_mapped)
+{
+	unsigned long next;
+	pmd_t *pmdp, pmd;
+
+	do {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
+
+		WARN_ON(!pmd_present(pmd));
+		if (pmd_sect(pmd)) {
+			pmd_clear(pmdp);
+
+			/*
+			 * One TLBI should be sufficient here as the PMD_SIZE
+			 * range is mapped with a single block entry.
+			 */
+			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+			if (free_mapped)
+				free_hotplug_page_range(pmd_page(pmd),
+							PMD_SIZE);
+			continue;
+		}
+		WARN_ON(!pmd_table(pmd));
+		unmap_hotplug_pte_range(pmdp, addr, next, free_mapped);
+	} while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
+				    unsigned long end, bool free_mapped)
+{
+	unsigned long next;
+	pud_t *pudp, pud;
+
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(p4dp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
+
+		WARN_ON(!pud_present(pud));
+		if (pud_sect(pud)) {
+			pud_clear(pudp);
+
+			/*
+			 * One TLBI should be sufficient here as the PUD_SIZE
+			 * range is mapped with a single block entry.
+			 */
+			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+			if (free_mapped)
+				free_hotplug_page_range(pud_page(pud),
+							PUD_SIZE);
+			continue;
+		}
+		WARN_ON(!pud_table(pud));
+		unmap_hotplug_pmd_range(pudp, addr, next, free_mapped);
+	} while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
+				    unsigned long end, bool free_mapped)
+{
+	unsigned long next;
+	p4d_t *p4dp, p4d;
+
+	do {
+		next = p4d_addr_end(addr, end);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		if (p4d_none(p4d))
+			continue;
+
+		WARN_ON(!p4d_present(p4d));
+		unmap_hotplug_pud_range(p4dp, addr, next, free_mapped);
+	} while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+				bool free_mapped)
+{
+	unsigned long next;
+	pgd_t *pgdp, pgd;
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
+
+		WARN_ON(!pgd_present(pgd));
+		unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped);
+	} while (addr = next, addr < end);
+}
+
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	pte_t *ptep, pte;
+	unsigned long i, start = addr;
+
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+
+		/*
+		 * This is just a sanity check here which verifies that
+		 * pte clearing has been done by earlier unmap loops.
+		 */
+		WARN_ON(!pte_none(pte));
+	} while (addr += PAGE_SIZE, addr < end);
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK))
+		return;
+
+	/*
+	 * Check whether we can free the pte page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
+	 */
+	ptep = pte_offset_kernel(pmdp, 0UL);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		if (!pte_none(READ_ONCE(ptep[i])))
+			return;
+	}
+
+	pmd_clear(pmdp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(ptep));
+}
+
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	pmd_t *pmdp, pmd;
+	unsigned long i, next, start = addr;
+
+	do {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
+
+		WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+		free_empty_pte_table(pmdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+
+	if (CONFIG_PGTABLE_LEVELS <= 2)
+		return;
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK))
+		return;
+
+	/*
+	 * Check whether we can free the pmd page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
+	 */
+	pmdp = pmd_offset(pudp, 0UL);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(READ_ONCE(pmdp[i])))
+			return;
+	}
+
+	pud_clear(pudp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(pmdp));
+}
+
+static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	pud_t *pudp, pud;
+	unsigned long i, next, start = addr;
+
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(p4dp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
+
+		WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+		free_empty_pmd_table(pudp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+
+	if (CONFIG_PGTABLE_LEVELS <= 3)
+		return;
+
+	if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK))
+		return;
+
+	/*
+	 * Check whether we can free the pud page if the rest of the
+	 * entries are empty. Overlap with other regions have been
+	 * handled by the floor/ceiling check.
+	 */
+	pudp = pud_offset(p4dp, 0UL);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (!pud_none(READ_ONCE(pudp[i])))
+			return;
+	}
+
+	p4d_clear(p4dp);
+	__flush_tlb_kernel_pgtable(start);
+	free_hotplug_pgtable_page(virt_to_page(pudp));
+}
+
+static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	unsigned long next;
+	p4d_t *p4dp, p4d;
+
+	do {
+		next = p4d_addr_end(addr, end);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		if (p4d_none(p4d))
+			continue;
+
+		WARN_ON(!p4d_present(p4d));
+		free_empty_pud_table(p4dp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+}
+
+static void free_empty_tables(unsigned long addr, unsigned long end,
+			      unsigned long floor, unsigned long ceiling)
+{
+	unsigned long next;
+	pgd_t *pgdp, pgd;
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
+
+		WARN_ON(!pgd_present(pgd));
+		free_empty_p4d_table(pgdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+}
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #if !ARM64_SWAPPER_USES_SECTION_MAPS
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -771,6 +1078,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
+#ifdef CONFIG_MEMORY_HOTPLUG
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+	unmap_hotplug_range(start, end, true);
+	free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
+#endif
 }
 #endif	/* CONFIG_SPARSEMEM_VMEMMAP */
 
@@ -1049,10 +1362,21 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
+{
+	unsigned long end = start + size;
+
+	WARN_ON(pgdir != init_mm.pgd);
+	WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
+
+	unmap_hotplug_range(start, end, false);
+	free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
+}
+
 int arch_add_memory(int nid, u64 start, u64 size,
 			struct mhp_restrictions *restrictions)
 {
-	int flags = 0;
+	int ret, flags = 0;
 
 	if (rodata_full || debug_pagealloc_enabled())
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
@@ -1062,22 +1386,59 @@ int arch_add_memory(int nid, u64 start, u64 size,
 
 	memblock_clear_nomap(start, size);
 
-	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+	ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   restrictions);
+	if (ret)
+		__remove_pgd_mapping(swapper_pg_dir,
+				     __phys_to_virt(start), size);
+	return ret;
 }
+
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	/*
-	 * FIXME: Cleanup page tables (also in arch_add_memory() in case
-	 * adding fails). Until then, this function should only be used
-	 * during memory hotplug (adding memory), not for memory
-	 * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
-	 * unlocked yet.
-	 */
 	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
+}
+
+/*
+ * This memory hotplug notifier helps prevent boot memory from being
+ * inadvertently removed as it blocks pfn range offlining process in
+ * __offline_pages(). Hence this prevents both offlining as well as
+ * removal process for boot memory which is initially always online.
+ * In future if and when boot memory could be removed, this notifier
+ * should be dropped and free_hotplug_page_range() should handle any
+ * reserved pages allocated during boot.
+ */
+static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
+					   unsigned long action, void *data)
+{
+	struct mem_section *ms;
+	struct memory_notify *arg = data;
+	unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
+	unsigned long pfn = arg->start_pfn;
+
+	if (action != MEM_GOING_OFFLINE)
+		return NOTIFY_OK;
+
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		ms = __pfn_to_section(pfn);
+		if (early_section(ms))
+			return NOTIFY_BAD;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block prevent_bootmem_remove_nb = {
+	.notifier_call = prevent_bootmem_remove_notifier,
+};
+
+static int __init prevent_bootmem_remove_init(void)
+{
+	return register_memory_notifier(&prevent_bootmem_remove_nb);
 }
+device_initcall(prevent_bootmem_remove_init);
 #endif
-- 
cgit v1.2.3


From 2c9d45b43c39e26fd2a73f2203321cdaee98b58b Mon Sep 17 00:00:00 2001
From: Ionela Voinescu
Date: Thu, 5 Mar 2020 09:06:21 +0000
Subject: arm64: add support for the AMU extension v1

The activity monitors extension is an optional extension introduced
by the ARMv8.4 CPU architecture. This implements basic support for
version 1 of the activity monitors architecture, AMUv1.

This support includes:
- Extension detection on each CPU (boot, secondary, hotplugged)
- Register interface for AMU aarch64 registers

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig                  | 27 +++++++++++++++
 arch/arm64/include/asm/cpucaps.h    |  3 +-
 arch/arm64/include/asm/cpufeature.h |  5 +++
 arch/arm64/include/asm/sysreg.h     | 38 +++++++++++++++++++++
 arch/arm64/kernel/cpufeature.c      | 66 +++++++++++++++++++++++++++++++++++++
 5 files changed, 138 insertions(+), 1 deletion(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0b30e884e088..fa4e3737149c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1517,6 +1517,33 @@ config ARM64_PTR_AUTH
 
 endmenu
 
+menu "ARMv8.4 architectural features"
+
+config ARM64_AMU_EXTN
+	bool "Enable support for the Activity Monitors Unit CPU extension"
+	default y
+	help
+	  The activity monitors extension is an optional extension introduced
+	  by the ARMv8.4 CPU architecture. This enables support for version 1
+	  of the activity monitors architecture, AMUv1.
+
+	  To enable the use of this extension on CPUs that implement it, say Y.
+
+	  Note that for architectural reasons, firmware _must_ implement AMU
+	  support when running on CPUs that present the activity monitors
+	  extension. The required support is present in:
+	    * Version 1.5 and later of the ARM Trusted Firmware
+
+	  For kernels that have this configuration enabled but boot with broken
+	  firmware, you may need to say N here until the firmware is fixed.
+	  Otherwise you may experience firmware panics or lockups when
+	  accessing the counter registers. Even if you are not observing these
+	  symptoms, the values returned by the register reads might not
+	  correctly reflect reality. Most commonly, the value read will be 0,
+	  indicating that the counter is not enabled.
+
+endmenu
+
 menu "ARMv8.5 architectural features"
 
 config ARM64_E0PD
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 865e0253fc1e..185e44aa2713 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -58,7 +58,8 @@
 #define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE	48
 #define ARM64_HAS_E0PD				49
 #define ARM64_HAS_RNG				50
+#define ARM64_HAS_AMU_EXTN			51
 
-#define ARM64_NCAPS				51
+#define ARM64_NCAPS				52
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 92ef9539874a..485e069d8768 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -678,6 +678,11 @@ static inline bool cpu_has_hw_af(void)
 						ID_AA64MMFR1_HADBS_SHIFT);
 }
 
+#ifdef CONFIG_ARM64_AMU_EXTN
+/* Check whether the cpu supports the Activity Monitors Unit (AMU) */
+extern bool cpu_has_amu_feat(int cpu);
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b91570ff9db1..085d248f824e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -386,6 +386,42 @@
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
 
+/* Definitions for system register interface to AMU for ARMv8.4 onwards */
+#define SYS_AM_EL0(crm, op2)		sys_reg(3, 3, 13, (crm), (op2))
+#define SYS_AMCR_EL0			SYS_AM_EL0(2, 0)
+#define SYS_AMCFGR_EL0			SYS_AM_EL0(2, 1)
+#define SYS_AMCGCR_EL0			SYS_AM_EL0(2, 2)
+#define SYS_AMUSERENR_EL0		SYS_AM_EL0(2, 3)
+#define SYS_AMCNTENCLR0_EL0		SYS_AM_EL0(2, 4)
+#define SYS_AMCNTENSET0_EL0		SYS_AM_EL0(2, 5)
+#define SYS_AMCNTENCLR1_EL0		SYS_AM_EL0(3, 0)
+#define SYS_AMCNTENSET1_EL0		SYS_AM_EL0(3, 1)
+
+/*
+ * Group 0 of activity monitors (architected):
+ *                op0  op1  CRn   CRm       op2
+ * Counter:       11   011  1101  010:n<3>  n<2:0>
+ * Type:          11   011  1101  011:n<3>  n<2:0>
+ * n: 0-15
+ *
+ * Group 1 of activity monitors (auxiliary):
+ *                op0  op1  CRn   CRm       op2
+ * Counter:       11   011  1101  110:n<3>  n<2:0>
+ * Type:          11   011  1101  111:n<3>  n<2:0>
+ * n: 0-15
+ */
+
+#define SYS_AMEVCNTR0_EL0(n)		SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPE0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVCNTR1_EL0(n)		SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPE1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+
+/* AMU v1: Fixed (architecturally defined) activity monitors */
+#define SYS_AMEVCNTR0_CORE_EL0		SYS_AMEVCNTR0_EL0(0)
+#define SYS_AMEVCNTR0_CONST_EL0		SYS_AMEVCNTR0_EL0(1)
+#define SYS_AMEVCNTR0_INST_RET_EL0	SYS_AMEVCNTR0_EL0(2)
+#define SYS_AMEVCNTR0_MEM_STALL		SYS_AMEVCNTR0_EL0(3)
+
 #define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
 
 #define SYS_CNTP_TVAL_EL0		sys_reg(3, 3, 14, 2, 0)
@@ -598,6 +634,7 @@
 #define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_DIT_SHIFT		48
+#define ID_AA64PFR0_AMU_SHIFT		44
 #define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_RAS_SHIFT		28
 #define ID_AA64PFR0_GIC_SHIFT		24
@@ -608,6 +645,7 @@
 #define ID_AA64PFR0_EL1_SHIFT		4
 #define ID_AA64PFR0_EL0_SHIFT		0
 
+#define ID_AA64PFR0_AMU			0x1
 #define ID_AA64PFR0_SVE			0x1
 #define ID_AA64PFR0_RAS_V1		0x1
 #define ID_AA64PFR0_FP_NI		0xf
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0b6715625cf6..301538d3a197 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -163,6 +163,7 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
@@ -1222,6 +1223,53 @@ static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap,
 
 #endif
 
+#ifdef CONFIG_ARM64_AMU_EXTN
+
+/*
+ * The "amu_cpus" cpumask only signals that the CPU implementation for the
+ * flagged CPUs supports the Activity Monitors Unit (AMU) but does not provide
+ * information regarding all the events that it supports. When a CPU bit is
+ * set in the cpumask, the user of this feature can only rely on the presence
+ * of the 4 fixed counters for that CPU. But this does not guarantee that the
+ * counters are enabled or access to these counters is enabled by code
+ * executed at higher exception levels (firmware).
+ */
+static struct cpumask amu_cpus __read_mostly;
+
+bool cpu_has_amu_feat(int cpu)
+{
+	return cpumask_test_cpu(cpu, &amu_cpus);
+}
+
+static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
+{
+	if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) {
+		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
+			smp_processor_id());
+		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
+	}
+}
+
+static bool has_amu(const struct arm64_cpu_capabilities *cap,
+		    int __unused)
+{
+	/*
+	 * The AMU extension is a non-conflicting feature: the kernel can
+	 * safely run a mix of CPUs with and without support for the
+	 * activity monitors extension. Therefore, unconditionally enable
+	 * the capability to allow any late CPU to use the feature.
+	 *
+	 * With this feature unconditionally enabled, the cpu_enable
+	 * function will be called for all CPUs that match the criteria,
+	 * including secondary and hotplugged, marking this feature as
+	 * present on that respective CPU. The enable function will also
+	 * print a detection message.
+	 */
+
+	return true;
+}
+#endif
+
 #ifdef CONFIG_ARM64_VHE
 static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused)
 {
@@ -1499,6 +1547,24 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_clear_disr,
 	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
+#ifdef CONFIG_ARM64_AMU_EXTN
+	{
+		/*
+		 * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y.
+		 * Therefore, don't provide .desc as we don't want the detection
+		 * message to be shown until at least one CPU is detected to
+		 * support the feature.
+		 */
+		.capability = ARM64_HAS_AMU_EXTN,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		.matches = has_amu,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_AMU_SHIFT,
+		.min_field_value = ID_AA64PFR0_AMU,
+		.cpu_enable = cpu_amu_enable,
+	},
+#endif /* CONFIG_ARM64_AMU_EXTN */
 	{
 		.desc = "Data cache clean to the PoU not required for I/D coherence",
 		.capability = ARM64_HAS_CACHE_IDC,
-- 
cgit v1.2.3


From 87a1f063464afd934f0f22aac710ca65bef77af3 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu
Date: Thu, 5 Mar 2020 09:06:22 +0000
Subject: arm64: trap to EL1 accesses to AMU counters from EL0

The activity monitors extension is an optional extension introduced
by the ARMv8.4 CPU architecture. In order to access the activity
monitors counters safely, if desired, the kernel should detect the
presence of the extension through the feature register, and mediate
the access.

Therefore, disable direct accesses to activity monitors counters
from EL0 (userspace) and trap them to EL1 (kernel).

To be noted that the ARM64_AMU_EXTN kernel config does not have an
effect on this code. Given that the amuserenr_el0 resets to an
UNKNOWN value, setting the trap of EL0 accesses to EL1 is always
attempted for safety and security considerations. Therefore firmware
should still ensure accesses to AMU registers are not trapped in
EL2/EL3 as this code cannot be bypassed if the CPU implements the
Activity Monitors Unit.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/assembler.h | 10 ++++++++++
 arch/arm64/mm/proc.S               |  3 +++
 2 files changed, 13 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aca337d79d12..c5487806273f 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -430,6 +430,16 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 9000:
 	.endm
 
+/*
+ * reset_amuserenr_el0 - reset AMUSERENR_EL0 if AMUv1 present
+ */
+	.macro	reset_amuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64pfr0_el1	// Check ID_AA64PFR0_EL1
+	ubfx	\tmpreg, \tmpreg, #ID_AA64PFR0_AMU_SHIFT, #4
+	cbz	\tmpreg, .Lskip_\@		// Skip if no AMU present
+	msr_s	SYS_AMUSERENR_EL0, xzr		// Disable AMU access from EL0
+.Lskip_\@:
+	.endm
 /*
  * copy_page - copy src to dest using temp registers t1-t8
  */
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aafed6902411..7103027b4e64 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -131,6 +131,7 @@ alternative_endif
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
+	reset_amuserenr_el0 x0			// Disable AMU access from EL0
 
 alternative_if ARM64_HAS_RAS_EXTN
 	msr_s	SYS_DISR_EL1, xzr
@@ -423,6 +424,8 @@ SYM_FUNC_START(__cpu_setup)
 	isb					// Unmask debug exceptions now,
 	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
+	reset_amuserenr_el0 x0			// Disable AMU access from EL0
+
 	/*
 	 * Memory region attributes
 	 */
-- 
cgit v1.2.3


From 4fcdf106a4330bb5c2306a1efbb3af3b7c0db537 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu
Date: Thu, 5 Mar 2020 09:06:23 +0000
Subject: arm64/kvm: disable access to AMU registers from kvm guests

Access to the AMU counters should be disabled by default in kvm guests,
as information from the counters might reveal activity in other guests
or activity on the host.

Therefore, disable access to AMU registers from EL0 and EL1 in kvm
guests by:
 - Hiding the presence of the extension in the feature register
   (SYS_ID_AA64PFR0_EL1) on the VCPU.
 - Disabling access to the AMU registers before switching to the guest.
 - Trapping accesses and injecting an undefined instruction into the
   guest.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Julien Thierry <julien.thierry.kdev@gmail.com>
Cc: James Morse <james.morse@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/kvm_arm.h |  1 +
 arch/arm64/kvm/hyp/switch.c      | 14 +++++-
 arch/arm64/kvm/sys_regs.c        | 93 +++++++++++++++++++++++++++++++++++++++-
 3 files changed, 105 insertions(+), 3 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6e5d839f42b5..51c1d9918999 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -267,6 +267,7 @@
 
 /* Hyp Coprocessor Trap Register */
 #define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index dfe8dd172512..46292a370781 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -98,6 +98,18 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
 	val &= ~CPACR_EL1_ZEN;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+
+	val |= CPTR_EL2_TAM;
+
 	if (update_fp_enabled(vcpu)) {
 		if (vcpu_has_sve(vcpu))
 			val |= CPACR_EL1_ZEN;
@@ -119,7 +131,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	__activate_traps_common(vcpu);
 
 	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
 	if (!update_fp_enabled(vcpu)) {
 		val |= CPTR_EL2_TFP;
 		__activate_traps_fpsimd32(vcpu);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3e909b117f0c..44354c812783 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1003,6 +1003,20 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
+static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	kvm_inject_undefined(vcpu);
+
+	return false;
+}
+
+/* Macro to expand the AMU counter and type registers*/
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
+#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
+#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu }
+
 static bool trap_ptrauth(struct kvm_vcpu *vcpu,
 			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *rd)
@@ -1078,8 +1092,10 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
-	if (id == SYS_ID_AA64PFR0_EL1 && !vcpu_has_sve(vcpu)) {
-		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+	if (id == SYS_ID_AA64PFR0_EL1) {
+		if (!vcpu_has_sve(vcpu))
+			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
 		val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
@@ -1565,6 +1581,79 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 
+	{ SYS_DESC(SYS_AMCR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCFGR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCGCR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+	AMU_AMEVCNTR0_EL0(0),
+	AMU_AMEVCNTR0_EL0(1),
+	AMU_AMEVCNTR0_EL0(2),
+	AMU_AMEVCNTR0_EL0(3),
+	AMU_AMEVCNTR0_EL0(4),
+	AMU_AMEVCNTR0_EL0(5),
+	AMU_AMEVCNTR0_EL0(6),
+	AMU_AMEVCNTR0_EL0(7),
+	AMU_AMEVCNTR0_EL0(8),
+	AMU_AMEVCNTR0_EL0(9),
+	AMU_AMEVCNTR0_EL0(10),
+	AMU_AMEVCNTR0_EL0(11),
+	AMU_AMEVCNTR0_EL0(12),
+	AMU_AMEVCNTR0_EL0(13),
+	AMU_AMEVCNTR0_EL0(14),
+	AMU_AMEVCNTR0_EL0(15),
+	AMU_AMEVTYPE0_EL0(0),
+	AMU_AMEVTYPE0_EL0(1),
+	AMU_AMEVTYPE0_EL0(2),
+	AMU_AMEVTYPE0_EL0(3),
+	AMU_AMEVTYPE0_EL0(4),
+	AMU_AMEVTYPE0_EL0(5),
+	AMU_AMEVTYPE0_EL0(6),
+	AMU_AMEVTYPE0_EL0(7),
+	AMU_AMEVTYPE0_EL0(8),
+	AMU_AMEVTYPE0_EL0(9),
+	AMU_AMEVTYPE0_EL0(10),
+	AMU_AMEVTYPE0_EL0(11),
+	AMU_AMEVTYPE0_EL0(12),
+	AMU_AMEVTYPE0_EL0(13),
+	AMU_AMEVTYPE0_EL0(14),
+	AMU_AMEVTYPE0_EL0(15),
+	AMU_AMEVCNTR1_EL0(0),
+	AMU_AMEVCNTR1_EL0(1),
+	AMU_AMEVCNTR1_EL0(2),
+	AMU_AMEVCNTR1_EL0(3),
+	AMU_AMEVCNTR1_EL0(4),
+	AMU_AMEVCNTR1_EL0(5),
+	AMU_AMEVCNTR1_EL0(6),
+	AMU_AMEVCNTR1_EL0(7),
+	AMU_AMEVCNTR1_EL0(8),
+	AMU_AMEVCNTR1_EL0(9),
+	AMU_AMEVCNTR1_EL0(10),
+	AMU_AMEVCNTR1_EL0(11),
+	AMU_AMEVCNTR1_EL0(12),
+	AMU_AMEVCNTR1_EL0(13),
+	AMU_AMEVCNTR1_EL0(14),
+	AMU_AMEVCNTR1_EL0(15),
+	AMU_AMEVTYPE1_EL0(0),
+	AMU_AMEVTYPE1_EL0(1),
+	AMU_AMEVTYPE1_EL0(2),
+	AMU_AMEVTYPE1_EL0(3),
+	AMU_AMEVTYPE1_EL0(4),
+	AMU_AMEVTYPE1_EL0(5),
+	AMU_AMEVTYPE1_EL0(6),
+	AMU_AMEVTYPE1_EL0(7),
+	AMU_AMEVTYPE1_EL0(8),
+	AMU_AMEVTYPE1_EL0(9),
+	AMU_AMEVTYPE1_EL0(10),
+	AMU_AMEVTYPE1_EL0(11),
+	AMU_AMEVTYPE1_EL0(12),
+	AMU_AMEVTYPE1_EL0(13),
+	AMU_AMEVTYPE1_EL0(14),
+	AMU_AMEVTYPE1_EL0(15),
+
 	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
-- 
cgit v1.2.3


From cd0ed03a8903a0b0c6fc36e32d133d1ddfe70cd6 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu
Date: Thu, 5 Mar 2020 09:06:26 +0000
Subject: arm64: use activity monitors for frequency invariance

The Frequency Invariance Engine (FIE) is providing a frequency
scaling correction factor that helps achieve more accurate
load-tracking.

So far, for arm and arm64 platforms, this scale factor has been
obtained based on the ratio between the current frequency and the
maximum supported frequency recorded by the cpufreq policy. The
setting of this scale factor is triggered from cpufreq drivers by
calling arch_set_freq_scale. The current frequency used in computation
is the frequency requested by a governor, but it may not be the
frequency that was implemented by the platform.

This correction factor can also be obtained using a core counter and a
constant counter to get information on the performance (frequency based
only) obtained in a period of time. This will more accurately reflect
the actual current frequency of the CPU, compared with the alternative
implementation that reflects the request of a performance level from
the OS.

Therefore, implement arch_scale_freq_tick to use activity monitors, if
present, for the computation of the frequency scale factor.

The use of AMU counters depends on:
 - CONFIG_ARM64_AMU_EXTN - depents on the AMU extension being present
 - CONFIG_CPU_FREQ - the current frequency obtained using counter
   information is divided by the maximum frequency obtained from the
   cpufreq policy.

While it is possible to have a combination of CPUs in the system with
and without support for activity monitors, the use of counters for
frequency invariance is only enabled for a CPU if all related CPUs
(CPUs in the same frequency domain) support and have enabled the core
and constant activity monitor counters. In this way, there is a clear
separation between the policies for which arch_set_freq_scale (cpufreq
based FIE) is used, and the policies for which arch_scale_freq_tick
(counter based FIE) is used to set the frequency scale factor. For
this purpose, a late_initcall_sync is registered to trigger validation
work for policies that will enable or disable the use of AMU counters
for frequency invariance. If CONFIG_CPU_FREQ is not defined, the use
of counters is enabled on all CPUs only if all possible CPUs correctly
support the necessary counters.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/topology.h |   9 ++
 arch/arm64/kernel/cpufeature.c    |   4 +
 arch/arm64/kernel/topology.c      | 180 ++++++++++++++++++++++++++++++++++++++
 drivers/base/arch_topology.c      |  12 +++
 include/linux/arch_topology.h     |   2 +
 5 files changed, 207 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index a4d945db95a2..21d4d40d6243 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -16,6 +16,15 @@ int pcibus_to_node(struct pci_bus *bus);
 
 #include <linux/arch_topology.h>
 
+#ifdef CONFIG_ARM64_AMU_EXTN
+/*
+ * Replace task scheduler's default counter-based
+ * frequency-invariance scale factor setting.
+ */
+void topology_scale_freq_tick(void);
+#define arch_scale_freq_tick topology_scale_freq_tick
+#endif /* CONFIG_ARM64_AMU_EXTN */
+
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 301538d3a197..bf98a2386534 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1241,12 +1241,16 @@ bool cpu_has_amu_feat(int cpu)
 	return cpumask_test_cpu(cpu, &amu_cpus);
 }
 
+/* Initialize the use of AMU counters for frequency invariance */
+extern void init_cpu_freq_invariance_counters(void);
+
 static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
 {
 	if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) {
 		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
 			smp_processor_id());
 		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
+		init_cpu_freq_invariance_counters();
 	}
 }
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index fa9528dfd0ce..0801a0f3c156 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -14,6 +14,7 @@
 #include <linux/acpi.h>
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
+#include <linux/cpufreq.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
 
@@ -120,4 +121,183 @@ int __init parse_acpi_topology(void)
 }
 #endif
 
+#ifdef CONFIG_ARM64_AMU_EXTN
 
+#undef pr_fmt
+#define pr_fmt(fmt) "AMU: " fmt
+
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
+static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
+static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
+static cpumask_var_t amu_fie_cpus;
+
+/* Initialize counter reference per-cpu variables for the current CPU */
+void init_cpu_freq_invariance_counters(void)
+{
+	this_cpu_write(arch_core_cycles_prev,
+		       read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0));
+	this_cpu_write(arch_const_cycles_prev,
+		       read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0));
+}
+
+static int validate_cpu_freq_invariance_counters(int cpu)
+{
+	u64 max_freq_hz, ratio;
+
+	if (!cpu_has_amu_feat(cpu)) {
+		pr_debug("CPU%d: counters are not supported.\n", cpu);
+		return -EINVAL;
+	}
+
+	if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
+		     !per_cpu(arch_core_cycles_prev, cpu))) {
+		pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
+		return -EINVAL;
+	}
+
+	/* Convert maximum frequency from KHz to Hz and validate */
+	max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000;
+	if (unlikely(!max_freq_hz)) {
+		pr_debug("CPU%d: invalid maximum frequency.\n", cpu);
+		return -EINVAL;
+	}
+
+	/*
+	 * Pre-compute the fixed ratio between the frequency of the constant
+	 * counter and the maximum frequency of the CPU.
+	 *
+	 *			      const_freq
+	 * arch_max_freq_scale =   ---------------- * SCHED_CAPACITY_SCALE²
+	 *			   cpuinfo_max_freq
+	 *
+	 * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE²
+	 * in order to ensure a good resolution for arch_max_freq_scale for
+	 * very low arch timer frequencies (down to the KHz range which should
+	 * be unlikely).
+	 */
+	ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT);
+	ratio = div64_u64(ratio, max_freq_hz);
+	if (!ratio) {
+		WARN_ONCE(1, "System timer frequency too low.\n");
+		return -EINVAL;
+	}
+
+	per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
+
+	return 0;
+}
+
+static inline bool
+enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+	if (!policy) {
+		pr_debug("CPU%d: No cpufreq policy found.\n", cpu);
+		return false;
+	}
+
+	if (cpumask_subset(policy->related_cpus, valid_cpus))
+		cpumask_or(amu_fie_cpus, policy->related_cpus,
+			   amu_fie_cpus);
+
+	cpufreq_cpu_put(policy);
+
+	return true;
+}
+
+static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
+#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key)
+
+static int __init init_amu_fie(void)
+{
+	cpumask_var_t valid_cpus;
+	bool have_policy = false;
+	int ret = 0;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto free_valid_mask;
+	}
+
+	for_each_present_cpu(cpu) {
+		if (validate_cpu_freq_invariance_counters(cpu))
+			continue;
+		cpumask_set_cpu(cpu, valid_cpus);
+		have_policy |= enable_policy_freq_counters(cpu, valid_cpus);
+	}
+
+	/*
+	 * If we are not restricted by cpufreq policies, we only enable
+	 * the use of the AMU feature for FIE if all CPUs support AMU.
+	 * Otherwise, enable_policy_freq_counters has already enabled
+	 * policy cpus.
+	 */
+	if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask))
+		cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus);
+
+	if (!cpumask_empty(amu_fie_cpus)) {
+		pr_info("CPUs[%*pbl]: counters will be used for FIE.",
+			cpumask_pr_args(amu_fie_cpus));
+		static_branch_enable(&amu_fie_key);
+	}
+
+free_valid_mask:
+	free_cpumask_var(valid_cpus);
+
+	return ret;
+}
+late_initcall_sync(init_amu_fie);
+
+bool arch_freq_counters_available(struct cpumask *cpus)
+{
+	return amu_freq_invariant() &&
+	       cpumask_subset(cpus, amu_fie_cpus);
+}
+
+void topology_scale_freq_tick(void)
+{
+	u64 prev_core_cnt, prev_const_cnt;
+	u64 core_cnt, const_cnt, scale;
+	int cpu = smp_processor_id();
+
+	if (!amu_freq_invariant())
+		return;
+
+	if (!cpumask_test_cpu(cpu, amu_fie_cpus))
+		return;
+
+	const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0);
+	core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0);
+	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
+	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+
+	if (unlikely(core_cnt <= prev_core_cnt ||
+		     const_cnt <= prev_const_cnt))
+		goto store_and_exit;
+
+	/*
+	 *	    /\core    arch_max_freq_scale
+	 * scale =  ------- * --------------------
+	 *	    /\const   SCHED_CAPACITY_SCALE
+	 *
+	 * See validate_cpu_freq_invariance_counters() for details on
+	 * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
+	 */
+	scale = core_cnt - prev_core_cnt;
+	scale *= this_cpu_read(arch_max_freq_scale);
+	scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
+			  const_cnt - prev_const_cnt);
+
+	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
+	this_cpu_write(freq_scale, (unsigned long)scale);
+
+store_and_exit:
+	this_cpu_write(arch_core_cycles_prev, core_cnt);
+	this_cpu_write(arch_const_cycles_prev, const_cnt);
+}
+#endif /* CONFIG_ARM64_AMU_EXTN */
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 6119e11a9f95..8d63673c1689 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,6 +21,10 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
+__weak bool arch_freq_counters_available(struct cpumask *cpus)
+{
+	return false;
+}
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
 void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
@@ -29,6 +33,14 @@ void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 	unsigned long scale;
 	int i;
 
+	/*
+	 * If the use of counters for FIE is enabled, just return as we don't
+	 * want to update the scale factor with information from CPUFREQ.
+	 * Instead the scale factor will be updated from arch_scale_freq_tick.
+	 */
+	if (arch_freq_counters_available(cpus))
+		return;
+
 	scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
 
 	for_each_cpu(i, cpus)
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 3015ecbb90b1..1ccdddb541a7 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -33,6 +33,8 @@ unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+bool arch_freq_counters_available(struct cpumask *cpus);
+
 struct cpu_topology {
 	int thread_id;
 	int core_id;
-- 
cgit v1.2.3


From 27afb236fe5adaa3911e47c91057ba783549226f Mon Sep 17 00:00:00 2001
From: 王程刚
Date: Mon, 9 Mar 2020 15:21:42 +0800
Subject: arch/arm64: fix typo in a comment

Fix typo in a comment in arch/arm64/include/asm/esr.h

"Unallocted" -> "Unallocated"

Signed-off-by: Chenggang Wang <wangchenggang@vivo.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/esr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index cb29253ae86b..6a395a7e6707 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -60,7 +60,7 @@
 #define ESR_ELx_EC_BKPT32	(0x38)
 /* Unallocated EC: 0x39 */
 #define ESR_ELx_EC_VECTOR32	(0x3A)	/* EL2 only */
-/* Unallocted EC: 0x3B */
+/* Unallocated EC: 0x3B */
 #define ESR_ELx_EC_BRK64	(0x3C)
 /* Unallocated EC: 0x3D - 0x3F */
 #define ESR_ELx_EC_MAX		(0x3F)
-- 
cgit v1.2.3


From 6e52aab9015277c39c6f03a76a7e9487370013f8 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 18 Feb 2020 19:58:38 +0000
Subject: arm64: kvm: Modernize annotation for __bp_harden_hyp_vecs

We have recently introduced new macros for annotating assembly symbols
for things that aren't C functions, SYM_CODE_START() and SYM_CODE_END(),
in an effort to clarify and simplify our annotations of assembly files.

Using these for __bp_harden_hyp_vecs is more involved than for most symbols
as this symbol is annotated quite unusually as rather than just have the
explicit symbol we define _start and _end symbols which we then use to
compute the length. This does not play at all nicely with the new style
macros. Since the size of the vectors is a known constant which won't vary
the simplest thing to do is simply to drop the separate _start and _end
symbols and just use a #define for the size.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_mmu.h | 9 ++++-----
 arch/arm64/include/asm/mmu.h     | 4 +++-
 arch/arm64/kernel/cpu_errata.c   | 2 +-
 arch/arm64/kvm/hyp/hyp-entry.S   | 6 ++++--
 4 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 53d846f1bfe7..b5f723cf9599 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -480,7 +480,7 @@ static inline void *kvm_get_hyp_vector(void)
 	int slot = -1;
 
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
-		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
+		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 		slot = data->hyp_vectors_slot;
 	}
 
@@ -509,14 +509,13 @@ static inline int kvm_map_vectors(void)
 	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
 	 */
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
-		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
+		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
 		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
 	}
 
 	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
-		unsigned long size = (__bp_harden_hyp_vecs_end -
-				      __bp_harden_hyp_vecs_start);
+		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
+		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
 
 		/*
 		 * Always allocate a spare vector slot, as we don't
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index e4d862420bb4..a3324d6ccbfe 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -13,6 +13,7 @@
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
 #define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K)
 
 #ifndef __ASSEMBLY__
 
@@ -45,7 +46,8 @@ struct bp_hardening_data {
 
 #if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
      defined(CONFIG_HARDEN_EL2_VECTORS))
-extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+extern char __bp_harden_hyp_vecs[];
 extern atomic_t arm64_el2_vector_last_slot;
 #endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 703ad0a84f99..0af2201cefda 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -119,7 +119,7 @@ extern char __smccc_workaround_1_smc_end[];
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
 {
-	void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K);
+	void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
 	int i;
 
 	for (i = 0; i < SZ_2K; i += 0x80)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 0aea8f9ab23d..1e2ab928a92f 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -312,11 +312,13 @@ alternative_cb_end
 .endm
 
 	.align	11
-ENTRY(__bp_harden_hyp_vecs_start)
+SYM_CODE_START(__bp_harden_hyp_vecs)
 	.rept BP_HARDEN_EL2_SLOTS
 	generate_vectors
 	.endr
-ENTRY(__bp_harden_hyp_vecs_end)
+1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
+	.org 1b
+SYM_CODE_END(__bp_harden_hyp_vecs)
 
 	.popsection
 
-- 
cgit v1.2.3


From 4db61fef16a104f94bde24fe163064b98cee6b7c Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 18 Feb 2020 19:58:39 +0000
Subject: arm64: kvm: Modernize __smccc_workaround_1_smc_start annotations

In an effort to clarify and simplify the annotation of assembly functions
in the kernel new macros have been introduced. These replace ENTRY and
ENDPROC with separate annotations for standard C callable functions,
data and code with different calling conventions.

Using these for __smccc_workaround_1_smc is more involved than for most
symbols as this symbol is annotated quite unusually, rather than just have
the explicit symbol we define _start and _end symbols which we then use to
compute the length. This does not play at all nicely with the new style
macros. Instead define a constant for the size of the function and use that
in both the C code and for .org based size checks in the assembly code.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_asm.h |  4 ++++
 arch/arm64/kernel/cpu_errata.c   | 14 ++++++--------
 arch/arm64/kvm/hyp/hyp-entry.S   |  6 ++++--
 3 files changed, 14 insertions(+), 10 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 44a243754c1b..7c7eeeaab9fa 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -36,6 +36,8 @@
  */
 #define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
 
+#define __SMCCC_WORKAROUND_1_SMC_SZ 36
+
 #ifndef __ASSEMBLY__
 
 #include <linux/mm.h>
@@ -75,6 +77,8 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
+extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
+
 /* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
 #define __hyp_this_cpu_ptr(sym)						\
 	({								\
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0af2201cefda..6a2ca339741c 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -11,6 +11,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/kvm_asm.h>
 #include <asm/smp_plat.h>
 
 static bool __maybe_unused
@@ -113,9 +114,6 @@ atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
-extern char __smccc_workaround_1_smc_start[];
-extern char __smccc_workaround_1_smc_end[];
-
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
 {
@@ -163,9 +161,6 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 	raw_spin_unlock(&bp_lock);
 }
 #else
-#define __smccc_workaround_1_smc_start		NULL
-#define __smccc_workaround_1_smc_end		NULL
-
 static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
@@ -239,11 +234,14 @@ static int detect_harden_bp_fw(void)
 		smccc_end = NULL;
 		break;
 
+#if IS_ENABLED(CONFIG_KVM_ARM_HOST)
 	case SMCCC_CONDUIT_SMC:
 		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		smccc_start = __smccc_workaround_1_smc;
+		smccc_end = __smccc_workaround_1_smc +
+			__SMCCC_WORKAROUND_1_SMC_SZ;
 		break;
+#endif
 
 	default:
 		return -1;
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 1e2ab928a92f..c2a13ab3c471 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -322,7 +322,7 @@ SYM_CODE_END(__bp_harden_hyp_vecs)
 
 	.popsection
 
-ENTRY(__smccc_workaround_1_smc_start)
+SYM_CODE_START(__smccc_workaround_1_smc)
 	esb
 	sub	sp, sp, #(8 * 4)
 	stp	x2, x3, [sp, #(8 * 0)]
@@ -332,5 +332,7 @@ ENTRY(__smccc_workaround_1_smc_start)
 	ldp	x2, x3, [sp, #(8 * 0)]
 	ldp	x0, x1, [sp, #(8 * 2)]
 	add	sp, sp, #(8 * 4)
-ENTRY(__smccc_workaround_1_smc_end)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_CODE_END(__smccc_workaround_1_smc)
 #endif
-- 
cgit v1.2.3


From e9c7ddbf8b4b6a291bf3b5bfa7c883235164d9be Mon Sep 17 00:00:00 2001
From: Robin Murphy
Date: Mon, 20 Jan 2020 18:52:29 +0000
Subject: arm64: csum: Optimise IPv6 header checksum

Throwing our __uint128_t idioms at csum_ipv6_magic() makes it
about 1.3x-2x faster across a range of microarchitecture/compiler
combinations. Not much in absolute terms, but every little helps.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/checksum.h |  7 ++++++-
 arch/arm64/lib/csum.c             | 27 +++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 8d2a7de39744..b6f7bc6da5fb 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -5,7 +5,12 @@
 #ifndef __ASM_CHECKSUM_H
 #define __ASM_CHECKSUM_H
 
-#include <linux/types.h>
+#include <linux/in6.h>
+
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
 
 static inline __sum16 csum_fold(__wsum csum)
 {
diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
index 1f82c66b32ea..60eccae2abad 100644
--- a/arch/arm64/lib/csum.c
+++ b/arch/arm64/lib/csum.c
@@ -124,3 +124,30 @@ unsigned int do_csum(const unsigned char *buff, int len)
 
 	return sum >> 16;
 }
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	__uint128_t src, dst;
+	u64 sum = (__force u64)csum;
+
+	src = *(const __uint128_t *)saddr->s6_addr;
+	dst = *(const __uint128_t *)daddr->s6_addr;
+
+	sum += (__force u32)htonl(len);
+#ifdef __LITTLE_ENDIAN
+	sum += (u32)proto << 24;
+#else
+	sum += proto;
+#endif
+	src += (src >> 64) | (src << 64);
+	dst += (dst >> 64) | (dst << 64);
+
+	sum = accumulate(sum, src >> 64);
+	sum = accumulate(sum, dst >> 64);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
-- 
cgit v1.2.3


From 1db5cdeccd813330aaab19b3fccab15e1d07fe12 Mon Sep 17 00:00:00 2001
From: Mark Rutland
Date: Fri, 21 Feb 2020 14:50:21 +0000
Subject: arm64: cpufeature: add cpus_have_final_cap()

When cpus_have_const_cap() was originally introduced it was intended to
be safe in hyp context, where it is not safe to access the cpu_hwcaps
array as cpus_have_cap() did. For more details see commit:

  a4023f682739439b ("arm64: Add hypervisor safe helper for checking constant capabilities")

We then made use of cpus_have_const_cap() throughout the kernel.

Subsequently, we had to defer updating the static_key associated with
each capability in order to avoid lockdep complaints. To avoid breaking
kernel-wide usage of cpus_have_const_cap(), this was updated to fall
back to the cpu_hwcaps array if called before the static_keys were
updated. As the kvm hyp code was only called later than this, the
fallback is redundant but not functionally harmful. For more details,
see commit:

  63a1e1c95e60e798 ("arm64/cpufeature: don't use mutex in bringup path")

Today we have more users of cpus_have_const_cap() which are only called
once the relevant static keys are initialized, and it would be
beneficial to avoid the redundant code.

To that end, this patch adds a new cpus_have_final_cap(), helper which
is intend to be used in code which is only run once capabilities have
been finalized, and will never check the cpus_hwcap array. This helps
the compiler to generate better code as it no longer needs to generate
code to address and test the cpus_hwcap array. To help catch misuse,
cpus_have_final_cap() will BUG() if called before capabilities are
finalized.

In hyp context, BUG() will result in a hyp panic, but the specific BUG()
instance will not be identified in the usual way.

Comments are added to the various cpus_have_*_cap() helpers to describe
the constraints on when they can be used. For clarity cpus_have_cap() is
moved above the other helpers. Similarly the helpers are updated to use
system_capabilities_finalized() consistently, and this is made
__always_inline as required by its new callers.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpufeature.h | 58 ++++++++++++++++++++++++++++++-------
 1 file changed, 47 insertions(+), 11 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 92ef9539874a..940b2b67b428 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -390,14 +390,16 @@ unsigned long cpu_get_elf_hwcap2(void);
 #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
 #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
-/* System capability check for constant caps */
-static __always_inline bool __cpus_have_const_cap(int num)
+static __always_inline bool system_capabilities_finalized(void)
 {
-	if (num >= ARM64_NCAPS)
-		return false;
-	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+	return static_branch_likely(&arm64_const_caps_ready);
 }
 
+/*
+ * Test for a capability with a runtime check.
+ *
+ * Before the capability is detected, this returns false.
+ */
 static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
@@ -405,14 +407,53 @@ static inline bool cpus_have_cap(unsigned int num)
 	return test_bit(num, cpu_hwcaps);
 }
 
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this returns false.
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool __cpus_have_const_cap(int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
+/*
+ * Test for a capability, possibly with a runtime check.
+ *
+ * Before capabilities are finalized, this behaves as cpus_have_cap().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
 static __always_inline bool cpus_have_const_cap(int num)
 {
-	if (static_branch_likely(&arm64_const_caps_ready))
+	if (system_capabilities_finalized())
 		return __cpus_have_const_cap(num);
 	else
 		return cpus_have_cap(num);
 }
 
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this will BUG().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool cpus_have_final_cap(int num)
+{
+	if (system_capabilities_finalized())
+		return __cpus_have_const_cap(num);
+	else
+		BUG();
+}
+
 static inline void cpus_set_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS) {
@@ -613,11 +654,6 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
-static inline bool system_capabilities_finalized(void)
-{
-	return static_branch_likely(&arm64_const_caps_ready);
-}
-
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
-- 
cgit v1.2.3


From c17a290f7e7e59d24b4507736b7b40b0eb5f8f1f Mon Sep 17 00:00:00 2001
From: glider@google.com
Date: Thu, 12 Mar 2020 16:59:20 +0100
Subject: arm64: define __alloc_zeroed_user_highpage

When running the kernel with init_on_alloc=1, calling the default
implementation of __alloc_zeroed_user_highpage() from include/linux/highmem.h
leads to double-initialization of the allocated page (first by the page
allocator, then by clear_user_page().
Calling alloc_page_vma() with __GFP_ZERO, similarly to e.g. x86, seems
to be enough to ensure the user page is zeroed only once.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/page.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index d39ddb258a04..75d6cd23a679 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,
 extern void copy_page(void *to, const void *from);
 extern void clear_page(void *to);
 
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
 #define clear_user_page(addr,vaddr,pg)  __cpu_clear_user_page(addr, vaddr)
 #define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
 
-- 
cgit v1.2.3


From 8e35aa642ee4dab01b16cc4b2df59d1936f3b3c2 Mon Sep 17 00:00:00 2001
From: Andrew Murray
Date: Mon, 2 Mar 2020 18:17:50 +0000
Subject: arm64: cpufeature: Extract capped perfmon fields

When emulating ID registers there is often a need to cap the version
bits of a feature such that the guest will not use features that the
host is not aware of. For example, when KVM mediates access to the PMU
by emulating register accesses.

Let's add a helper that extracts a performance monitors ID field and
caps the version to a given value.

Fields that identify the version of the Performance Monitors Extension
do not follow the standard ID scheme, and instead follow the scheme
described in ARM DDI 0487E.a page D13-2825 "Alternative ID scheme used
for the Performance Monitors Extension version". The value 0xF means an
IMPLEMENTATION DEFINED PMU is present, and values 0x0-OxE can be treated
the same as an unsigned field with 0x0 meaning no PMU is present.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
[Mark: rework to handle perfmon fields]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cpufeature.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 92ef9539874a..186f4e19207e 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -447,6 +447,29 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
 	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
 }
 
+/*
+ * Fields that identify the version of the Performance Monitors Extension do
+ * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825,
+ * "Alternative ID scheme used for the Performance Monitors Extension version".
+ */
+static inline u64 __attribute_const__
+cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap)
+{
+	u64 val = cpuid_feature_extract_unsigned_field(features, field);
+	u64 mask = GENMASK_ULL(field + 3, field);
+
+	/* Treat IMPLEMENTATION DEFINED functionality as unimplemented */
+	if (val == 0xf)
+		val = 0;
+
+	if (val > cap) {
+		features &= ~mask;
+		features |= (cap << field) & mask;
+	}
+
+	return features;
+}
+
 static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
-- 
cgit v1.2.3


From c854188ea01062f5a5fd7f05658feb1863774eaa Mon Sep 17 00:00:00 2001
From: Andrew Murray
Date: Mon, 2 Mar 2020 18:17:51 +0000
Subject: KVM: arm64: limit PMU version to PMUv3 for ARMv8.1

We currently expose the PMU version of the host to the guest via
emulation of the DFR0_EL1 and AA64DFR0_EL1 debug feature registers.
However many of the features offered beyond PMUv3 for 8.1 are not
supported in KVM. Examples of this include support for the PMMIR
registers (added in PMUv3 for ARMv8.4) and 64-bit event counters
added in (PMUv3 for ARMv8.5).

Let's trap the Debug Feature Registers in order to limit
PMUVer/PerfMon in the Debug Feature Registers to PMUv3 for ARMv8.1
to avoid unexpected behaviour.

Both ID_AA64DFR0.PMUVer and ID_DFR0.PerfMon follow the "Alternative ID
scheme used for the Performance Monitors Extension version" where 0xF
means an IMPLEMENTATION DEFINED PMU is implemented, and values 0x0-0xE
are treated as with an unsigned field (with 0x0 meaning no PMU is
present). As we don't expect to expose an IMPLEMENTATION DEFINED PMU,
and our cap is below 0xF, we can treat these fields as unsigned when
applying the cap.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
[Mark: make field names consistent, use perfmon cap]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/sysreg.h |  6 ++++++
 arch/arm64/kvm/sys_regs.c       | 10 ++++++++++
 2 files changed, 16 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b91570ff9db1..d8f1eed070f0 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -702,6 +702,12 @@
 #define ID_AA64DFR0_TRACEVER_SHIFT	4
 #define ID_AA64DFR0_DEBUGVER_SHIFT	0
 
+#define ID_AA64DFR0_PMUVER_8_1		0x4
+
+#define ID_DFR0_PERFMON_SHIFT		24
+
+#define ID_DFR0_PERFMON_8_1		0x4
+
 #define ID_ISAR5_RDM_SHIFT		24
 #define ID_ISAR5_CRC32_SHIFT		16
 #define ID_ISAR5_SHA2_SHIFT		12
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3e909b117f0c..b0a3e8976b90 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1085,6 +1085,16 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_GPI_SHIFT));
+	} else if (id == SYS_ID_AA64DFR0_EL1) {
+		/* Limit guests to PMUv3 for ARMv8.1 */
+		val = cpuid_feature_cap_perfmon_field(val,
+						ID_AA64DFR0_PMUVER_SHIFT,
+						ID_AA64DFR0_PMUVER_8_1);
+	} else if (id == SYS_ID_DFR0_EL1) {
+		/* Limit guests to PMUv3 for ARMv8.1 */
+		val = cpuid_feature_cap_perfmon_field(val,
+						ID_DFR0_PERFMON_SHIFT,
+						ID_DFR0_PERFMON_8_1);
 	}
 
 	return val;
-- 
cgit v1.2.3


From 8673e02e58410e6c4cefa499efa846286e45a991 Mon Sep 17 00:00:00 2001
From: Andrew Murray
Date: Mon, 2 Mar 2020 18:17:52 +0000
Subject: arm64: perf: Add support for ARMv8.5-PMU 64-bit counters

At present ARMv8 event counters are limited to 32-bits, though by
using the CHAIN event it's possible to combine adjacent counters to
achieve 64-bits. The perf config1:0 bit can be set to use such a
configuration.

With the introduction of ARMv8.5-PMU support, all event counters can
now be used as 64-bit counters.

Let's enable 64-bit event counters where support exists. Unless the
user sets config1:0 we will adjust the counter value such that it
overflows upon 32-bit overflow. This follows the same behaviour as
the cycle counter which has always been (and remains) 64-bits.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
[Mark: fix ID field names, compare with 8.5 value]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/perf_event.h |  3 +-
 arch/arm64/include/asm/sysreg.h     |  4 ++
 arch/arm64/kernel/perf_event.c      | 87 ++++++++++++++++++++++++++++++-------
 include/linux/perf/arm_pmu.h        |  1 +
 4 files changed, 78 insertions(+), 17 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2bdbc79bbd01..e7765b62c712 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -176,9 +176,10 @@
 #define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
+#define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
 #define	ARMV8_PMU_PMCR_N_SHIFT	11	 /* Number of counters supported */
 #define	ARMV8_PMU_PMCR_N_MASK	0x1f
-#define	ARMV8_PMU_PMCR_MASK	0x7f	 /* Mask for writable bits */
+#define	ARMV8_PMU_PMCR_MASK	0xff	 /* Mask for writable bits */
 
 /*
  * PMOVSR: counters overflow flag status reg
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d8f1eed070f0..9b66c5b5b36f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -702,7 +702,11 @@
 #define ID_AA64DFR0_TRACEVER_SHIFT	4
 #define ID_AA64DFR0_DEBUGVER_SHIFT	0
 
+#define ID_AA64DFR0_PMUVER_8_0		0x1
 #define ID_AA64DFR0_PMUVER_8_1		0x4
+#define ID_AA64DFR0_PMUVER_8_4		0x5
+#define ID_AA64DFR0_PMUVER_8_5		0x6
+#define ID_AA64DFR0_PMUVER_IMP_DEF	0xf
 
 #define ID_DFR0_PERFMON_SHIFT		24
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8062d79f4cbb..4d7879484cec 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -285,6 +285,17 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 #define	ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
 	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
 
+
+/*
+ * We unconditionally enable ARMv8.5-PMU long event counter support
+ * (64-bit events) where supported. Indicate if this arm_pmu has long
+ * event counter support.
+ */
+static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
+{
+	return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5);
+}
+
 /*
  * We must chain two programmable counters for 64 bit events,
  * except when we have allocated the 64bit cycle counter (for CPU
@@ -294,9 +305,11 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 static inline bool armv8pmu_event_is_chained(struct perf_event *event)
 {
 	int idx = event->hw.idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 
 	return !WARN_ON(idx < 0) &&
 	       armv8pmu_event_is_64bit(event) &&
+	       !armv8pmu_has_long_event(cpu_pmu) &&
 	       (idx != ARMV8_IDX_CYCLE_COUNTER);
 }
 
@@ -345,7 +358,7 @@ static inline void armv8pmu_select_counter(int idx)
 	isb();
 }
 
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
 {
 	armv8pmu_select_counter(idx);
 	return read_sysreg(pmxevcntr_el0);
@@ -362,6 +375,44 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
 	return val;
 }
 
+/*
+ * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP
+ * is set the event counters also become 64-bit counters. Unless the
+ * user has requested a long counter (attr.config1) then we want to
+ * interrupt upon 32-bit overflow - we achieve this by applying a bias.
+ */
+static bool armv8pmu_event_needs_bias(struct perf_event *event)
+{
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (armv8pmu_event_is_64bit(event))
+		return false;
+
+	if (armv8pmu_has_long_event(cpu_pmu) ||
+	    idx == ARMV8_IDX_CYCLE_COUNTER)
+		return true;
+
+	return false;
+}
+
+static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value |= GENMASK(63, 32);
+
+	return value;
+}
+
+static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value &= ~GENMASK(63, 32);
+
+	return value;
+}
+
 static u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -377,10 +428,10 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
 	else
 		value = armv8pmu_read_hw_counter(event);
 
-	return value;
+	return  armv8pmu_unbias_long_counter(event, value);
 }
 
-static inline void armv8pmu_write_evcntr(int idx, u32 value)
+static inline void armv8pmu_write_evcntr(int idx, u64 value)
 {
 	armv8pmu_select_counter(idx);
 	write_sysreg(value, pmxevcntr_el0);
@@ -405,20 +456,14 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	value = armv8pmu_bias_long_counter(event, value);
+
 	if (!armv8pmu_counter_valid(cpu_pmu, idx))
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
-	else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
-		/*
-		 * The cycles counter is really a 64-bit counter.
-		 * When treating it as a 32-bit counter, we only count
-		 * the lower 32 bits, and set the upper 32-bits so that
-		 * we get an interrupt upon 32-bit overflow.
-		 */
-		if (!armv8pmu_event_is_64bit(event))
-			value |= 0xffffffff00000000ULL;
+	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		write_sysreg(value, pmccntr_el0);
-	} else
+	else
 		armv8pmu_write_hw_counter(event, value);
 }
 
@@ -731,7 +776,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	/*
 	 * Otherwise use events counters
 	 */
-	if (armv8pmu_event_is_64bit(event))
+	if (armv8pmu_event_is_64bit(event) &&
+	    !armv8pmu_has_long_event(cpu_pmu))
 		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
 	else
 		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
@@ -802,6 +848,9 @@ static int armv8pmu_filter_match(struct perf_event *event)
 
 static void armv8pmu_reset(void *info)
 {
+	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
+	u32 pmcr;
+
 	/* The counter and interrupt enable registers are unknown at reset. */
 	armv8pmu_disable_counter(U32_MAX);
 	armv8pmu_disable_intens(U32_MAX);
@@ -813,8 +862,13 @@ static void armv8pmu_reset(void *info)
 	 * Initialize & Reset PMNC. Request overflow interrupt for
 	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
 	 */
-	armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C |
-			    ARMV8_PMU_PMCR_LC);
+	pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC;
+
+	/* Enable long event counter support where available */
+	if (armv8pmu_has_long_event(cpu_pmu))
+		pmcr |= ARMV8_PMU_PMCR_LP;
+
+	armv8pmu_pmcr_write(pmcr);
 }
 
 static int __armv8_pmuv3_map_event(struct perf_event *event,
@@ -897,6 +951,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	if (pmuver == 0xf || pmuver == 0)
 		return;
 
+	cpu_pmu->pmuver = pmuver;
 	probe->present = true;
 
 	/* Read the nb of CNTx counters supported from PMNC */
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 71f525a35ac2..5b616dde9a4c 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -80,6 +80,7 @@ struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	supported_cpus;
 	char		*name;
+	int		pmuver;
 	irqreturn_t	(*handle_irq)(struct arm_pmu *pmu);
 	void		(*enable)(struct perf_event *event);
 	void		(*disable)(struct perf_event *event);
-- 
cgit v1.2.3


From cfef06bd0686a578aa53e039c9aec0b1a5581d3b Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:49 +0530
Subject: arm64: cpufeature: add pointer auth meta-capabilities

To enable pointer auth for the kernel, we're going to need to check for
the presence of address auth and generic auth using alternative_if. We
currently have two cpucaps for each, but alternative_if needs to check a
single cpucap. So define meta-capabilities that are present when either
of the current two capabilities is present.

Leave the existing four cpucaps in place, as they are still needed to
check for mismatched systems where one CPU has the architected algorithm
but another has the IMP DEF algorithm.

Note, the meta-capabilities were present before but were removed in
commit a56005d32105 ("arm64: cpufeature: Reduce number of pointer auth
CPU caps from 6 to 4") and commit 1e013d06120c ("arm64: cpufeature: Rework
ptr auth hwcaps using multi_entry_cap_matches"), as they were not needed
then. Note, unlike before, the current patch checks the cpucap values
directly, instead of reading the CPU ID register value.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[Amit: commit message and macro rebase, use __system_matches_cap]
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpucaps.h    |  4 +++-
 arch/arm64/include/asm/cpufeature.h |  6 ++----
 arch/arm64/kernel/cpufeature.c      | 25 ++++++++++++++++++++++++-
 3 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 865e0253fc1e..72e4e0580ddb 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -58,7 +58,9 @@
 #define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE	48
 #define ARM64_HAS_E0PD				49
 #define ARM64_HAS_RNG				50
+#define ARM64_HAS_ADDRESS_AUTH			51
+#define ARM64_HAS_GENERIC_AUTH			52
 
-#define ARM64_NCAPS				51
+#define ARM64_NCAPS				53
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 92ef9539874a..8c8048372c8e 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -590,15 +590,13 @@ static inline bool system_supports_cnp(void)
 static inline bool system_supports_address_auth(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		(cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
-		 cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF));
+		cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH);
 }
 
 static inline bool system_supports_generic_auth(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		(cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_ARCH) ||
-		 cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
+		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
 static inline bool system_uses_irq_prio_masking(void)
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4f2e95e6ecd1..01f50f043831 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1323,6 +1323,20 @@ static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap)
 	sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
 				       SCTLR_ELx_ENDA | SCTLR_ELx_ENDB);
 }
+
+static bool has_address_auth(const struct arm64_cpu_capabilities *entry,
+			     int __unused)
+{
+	return __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
+	       __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF);
+}
+
+static bool has_generic_auth(const struct arm64_cpu_capabilities *entry,
+			     int __unused)
+{
+	return __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH) ||
+	       __system_matches_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF);
+}
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #ifdef CONFIG_ARM64_E0PD
@@ -1600,7 +1614,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64ISAR1_APA_SHIFT,
 		.min_field_value = ID_AA64ISAR1_APA_ARCHITECTED,
 		.matches = has_cpuid_feature,
-		.cpu_enable = cpu_enable_address_auth,
 	},
 	{
 		.desc = "Address authentication (IMP DEF algorithm)",
@@ -1611,6 +1624,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64ISAR1_API_SHIFT,
 		.min_field_value = ID_AA64ISAR1_API_IMP_DEF,
 		.matches = has_cpuid_feature,
+	},
+	{
+		.capability = ARM64_HAS_ADDRESS_AUTH,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_address_auth,
 		.cpu_enable = cpu_enable_address_auth,
 	},
 	{
@@ -1633,6 +1651,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = ID_AA64ISAR1_GPI_IMP_DEF,
 		.matches = has_cpuid_feature,
 	},
+	{
+		.capability = ARM64_HAS_GENERIC_AUTH,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_generic_auth,
+	},
 #endif /* CONFIG_ARM64_PTR_AUTH */
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 	{
-- 
cgit v1.2.3


From 91a1b6ccff323e60615e3118eceb2d8cbc4f69ab Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:50 +0530
Subject: arm64: rename ptrauth key structures to be user-specific

We currently enable ptrauth for userspace, but do not use it within the
kernel. We're going to enable it for the kernel, and will need to manage
a separate set of ptrauth keys for the kernel.

We currently keep all 5 keys in struct ptrauth_keys. However, as the
kernel will only need to use 1 key, it is a bit wasteful to allocate a
whole ptrauth_keys struct for every thread.

Therefore, a subsequent patch will define a separate struct, with only 1
key, for the kernel. In preparation for that, rename the existing struct
(and associated macros and functions) to reflect that they are specific
to userspace.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[Amit: Re-positioned the patch to reduce the diff]
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/pointer_auth.h | 12 ++++++------
 arch/arm64/include/asm/processor.h    |  2 +-
 arch/arm64/kernel/pointer_auth.c      |  8 ++++----
 arch/arm64/kernel/ptrace.c            | 16 ++++++++--------
 4 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 7a24bad1a58b..799b079e69a5 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -22,7 +22,7 @@ struct ptrauth_key {
  * We give each process its own keys, which are shared by all threads. The keys
  * are inherited upon fork(), and reinitialised upon exec*().
  */
-struct ptrauth_keys {
+struct ptrauth_keys_user {
 	struct ptrauth_key apia;
 	struct ptrauth_key apib;
 	struct ptrauth_key apda;
@@ -30,7 +30,7 @@ struct ptrauth_keys {
 	struct ptrauth_key apga;
 };
 
-static inline void ptrauth_keys_init(struct ptrauth_keys *keys)
+static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
 {
 	if (system_supports_address_auth()) {
 		get_random_bytes(&keys->apia, sizeof(keys->apia));
@@ -50,7 +50,7 @@ do {								\
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
-static inline void ptrauth_keys_switch(struct ptrauth_keys *keys)
+static inline void ptrauth_keys_switch_user(struct ptrauth_keys_user *keys)
 {
 	if (system_supports_address_auth()) {
 		__ptrauth_key_install(APIA, keys->apia);
@@ -80,12 +80,12 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 #define ptrauth_thread_init_user(tsk)					\
 do {									\
 	struct task_struct *__ptiu_tsk = (tsk);				\
-	ptrauth_keys_init(&__ptiu_tsk->thread.keys_user);		\
-	ptrauth_keys_switch(&__ptiu_tsk->thread.keys_user);		\
+	ptrauth_keys_init_user(&__ptiu_tsk->thread.keys_user);		\
+	ptrauth_keys_switch_user(&__ptiu_tsk->thread.keys_user);		\
 } while (0)
 
 #define ptrauth_thread_switch(tsk)	\
-	ptrauth_keys_switch(&(tsk)->thread.keys_user)
+	ptrauth_keys_switch_user(&(tsk)->thread.keys_user)
 
 #else /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5ba63204d078..496a92873290 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -146,7 +146,7 @@ struct thread_struct {
 	unsigned long		fault_code;	/* ESR_EL1 value */
 	struct debug_info	debug;		/* debugging */
 #ifdef CONFIG_ARM64_PTR_AUTH
-	struct ptrauth_keys	keys_user;
+	struct ptrauth_keys_user	keys_user;
 #endif
 };
 
diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c
index c507b584259d..af5a638207f8 100644
--- a/arch/arm64/kernel/pointer_auth.c
+++ b/arch/arm64/kernel/pointer_auth.c
@@ -9,7 +9,7 @@
 
 int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
 {
-	struct ptrauth_keys *keys = &tsk->thread.keys_user;
+	struct ptrauth_keys_user *keys = &tsk->thread.keys_user;
 	unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY |
 				      PR_PAC_APDAKEY | PR_PAC_APDBKEY;
 	unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY;
@@ -18,8 +18,8 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
 		return -EINVAL;
 
 	if (!arg) {
-		ptrauth_keys_init(keys);
-		ptrauth_keys_switch(keys);
+		ptrauth_keys_init_user(keys);
+		ptrauth_keys_switch_user(keys);
 		return 0;
 	}
 
@@ -41,7 +41,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
 	if (arg & PR_PAC_APGAKEY)
 		get_random_bytes(&keys->apga, sizeof(keys->apga));
 
-	ptrauth_keys_switch(keys);
+	ptrauth_keys_switch_user(keys);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index cd6e5fa48b9c..b3d3005d9515 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -999,7 +999,7 @@ static struct ptrauth_key pac_key_from_user(__uint128_t ukey)
 }
 
 static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
-				     const struct ptrauth_keys *keys)
+				     const struct ptrauth_keys_user *keys)
 {
 	ukeys->apiakey = pac_key_to_user(&keys->apia);
 	ukeys->apibkey = pac_key_to_user(&keys->apib);
@@ -1007,7 +1007,7 @@ static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
 	ukeys->apdbkey = pac_key_to_user(&keys->apdb);
 }
 
-static void pac_address_keys_from_user(struct ptrauth_keys *keys,
+static void pac_address_keys_from_user(struct ptrauth_keys_user *keys,
 				       const struct user_pac_address_keys *ukeys)
 {
 	keys->apia = pac_key_from_user(ukeys->apiakey);
@@ -1021,7 +1021,7 @@ static int pac_address_keys_get(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				void *kbuf, void __user *ubuf)
 {
-	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct ptrauth_keys_user *keys = &target->thread.keys_user;
 	struct user_pac_address_keys user_keys;
 
 	if (!system_supports_address_auth())
@@ -1038,7 +1038,7 @@ static int pac_address_keys_set(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				const void *kbuf, const void __user *ubuf)
 {
-	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct ptrauth_keys_user *keys = &target->thread.keys_user;
 	struct user_pac_address_keys user_keys;
 	int ret;
 
@@ -1056,12 +1056,12 @@ static int pac_address_keys_set(struct task_struct *target,
 }
 
 static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys,
-				     const struct ptrauth_keys *keys)
+				     const struct ptrauth_keys_user *keys)
 {
 	ukeys->apgakey = pac_key_to_user(&keys->apga);
 }
 
-static void pac_generic_keys_from_user(struct ptrauth_keys *keys,
+static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys,
 				       const struct user_pac_generic_keys *ukeys)
 {
 	keys->apga = pac_key_from_user(ukeys->apgakey);
@@ -1072,7 +1072,7 @@ static int pac_generic_keys_get(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				void *kbuf, void __user *ubuf)
 {
-	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct ptrauth_keys_user *keys = &target->thread.keys_user;
 	struct user_pac_generic_keys user_keys;
 
 	if (!system_supports_generic_auth())
@@ -1089,7 +1089,7 @@ static int pac_generic_keys_set(struct task_struct *target,
 				unsigned int pos, unsigned int count,
 				const void *kbuf, const void __user *ubuf)
 {
-	struct ptrauth_keys *keys = &target->thread.keys_user;
+	struct ptrauth_keys_user *keys = &target->thread.keys_user;
 	struct user_pac_generic_keys user_keys;
 	int ret;
 
-- 
cgit v1.2.3


From be129842566599f2c6f8fbba277c098802cd4b3d Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:51 +0530
Subject: arm64: install user ptrauth keys at kernel exit time

As we're going to enable pointer auth within the kernel and use a
different APIAKey for the kernel itself, so move the user APIAKey
switch to EL0 exception return.

The other 4 keys could remain switched during task switch, but are also
moved to keep things consistent.

Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[Amit: commit msg, re-positioned the patch, comments]
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/asm_pointer_auth.h | 49 +++++++++++++++++++++++++++++++
 arch/arm64/include/asm/pointer_auth.h     | 23 +--------------
 arch/arm64/kernel/asm-offsets.c           | 11 +++++++
 arch/arm64/kernel/entry.S                 |  3 ++
 arch/arm64/kernel/pointer_auth.c          |  3 --
 arch/arm64/kernel/process.c               |  1 -
 6 files changed, 64 insertions(+), 26 deletions(-)
 create mode 100644 arch/arm64/include/asm/asm_pointer_auth.h

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
new file mode 100644
index 000000000000..3482348ec07f
--- /dev/null
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_POINTER_AUTH_H
+#define __ASM_ASM_POINTER_AUTH_H
+
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+/*
+ * thread.keys_user.ap* as offset exceeds the #imm offset range
+ * so use the base value of ldp as thread.keys_user and offset as
+ * thread.keys_user.ap*.
+ */
+	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	mov	\tmp1, #THREAD_KEYS_USER
+	add	\tmp1, \tsk, \tmp1
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.Laddr_auth_skip_\@
+alternative_else_nop_endif
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIB]
+	msr_s	SYS_APIBKEYLO_EL1, \tmp2
+	msr_s	SYS_APIBKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDA]
+	msr_s	SYS_APDAKEYLO_EL1, \tmp2
+	msr_s	SYS_APDAKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDB]
+	msr_s	SYS_APDBKEYLO_EL1, \tmp2
+	msr_s	SYS_APDBKEYHI_EL1, \tmp3
+.Laddr_auth_skip_\@:
+alternative_if ARM64_HAS_GENERIC_AUTH
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APGA]
+	msr_s	SYS_APGAKEYLO_EL1, \tmp2
+	msr_s	SYS_APGAKEYHI_EL1, \tmp3
+alternative_else_nop_endif
+	.endm
+
+#else /* CONFIG_ARM64_PTR_AUTH */
+
+	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	.endm
+
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 799b079e69a5..dabe026ca8ca 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -50,19 +50,6 @@ do {								\
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
-static inline void ptrauth_keys_switch_user(struct ptrauth_keys_user *keys)
-{
-	if (system_supports_address_auth()) {
-		__ptrauth_key_install(APIA, keys->apia);
-		__ptrauth_key_install(APIB, keys->apib);
-		__ptrauth_key_install(APDA, keys->apda);
-		__ptrauth_key_install(APDB, keys->apdb);
-	}
-
-	if (system_supports_generic_auth())
-		__ptrauth_key_install(APGA, keys->apga);
-}
-
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
 /*
@@ -78,20 +65,12 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 }
 
 #define ptrauth_thread_init_user(tsk)					\
-do {									\
-	struct task_struct *__ptiu_tsk = (tsk);				\
-	ptrauth_keys_init_user(&__ptiu_tsk->thread.keys_user);		\
-	ptrauth_keys_switch_user(&__ptiu_tsk->thread.keys_user);		\
-} while (0)
-
-#define ptrauth_thread_switch(tsk)	\
-	ptrauth_keys_switch_user(&(tsk)->thread.keys_user)
+	ptrauth_keys_init_user(&(tsk)->thread.keys_user)
 
 #else /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_thread_init_user(tsk)
-#define ptrauth_thread_switch(tsk)
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index a5bdce8af65b..7b1ea2aece58 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -40,6 +40,9 @@ int main(void)
 #endif
   BLANK();
   DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
+#ifdef CONFIG_ARM64_PTR_AUTH
+  DEFINE(THREAD_KEYS_USER,	offsetof(struct task_struct, thread.keys_user));
+#endif
   BLANK();
   DEFINE(S_X0,			offsetof(struct pt_regs, regs[0]));
   DEFINE(S_X2,			offsetof(struct pt_regs, regs[2]));
@@ -127,6 +130,14 @@ int main(void)
 #ifdef CONFIG_ARM_SDE_INTERFACE
   DEFINE(SDEI_EVENT_INTREGS,	offsetof(struct sdei_registered_event, interrupted_regs));
   DEFINE(SDEI_EVENT_PRIORITY,	offsetof(struct sdei_registered_event, priority));
+#endif
+#ifdef CONFIG_ARM64_PTR_AUTH
+  DEFINE(PTRAUTH_USER_KEY_APIA,		offsetof(struct ptrauth_keys_user, apia));
+  DEFINE(PTRAUTH_USER_KEY_APIB,		offsetof(struct ptrauth_keys_user, apib));
+  DEFINE(PTRAUTH_USER_KEY_APDA,		offsetof(struct ptrauth_keys_user, apda));
+  DEFINE(PTRAUTH_USER_KEY_APDB,		offsetof(struct ptrauth_keys_user, apdb));
+  DEFINE(PTRAUTH_USER_KEY_APGA,		offsetof(struct ptrauth_keys_user, apga));
+  BLANK();
 #endif
   return 0;
 }
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 9461d812ae27..684e475bfda0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -14,6 +14,7 @@
 #include <asm/alternative.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/asm_pointer_auth.h>
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
@@ -341,6 +342,8 @@ alternative_else_nop_endif
 	msr	cntkctl_el1, x1
 4:
 #endif
+	ptrauth_keys_install_user tsk, x0, x1, x2
+
 	apply_ssbd 0, x0, x1
 	.endif
 
diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c
index af5a638207f8..1e77736a4f66 100644
--- a/arch/arm64/kernel/pointer_auth.c
+++ b/arch/arm64/kernel/pointer_auth.c
@@ -19,7 +19,6 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
 
 	if (!arg) {
 		ptrauth_keys_init_user(keys);
-		ptrauth_keys_switch_user(keys);
 		return 0;
 	}
 
@@ -41,7 +40,5 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
 	if (arg & PR_PAC_APGAKEY)
 		get_random_bytes(&keys->apga, sizeof(keys->apga));
 
-	ptrauth_keys_switch_user(keys);
-
 	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 00626057a384..6140e791bf92 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -512,7 +512,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
 	uao_thread_switch(next);
-	ptrauth_thread_switch(next);
 	ssbs_thread_switch(next);
 
 	/*
-- 
cgit v1.2.3


From df3551011b8188e7a9291a66c2c0a04c4eb9d8eb Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap
Date: Fri, 13 Mar 2020 14:34:52 +0530
Subject: arm64: ptrauth: Add bootup/runtime flags for __cpu_setup

This patch allows __cpu_setup to be invoked with one of these flags,
ARM64_CPU_BOOT_PRIMARY, ARM64_CPU_BOOT_SECONDARY or ARM64_CPU_RUNTIME.
This is required as some cpufeatures need different handling during
different scenarios.

The input parameter in x0 is preserved till the end to be used inside
this function.

There should be no functional change with this patch and is useful
for the subsequent ptrauth patch which utilizes it. Some upcoming
arm cpufeatures can also utilize these flags.

Suggested-by: James Morse <james.morse@arm.com>
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/smp.h |  8 ++++++++
 arch/arm64/kernel/head.S     |  2 ++
 arch/arm64/kernel/sleep.S    |  2 ++
 arch/arm64/mm/proc.S         | 26 +++++++++++++++-----------
 4 files changed, 27 insertions(+), 11 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a0c8a0b65259..8d66497d8157 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -23,6 +23,14 @@
 #define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
 #define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
 
+/* Possible options for __cpu_setup */
+/* Option to setup primary cpu */
+#define ARM64_CPU_BOOT_PRIMARY		(1)
+/* Option to setup secondary cpus */
+#define ARM64_CPU_BOOT_SECONDARY	(2)
+/* Option to setup cpus for different cpu run time services */
+#define ARM64_CPU_RUNTIME		(3)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/percpu.h>
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 989b1944cb71..797573fe0e9c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -118,6 +118,7 @@ ENTRY(stext)
 	 * On return, the CPU will be ready for the MMU to be turned on and
 	 * the TCR will have been set.
 	 */
+	mov	x0, #ARM64_CPU_BOOT_PRIMARY
 	bl	__cpu_setup			// initialise processor
 	b	__primary_switch
 ENDPROC(stext)
@@ -712,6 +713,7 @@ secondary_startup:
 	 * Common entry point for secondary CPUs.
 	 */
 	bl	__cpu_secondary_check52bitva
+	mov	x0, #ARM64_CPU_BOOT_SECONDARY
 	bl	__cpu_setup			// initialise processor
 	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index f5b04dd8a710..7b2f2e650c44 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include <asm/smp.h>
 
 	.text
 /*
@@ -99,6 +100,7 @@ ENDPROC(__cpu_suspend_enter)
 	.pushsection ".idmap.text", "awx"
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
+	mov	x0, #ARM64_CPU_RUNTIME
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adrp	x1, swapper_pg_dir
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aafed6902411..ea0db1744c29 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -408,30 +408,30 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings)
 /*
  *	__cpu_setup
  *
- *	Initialise the processor for turning the MMU on.  Return in x0 the
- *	value of the SCTLR_EL1 register.
+ *	Initialise the processor for turning the MMU on.
+ *
+ * Input:
+ *	x0 with a flag ARM64_CPU_BOOT_PRIMARY/ARM64_CPU_BOOT_SECONDARY/ARM64_CPU_RUNTIME.
+ * Output:
+ *	Return in x0 the value of the SCTLR_EL1 register.
  */
 	.pushsection ".idmap.text", "awx"
 SYM_FUNC_START(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
 
-	mov	x0, #3 << 20
-	msr	cpacr_el1, x0			// Enable FP/ASIMD
-	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
-	msr	mdscr_el1, x0			// access to the DCC from EL0
+	mov	x1, #3 << 20
+	msr	cpacr_el1, x1			// Enable FP/ASIMD
+	mov	x1, #1 << 12			// Reset mdscr_el1 and disable
+	msr	mdscr_el1, x1			// access to the DCC from EL0
 	isb					// Unmask debug exceptions now,
 	enable_dbg				// since this is per-cpu
-	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
+	reset_pmuserenr_el0 x1			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes
 	 */
 	mov_q	x5, MAIR_EL1_SET
 	msr	mair_el1, x5
-	/*
-	 * Prepare SCTLR
-	 */
-	mov_q	x0, SCTLR_EL1_SET
 	/*
 	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
 	 * both user and kernel.
@@ -468,5 +468,9 @@ SYM_FUNC_START(__cpu_setup)
 1:
 #endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
+	/*
+	 * Prepare SCTLR
+	 */
+	mov_q	x0, SCTLR_EL1_SET
 	ret					// return to head.S
 SYM_FUNC_END(__cpu_setup)
-- 
cgit v1.2.3


From 8c176e1625a66d35362d4eac7ceab55c1229b481 Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap
Date: Fri, 13 Mar 2020 14:34:53 +0530
Subject: arm64: cpufeature: Move cpu capability helpers inside C file

These helpers are used only by functions inside cpufeature.c and
hence makes sense to be moved from cpufeature.h to cpufeature.c as
they are not expected to be used globally.

This change helps in reducing the header file size as well as to add
future cpu capability types without confusion. Only a cpu capability
type macro is sufficient to expose those capabilities globally.

Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpufeature.h | 12 ------------
 arch/arm64/kernel/cpufeature.c      | 13 +++++++++++++
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8c8048372c8e..cea3c1cdf252 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -340,18 +340,6 @@ static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
 	return cap->type & ARM64_CPUCAP_SCOPE_MASK;
 }
 
-static inline bool
-cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
-{
-	return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
-}
-
-static inline bool
-cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
-{
-	return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
-}
-
 /*
  * Generic helper for handling capabilties with multiple (match,enable) pairs
  * of call backs, sharing the same capability bit.
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 01f50f043831..04ecf1cc3306 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1363,6 +1363,19 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
 }
 #endif
 
+/* Internal helper functions to match cpu capability type */
+static bool
+cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
+{
+	return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
+}
+
+static bool
+cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
+{
+	return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
-- 
cgit v1.2.3


From deeaac5175a577cbbe1a2319903781d0a7ef7720 Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:54 +0530
Subject: arm64: cpufeature: handle conflicts based on capability

Each system capability can be of either boot, local, or system scope,
depending on when the state of the capability is finalized. When we
detect a conflict on a late CPU, we either offline the CPU or panic the
system. We currently always panic if the conflict is caused by a boot
scope capability, and offline the CPU if the conflict is caused by a
local or system scope capability.

We're going to want to add a new capability (for pointer authentication)
which needs to be boot scope but doesn't need to panic the system when a
conflict is detected. So add a new flag to specify whether the
capability requires the system to panic or not. Current boot scope
capabilities are updated to set the flag, so there should be no
functional change as a result of this patch.

Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpufeature.h | 12 ++++++++++--
 arch/arm64/kernel/cpufeature.c      | 29 +++++++++++++++--------------
 2 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index cea3c1cdf252..46388e65bbcd 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -208,6 +208,10 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
  *     In some non-typical cases either both (a) and (b), or neither,
  *     should be permitted. This can be described by including neither
  *     or both flags in the capability's type field.
+ *
+ *     In case of a conflict, the CPU is prevented from booting. If the
+ *     ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability,
+ *     then a kernel panic is triggered.
  */
 
 
@@ -240,6 +244,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU	((u16)BIT(4))
 /* Is it safe for a late CPU to miss this capability when system has it */
 #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	((u16)BIT(5))
+/* Panic when a conflict is detected */
+#define ARM64_CPUCAP_PANIC_ON_CONFLICT		((u16)BIT(6))
 
 /*
  * CPU errata workarounds that need to be enabled at boot time if one or
@@ -279,9 +285,11 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 
 /*
  * CPU feature used early in the boot based on the boot CPU. All secondary
- * CPUs must match the state of the capability as detected by the boot CPU.
+ * CPUs must match the state of the capability as detected by the boot CPU. In
+ * case of a conflict, a kernel panic is triggered.
  */
-#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU
+#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE		\
+	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT)
 
 struct arm64_cpu_capabilities {
 	const char *desc;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 04ecf1cc3306..d6033f45c3cd 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1376,6 +1376,12 @@ cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
 	return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
 }
 
+static bool
+cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap)
+{
+	return !!(cap->type & ARM64_CPUCAP_PANIC_ON_CONFLICT);
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -2018,10 +2024,8 @@ static void __init enable_cpu_capabilities(u16 scope_mask)
  * Run through the list of capabilities to check for conflicts.
  * If the system has already detected a capability, take necessary
  * action on this CPU.
- *
- * Returns "false" on conflicts.
  */
-static bool verify_local_cpu_caps(u16 scope_mask)
+static void verify_local_cpu_caps(u16 scope_mask)
 {
 	int i;
 	bool cpu_has_cap, system_has_cap;
@@ -2066,10 +2070,12 @@ static bool verify_local_cpu_caps(u16 scope_mask)
 		pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n",
 			smp_processor_id(), caps->capability,
 			caps->desc, system_has_cap, cpu_has_cap);
-		return false;
-	}
 
-	return true;
+		if (cpucap_panic_on_conflict(caps))
+			cpu_panic_kernel();
+		else
+			cpu_die_early();
+	}
 }
 
 /*
@@ -2079,12 +2085,8 @@ static bool verify_local_cpu_caps(u16 scope_mask)
 static void check_early_cpu_features(void)
 {
 	verify_cpu_asid_bits();
-	/*
-	 * Early features are used by the kernel already. If there
-	 * is a conflict, we cannot proceed further.
-	 */
-	if (!verify_local_cpu_caps(SCOPE_BOOT_CPU))
-		cpu_panic_kernel();
+
+	verify_local_cpu_caps(SCOPE_BOOT_CPU);
 }
 
 static void
@@ -2132,8 +2134,7 @@ static void verify_local_cpu_capabilities(void)
 	 * check_early_cpu_features(), as they need to be verified
 	 * on all secondary CPUs.
 	 */
-	if (!verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU))
-		cpu_die_early();
+	verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU);
 
 	verify_local_elf_hwcaps(arm64_elf_hwcaps);
 
-- 
cgit v1.2.3


From 6982934e19f8ebb4152ba77308facdb1a38533f9 Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:55 +0530
Subject: arm64: enable ptrauth earlier

When the kernel is compiled with pointer auth instructions, the boot CPU
needs to start using address auth very early, so change the cpucap to
account for this.

Pointer auth must be enabled before we call C functions, because it is
not possible to enter a function with pointer auth disabled and exit it
with pointer auth enabled. Note, mismatches between architected and
IMPDEF algorithms will still be caught by the cpufeature framework (the
separate *_ARCH and *_IMP_DEF cpucaps).

Note the change in behavior: if the boot CPU has address auth and a
late CPU does not, then the late CPU is parked by the cpufeature
framework. This is possible as kernel will only have NOP space intructions
for PAC so such mismatched late cpu will silently ignore those
instructions in C functions. Also, if the boot CPU does not have address
auth and the late CPU has then the late cpu will still boot but with
ptrauth feature disabled.

Leave generic authentication as a "system scope" cpucap for now, since
initially the kernel will only use address authentication.

Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[Amit: Re-worked ptrauth setup logic, comments]
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig                  |  6 ++++++
 arch/arm64/include/asm/cpufeature.h |  9 +++++++++
 arch/arm64/kernel/cpufeature.c      | 13 +++----------
 arch/arm64/mm/proc.S                | 31 +++++++++++++++++++++++++++++++
 4 files changed, 49 insertions(+), 10 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0b30e884e088..87e2cbb76930 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1515,6 +1515,12 @@ config ARM64_PTR_AUTH
 	  be enabled. However, KVM guest also require VHE mode and hence
 	  CONFIG_ARM64_VHE=y option to use this feature.
 
+	  If the feature is present on the boot CPU but not on a late CPU, then
+	  the late CPU will be parked. Also, if the boot CPU does not have
+	  address auth and the late CPU has then the late CPU will still boot
+	  but with the feature disabled. On such a system, this option should
+	  not be selected.
+
 endmenu
 
 menu "ARMv8.5 architectural features"
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 46388e65bbcd..2b5a088053e4 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -291,6 +291,15 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE		\
 	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT)
 
+/*
+ * CPU feature used early in the boot based on the boot CPU. It is safe for a
+ * late CPU to have this feature even though the boot CPU hasn't enabled it,
+ * although the feature will not be used by Linux in this case. If the boot CPU
+ * has enabled this feature already, then every late CPU must have it.
+ */
+#define ARM64_CPUCAP_BOOT_CPU_FEATURE                  \
+	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
+
 struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d6033f45c3cd..f6c0cb755107 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1318,12 +1318,6 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 #endif /* CONFIG_ARM64_RAS_EXTN */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
-static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap)
-{
-	sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
-				       SCTLR_ELx_ENDA | SCTLR_ELx_ENDB);
-}
-
 static bool has_address_auth(const struct arm64_cpu_capabilities *entry,
 			     int __unused)
 {
@@ -1627,7 +1621,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "Address authentication (architected algorithm)",
 		.capability = ARM64_HAS_ADDRESS_AUTH_ARCH,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
 		.sys_reg = SYS_ID_AA64ISAR1_EL1,
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64ISAR1_APA_SHIFT,
@@ -1637,7 +1631,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "Address authentication (IMP DEF algorithm)",
 		.capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
 		.sys_reg = SYS_ID_AA64ISAR1_EL1,
 		.sign = FTR_UNSIGNED,
 		.field_pos = ID_AA64ISAR1_API_SHIFT,
@@ -1646,9 +1640,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	},
 	{
 		.capability = ARM64_HAS_ADDRESS_AUTH,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
 		.matches = has_address_auth,
-		.cpu_enable = cpu_enable_address_auth,
 	},
 	{
 		.desc = "Generic authentication (architected algorithm)",
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index ea0db1744c29..4cf19a26af2d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -16,6 +16,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
+#include <asm/smp.h>
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
@@ -468,9 +469,39 @@ SYM_FUNC_START(__cpu_setup)
 1:
 #endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
+	mov	x1, x0
 	/*
 	 * Prepare SCTLR
 	 */
 	mov_q	x0, SCTLR_EL1_SET
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+	/* No ptrauth setup for run time cpus */
+	cmp	x1, #ARM64_CPU_RUNTIME
+	b.eq	3f
+
+	/* Check if the CPU supports ptrauth */
+	mrs	x2, id_aa64isar1_el1
+	ubfx	x2, x2, #ID_AA64ISAR1_APA_SHIFT, #8
+	cbz	x2, 3f
+
+	msr_s	SYS_APIAKEYLO_EL1, xzr
+	msr_s	SYS_APIAKEYHI_EL1, xzr
+
+	/* Just enable ptrauth for primary cpu */
+	cmp	x1, #ARM64_CPU_BOOT_PRIMARY
+	b.eq	2f
+
+	/* if !system_supports_address_auth() then skip enable */
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	3f
+alternative_else_nop_endif
+
+2:	/* Enable ptrauth instructions */
+	ldr	x2, =SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB
+	orr	x0, x0, x2
+3:
+#endif
 	ret					// return to head.S
 SYM_FUNC_END(__cpu_setup)
-- 
cgit v1.2.3


From 33e45234987ea3ed4b05fc512f4441696478f12d Mon Sep 17 00:00:00 2001
From: Kristina Martsenko
Date: Fri, 13 Mar 2020 14:34:56 +0530
Subject: arm64: initialize and switch ptrauth kernel keys

Set up keys to use pointer authentication within the kernel. The kernel
will be compiled with APIAKey instructions, the other keys are currently
unused. Each task is given its own APIAKey, which is initialized during
fork. The key is changed during context switch and on kernel entry from
EL0.

The keys for idle threads need to be set before calling any C functions,
because it is not possible to enter and exit a function with different
keys.

Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
[Amit: Modified secondary cores key structure, comments]
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/asm_pointer_auth.h | 14 ++++++++++++++
 arch/arm64/include/asm/pointer_auth.h     | 13 +++++++++++++
 arch/arm64/include/asm/processor.h        |  1 +
 arch/arm64/include/asm/smp.h              |  4 ++++
 arch/arm64/kernel/asm-offsets.c           |  5 +++++
 arch/arm64/kernel/entry.S                 |  3 +++
 arch/arm64/kernel/process.c               |  2 ++
 arch/arm64/kernel/smp.c                   |  8 ++++++++
 arch/arm64/mm/proc.S                      | 12 ++++++++++++
 9 files changed, 62 insertions(+)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
index 3482348ec07f..d3f4aee42851 100644
--- a/arch/arm64/include/asm/asm_pointer_auth.h
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -39,11 +39,25 @@ alternative_if ARM64_HAS_GENERIC_AUTH
 alternative_else_nop_endif
 	.endm
 
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	mov	\tmp1, #THREAD_KEYS_KERNEL
+	add	\tmp1, \tsk, \tmp1
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	isb
+alternative_else_nop_endif
+	.endm
+
 #else /* CONFIG_ARM64_PTR_AUTH */
 
 	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
 	.endm
 
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+	.endm
+
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index dabe026ca8ca..aa956ca5f2c2 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -30,6 +30,10 @@ struct ptrauth_keys_user {
 	struct ptrauth_key apga;
 };
 
+struct ptrauth_keys_kernel {
+	struct ptrauth_key apia;
+};
+
 static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
 {
 	if (system_supports_address_auth()) {
@@ -50,6 +54,12 @@ do {								\
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
+static inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (system_supports_address_auth())
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+}
+
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
 /*
@@ -66,11 +76,14 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 
 #define ptrauth_thread_init_user(tsk)					\
 	ptrauth_keys_init_user(&(tsk)->thread.keys_user)
+#define ptrauth_thread_init_kernel(tsk)					\
+	ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
 
 #else /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_thread_init_user(tsk)
+#define ptrauth_thread_init_kernel(tsk)
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 496a92873290..4c77da5dc819 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -147,6 +147,7 @@ struct thread_struct {
 	struct debug_info	debug;		/* debugging */
 #ifdef CONFIG_ARM64_PTR_AUTH
 	struct ptrauth_keys_user	keys_user;
+	struct ptrauth_keys_kernel	keys_kernel;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 8d66497d8157..40d5ba029615 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -38,6 +38,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
+#include <asm/pointer_auth.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
@@ -95,6 +96,9 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	void *stack;
 	struct task_struct *task;
+#ifdef CONFIG_ARM64_PTR_AUTH
+	struct ptrauth_keys_kernel ptrauth_key;
+#endif
 	long status;
 };
 
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7b1ea2aece58..9981a0a5a87f 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -42,6 +42,7 @@ int main(void)
   DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
 #ifdef CONFIG_ARM64_PTR_AUTH
   DEFINE(THREAD_KEYS_USER,	offsetof(struct task_struct, thread.keys_user));
+  DEFINE(THREAD_KEYS_KERNEL,	offsetof(struct task_struct, thread.keys_kernel));
 #endif
   BLANK();
   DEFINE(S_X0,			offsetof(struct pt_regs, regs[0]));
@@ -91,6 +92,9 @@ int main(void)
   BLANK();
   DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
+#ifdef CONFIG_ARM64_PTR_AUTH
+  DEFINE(CPU_BOOT_PTRAUTH_KEY,	offsetof(struct secondary_data, ptrauth_key));
+#endif
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
@@ -137,6 +141,7 @@ int main(void)
   DEFINE(PTRAUTH_USER_KEY_APDA,		offsetof(struct ptrauth_keys_user, apda));
   DEFINE(PTRAUTH_USER_KEY_APDB,		offsetof(struct ptrauth_keys_user, apdb));
   DEFINE(PTRAUTH_USER_KEY_APGA,		offsetof(struct ptrauth_keys_user, apga));
+  DEFINE(PTRAUTH_KERNEL_KEY_APIA,	offsetof(struct ptrauth_keys_kernel, apia));
   BLANK();
 #endif
   return 0;
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 684e475bfda0..3dad2d000e3c 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -178,6 +178,7 @@ alternative_cb_end
 
 	apply_ssbd 1, x22, x23
 
+	ptrauth_keys_install_kernel tsk, x20, x22, x23
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_current_task tsk
@@ -342,6 +343,7 @@ alternative_else_nop_endif
 	msr	cntkctl_el1, x1
 4:
 #endif
+	/* No kernel C function calls after this as user keys are set. */
 	ptrauth_keys_install_user tsk, x0, x1, x2
 
 	apply_ssbd 0, x0, x1
@@ -898,6 +900,7 @@ ENTRY(cpu_switch_to)
 	ldr	lr, [x8]
 	mov	sp, x9
 	msr	sp_el0, x1
+	ptrauth_keys_install_kernel x1, x8, x9, x10
 	ret
 ENDPROC(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6140e791bf92..7db0302bec00 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -376,6 +376,8 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
 	 */
 	fpsimd_flush_task_state(p);
 
+	ptrauth_thread_init_kernel(p);
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d4ed9a19d8fe..08903413f106 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -112,6 +112,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 */
 	secondary_data.task = idle;
 	secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
+#if defined(CONFIG_ARM64_PTR_AUTH)
+	secondary_data.ptrauth_key.apia.lo = idle->thread.keys_kernel.apia.lo;
+	secondary_data.ptrauth_key.apia.hi = idle->thread.keys_kernel.apia.hi;
+#endif
 	update_cpu_boot_status(CPU_MMU_OFF);
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 
@@ -138,6 +142,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
+#if defined(CONFIG_ARM64_PTR_AUTH)
+	secondary_data.ptrauth_key.apia.lo = 0;
+	secondary_data.ptrauth_key.apia.hi = 0;
+#endif
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (ret && status) {
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 4cf19a26af2d..5a11a895e923 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -485,6 +485,10 @@ SYM_FUNC_START(__cpu_setup)
 	ubfx	x2, x2, #ID_AA64ISAR1_APA_SHIFT, #8
 	cbz	x2, 3f
 
+	/*
+	 * The primary cpu keys are reset here and can be
+	 * re-initialised with some proper values later.
+	 */
 	msr_s	SYS_APIAKEYLO_EL1, xzr
 	msr_s	SYS_APIAKEYHI_EL1, xzr
 
@@ -497,6 +501,14 @@ alternative_if_not ARM64_HAS_ADDRESS_AUTH
 	b	3f
 alternative_else_nop_endif
 
+	/* Install ptrauth key for secondary cpus */
+	adr_l	x2, secondary_data
+	ldr	x3, [x2, #CPU_BOOT_TASK]	// get secondary_data.task
+	cbz	x3, 2f				// check for slow booting cpus
+	ldp	x3, x4, [x2, #CPU_BOOT_PTRAUTH_KEY]
+	msr_s	SYS_APIAKEYLO_EL1, x3
+	msr_s	SYS_APIAKEYHI_EL1, x4
+
 2:	/* Enable ptrauth instructions */
 	ldr	x2, =SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
 		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB
-- 
cgit v1.2.3


From 28321582334c261c13b20d7efe634e610b4c100b Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap
Date: Fri, 13 Mar 2020 14:34:57 +0530
Subject: arm64: initialize ptrauth keys for kernel booting task

This patch uses the existing boot_init_stack_canary arch function
to initialize the ptrauth keys for the booting task in the primary
core. The requirement here is that it should be always inline and
the caller must never return.

As pointer authentication too detects a subset of stack corruption
so it makes sense to place this code here.

Both pointer authentication and stack canary codes are protected
by their respective config option.

Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/pointer_auth.h   | 11 ++++++++++-
 arch/arm64/include/asm/stackprotector.h |  5 +++++
 include/linux/stackprotector.h          |  2 +-
 3 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index aa956ca5f2c2..833d3f948de0 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -54,12 +54,18 @@ do {								\
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
-static inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
+static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
 {
 	if (system_supports_address_auth())
 		get_random_bytes(&keys->apia, sizeof(keys->apia));
 }
 
+static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (system_supports_address_auth())
+		__ptrauth_key_install(APIA, keys->apia);
+}
+
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
 /*
@@ -78,12 +84,15 @@ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 	ptrauth_keys_init_user(&(tsk)->thread.keys_user)
 #define ptrauth_thread_init_kernel(tsk)					\
 	ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
+#define ptrauth_thread_switch_kernel(tsk)				\
+	ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
 
 #else /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_thread_init_user(tsk)
 #define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_kernel(tsk)
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
index 5884a2b02827..7263e0bac680 100644
--- a/arch/arm64/include/asm/stackprotector.h
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -15,6 +15,7 @@
 
 #include <linux/random.h>
 #include <linux/version.h>
+#include <asm/pointer_auth.h>
 
 extern unsigned long __stack_chk_guard;
 
@@ -26,6 +27,7 @@ extern unsigned long __stack_chk_guard;
  */
 static __always_inline void boot_init_stack_canary(void)
 {
+#if defined(CONFIG_STACKPROTECTOR)
 	unsigned long canary;
 
 	/* Try to get a semi random initial value. */
@@ -36,6 +38,9 @@ static __always_inline void boot_init_stack_canary(void)
 	current->stack_canary = canary;
 	if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK))
 		__stack_chk_guard = current->stack_canary;
+#endif
+	ptrauth_thread_init_kernel(current);
+	ptrauth_thread_switch_kernel(current);
 }
 
 #endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h
index 6b792d080eee..4c678c4fec58 100644
--- a/include/linux/stackprotector.h
+++ b/include/linux/stackprotector.h
@@ -6,7 +6,7 @@
 #include <linux/sched.h>
 #include <linux/random.h>
 
-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) || defined(CONFIG_ARM64_PTR_AUTH)
 # include <asm/stackprotector.h>
 #else
 static inline void boot_init_stack_canary(void)
-- 
cgit v1.2.3


From 689eae42afd7a916634146edca38463769969184 Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap
Date: Fri, 13 Mar 2020 14:34:58 +0530
Subject: arm64: mask PAC bits of __builtin_return_address

Functions like vmap() record how much memory has been allocated by their
callers, and callers are identified using __builtin_return_address(). Once
the kernel is using pointer-auth the return address will be signed. This
means it will not match any kernel symbol, and will vary between threads
even for the same caller.

The output of /proc/vmallocinfo in this case may look like,
0x(____ptrval____)-0x(____ptrval____)   20480 0x86e28000100e7c60 pages=4 vmalloc N0=4
0x(____ptrval____)-0x(____ptrval____)   20480 0x86e28000100e7c60 pages=4 vmalloc N0=4
0x(____ptrval____)-0x(____ptrval____)   20480 0xc5c78000100e7c60 pages=4 vmalloc N0=4

The above three 64bit values should be the same symbol name and not
different LR values.

Use the pre-processor to add logic to clear the PAC to
__builtin_return_address() callers. This patch adds a new file
asm/compiler.h and is transitively included via include/compiler_types.h on
the compiler command line so it is guaranteed to be loaded and the users of
this macro will not find a wrong version.

Helper macros ptrauth_kernel_pac_mask/ptrauth_clear_pac are created for
this purpose and added in this file. Existing macro ptrauth_user_pac_mask
moved from asm/pointer_auth.h.

Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig                    |  1 +
 arch/arm64/include/asm/compiler.h     | 24 ++++++++++++++++++++++++
 arch/arm64/include/asm/pointer_auth.h |  9 +--------
 3 files changed, 26 insertions(+), 8 deletions(-)
 create mode 100644 arch/arm64/include/asm/compiler.h

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 87e2cbb76930..115ceea0293e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -118,6 +118,7 @@ config ARM64
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
+	select HAVE_ARCH_COMPILER_H
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
new file mode 100644
index 000000000000..eece20d2c55f
--- /dev/null
+++ b/arch/arm64/include/asm/compiler.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_COMPILER_H
+#define __ASM_COMPILER_H
+
+#if defined(CONFIG_ARM64_PTR_AUTH)
+
+/*
+ * The EL0/EL1 pointer bits used by a pointer authentication code.
+ * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
+ */
+#define ptrauth_user_pac_mask()		GENMASK_ULL(54, vabits_actual)
+#define ptrauth_kernel_pac_mask()	GENMASK_ULL(63, vabits_actual)
+
+/* Valid for EL0 TTBR0 and EL1 TTBR1 instruction pointers */
+#define ptrauth_clear_pac(ptr)						\
+	((ptr & BIT_ULL(55)) ? (ptr | ptrauth_kernel_pac_mask()) :	\
+			       (ptr & ~ptrauth_user_pac_mask()))
+
+#define __builtin_return_address(val)					\
+	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
+
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 833d3f948de0..70c47156e54b 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -68,16 +68,9 @@ static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kerne
 
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
-/*
- * The EL0 pointer bits used by a pointer authentication code.
- * This is dependent on TBI0 being enabled, or bits 63:56 would also apply.
- */
-#define ptrauth_user_pac_mask()	GENMASK(54, vabits_actual)
-
-/* Only valid for EL0 TTBR0 instruction pointers */
 static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 {
-	return ptr & ~ptrauth_user_pac_mask();
+	return ptrauth_clear_pac(ptr);
 }
 
 #define ptrauth_thread_init_user(tsk)					\
-- 
cgit v1.2.3


From e51f5f56dd69e009e22af8a4354dce0817a7addb Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap
Date: Fri, 13 Mar 2020 14:35:01 +0530
Subject: arm64: suspend: restore the kernel ptrauth keys

This patch restores the kernel keys from current task during cpu resume
after the mmu is turned on and ptrauth is enabled.

A flag is added in macro ptrauth_keys_install_kernel to check if isb
instruction needs to be executed.

Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Reviewed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/asm_pointer_auth.h | 6 ++++--
 arch/arm64/kernel/entry.S                 | 4 ++--
 arch/arm64/mm/proc.S                      | 2 ++
 3 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
index d3f4aee42851..ce2a8486992b 100644
--- a/arch/arm64/include/asm/asm_pointer_auth.h
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -39,14 +39,16 @@ alternative_if ARM64_HAS_GENERIC_AUTH
 alternative_else_nop_endif
 	.endm
 
-	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+	.macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
 alternative_if ARM64_HAS_ADDRESS_AUTH
 	mov	\tmp1, #THREAD_KEYS_KERNEL
 	add	\tmp1, \tsk, \tmp1
 	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA]
 	msr_s	SYS_APIAKEYLO_EL1, \tmp2
 	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	.if     \sync == 1
 	isb
+	.endif
 alternative_else_nop_endif
 	.endm
 
@@ -55,7 +57,7 @@ alternative_else_nop_endif
 	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
 	.endm
 
-	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+	.macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
 	.endm
 
 #endif /* CONFIG_ARM64_PTR_AUTH */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 3dad2d000e3c..6273d7bed962 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -178,7 +178,7 @@ alternative_cb_end
 
 	apply_ssbd 1, x22, x23
 
-	ptrauth_keys_install_kernel tsk, x20, x22, x23
+	ptrauth_keys_install_kernel tsk, 1, x20, x22, x23
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_current_task tsk
@@ -900,7 +900,7 @@ ENTRY(cpu_switch_to)
 	ldr	lr, [x8]
 	mov	sp, x9
 	msr	sp_el0, x1
-	ptrauth_keys_install_kernel x1, x8, x9, x10
+	ptrauth_keys_install_kernel x1, 1, x8, x9, x10
 	ret
 ENDPROC(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 5a11a895e923..4450dc83cf5c 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -11,6 +11,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/asm_pointer_auth.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
@@ -137,6 +138,7 @@ alternative_if ARM64_HAS_RAS_EXTN
 	msr_s	SYS_DISR_EL1, xzr
 alternative_else_nop_endif
 
+	ptrauth_keys_install_kernel x14, 0, x1, x2, x3
 	isb
 	ret
 SYM_FUNC_END(cpu_do_resume)
-- 
cgit v1.2.3


From 6885fb129be30c627eb2f5b1498dba498ff6c037 Mon Sep 17 00:00:00 2001
From: Gavin Shan
Date: Thu, 19 Mar 2020 10:01:43 +1100
Subject: arm64: Rename cpu_read_ops() to init_cpu_ops()

This renames cpu_read_ops() to init_cpu_ops() as the function is only
called in initialization phase. Also, we will introduce get_cpu_ops() in
the subsequent patches, to retireve the CPU operation by the given CPU
index. The usage of cpu_read_ops() and get_cpu_ops() are difficult to be
distinguished from their names.

Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpu_ops.h | 6 +++---
 arch/arm64/kernel/cpu_ops.c      | 2 +-
 arch/arm64/kernel/setup.c        | 2 +-
 arch/arm64/kernel/smp.c          | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 86aabf1e0199..baa13b5db2ca 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -56,11 +56,11 @@ struct cpu_operations {
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
-int __init cpu_read_ops(int cpu);
+int __init init_cpu_ops(int cpu);
 
-static inline void __init cpu_read_bootcpu_ops(void)
+static inline void __init init_bootcpu_ops(void)
 {
-	cpu_read_ops(0);
+	init_cpu_ops(0);
 }
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index 2082cfb1be86..a6c3c816b618 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -96,7 +96,7 @@ static const char *__init cpu_read_enable_method(int cpu)
 /*
  * Read a cpu's enable method and record it in cpu_ops.
  */
-int __init cpu_read_ops(int cpu)
+int __init init_cpu_ops(int cpu)
 {
 	const char *enable_method = cpu_read_enable_method(cpu);
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index a34890bf309f..f66bd260cce8 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -344,7 +344,7 @@ void __init setup_arch(char **cmdline_p)
 	else
 		psci_acpi_init();
 
-	cpu_read_bootcpu_ops();
+	init_bootcpu_ops();
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d4ed9a19d8fe..6f8477d7f3be 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -488,7 +488,7 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
  */
 static int __init smp_cpu_setup(int cpu)
 {
-	if (cpu_read_ops(cpu))
+	if (init_cpu_ops(cpu))
 		return -ENODEV;
 
 	if (cpu_ops[cpu]->cpu_init(cpu))
-- 
cgit v1.2.3


From de58ed5e16e62f36c7ed05552f18b7f9c647dcaf Mon Sep 17 00:00:00 2001
From: Gavin Shan
Date: Thu, 19 Mar 2020 10:01:44 +1100
Subject: arm64: Introduce get_cpu_ops() helper function

This introduces get_cpu_ops() to return the CPU operations according to
the given CPU index. For now, it simply returns the @cpu_ops[cpu] as
before. Also, helper function __cpu_try_die() is introduced to be shared
by cpu_die() and ipi_cpu_crash_stop(). So it shouldn't introduce any
functional changes.

Signed-off-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
---
 arch/arm64/include/asm/cpu_ops.h |  2 +-
 arch/arm64/kernel/cpu_ops.c      |  7 +++-
 arch/arm64/kernel/cpuidle.c      |  9 +++---
 arch/arm64/kernel/setup.c        |  6 ++--
 arch/arm64/kernel/smp.c          | 70 ++++++++++++++++++++++++++--------------
 5 files changed, 62 insertions(+), 32 deletions(-)

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index baa13b5db2ca..d28e8f37d3b4 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -55,8 +55,8 @@ struct cpu_operations {
 #endif
 };
 
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
 int __init init_cpu_ops(int cpu);
+extern const struct cpu_operations *get_cpu_ops(int cpu);
 
 static inline void __init init_bootcpu_ops(void)
 {
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index a6c3c816b618..e133011f64b5 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -20,7 +20,7 @@ extern const struct cpu_operations acpi_parking_protocol_ops;
 #endif
 extern const struct cpu_operations cpu_psci_ops;
 
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+static const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
 static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
 	&smp_spin_table_ops,
@@ -111,3 +111,8 @@ int __init init_cpu_ops(int cpu)
 
 	return 0;
 }
+
+const struct cpu_operations *get_cpu_ops(int cpu)
+{
+	return cpu_ops[cpu];
+}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index e4d6af2fdec7..b512b5503f6e 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -18,11 +18,11 @@
 
 int arm_cpuidle_init(unsigned int cpu)
 {
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
 	int ret = -EOPNOTSUPP;
 
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_suspend &&
-			cpu_ops[cpu]->cpu_init_idle)
-		ret = cpu_ops[cpu]->cpu_init_idle(cpu);
+	if (ops && ops->cpu_suspend && ops->cpu_init_idle)
+		ret = ops->cpu_init_idle(cpu);
 
 	return ret;
 }
@@ -37,8 +37,9 @@ int arm_cpuidle_init(unsigned int cpu)
 int arm_cpuidle_suspend(int index)
 {
 	int cpu = smp_processor_id();
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
 
-	return cpu_ops[cpu]->cpu_suspend(index);
+	return ops->cpu_suspend(index);
 }
 
 #ifdef CONFIG_ACPI
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f66bd260cce8..3fd2c11c09fc 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -371,8 +371,10 @@ void __init setup_arch(char **cmdline_p)
 static inline bool cpu_can_disable(unsigned int cpu)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
-		return cpu_ops[cpu]->cpu_can_disable(cpu);
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops && ops->cpu_can_disable)
+		return ops->cpu_can_disable(cpu);
 #endif
 	return false;
 }
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6f8477d7f3be..e5c9862c271b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -93,8 +93,10 @@ static inline int op_cpu_kill(unsigned int cpu)
  */
 static int boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	if (cpu_ops[cpu]->cpu_boot)
-		return cpu_ops[cpu]->cpu_boot(cpu);
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops->cpu_boot)
+		return ops->cpu_boot(cpu);
 
 	return -EOPNOTSUPP;
 }
@@ -196,6 +198,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
+	const struct cpu_operations *ops;
 	unsigned int cpu;
 
 	cpu = task_cpu(current);
@@ -227,8 +230,9 @@ asmlinkage notrace void secondary_start_kernel(void)
 	 */
 	check_local_cpu_capabilities();
 
-	if (cpu_ops[cpu]->cpu_postboot)
-		cpu_ops[cpu]->cpu_postboot();
+	ops = get_cpu_ops(cpu);
+	if (ops->cpu_postboot)
+		ops->cpu_postboot();
 
 	/*
 	 * Log the CPU info before it is marked online and might get read.
@@ -266,19 +270,21 @@ asmlinkage notrace void secondary_start_kernel(void)
 #ifdef CONFIG_HOTPLUG_CPU
 static int op_cpu_disable(unsigned int cpu)
 {
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
 	/*
 	 * If we don't have a cpu_die method, abort before we reach the point
 	 * of no return. CPU0 may not have an cpu_ops, so test for it.
 	 */
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+	if (!ops || !ops->cpu_die)
 		return -EOPNOTSUPP;
 
 	/*
 	 * We may need to abort a hot unplug for some other mechanism-specific
 	 * reason.
 	 */
-	if (cpu_ops[cpu]->cpu_disable)
-		return cpu_ops[cpu]->cpu_disable(cpu);
+	if (ops->cpu_disable)
+		return ops->cpu_disable(cpu);
 
 	return 0;
 }
@@ -314,15 +320,17 @@ int __cpu_disable(void)
 
 static int op_cpu_kill(unsigned int cpu)
 {
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
 	/*
 	 * If we have no means of synchronising with the dying CPU, then assume
 	 * that it is really dead. We can only wait for an arbitrary length of
 	 * time and hope that it's dead, so let's skip the wait and just hope.
 	 */
-	if (!cpu_ops[cpu]->cpu_kill)
+	if (!ops->cpu_kill)
 		return 0;
 
-	return cpu_ops[cpu]->cpu_kill(cpu);
+	return ops->cpu_kill(cpu);
 }
 
 /*
@@ -357,6 +365,7 @@ void __cpu_die(unsigned int cpu)
 void cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
 
 	idle_task_exit();
 
@@ -370,12 +379,22 @@ void cpu_die(void)
 	 * mechanism must perform all required cache maintenance to ensure that
 	 * no dirty lines are lost in the process of shutting down the CPU.
 	 */
-	cpu_ops[cpu]->cpu_die(cpu);
+	ops->cpu_die(cpu);
 
 	BUG();
 }
 #endif
 
+static void __cpu_try_die(int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops && ops->cpu_die)
+		ops->cpu_die(cpu);
+#endif
+}
+
 /*
  * Kill the calling secondary CPU, early in bringup before it is turned
  * online.
@@ -389,12 +408,11 @@ void cpu_die_early(void)
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	update_cpu_boot_status(CPU_KILL_ME);
-	/* Check if we can park ourselves */
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
-		cpu_ops[cpu]->cpu_die(cpu);
-#endif
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+		update_cpu_boot_status(CPU_KILL_ME);
+		__cpu_try_die(cpu);
+	}
+
 	update_cpu_boot_status(CPU_STUCK_IN_KERNEL);
 
 	cpu_park_loop();
@@ -488,10 +506,13 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
  */
 static int __init smp_cpu_setup(int cpu)
 {
+	const struct cpu_operations *ops;
+
 	if (init_cpu_ops(cpu))
 		return -ENODEV;
 
-	if (cpu_ops[cpu]->cpu_init(cpu))
+	ops = get_cpu_ops(cpu);
+	if (ops->cpu_init(cpu))
 		return -ENODEV;
 
 	set_cpu_possible(cpu, true);
@@ -714,6 +735,7 @@ void __init smp_init_cpus(void)
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
+	const struct cpu_operations *ops;
 	int err;
 	unsigned int cpu;
 	unsigned int this_cpu;
@@ -744,10 +766,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (cpu == smp_processor_id())
 			continue;
 
-		if (!cpu_ops[cpu])
+		ops = get_cpu_ops(cpu);
+		if (!ops)
 			continue;
 
-		err = cpu_ops[cpu]->cpu_prepare(cpu);
+		err = ops->cpu_prepare(cpu);
 		if (err)
 			continue;
 
@@ -863,10 +886,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 	local_irq_disable();
 	sdei_mask_local_cpu();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	if (cpu_ops[cpu]->cpu_die)
-		cpu_ops[cpu]->cpu_die(cpu);
-#endif
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		__cpu_try_die(cpu);
 
 	/* just in case */
 	cpu_park_loop();
@@ -1044,8 +1065,9 @@ static bool have_cpu_die(void)
 {
 #ifdef CONFIG_HOTPLUG_CPU
 	int any_cpu = raw_smp_processor_id();
+	const struct cpu_operations *ops = get_cpu_ops(any_cpu);
 
-	if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
+	if (ops && ops->cpu_die)
 		return true;
 #endif
 	return false;
-- 
cgit v1.2.3