spectre on 4.9 backporting review

spectre on 4.9 backporting review

[Alex Shi]

Hi All,

This backport patchset fixed the spectre issue, it's original branch:
https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git/log/?h=kpti
A few dependency or fixingpatches are also picked up, if they are necessary
 or no functional changes.

arm64: cpu_errata: Allow an erratum to be match for all revisions of a core
arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early
arm64: syscallno is secretly an int, make it official
arm64: uaccess: consistently check object sizes
arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
arm64: move TASK_* definitions to <asm/processor.h>
arm64: alternatives: apply boot time fixups via the linear mapping
mm: Introduce lm_alias

The patchset also on repository:
	git://git.linaro.org/kernel/linux-linaro-stable.git lts-4.9-spectrevv2 

The kernelci.org and lkft testing show no regressions.

Any comments are appreciated!

Regards
Alex

---
Ard Biesheuvel <ard.biesheuvel@linaro.org> (1):
      arm64: alternatives: apply boot time fixups via the linear mapping

Catalin Marinas <catalin.marinas@arm.com> (2):
      arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
      arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro

Dave Martin <Dave.Martin@arm.com> (1):
      arm64: syscallno is secretly an int, make it official

James Morse <james.morse@arm.com> (1):
      arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early

Laura Abbott <labbott@redhat.com> (1):
      mm: Introduce lm_alias

Marc Zyngier <marc.zyngier@arm.com> (26):
      arm64: cpu_errata: Allow an erratum to be match for all revisions of a core
      arm64: Move post_ttbr_update_workaround to C code
      arm64: Move BP hardening to check_and_switch_context
      arm64: KVM: Use per-CPU vector when BP hardening is enabled
      arm64: KVM: Increment PC after handling an SMC trap
      arm/arm64: KVM: Consolidate the PSCI include files
      arm/arm64: KVM: Add PSCI_VERSION helper
      arm/arm64: KVM: Add smccc accessors to PSCI code
      arm/arm64: KVM: Implement PSCI 1.0 support
      arm/arm64: KVM: Advertise SMCCC v1.1
      arm64: KVM: Make PSCI_VERSION a fast path
      arm/arm64: KVM: Turn kvm_psci_version into a static inline
      arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support
      arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling
      firmware/psci: Expose PSCI conduit
      firmware/psci: Expose SMCCC version through psci_ops
      arm/arm64: smccc: Make function identifiers an unsigned quantity
      arm/arm64: smccc: Implement SMCCC v1.1 inline primitive
      arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support
      arm64: Kill PSCI_GET_VERSION as a variant-2 workaround
      arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17
      arm: Invalidate BTB on prefetch abort outside of user mapping on Cortex A8, A9, A12 and A17
      arm: KVM: Invalidate BTB on guest exit for Cortex-A12/A17
      arm: Add icache invalidation on switch_mm for Cortex-A15
      arm: Invalidate icache on prefetch abort outside of user mapping on Cortex-A15
      arm: KVM: Invalidate icache on guest exit for Cortex-A15

Mark Rutland <mark.rutland@arm.com> (1):
      arm64: uaccess: consistently check object sizes

Robin Murphy <robin.murphy@arm.com> (3):
      arm64: Implement array_index_mask_nospec()
      arm64: Make USER_DS an inclusive limit
      arm64: Use pointer masking to limit uaccess speculation

Suzuki K Poulose <suzuki.poulose@arm.com> (1):
      arm64: Run enable method for errata work arounds on late CPUs

Will Deacon <will.deacon@arm.com> (14):
      arm64: barrier: Add CSDB macros to control data-value prediction
      arm64: entry: Ensure branch through syscall table is bounded under speculation
      arm64: uaccess: Prevent speculative use of the current addr_limit
      arm64: uaccess: Don't bother eliding access_ok checks in __{get, put}_user
      arm64: uaccess: Mask __user pointers for __arch_{clear, copy_*}_user
      arm64: futex: Mask __user pointers prior to dereference
      drivers/firmware: Expose psci_get_version through psci_ops structure
      arm64: cpufeature: Pass capability structure to ->enable callback
      arm64: Add skeleton to harden the branch predictor against aliasing attacks
      arm64: entry: Apply BP hardening for high-priority synchronous exceptions
      arm64: entry: Apply BP hardening for suspicious interrupts from EL0
      arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75
      arm64: Implement branch predictor hardening for affected Cortex-A CPUs
      arm64: Add README describing the branch

Yury Norov <ynorov@caviumnetworks.com> (1):
      arm64: move TASK_* definitions to <asm/processor.h>

[PATCH 01/52] mm: Introduce lm_alias

[Alex Shi]

From: Laura Abbott <labbott@redhat.com>

commit 568c5fe5a54 upstream.

Certain architectures may have the kernel image mapped separately to
alias the linear map. Introduce a macro lm_alias to translate a kernel
image symbol into its linear alias. This is used in part with work to
add CONFIG_DEBUG_VIRTUAL support for arm64.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 include/linux/mm.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2217e2f..edd2480 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -76,6 +76,10 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #define page_to_virt(x)	__va(PFN_PHYS(page_to_pfn(x)))
 #endif
 
+#ifndef lm_alias
+#define lm_alias(x)	__va(__pa_symbol(x))
+#endif
+
 /*
  * To prevent common memory management code establishing
  * a zero page mapping on a read fault.
-- 
2.7.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 02/52] arm64: alternatives: apply boot time fixups via the linear mapping

[Alex Shi]

From: Ard Biesheuvel <ard.biesheuvel@linaro.org>

commit 5ea5306c323 upstream.

One important rule of thumb when desiging a secure software system is
that memory should never be writable and executable at the same time.
We mostly adhere to this rule in the kernel, except at boot time, when
regions may be mapped RWX until after we are done applying alternatives
or making other one-off changes.

For the alternative patching, we can improve the situation by applying
the fixups via the linear mapping, which is never mapped with executable
permissions. So map the linear alias of .text with RW- permissions
initially, and remove the write permissions as soon as alternative
patching has completed.

Reviewed-by: Laura Abbott <labbott@redhat.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	replace update_mapping_prot with old create_mapping_late
	arch/arm64/mm/mmu.c
---
 arch/arm64/include/asm/mmu.h    |  1 +
 arch/arm64/kernel/alternative.c | 11 ++++++-----
 arch/arm64/kernel/smp.c         |  1 +
 arch/arm64/mm/mmu.c             | 22 +++++++++++++++++-----
 4 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 8d9fce0..b075140 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -36,5 +36,6 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot, bool allow_block_mappings);
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
+extern void mark_linear_text_alias_ro(void);
 
 #endif
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 06d650f..8840c10 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -105,11 +105,11 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 	return insn;
 }
 
-static void __apply_alternatives(void *alt_region)
+static void __apply_alternatives(void *alt_region, bool use_linear_alias)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
-	u32 *origptr, *replptr;
+	u32 *origptr, *replptr, *updptr;
 
 	for (alt = region->begin; alt < region->end; alt++) {
 		u32 insn;
@@ -124,11 +124,12 @@ static void __apply_alternatives(void *alt_region)
 
 		origptr = ALT_ORIG_PTR(alt);
 		replptr = ALT_REPL_PTR(alt);
+		updptr = use_linear_alias ? (u32 *)lm_alias(origptr) : origptr;
 		nr_inst = alt->alt_len / sizeof(insn);
 
 		for (i = 0; i < nr_inst; i++) {
 			insn = get_alt_insn(alt, origptr + i, replptr + i);
-			*(origptr + i) = cpu_to_le32(insn);
+			updptr[i] = cpu_to_le32(insn);
 		}
 
 		flush_icache_range((uintptr_t)origptr,
@@ -155,7 +156,7 @@ static int __apply_alternatives_multi_stop(void *unused)
 		isb();
 	} else {
 		BUG_ON(patched);
-		__apply_alternatives(&region);
+		__apply_alternatives(&region, true);
 		/* Barriers provided by the cache flushing */
 		WRITE_ONCE(patched, 1);
 	}
@@ -176,5 +177,5 @@ void apply_alternatives(void *start, size_t length)
 		.end	= start + length,
 	};
 
-	__apply_alternatives(&region);
+	__apply_alternatives(&region, false);
 }
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a70f7d3..66db515 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -426,6 +426,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	setup_cpu_features();
 	hyp_mode_check();
 	apply_alternatives_all();
+	mark_linear_text_alias_ro();
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index d5cc6d7..5dc72c0 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -354,16 +354,28 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end
 				     !debug_pagealloc_enabled());
 
 	/*
-	 * Map the linear alias of the [_text, __init_begin) interval as
-	 * read-only/non-executable. This makes the contents of the
-	 * region accessible to subsystems such as hibernate, but
-	 * protects it from inadvertent modification or execution.
+	 * Map the linear alias of the [_text, __init_begin) interval
+	 * as non-executable now, and remove the write permission in
+	 * mark_linear_text_alias_ro() below (which will be called after
+	 * alternative patching has completed). This makes the contents
+	 * of the region accessible to subsystems such as hibernate,
+	 * but protects it from inadvertent modification or execution.
 	 */
 	__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
-			     kernel_end - kernel_start, PAGE_KERNEL_RO,
+			     kernel_end - kernel_start, PAGE_KERNEL,
 			     early_pgtable_alloc, !debug_pagealloc_enabled());
 }
 
+void __init mark_linear_text_alias_ro(void)
+{
+	/*
+	 * Remove the write permissions from the linear alias of .text/.rodata
+	 */
+	create_mapping_late(__pa_symbol(_text), (unsigned long)lm_alias(_text),
+			    (unsigned long)__init_begin - (unsigned long)_text,
+			    PAGE_KERNEL_RO);
+}
+
 static void __init map_mem(pgd_t *pgd)
 {
 	struct memblock_region *reg;
-- 
2.7.4

[PATCH 03/52] arm64: barrier: Add CSDB macros to control data-value prediction

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 669474e772b9 upstream.

For CPUs capable of data value prediction, CSDB waits for any outstanding
predictions to architecturally resolve before allowing speculative execution
to continue. Provide macros to expose it to the arch code.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	arch/arm64/include/asm/assembler.h
	no psb_csync in arch/arm64/include/asm/barrier.h
---
 arch/arm64/include/asm/assembler.h | 7 +++++++
 arch/arm64/include/asm/barrier.h   | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 851290d..8760300 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -87,6 +87,13 @@
 	.endm
 
 /*
+ * Value prediction barrier
+ */
+	.macro	csdb
+	hint	#20
+	.endm
+
+/*
  * NOP sequence
  */
 	.macro	nops, num
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 0fe7e43..c68fdc5 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -31,6 +31,8 @@
 #define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
+#define csdb()		asm volatile("hint #20" : : : "memory")
+
 #define mb()		dsb(sy)
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
-- 
2.7.4

[PATCH 04/52] arm64: Implement array_index_mask_nospec()

[Alex Shi]

From: Robin Murphy <robin.murphy@arm.com>

commit 022620eed3d0 upstream.

Provide an optimised, assembly implementation of array_index_mask_nospec()
for arm64 so that the compiler is not in a position to transform the code
in ways which affect its ability to inhibit speculation (e.g. by introducing
conditional branches).

This is similar to the sequence used by x86, modulo architectural differences
in the carry/borrow flags.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/barrier.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index c68fdc5..0b0755c 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -40,6 +40,27 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+/*
+ * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
+ * and 0 otherwise.
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+						    unsigned long sz)
+{
+	unsigned long mask;
+
+	asm volatile(
+	"	cmp	%1, %2\n"
+	"	sbc	%0, xzr, xzr\n"
+	: "=r" (mask)
+	: "r" (idx), "Ir" (sz)
+	: "cc");
+
+	csdb();
+	return mask;
+}
+
 #define __smp_mb()	dmb(ish)
 #define __smp_rmb()	dmb(ishld)
 #define __smp_wmb()	dmb(ishst)
-- 
2.7.4

[PATCH 05/52] arm64: move TASK_* definitions to <asm/processor.h>

[Alex Shi]

From: Yury Norov <ynorov@caviumnetworks.com>

commit eef94a3d09aab upstream.

ILP32 series [1] introduces the dependency on <asm/is_compat.h> for
TASK_SIZE macro. Which in turn requires <asm/thread_info.h>, and
<asm/thread_info.h> include <asm/memory.h>, giving a circular dependency,
because TASK_SIZE is currently located in <asm/memory.h>.

In other architectures, TASK_SIZE is defined in <asm/processor.h>, and
moving TASK_SIZE there fixes the problem.

Discussion: https://patchwork.kernel.org/patch/9929107/

[1] https://github.com/norov/linux/tree/ilp32-next

CC: Will Deacon <will.deacon@arm.com>
CC: Laura Abbott <labbott@redhat.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yury Norov <ynorov@caviumnetworks.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no ptrace.h in arch/arm64/kernel/entry.S
---
 arch/arm64/include/asm/memory.h    | 15 ---------------
 arch/arm64/include/asm/processor.h | 21 +++++++++++++++++++++
 arch/arm64/kernel/entry.S          |  2 +-
 3 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 53211a0..269b979 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -60,8 +60,6 @@
  * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
- * TASK_SIZE - the maximum size of a user space task.
- * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define VA_START		(UL(0xffffffffffffffff) << VA_BITS)
@@ -74,19 +72,6 @@
 #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)
-#define TASK_SIZE_64		(UL(1) << VA_BITS)
-
-#ifdef CONFIG_COMPAT
-#define TASK_SIZE_32		UL(0x100000000)
-#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
-				TASK_SIZE_32 : TASK_SIZE_64)
-#else
-#define TASK_SIZE		TASK_SIZE_64
-#endif /* CONFIG_COMPAT */
-
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
 
 #define KERNEL_START      _text
 #define KERNEL_END        _end
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 60e3482..4258f4d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -19,6 +19,10 @@
 #ifndef __ASM_PROCESSOR_H
 #define __ASM_PROCESSOR_H
 
+#define TASK_SIZE_64		(UL(1) << VA_BITS)
+
+#ifndef __ASSEMBLY__
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -37,6 +41,22 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
+/*
+ * TASK_SIZE - the maximum size of a user space task.
+ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
+ */
+#ifdef CONFIG_COMPAT
+#define TASK_SIZE_32		UL(0x100000000)
+#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#else
+#define TASK_SIZE		TASK_SIZE_64
+#endif /* CONFIG_COMPAT */
+
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
+
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
@@ -192,4 +212,5 @@ int cpu_enable_pan(void *__unused);
 int cpu_enable_uao(void *__unused);
 int cpu_enable_cache_maint_trap(void *__unused);
 
+#endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b4c7db4..478f0fe 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,7 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
-#include <asm/memory.h>
+#include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
-- 
2.7.4

[PATCH 06/52] arm64: Factor out PAN enabling/disabling into separate uaccess_* macros

[Alex Shi]

From: Catalin Marinas <catalin.marinas@arm.com>

commit bd38967d406 upstream.

This patch moves the directly coded alternatives for turning PAN on/off
into separate uaccess_{enable,disable} macros or functions. The asm
macros take a few arguments which will be used in subsequent patches.

Note that any (unlikely) access that the compiler might generate between
uaccess_enable() and uaccess_disable(), other than those explicitly
specified by the user access code, will not be protected by PAN.

Cc: Will Deacon <will.deacon@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Kees Cook <keescook@chromium.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/futex.h       | 17 ++++----
 arch/arm64/include/asm/uaccess.h     | 79 +++++++++++++++++++++++++++++++-----
 arch/arm64/kernel/armv8_deprecated.c | 11 +++--
 arch/arm64/lib/clear_user.S          | 11 ++---
 arch/arm64/lib/copy_from_user.S      | 11 ++---
 arch/arm64/lib/copy_in_user.S        | 11 ++---
 arch/arm64/lib/copy_to_user.S        | 11 ++---
 7 files changed, 93 insertions(+), 58 deletions(-)

diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index f2585cd..85c4a89 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -21,15 +21,12 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 
-#include <asm/alternative.h>
-#include <asm/cpufeature.h>
 #include <asm/errno.h>
-#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
+do {									\
+	uaccess_enable();						\
 	asm volatile(							\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
@@ -44,11 +41,11 @@
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "memory")
+	: "memory");							\
+	uaccess_disable();						\
+} while (0)
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -118,8 +115,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	uaccess_enable();
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -134,10 +131,10 @@ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	.popsection\n"
 	_ASM_EXTABLE(1b, 4b)
 	_ASM_EXTABLE(2b, 4b)
-ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
+	uaccess_disable();
 
 	*uval = val;
 	return ret;
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 811cf16..94e1457 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -18,6 +18,11 @@
 #ifndef __ASM_UACCESS_H
 #define __ASM_UACCESS_H
 
+#include <asm/alternative.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
 /*
  * User space memory access functions
  */
@@ -26,10 +31,8 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/ptrace.h>
-#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -121,6 +124,44 @@ static inline void set_fs(mm_segment_t fs)
 	"	.popsection\n"
 
 /*
+ * User access enabling/disabling.
+ */
+#define __uaccess_disable(alt)						\
+do {									\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt,			\
+			CONFIG_ARM64_PAN));				\
+} while (0)
+
+#define __uaccess_enable(alt)						\
+do {									\
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt,			\
+			CONFIG_ARM64_PAN));				\
+} while (0)
+
+static inline void uaccess_disable(void)
+{
+	__uaccess_disable(ARM64_HAS_PAN);
+}
+
+static inline void uaccess_enable(void)
+{
+	__uaccess_enable(ARM64_HAS_PAN);
+}
+
+/*
+ * These functions are no-ops when UAO is present.
+ */
+static inline void uaccess_disable_not_uao(void)
+{
+	__uaccess_disable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+static inline void uaccess_enable_not_uao(void)
+{
+	__uaccess_enable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+/*
  * The "__xxx" versions of the user access functions do not verify the address
  * space - it must have been done previously with a separate "access_ok()"
  * call.
@@ -147,8 +188,7 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr),  \
@@ -169,9 +209,8 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
+	uaccess_disable_not_uao();					\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __get_user(x, ptr)						\
@@ -216,8 +255,7 @@ do {									\
 do {									\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr),	\
@@ -238,8 +276,7 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_disable_not_uao();					\
 } while (0)
 
 #define __put_user(x, ptr)						\
@@ -332,4 +369,26 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+#else	/* __ASSEMBLY__ */
+
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros. These are no-ops when UAO is
+ * present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif	/* __ASSEMBLY__ */
+
 #endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index c0ede23..29d2ad8 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -14,7 +14,6 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/insn.h>
 #include <asm/opcodes.h>
@@ -285,10 +284,10 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 #define __SWP_LL_SC_LOOPS	4
 
 #define __user_swpX_asm(data, addr, res, temp, temp2, B)	\
+do {								\
+	uaccess_enable();					\
 	__asm__ __volatile__(					\
 	"	mov		%w3, %w7\n"			\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
-		    CONFIG_ARM64_PAN)				\
 	"0:	ldxr"B"		%w2, [%4]\n"			\
 	"1:	stxr"B"		%w0, %w1, [%4]\n"		\
 	"	cbz		%w0, 2f\n"			\
@@ -306,13 +305,13 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 	"	.popsection"					\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
-		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
 	: "r" ((unsigned long)addr), "i" (-EAGAIN),		\
 	  "i" (-EFAULT),					\
 	  "i" (__SWP_LL_SC_LOOPS)				\
-	: "memory")
+	: "memory");						\
+	uaccess_disable();					\
+} while (0)
 
 #define __user_swp_asm(data, addr, res, temp, temp2) \
 	__user_swpX_asm(data, addr, res, temp, temp2, "")
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 5d1cad3..d7150e3 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,10 +17,7 @@
  */
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 	.text
 
@@ -33,8 +30,7 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x2, x3
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -54,8 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x2
 	ret
 ENDPROC(__clear_user)
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 4fd67ea..cfe1339 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -16,11 +16,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -67,12 +64,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_from_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index f7292dd0..718b1c4 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -18,11 +18,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
@@ -68,12 +65,10 @@
 
 end	.req	x5
 ENTRY(__copy_in_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0
 	ret
 ENDPROC(__copy_in_user)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 7a7efe2..e99e31c 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -16,11 +16,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -66,12 +63,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_to_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
-- 
2.7.4

[PATCH 07/52] arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro

[Alex Shi]

From: Catalin Marinas <catalin.marinas@arm.com>

commit f33bcf03e6 upstream

This patch takes the errata workaround code out of cpu_do_switch_mm into
a dedicated post_ttbr0_update_workaround macro which will be reused in a
subsequent patch.

Cc: Will Deacon <will.deacon@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Kees Cook <keescook@chromium.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/assembler.h | 13 +++++++++++++
 arch/arm64/mm/proc.S               |  6 +-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 8760300..ab3a179 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -420,4 +420,17 @@ alternative_endif
 	movk	\reg, :abs_g0_nc:\val
 	.endm
 
+/*
+ * Errata workaround post TTBR0_EL1 update.
+ */
+	.macro	post_ttbr0_update_workaround
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
+	ic	iallu
+	dsb	nsh
+	isb
+alternative_else_nop_endif
+#endif
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 352c73b..c2adb0c 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -136,11 +136,7 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
-	ic	iallu
-	dsb	nsh
-	isb
-alternative_else_nop_endif
+	post_ttbr0_update_workaround
 	ret
 ENDPROC(cpu_do_switch_mm)
 
-- 
2.7.4

[PATCH 08/52] arm64: uaccess: consistently check object sizes

[Alex Shi]

From: Mark Rutland <mark.rutland@arm.com>

commit 76624175dca upstream.

Currently in arm64's copy_{to,from}_user, we only check the
source/destination object size if access_ok() tells us the user access
is permissible.

However, in copy_from_user() we'll subsequently zero any remainder on
the destination object. If we failed the access_ok() check, that applies
to the whole object size, which we didn't check.

To ensure that we catch that case, this patch hoists check_object_size()
to the start of copy_from_user(), matching __copy_from_user() and
__copy_to_user(). To make all of our uaccess copy primitives consistent,
the same is done to copy_to_user().

Cc: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/uaccess.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 94e1457..09c9b59 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -326,9 +326,9 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u
 {
 	unsigned long res = n;
 	kasan_check_write(to, n);
+	check_object_size(to, n, false);
 
 	if (access_ok(VERIFY_READ, from, n)) {
-		check_object_size(to, n, false);
 		res = __arch_copy_from_user(to, from, n);
 	}
 	if (unlikely(res))
@@ -339,9 +339,9 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u
 static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	kasan_check_read(from, n);
+	check_object_size(from, n, true);
 
 	if (access_ok(VERIFY_WRITE, to, n)) {
-		check_object_size(from, n, true);
 		n = __arch_copy_to_user(to, from, n);
 	}
 	return n;
-- 
2.7.4

[PATCH 09/52] arm64: Make USER_DS an inclusive limit

[Alex Shi]

From: Robin Murphy <robin.murphy@arm.com>

commit 51369e398d0d upstream.

Currently, USER_DS represents an exclusive limit while KERNEL_DS is
inclusive. In order to do some clever trickery for speculation-safe
masking, we need them both to behave equivalently - there aren't enough
bits to make KERNEL_DS exclusive, so we have precisely one option. This
also happens to correct a longstanding false negative for a range
ending on the very top byte of kernel memory.

Mark Rutland points out that we've actually got the semantics of
addresses vs. segments muddled up in most of the places we need to
amend, so shuffle the {USER,KERNEL}_DS definitions around such that we
can correct those properly instead of just pasting "-1"s everywhere.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
(cherry picked from commit 83b20dff71ea949431cf57c6aebaaf7ebd5c1991)
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	force replace __range_ok and add asm/processor.h
	in arch/arm64/include/asm/uaccess.h
	using old macro TI_ADDR_LIMIT instead of TSK_TI_ADDR_LIMIT
	in arch/arm64/kernel/entry.S
	manual change USER_DS to TASK_SIZE in arch/arm64/mm/fault.c
---
 arch/arm64/include/asm/processor.h |  3 +++
 arch/arm64/include/asm/uaccess.h   | 46 ++++++++++++++++++++++----------------
 arch/arm64/kernel/entry.S          |  2 +-
 arch/arm64/mm/fault.c              |  2 +-
 4 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 4258f4d..5917147 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -21,6 +21,9 @@
 
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
+#define KERNEL_DS	UL(-1)
+#define USER_DS		(TASK_SIZE_64 - 1)
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 09c9b59..7b1eb49 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -36,6 +36,7 @@
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
+#include <asm/processor.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
@@ -62,10 +63,7 @@ struct exception_table_entry
 
 extern int fixup_exception(struct pt_regs *regs);
 
-#define KERNEL_DS	(-1UL)
 #define get_ds()	(KERNEL_DS)
-
-#define USER_DS		TASK_SIZE_64
 #define get_fs()	(current_thread_info()->addr_limit)
 
 static inline void set_fs(mm_segment_t fs)
@@ -90,22 +88,32 @@ static inline void set_fs(mm_segment_t fs)
  * Returns 1 if the range is valid, 0 otherwise.
  *
  * This is equivalent to the following test:
- * (u65)addr + (u65)size <= current->addr_limit
- *
- * This needs 65-bit arithmetic.
+ * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
  */
-#define __range_ok(addr, size)						\
-({									\
-	unsigned long __addr = (unsigned long __force)(addr);		\
-	unsigned long flag, roksum;					\
-	__chk_user_ptr(addr);						\
-	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
-		: "=&r" (flag), "=&r" (roksum)				\
-		: "1" (__addr), "Ir" (size),				\
-		  "r" (current_thread_info()->addr_limit)		\
-		: "cc");						\
-	flag;								\
-})
+static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
+{
+	unsigned long limit = current_thread_info()->addr_limit;
+
+	__chk_user_ptr(addr);
+	asm volatile(
+	// A + B <= C + 1 for all A,B,C, in four easy steps:
+	// 1: X = A + B; X' = X % 2^64
+	"	adds	%0, %0, %2\n"
+	// 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
+	"	csel	%1, xzr, %1, hi\n"
+	// 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
+	//    to compensate for the carry flag being set in step 4. For
+	//    X > 2^64, X' merely has to remain nonzero, which it does.
+	"	csinv	%0, %0, xzr, cc\n"
+	// 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1
+	//    comes from the carry in being clear. Otherwise, we are
+	//    testing X' - C == 0, subject to the previous adjustments.
+	"	sbcs	xzr, %0, %1\n"
+	"	cset	%0, ls\n"
+	: "+r" (addr), "+r" (limit) : "Ir" (size) : "cc");
+
+	return addr;
+}
 
 /*
  * When dealing with data aborts, watchpoints, or instruction traps we may end
@@ -114,7 +122,7 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define untagged_addr(addr)		sign_extend64(addr, 55)
 
-#define access_ok(type, addr, size)	__range_ok(addr, size)
+#define access_ok(type, addr, size)	__range_ok((unsigned long)(addr), size)
 #define user_addr_max			get_fs
 
 #define _ASM_EXTABLE(from, to)						\
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 478f0fe..6915697 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -103,7 +103,7 @@
 	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
 	ldr	x20, [tsk, #TI_ADDR_LIMIT]
 	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
-	mov	x20, #TASK_SIZE_64
+	mov	x20, #USER_DS
 	str	x20, [tsk, #TI_ADDR_LIMIT]
 	/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
 	.endif /* \el == 0 */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 403fe9e..4df70c9 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -332,7 +332,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
-	if (is_permission_fault(esr) && (addr < USER_DS)) {
+	if (is_permission_fault(esr) && (addr < TASK_SIZE)) {
 		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
-- 
2.7.4

[PATCH 10/52] arm64: Use pointer masking to limit uaccess speculation

[Alex Shi]

From: Robin Murphy <robin.murphy@arm.com>

commit 4d8efc2d5ee4 upstream.

Similarly to x86, mitigate speculation past an access_ok() check by
masking the pointer against the address limit before use.

Even if we don't expect speculative writes per se, it is plausible that
a CPU may still speculate at least as far as fetching a cache line for
writing, hence we also harden put_user() and clear_user() for peace of
mind.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/uaccess.h | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 7b1eb49..3531fec 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -170,6 +170,26 @@ static inline void uaccess_enable_not_uao(void)
 }
 
 /*
+ * Sanitise a uaccess pointer such that it becomes NULL if above the
+ * current addr_limit.
+ */
+#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
+static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
+{
+	void __user *safe_ptr;
+
+	asm volatile(
+	"	bics	xzr, %1, %2\n"
+	"	csel	%0, %1, xzr, eq\n"
+	: "=&r" (safe_ptr)
+	: "r" (ptr), "r" (current_thread_info()->addr_limit)
+	: "cc");
+
+	csdb();
+	return safe_ptr;
+}
+
+/*
  * The "__xxx" versions of the user access functions do not verify the address
  * space - it must have been done previously with a separate "access_ok()"
  * call.
@@ -241,7 +261,7 @@ do {									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
 	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
-		__get_user((x), __p) :					\
+		__p = uaccess_mask_ptr(__p), __get_user((x), __p) :	\
 		((x) = 0, -EFAULT);					\
 })
 
@@ -307,7 +327,7 @@ do {									\
 	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
 	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
-		__put_user((x), __p) :					\
+		__p = uaccess_mask_ptr(__p), __put_user((x), __p) :	\
 		-EFAULT;						\
 })
 
@@ -368,7 +388,7 @@ static inline unsigned long __must_check copy_in_user(void __user *to, const voi
 static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	if (access_ok(VERIFY_WRITE, to, n))
-		n = __clear_user(to, n);
+		n = __clear_user(__uaccess_mask_ptr(to), n);
 	return n;
 }
 
-- 
2.7.4

[PATCH 11/52] arm64: syscallno is secretly an int, make it official

[Alex Shi]

From: Dave Martin <Dave.Martin@arm.com>

commit 35d0e6fb4d upstream.

The upper 32 bits of the syscallno field in thread_struct are
handled inconsistently, being sometimes zero extended and sometimes
sign-extended.  In fact, only the lower 32 bits seem to have any
real significance for the behaviour of the code: it's been OK to
handle the upper bits inconsistently because they don't matter.

Currently, the only place I can find where those bits are
significant is in calling trace_sys_enter(), which may be
unintentional: for example, if a compat tracer attempts to cancel a
syscall by passing -1 to (COMPAT_)PTRACE_SET_SYSCALL at the
syscall-enter-stop, it will be traced as syscall 4294967295
rather than -1 as might be expected (and as occurs for a native
tracer doing the same thing).  Elsewhere, reads of syscallno cast
it to an int or truncate it.

There's also a conspicuous amount of code and casting to bodge
around the fact that although semantically an int, syscallno is
stored as a u64.

Let's not pretend any more.

In order to preserve the stp x instruction that stores the syscall
number in entry.S, this patch special-cases the layout of struct
pt_regs for big endian so that the newly 32-bit syscallno field
maps onto the low bits of the stored value.  This is not beautiful,
but benchmarking of the getpid syscall on Juno suggests indicates a
minor slowdown if the stp is split into an stp x and stp w.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/processor.h |  2 +-
 arch/arm64/include/asm/ptrace.h    |  9 ++++++++-
 arch/arm64/kernel/entry.S          | 34 +++++++++++++++++-----------------
 arch/arm64/kernel/ptrace.c         |  2 +-
 arch/arm64/kernel/signal.c         |  6 +++---
 arch/arm64/kernel/signal32.c       |  2 +-
 arch/arm64/kernel/traps.c          |  2 +-
 7 files changed, 32 insertions(+), 25 deletions(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5917147..f5cdda6 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -130,7 +130,7 @@ struct thread_struct {
 static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
 {
 	memset(regs, 0, sizeof(*regs));
-	regs->syscallno = ~0UL;
+	regs->syscallno = ~0;
 	regs->pc = pc;
 }
 
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ada08b5..7721d7a 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -116,7 +116,14 @@ struct pt_regs {
 		};
 	};
 	u64 orig_x0;
-	u64 syscallno;
+#ifdef __AARCH64EB__
+	u32 unused2;
+	s32 syscallno;
+#else
+	s32 syscallno;
+	u32 unused2;
+#endif
+
 	u64 orig_addr_limit;
 	u64 unused;	// maintain 16 byte alignment
 };
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6915697..48c41ff 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -116,8 +116,8 @@
 	 * Set syscallno to -1 by default (overridden later if real syscall).
 	 */
 	.if	\el == 0
-	mvn	x21, xzr
-	str	x21, [sp, #S_SYSCALLNO]
+	mvn	w21, wzr
+	str	w21, [sp, #S_SYSCALLNO]
 	.endif
 
 	/*
@@ -232,8 +232,9 @@ alternative_else_nop_endif
  *
  * x7 is reserved for the system call number in 32-bit mode.
  */
-sc_nr	.req	x25		// number of system calls
-scno	.req	x26		// syscall number
+wsc_nr	.req	w25		// number of system calls
+wscno	.req	w26		// syscall number
+xscno	.req	x26		// syscall number (zero-extended)
 stbl	.req	x27		// syscall table pointer
 tsk	.req	x28		// current thread_info
 
@@ -519,8 +520,8 @@ el0_svc_compat:
 	 * AArch32 syscall handling
 	 */
 	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
-	uxtw	scno, w7			// syscall number in w7 (r7)
-	mov     sc_nr, #__NR_compat_syscalls
+	mov	wscno, w7			// syscall number in w7 (r7)
+	mov     wsc_nr, #__NR_compat_syscalls
 	b	el0_svc_naked
 
 	.align	6
@@ -741,19 +742,19 @@ ENDPROC(ret_from_fork)
 	.align	6
 el0_svc:
 	adrp	stbl, sys_call_table		// load syscall table pointer
-	uxtw	scno, w8			// syscall number in w8
-	mov	sc_nr, #__NR_syscalls
+	mov	wscno, w8			// syscall number in w8
+	mov	wsc_nr, #__NR_syscalls
 el0_svc_naked:					// compat entry point
-	stp	x0, scno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
+	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
 	enable_dbg_and_irq
 	ct_user_exit 1
 
 	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
 	tst	x16, #_TIF_SYSCALL_WORK
 	b.ne	__sys_trace
-	cmp     scno, sc_nr                     // check upper syscall limit
+	cmp     wscno, wsc_nr			// check upper syscall limit
 	b.hs	ni_sys
-	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
+	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
 	blr	x16				// call sys_* routine
 	b	ret_fast_syscall
 ni_sys:
@@ -767,24 +768,23 @@ ENDPROC(el0_svc)
 	 * switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	w0, #-1				// set default errno for
-	cmp     scno, x0			// user-issued syscall(-1)
+	cmp     wscno, #-1			// user-issued syscall(-1)?
 	b.ne	1f
-	mov	x0, #-ENOSYS
+	mov	x0, #-ENOSYS			// set default errno if so
 	str	x0, [sp, #S_X0]
 1:	mov	x0, sp
 	bl	syscall_trace_enter
 	cmp	w0, #-1				// skip the syscall?
 	b.eq	__sys_trace_return_skipped
-	uxtw	scno, w0			// syscall number (possibly new)
+	mov	wscno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
-	cmp	scno, sc_nr			// check upper syscall limit
+	cmp	wscno, wsc_nr			// check upper syscall limit
 	b.hs	__ni_sys_trace
 	ldp	x0, x1, [sp]			// restore the syscall args
 	ldp	x2, x3, [sp, #S_X2]
 	ldp	x4, x5, [sp, #S_X4]
 	ldp	x6, x7, [sp, #S_X6]
-	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
+	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
 	blr	x16				// call sys_* routine
 
 __sys_trace_return:
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 8eedeef..193c621 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1346,7 +1346,7 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	if (dir == PTRACE_SYSCALL_EXIT)
 		tracehook_report_syscall_exit(regs, 0);
 	else if (tracehook_report_syscall_entry(regs))
-		regs->syscallno = ~0UL;
+		regs->syscallno = ~0;
 
 	regs->regs[regno] = saved_reg;
 }
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 404dd67..fd7eba8 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -113,7 +113,7 @@ static int restore_sigframe(struct pt_regs *regs,
 	/*
 	 * Avoid sys_rt_sigreturn() restarting.
 	 */
-	regs->syscallno = ~0UL;
+	regs->syscallno = ~0;
 
 	err |= !valid_user_regs(&regs->user_regs, current);
 
@@ -332,7 +332,7 @@ static void do_signal(struct pt_regs *regs)
 {
 	unsigned long continue_addr = 0, restart_addr = 0;
 	int retval = 0;
-	int syscall = (int)regs->syscallno;
+	int syscall = regs->syscallno;
 	struct ksignal ksig;
 
 	/*
@@ -346,7 +346,7 @@ static void do_signal(struct pt_regs *regs)
 		/*
 		 * Avoid additional syscall restarting via ret_to_user.
 		 */
-		regs->syscallno = ~0UL;
+		regs->syscallno = ~0;
 
 		/*
 		 * Prepare for system call restart. We do this here so that a
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index b7063de..1effea2 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -354,7 +354,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	/*
 	 * Avoid compat_sys_sigreturn() restarting.
 	 */
-	regs->syscallno = ~0UL;
+	regs->syscallno = ~0;
 
 	err |= !valid_user_regs(&regs->user_regs, current);
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c743d1f..59f80b0 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -541,7 +541,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 
 	if (show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: syscall %d\n", current->comm,
-			task_pid_nr(current), (int)regs->syscallno);
+			task_pid_nr(current), regs->syscallno);
 		dump_instr("", regs);
 		if (user_mode(regs))
 			__show_regs(regs);
-- 
2.7.4

[PATCH 12/52] arm64: entry: Ensure branch through syscall table is bounded under speculation

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 6314d90e6493 upstream.

In a similar manner to array_index_mask_nospec, this patch introduces an
assembly macro (mask_nospec64) which can be used to bound a value under
speculation. This macro is then used to ensure that the indirect branch
through the syscall table is bounded under speculation, with out-of-range
addresses speculating as calls to sys_io_setup (0).

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/assembler.h | 11 +++++++++++
 arch/arm64/kernel/entry.S          |  2 ++
 2 files changed, 13 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ab3a179..a109d30 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -94,6 +94,17 @@
 	.endm
 
 /*
+ * Sanitise a 64-bit bounded index wrt speculation, returning zero if out
+ * of bounds.
+ */
+	.macro	mask_nospec64, idx, limit, tmp
+	sub	\tmp, \idx, \limit
+	bic	\tmp, \tmp, \idx
+	and	\idx, \idx, \tmp, asr #63
+	csdb
+	.endm
+
+/*
  * NOP sequence
  */
 	.macro	nops, num
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 48c41ff..0a27e12 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -233,6 +233,7 @@ alternative_else_nop_endif
  * x7 is reserved for the system call number in 32-bit mode.
  */
 wsc_nr	.req	w25		// number of system calls
+xsc_nr	.req	x25		// number of system calls (zero-extended)
 wscno	.req	w26		// syscall number
 xscno	.req	x26		// syscall number (zero-extended)
 stbl	.req	x27		// syscall table pointer
@@ -754,6 +755,7 @@ el0_svc_naked:					// compat entry point
 	b.ne	__sys_trace
 	cmp     wscno, wsc_nr			// check upper syscall limit
 	b.hs	ni_sys
+	mask_nospec64 xscno, xsc_nr, x19	// enforce bounds for syscall number
 	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
 	blr	x16				// call sys_* routine
 	b	ret_fast_syscall
-- 
2.7.4

[PATCH 13/52] arm64: uaccess: Prevent speculative use of the current addr_limit

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit c2f0ad4fc089 upstream.

A mispredicted conditional call to set_fs could result in the wrong
addr_limit being forwarded under speculation to a subsequent access_ok
check, potentially forming part of a spectre-v1 attack using uaccess
routines.

This patch prevents this forwarding from taking place, but putting heavy
barriers in set_fs after writing the addr_limit.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no set_thread_flag(TIF_FSCHECK) in arch/arm64/include/asm/uaccess.h
---
 arch/arm64/include/asm/uaccess.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 3531fec..00025c5 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -71,6 +71,13 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 
 	/*
+	 * Prevent a mispredicted conditional call to set_fs from forwarding
+	 * the wrong address limit to access_ok under speculation.
+	 */
+	dsb(nsh);
+	isb();
+
+	/*
 	 * Enable/disable UAO so that copy_to_user() etc can access
 	 * kernel memory with the unprivileged instructions.
 	 */
-- 
2.7.4

[PATCH 14/52] arm64: uaccess: Don't bother eliding access_ok checks in __{get, put}_user

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 84624087dd7e upstream.

access_ok isn't an expensive operation once the addr_limit for the current
thread has been loaded into the cache. Given that the initial access_ok
check preceding a sequence of __{get,put}_user operations will take
the brunt of the miss, we can make the __* variants identical to the
full-fat versions, which brings with it the benefits of address masking.

The likely cost in these sequences will be from toggling PAN/UAO, which
we can address later by implementing the *_unsafe versions.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	keep __{get/put}_user_unaligned in arch/arm64/include/asm/uaccess.h
---
 arch/arm64/include/asm/uaccess.h | 54 ++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 00025c5..ffa4e39 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -248,30 +248,35 @@ do {									\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 } while (0)
 
-#define __get_user(x, ptr)						\
+#define __get_user_check(x, ptr, err)					\
 ({									\
-	int __gu_err = 0;						\
-	__get_user_err((x), (ptr), __gu_err);				\
-	__gu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_READ, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__get_user_err((x), __p, (err));			\
+	} else {							\
+		(x) = 0; (err) = -EFAULT;				\
+	}								\
 })
 
 #define __get_user_error(x, ptr, err)					\
 ({									\
-	__get_user_err((x), (ptr), (err));				\
+	__get_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
 #define __get_user_unaligned __get_user
 
-#define get_user(x, ptr)						\
+#define __get_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __get_user((x), __p) :	\
-		((x) = 0, -EFAULT);					\
+	int __gu_err = 0;						\
+	__get_user_check((x), (ptr), __gu_err);				\
+	__gu_err;							\
 })
 
+#define get_user	__get_user
+
 #define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature)	\
 	asm volatile(							\
 	"1:"ALTERNATIVE(instr "     " reg "1, [%2]\n",			\
@@ -314,30 +319,35 @@ do {									\
 	uaccess_disable_not_uao();					\
 } while (0)
 
-#define __put_user(x, ptr)						\
+#define __put_user_check(x, ptr, err)					\
 ({									\
-	int __pu_err = 0;						\
-	__put_user_err((x), (ptr), __pu_err);				\
-	__pu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__put_user_err((x), __p, (err));			\
+	} else	{							\
+		(err) = -EFAULT;					\
+	}								\
 })
 
 #define __put_user_error(x, ptr, err)					\
 ({									\
-	__put_user_err((x), (ptr), (err));				\
+	__put_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
 #define __put_user_unaligned __put_user
 
-#define put_user(x, ptr)						\
+#define __put_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __put_user((x), __p) :	\
-		-EFAULT;						\
+	int __pu_err = 0;						\
+	__put_user_check((x), (ptr), __pu_err);				\
+	__pu_err;							\
 })
 
+#define put_user	__put_user
+
 extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
 extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
 extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
-- 
2.7.4

[PATCH 15/52] arm64: uaccess: Mask __user pointers for __arch_{clear, copy_*}_user

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

Rewritting from commit f71c2ffcb20d upstream. On LTS 4.9, there has no
raw_copy_from/to_user, neither __copy_user_flushcache, and it isn't good
idead to pick up them. The following is origin commit log, that's also
applicable for the new patch.

    Like we've done for get_user and put_user, ensure that user pointers
    are masked before invoking the underlying __arch_{clear,copy_*}_user
    operations.

    Signed-off-by: Will Deacon <will.deacon@arm.com>
    Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/uaccess.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index ffa4e39..fbf4ce4 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -357,14 +357,14 @@ static inline unsigned long __must_check __copy_from_user(void *to, const void _
 {
 	kasan_check_write(to, n);
 	check_object_size(to, n, false);
-	return __arch_copy_from_user(to, from, n);
+	return __arch_copy_from_user(to, __uaccess_mask_ptr(from), n);
 }
 
 static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	kasan_check_read(from, n);
 	check_object_size(from, n, true);
-	return __arch_copy_to_user(to, from, n);
+	return __arch_copy_to_user(__uaccess_mask_ptr(to), from, n);
 }
 
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
@@ -374,7 +374,7 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u
 	check_object_size(to, n, false);
 
 	if (access_ok(VERIFY_READ, from, n)) {
-		res = __arch_copy_from_user(to, from, n);
+		res = __arch_copy_from_user(to, __uaccess_mask_ptr(from), n);
 	}
 	if (unlikely(res))
 		memset(to + (n - res), 0, res);
@@ -387,7 +387,7 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const voi
 	check_object_size(from, n, true);
 
 	if (access_ok(VERIFY_WRITE, to, n)) {
-		n = __arch_copy_to_user(to, from, n);
+		n = __arch_copy_to_user(__uaccess_mask_ptr(to), from, n);
 	}
 	return n;
 }
@@ -395,7 +395,7 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const voi
 static inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n))
-		n = __copy_in_user(to, from, n);
+		n = __copy_in_user(__uaccess_mask_ptr(to), __uaccess_mask_ptr(from), n);
 	return n;
 }
 
-- 
2.7.4

[PATCH 16/52] arm64: futex: Mask __user pointers prior to dereference

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 91b2d3442f6a upstream.

The arm64 futex code has some explicit dereferencing of user pointers
where performing atomic operations in response to a futex command. This
patch uses masking to limit any speculative futex operations to within
the user address space.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	change on old futex_atomic_op_inuser function instead of
	arch_futex_atomic_op_inuser in arch/arm64/include/asm/futex.h
---
 arch/arm64/include/asm/futex.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 85c4a89..1943cf6 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -48,13 +48,14 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *_uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tmp;
+	u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
@@ -106,15 +107,17 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
 	u32 val, tmp;
+	u32 __user *uaddr;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, _uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	uaddr = __uaccess_mask_ptr(_uaddr);
 	uaccess_enable();
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
-- 
2.7.4

[PATCH 17/52] drivers/firmware: Expose psci_get_version through psci_ops structure

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit d68e3ba5303f upstream.

Entry into recent versions of ARM Trusted Firmware will invalidate the CPU
branch predictor state in order to protect against aliasing attacks.

This patch exposes the PSCI "VERSION" function via psci_ops, so that it
can be invoked outside of the PSCI driver where necessary.

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 drivers/firmware/psci.c | 2 ++
 include/linux/psci.h    | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index 8263429..9a3ce76 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -496,6 +496,8 @@ static void __init psci_init_migrate(void)
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_ops.get_version = psci_get_version;
+
 	psci_function_id[PSCI_FN_CPU_SUSPEND] =
 					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
 	psci_ops.cpu_suspend = psci_cpu_suspend;
diff --git a/include/linux/psci.h b/include/linux/psci.h
index bdea1cb..6306ab1 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -26,6 +26,7 @@ int psci_cpu_init_idle(unsigned int cpu);
 int psci_cpu_suspend_enter(unsigned long index);
 
 struct psci_operations {
+	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
 	int (*cpu_off)(u32 state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-- 
2.7.4

[PATCH 18/52] arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early

[Alex Shi]

From: James Morse <james.morse@arm.com>

commit edf298cfce47 upstream.
Alex Shi rewrite this commit on func this_cpu_has_cap(). The following commit
log is still meaningful.

    this_cpu_has_cap() tests caps->desc not caps->matches, so it stops
    walking the list when it finds a 'silent' feature, instead of
    walking to the end of the list.

    Prior to v4.6's 644c2ae198412 ("arm64: cpufeature: Test 'matches' pointer
    to find the end of the list") we always tested desc to find the end of
    a capability list. This was changed for dubious things like PAN_NOT_UAO.
    v4.7's e3661b128e53e ("arm64: Allow a capability to be checked on
    single CPU") added this_cpu_has_cap() using the old desc style test.

    CC: Suzuki K Poulose <suzuki.poulose@arm.com>
    Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
    Acked-by: Marc Zyngier <marc.zyngier@arm.com>
    Signed-off-by: James Morse <james.morse@arm.com>
    Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
    Signed-off-by: Will Deacon <will.deacon@arm.com>

Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/include/asm/futex.h | 1 +
 arch/arm64/kernel/cpufeature.c | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 1943cf6..718140a 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -20,6 +20,7 @@
 
 #include <linux/futex.h>
 #include <linux/uaccess.h>
+#include <linux/compiler.h>
 
 #include <asm/errno.h>
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3a129d4..fcb67e0 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1063,8 +1063,8 @@ bool this_cpu_has_cap(unsigned int cap)
 	if (WARN_ON(preemptible()))
 		return false;
 
-	for (caps = arm64_features; caps->desc; caps++)
-		if (caps->capability == cap && caps->matches)
+	for (caps = arm64_features; caps->matches; caps++)
+		if (caps->capability == cap)
 			return caps->matches(caps, SCOPE_LOCAL_CPU);
 
 	return false;
-- 
2.7.4

[PATCH 19/52] arm64: cpu_errata: Allow an erratum to be match for all revisions of a core

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 06f1494f837 upstream.

Some minor erratum may not be fixed in further revisions of a core,
leading to a situation where the workaround needs to be updated each
time an updated core is released.

Introduce a MIDR_ALL_VERSIONS match helper that will work for all
versions of that MIDR, once and for all.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kernel/cpu_errata.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index b75e917..c66a673c 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -53,6 +53,13 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 	.midr_range_min = min, \
 	.midr_range_max = max
 
+#define MIDR_ALL_VERSIONS(model) \
+	.def_scope = SCOPE_LOCAL_CPU, \
+	.matches = is_affected_midr_range, \
+	.midr_model = model, \
+	.midr_range_min = 0, \
+	.midr_range_max = (MIDR_VARIANT_MASK | MIDR_REVISION_MASK)
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #if	defined(CONFIG_ARM64_ERRATUM_826319) || \
 	defined(CONFIG_ARM64_ERRATUM_827319) || \
-- 
2.7.4

[PATCH 20/52] arm64: Run enable method for errata work arounds on late CPUs

[Alex Shi]

From: Suzuki K Poulose <suzuki.poulose@arm.com>

commit 55b35d070c25 upstream.

When a CPU is brought up after we have finalised the system
wide capabilities (i.e, features and errata), we make sure the
new CPU doesn't need a new errata work around which has not been
detected already. However we don't run enable() method on the new
CPU for the errata work arounds already detected. This could
cause the new CPU running without potential work arounds.
It is upto the "enable()" method to decide if this CPU should
do something about the errata.

Fixes: commit 6a6efbb45b7d95c84 ("arm64: Verify CPU errata work arounds on hotplugged CPU")
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Andre Przywara <andre.przywara@arm.com>
Cc: Dave Martin <dave.martin@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kernel/cpu_errata.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c66a673c..8de43799 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -150,15 +150,18 @@ void verify_local_cpu_errata_workarounds(void)
 {
 	const struct arm64_cpu_capabilities *caps = arm64_errata;
 
-	for (; caps->matches; caps++)
-		if (!cpus_have_cap(caps->capability) &&
-			caps->matches(caps, SCOPE_LOCAL_CPU)) {
+	for (; caps->matches; caps++) {
+		if (cpus_have_cap(caps->capability)) {
+			if (caps->enable)
+				caps->enable((void *)caps);
+		} else if (caps->matches(caps, SCOPE_LOCAL_CPU)) {
 			pr_crit("CPU%d: Requires work around for %s, not detected"
 					" at boot time\n",
 				smp_processor_id(),
 				caps->desc ? : "an erratum");
 			cpu_die_early();
 		}
+	}
 }
 
 void update_cpu_errata_workarounds(void)
-- 
2.7.4

[PATCH 21/52] arm64: cpufeature: Pass capability structure to ->enable callback

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 0a0d111d40fd upstream.

In order to invoke the CPU capability ->matches callback from the ->enable
callback for applying local-CPU workarounds, we need a handle on the
capability structure.

This patch passes a pointer to the capability structure to the ->enable
callback.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	arch/arm64/kernel/cpufeature.c
---
 arch/arm64/kernel/cpufeature.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index fcb67e0..5c41ef6 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -949,7 +949,7 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 			 * uses an IPI, giving us a PSTATE that disappears when
 			 * we return.
 			 */
-			stop_machine(caps->enable, NULL, cpu_online_mask);
+			stop_machine(caps->enable, (void *)caps, cpu_online_mask);
 }
 
 /*
@@ -1005,7 +1005,7 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 			cpu_die_early();
 		}
 		if (caps->enable)
-			caps->enable(NULL);
+			caps->enable((void *)caps);
 	}
 }
 
-- 
2.7.4

[PATCH 22/52] arm64: Move post_ttbr_update_workaround to C code

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 95e3de3590e3 upstream.

We will soon need to invoke a CPU-specific function pointer after changing
page tables, so move post_ttbr_update_workaround out into C code to make
this possible.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	don't include PAN related changes
	arch/arm64/include/asm/assembler.h
	arch/arm64/kernel/entry.S
	arch/arm64/mm/proc.S
---
 arch/arm64/mm/context.c | 9 +++++++++
 arch/arm64/mm/proc.S    | 3 +--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index efcf1f7..32eeabe91 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -224,6 +224,15 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	cpu_switch_mm(mm->pgd, mm);
 }
 
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+	asm(ALTERNATIVE("nop; nop; nop",
+			"ic iallu; dsb nsh; isb",
+			ARM64_WORKAROUND_CAVIUM_27456,
+			CONFIG_CAVIUM_ERRATUM_27456));
+}
+
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c2adb0c..cca061a 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -136,8 +136,7 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
-	post_ttbr0_update_workaround
-	ret
+	b	post_ttbr_update_workaround	// Back to C code...
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "ax"
-- 
2.7.4

[PATCH 23/52] arm64: Add skeleton to harden the branch predictor against aliasing attacks

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 0f15adbb2861 upstream.

Aliasing attacks against CPU branch predictors can allow an attacker to
redirect speculative control flow on some CPUs and potentially divulge
information from one context to another.

This patch adds initial skeleton code behind a new Kconfig option to
enable implementation-specific mitigations against these attacks for
CPUs that are affected.

Co-developed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	expand enable_da_f in entry.S
	use 5 parameters ARM64_FTR_BITS()
	add percpu.h in mm_types.h for percpu functions
	use cpus_have_cap instead of cpus_have_const_cap
	arch/arm64/Kconfig
	arch/arm64/include/asm/cpucaps.h
	arch/arm64/include/asm/mmu.h
	arch/arm64/include/asm/sysreg.h
	arch/arm64/kernel/cpufeature.c
	arch/arm64/kernel/entry.S
	arch/arm64/mm/fault.c
---
 arch/arm64/Kconfig               | 17 +++++++++
 arch/arm64/include/asm/cpucaps.h |  3 +-
 arch/arm64/include/asm/mmu.h     | 38 +++++++++++++++++++++
 arch/arm64/include/asm/sysreg.h  |  1 +
 arch/arm64/kernel/Makefile       |  4 +++
 arch/arm64/kernel/bpi.S          | 55 +++++++++++++++++++++++++++++
 arch/arm64/kernel/cpu_errata.c   | 74 ++++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/cpufeature.c   |  1 +
 arch/arm64/kernel/entry.S        |  8 +++--
 arch/arm64/mm/context.c          |  2 ++
 arch/arm64/mm/fault.c            | 17 +++++++++
 include/linux/mm_types.h         |  1 +
 12 files changed, 217 insertions(+), 4 deletions(-)
 create mode 100644 arch/arm64/kernel/bpi.S

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7769c2e..0c4be63 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -733,6 +733,23 @@ config FORCE_MAX_ZONEORDER
 	  However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
 	  4M allocations matching the default size used by generic code.
 
+config HARDEN_BRANCH_PREDICTOR
+	bool "Harden the branch predictor against aliasing attacks" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors rely on
+	  being able to manipulate the branch predictor for a victim context by
+	  executing aliasing branches in the attacker context.  Such attacks
+	  can be partially mitigated against by clearing internal branch
+	  predictor state and limiting the prediction logic in some situations.
+
+	  This config option will take CPU-specific actions to harden the
+	  branch predictor against aliasing attacks and may rely on specific
+	  instruction sequences or control bits being set by the system
+	  firmware.
+
+	  If unsure, say Y.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 87b4465..f8b7799 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -34,7 +34,8 @@
 #define ARM64_HAS_32BIT_EL0			13
 #define ARM64_HYP_OFFSET_LOW			14
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
+#define ARM64_HARDEN_BRANCH_PREDICTOR		16
 
-#define ARM64_NCAPS				16
+#define ARM64_NCAPS				17
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index b075140..203974c 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -28,6 +28,44 @@ typedef struct {
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
+
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+	int			hyp_vectors_slot;
+	bp_hardening_cb_t	fn;
+};
+
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return this_cpu_ptr(&bp_hardening_data);
+}
+
+static inline void arm64_apply_bp_hardening(void)
+{
+	struct bp_hardening_data *d;
+
+	if (!cpus_have_cap(ARM64_HARDEN_BRANCH_PREDICTOR))
+		return;
+
+	d = arm64_get_bp_hardening_data();
+	if (d->fn)
+		d->fn();
+}
+#else
+static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
+{
+	return NULL;
+}
+
+static inline void arm64_apply_bp_hardening(void)	{ }
+#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
 extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7393cc7..e91710f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -117,6 +117,7 @@
 #define ID_AA64ISAR0_AES_SHIFT		4
 
 /* id_aa64pfr0 */
+#define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_GIC_SHIFT		24
 #define ID_AA64PFR0_ASIMD_SHIFT		20
 #define ID_AA64PFR0_FP_SHIFT		16
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7d66bba..74b8fd8 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -51,6 +51,10 @@ arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
 
+ifeq ($(CONFIG_KVM),y)
+arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR)	+= bpi.o
+endif
+
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
 head-y					:= head.o
diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
new file mode 100644
index 0000000..06a931e
--- /dev/null
+++ b/arch/arm64/kernel/bpi.S
@@ -0,0 +1,55 @@
+/*
+ * Contains CPU specific branch predictor invalidation sequences
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+.macro ventry target
+	.rept 31
+	nop
+	.endr
+	b	\target
+.endm
+
+.macro vectors target
+	ventry \target + 0x000
+	ventry \target + 0x080
+	ventry \target + 0x100
+	ventry \target + 0x180
+
+	ventry \target + 0x200
+	ventry \target + 0x280
+	ventry \target + 0x300
+	ventry \target + 0x380
+
+	ventry \target + 0x400
+	ventry \target + 0x480
+	ventry \target + 0x500
+	ventry \target + 0x580
+
+	ventry \target + 0x600
+	ventry \target + 0x680
+	ventry \target + 0x700
+	ventry \target + 0x780
+.endm
+
+	.align	11
+ENTRY(__bp_harden_hyp_vecs_start)
+	.rept 4
+	vectors __kvm_hyp_vector
+	.endr
+ENTRY(__bp_harden_hyp_vecs_end)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 8de43799..0e07893 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -46,6 +46,80 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 	return 0;
 }
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu_context.h>
+#include <asm/cacheflush.h>
+
+DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+#ifdef CONFIG_KVM
+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);
+	int i;
+
+	for (i = 0; i < SZ_2K; i += 0x80)
+		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
+
+	flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+}
+
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+				      const char *hyp_vecs_start,
+				      const char *hyp_vecs_end)
+{
+	static int last_slot = -1;
+	static DEFINE_SPINLOCK(bp_lock);
+	int cpu, slot = -1;
+
+	spin_lock(&bp_lock);
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
+			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		last_slot++;
+		BUG_ON(((__bp_harden_hyp_vecs_end - __bp_harden_hyp_vecs_start)
+			/ SZ_2K) <= last_slot);
+		slot = last_slot;
+		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+	}
+
+	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+	__this_cpu_write(bp_hardening_data.fn, fn);
+	spin_unlock(&bp_lock);
+}
+#else
+static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+				      const char *hyp_vecs_start,
+				      const char *hyp_vecs_end)
+{
+	__this_cpu_write(bp_hardening_data.fn, fn);
+}
+#endif	/* CONFIG_KVM */
+
+static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
+				     bp_hardening_cb_t fn,
+				     const char *hyp_vecs_start,
+				     const char *hyp_vecs_end)
+{
+	u64 pfr0;
+
+	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
+		return;
+
+	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
+		return;
+
+	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
+}
+#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
+
 #define MIDR_RANGE(model, min, max) \
 	.def_scope = SCOPE_LOCAL_CPU, \
 	.matches = is_affected_midr_range, \
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 5c41ef6..6e7fda3 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -98,6 +98,7 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
+	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
 	/* Linux doesn't care about the EL3 */
 	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0),
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 0a27e12..bdb0139 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -549,13 +549,15 @@ el0_ia:
 	 * Instruction abort handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	msr	daifclr, #(8 | 4 | 1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
-	bl	do_mem_abort
+	bl	do_el0_ia_bp_hardening
 	b	ret_to_user
 el0_fpsimd_acc:
 	/*
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 32eeabe91..afc9266 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -231,6 +231,8 @@ asmlinkage void post_ttbr_update_workaround(void)
 			"ic iallu; dsb nsh; isb",
 			ARM64_WORKAROUND_CAVIUM_27456,
 			CONFIG_CAVIUM_ERRATUM_27456));
+
+	arm64_apply_bp_hardening();
 }
 
 static int asids_init(void)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4df70c9..c95b194 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -590,6 +590,23 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die("", regs, &info, esr);
 }
 
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+						   unsigned int esr,
+						   struct pt_regs *regs)
+{
+	/*
+	 * We've taken an instruction abort from userspace and not yet
+	 * re-enabled IRQs. If the address is a kernel address, apply
+	 * BP hardening prior to enabling IRQs and pre-emption.
+	 */
+	if (addr > TASK_SIZE)
+		arm64_apply_bp_hardening();
+
+	local_irq_enable();
+	do_mem_abort(addr, esr, regs);
+}
+
+
 /*
  * Handle stack alignment exceptions.
  */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e8471c2..15a82f3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -13,6 +13,7 @@
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
+#include <linux/percpu.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
-- 
2.7.4

[PATCH 24/52] arm64: Move BP hardening to check_and_switch_context

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit a8e4c0a919ae upstream.

We call arm64_apply_bp_hardening() from post_ttbr_update_workaround,
which has the unexpected consequence of being triggered on every
exception return to userspace when ARM64_SW_TTBR0_PAN is selected,
even if no context switch actually occured.

This is a bit suboptimal, and it would be more logical to only
invalidate the branch predictor when we actually switch to
a different mm.

In order to solve this, move the call to arm64_apply_bp_hardening()
into check_and_switch_context(), where we're guaranteed to pick
a different mm context.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no sw pan in arch/arm64/mm/context.c
---
 arch/arm64/mm/context.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index afc9266..36416e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -221,6 +221,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
+	arm64_apply_bp_hardening();
 	cpu_switch_mm(mm->pgd, mm);
 }
 
@@ -231,8 +232,6 @@ asmlinkage void post_ttbr_update_workaround(void)
 			"ic iallu; dsb nsh; isb",
 			ARM64_WORKAROUND_CAVIUM_27456,
 			CONFIG_CAVIUM_ERRATUM_27456));
-
-	arm64_apply_bp_hardening();
 }
 
 static int asids_init(void)
-- 
2.7.4

[PATCH 25/52] arm64: KVM: Use per-CPU vector when BP hardening is enabled

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 6840bdd73d07 upstream

Now that we have per-CPU vectors, let's plug then in the KVM/arm64 code.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv changes from virt/kvm/arm/arm.c to arch/arm/kvm/arm.c
---
 arch/arm/include/asm/kvm_mmu.h   | 10 ++++++++++
 arch/arm/kvm/arm.c               |  8 +++++++-
 arch/arm64/include/asm/kvm_mmu.h | 38 ++++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/switch.c      |  2 +-
 4 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index a58bbaa..d10e362 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -223,6 +223,16 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return 8;
 }
 
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index c38bfbe..4e4ae07 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1088,7 +1088,7 @@ static void cpu_init_hyp_mode(void *dummy)
 	pgd_ptr = kvm_mmu_get_httbr();
 	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
-	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
+	vector_ptr = (unsigned long)kvm_get_hyp_vector();
 
 	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
@@ -1345,6 +1345,12 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = kvm_map_vectors();
+	if (err) {
+		kvm_err("Cannot map vectors\n");
+		goto out_err;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6d22017..80bf337 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -313,5 +313,43 @@ static inline unsigned int kvm_get_vmid_bits(void)
 	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
 }
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+#include <asm/mmu.h>
+
+static inline void *kvm_get_hyp_vector(void)
+{
+	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
+	void *vect = kvm_ksym_ref(__kvm_hyp_vector);
+
+	if (data->fn) {
+		vect = __bp_harden_hyp_vecs_start +
+		       data->hyp_vectors_slot * SZ_2K;
+
+		if (!cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+			vect = lm_alias(vect);
+	}
+
+	return vect;
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start),
+				   kvm_ksym_ref(__bp_harden_hyp_vecs_end),
+				   PAGE_HYP_EXEC);
+}
+
+#else
+static inline void *kvm_get_hyp_vector(void)
+{
+	return kvm_ksym_ref(__kvm_hyp_vector);
+}
+
+static inline int kvm_map_vectors(void)
+{
+	return 0;
+}
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 0c848c1..cf6d962 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -50,7 +50,7 @@ static void __hyp_text __activate_traps_vhe(void)
 	val &= ~CPACR_EL1_FPEN;
 	write_sysreg(val, cpacr_el1);
 
-	write_sysreg(__kvm_hyp_vector, vbar_el1);
+	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
 }
 
 static void __hyp_text __activate_traps_nvhe(void)
-- 
2.7.4

[PATCH 26/52] arm64: entry: Apply BP hardening for high-priority synchronous exceptions

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 5dfc6ed27710 upstream.

Software-step and PC alignment fault exceptions have higher priority than
instruction abort exceptions, so apply the BP hardening hooks there too
if the user PC appears to reside in kernel space.

Reported-by: Dan Hettena <dhettena@nvidia.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	expand enable_da_f to 'msr daifclr, #(8 | 4 | 1)'
	in arch/arm64/kernel/entry.S
---
 arch/arm64/kernel/entry.S | 6 ++++--
 arch/arm64/mm/fault.c     | 9 +++++++++
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index bdb0139..d50c2fe 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -584,8 +584,10 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x26, far_el1
-	// enable interrupts before calling the main handler
-	enable_dbg_and_irq
+	msr	daifclr, #(8 | 4 | 1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off
+#endif
 	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c95b194..6120a14 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -617,6 +617,12 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 	struct siginfo info;
 	struct task_struct *tsk = current;
 
+	if (user_mode(regs)) {
+		if (instruction_pointer(regs) > TASK_SIZE)
+			arm64_apply_bp_hardening();
+		local_irq_enable();
+	}
+
 	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
 		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
 				    tsk->comm, task_pid_nr(tsk),
@@ -676,6 +682,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 	if (interrupts_enabled(regs))
 		trace_hardirqs_off();
 
+	if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE)
+		arm64_apply_bp_hardening();
+
 	if (!inf->fn(addr, esr, regs)) {
 		rv = 1;
 	} else {
-- 
2.7.4

[PATCH 27/52] arm64: entry: Apply BP hardening for suspicious interrupts from EL0

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit 30d88c0e3ace upstream.

It is possible to take an IRQ from EL0 following a branch to a kernel
address in such a way that the IRQ is prioritised over the instruction
abort. Whilst an attacker would need to get the stars to align here,
it might be sufficient with enough calibration so perform BP hardening
in the rare case that we see a kernel address in the ELR when handling
an IRQ from EL0.

Reported-by: Dan Hettena <dhettena@nvidia.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kernel/entry.S | 5 +++++
 arch/arm64/mm/fault.c     | 6 ++++++
 2 files changed, 11 insertions(+)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index d50c2fe..e26a114 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -646,6 +646,11 @@ el0_irq_naked:
 #endif
 
 	ct_user_exit
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	tbz	x22, #55, 1f
+	bl	do_el0_irq_bp_hardening
+1:
+#endif
 	irq_handler
 
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6120a14..ad49ae8 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -590,6 +590,12 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	arm64_notify_die("", regs, &info, esr);
 }
 
+asmlinkage void __exception do_el0_irq_bp_hardening(void)
+{
+	/* PC has already been checked in entry.S */
+	arm64_apply_bp_hardening();
+}
+
 asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
 						   unsigned int esr,
 						   struct pt_regs *regs)
-- 
2.7.4

[PATCH 28/52] arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit a65d219fe5dc upstream.

Hook up MIDR values for the Cortex-A72 and Cortex-A75 CPUs, since they
will soon need MIDR matches for hardening the branch predictor.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	pick A73 too in arch/arm64/include/asm/cputype.h
---
 arch/arm64/include/asm/cputype.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 26a68dd..0843b3f 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,7 +75,10 @@
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
 #define ARM_CPU_PART_CORTEX_A57		0xD07
+#define ARM_CPU_PART_CORTEX_A72		0xD08
 #define ARM_CPU_PART_CORTEX_A53		0xD03
+#define ARM_CPU_PART_CORTEX_A73		0xD09
+#define ARM_CPU_PART_CORTEX_A75		0xD0A
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -86,6 +89,9 @@
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
+#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
+#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
-- 
2.7.4

[PATCH 29/52] arm64: Implement branch predictor hardening for affected Cortex-A CPUs

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

commit aa6acde65e03 upstream.

Cortex-A57, A72, A73 and A75 are susceptible to branch predictor aliasing
and can theoretically be attacked by malicious code.

This patch implements a PSCI-based mitigation for these CPUs when available.
The call into firmware will invalidate the branch predictor state, preventing
any malicious entries from affecting other victim contexts.

Co-developed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no falkor in arch/arm64/kernel/cpu_errata.c
---
 arch/arm64/kernel/bpi.S        | 24 ++++++++++++++++++++++++
 arch/arm64/kernel/cpu_errata.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
index 06a931e..dec95bd 100644
--- a/arch/arm64/kernel/bpi.S
+++ b/arch/arm64/kernel/bpi.S
@@ -53,3 +53,27 @@ ENTRY(__bp_harden_hyp_vecs_start)
 	vectors __kvm_hyp_vector
 	.endr
 ENTRY(__bp_harden_hyp_vecs_end)
+ENTRY(__psci_hyp_bp_inval_start)
+	sub	sp, sp, #(8 * 18)
+	stp	x16, x17, [sp, #(16 * 0)]
+	stp	x14, x15, [sp, #(16 * 1)]
+	stp	x12, x13, [sp, #(16 * 2)]
+	stp	x10, x11, [sp, #(16 * 3)]
+	stp	x8, x9, [sp, #(16 * 4)]
+	stp	x6, x7, [sp, #(16 * 5)]
+	stp	x4, x5, [sp, #(16 * 6)]
+	stp	x2, x3, [sp, #(16 * 7)]
+	stp	x0, x1, [sp, #(16 * 8)]
+	mov	x0, #0x84000000
+	smc	#0
+	ldp	x16, x17, [sp, #(16 * 0)]
+	ldp	x14, x15, [sp, #(16 * 1)]
+	ldp	x12, x13, [sp, #(16 * 2)]
+	ldp	x10, x11, [sp, #(16 * 3)]
+	ldp	x8, x9, [sp, #(16 * 4)]
+	ldp	x6, x7, [sp, #(16 * 5)]
+	ldp	x4, x5, [sp, #(16 * 6)]
+	ldp	x2, x3, [sp, #(16 * 7)]
+	ldp	x0, x1, [sp, #(16 * 8)]
+	add	sp, sp, #(8 * 18)
+ENTRY(__psci_hyp_bp_inval_end)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0e07893..f8810bf 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -53,6 +53,8 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 #ifdef CONFIG_KVM
+extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
+
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
 {
@@ -94,6 +96,9 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 	spin_unlock(&bp_lock);
 }
 #else
+#define __psci_hyp_bp_inval_start	NULL
+#define __psci_hyp_bp_inval_end		NULL
+
 static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
@@ -118,6 +123,21 @@ static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
 
 	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
 }
+
+#include <linux/psci.h>
+
+static int enable_psci_bp_hardening(void *data)
+{
+	const struct arm64_cpu_capabilities *entry = data;
+
+	if (psci_ops.get_version)
+		install_bp_hardening_cb(entry,
+				       (bp_hardening_cb_t)psci_ops.get_version,
+				       __psci_hyp_bp_inval_start,
+				       __psci_hyp_bp_inval_end);
+
+	return 0;
+}
 #endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
 #define MIDR_RANGE(model, min, max) \
@@ -211,6 +231,28 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.def_scope = SCOPE_LOCAL_CPU,
 		.enable = cpu_enable_trap_ctr_access,
 	},
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+		.enable = enable_psci_bp_hardening,
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
+		.enable = enable_psci_bp_hardening,
+	},
+#endif
 	{
 	}
 };
-- 
2.7.4

[PATCH 30/52] arm64: KVM: Increment PC after handling an SMC trap

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit f5115e8869e1 upstream.

When handling an SMC trap, the "preferred return address" is set
to that of the SMC, and not the next PC (which is a departure from
the behaviour of an SMC that isn't trapped).

Increment PC in the handler, as the guest is otherwise forever
stuck...

Cc: stable@vger.kernel.org
Fixes: acfb3b883f6d ("arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls")
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kvm/handle_exit.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 2e6e9e9..5b56b09 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -53,7 +53,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
+	/*
+	 * "If an SMC instruction executed at Non-secure EL1 is
+	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
+	 * Trap exception, not a Secure Monitor Call exception [...]"
+	 *
+	 * We need to advance the PC after the trap, as it would
+	 * otherwise return to the same address...
+	 */
 	vcpu_set_reg(vcpu, 0, ~0UL);
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 	return 1;
 }
 
-- 
2.7.4

[PATCH 31/52] arm/arm64: KVM: Consolidate the PSCI include files

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 1a2fb94e6a77 upstream.

As we're about to update the PSCI support, and because I'm lazy,
let's move the PSCI include file to include/kvm so that both
ARM architectures can find it.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	need kvm/arm_psci.h in files:
	arch/arm64/kvm/handle_exit.c
	arch/arm/kvm/psci.c and arch/arm/kvm/arm.c
	no virt/kvm/arm/arm.c and virt/kvm/arm/psci.c
---
 arch/arm/include/asm/kvm_psci.h   | 27 ---------------------------
 arch/arm/kvm/arm.c                |  2 +-
 arch/arm/kvm/handle_exit.c        |  2 +-
 arch/arm/kvm/psci.c               |  2 +-
 arch/arm64/include/asm/kvm_psci.h | 27 ---------------------------
 arch/arm64/kvm/handle_exit.c      |  3 ++-
 include/kvm/arm_psci.h            | 27 +++++++++++++++++++++++++++
 7 files changed, 32 insertions(+), 58 deletions(-)
 delete mode 100644 arch/arm/include/asm/kvm_psci.h
 delete mode 100644 arch/arm64/include/asm/kvm_psci.h
 create mode 100644 include/kvm/arm_psci.h

diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h
deleted file mode 100644
index 6bda945..0000000
--- a/arch/arm/include/asm/kvm_psci.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2012 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM_KVM_PSCI_H__
-#define __ARM_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM_KVM_PSCI_H__ */
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 4e4ae07..8588e67 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -44,8 +44,8 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
-#include <asm/kvm_psci.h>
 #include <asm/sections.h>
+#include <kvm/arm_psci.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 4e57ebc..0a2b758 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -21,7 +21,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
+#include <kvm/arm_psci.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index a08d7a9..18f9e9d 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -21,8 +21,8 @@
 
 #include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_psci.h>
 #include <asm/kvm_host.h>
+#include <kvm/arm_psci.h>
 
 #include <uapi/linux/psci.h>
 
diff --git a/arch/arm64/include/asm/kvm_psci.h b/arch/arm64/include/asm/kvm_psci.h
deleted file mode 100644
index bc39e55..0000000
--- a/arch/arm64/include/asm/kvm_psci.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_KVM_PSCI_H__
-#define __ARM64_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM64_KVM_PSCI_H__ */
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5b56b09..0231ebc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -22,12 +22,13 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <kvm/arm_psci.h>
+
 #include <asm/esr.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
new file mode 100644
index 0000000..2042bb9
--- /dev/null
+++ b/include/kvm/arm_psci.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __KVM_ARM_PSCI_H__
+#define __KVM_ARM_PSCI_H__
+
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_ARM_PSCI_H__ */
-- 
2.7.4

[PATCH 32/52] arm/arm64: KVM: Add PSCI_VERSION helper

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit d0a144f12a7c upstream.

As we're about to trigger a PSCI version explosion, it doesn't
hurt to introduce a PSCI_VERSION helper that is going to be
used everywhere.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv change form virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
---
 arch/arm/kvm/psci.c       | 2 +-
 include/kvm/arm_psci.h    | 6 ++++--
 include/uapi/linux/psci.h | 3 +++
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 18f9e9d..4adfa28 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -219,7 +219,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 * Bits[31:16] = Major Version = 0
 		 * Bits[15:0] = Minor Version = 2
 		 */
-		val = 2;
+		val = KVM_ARM_PSCI_0_2;
 		break;
 	case PSCI_0_2_FN_CPU_SUSPEND:
 	case PSCI_0_2_FN64_CPU_SUSPEND:
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 2042bb9..5659343 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -18,8 +18,10 @@
 #ifndef __KVM_ARM_PSCI_H__
 #define __KVM_ARM_PSCI_H__
 
-#define KVM_ARM_PSCI_0_1	1
-#define KVM_ARM_PSCI_0_2	2
+#include <uapi/linux/psci.h>
+
+#define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
+#define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
 int kvm_psci_call(struct kvm_vcpu *vcpu);
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
index 3d7a0fc..39930ca 100644
--- a/include/uapi/linux/psci.h
+++ b/include/uapi/linux/psci.h
@@ -87,6 +87,9 @@
 		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
 #define PSCI_VERSION_MINOR(ver)			\
 		((ver) & PSCI_VERSION_MINOR_MASK)
+#define PSCI_VERSION(maj, min)						\
+	((((maj) << PSCI_VERSION_MAJOR_SHIFT) & PSCI_VERSION_MAJOR_MASK) | \
+	 ((min) & PSCI_VERSION_MINOR_MASK))
 
 /* PSCI features decoding (>=1.0) */
 #define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT	1
-- 
2.7.4

[PATCH 33/52] arm/arm64: KVM: Add smccc accessors to PSCI code

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 84684fecd7ea upstream.

Instead of open coding the accesses to the various registers,
let's add explicit SMCCC accessors.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv change from virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
---
 arch/arm/kvm/psci.c | 52 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 10 deletions(-)

diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 4adfa28..bc334d6 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -33,6 +33,38 @@
 
 #define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
 
+static u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 0);
+}
+
+static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 1);
+}
+
+static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 2);
+}
+
+static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_reg(vcpu, 3);
+}
+
+static void smccc_set_retval(struct kvm_vcpu *vcpu,
+			     unsigned long a0,
+			     unsigned long a1,
+			     unsigned long a2,
+			     unsigned long a3)
+{
+	vcpu_set_reg(vcpu, 0, a0);
+	vcpu_set_reg(vcpu, 1, a1);
+	vcpu_set_reg(vcpu, 2, a2);
+	vcpu_set_reg(vcpu, 3, a3);
+}
+
 static unsigned long psci_affinity_mask(unsigned long affinity_level)
 {
 	if (affinity_level <= 3)
@@ -75,7 +107,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	unsigned long context_id;
 	phys_addr_t target_pc;
 
-	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
@@ -94,8 +126,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = vcpu_get_reg(source_vcpu, 2);
-	context_id = vcpu_get_reg(source_vcpu, 3);
+	target_pc = smccc_get_arg2(source_vcpu);
+	context_id = smccc_get_arg3(source_vcpu);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -114,7 +146,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	vcpu_set_reg(vcpu, 0, context_id);
+	smccc_set_retval(vcpu, context_id, 0, 0, 0);
 	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
@@ -134,8 +166,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tmp;
 
-	target_affinity = vcpu_get_reg(vcpu, 1);
-	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
+	target_affinity = smccc_get_arg1(vcpu);
+	lowest_affinity_level = smccc_get_arg2(vcpu);
 
 	/* Determine target affinity mask */
 	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -209,7 +241,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	u32 psci_fn = smccc_get_function(vcpu);
 	unsigned long val;
 	int ret = 1;
 
@@ -276,14 +308,14 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	vcpu_set_reg(vcpu, 0, val);
+	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+	u32 psci_fn = smccc_get_function(vcpu);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -301,7 +333,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	vcpu_set_reg(vcpu, 0, val);
+	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return 1;
 }
 
-- 
2.7.4

[PATCH 34/52] arm/arm64: KVM: Implement PSCI 1.0 support

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 58e0b2239a4d upstream.

PSCI 1.0 can be trivially implemented by providing the FEATURES
call on top of PSCI 0.2 and returning 1.0 as the PSCI version.

We happily ignore everything else, as they are either optional or
are clarifications that do not require any additional change.

PSCI 1.0 is now the default until we decide to add a userspace
selection API.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv chagnes from virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
---
 arch/arm/kvm/psci.c    | 45 ++++++++++++++++++++++++++++++++++++++++++++-
 include/kvm/arm_psci.h |  3 +++
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index bc334d6..097632c 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -233,7 +233,7 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
 int kvm_psci_version(struct kvm_vcpu *vcpu)
 {
 	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
-		return KVM_ARM_PSCI_0_2;
+		return KVM_ARM_PSCI_LATEST;
 
 	return KVM_ARM_PSCI_0_1;
 }
@@ -312,6 +312,47 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
+{
+	u32 psci_fn = smccc_get_function(vcpu);
+	u32 feature;
+	unsigned long val;
+	int ret = 1;
+
+	switch(psci_fn) {
+	case PSCI_0_2_FN_PSCI_VERSION:
+		val = KVM_ARM_PSCI_1_0;
+		break;
+	case PSCI_1_0_FN_PSCI_FEATURES:
+		feature = smccc_get_arg1(vcpu);
+		switch(feature) {
+		case PSCI_0_2_FN_PSCI_VERSION:
+		case PSCI_0_2_FN_CPU_SUSPEND:
+		case PSCI_0_2_FN64_CPU_SUSPEND:
+		case PSCI_0_2_FN_CPU_OFF:
+		case PSCI_0_2_FN_CPU_ON:
+		case PSCI_0_2_FN64_CPU_ON:
+		case PSCI_0_2_FN_AFFINITY_INFO:
+		case PSCI_0_2_FN64_AFFINITY_INFO:
+		case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+		case PSCI_0_2_FN_SYSTEM_OFF:
+		case PSCI_0_2_FN_SYSTEM_RESET:
+		case PSCI_1_0_FN_PSCI_FEATURES:
+			val = 0;
+			break;
+		default:
+			val = PSCI_RET_NOT_SUPPORTED;
+			break;
+		}
+		break;
+	default:
+		return kvm_psci_0_2_call(vcpu);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return ret;
+}
+
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -354,6 +395,8 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
 	switch (kvm_psci_version(vcpu)) {
+	case KVM_ARM_PSCI_1_0:
+		return kvm_psci_1_0_call(vcpu);
 	case KVM_ARM_PSCI_0_2:
 		return kvm_psci_0_2_call(vcpu);
 	case KVM_ARM_PSCI_0_1:
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 5659343..3236043 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -22,6 +22,9 @@
 
 #define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
 #define KVM_ARM_PSCI_0_2	PSCI_VERSION(0, 2)
+#define KVM_ARM_PSCI_1_0	PSCI_VERSION(1, 0)
+
+#define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
 int kvm_psci_call(struct kvm_vcpu *vcpu);
-- 
2.7.4

[PATCH 35/52] arm/arm64: KVM: Advertise SMCCC v1.1

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 09e6be12effd upstream.

The new SMC Calling Convention (v1.1) allows for a reduced overhead
when calling into the firmware, and provides a new feature discovery
mechanism.

Make it visible to KVM guests.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv change from virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
---
 arch/arm/kvm/handle_exit.c   |  2 +-
 arch/arm/kvm/psci.c          | 24 +++++++++++++++++++++++-
 arch/arm64/kvm/handle_exit.c |  2 +-
 include/kvm/arm_psci.h       |  2 +-
 include/linux/arm-smccc.h    | 13 +++++++++++++
 5 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 0a2b758..de1aedc 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -36,7 +36,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		      kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
-	ret = kvm_psci_call(vcpu);
+	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 097632c..7b44253 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/preempt.h>
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
@@ -338,6 +339,7 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
 		case PSCI_0_2_FN_SYSTEM_OFF:
 		case PSCI_0_2_FN_SYSTEM_RESET:
 		case PSCI_1_0_FN_PSCI_FEATURES:
+		case ARM_SMCCC_VERSION_FUNC_ID:
 			val = 0;
 			break;
 		default:
@@ -392,7 +394,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  * Errors:
  * -EINVAL: Unrecognized PSCI function
  */
-int kvm_psci_call(struct kvm_vcpu *vcpu)
+static int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
 	switch (kvm_psci_version(vcpu)) {
 	case KVM_ARM_PSCI_1_0:
@@ -405,3 +407,23 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	};
 }
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+	u32 func_id = smccc_get_function(vcpu);
+	u32 val = PSCI_RET_NOT_SUPPORTED;
+
+	switch (func_id) {
+	case ARM_SMCCC_VERSION_FUNC_ID:
+		val = ARM_SMCCC_VERSION_1_1;
+		break;
+	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+		/* Nothing supported yet */
+		break;
+	default:
+		return kvm_psci_call(vcpu);
+	}
+
+	smccc_set_retval(vcpu, val, 0, 0, 0);
+	return 1;
+}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 0231ebc..d4047fc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -43,7 +43,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			    kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
-	ret = kvm_psci_call(vcpu);
+	ret = kvm_hvc_call_handler(vcpu);
 	if (ret < 0) {
 		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 3236043..ed1dd80 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -27,6 +27,6 @@
 #define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
 int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_ARM_PSCI_H__ */
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 4c5bca38..dc68aa5 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -60,6 +60,19 @@
 #define ARM_SMCCC_QUIRK_NONE		0
 #define ARM_SMCCC_QUIRK_QCOM_A6		1 /* Save/restore register a6 */
 
+#define ARM_SMCCC_VERSION_1_0		0x10000
+#define ARM_SMCCC_VERSION_1_1		0x10001
+
+#define ARM_SMCCC_VERSION_FUNC_ID					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0)
+
+#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 1)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
-- 
2.7.4

[PATCH 36/52] arm64: KVM: Make PSCI_VERSION a fast path

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 90348689d500 upstream.

For those CPUs that require PSCI to perform a BP invalidation,
going all the way to the PSCI code for not much is a waste of
precious cycles. Let's terminate that call as early as possible.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kvm/hyp/switch.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index cf6d962..3eab6ac 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -17,6 +17,7 @@
 
 #include <linux/types.h>
 #include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -308,6 +309,18 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
 		goto again;
 
+	if (exit_code == ARM_EXCEPTION_TRAP &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
+	    vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
+		u64 val = PSCI_RET_NOT_SUPPORTED;
+		if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+			val = 2;
+
+		vcpu_set_reg(vcpu, 0, val);
+		goto again;
+	}
+
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
 	    exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
-- 
2.7.4

[PATCH 37/52] arm/arm64: KVM: Turn kvm_psci_version into a static inline

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit a4097b351118 upstream.

We're about to need kvm_psci_version in HYP too. So let's turn it
into a static inline, and pass the kvm structure as a second
parameter (so that HYP can do a kern_hyp_va on it).

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	mv changes from virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
---
 arch/arm/kvm/psci.c         | 12 ++----------
 arch/arm64/kvm/hyp/switch.c | 20 ++++++++++++--------
 include/kvm/arm_psci.h      | 21 ++++++++++++++++++++-
 3 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 7b44253..396eb5d 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -121,7 +121,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
 	if (!vcpu->arch.power_off) {
-		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+		if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
 			return PSCI_RET_INVALID_PARAMS;
@@ -231,14 +231,6 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
 	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
 }
 
-int kvm_psci_version(struct kvm_vcpu *vcpu)
-{
-	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
-		return KVM_ARM_PSCI_LATEST;
-
-	return KVM_ARM_PSCI_0_1;
-}
-
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -396,7 +388,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
  */
 static int kvm_psci_call(struct kvm_vcpu *vcpu)
 {
-	switch (kvm_psci_version(vcpu)) {
+	switch (kvm_psci_version(vcpu, vcpu->kvm)) {
 	case KVM_ARM_PSCI_1_0:
 		return kvm_psci_1_0_call(vcpu);
 	case KVM_ARM_PSCI_0_2:
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 3eab6ac..996328e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -19,6 +19,8 @@
 #include <linux/jump_label.h>
 #include <uapi/linux/psci.h>
 
+#include <kvm/arm_psci.h>
+
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
@@ -311,14 +313,16 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	if (exit_code == ARM_EXCEPTION_TRAP &&
 	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
-	    vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
-		u64 val = PSCI_RET_NOT_SUPPORTED;
-		if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
-			val = 2;
-
-		vcpu_set_reg(vcpu, 0, val);
-		goto again;
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32)) {
+		u32 val = vcpu_get_reg(vcpu, 0);
+
+		if (val == PSCI_0_2_FN_PSCI_VERSION) {
+			val = kvm_psci_version(vcpu, kern_hyp_va(vcpu->kvm));
+			if (unlikely(val == KVM_ARM_PSCI_0_1))
+				val = PSCI_RET_NOT_SUPPORTED;
+			vcpu_set_reg(vcpu, 0, val);
+			goto again;
+		}
 	}
 
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index ed1dd80..e518e4e 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -18,6 +18,7 @@
 #ifndef __KVM_ARM_PSCI_H__
 #define __KVM_ARM_PSCI_H__
 
+#include <linux/kvm_host.h>
 #include <uapi/linux/psci.h>
 
 #define KVM_ARM_PSCI_0_1	PSCI_VERSION(0, 1)
@@ -26,7 +27,25 @@
 
 #define KVM_ARM_PSCI_LATEST	KVM_ARM_PSCI_1_0
 
-int kvm_psci_version(struct kvm_vcpu *vcpu);
+/*
+ * We need the KVM pointer independently from the vcpu as we can call
+ * this from HYP, and need to apply kern_hyp_va on it...
+ */
+static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+	/*
+	 * Our PSCI implementation stays the same across versions from
+	 * v0.2 onward, only adding the few mandatory functions (such
+	 * as FEATURES with 1.0) that are required by newer
+	 * revisions. It is thus safe to return the latest.
+	 */
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+		return KVM_ARM_PSCI_LATEST;
+
+	return KVM_ARM_PSCI_0_1;
+}
+
+
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_ARM_PSCI_H__ */
-- 
2.7.4

[PATCH 38/52] arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 6167ec5c9145 upstream.

A new feature of SMCCC 1.1 is that it offers firmware-based CPU
workarounds. In particular, SMCCC_ARCH_WORKAROUND_1 provides
BP hardening for CVE-2017-5715.

If the host has some mitigation for this issue, report that
we deal with it using SMCCC_ARCH_WORKAROUND_1, as we apply the
host workaround on every guest exit.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no sve support in arch/arm64/include/asm/kvm_host.h
	mv changes from virt/kvm/arm/psci.c to arch/arm/kvm/psci.c
	using cpus_have_cap instead of cpus_have_const_cap
---
 arch/arm/include/asm/kvm_host.h   | 6 ++++++
 arch/arm/kvm/psci.c               | 9 ++++++++-
 arch/arm64/include/asm/kvm_host.h | 6 ++++++
 include/linux/arm-smccc.h         | 5 +++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d5423ab..9fe1043 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -318,4 +318,10 @@ static inline int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 	return -ENXIO;
 }
 
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+	/* No way to detect it yet, pretend it is not there. */
+	return false;
+}
+
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 396eb5d..a825638 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -404,13 +404,20 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 {
 	u32 func_id = smccc_get_function(vcpu);
 	u32 val = PSCI_RET_NOT_SUPPORTED;
+	u32 feature;
 
 	switch (func_id) {
 	case ARM_SMCCC_VERSION_FUNC_ID:
 		val = ARM_SMCCC_VERSION_1_1;
 		break;
 	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
-		/* Nothing supported yet */
+		feature = smccc_get_arg1(vcpu);
+		switch(feature) {
+		case ARM_SMCCC_ARCH_WORKAROUND_1:
+			if (kvm_arm_harden_branch_predictor())
+				val = 0;
+			break;
+		}
 		break;
 	default:
 		return kvm_psci_call(vcpu);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e505038..7f5244a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -393,4 +393,10 @@ static inline void __cpu_init_stage2(void)
 		  "PARange is %d bits, unsupported configuration!", parange);
 }
 
+
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+	return cpus_have_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index dc68aa5..e1ef944 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -73,6 +73,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 1)
 
+#define ARM_SMCCC_ARCH_WORKAROUND_1					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0x8000)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
-- 
2.7.4

[PATCH 39/52] arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit f72af90c3783 upstream.

We want SMCCC_ARCH_WORKAROUND_1 to be fast. As fast as possible.
So let's intercept it as early as we can by testing for the
function call number as soon as we've identified a HVC call
coming from the guest.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm64/kvm/hyp/hyp-entry.S | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 4e92399..4e9d50c 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -79,10 +80,11 @@ alternative_endif
 	lsr	x0, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x0, #ESR_ELx_EC_HVC64
+	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
-	mrs	x1, vttbr_el2		// If vttbr is valid, the 64bit guest
-	cbnz	x1, el1_trap		// called HVC
+	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
+	cbnz	x1, el1_hvc_guest	// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
 	ldp	x0, x1, [sp], #16
@@ -101,6 +103,20 @@ alternative_endif
 
 2:	eret
 
+el1_hvc_guest:
+	/*
+	 * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1.
+	 * The workaround has already been applied on the host,
+	 * so let's quickly get back to the guest. We don't bother
+	 * restoring x1, as it can be clobbered anyway.
+	 */
+	ldr	x1, [sp]				// Guest's x0
+	eor	w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1
+	cbnz	w1, el1_trap
+	mov	x0, x1
+	add	sp, sp, #16
+	eret
+
 el1_trap:
 	/*
 	 * x0: ESR_EC
-- 
2.7.4

[PATCH 40/52] firmware/psci: Expose PSCI conduit

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 09a8d6d48499 upstream.

In order to call into the firmware to apply workarounds, it is
useful to find out whether we're using HVC or SMC. Let's expose
this through the psci_ops.

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 drivers/firmware/psci.c | 28 +++++++++++++++++++++++-----
 include/linux/psci.h    |  7 +++++++
 2 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index 9a3ce76..a49196a 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -59,7 +59,9 @@ bool psci_tos_resident_on(int cpu)
 	return cpu == resident_cpu;
 }
 
-struct psci_operations psci_ops;
+struct psci_operations psci_ops = {
+	.conduit = PSCI_CONDUIT_NONE,
+};
 
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
@@ -210,6 +212,22 @@ static unsigned long psci_migrate_info_up_cpu(void)
 			      0, 0, 0);
 }
 
+static void set_conduit(enum psci_conduit conduit)
+{
+	switch (conduit) {
+	case PSCI_CONDUIT_HVC:
+		invoke_psci_fn = __invoke_psci_fn_hvc;
+		break;
+	case PSCI_CONDUIT_SMC:
+		invoke_psci_fn = __invoke_psci_fn_smc;
+		break;
+	default:
+		WARN(1, "Unexpected PSCI conduit %d\n", conduit);
+	}
+
+	psci_ops.conduit = conduit;
+}
+
 static int get_set_conduit_method(struct device_node *np)
 {
 	const char *method;
@@ -222,9 +240,9 @@ static int get_set_conduit_method(struct device_node *np)
 	}
 
 	if (!strcmp("hvc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_hvc;
+		set_conduit(PSCI_CONDUIT_HVC);
 	} else if (!strcmp("smc", method)) {
-		invoke_psci_fn = __invoke_psci_fn_smc;
+		set_conduit(PSCI_CONDUIT_SMC);
 	} else {
 		pr_warn("invalid \"method\" property: %s\n", method);
 		return -EINVAL;
@@ -654,9 +672,9 @@ int __init psci_acpi_init(void)
 	pr_info("probing for conduit method from ACPI.\n");
 
 	if (acpi_psci_use_hvc())
-		invoke_psci_fn = __invoke_psci_fn_hvc;
+		set_conduit(PSCI_CONDUIT_HVC);
 	else
-		invoke_psci_fn = __invoke_psci_fn_smc;
+		set_conduit(PSCI_CONDUIT_SMC);
 
 	return psci_probe();
 }
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 6306ab1..66ff547 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -25,6 +25,12 @@ bool psci_tos_resident_on(int cpu);
 int psci_cpu_init_idle(unsigned int cpu);
 int psci_cpu_suspend_enter(unsigned long index);
 
+enum psci_conduit {
+	PSCI_CONDUIT_NONE,
+	PSCI_CONDUIT_SMC,
+	PSCI_CONDUIT_HVC,
+};
+
 struct psci_operations {
 	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
@@ -34,6 +40,7 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
+	enum psci_conduit conduit;
 };
 
 extern struct psci_operations psci_ops;
-- 
2.7.4

[PATCH 41/52] firmware/psci: Expose SMCCC version through psci_ops

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit e78eef554a91 upstream.

Since PSCI 1.0 allows the SMCCC version to be (indirectly) probed,
let's do that at boot time, and expose the version of the calling
convention as part of the psci_ops structure.

Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 drivers/firmware/psci.c | 27 +++++++++++++++++++++++++++
 include/linux/psci.h    |  6 ++++++
 2 files changed, 33 insertions(+)

diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index a49196a..79a48c3 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -61,6 +61,7 @@ bool psci_tos_resident_on(int cpu)
 
 struct psci_operations psci_ops = {
 	.conduit = PSCI_CONDUIT_NONE,
+	.smccc_version = SMCCC_VERSION_1_0,
 };
 
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
@@ -511,6 +512,31 @@ static void __init psci_init_migrate(void)
 	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
 }
 
+static void __init psci_init_smccc(void)
+{
+	u32 ver = ARM_SMCCC_VERSION_1_0;
+	int feature;
+
+	feature = psci_features(ARM_SMCCC_VERSION_FUNC_ID);
+
+	if (feature != PSCI_RET_NOT_SUPPORTED) {
+		u32 ret;
+		ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0);
+		if (ret == ARM_SMCCC_VERSION_1_1) {
+			psci_ops.smccc_version = SMCCC_VERSION_1_1;
+			ver = ret;
+		}
+	}
+
+	/*
+	 * Conveniently, the SMCCC and PSCI versions are encoded the
+	 * same way. No, this isn't accidental.
+	 */
+	pr_info("SMC Calling Convention v%d.%d\n",
+		PSCI_VERSION_MAJOR(ver), PSCI_VERSION_MINOR(ver));
+
+}
+
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
@@ -559,6 +585,7 @@ static int __init psci_probe(void)
 	psci_init_migrate();
 
 	if (PSCI_VERSION_MAJOR(ver) >= 1) {
+		psci_init_smccc();
 		psci_init_cpu_suspend();
 		psci_init_system_suspend();
 	}
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 66ff547..347077c 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -31,6 +31,11 @@ enum psci_conduit {
 	PSCI_CONDUIT_HVC,
 };
 
+enum smccc_version {
+	SMCCC_VERSION_1_0,
+	SMCCC_VERSION_1_1,
+};
+
 struct psci_operations {
 	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
@@ -41,6 +46,7 @@ struct psci_operations {
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
 	enum psci_conduit conduit;
+	enum smccc_version smccc_version;
 };
 
 extern struct psci_operations psci_ops;
-- 
2.7.4

[PATCH 42/52] arm/arm64: smccc: Make function identifiers an unsigned quantity

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit ded4c39e93f3 upstream.

Function identifiers are a 32bit, unsigned quantity. But we never
tell so to the compiler, resulting in the following:

 4ac:   b26187e0        mov     x0, #0xffffffff80000001

We thus rely on the firmware narrowing it for us, which is not
always a reasonable expectation.

Cc: stable@vger.kernel.org
Reported-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 include/linux/arm-smccc.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index e1ef944..dd44d84 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -14,14 +14,16 @@
 #ifndef __LINUX_ARM_SMCCC_H
 #define __LINUX_ARM_SMCCC_H
 
+#include <uapi/linux/const.h>
+
 /*
  * This file provides common defines for ARM SMC Calling Convention as
  * specified in
  * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
  */
 
-#define ARM_SMCCC_STD_CALL		0
-#define ARM_SMCCC_FAST_CALL		1
+#define ARM_SMCCC_STD_CALL	        _AC(0,U)
+#define ARM_SMCCC_FAST_CALL	        _AC(1,U)
 #define ARM_SMCCC_TYPE_SHIFT		31
 
 #define ARM_SMCCC_SMC_32		0
-- 
2.7.4

[PATCH 43/52] arm/arm64: smccc: Implement SMCCC v1.1 inline primitive

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit f2d3b2e8759a upstream.

One of the major improvement of SMCCC v1.1 is that it only clobbers
the first 4 registers, both on 32 and 64bit. This means that it
becomes very easy to provide an inline version of the SMC call
primitive, and avoid performing a function call to stash the
registers that would otherwise be clobbered by SMCCC v1.0.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 include/linux/arm-smccc.h | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index dd44d84..a031897 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -150,5 +150,146 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__)
 
+/* SMCCC v1.1 implementation madness follows */
+#ifdef CONFIG_ARM64
+
+#define SMCCC_SMC_INST	"smc	#0"
+#define SMCCC_HVC_INST	"hvc	#0"
+
+#elif defined(CONFIG_ARM)
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+#define SMCCC_SMC_INST	__SMC(0)
+#define SMCCC_HVC_INST	__HVC(0)
+
+#endif
+
+#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
+
+#define __count_args(...)						\
+	___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __constraint_write_0						\
+	"+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_1						\
+	"+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_2						\
+	"+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
+#define __constraint_write_3						\
+	"+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
+#define __constraint_write_4	__constraint_write_3
+#define __constraint_write_5	__constraint_write_4
+#define __constraint_write_6	__constraint_write_5
+#define __constraint_write_7	__constraint_write_6
+
+#define __constraint_read_0
+#define __constraint_read_1
+#define __constraint_read_2
+#define __constraint_read_3
+#define __constraint_read_4	"r" (r4)
+#define __constraint_read_5	__constraint_read_4, "r" (r5)
+#define __constraint_read_6	__constraint_read_5, "r" (r6)
+#define __constraint_read_7	__constraint_read_6, "r" (r7)
+
+#define __declare_arg_0(a0, res)					\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register unsigned long r1 asm("r1");				\
+	register unsigned long r2 asm("r2");				\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_1(a0, a1, res)					\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register unsigned long r2 asm("r2");				\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_2(a0, a1, a2, res)				\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register typeof(a2)    r2 asm("r2") = a2;			\
+	register unsigned long r3 asm("r3")
+
+#define __declare_arg_3(a0, a1, a2, a3, res)				\
+	struct arm_smccc_res   *___res = res;				\
+	register u32           r0 asm("r0") = a0;			\
+	register typeof(a1)    r1 asm("r1") = a1;			\
+	register typeof(a2)    r2 asm("r2") = a2;			\
+	register typeof(a3)    r3 asm("r3") = a3
+
+#define __declare_arg_4(a0, a1, a2, a3, a4, res)			\
+	__declare_arg_3(a0, a1, a2, a3, res);				\
+	register typeof(a4) r4 asm("r4") = a4
+
+#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res)			\
+	__declare_arg_4(a0, a1, a2, a3, a4, res);			\
+	register typeof(a5) r5 asm("r5") = a5
+
+#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res)		\
+	__declare_arg_5(a0, a1, a2, a3, a4, a5, res);			\
+	register typeof(a6) r6 asm("r6") = a6
+
+#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
+	__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res);		\
+	register typeof(a7) r7 asm("r7") = a7
+
+#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
+#define __declare_args(count, ...)  ___declare_args(count, __VA_ARGS__)
+
+#define ___constraints(count)						\
+	: __constraint_write_ ## count					\
+	: __constraint_read_ ## count					\
+	: "memory"
+#define __constraints(count)	___constraints(count)
+
+/*
+ * We have an output list that is not necessarily used, and GCC feels
+ * entitled to optimise the whole sequence away. "volatile" is what
+ * makes it stick.
+ */
+#define __arm_smccc_1_1(inst, ...)					\
+	do {								\
+		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
+		asm volatile(inst "\n"					\
+			     __constraints(__count_args(__VA_ARGS__)));	\
+		if (___res)						\
+			*___res = (typeof(*___res)){r0, r1, r2, r3};	\
+	} while (0)
+
+/*
+ * arm_smccc_1_1_smc() - make an SMCCC v1.1 compliant SMC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make SMC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the SMC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the SMC instruction if not NULL.
+ */
+#define arm_smccc_1_1_smc(...)	__arm_smccc_1_1(SMCCC_SMC_INST, __VA_ARGS__)
+
+/*
+ * arm_smccc_1_1_hvc() - make an SMCCC v1.1 compliant HVC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make HVC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the HVC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the HVC instruction if not NULL.
+ */
+#define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
-- 
2.7.4

[PATCH 44/52] arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit b092201e0020 upstream.

Add the detection and runtime code for ARM_SMCCC_ARCH_WORKAROUND_1.
It is lovely. Really.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no qcom hyp functions in
	arch/arm64/kernel/bpi.S
	arch/arm64/kernel/cpu_errata.c
---
 arch/arm64/kernel/bpi.S        | 20 ++++++++++++
 arch/arm64/kernel/cpu_errata.c | 72 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 89 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
index dec95bd..c72f261 100644
--- a/arch/arm64/kernel/bpi.S
+++ b/arch/arm64/kernel/bpi.S
@@ -17,6 +17,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/arm-smccc.h>
 
 .macro ventry target
 	.rept 31
@@ -77,3 +78,22 @@ ENTRY(__psci_hyp_bp_inval_start)
 	ldp	x0, x1, [sp, #(16 * 8)]
 	add	sp, sp, #(8 * 18)
 ENTRY(__psci_hyp_bp_inval_end)
+
+.macro smccc_workaround_1 inst
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	\inst	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+.endm
+
+ENTRY(__smccc_workaround_1_smc_start)
+	smccc_workaround_1	smc
+ENTRY(__smccc_workaround_1_smc_end)
+
+ENTRY(__smccc_workaround_1_hvc_start)
+	smccc_workaround_1	hvc
+ENTRY(__smccc_workaround_1_hvc_end)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index f8810bf..9632319 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -54,6 +54,10 @@ DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 #ifdef CONFIG_KVM
 extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
+extern char __smccc_workaround_1_smc_start[];
+extern char __smccc_workaround_1_smc_end[];
+extern char __smccc_workaround_1_hvc_start[];
+extern char __smccc_workaround_1_hvc_end[];
 
 static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 				const char *hyp_vecs_end)
@@ -96,8 +100,12 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 	spin_unlock(&bp_lock);
 }
 #else
-#define __psci_hyp_bp_inval_start	NULL
-#define __psci_hyp_bp_inval_end		NULL
+#define __psci_hyp_bp_inval_start		NULL
+#define __psci_hyp_bp_inval_end			NULL
+#define __smccc_workaround_1_smc_start		NULL
+#define __smccc_workaround_1_smc_end		NULL
+#define __smccc_workaround_1_hvc_start		NULL
+#define __smccc_workaround_1_hvc_end		NULL
 
 static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
@@ -124,17 +132,75 @@ static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
 	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
 }
 
+#include <uapi/linux/psci.h>
+#include <linux/arm-smccc.h>
 #include <linux/psci.h>
 
+static void call_smc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void call_hvc_arch_workaround_1(void)
+{
+	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static bool check_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+{
+	bp_hardening_cb_t cb;
+	void *smccc_start, *smccc_end;
+	struct arm_smccc_res res;
+
+	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
+		return false;
+
+	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+		return false;
+
+	switch (psci_ops.conduit) {
+	case PSCI_CONDUIT_HVC:
+		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+		if (res.a0)
+			return false;
+		cb = call_hvc_arch_workaround_1;
+		smccc_start = __smccc_workaround_1_hvc_start;
+		smccc_end = __smccc_workaround_1_hvc_end;
+		break;
+
+	case PSCI_CONDUIT_SMC:
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+		if (res.a0)
+			return false;
+		cb = call_smc_arch_workaround_1;
+		smccc_start = __smccc_workaround_1_smc_start;
+		smccc_end = __smccc_workaround_1_smc_end;
+		break;
+
+	default:
+		return false;
+	}
+
+	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+
+	return true;
+}
+
 static int enable_psci_bp_hardening(void *data)
 {
 	const struct arm64_cpu_capabilities *entry = data;
 
-	if (psci_ops.get_version)
+	if (psci_ops.get_version) {
+		if (check_smccc_arch_workaround_1(entry))
+			return 0;
+
 		install_bp_hardening_cb(entry,
 				       (bp_hardening_cb_t)psci_ops.get_version,
 				       __psci_hyp_bp_inval_start,
 				       __psci_hyp_bp_inval_end);
+	}
 
 	return 0;
 }
-- 
2.7.4

[PATCH 45/52] arm64: Kill PSCI_GET_VERSION as a variant-2 workaround

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

commit 3a0a397ff5ff upstream.

Now that we've standardised on SMCCC v1.1 to perform the branch
prediction invalidation, let's drop the previous band-aid.
If vendors haven't updated their firmware to do SMCCC 1.1, they
haven't updated PSCI either, so we don't loose anything.

Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no falkor/thunderx2/vulcan in arch/arm64/kernel/cpu_errata.c
---
 arch/arm64/kernel/bpi.S        | 24 ------------------------
 arch/arm64/kernel/cpu_errata.c | 41 +++++++++++------------------------------
 arch/arm64/kvm/hyp/switch.c    | 14 --------------
 3 files changed, 11 insertions(+), 68 deletions(-)

diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S
index c72f261..dc4eb15 100644
--- a/arch/arm64/kernel/bpi.S
+++ b/arch/arm64/kernel/bpi.S
@@ -54,30 +54,6 @@ ENTRY(__bp_harden_hyp_vecs_start)
 	vectors __kvm_hyp_vector
 	.endr
 ENTRY(__bp_harden_hyp_vecs_end)
-ENTRY(__psci_hyp_bp_inval_start)
-	sub	sp, sp, #(8 * 18)
-	stp	x16, x17, [sp, #(16 * 0)]
-	stp	x14, x15, [sp, #(16 * 1)]
-	stp	x12, x13, [sp, #(16 * 2)]
-	stp	x10, x11, [sp, #(16 * 3)]
-	stp	x8, x9, [sp, #(16 * 4)]
-	stp	x6, x7, [sp, #(16 * 5)]
-	stp	x4, x5, [sp, #(16 * 6)]
-	stp	x2, x3, [sp, #(16 * 7)]
-	stp	x0, x1, [sp, #(16 * 8)]
-	mov	x0, #0x84000000
-	smc	#0
-	ldp	x16, x17, [sp, #(16 * 0)]
-	ldp	x14, x15, [sp, #(16 * 1)]
-	ldp	x12, x13, [sp, #(16 * 2)]
-	ldp	x10, x11, [sp, #(16 * 3)]
-	ldp	x8, x9, [sp, #(16 * 4)]
-	ldp	x6, x7, [sp, #(16 * 5)]
-	ldp	x4, x5, [sp, #(16 * 6)]
-	ldp	x2, x3, [sp, #(16 * 7)]
-	ldp	x0, x1, [sp, #(16 * 8)]
-	add	sp, sp, #(8 * 18)
-ENTRY(__psci_hyp_bp_inval_end)
 
 .macro smccc_workaround_1 inst
 	sub	sp, sp, #(8 * 4)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 9632319..8b74f80 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -53,7 +53,6 @@ static int cpu_enable_trap_ctr_access(void *__unused)
 DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 #ifdef CONFIG_KVM
-extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
 extern char __smccc_workaround_1_smc_start[];
 extern char __smccc_workaround_1_smc_end[];
 extern char __smccc_workaround_1_hvc_start[];
@@ -100,8 +99,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 	spin_unlock(&bp_lock);
 }
 #else
-#define __psci_hyp_bp_inval_start		NULL
-#define __psci_hyp_bp_inval_end			NULL
 #define __smccc_workaround_1_smc_start		NULL
 #define __smccc_workaround_1_smc_end		NULL
 #define __smccc_workaround_1_hvc_start		NULL
@@ -146,24 +143,25 @@ static void call_hvc_arch_workaround_1(void)
 	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static bool check_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static int enable_smccc_arch_workaround_1(void *data)
 {
+	const struct arm64_cpu_capabilities *entry = data;
 	bp_hardening_cb_t cb;
 	void *smccc_start, *smccc_end;
 	struct arm_smccc_res res;
 
 	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return false;
+		return 0;
 
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return false;
+		return 0;
 
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		if (res.a0)
-			return false;
+			return 0;
 		cb = call_hvc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_hvc_start;
 		smccc_end = __smccc_workaround_1_hvc_end;
@@ -173,35 +171,18 @@ static bool check_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *e
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 		if (res.a0)
-			return false;
+			return 0;
 		cb = call_smc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_smc_start;
 		smccc_end = __smccc_workaround_1_smc_end;
 		break;
 
 	default:
-		return false;
+		return 0;
 	}
 
 	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
 
-	return true;
-}
-
-static int enable_psci_bp_hardening(void *data)
-{
-	const struct arm64_cpu_capabilities *entry = data;
-
-	if (psci_ops.get_version) {
-		if (check_smccc_arch_workaround_1(entry))
-			return 0;
-
-		install_bp_hardening_cb(entry,
-				       (bp_hardening_cb_t)psci_ops.get_version,
-				       __psci_hyp_bp_inval_start,
-				       __psci_hyp_bp_inval_end);
-	}
-
 	return 0;
 }
 #endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
@@ -301,22 +282,22 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-		.enable = enable_psci_bp_hardening,
+		.enable = enable_smccc_arch_workaround_1,
 	},
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-		.enable = enable_psci_bp_hardening,
+		.enable = enable_smccc_arch_workaround_1,
 	},
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-		.enable = enable_psci_bp_hardening,
+		.enable = enable_smccc_arch_workaround_1,
 	},
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-		.enable = enable_psci_bp_hardening,
+		.enable = enable_smccc_arch_workaround_1,
 	},
 #endif
 	{
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 996328e..154b471 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -311,20 +311,6 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
 		goto again;
 
-	if (exit_code == ARM_EXCEPTION_TRAP &&
-	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
-	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32)) {
-		u32 val = vcpu_get_reg(vcpu, 0);
-
-		if (val == PSCI_0_2_FN_PSCI_VERSION) {
-			val = kvm_psci_version(vcpu, kern_hyp_va(vcpu->kvm));
-			if (unlikely(val == KVM_ARM_PSCI_0_1))
-				val = PSCI_RET_NOT_SUPPORTED;
-			vcpu_set_reg(vcpu, 0, val);
-			goto again;
-		}
-	}
-
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
 	    exit_code == ARM_EXCEPTION_TRAP) {
 		bool valid;
-- 
2.7.4

[PATCH 46/52] arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to avoid aliasing attacks against the branch predictor,
some implementations require to invalidate the BTB when switching
from one user context to another.

For this, we reuse the existing implementation for Cortex-A8, and
apply it to A9, A12 and A17.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm/mm/Kconfig          | 17 +++++++++++++++++
 arch/arm/mm/proc-v7-2level.S |  4 ++--
 arch/arm/mm/proc-v7-3level.S |  5 +++++
 arch/arm/mm/proc-v7.S        | 30 ++++++++++++++++++++++++++++--
 4 files changed, 52 insertions(+), 4 deletions(-)

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c1799dd..1a5acee 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1068,3 +1068,20 @@ config DEBUG_ALIGN_RODATA
 	  additional section-aligned split of rodata from kernel text so it
 	  can be made explicitly non-executable. This padding may waste memory
 	  space to gain the additional protection.
+
+config HARDEN_BRANCH_PREDICTOR
+	bool "Harden the branch predictor against aliasing attacks" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors rely on
+	  being able to manipulate the branch predictor for a victim context by
+	  executing aliasing branches in the attacker context.  Such attacks
+	  can be partially mitigated against by clearing internal branch
+	  predictor state and limiting the prediction logic in some situations.
+
+	  This config option will take CPU-specific actions to harden the
+	  branch predictor against aliasing attacks and may rely on specific
+	  instruction sequences or control bits being set by the system
+	  firmware.
+
+	  If unsure, say Y.
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index c6141a5..0422e58b 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -41,7 +41,7 @@
  *	even on Cortex-A8 revisions not affected by 430973.
  *	If IBE is not set, the flush BTAC/BTB won't do anything.
  */
-ENTRY(cpu_ca8_switch_mm)
+ENTRY(cpu_v7_btbinv_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
@@ -66,7 +66,7 @@ ENTRY(cpu_v7_switch_mm)
 #endif
 	bx	lr
 ENDPROC(cpu_v7_switch_mm)
-ENDPROC(cpu_ca8_switch_mm)
+ENDPROC(cpu_v7_btbinv_switch_mm)
 
 /*
  *	cpu_v7_set_pte_ext(ptep, pte)
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 5e5720e..a25450b 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -54,6 +54,10 @@
  * Set the translation table base pointer to be pgd_phys (physical address of
  * the new TTB).
  */
+ENTRY(cpu_v7_btbinv_switch_mm)
+#ifdef CONFIG_MMU
+	mcr	p15, 0, r0, c7, c5, 6			@ flush BTAC/BTB
+#endif
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mmid	r2, r2
@@ -64,6 +68,7 @@ ENTRY(cpu_v7_switch_mm)
 #endif
 	ret	lr
 ENDPROC(cpu_v7_switch_mm)
+ENDPROC(cpu_v7_btbinv_switch_mm)
 
 #ifdef __ARMEB__
 #define rl r3
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index d00d52c..ff7018a 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -163,6 +163,7 @@ ENDPROC(cpu_v7_do_resume)
 	globl_equ	cpu_ca8_dcache_clean_area, cpu_v7_dcache_clean_area
 	globl_equ	cpu_ca8_set_pte_ext,	cpu_v7_set_pte_ext
 	globl_equ	cpu_ca8_suspend_size,	cpu_v7_suspend_size
+	globl_equ	cpu_ca8_switch_mm,	cpu_v7_btbinv_switch_mm
 #ifdef CONFIG_ARM_CPU_SUSPEND
 	globl_equ	cpu_ca8_do_suspend,	cpu_v7_do_suspend
 	globl_equ	cpu_ca8_do_resume,	cpu_v7_do_resume
@@ -176,7 +177,11 @@ ENDPROC(cpu_v7_do_resume)
 	globl_equ	cpu_ca9mp_reset,	cpu_v7_reset
 	globl_equ	cpu_ca9mp_do_idle,	cpu_v7_do_idle
 	globl_equ	cpu_ca9mp_dcache_clean_area, cpu_v7_dcache_clean_area
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	globl_equ	cpu_ca9mp_switch_mm,	cpu_v7_btbinv_switch_mm
+#else
 	globl_equ	cpu_ca9mp_switch_mm,	cpu_v7_switch_mm
+#endif
 	globl_equ	cpu_ca9mp_set_pte_ext,	cpu_v7_set_pte_ext
 .globl	cpu_ca9mp_suspend_size
 .equ	cpu_ca9mp_suspend_size, cpu_v7_suspend_size + 4 * 2
@@ -202,6 +207,26 @@ ENTRY(cpu_ca9mp_do_resume)
 ENDPROC(cpu_ca9mp_do_resume)
 #endif
 
+/*
+ * Cortex-A12/A17
+ */
+	globl_equ	cpu_ca17_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca17_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca17_reset,		cpu_v7_reset
+	globl_equ	cpu_ca17_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca17_dcache_clean_area, cpu_v7_dcache_clean_area
+	globl_equ	cpu_ca17_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_ca17_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	globl_equ	cpu_ca17_switch_mm,	cpu_v7_btbinv_switch_mm
+#else
+	globl_equ	cpu_ca17_switch_mm,	cpu_v7_switch_mm
+#endif
+#ifdef CONFIG_ARM_CPU_SUSPEND
+	globl_equ	cpu_ca17_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_ca17_do_resume,	cpu_v7_do_resume
+#endif
+
 #ifdef CONFIG_CPU_PJ4B
 	globl_equ	cpu_pj4b_switch_mm,     cpu_v7_switch_mm
 	globl_equ	cpu_pj4b_set_pte_ext,	cpu_v7_set_pte_ext
@@ -543,6 +568,7 @@ __v7_setup_stack:
 
 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
 	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+	define_processor_functions ca17, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 #ifndef CONFIG_ARM_LPAE
 	define_processor_functions ca8, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 	define_processor_functions ca9mp, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
@@ -653,7 +679,7 @@ __v7_ca7mp_proc_info:
 __v7_ca12mp_proc_info:
 	.long	0x410fc0d0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca12mp_proc_info, __v7_ca12mp_setup
+	__v7_proc __v7_ca12mp_proc_info, __v7_ca12mp_setup, proc_fns = ca17_processor_functions
 	.size	__v7_ca12mp_proc_info, . - __v7_ca12mp_proc_info
 
 	/*
@@ -683,7 +709,7 @@ __v7_b15mp_proc_info:
 __v7_ca17mp_proc_info:
 	.long	0x410fc0e0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca17mp_proc_info, __v7_ca17mp_setup
+	__v7_proc __v7_ca17mp_proc_info, __v7_ca17mp_setup, proc_fns = ca17_processor_functions
 	.size	__v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info
 
 	/*
-- 
2.7.4

Re: [PATCH 46/52] arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17

[Greg KH]

On Mon, Feb 26, 2018 at 04:20:20PM +0800, Alex Shi wrote:
> From: Marc Zyngier <marc.zyngier@arm.com>
> 
> ** Not yet queued for inclusion in mainline **

As Marc said, this should have been a HUGE clue that we can't take this
patch.  Please go re-read
	https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html

thanks,

greg k-h

Re: [PATCH 46/52] arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17

[Alex Shi]

On 02/26/2018 06:05 PM, Greg KH wrote:
> On Mon, Feb 26, 2018 at 04:20:20PM +0800, Alex Shi wrote:
>> From: Marc Zyngier <marc.zyngier@arm.com>
>>
>> ** Not yet queued for inclusion in mainline **
> 
> As Marc said, this should have been a HUGE clue that we can't take this
> patch.  Please go re-read
> 	https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
> 

Thanks for comments, Greg!

I read the rules for several times, and thought it maybe a exception for
this bug fix. But since MarcZ said so. We can wait. :)

Regards
Alex

Re: [PATCH 46/52] arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17

[Will Deacon]

On Mon, Feb 26, 2018 at 06:40:42PM +0800, Alex Shi wrote:
> 
> 
> On 02/26/2018 06:05 PM, Greg KH wrote:
> > On Mon, Feb 26, 2018 at 04:20:20PM +0800, Alex Shi wrote:
> >> From: Marc Zyngier <marc.zyngier@arm.com>
> >>
> >> ** Not yet queued for inclusion in mainline **
> > 
> > As Marc said, this should have been a HUGE clue that we can't take this
> > patch.  Please go re-read
> > 	https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
> > 
> 
> Thanks for comments, Greg!
> 
> I read the rules for several times, and thought it maybe a exception for
> this bug fix. But since MarcZ said so. We can wait. :)

The reason I added the disclaimer to the commit message was precisely to
avoid these things accidentally going into stable. If stable diverges
significantly from mainline, it's just going to make backports of other
patches more difficult. So no, we shouldn't be considering an exception
for this.

Will

Re: [PATCH 46/52] arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17

[Alex Shi]

On 02/26/2018 06:45 PM, Will Deacon wrote:
> On Mon, Feb 26, 2018 at 06:40:42PM +0800, Alex Shi wrote:
>>
>>
>> On 02/26/2018 06:05 PM, Greg KH wrote:
>>> On Mon, Feb 26, 2018 at 04:20:20PM +0800, Alex Shi wrote:
>>>> From: Marc Zyngier <marc.zyngier@arm.com>
>>>>
>>>> ** Not yet queued for inclusion in mainline **
>>>
>>> As Marc said, this should have been a HUGE clue that we can't take this
>>> patch.  Please go re-read
>>> 	https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
>>>
>>
>> Thanks for comments, Greg!
>>
>> I read the rules for several times, and thought it maybe a exception for
>> this bug fix. But since MarcZ said so. We can wait. :)
> 
> The reason I added the disclaimer to the commit message was precisely to
> avoid these things accidentally going into stable. If stable diverges
> significantly from mainline, it's just going to make backports of other
> patches more difficult. So no, we shouldn't be considering an exception
> for this.
> 

Hi Will,

Got it. Thanks for explanations!
I remove all non upstream patches and put it on

git://git.linaro.org/kernel/linux-linaro-stable.git
v4.9-spectre-upstream-only

If other patches passed review. it could be got as whole branch from there.

Thanks
Alex

[PATCH 47/52] arm: Invalidate BTB on prefetch abort outside of user mapping on Cortex A8, A9, A12 and A17

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to prevent aliasing attacks on the branch predictor,
invalidate the BTB on CPUs that are known to be affected when taking
a prefetch abort on a address that is outside of a user task limit.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm/include/asm/cp15.h |  2 ++
 arch/arm/mm/fault.c         | 25 ++++++++++++++++
 arch/arm/mm/fsr-2level.c    |  4 +--
 arch/arm/mm/fsr-3level.c    | 69 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index dbdbce1..0672ddc 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -64,6 +64,8 @@
 #define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
 #define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
 
+#define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index f7861dc..17fd0c7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/cp15.h>
 #include <asm/exception.h>
 #include <asm/pgtable.h>
 #include <asm/system_misc.h>
@@ -395,12 +396,36 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	__do_kernel_fault(mm, addr, fsr, regs);
 	return 0;
 }
+
+static int __maybe_unused
+do_pabt_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
+{
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	if (addr > TASK_SIZE) {
+		switch (read_cpuid_part()) {
+		case ARM_CPU_PART_CORTEX_A8:
+		case ARM_CPU_PART_CORTEX_A9:
+		case ARM_CPU_PART_CORTEX_A12:
+		case ARM_CPU_PART_CORTEX_A17:
+			write_sysreg(0, BPIALL);
+			break;
+		}
+	}
+#endif
+	return do_page_fault(addr, fsr, regs);
+}
 #else					/* CONFIG_MMU */
 static int
 do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	return 0;
 }
+
+static int
+do_pabt_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
+{
+	return 0;
+}
 #endif					/* CONFIG_MMU */
 
 /*
diff --git a/arch/arm/mm/fsr-2level.c b/arch/arm/mm/fsr-2level.c
index 18ca74c..4cede9b 100644
--- a/arch/arm/mm/fsr-2level.c
+++ b/arch/arm/mm/fsr-2level.c
@@ -50,7 +50,7 @@ static struct fsr_info ifsr_info[] = {
 	{ do_bad,		SIGBUS,  0,		"unknown 4"			   },
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page access flag fault"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
 	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
 	{ do_bad,		SIGBUS,  0,		"unknown 10"			   },
@@ -58,7 +58,7 @@ static struct fsr_info ifsr_info[] = {
 	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
 	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
 	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
-	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
 	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c
index ab4409a..2745f7f 100644
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@@ -65,4 +65,73 @@ static struct fsr_info fsr_info[] = {
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+static struct fsr_info ifsr_info[] = {
+	{ do_bad,		SIGBUS,  0,		"unknown 0"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 1"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 2"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 3"			},
+	{ do_bad,		SIGBUS,  0,		"reserved translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_pabt_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
+	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
+	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
+};
+#else
 #define ifsr_info	fsr_info
+#endif
-- 
2.7.4

[PATCH 48/52] arm: KVM: Invalidate BTB on guest exit for Cortex-A12/A17

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to avoid aliasing attacks against the branch predictor,
let's invalidate the BTB on guest exit. This is made complicated
by the fact that we cannot take a branch before invalidating the
BTB.

We only apply this to A12 and A17, which are the only two ARM
cores on which this useful.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	no hvc stub in hyp_hvc in arch/arm/kvm/hyp/hyp-entry.S
---
 arch/arm/include/asm/kvm_asm.h |  2 --
 arch/arm/include/asm/kvm_mmu.h | 18 ++++++++++-
 arch/arm/kvm/hyp/hyp-entry.S   | 71 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 86 insertions(+), 5 deletions(-)

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 8ef0538..24f3ec7 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,8 +61,6 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index d10e362..2887129 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -37,6 +37,7 @@
 
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
@@ -225,7 +226,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
 
 static inline void *kvm_get_hyp_vector(void)
 {
-	return kvm_ksym_ref(__kvm_hyp_vector);
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A17:
+	{
+		extern char __kvm_hyp_vector_bp_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
+	}
+
+#endif
+	default:
+	{
+		extern char __kvm_hyp_vector[];
+		return kvm_ksym_ref(__kvm_hyp_vector);
+	}
+	}
 }
 
 static inline int kvm_map_vectors(void)
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
index 96beb53..b6b8cb1 100644
--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -71,6 +71,66 @@ __kvm_hyp_vector:
 	W(b)	hyp_irq
 	W(b)	hyp_fiq
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	.align 5
+__kvm_hyp_vector_bp_inv:
+	.global __kvm_hyp_vector_bp_inv
+
+	/*
+	 * We encode the exception entry in the bottom 3 bits of
+	 * SP, and we have to guarantee to be 8 bytes aligned.
+	 */
+	W(add)	sp, sp, #1	/* Reset 	  7 */
+	W(add)	sp, sp, #1	/* Undef	  6 */
+	W(add)	sp, sp, #1	/* Syscall	  5 */
+	W(add)	sp, sp, #1	/* Prefetch abort 4 */
+	W(add)	sp, sp, #1	/* Data abort	  3 */
+	W(add)	sp, sp, #1	/* HVC		  2 */
+	W(add)	sp, sp, #1	/* IRQ		  1 */
+	W(nop)			/* FIQ		  0 */
+
+	mcr	p15, 0, r0, c7, c5, 6	/* BPIALL */
+	isb
+
+#ifdef CONFIG_THUMB2_KERNEL
+	/*
+	 * Yet another silly hack: Use VPIDR as a temp register.
+	 * Thumb2 is really a pain, as SP cannot be used with most
+	 * of the bitwise instructions. The vect_br macro ensures
+	 * things gets cleaned-up.
+	 */
+	mcr	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mov	r0, sp
+	and	r0, r0, #7
+	sub	sp, sp, r0
+	push	{r1, r2}
+	mov	r1, r0
+	mrc	p15, 4, r0, c0, c0, 0	/* VPIDR */
+	mrc	p15, 0, r2, c0, c0, 0	/* MIDR  */
+	mcr	p15, 4, r2, c0, c0, 0	/* VPIDR */
+#endif
+
+.macro vect_br val, targ
+ARM(	eor	sp, sp, #\val	)
+ARM(	tst	sp, #7		)
+ARM(	eorne	sp, sp, #\val	)
+
+THUMB(	cmp	r1, #\val	)
+THUMB(	popeq	{r1, r2}	)
+
+	beq	\targ
+.endm
+
+	vect_br	0, hyp_fiq
+	vect_br	1, hyp_irq
+	vect_br	2, hyp_hvc
+	vect_br	3, hyp_dabt
+	vect_br	4, hyp_pabt
+	vect_br	5, hyp_svc
+	vect_br	6, hyp_undef
+	vect_br	7, hyp_reset
+#endif
+
 .macro invalid_vector label, cause
 	.align
 \label:	mov	r0, #\cause
@@ -131,7 +191,14 @@ hyp_hvc:
 	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
 	beq	1f
 
-	push	{lr}
+	/*
+	 * Pushing r2 here is just a way of keeping the stack aligned to
+	 * 8 bytes on any path that can trigger a HYP exception. Here,
+	 * we may well be about to jump into the guest, and the guest
+	 * exit would otherwise be badly decoded by our fancy
+	 * "decode-exception-without-a-branch" code...
+	 */
+	push    {r2, lr}
 
 	mov	lr, r0
 	mov	r0, r1
@@ -141,7 +208,7 @@ hyp_hvc:
 THUMB(	orr	lr, #1)
 	blx	lr			@ Call the HYP function
 
-	pop	{lr}
+	pop	{r2, lr}
 1:	eret
 
 guest_trap:
-- 
2.7.4

[PATCH 49/52] arm: Add icache invalidation on switch_mm for Cortex-A15

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to avoid aliasing attacks against the branch predictor,
Cortex-A15 require to invalidate the BTB when switching
from one user context to another. The only way to do so on this
CPU is to perform an ICIALLU, having set ACTLR[0] to 1 from secure
mode.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm/mm/proc-v7-2level.S | 10 ++++++++++
 arch/arm/mm/proc-v7-3level.S | 10 ++++++++++
 arch/arm/mm/proc-v7.S        | 23 ++++++++++++++++++++++-
 3 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 0422e58b..6d81ed7 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -40,7 +40,16 @@
  *	Note that we always need to flush BTAC/BTB if IBE is set
  *	even on Cortex-A8 revisions not affected by 430973.
  *	If IBE is not set, the flush BTAC/BTB won't do anything.
+ *
+ *	Cortex-A15 requires ACTLR[0] to be set from secure in order
+ *	for the icache invalidation to also invalidate the BTB.
  */
+ENTRY(cpu_v7_icinv_switch_mm)
+#ifdef CONFIG_MMU
+	mcr	p15, 0, r0, c7, c5, 0		@ ICIALLU
+	/* Fall through to switch_mm... */
+#endif
+
 ENTRY(cpu_v7_btbinv_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
@@ -67,6 +76,7 @@ ENTRY(cpu_v7_switch_mm)
 	bx	lr
 ENDPROC(cpu_v7_switch_mm)
 ENDPROC(cpu_v7_btbinv_switch_mm)
+ENDPROC(cpu_v7_icinv_switch_mm)
 
 /*
  *	cpu_v7_set_pte_ext(ptep, pte)
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index a25450b..af6d7b1 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -54,6 +54,15 @@
  * Set the translation table base pointer to be pgd_phys (physical address of
  * the new TTB).
  */
+ENTRY(cpu_v7_icinv_switch_mm)
+#ifdef CONFIG_MMU
+	/*
+	 * Cortex-A15 requires ACTLR[0] to be set from secure in order
+	 * for the icache invalidation to also invalidate the BTB.
+	 */
+	mcr	p15, 0, r0, c7, c5, 0		@ ICIALLU
+	/* Fall through to switch_mm... */
+#endif
 ENTRY(cpu_v7_btbinv_switch_mm)
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c7, c5, 6			@ flush BTAC/BTB
@@ -69,6 +78,7 @@ ENTRY(cpu_v7_switch_mm)
 	ret	lr
 ENDPROC(cpu_v7_switch_mm)
 ENDPROC(cpu_v7_btbinv_switch_mm)
+ENDPROC(cpu_v7_icinv_switch_mm)
 
 #ifdef __ARMEB__
 #define rl r3
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index ff7018a..f385933 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -227,6 +227,26 @@ ENDPROC(cpu_ca9mp_do_resume)
 	globl_equ	cpu_ca17_do_resume,	cpu_v7_do_resume
 #endif
 
+/*
+ * Cortex-A15
+ */
+	globl_equ	cpu_ca15_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca15_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca15_reset,		cpu_v7_reset
+	globl_equ	cpu_ca15_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca15_dcache_clean_area, cpu_v7_dcache_clean_area
+	globl_equ	cpu_ca15_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_ca15_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	globl_equ	cpu_ca15_switch_mm,	cpu_v7_icinv_switch_mm
+#else
+	globl_equ	cpu_ca15_switch_mm,	cpu_v7_switch_mm
+#endif
+#ifdef CONFIG_ARM_CPU_SUSPEND
+	globl_equ	cpu_ca15_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_ca15_do_resume,	cpu_v7_do_resume
+#endif
+
 #ifdef CONFIG_CPU_PJ4B
 	globl_equ	cpu_pj4b_switch_mm,     cpu_v7_switch_mm
 	globl_equ	cpu_pj4b_set_pte_ext,	cpu_v7_set_pte_ext
@@ -568,6 +588,7 @@ __v7_setup_stack:
 
 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
 	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+	define_processor_functions ca15, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 	define_processor_functions ca17, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 #ifndef CONFIG_ARM_LPAE
 	define_processor_functions ca8, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
@@ -689,7 +710,7 @@ __v7_ca12mp_proc_info:
 __v7_ca15mp_proc_info:
 	.long	0x410fc0f0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca15mp_proc_info, __v7_ca15mp_setup
+	__v7_proc __v7_ca15mp_proc_info, __v7_ca15mp_setup, proc_fns = ca15_processor_functions
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
-- 
2.7.4

[PATCH 50/52] arm: Invalidate icache on prefetch abort outside of user mapping on Cortex-A15

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to prevent aliasing attacks on the branch predictor,
invalidate the icache on Cortex-A15, which has the side effect
of invalidating the BTB. This requires ACTLR[0] to be set to 1
(secure operation).

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm/include/asm/cp15.h | 1 +
 arch/arm/mm/fault.c         | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 0672ddc..b74b174 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -65,6 +65,7 @@
 #define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
 
 #define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
+#define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
 
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 17fd0c7..a9c924b 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -409,6 +409,10 @@ do_pabt_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		case ARM_CPU_PART_CORTEX_A17:
 			write_sysreg(0, BPIALL);
 			break;
+
+		case ARM_CPU_PART_CORTEX_A15:
+			write_sysreg(0, ICIALLU);
+			break;
 		}
 	}
 #endif
-- 
2.7.4

[PATCH 51/52] arm: KVM: Invalidate icache on guest exit for Cortex-A15

[Alex Shi]

From: Marc Zyngier <marc.zyngier@arm.com>

** Not yet queued for inclusion in mainline **

In order to avoid aliasing attacks against the branch predictor
on Cortex-A15, let's invalidate the BTB on guest exit, which can
only be done by invalidating the icache (with ACTLR[0] being set).

We use the same hack as for A12/A17 to perform the vector decoding.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 arch/arm/include/asm/kvm_mmu.h |  5 +++++
 arch/arm/kvm/hyp/hyp-entry.S   | 24 ++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 2887129..a602467 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -235,6 +235,11 @@ static inline void *kvm_get_hyp_vector(void)
 		return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
 	}
 
+	case ARM_CPU_PART_CORTEX_A15:
+	{
+		extern char __kvm_hyp_vector_ic_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_ic_inv);
+	}
 #endif
 	default:
 	{
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
index b6b8cb1..4492768 100644
--- a/arch/arm/kvm/hyp/hyp-entry.S
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -73,6 +73,28 @@ __kvm_hyp_vector:
 
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	.align 5
+__kvm_hyp_vector_ic_inv:
+	.global __kvm_hyp_vector_ic_inv
+
+	/*
+	 * We encode the exception entry in the bottom 3 bits of
+	 * SP, and we have to guarantee to be 8 bytes aligned.
+	 */
+	W(add)	sp, sp, #1	/* Reset 	  7 */
+	W(add)	sp, sp, #1	/* Undef	  6 */
+	W(add)	sp, sp, #1	/* Syscall	  5 */
+	W(add)	sp, sp, #1	/* Prefetch abort 4 */
+	W(add)	sp, sp, #1	/* Data abort	  3 */
+	W(add)	sp, sp, #1	/* HVC		  2 */
+	W(add)	sp, sp, #1	/* IRQ		  1 */
+	W(nop)			/* FIQ		  0 */
+
+	mcr	p15, 0, r0, c7, c5, 0	/* ICIALLU */
+	isb
+
+	b	decode_vectors
+
+	.align 5
 __kvm_hyp_vector_bp_inv:
 	.global __kvm_hyp_vector_bp_inv
 
@@ -92,6 +114,8 @@ __kvm_hyp_vector_bp_inv:
 	mcr	p15, 0, r0, c7, c5, 6	/* BPIALL */
 	isb
 
+decode_vectors:
+
 #ifdef CONFIG_THUMB2_KERNEL
 	/*
 	 * Yet another silly hack: Use VPIDR as a temp register.
-- 
2.7.4

[PATCH 52/52] arm64: Add README describing the branch

[Alex Shi]

From: Will Deacon <will.deacon@arm.com>

Provide some basic guidance about this branch, its layout and how we plan
to deploy changes in the future.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Shi <alex.shi@linaro.org>
---
 SPECTRE-MELTDOWN-MITIGATIONS.README | 41 +++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 SPECTRE-MELTDOWN-MITIGATIONS.README

diff --git a/SPECTRE-MELTDOWN-MITIGATIONS.README b/SPECTRE-MELTDOWN-MITIGATIONS.README
new file mode 100644
index 0000000..7b71b81
--- /dev/null
+++ b/SPECTRE-MELTDOWN-MITIGATIONS.README
@@ -0,0 +1,41 @@
+INTRODUCTION
+============
+
+This branch is based on the v4.15 release of Linux and contains arm64
+mitigations against the cache speculation side-channels described at
+http://www.arm.com/security-update and commonly referred to as "Spectre" and
+"Meltdown". Mitigations against variant 2 are also included for the 32-bit
+armv7 architecture.
+
+
+LAYOUT
+======
+
+Each commit contains a subject prefix which clearly identifies the variant
+which it is attempting to mitigate against:
+
+  [Variant 1/Spectre-v1]
+  [Variant 2/Spectre-v2]
+  [Variant 3/Meltdown]
+
+The commit message begins with a reference to the upstream commit ID. The
+arm64 patches are targeting the v4.16 release of Linux and so the upstream
+commit IDs may not appear in mainline releases prior to v4.16, although they
+should still be accurate.
+
+
+NOTES TO INTEGRATORS
+====================
+
+Please note that this branch is intended to be used as the basis for backport
+efforts into stable and distribution kernels. It is not intended to be
+integrated directly into production kernels and will consequently be frozen
+when v4.16 is released after which it *WILL NOT RECEIVE FURTHER UPDATES*.
+
+Subsequent fixes and mitigation work will be queued in the mainline kernel
+and CC'd to the stable trees as per the usual kernel development process.
+Integrators are advised to track these trees as closely as possible.
+
+The patches here are intended to be specific to the arm/arm64 architectures
+and therefore mitigation efforts elsewhere in the kernel (for example, in the
+eBPF subsystem) are not included as part of this branch.
-- 
2.7.4

Re: spectre on 4.9 backporting review

[Marc Zyngier]

Hi Alex,

On 26/02/18 08:19, Alex Shi wrote:
> Hi All,
> 
> This backport patchset fixed the spectre issue, it's original branch:
> https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git/log/?h=kpti
> A few dependency or fixingpatches are also picked up, if they are necessary
>  or no functional changes.
> 
> arm64: cpu_errata: Allow an erratum to be match for all revisions of a core
> arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early
> arm64: syscallno is secretly an int, make it official
> arm64: uaccess: consistently check object sizes
> arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
> arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
> arm64: move TASK_* definitions to <asm/processor.h>
> arm64: alternatives: apply boot time fixups via the linear mapping
> mm: Introduce lm_alias
> 
> The patchset also on repository:
> 	git://git.linaro.org/kernel/linux-linaro-stable.git lts-4.9-spectrevv2 
> 
> The kernelci.org and lkft testing show no regressions.
> 
> Any comments are appreciated!
> 
> Regards
> Alex

[...]

>       arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17
>       arm: Invalidate BTB on prefetch abort outside of user mapping on Cortex A8, A9, A12 and A17
>       arm: KVM: Invalidate BTB on guest exit for Cortex-A12/A17
>       arm: Add icache invalidation on switch_mm for Cortex-A15
>       arm: Invalidate icache on prefetch abort outside of user mapping on Cortex-A15
>       arm: KVM: Invalidate icache on guest exit for Cortex-A15

Please drop these patches. They were never merged in mainline, and thus
cannot be "backported". If they ever make it into a mainline kernel,
then will be the time to backport them. In the meantime, let's remove them.

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...

Re: spectre on 4.9 backporting review

[Alex Shi]

> 
>>       arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17
>>       arm: Invalidate BTB on prefetch abort outside of user mapping on Cortex A8, A9, A12 and A17
>>       arm: KVM: Invalidate BTB on guest exit for Cortex-A12/A17
>>       arm: Add icache invalidation on switch_mm for Cortex-A15
>>       arm: Invalidate icache on prefetch abort outside of user mapping on Cortex-A15
>>       arm: KVM: Invalidate icache on guest exit for Cortex-A15
> 
> Please drop these patches. They were never merged in mainline, and thus
> cannot be "backported". If they ever make it into a mainline kernel,
> then will be the time to backport them. In the meantime, let's remove them.
> 

Thanks Marc,

Could I take this message as the others commit are ready for pick up if
they are past review. :)

Regards
Alex

Re: spectre on 4.9 backporting review

[Marc Zyngier]

On 26/02/18 09:37, Alex Shi wrote:
>>
>>>       arm: Add BTB invalidation on switch_mm for Cortex-A9, A12 and A17
>>>       arm: Invalidate BTB on prefetch abort outside of user mapping on Cortex A8, A9, A12 and A17
>>>       arm: KVM: Invalidate BTB on guest exit for Cortex-A12/A17
>>>       arm: Add icache invalidation on switch_mm for Cortex-A15
>>>       arm: Invalidate icache on prefetch abort outside of user mapping on Cortex-A15
>>>       arm: KVM: Invalidate icache on guest exit for Cortex-A15
>>
>> Please drop these patches. They were never merged in mainline, and thus
>> cannot be "backported". If they ever make it into a mainline kernel,
>> then will be the time to backport them. In the meantime, let's remove them.
>>
> 
> Thanks Marc,
> 
> Could I take this message as the others commit are ready for pick up if
> they are past review. :)

I haven't looked past the cover letter.

	M.
-- 
Jazz is not dead. It just smells funny...