From 4d80d6ca5d77fde9880da8466e5b64f250e5bf82 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 18 May 2021 11:17:26 +0200
Subject: genirq: Export affinity setter for modules

Perf modules abuse irq_set_affinity_hint() to set the affinity of system
PMU interrupts just because irq_set_affinity() was not exported.

The fact that irq_set_affinity_hint() actually sets the affinity is a
non-documented side effect and the name is clearly saying it's a hint.

To clean this up, export the real affinity setter.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20210518093117.968251441@linutronix.de
---
 include/linux/interrupt.h | 35 ++---------------------------------
 1 file changed, 2 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 4777850a6dc7..35a374241515 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -319,39 +319,8 @@ struct irq_affinity_desc {
 
 extern cpumask_var_t irq_default_affinity;
 
-/* Internal implementation. Use the helpers below */
-extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
-			      bool force);
-
-/**
- * irq_set_affinity - Set the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Fails if cpumask does not contain an online CPU
- */
-static inline int
-irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, false);
-}
-
-/**
- * irq_force_affinity - Force the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Same as irq_set_affinity, but without checking the mask against
- * online cpus.
- *
- * Solely for low level cpu hotplug code, where we need to make per
- * cpu interrupts affine before the cpu becomes online.
- */
-static inline int
-irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, true);
-}
+extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask);
 
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
-- 
cgit v1.2.3


From 3fdc0cb59d97f87e2cc708d424f1538e31744286 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 18 May 2021 17:36:18 +0100
Subject: arm64: smccc: Add support for SMCCCv1.2 extended input/output
 registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SMCCC v1.2 allows x8-x17 to be used as parameter registers and x4—x17
to be used as result registers in SMC64/HVC64. Arm Firmware Framework
for Armv8-A specification makes use of x0-x7 as parameter and result
registers. There are other users like Hyper-V who intend to use beyond
x0-x7 as well.

Current SMCCC interface in the kernel just use x0-x7 as parameter and
x0-x3 as result registers as required by SMCCCv1.0. Let us add new
interface to support this extended set of input/output registers namely
x0-x17 as both parameter and result registers.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20210518163618.43950-1-sudeep.holla@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/asm-offsets.c |  9 +++++++
 arch/arm64/kernel/smccc-call.S  | 57 +++++++++++++++++++++++++++++++++++++++++
 include/linux/arm-smccc.h       | 55 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 121 insertions(+)

(limited to 'include')

diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0cb34ccb6e73..74321bc9a459 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -138,6 +138,15 @@ int main(void)
   DEFINE(ARM_SMCCC_RES_X2_OFFS,		offsetof(struct arm_smccc_res, a2));
   DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
   DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
+  DEFINE(ARM_SMCCC_1_2_REGS_X0_OFFS,	offsetof(struct arm_smccc_1_2_regs, a0));
+  DEFINE(ARM_SMCCC_1_2_REGS_X2_OFFS,	offsetof(struct arm_smccc_1_2_regs, a2));
+  DEFINE(ARM_SMCCC_1_2_REGS_X4_OFFS,	offsetof(struct arm_smccc_1_2_regs, a4));
+  DEFINE(ARM_SMCCC_1_2_REGS_X6_OFFS,	offsetof(struct arm_smccc_1_2_regs, a6));
+  DEFINE(ARM_SMCCC_1_2_REGS_X8_OFFS,	offsetof(struct arm_smccc_1_2_regs, a8));
+  DEFINE(ARM_SMCCC_1_2_REGS_X10_OFFS,	offsetof(struct arm_smccc_1_2_regs, a10));
+  DEFINE(ARM_SMCCC_1_2_REGS_X12_OFFS,	offsetof(struct arm_smccc_1_2_regs, a12));
+  DEFINE(ARM_SMCCC_1_2_REGS_X14_OFFS,	offsetof(struct arm_smccc_1_2_regs, a14));
+  DEFINE(ARM_SMCCC_1_2_REGS_X16_OFFS,	offsetof(struct arm_smccc_1_2_regs, a16));
   BLANK();
   DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
   DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index d62447964ed9..2def9d0dd3dd 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -43,3 +43,60 @@ SYM_FUNC_START(__arm_smccc_hvc)
 	SMCCC	hvc
 SYM_FUNC_END(__arm_smccc_hvc)
 EXPORT_SYMBOL(__arm_smccc_hvc)
+
+	.macro SMCCC_1_2 instr
+	/* Save `res` and free a GPR that won't be clobbered */
+	stp     x1, x19, [sp, #-16]!
+
+	/* Ensure `args` won't be clobbered while loading regs in next step */
+	mov	x19, x0
+
+	/* Load the registers x0 - x17 from the struct arm_smccc_1_2_regs */
+	ldp	x0, x1, [x19, #ARM_SMCCC_1_2_REGS_X0_OFFS]
+	ldp	x2, x3, [x19, #ARM_SMCCC_1_2_REGS_X2_OFFS]
+	ldp	x4, x5, [x19, #ARM_SMCCC_1_2_REGS_X4_OFFS]
+	ldp	x6, x7, [x19, #ARM_SMCCC_1_2_REGS_X6_OFFS]
+	ldp	x8, x9, [x19, #ARM_SMCCC_1_2_REGS_X8_OFFS]
+	ldp	x10, x11, [x19, #ARM_SMCCC_1_2_REGS_X10_OFFS]
+	ldp	x12, x13, [x19, #ARM_SMCCC_1_2_REGS_X12_OFFS]
+	ldp	x14, x15, [x19, #ARM_SMCCC_1_2_REGS_X14_OFFS]
+	ldp	x16, x17, [x19, #ARM_SMCCC_1_2_REGS_X16_OFFS]
+
+	\instr #0
+
+	/* Load the `res` from the stack */
+	ldr	x19, [sp]
+
+	/* Store the registers x0 - x17 into the result structure */
+	stp	x0, x1, [x19, #ARM_SMCCC_1_2_REGS_X0_OFFS]
+	stp	x2, x3, [x19, #ARM_SMCCC_1_2_REGS_X2_OFFS]
+	stp	x4, x5, [x19, #ARM_SMCCC_1_2_REGS_X4_OFFS]
+	stp	x6, x7, [x19, #ARM_SMCCC_1_2_REGS_X6_OFFS]
+	stp	x8, x9, [x19, #ARM_SMCCC_1_2_REGS_X8_OFFS]
+	stp	x10, x11, [x19, #ARM_SMCCC_1_2_REGS_X10_OFFS]
+	stp	x12, x13, [x19, #ARM_SMCCC_1_2_REGS_X12_OFFS]
+	stp	x14, x15, [x19, #ARM_SMCCC_1_2_REGS_X14_OFFS]
+	stp	x16, x17, [x19, #ARM_SMCCC_1_2_REGS_X16_OFFS]
+
+	/* Restore original x19 */
+	ldp     xzr, x19, [sp], #16
+	ret
+.endm
+
+/*
+ * void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args,
+ *			  struct arm_smccc_1_2_regs *res);
+ */
+SYM_FUNC_START(arm_smccc_1_2_hvc)
+	SMCCC_1_2 hvc
+SYM_FUNC_END(arm_smccc_1_2_hvc)
+EXPORT_SYMBOL(arm_smccc_1_2_hvc)
+
+/*
+ * void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args,
+ *			  struct arm_smccc_1_2_regs *res);
+ */
+SYM_FUNC_START(arm_smccc_1_2_smc)
+	SMCCC_1_2 smc
+SYM_FUNC_END(arm_smccc_1_2_smc)
+EXPORT_SYMBOL(arm_smccc_1_2_smc)
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 6861489a1890..5cef2b8b0479 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -227,6 +227,61 @@ struct arm_smccc_res {
 	unsigned long a3;
 };
 
+#ifdef CONFIG_ARM64
+/**
+ * struct arm_smccc_1_2_regs - Arguments for or Results from SMC/HVC call
+ * @a0-a17 argument values from registers 0 to 17
+ */
+struct arm_smccc_1_2_regs {
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long a8;
+	unsigned long a9;
+	unsigned long a10;
+	unsigned long a11;
+	unsigned long a12;
+	unsigned long a13;
+	unsigned long a14;
+	unsigned long a15;
+	unsigned long a16;
+	unsigned long a17;
+};
+
+/**
+ * arm_smccc_1_2_hvc() - make HVC calls
+ * @args: arguments passed via struct arm_smccc_1_2_regs
+ * @res: result values via struct arm_smccc_1_2_regs
+ *
+ * This function is used to make HVC calls following SMC Calling Convention
+ * v1.2 or above. The content of the supplied param are copied from the
+ * structure to registers prior to the HVC instruction. The return values
+ * are updated with the content from registers on return from the HVC
+ * instruction.
+ */
+asmlinkage void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args,
+				  struct arm_smccc_1_2_regs *res);
+
+/**
+ * arm_smccc_1_2_smc() - make SMC calls
+ * @args: arguments passed via struct arm_smccc_1_2_regs
+ * @res: result values via struct arm_smccc_1_2_regs
+ *
+ * This function is used to make SMC calls following SMC Calling Convention
+ * v1.2 or above. The content of the supplied param are copied from the
+ * structure to registers prior to the SMC instruction. The return values
+ * are updated with the content from registers on return from the SMC
+ * instruction.
+ */
+asmlinkage void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args,
+				  struct arm_smccc_1_2_regs *res);
+#endif
+
 /**
  * struct arm_smccc_quirk - Contains quirk information
  * @id: quirk identification
-- 
cgit v1.2.3


From 92638b4e1b47f97d7269e74465dedf73096f777d Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 2 Jun 2021 16:52:27 -0700
Subject: mm: arch: remove indirection level in
 alloc_zeroed_user_highpage_movable()

In an upcoming change we would like to add a flag to
GFP_HIGHUSER_MOVABLE so that it would no longer be an OR
of GFP_HIGHUSER and __GFP_MOVABLE. This poses a problem for
alloc_zeroed_user_highpage_movable() which passes __GFP_MOVABLE
into an arch-specific __alloc_zeroed_user_highpage() hook which ORs
in GFP_HIGHUSER.

Since __alloc_zeroed_user_highpage() is only ever called from
alloc_zeroed_user_highpage_movable(), we can remove one level
of indirection here. Remove __alloc_zeroed_user_highpage(),
make alloc_zeroed_user_highpage_movable() the hook, and use
GFP_HIGHUSER_MOVABLE in the hook implementations so that they will
pick up the new flag that we are going to add.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Link: https://linux-review.googlesource.com/id/Ic6361c657b2cdcd896adbe0cf7cb5a7fbb1ed7bf
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20210602235230.3928842-2-pcc@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/alpha/include/asm/page.h   |  6 +++---
 arch/arm64/include/asm/page.h   |  6 +++---
 arch/ia64/include/asm/page.h    |  6 +++---
 arch/m68k/include/asm/page_no.h |  6 +++---
 arch/s390/include/asm/page.h    |  6 +++---
 arch/x86/include/asm/page.h     |  6 +++---
 include/linux/highmem.h         | 35 ++++++++---------------------------
 7 files changed, 26 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h
index 268f99b4602b..18f48a6f2ff6 100644
--- a/arch/alpha/include/asm/page.h
+++ b/arch/alpha/include/asm/page.h
@@ -17,9 +17,9 @@
 extern void clear_page(void *page);
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vmaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vmaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 extern void copy_page(void * _to, void * _from);
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 012cffc574e8..e1fc0f60e79f 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -28,9 +28,9 @@ void copy_user_highpage(struct page *to, struct page *from,
 void copy_highpage(struct page *to, struct page *from);
 #define __HAVE_ARCH_COPY_HIGHPAGE
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h
index f4dc81fa7146..1b990466d540 100644
--- a/arch/ia64/include/asm/page.h
+++ b/arch/ia64/include/asm/page.h
@@ -82,16 +82,16 @@ do {						\
 } while (0)
 
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr)		\
+#define alloc_zeroed_user_highpage_movable(vma, vaddr)			\
 ({									\
 	struct page *page = alloc_page_vma(				\
-		GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr);	\
+		GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr);		\
 	if (page)							\
  		flush_dcache_page(page);				\
 	page;								\
 })
 
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 8d0f862ee9d7..c9d0d84158a4 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -13,9 +13,9 @@ extern unsigned long memory_end;
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
 #define __va(paddr)		((void *)((unsigned long)(paddr)))
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index cc98f9b78fd4..479dc76e0eca 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -68,9 +68,9 @@ static inline void copy_page(void *to, void *from)
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 /*
  * These are used to make use of C type-checking..
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 7555b48803a8..4d5810c8fab7 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -34,9 +34,9 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 	copy_page(to, from);
 }
 
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
 #ifndef __pa
 #define __pa(x)		__phys_addr((unsigned long)(x))
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 832b49b50c7b..54d0643b8fcf 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -152,28 +152,24 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
 }
 #endif
 
-#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 /**
- * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags
- * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
- * This function will allocate a page for a VMA but the caller is expected
- * to specify via movableflags whether the page will be movable in the
- * future or not
+ * This function will allocate a page for a VMA that the caller knows will
+ * be able to migrate in the future using move_pages() or reclaimed
  *
  * An architecture may override this function by defining
- * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own
+ * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own
  * implementation.
  */
 static inline struct page *
-__alloc_zeroed_user_highpage(gfp_t movableflags,
-			struct vm_area_struct *vma,
-			unsigned long vaddr)
+alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+				   unsigned long vaddr)
 {
-	struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags,
-			vma, vaddr);
+	struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 
 	if (page)
 		clear_user_highpage(page, vaddr);
@@ -182,21 +178,6 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
 }
 #endif
 
-/**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move
- * @vma: The VMA the page is to be allocated for
- * @vaddr: The virtual address the page will be inserted into
- *
- * This function will allocate a page for a VMA that the caller knows will
- * be able to migrate in the future using move_pages() or reclaimed
- */
-static inline struct page *
-alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-					unsigned long vaddr)
-{
-	return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
-}
-
 static inline void clear_highpage(struct page *page)
 {
 	void *kaddr = kmap_atomic(page);
-- 
cgit v1.2.3


From 7a3b835371883558eb63e069d891bd87f562380d Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 2 Jun 2021 16:52:28 -0700
Subject: kasan: use separate (un)poison implementation for integrated init

Currently with integrated init page_alloc.c needs to know whether
kasan_alloc_pages() will zero initialize memory, but this will start
becoming more complicated once we start adding tag initialization
support for user pages. To avoid page_alloc.c needing to know more
details of what integrated init will do, move the unpoisoning logic
for integrated init into the HW tags implementation. Currently the
logic is identical but it will diverge in subsequent patches.

For symmetry do the same for poisoning although this logic will
be unaffected by subsequent patches.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://linux-review.googlesource.com/id/I2c550234c6c4a893c48c18ff0c6ce658c7c67056
Link: https://lore.kernel.org/r/20210602235230.3928842-3-pcc@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/kasan.h | 64 ++++++++++++++++++++++++++++++---------------------
 mm/kasan/common.c     |  4 ++--
 mm/kasan/hw_tags.c    | 22 ++++++++++++++++++
 mm/mempool.c          |  6 +++--
 mm/page_alloc.c       | 55 ++++++++++++++++++++++---------------------
 5 files changed, 95 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b1678a61e6a7..a1c7ce5f3e4f 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/bug.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
 
@@ -79,14 +80,6 @@ static inline void kasan_disable_current(void) {}
 
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-#ifdef CONFIG_KASAN
-
-struct kasan_cache {
-	int alloc_meta_offset;
-	int free_meta_offset;
-	bool is_kmalloc;
-};
-
 #ifdef CONFIG_KASAN_HW_TAGS
 
 DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
@@ -101,11 +94,14 @@ static inline bool kasan_has_integrated_init(void)
 	return kasan_enabled();
 }
 
+void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags);
+void kasan_free_pages(struct page *page, unsigned int order);
+
 #else /* CONFIG_KASAN_HW_TAGS */
 
 static inline bool kasan_enabled(void)
 {
-	return true;
+	return IS_ENABLED(CONFIG_KASAN);
 }
 
 static inline bool kasan_has_integrated_init(void)
@@ -113,8 +109,30 @@ static inline bool kasan_has_integrated_init(void)
 	return false;
 }
 
+static __always_inline void kasan_alloc_pages(struct page *page,
+					      unsigned int order, gfp_t flags)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
+static __always_inline void kasan_free_pages(struct page *page,
+					     unsigned int order)
+{
+	/* Only available for integrated init. */
+	BUILD_BUG();
+}
+
 #endif /* CONFIG_KASAN_HW_TAGS */
 
+#ifdef CONFIG_KASAN
+
+struct kasan_cache {
+	int alloc_meta_offset;
+	int free_meta_offset;
+	bool is_kmalloc;
+};
+
 slab_flags_t __kasan_never_merge(void);
 static __always_inline slab_flags_t kasan_never_merge(void)
 {
@@ -130,20 +148,20 @@ static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
 		__kasan_unpoison_range(addr, size);
 }
 
-void __kasan_alloc_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_alloc_pages(struct page *page,
+void __kasan_poison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_poison_pages(struct page *page,
 						unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_alloc_pages(page, order, init);
+		__kasan_poison_pages(page, order, init);
 }
 
-void __kasan_free_pages(struct page *page, unsigned int order, bool init);
-static __always_inline void kasan_free_pages(struct page *page,
-						unsigned int order, bool init)
+void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init);
+static __always_inline void kasan_unpoison_pages(struct page *page,
+						 unsigned int order, bool init)
 {
 	if (kasan_enabled())
-		__kasan_free_pages(page, order, init);
+		__kasan_unpoison_pages(page, order, init);
 }
 
 void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
@@ -285,21 +303,15 @@ void kasan_restore_multi_shot(bool enabled);
 
 #else /* CONFIG_KASAN */
 
-static inline bool kasan_enabled(void)
-{
-	return false;
-}
-static inline bool kasan_has_integrated_init(void)
-{
-	return false;
-}
 static inline slab_flags_t kasan_never_merge(void)
 {
 	return 0;
 }
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
-static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {}
-static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {}
+static inline void kasan_poison_pages(struct page *page, unsigned int order,
+				      bool init) {}
+static inline void kasan_unpoison_pages(struct page *page, unsigned int order,
+					bool init) {}
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
 				      slab_flags_t *flags) {}
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6bb87f2acd4e..0ecd293af344 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -97,7 +97,7 @@ slab_flags_t __kasan_never_merge(void)
 	return 0;
 }
 
-void __kasan_alloc_pages(struct page *page, unsigned int order, bool init)
+void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init)
 {
 	u8 tag;
 	unsigned long i;
@@ -111,7 +111,7 @@ void __kasan_alloc_pages(struct page *page, unsigned int order, bool init)
 	kasan_unpoison(page_address(page), PAGE_SIZE << order, init);
 }
 
-void __kasan_free_pages(struct page *page, unsigned int order, bool init)
+void __kasan_poison_pages(struct page *page, unsigned int order, bool init)
 {
 	if (likely(!PageHighMem(page)))
 		kasan_poison(page_address(page), PAGE_SIZE << order,
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 4004388b4e4b..9d0f6f934016 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -238,6 +238,28 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 	return &alloc_meta->free_track[0];
 }
 
+void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags)
+{
+	/*
+	 * This condition should match the one in post_alloc_hook() in
+	 * page_alloc.c.
+	 */
+	bool init = !want_init_on_free() && want_init_on_alloc(flags);
+
+	kasan_unpoison_pages(page, order, init);
+}
+
+void kasan_free_pages(struct page *page, unsigned int order)
+{
+	/*
+	 * This condition should match the one in free_pages_prepare() in
+	 * page_alloc.c.
+	 */
+	bool init = want_init_on_free();
+
+	kasan_poison_pages(page, order, init);
+}
+
 #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
 
 void kasan_set_tagging_report_once(bool state)
diff --git a/mm/mempool.c b/mm/mempool.c
index a258cf4de575..0b8afbec3e35 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -106,7 +106,8 @@ static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
 		kasan_slab_free_mempool(element);
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_free_pages(element, (unsigned long)pool->pool_data, false);
+		kasan_poison_pages(element, (unsigned long)pool->pool_data,
+				   false);
 }
 
 static void kasan_unpoison_element(mempool_t *pool, void *element)
@@ -114,7 +115,8 @@ static void kasan_unpoison_element(mempool_t *pool, void *element)
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
 		kasan_unpoison_range(element, __ksize(element));
 	else if (pool->alloc == mempool_alloc_pages)
-		kasan_alloc_pages(element, (unsigned long)pool->pool_data, false);
+		kasan_unpoison_pages(element, (unsigned long)pool->pool_data,
+				     false);
 }
 
 static __always_inline void add_element(mempool_t *pool, void *element)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index aaa1655cf682..4fddb7cac3c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -382,7 +382,7 @@ int page_group_by_mobility_disabled __read_mostly;
 static DEFINE_STATIC_KEY_TRUE(deferred_pages);
 
 /*
- * Calling kasan_free_pages() only after deferred memory initialization
+ * Calling kasan_poison_pages() only after deferred memory initialization
  * has completed. Poisoning pages during deferred memory init will greatly
  * lengthen the process and cause problem in large memory systems as the
  * deferred pages initialization is done with interrupt disabled.
@@ -394,15 +394,11 @@ static DEFINE_STATIC_KEY_TRUE(deferred_pages);
  * on-demand allocation and then freed again before the deferred pages
  * initialization is done, but this is not likely to happen.
  */
-static inline void kasan_free_nondeferred_pages(struct page *page, int order,
-						bool init, fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(fpi_t fpi_flags)
 {
-	if (static_branch_unlikely(&deferred_pages))
-		return;
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-			(fpi_flags & FPI_SKIP_KASAN_POISON))
-		return;
-	kasan_free_pages(page, order, init);
+	return static_branch_unlikely(&deferred_pages) ||
+	       (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+		(fpi_flags & FPI_SKIP_KASAN_POISON));
 }
 
 /* Returns true if the struct page for the pfn is uninitialised */
@@ -453,13 +449,10 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	return false;
 }
 #else
-static inline void kasan_free_nondeferred_pages(struct page *page, int order,
-						bool init, fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(fpi_t fpi_flags)
 {
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-			(fpi_flags & FPI_SKIP_KASAN_POISON))
-		return;
-	kasan_free_pages(page, order, init);
+	return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+		(fpi_flags & FPI_SKIP_KASAN_POISON));
 }
 
 static inline bool early_page_uninitialised(unsigned long pfn)
@@ -1245,7 +1238,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 			unsigned int order, bool check_free, fpi_t fpi_flags)
 {
 	int bad = 0;
-	bool init;
+	bool skip_kasan_poison = should_skip_kasan_poison(fpi_flags);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
@@ -1314,10 +1307,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	 * With hardware tag-based KASAN, memory tags must be set before the
 	 * page becomes unavailable via debug_pagealloc or arch_free_page.
 	 */
-	init = want_init_on_free();
-	if (init && !kasan_has_integrated_init())
-		kernel_init_free_pages(page, 1 << order);
-	kasan_free_nondeferred_pages(page, order, init, fpi_flags);
+	if (kasan_has_integrated_init()) {
+		if (!skip_kasan_poison)
+			kasan_free_pages(page, order);
+	} else {
+		bool init = want_init_on_free();
+
+		if (init)
+			kernel_init_free_pages(page, 1 << order);
+		if (!skip_kasan_poison)
+			kasan_poison_pages(page, order, init);
+	}
 
 	/*
 	 * arch_free_page() can make the page's contents inaccessible.  s390
@@ -2324,8 +2324,6 @@ static bool check_new_pages(struct page *page, unsigned int order)
 inline void post_alloc_hook(struct page *page, unsigned int order,
 				gfp_t gfp_flags)
 {
-	bool init;
-
 	set_page_private(page, 0);
 	set_page_refcounted(page);
 
@@ -2344,10 +2342,15 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	 * kasan_alloc_pages and kernel_init_free_pages must be
 	 * kept together to avoid discrepancies in behavior.
 	 */
-	init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
-	kasan_alloc_pages(page, order, init);
-	if (init && !kasan_has_integrated_init())
-		kernel_init_free_pages(page, 1 << order);
+	if (kasan_has_integrated_init()) {
+		kasan_alloc_pages(page, order, gfp_flags);
+	} else {
+		bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags);
+
+		kasan_unpoison_pages(page, order, init);
+		if (init)
+			kernel_init_free_pages(page, 1 << order);
+	}
 
 	set_page_owner(page, order, gfp_flags);
 }
-- 
cgit v1.2.3


From 013bb59dbb7cf876449df860946458a595a96d51 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 2 Jun 2021 16:52:29 -0700
Subject: arm64: mte: handle tags zeroing at page allocation time

Currently, on an anonymous page fault, the kernel allocates a zeroed
page and maps it in user space. If the mapping is tagged (PROT_MTE),
set_pte_at() additionally clears the tags. It is, however, more
efficient to clear the tags at the same time as zeroing the data on
allocation. To avoid clearing the tags on any page (which may not be
mapped as tagged), only do this if the vma flags contain VM_MTE. This
requires introducing a new GFP flag that is used to determine whether
to clear the tags.

The DC GZVA instruction with a 0 top byte (and 0 tag) requires
top-byte-ignore. Set the TCR_EL1.{TBI1,TBID1} bits irrespective of
whether KASAN_HW is enabled.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Co-developed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://linux-review.googlesource.com/id/Id46dc94e30fe11474f7e54f5d65e7658dbdddb26
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://lore.kernel.org/r/20210602235230.3928842-4-pcc@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mte.h  |  4 ++++
 arch/arm64/include/asm/page.h |  8 ++++++--
 arch/arm64/lib/mte.S          | 20 ++++++++++++++++++++
 arch/arm64/mm/fault.c         | 26 ++++++++++++++++++++++++++
 arch/arm64/mm/proc.S          | 10 +++++++---
 include/linux/gfp.h           |  9 +++++++--
 include/linux/highmem.h       |  8 ++++++++
 mm/kasan/hw_tags.c            |  9 ++++++++-
 mm/page_alloc.c               | 13 ++++++++++---
 9 files changed, 96 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index bc88a1ced0d7..67bf259ae768 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -37,6 +37,7 @@ void mte_free_tag_storage(char *storage);
 /* track which pages have valid allocation tags */
 #define PG_mte_tagged	PG_arch_2
 
+void mte_zero_clear_page_tags(void *addr);
 void mte_sync_tags(pte_t *ptep, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
@@ -53,6 +54,9 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
 /* unused if !CONFIG_ARM64_MTE, silence the compiler */
 #define PG_mte_tagged	0
 
+static inline void mte_zero_clear_page_tags(void *addr)
+{
+}
 static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
 {
 }
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index e1fc0f60e79f..ed1b9dcf12b2 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -13,6 +13,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
+#include <linux/types.h> /* for gfp_t */
 #include <asm/pgtable-types.h>
 
 struct page;
@@ -28,10 +29,13 @@ void copy_user_highpage(struct page *to, struct page *from,
 void copy_highpage(struct page *to, struct page *from);
 #define __HAVE_ARCH_COPY_HIGHPAGE
 
-#define alloc_zeroed_user_highpage_movable(vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr)
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr);
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
 
+void tag_clear_highpage(struct page *to);
+#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
index 351537c12f36..e83643b3995f 100644
--- a/arch/arm64/lib/mte.S
+++ b/arch/arm64/lib/mte.S
@@ -36,6 +36,26 @@ SYM_FUNC_START(mte_clear_page_tags)
 	ret
 SYM_FUNC_END(mte_clear_page_tags)
 
+/*
+ * Zero the page and tags at the same time
+ *
+ * Parameters:
+ *	x0 - address to the beginning of the page
+ */
+SYM_FUNC_START(mte_zero_clear_page_tags)
+	mrs	x1, dczid_el0
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+	and	x0, x0, #(1 << MTE_TAG_SHIFT) - 1	// clear the tag
+
+1:	dc	gzva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_zero_clear_page_tags)
+
 /*
  * Copy the tags from the source page to the destination one
  *   x0 - address of the destination page
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 871c82ab0a30..180c0343d82a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -921,3 +921,29 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 	debug_exception_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug_exception);
+
+/*
+ * Used during anonymous page fault handling.
+ */
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr)
+{
+	gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO;
+
+	/*
+	 * If the page is mapped with PROT_MTE, initialise the tags at the
+	 * point of allocation and page zeroing as this is usually faster than
+	 * separate DC ZVA and STGM.
+	 */
+	if (vma->vm_flags & VM_MTE)
+		flags |= __GFP_ZEROTAGS;
+
+	return alloc_page_vma(flags, vma, vaddr);
+}
+
+void tag_clear_highpage(struct page *page)
+{
+	mte_zero_clear_page_tags(page_address(page));
+	page_kasan_tag_reset(page);
+	set_bit(PG_mte_tagged, &page->flags);
+}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 97d7bcd8d4f2..48fd1df3d05a 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,9 +46,13 @@
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
+#define TCR_MTE_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
 #else
-#define TCR_KASAN_HW_FLAGS 0
+/*
+ * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on
+ * TBI being enabled at EL1.
+ */
+#define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1
 #endif
 
 /*
@@ -464,7 +468,7 @@ SYM_FUNC_START(__cpu_setup)
 	msr_s	SYS_TFSRE0_EL1, xzr
 
 	/* set the TCR_EL1 bits */
-	mov_q	x10, TCR_KASAN_HW_FLAGS
+	mov_q	x10, TCR_MTE_FLAGS
 	orr	tcr, tcr, x10
 1:
 #endif
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 11da8af06704..68ba237365dc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -53,8 +53,9 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x100000u
 #define ___GFP_THISNODE		0x200000u
 #define ___GFP_ACCOUNT		0x400000u
+#define ___GFP_ZEROTAGS		0x800000u
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x800000u
+#define ___GFP_NOLOCKDEP	0x1000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
@@ -229,16 +230,20 @@ struct vm_area_struct;
  * %__GFP_COMP address compound page metadata.
  *
  * %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if
+ * __GFP_ZERO is set.
  */
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
+#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP))
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /**
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 54d0643b8fcf..8c6e8e996c87 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -185,6 +185,14 @@ static inline void clear_highpage(struct page *page)
 	kunmap_atomic(kaddr);
 }
 
+#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+
+static inline void tag_clear_highpage(struct page *page)
+{
+}
+
+#endif
+
 /*
  * If we pass in a base or tail page, we can zero up to PAGE_SIZE.
  * If we pass in a head page, we can zero up to the size of the compound page.
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 9d0f6f934016..41fd5326ee0a 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -246,7 +246,14 @@ void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags)
 	 */
 	bool init = !want_init_on_free() && want_init_on_alloc(flags);
 
-	kasan_unpoison_pages(page, order, init);
+	if (flags & __GFP_ZEROTAGS) {
+		int i;
+
+		for (i = 0; i != 1 << order; ++i)
+			tag_clear_highpage(page + i);
+	} else {
+		kasan_unpoison_pages(page, order, init);
+	}
 }
 
 void kasan_free_pages(struct page *page, unsigned int order)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4fddb7cac3c6..13937e793fda 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1219,10 +1219,16 @@ out:
 	return ret;
 }
 
-static void kernel_init_free_pages(struct page *page, int numpages)
+static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags)
 {
 	int i;
 
+	if (zero_tags) {
+		for (i = 0; i < numpages; i++)
+			tag_clear_highpage(page + i);
+		return;
+	}
+
 	/* s390's use of memset() could override KASAN redzones. */
 	kasan_disable_current();
 	for (i = 0; i < numpages; i++) {
@@ -1314,7 +1320,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 		bool init = want_init_on_free();
 
 		if (init)
-			kernel_init_free_pages(page, 1 << order);
+			kernel_init_free_pages(page, 1 << order, false);
 		if (!skip_kasan_poison)
 			kasan_poison_pages(page, order, init);
 	}
@@ -2349,7 +2355,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 
 		kasan_unpoison_pages(page, order, init);
 		if (init)
-			kernel_init_free_pages(page, 1 << order);
+			kernel_init_free_pages(page, 1 << order,
+					       gfp_flags & __GFP_ZEROTAGS);
 	}
 
 	set_page_owner(page, order, gfp_flags);
-- 
cgit v1.2.3


From c275c5c6d50a0518cdb0584e85905d10e7cefc6e Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 2 Jun 2021 16:52:30 -0700
Subject: kasan: disable freed user page poisoning with HW tags

Poisoning freed pages protects against kernel use-after-free. The
likelihood of such a bug involving kernel pages is significantly higher
than that for user pages. At the same time, poisoning freed pages can
impose a significant performance cost, which cannot always be justified
for user pages given the lower probability of finding a bug. Therefore,
disable freed user page poisoning when using HW tags. We identify
"user" pages via the flag set GFP_HIGHUSER_MOVABLE, which indicates
a strong likelihood of not being directly accessible to the kernel.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://linux-review.googlesource.com/id/I716846e2de8ef179f44e835770df7e6307be96c9
Link: https://lore.kernel.org/r/20210602235230.3928842-5-pcc@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/gfp.h            | 13 ++++++++++---
 include/linux/page-flags.h     |  9 +++++++++
 include/trace/events/mmflags.h |  9 ++++++++-
 mm/kasan/hw_tags.c             |  3 +++
 mm/page_alloc.c                | 12 +++++++-----
 5 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 68ba237365dc..e6102dfa4faa 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -54,8 +54,9 @@ struct vm_area_struct;
 #define ___GFP_THISNODE		0x200000u
 #define ___GFP_ACCOUNT		0x400000u
 #define ___GFP_ZEROTAGS		0x800000u
+#define ___GFP_SKIP_KASAN_POISON	0x1000000u
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x1000000u
+#define ___GFP_NOLOCKDEP	0x2000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
@@ -233,17 +234,22 @@ struct vm_area_struct;
  *
  * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if
  * __GFP_ZERO is set.
+ *
+ * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned
+ * on deallocation. Typically used for userspace pages. Currently only has an
+ * effect in HW tags mode.
  */
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
 #define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
+#define __GFP_SKIP_KASAN_POISON	((__force gfp_t)___GFP_SKIP_KASAN_POISON)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP))
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /**
@@ -324,7 +330,8 @@ struct vm_area_struct;
 #define GFP_DMA		__GFP_DMA
 #define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
+#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
+			 __GFP_SKIP_KASAN_POISON)
 #define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
 			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
 #define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 04a34c08e0a6..40e2c5000585 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -137,6 +137,9 @@ enum pageflags {
 #endif
 #ifdef CONFIG_64BIT
 	PG_arch_2,
+#endif
+#ifdef CONFIG_KASAN_HW_TAGS
+	PG_skip_kasan_poison,
 #endif
 	__NR_PAGEFLAGS,
 
@@ -443,6 +446,12 @@ TESTCLEARFLAG(Young, young, PF_ANY)
 PAGEFLAG(Idle, idle, PF_ANY)
 #endif
 
+#ifdef CONFIG_KASAN_HW_TAGS
+PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
+#else
+PAGEFLAG_FALSE(SkipKASanPoison)
+#endif
+
 /*
  * PageReported() is used to track reported free pages within the Buddy
  * allocator. We can use the non-atomic version of the test and set
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 629c7a0eaff2..390270e00a1d 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -85,6 +85,12 @@
 #define IF_HAVE_PG_ARCH_2(flag,string)
 #endif
 
+#ifdef CONFIG_KASAN_HW_TAGS
+#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string)
+#endif
+
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
 	{1UL << PG_waiters,		"waiters"	},		\
@@ -112,7 +118,8 @@ IF_HAVE_PG_UNCACHED(PG_uncached,	"uncached"	)		\
 IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
 IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
-IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
+IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)		\
+IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
 
 #define show_page_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 41fd5326ee0a..ed5e5b833d61 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -246,6 +246,9 @@ void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags)
 	 */
 	bool init = !want_init_on_free() && want_init_on_alloc(flags);
 
+	if (flags & __GFP_SKIP_KASAN_POISON)
+		SetPageSkipKASanPoison(page);
+
 	if (flags & __GFP_ZEROTAGS) {
 		int i;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 13937e793fda..5ad76e540a22 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -394,11 +394,12 @@ static DEFINE_STATIC_KEY_TRUE(deferred_pages);
  * on-demand allocation and then freed again before the deferred pages
  * initialization is done, but this is not likely to happen.
  */
-static inline bool should_skip_kasan_poison(fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
 	return static_branch_unlikely(&deferred_pages) ||
 	       (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-		(fpi_flags & FPI_SKIP_KASAN_POISON));
+		(fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+	       PageSkipKASanPoison(page);
 }
 
 /* Returns true if the struct page for the pfn is uninitialised */
@@ -449,10 +450,11 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	return false;
 }
 #else
-static inline bool should_skip_kasan_poison(fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 {
 	return (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-		(fpi_flags & FPI_SKIP_KASAN_POISON));
+		(fpi_flags & FPI_SKIP_KASAN_POISON)) ||
+	       PageSkipKASanPoison(page);
 }
 
 static inline bool early_page_uninitialised(unsigned long pfn)
@@ -1244,7 +1246,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 			unsigned int order, bool check_free, fpi_t fpi_flags)
 {
 	int bad = 0;
-	bool skip_kasan_poison = should_skip_kasan_poison(fpi_flags);
+	bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
-- 
cgit v1.2.3


From cfa7ff959a789a953eac40c8ac793e2cfc2db931 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 3 Jun 2021 19:41:18 +0100
Subject: arm64: smccc: Support SMCCC v1.3 SVE register saving hint

SMCCC v1.2 requires that all SVE state be preserved over SMC calls which
introduces substantial overhead in the common case where there is no SVE
state in the registers. To avoid this SMCCC v1.3 introduces a flag which
allows the caller to say that there is no state that needs to be preserved
in the registers. Make use of this flag, setting it if the SMCCC version
indicates support for it and the TIF_ flags indicate that there is no live
SVE state in the registers, this avoids placing any constraints on when
SMCCC calls can be done or triggering extra saving and reloading of SVE
register state in the kernel.

This would be straightforward enough except for the rather entertaining
inline assembly we use to do SMCCC v1.1 calls to allow us to take advantage
of the limited number of registers it clobbers. Deal with this by having a
function which we call immediately before issuing the SMCCC call to make
our checks and set the flag. Using alternatives the overhead if SVE is
supported but not detected at runtime can be reduced to a single NOP.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210603184118.15090-1-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/smccc-call.S | 26 ++++++++++++++++++++++++++
 drivers/firmware/smccc/smccc.c |  4 ++++
 include/linux/arm-smccc.h      | 33 +++++++++++++++++++++++++++++++--
 3 files changed, 61 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index 2def9d0dd3dd..d3d37f932b97 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -7,8 +7,34 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include <asm/thread_info.h>
+
+/*
+ * If we have SMCCC v1.3 and (as is likely) no SVE state in
+ * the registers then set the SMCCC hint bit to say there's no
+ * need to preserve it.  Do this by directly adjusting the SMCCC
+ * function value which is already stored in x0 ready to be called.
+ */
+SYM_FUNC_START(__arm_smccc_sve_check)
+
+	ldr_l	x16, smccc_has_sve_hint
+	cbz	x16, 2f
+
+	get_current_task x16
+	ldr	x16, [x16, #TSK_TI_FLAGS]
+	tbnz	x16, #TIF_FOREIGN_FPSTATE, 1f	// Any live FP state?
+	tbnz	x16, #TIF_SVE, 2f		// Does that state include SVE?
+
+1:	orr	x0, x0, ARM_SMCCC_1_3_SVE_HINT
+
+2:	ret
+SYM_FUNC_END(__arm_smccc_sve_check)
+EXPORT_SYMBOL(__arm_smccc_sve_check)
 
 	.macro SMCCC instr
+alternative_if ARM64_SVE
+	bl	__arm_smccc_sve_check
+alternative_else_nop_endif
 	\instr	#0
 	ldr	x4, [sp]
 	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
index 028f81d702cc..9f937b125ab0 100644
--- a/drivers/firmware/smccc/smccc.c
+++ b/drivers/firmware/smccc/smccc.c
@@ -15,6 +15,7 @@ static u32 smccc_version = ARM_SMCCC_VERSION_1_0;
 static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
 
 bool __ro_after_init smccc_trng_available = false;
+u64 __ro_after_init smccc_has_sve_hint = false;
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
 {
@@ -22,6 +23,9 @@ void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
 	smccc_conduit = conduit;
 
 	smccc_trng_available = smccc_probe_trng();
+	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+	    smccc_version >= ARM_SMCCC_VERSION_1_3)
+		smccc_has_sve_hint = true;
 }
 
 enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 5cef2b8b0479..7d1cabe15262 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -63,6 +63,9 @@
 #define ARM_SMCCC_VERSION_1_0		0x10000
 #define ARM_SMCCC_VERSION_1_1		0x10001
 #define ARM_SMCCC_VERSION_1_2		0x10002
+#define ARM_SMCCC_VERSION_1_3		0x10003
+
+#define ARM_SMCCC_1_3_SVE_HINT		0x10000
 
 #define ARM_SMCCC_VERSION_FUNC_ID					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -216,6 +219,8 @@ u32 arm_smccc_get_version(void);
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
 
+extern u64 smccc_has_sve_hint;
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -295,6 +300,15 @@ struct arm_smccc_quirk {
 	} state;
 };
 
+/**
+ * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls
+ *
+ * Sets the SMCCC hint bit to indicate if there is live state in the SVE
+ * registers, this modifies x0 in place and should never be called from C
+ * code.
+ */
+asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
+
 /**
  * __arm_smccc_smc() - make SMC calls
  * @a0-a7: arguments passed in registers 0 to 7
@@ -352,6 +366,20 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #endif
 
+/* nVHE hypervisor doesn't have a current thread so needs separate checks */
+#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__)
+
+#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n",  "bl __arm_smccc_sve_check \n", \
+				    ARM64_SVE)
+#define smccc_sve_clobbers "x16", "x30", "cc",
+
+#else
+
+#define SMCCC_SVE_CHECK
+#define smccc_sve_clobbers
+
+#endif
+
 #define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
 
 #define __count_args(...)						\
@@ -419,7 +447,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #define ___constraints(count)						\
 	: __constraint_read_ ## count					\
-	: "memory"
+	: smccc_sve_clobbers "memory"
 #define __constraints(count)	___constraints(count)
 
 /*
@@ -434,7 +462,8 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		register unsigned long r2 asm("r2");			\
 		register unsigned long r3 asm("r3"); 			\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(inst "\n" :				\
+		asm volatile(SMCCC_SVE_CHECK				\
+			     inst "\n" :				\
 			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
 			     __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
-- 
cgit v1.2.3


From f8e6d24144d1bfbb8714faa9044e135c0c00bd89 Mon Sep 17 00:00:00 2001
From: Qi Liu <liuqi115@huawei.com>
Date: Wed, 9 Jun 2021 14:40:57 +0800
Subject: perf: Add EVENT_ATTR_ID to simplify event attributes

Similar EVENT_ATTR macros are defined in many PMU drivers,
like Arm PMU driver, Arm SMMU PMU driver. So add a generic
macro to simplify code.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Qi Liu <liuqi115@huawei.com>
Link: https://lore.kernel.org/r/1623220863-58233-2-git-send-email-liuqi115@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/perf_event.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f5a6a2f069ed..2d510ad750ed 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1576,6 +1576,12 @@ static struct perf_pmu_events_attr _var = {				    \
 	.event_str	= _str,						    \
 };
 
+#define PMU_EVENT_ATTR_ID(_name, _show, _id)				\
+	(&((struct perf_pmu_events_attr[]) {				\
+		{ .attr = __ATTR(_name, 0444, _show, NULL),		\
+		  .id = _id, }						\
+	})[0].attr.attr)
+
 #define PMU_FORMAT_ATTR(_name, _format)					\
 static ssize_t								\
 _name##_show(struct device *dev,					\
-- 
cgit v1.2.3