[PATCH 0/8] arm64 kexec kernel patches V4

[PATCH 0/8] arm64 kexec kernel patches V4

[Geoff Levand]

Hi All,

This series adds the core support for kexec re-boots on arm64.  I have tested
with  the arm64 wrapper program on the ARM VE fast model and the Foundation
model, and using Linaro's EFI build on the ARM base AEMv8 fast model with
various kernel config options for both the first and second stage kernels.

To load a second stage kernel and execute a kexec re-boot on arm64 my patches to
kexec-tools [2], which have not yet been merged upstream, are needed.

This series does not include some re-work of the spin-table CPU enable method
that is needed to support it, nor does it include some re-work of KVM to support
CPU soft reset.  A first stage kernel built with these patches will boot and run
correctly, but will fail to load a second stage kernel if running on a machine
with any spin-table enabled secondary CPUs (CONFIG_SMP=n works OK), and will
fail the kexec re-boot resulting in a system hang if the first stage kernel was
built with CONFIG_KVM=y.  Work-in-progress patches to support these are in my
linux-kexec source repository [1].

Patches 1-4 rework the arm64 hcall mechanism to give the arm64 soft_restart()
routine the ability to switch exception levels from EL1 to EL2 for kernels that
were entered in EL2.

Patch 5 moves proc-macros.S from arm64/mm to arm64/include/asm so that the
dcache_line_size macro it defines can be uesd by kexec's relocate kernel
routine.

Patches 11-13 add the actual kexec support.

Please consider all patches for inclusion.  Any comments or suggestions on how 
to improve are welcome.

[1]  https://git.linaro.org/people/geoff.levand/linux-kexec.git
[2]  https://git.linaro.org/people/geoff.levand/kexec-tools.git

-Geoff

The following changes since commit 0a6479b0ffad8dd236915e271faaf2cbb4cac287:

	arm64: Remove unneeded extern keyword (2014-10-03 14:51:02 +0100)

are available in the git repository at:

	git://git.linaro.org/people/geoff.levand/linux-kexec.git kexec-v4

for you to fetch changes up to e122ed3a1b2afbaf69baf2c7cf354f7e557c5851:

	arm64/kexec: Add pr_devel output (2014-10-03 15:53:58 -0700)

----------------------------------------------------------------
Geoff Levand (8):
	arm64/kvm: Fix assembler compatibility of macros
	arm64: Convert hcalls to use ISS field
	arm64: Add new hcall HVC_CALL_FUNC
	arm64: Add EL2 switch to soft_restart
	arm64: Move proc-macros.S to include/asm
	arm64/kexec: Add core kexec support
	arm64/kexec: Enable kexec in the arm64 defconfig
	arm64/kexec: Add pr_devel output

arch/arm64/Kconfig                           |   9 ++
arch/arm64/configs/defconfig                 |   1 +
arch/arm64/include/asm/kexec.h               |  47 ++++++
arch/arm64/include/asm/kvm_arm.h             |  21 +--
arch/arm64/include/asm/proc-fns.h            |   4 +-
arch/arm64/{mm => include/asm}/proc-macros.S |   0
arch/arm64/include/asm/virt.h                |  33 ++++
arch/arm64/kernel/Makefile                   |   1 +
arch/arm64/kernel/hyp-stub.S                 |  45 ++++--
arch/arm64/kernel/machine_kexec.c            | 225 +++++++++++++++++++++++++++
arch/arm64/kernel/process.c                  |   6 +-
arch/arm64/kernel/relocate_kernel.S          | 184 ++++++++++++++++++++++
arch/arm64/kvm/hyp.S                         |  18 ++-
arch/arm64/mm/cache.S                        |   3 +-
arch/arm64/mm/proc.S                         |  50 ++++--
include/uapi/linux/kexec.h                   |   1 +
16 files changed, 600 insertions(+), 48 deletions(-)
create mode 100644 arch/arm64/include/asm/kexec.h
rename arch/arm64/{mm => include/asm}/proc-macros.S (100%)
create mode 100644 arch/arm64/kernel/machine_kexec.c
create mode 100644 arch/arm64/kernel/relocate_kernel.S

-- 
1.9.1

[PATCH 2/8] arm64: Convert hcalls to use ISS field

[Geoff Levand]

To allow for additional hcalls to be defined and to make the arm64 hcall API
more consistent across exception vector routines change the hcall implementations
to use the ISS field of the ESR_EL2 register to specify the hcall type.

The existing arm64 hcall implementations are limited in that they only allow
for two distinct hcalls; with the x0 register either zero, or not zero.  Also,
the API of the hyp-stub exception vector routines and the KVM exception vector
routines differ; hyp-stub uses a non-zero value in x0 to implement
__hyp_set_vectors, whereas KVM uses it to implement kvm_call_hyp.

Define three new preprocessor macros HVC_GET_VECTORS, HVC_SET_VECTORS and
HVC_CALL_HYP and to be used as hcall type specifiers and convert the
existing __hyp_get_vectors(), __hyp_set_vectors() and kvm_call_hyp() routines
to use these new macros when executing and HVC call.  Also change the
corresponding hyp-stub and KVM el1_sync exception vector routines to use these
new macros.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/virt.h | 20 ++++++++++++++++++++
 arch/arm64/kernel/hyp-stub.S  | 34 ++++++++++++++++++++++------------
 arch/arm64/kvm/hyp.S          | 18 +++++++++++-------
 3 files changed, 53 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 7a5df52..99c319c 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -21,6 +21,26 @@
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 
+/*
+ * HVC_GET_VECTORS - Return the value of the vbar_el2 register.
+ */
+
+#define HVC_GET_VECTORS 1
+
+/*
+ * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
+ *
+ * @x0: Physical address of the new vector table.
+ */
+
+#define HVC_SET_VECTORS 2
+
+/*
+ * HVC_CALL_HYP - Execute a hyp routine.
+ */
+
+#define HVC_CALL_HYP 3
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index a272f33..9ce8746 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -22,6 +22,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
+#include <asm/kvm_arm.h>
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
@@ -53,14 +54,22 @@ ENDPROC(__hyp_stub_vectors)
 	.align 11
 
 el1_sync:
-	mrs	x1, esr_el2
-	lsr	x1, x1, #26
-	cmp	x1, #0x16
-	b.ne	2f				// Not an HVC trap
-	cbz	x0, 1f
-	msr	vbar_el2, x0			// Set vbar_el2
+	mrs	x18, esr_el2
+	lsr	x17, x18, #ESR_EL2_EC_SHIFT
+	and	x18, x18, #ESR_EL2_ISS
+
+	cmp     x17, #ESR_EL2_EC_HVC64
+	b.ne    2f				// Not an HVC trap
+
+	cmp	x18, #HVC_GET_VECTORS
+	b.ne	1f
+	mrs	x0, vbar_el2
 	b	2f
-1:	mrs	x0, vbar_el2			// Return vbar_el2
+
+1:	cmp	x18, #HVC_SET_VECTORS
+	b.ne	2f
+	msr	vbar_el2, x0
+
 2:	eret
 ENDPROC(el1_sync)
 
@@ -100,11 +109,12 @@ ENDPROC(\label)
  * initialisation entry point.
  */
 
-ENTRY(__hyp_get_vectors)
-	mov	x0, xzr
-	// fall through
 ENTRY(__hyp_set_vectors)
-	hvc	#0
+	hvc	#HVC_SET_VECTORS
 	ret
-ENDPROC(__hyp_get_vectors)
 ENDPROC(__hyp_set_vectors)
+
+ENTRY(__hyp_get_vectors)
+	hvc	#HVC_GET_VECTORS
+	ret
+ENDPROC(__hyp_get_vectors)
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index b72aa9f..9607f15 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -26,6 +26,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/virt.h>
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
@@ -1105,12 +1106,9 @@ __hyp_panic_str:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
- * A function pointer with a value of 0 has a special meaning, and is
- * used to implement __hyp_get_vectors in the same way as in
- * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(kvm_call_hyp)
-	hvc	#0
+	hvc	#HVC_CALL_HYP
 	ret
 ENDPROC(kvm_call_hyp)
 
@@ -1140,6 +1138,7 @@ el1_sync:					// Guest trapped into EL2
 	push	x2, x3
 
 	mrs	x1, esr_el2
+	and	x0, x1, #ESR_EL2_ISS
 	lsr	x2, x1, #ESR_EL2_EC_SHIFT
 
 	cmp	x2, #ESR_EL2_EC_HVC64
@@ -1149,15 +1148,19 @@ el1_sync:					// Guest trapped into EL2
 	cbnz	x3, el1_trap			// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
+	mov	x18, x0
 	pop	x2, x3
 	pop	x0, x1
 
-	/* Check for __hyp_get_vectors */
-	cbnz	x0, 1f
+	cmp	x18, #HVC_GET_VECTORS
+	b.ne	1f
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	push	lr, xzr
+1:	cmp	x18, #HVC_CALL_HYP
+	b.ne	2f
+
+	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -1170,6 +1173,7 @@ el1_sync:					// Guest trapped into EL2
 	blr	lr
 
 	pop	lr, xzr
+
 2:	eret
 
 el1_trap:
-- 
1.9.1

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

When a CPU is reset it needs to be put into the exception level it had when it
entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
not set the soft reset address will be entered at EL1.

Update cpu_soft_restart() and soft_restart() to pass the return of
is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
change.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-fns.h |  4 ++--
 arch/arm64/kernel/process.c       |  6 ++++-
 arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
 3 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..339394d 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
-		unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
+		      unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index bf66922..0a3414b 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -50,6 +50,7 @@
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
+#include <asm/virt.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -60,7 +61,10 @@ EXPORT_SYMBOL(__stack_chk_guard);
 void soft_restart(unsigned long addr)
 {
 	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
+
+	cpu_soft_restart(virt_to_phys(cpu_reset), is_hyp_mode_available(),
+			 addr);
+
 	/* Should never get here */
 	BUG();
 }
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 4e778b1..7467199 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,6 +25,7 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/virt.h>
 
 #include "proc-macros.S"
 
@@ -59,27 +60,48 @@ ENTRY(cpu_cache_off)
 ENDPROC(cpu_cache_off)
 
 /*
- *	cpu_reset(loc)
+ * cpu_reset(el2_switch, loc) - Helper for cpu_soft_restart.
  *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @addr: Location to jump to for soft reset.
  *
- *	- loc   - location to jump to for soft reset
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
  */
+
 	.align	5
+
 ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
+	mrs	x2, sctlr_el1
+	bic	x2, x2, #1
+	msr	sctlr_el1, x2			// disable the MMU
 	isb
-	ret	x0
+
+	cbz	x0, 1f				// el2_switch?
+	mov	x0, x1
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	hvc	#HVC_CALL_FUNC			// no return
+
+1:	ret	x1
 ENDPROC(cpu_reset)
 
+/*
+ * cpu_soft_restart(cpu_reset, el2_switch, addr) - Perform a cpu soft reset.
+ *
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed, passed to cpu_reset.
+ * @addr: Location to jump to for soft reset, passed to cpu_reset.
+ *
+ */
+
 ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
+	mov	x19, x0				// cpu_reset
+	mov	x20, x1				// el2_switch
+	mov	x21, x2				// addr
 
 	/* Turn D-cache off */
 	bl	cpu_cache_off
@@ -88,6 +110,7 @@ ENTRY(cpu_soft_restart)
 	bl	flush_cache_all
 
 	mov	x0, x20
+	mov	x1, x21
 	ret	x19
 ENDPROC(cpu_soft_restart)
 
-- 
1.9.1

[PATCH 1/8] arm64/kvm: Fix assembler compatibility of macros

[Geoff Levand]

Some of the macros defined in kvm_arm.h are useful in assembly files, but are
not compatible with the assembler.  Change any C language integer constant
definitions using appended U, UL, or ULL to the UL() preprocessor macro.  Also,
add a preprocessor include of the asm/memory.h file which defines the UL()
macro.

Fixes build errors like these when using kvm_arm.h in assembly
source files:

  Error: unexpected characters following instruction at operand 3 -- `and x0,x1,#((1U<<25)-1)'

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/kvm_arm.h | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index cc83520..9038a26 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -149,9 +150,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -174,13 +175,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -194,16 +195,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
-- 
1.9.1

[PATCH 3/8] arm64: Add new hcall HVC_CALL_FUNC

[Geoff Levand]

Add the new hcall HVC_CALL_FUNC that allows execution of a function at EL2.
During CPU reset the CPU must be brought to the exception level it had on
entry to the kernel.  The HVC_CALL_FUNC hcall will provide the mechanism
needed for this exception level switch.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/virt.h | 13 +++++++++++++
 arch/arm64/kernel/hyp-stub.S  | 17 ++++++++++++++---
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 99c319c..055e8d8 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -41,6 +41,19 @@
 
 #define HVC_CALL_HYP 3
 
+/*
+ * HVC_CALL_FUNC - Execute a function at EL2.
+ *
+ * @x0: Physical address of the funtion to be executed.
+ * @x1: Passed as the first argument to the function.
+ * @x2: Passed as the second argument to the function.
+ * @x3: Passed as the third argument to the function.
+ *
+ * The called function must preserve the contents of register x18.
+ */
+
+#define HVC_CALL_FUNC 4
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 9ce8746..719c726 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -66,9 +66,20 @@ el1_sync:
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	cmp	x18, #HVC_SET_VECTORS
-	b.ne	2f
-	msr	vbar_el2, x0
+1:	cmp     x18, #HVC_SET_VECTORS
+	b.ne    1f
+	msr     vbar_el2, x0
+	b       2f
+
+1:	cmp     x18, #HVC_CALL_FUNC
+	b.ne    2f
+	mov     x18, lr
+	mov     lr, x0
+	mov     x0, x1
+	mov     x1, x2
+	mov     x2, x3
+	blr     lr
+	mov     lr, x18
 
 2:	eret
 ENDPROC(el1_sync)
-- 
1.9.1

[PATCH 6/8] arm64/kexec: Add core kexec support

[Geoff Levand]

Add three new files, kexec.h, machine_kexec.c and relocate_kernel.S to the
arm64 architecture that add support for the kexec re-boot mechanism
(CONFIG_KEXEC) on arm64 platforms.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/Kconfig                  |   9 ++
 arch/arm64/include/asm/kexec.h      |  47 +++++++++
 arch/arm64/kernel/Makefile          |   1 +
 arch/arm64/kernel/machine_kexec.c   | 169 +++++++++++++++++++++++++++++++++
 arch/arm64/kernel/relocate_kernel.S | 184 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/kexec.h          |   1 +
 6 files changed, 411 insertions(+)
 create mode 100644 arch/arm64/include/asm/kexec.h
 create mode 100644 arch/arm64/kernel/machine_kexec.c
 create mode 100644 arch/arm64/kernel/relocate_kernel.S

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f0d3a2d..af03449 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -313,6 +313,15 @@ config ARCH_HAS_CACHE_LINE_SIZE
 
 source "mm/Kconfig"
 
+config KEXEC
+	depends on (!SMP || PM_SLEEP_SMP)
+	bool "kexec system call"
+	---help---
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel.  It is like a reboot
+	  but it is independent of the system firmware.   And like a reboot
+	  you can start any kernel with it, not just Linux.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
new file mode 100644
index 0000000..e7bd7ab
--- /dev/null
+++ b/arch/arm64/include/asm/kexec.h
@@ -0,0 +1,47 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#if !defined(_ARM64_KEXEC_H)
+#define _ARM64_KEXEC_H
+
+/* Maximum physical address we can use pages from */
+
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE	4096
+
+#define KEXEC_ARCH KEXEC_ARCH_ARM64
+
+#if !defined(__ASSEMBLY__)
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ *
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	/* Empty routine needed to avoid build errors. */
+}
+
+#endif /* !defined(__ASSEMBLY__) */
+
+#endif
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6e9538c..77a7351 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -30,6 +30,7 @@ arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
+arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
new file mode 100644
index 0000000..95bc8d9
--- /dev/null
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -0,0 +1,169 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#include <linux/kexec.h>
+#include <linux/of_fdt.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/system_misc.h>
+
+/* Global variables for the relocate_kernel routine. */
+
+extern const unsigned char relocate_new_kernel[];
+extern const unsigned long relocate_new_kernel_size;
+extern unsigned long arm64_kexec_dtb_addr;
+extern unsigned long arm64_kexec_kimage_head;
+extern unsigned long arm64_kexec_kimage_start;
+
+/**
+ * kexec_is_dtb - Helper routine to check the device tree header signature.
+ */
+
+static bool kexec_is_dtb(const void *dtb)
+{
+	__be32 magic;
+
+	return get_user(magic, (__be32 *)dtb) ? false :
+		(be32_to_cpu(magic) == OF_DT_HEADER);
+}
+
+/**
+ * kexec_find_dtb_seg - Helper routine to find the dtb segment.
+ */
+
+static const struct kexec_segment *kexec_find_dtb_seg(
+	const struct kimage *image)
+{
+	int i;
+
+	for (i = 0; i < image->nr_segments; i++) {
+		if (kexec_is_dtb(image->segment[i].buf))
+			return &image->segment[i];
+	}
+
+	return NULL;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+	/* Empty routine needed to avoid build errors. */
+}
+
+/**
+ * machine_kexec_prepare - Prepare for a kexec reboot.
+ *
+ * Called from the core kexec code when a kernel image is loaded.
+ */
+
+int machine_kexec_prepare(struct kimage *image)
+{
+	const struct kexec_segment *dtb_seg = kexec_find_dtb_seg(image);
+
+	if (!dtb_seg)
+		pr_warn("%s: No device tree segment found.\n", __func__);
+
+	arm64_kexec_dtb_addr = dtb_seg ? dtb_seg->mem : 0;
+	arm64_kexec_kimage_start = image->start;
+
+	return 0;
+}
+
+/**
+ * kexec_list_flush - Helper to flush the kimage list to PoC.
+ */
+
+static void kexec_list_flush(unsigned long kimage_head)
+{
+	void *dest;
+	unsigned long *entry;
+
+	for (entry = &kimage_head, dest = NULL; ; entry++) {
+		unsigned int flag = *entry &
+			(IND_DESTINATION | IND_INDIRECTION | IND_DONE |
+			IND_SOURCE);
+		void *addr = phys_to_virt(*entry & PAGE_MASK);
+
+		switch (flag) {
+		case IND_INDIRECTION:
+			entry = (unsigned long *)addr - 1;
+			__flush_dcache_area(addr, PAGE_SIZE);
+			break;
+		case IND_DESTINATION:
+			dest = addr;
+			break;
+		case IND_SOURCE:
+			__flush_dcache_area(addr, PAGE_SIZE);
+			dest += PAGE_SIZE;
+			break;
+		case IND_DONE:
+			return;
+		default:
+			break;
+		}
+	}
+}
+
+/**
+ * machine_kexec - Do the kexec reboot.
+ *
+ * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC.
+ */
+
+void machine_kexec(struct kimage *image)
+{
+	phys_addr_t reboot_code_buffer_phys;
+	void *reboot_code_buffer;
+
+	BUG_ON(num_online_cpus() > 1);
+
+	arm64_kexec_kimage_head = image->head;
+
+	reboot_code_buffer_phys = page_to_phys(image->control_code_page);
+	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
+
+	/*
+	 * Copy relocate_new_kernel to the reboot_code_buffer for use
+	 * after the kernel is shut down.
+	 */
+
+	memcpy(reboot_code_buffer, relocate_new_kernel,
+		relocate_new_kernel_size);
+
+	/* Flush the reboot_code_buffer in preparation for its execution. */
+
+	__flush_dcache_area(reboot_code_buffer, relocate_new_kernel_size);
+
+	/* Flush the kimage list. */
+
+	kexec_list_flush(image->head);
+
+	pr_info("Bye!\n");
+
+	/* Disable all DAIF exceptions. */
+
+	asm volatile ("msr daifset, #0xf" : : : "memory");
+
+	/*
+	 * soft_restart() will shutdown the MMU, disable data caches, then
+	 * transfer control to the reboot_code_buffer which contains a copy of
+	 * the relocate_new_kernel routine.  relocate_new_kernel will use
+	 * physical addressing to relocate the new kernel to its final position
+	 * and then will transfer control to the entry point of the new kernel.
+	 */
+
+	soft_restart(reboot_code_buffer_phys);
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	/* Empty routine needed to avoid build errors. */
+}
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
new file mode 100644
index 0000000..ac68322
--- /dev/null
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -0,0 +1,184 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#include <asm/assembler.h>
+#include <asm/kexec.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+#include <asm/proc-macros.S>
+
+/* The list entry flags. */
+
+#define IND_DESTINATION_BIT 0
+#define IND_INDIRECTION_BIT 1
+#define IND_DONE_BIT        2
+#define IND_SOURCE_BIT      3
+
+/*
+ * relocate_new_kernel - Put the 2nd stage kernel image in place and boot it.
+ *
+ * The memory that the old kernel occupies may be overwritten when coping the
+ * new kernel to its final location.  To assure that the relocate_new_kernel
+ * routine which does that copy is not overwritten all code and data needed
+ * by relocate_new_kernel must be between the symbols relocate_new_kernel and
+ * relocate_new_kernel_end.  The machine_kexec() routine will copy
+ * relocate_new_kernel to the kexec control_code_page, a special page which
+ * has been set up to be preserved during the kernel copy operation.
+ */
+
+.globl relocate_new_kernel
+relocate_new_kernel:
+
+	/* Setup the list loop variables. */
+
+	ldr	x18, arm64_kexec_kimage_head	/* x18 = list entry */
+	dcache_line_size x17, x0		/* x17 = dcache line size */
+	mov	x16, xzr			/* x16 = segment start */
+	mov	x15, xzr			/* x15 = entry ptr */
+	mov	x14, xzr			/* x14 = copy dest */
+
+	/* Check if the new kernel needs relocation. */
+
+	cbz	x18, .Ldone
+	tbnz	x18, IND_DONE_BIT, .Ldone
+
+.Lloop:
+	and	x13, x18, PAGE_MASK		/* x13 = addr */
+
+	/* Test the entry flags. */
+
+.Ltest_source:
+	tbz	x18, IND_SOURCE_BIT, .Ltest_indirection
+
+	/* copy_page(x20 = dest, x21 = src) */
+
+	mov x20, x14
+	mov x21, x13
+
+1:	ldp	x22, x23, [x21]
+	ldp	x24, x25, [x21, #16]
+	ldp	x26, x27, [x21, #32]
+	ldp	x28, x29, [x21, #48]
+	add	x21, x21, #64
+	stnp	x22, x23, [x20]
+	stnp	x24, x25, [x20, #16]
+	stnp	x26, x27, [x20, #32]
+	stnp	x28, x29, [x20, #48]
+	add	x20, x20, #64
+	tst	x21, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	/* dest += PAGE_SIZE */
+
+	add	x14, x14, PAGE_SIZE
+	b	.Lnext
+
+.Ltest_indirection:
+	tbz	x18, IND_INDIRECTION_BIT, .Ltest_destination
+
+	/* ptr = addr */
+
+	mov	x15, x13
+	b	.Lnext
+
+.Ltest_destination:
+	tbz	x18, IND_DESTINATION_BIT, .Lnext
+
+	/* flush segment */
+
+	bl	.Lflush
+	mov	x16, x13
+
+	/* dest = addr */
+
+	mov	x14, x13
+
+.Lnext:
+	/* entry = *ptr++ */
+
+	ldr	x18, [x15], #8
+
+	/* while (!(entry & DONE)) */
+
+	tbz	x18, IND_DONE_BIT, .Lloop
+
+.Ldone:
+	/* flush last segment */
+
+	bl	.Lflush
+
+	dsb	sy
+	isb
+	ic	ialluis
+	dsb	sy
+	isb
+
+	/* start_new_kernel */
+
+	ldr	x4, arm64_kexec_kimage_start
+	ldr	x0, arm64_kexec_dtb_addr
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	br	x4
+
+/* flush - x17 = line size, x16 = start addr, x14 = end addr. */
+
+.Lflush:
+	cbz	x16, 2f
+	mov	x0, x16
+	sub	x1, x17, #1
+	bic	x0, x0, x1
+1:	dc	civac, x0
+	add	x0, x0, x17
+	cmp	x0, x14
+	b.lo	1b
+2:	ret
+
+.align 3	/* To keep the 64-bit values below naturally aligned. */
+
+/* The machine_kexec routines set these variables. */
+
+/*
+ * arm64_kexec_dtb_addr - Physical address of the new kernel's device tree.
+ */
+
+.globl arm64_kexec_dtb_addr
+arm64_kexec_dtb_addr:
+	.quad	0x0
+
+/*
+ * arm64_kexec_kimage_head - Copy of image->head, the list of kimage entries.
+ */
+
+.globl arm64_kexec_kimage_head
+arm64_kexec_kimage_head:
+	.quad	0x0
+
+/*
+ * arm64_kexec_kimage_start - Copy of image->start, the entry point of the new
+ * kernel.
+ */
+
+.globl arm64_kexec_kimage_start
+arm64_kexec_kimage_start:
+	.quad	0x0
+
+.Lrelocate_new_kernel_end:
+
+/*
+ * relocate_new_kernel_size - Number of bytes to copy to the control_code_page.
+ */
+
+.globl relocate_new_kernel_size
+relocate_new_kernel_size:
+	.quad .Lrelocate_new_kernel_end - relocate_new_kernel
+
+.org	KEXEC_CONTROL_PAGE_SIZE
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 6925f5b..04626b9 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -39,6 +39,7 @@
 #define KEXEC_ARCH_SH      (42 << 16)
 #define KEXEC_ARCH_MIPS_LE (10 << 16)
 #define KEXEC_ARCH_MIPS    ( 8 << 16)
+#define KEXEC_ARCH_ARM64   (183 << 16)
 
 /* The artificial cap on the number of segments passed to kexec_load. */
 #define KEXEC_SEGMENT_MAX 16
-- 
1.9.1

[PATCH 5/8] arm64: Move proc-macros.S to include/asm

[Geoff Levand]

To allow the assembler macros defined in proc-macros.S to be used outside
the mm code move the proc-macros.S file from arch/arm64/mm/ to
arch/arm64/include/asm/ and fix up any preprocessor includes to use the new
file location.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-macros.S | 54 ++++++++++++++++++++++++++++++++++++
 arch/arm64/mm/cache.S                |  3 +-
 arch/arm64/mm/proc-macros.S          | 54 ------------------------------------
 arch/arm64/mm/proc.S                 |  3 +-
 4 files changed, 56 insertions(+), 58 deletions(-)
 create mode 100644 arch/arm64/include/asm/proc-macros.S
 delete mode 100644 arch/arm64/mm/proc-macros.S

diff --git a/arch/arm64/include/asm/proc-macros.S b/arch/arm64/include/asm/proc-macros.S
new file mode 100644
index 0000000..005d29e
--- /dev/null
+++ b/arch/arm64/include/asm/proc-macros.S
@@ -0,0 +1,54 @@
+/*
+ * Based on arch/arm/mm/proc-macros.S
+ *
+ * Copyright (C) 2012 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 <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+
+/*
+ * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
+ */
+	.macro	vma_vm_mm, rd, rn
+	ldr	\rd, [\rn, #VMA_VM_MM]
+	.endm
+
+/*
+ * mmid - get context id from mm pointer (mm->context.id)
+ */
+	.macro	mmid, rd, rn
+	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+	.endm
+
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ */
+	.macro	dcache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	and	\tmp, \tmp, #0xf		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2366383..4e811a4 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -20,8 +20,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
-
-#include "proc-macros.S"
+#include <asm/proc-macros.S>
 
 /*
  *	__flush_dcache_all()
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
deleted file mode 100644
index 005d29e..0000000
--- a/arch/arm64/mm/proc-macros.S
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Based on arch/arm/mm/proc-macros.S
- *
- * Copyright (C) 2012 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 <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-/*
- * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
- */
-	.macro	vma_vm_mm, rd, rn
-	ldr	\rd, [\rn, #VMA_VM_MM]
-	.endm
-
-/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldr	\rd, [\rn, #MM_CONTEXT_ID]
-	.endm
-
-/*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
- */
-	.macro	dcache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
-
-/*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
- */
-	.macro	icache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	and	\tmp, \tmp, #0xf		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 7467199..b767032 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,10 +25,9 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/proc-macros.S>
 #include <asm/virt.h>
 
-#include "proc-macros.S"
-
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
 #else
-- 
1.9.1

[PATCH 7/8] arm64/kexec: Enable kexec in the arm64 defconfig

[Geoff Levand]

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/configs/defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index d92ef3c..ebf8b3f 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -39,6 +39,7 @@ CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_KEXEC=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
-- 
1.9.1

[PATCH 3/8] arm64: Add new hcall HVC_CALL_FUNC

[Geoff Levand]

Add the new hcall HVC_CALL_FUNC that allows execution of a function at EL2.
During CPU reset the CPU must be brought to the exception level it had on
entry to the kernel.  The HVC_CALL_FUNC hcall will provide the mechanism
needed for this exception level switch.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/virt.h | 13 +++++++++++++
 arch/arm64/kernel/hyp-stub.S  | 17 ++++++++++++++---
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 99c319c..055e8d8 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -41,6 +41,19 @@
 
 #define HVC_CALL_HYP 3
 
+/*
+ * HVC_CALL_FUNC - Execute a function at EL2.
+ *
+ * @x0: Physical address of the funtion to be executed.
+ * @x1: Passed as the first argument to the function.
+ * @x2: Passed as the second argument to the function.
+ * @x3: Passed as the third argument to the function.
+ *
+ * The called function must preserve the contents of register x18.
+ */
+
+#define HVC_CALL_FUNC 4
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 9ce8746..719c726 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -66,9 +66,20 @@ el1_sync:
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	cmp	x18, #HVC_SET_VECTORS
-	b.ne	2f
-	msr	vbar_el2, x0
+1:	cmp     x18, #HVC_SET_VECTORS
+	b.ne    1f
+	msr     vbar_el2, x0
+	b       2f
+
+1:	cmp     x18, #HVC_CALL_FUNC
+	b.ne    2f
+	mov     x18, lr
+	mov     lr, x0
+	mov     x0, x1
+	mov     x1, x2
+	mov     x2, x3
+	blr     lr
+	mov     lr, x18
 
 2:	eret
 ENDPROC(el1_sync)
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 2/8] arm64: Convert hcalls to use ISS field

[Geoff Levand]

To allow for additional hcalls to be defined and to make the arm64 hcall API
more consistent across exception vector routines change the hcall implementations
to use the ISS field of the ESR_EL2 register to specify the hcall type.

The existing arm64 hcall implementations are limited in that they only allow
for two distinct hcalls; with the x0 register either zero, or not zero.  Also,
the API of the hyp-stub exception vector routines and the KVM exception vector
routines differ; hyp-stub uses a non-zero value in x0 to implement
__hyp_set_vectors, whereas KVM uses it to implement kvm_call_hyp.

Define three new preprocessor macros HVC_GET_VECTORS, HVC_SET_VECTORS and
HVC_CALL_HYP and to be used as hcall type specifiers and convert the
existing __hyp_get_vectors(), __hyp_set_vectors() and kvm_call_hyp() routines
to use these new macros when executing and HVC call.  Also change the
corresponding hyp-stub and KVM el1_sync exception vector routines to use these
new macros.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/virt.h | 20 ++++++++++++++++++++
 arch/arm64/kernel/hyp-stub.S  | 34 ++++++++++++++++++++++------------
 arch/arm64/kvm/hyp.S          | 18 +++++++++++-------
 3 files changed, 53 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 7a5df52..99c319c 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -21,6 +21,26 @@
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 
+/*
+ * HVC_GET_VECTORS - Return the value of the vbar_el2 register.
+ */
+
+#define HVC_GET_VECTORS 1
+
+/*
+ * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
+ *
+ * @x0: Physical address of the new vector table.
+ */
+
+#define HVC_SET_VECTORS 2
+
+/*
+ * HVC_CALL_HYP - Execute a hyp routine.
+ */
+
+#define HVC_CALL_HYP 3
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index a272f33..9ce8746 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -22,6 +22,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
+#include <asm/kvm_arm.h>
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
@@ -53,14 +54,22 @@ ENDPROC(__hyp_stub_vectors)
 	.align 11
 
 el1_sync:
-	mrs	x1, esr_el2
-	lsr	x1, x1, #26
-	cmp	x1, #0x16
-	b.ne	2f				// Not an HVC trap
-	cbz	x0, 1f
-	msr	vbar_el2, x0			// Set vbar_el2
+	mrs	x18, esr_el2
+	lsr	x17, x18, #ESR_EL2_EC_SHIFT
+	and	x18, x18, #ESR_EL2_ISS
+
+	cmp     x17, #ESR_EL2_EC_HVC64
+	b.ne    2f				// Not an HVC trap
+
+	cmp	x18, #HVC_GET_VECTORS
+	b.ne	1f
+	mrs	x0, vbar_el2
 	b	2f
-1:	mrs	x0, vbar_el2			// Return vbar_el2
+
+1:	cmp	x18, #HVC_SET_VECTORS
+	b.ne	2f
+	msr	vbar_el2, x0
+
 2:	eret
 ENDPROC(el1_sync)
 
@@ -100,11 +109,12 @@ ENDPROC(\label)
  * initialisation entry point.
  */
 
-ENTRY(__hyp_get_vectors)
-	mov	x0, xzr
-	// fall through
 ENTRY(__hyp_set_vectors)
-	hvc	#0
+	hvc	#HVC_SET_VECTORS
 	ret
-ENDPROC(__hyp_get_vectors)
 ENDPROC(__hyp_set_vectors)
+
+ENTRY(__hyp_get_vectors)
+	hvc	#HVC_GET_VECTORS
+	ret
+ENDPROC(__hyp_get_vectors)
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index b72aa9f..9607f15 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -26,6 +26,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/virt.h>
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
@@ -1105,12 +1106,9 @@ __hyp_panic_str:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
- * A function pointer with a value of 0 has a special meaning, and is
- * used to implement __hyp_get_vectors in the same way as in
- * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(kvm_call_hyp)
-	hvc	#0
+	hvc	#HVC_CALL_HYP
 	ret
 ENDPROC(kvm_call_hyp)
 
@@ -1140,6 +1138,7 @@ el1_sync:					// Guest trapped into EL2
 	push	x2, x3
 
 	mrs	x1, esr_el2
+	and	x0, x1, #ESR_EL2_ISS
 	lsr	x2, x1, #ESR_EL2_EC_SHIFT
 
 	cmp	x2, #ESR_EL2_EC_HVC64
@@ -1149,15 +1148,19 @@ el1_sync:					// Guest trapped into EL2
 	cbnz	x3, el1_trap			// called HVC
 
 	/* Here, we're pretty sure the host called HVC. */
+	mov	x18, x0
 	pop	x2, x3
 	pop	x0, x1
 
-	/* Check for __hyp_get_vectors */
-	cbnz	x0, 1f
+	cmp	x18, #HVC_GET_VECTORS
+	b.ne	1f
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	push	lr, xzr
+1:	cmp	x18, #HVC_CALL_HYP
+	b.ne	2f
+
+	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -1170,6 +1173,7 @@ el1_sync:					// Guest trapped into EL2
 	blr	lr
 
 	pop	lr, xzr
+
 2:	eret
 
 el1_trap:
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 0/8] arm64 kexec kernel patches V4

[Geoff Levand]

Hi All,

This series adds the core support for kexec re-boots on arm64.  I have tested
with  the arm64 wrapper program on the ARM VE fast model and the Foundation
model, and using Linaro's EFI build on the ARM base AEMv8 fast model with
various kernel config options for both the first and second stage kernels.

To load a second stage kernel and execute a kexec re-boot on arm64 my patches to
kexec-tools [2], which have not yet been merged upstream, are needed.

This series does not include some re-work of the spin-table CPU enable method
that is needed to support it, nor does it include some re-work of KVM to support
CPU soft reset.  A first stage kernel built with these patches will boot and run
correctly, but will fail to load a second stage kernel if running on a machine
with any spin-table enabled secondary CPUs (CONFIG_SMP=n works OK), and will
fail the kexec re-boot resulting in a system hang if the first stage kernel was
built with CONFIG_KVM=y.  Work-in-progress patches to support these are in my
linux-kexec source repository [1].

Patches 1-4 rework the arm64 hcall mechanism to give the arm64 soft_restart()
routine the ability to switch exception levels from EL1 to EL2 for kernels that
were entered in EL2.

Patch 5 moves proc-macros.S from arm64/mm to arm64/include/asm so that the
dcache_line_size macro it defines can be uesd by kexec's relocate kernel
routine.

Patches 11-13 add the actual kexec support.

Please consider all patches for inclusion.  Any comments or suggestions on how 
to improve are welcome.

[1]  https://git.linaro.org/people/geoff.levand/linux-kexec.git
[2]  https://git.linaro.org/people/geoff.levand/kexec-tools.git

-Geoff

The following changes since commit 0a6479b0ffad8dd236915e271faaf2cbb4cac287:

	arm64: Remove unneeded extern keyword (2014-10-03 14:51:02 +0100)

are available in the git repository at:

	git://git.linaro.org/people/geoff.levand/linux-kexec.git kexec-v4

for you to fetch changes up to e122ed3a1b2afbaf69baf2c7cf354f7e557c5851:

	arm64/kexec: Add pr_devel output (2014-10-03 15:53:58 -0700)

----------------------------------------------------------------
Geoff Levand (8):
	arm64/kvm: Fix assembler compatibility of macros
	arm64: Convert hcalls to use ISS field
	arm64: Add new hcall HVC_CALL_FUNC
	arm64: Add EL2 switch to soft_restart
	arm64: Move proc-macros.S to include/asm
	arm64/kexec: Add core kexec support
	arm64/kexec: Enable kexec in the arm64 defconfig
	arm64/kexec: Add pr_devel output

arch/arm64/Kconfig                           |   9 ++
arch/arm64/configs/defconfig                 |   1 +
arch/arm64/include/asm/kexec.h               |  47 ++++++
arch/arm64/include/asm/kvm_arm.h             |  21 +--
arch/arm64/include/asm/proc-fns.h            |   4 +-
arch/arm64/{mm => include/asm}/proc-macros.S |   0
arch/arm64/include/asm/virt.h                |  33 ++++
arch/arm64/kernel/Makefile                   |   1 +
arch/arm64/kernel/hyp-stub.S                 |  45 ++++--
arch/arm64/kernel/machine_kexec.c            | 225 +++++++++++++++++++++++++++
arch/arm64/kernel/process.c                  |   6 +-
arch/arm64/kernel/relocate_kernel.S          | 184 ++++++++++++++++++++++
arch/arm64/kvm/hyp.S                         |  18 ++-
arch/arm64/mm/cache.S                        |   3 +-
arch/arm64/mm/proc.S                         |  50 ++++--
include/uapi/linux/kexec.h                   |   1 +
16 files changed, 600 insertions(+), 48 deletions(-)
create mode 100644 arch/arm64/include/asm/kexec.h
rename arch/arm64/{mm => include/asm}/proc-macros.S (100%)
create mode 100644 arch/arm64/kernel/machine_kexec.c
create mode 100644 arch/arm64/kernel/relocate_kernel.S

-- 
1.9.1


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

When a CPU is reset it needs to be put into the exception level it had when it
entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
not set the soft reset address will be entered at EL1.

Update cpu_soft_restart() and soft_restart() to pass the return of
is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
change.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-fns.h |  4 ++--
 arch/arm64/kernel/process.c       |  6 ++++-
 arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
 3 files changed, 42 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..339394d 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
-		unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
+		      unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index bf66922..0a3414b 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -50,6 +50,7 @@
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
+#include <asm/virt.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -60,7 +61,10 @@ EXPORT_SYMBOL(__stack_chk_guard);
 void soft_restart(unsigned long addr)
 {
 	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
+
+	cpu_soft_restart(virt_to_phys(cpu_reset), is_hyp_mode_available(),
+			 addr);
+
 	/* Should never get here */
 	BUG();
 }
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 4e778b1..7467199 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,6 +25,7 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/virt.h>
 
 #include "proc-macros.S"
 
@@ -59,27 +60,48 @@ ENTRY(cpu_cache_off)
 ENDPROC(cpu_cache_off)
 
 /*
- *	cpu_reset(loc)
+ * cpu_reset(el2_switch, loc) - Helper for cpu_soft_restart.
  *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @addr: Location to jump to for soft reset.
  *
- *	- loc   - location to jump to for soft reset
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
  */
+
 	.align	5
+
 ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
+	mrs	x2, sctlr_el1
+	bic	x2, x2, #1
+	msr	sctlr_el1, x2			// disable the MMU
 	isb
-	ret	x0
+
+	cbz	x0, 1f				// el2_switch?
+	mov	x0, x1
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	hvc	#HVC_CALL_FUNC			// no return
+
+1:	ret	x1
 ENDPROC(cpu_reset)
 
+/*
+ * cpu_soft_restart(cpu_reset, el2_switch, addr) - Perform a cpu soft reset.
+ *
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed, passed to cpu_reset.
+ * @addr: Location to jump to for soft reset, passed to cpu_reset.
+ *
+ */
+
 ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
+	mov	x19, x0				// cpu_reset
+	mov	x20, x1				// el2_switch
+	mov	x21, x2				// addr
 
 	/* Turn D-cache off */
 	bl	cpu_cache_off
@@ -88,6 +110,7 @@ ENTRY(cpu_soft_restart)
 	bl	flush_cache_all
 
 	mov	x0, x20
+	mov	x1, x21
 	ret	x19
 ENDPROC(cpu_soft_restart)
 
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 5/8] arm64: Move proc-macros.S to include/asm

[Geoff Levand]

To allow the assembler macros defined in proc-macros.S to be used outside
the mm code move the proc-macros.S file from arch/arm64/mm/ to
arch/arm64/include/asm/ and fix up any preprocessor includes to use the new
file location.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-macros.S | 54 ++++++++++++++++++++++++++++++++++++
 arch/arm64/mm/cache.S                |  3 +-
 arch/arm64/mm/proc-macros.S          | 54 ------------------------------------
 arch/arm64/mm/proc.S                 |  3 +-
 4 files changed, 56 insertions(+), 58 deletions(-)
 create mode 100644 arch/arm64/include/asm/proc-macros.S
 delete mode 100644 arch/arm64/mm/proc-macros.S

diff --git a/arch/arm64/include/asm/proc-macros.S b/arch/arm64/include/asm/proc-macros.S
new file mode 100644
index 0000000..005d29e
--- /dev/null
+++ b/arch/arm64/include/asm/proc-macros.S
@@ -0,0 +1,54 @@
+/*
+ * Based on arch/arm/mm/proc-macros.S
+ *
+ * Copyright (C) 2012 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 <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+
+/*
+ * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
+ */
+	.macro	vma_vm_mm, rd, rn
+	ldr	\rd, [\rn, #VMA_VM_MM]
+	.endm
+
+/*
+ * mmid - get context id from mm pointer (mm->context.id)
+ */
+	.macro	mmid, rd, rn
+	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+	.endm
+
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ */
+	.macro	dcache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	and	\tmp, \tmp, #0xf		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2366383..4e811a4 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -20,8 +20,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
-
-#include "proc-macros.S"
+#include <asm/proc-macros.S>
 
 /*
  *	__flush_dcache_all()
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
deleted file mode 100644
index 005d29e..0000000
--- a/arch/arm64/mm/proc-macros.S
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Based on arch/arm/mm/proc-macros.S
- *
- * Copyright (C) 2012 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 <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-/*
- * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
- */
-	.macro	vma_vm_mm, rd, rn
-	ldr	\rd, [\rn, #VMA_VM_MM]
-	.endm
-
-/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldr	\rd, [\rn, #MM_CONTEXT_ID]
-	.endm
-
-/*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
- */
-	.macro	dcache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
-
-/*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
- */
-	.macro	icache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	and	\tmp, \tmp, #0xf		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 7467199..b767032 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,10 +25,9 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/proc-macros.S>
 #include <asm/virt.h>
 
-#include "proc-macros.S"
-
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
 #else
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 7/8] arm64/kexec: Enable kexec in the arm64 defconfig

[Geoff Levand]

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/configs/defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index d92ef3c..ebf8b3f 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -39,6 +39,7 @@ CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_KEXEC=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 1/8] arm64/kvm: Fix assembler compatibility of macros

[Geoff Levand]

Some of the macros defined in kvm_arm.h are useful in assembly files, but are
not compatible with the assembler.  Change any C language integer constant
definitions using appended U, UL, or ULL to the UL() preprocessor macro.  Also,
add a preprocessor include of the asm/memory.h file which defines the UL()
macro.

Fixes build errors like these when using kvm_arm.h in assembly
source files:

  Error: unexpected characters following instruction at operand 3 -- `and x0,x1,#((1U<<25)-1)'

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/kvm_arm.h | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index cc83520..9038a26 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -149,9 +150,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -174,13 +175,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -194,16 +195,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 6/8] arm64/kexec: Add core kexec support

[Geoff Levand]

Add three new files, kexec.h, machine_kexec.c and relocate_kernel.S to the
arm64 architecture that add support for the kexec re-boot mechanism
(CONFIG_KEXEC) on arm64 platforms.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/Kconfig                  |   9 ++
 arch/arm64/include/asm/kexec.h      |  47 +++++++++
 arch/arm64/kernel/Makefile          |   1 +
 arch/arm64/kernel/machine_kexec.c   | 169 +++++++++++++++++++++++++++++++++
 arch/arm64/kernel/relocate_kernel.S | 184 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/kexec.h          |   1 +
 6 files changed, 411 insertions(+)
 create mode 100644 arch/arm64/include/asm/kexec.h
 create mode 100644 arch/arm64/kernel/machine_kexec.c
 create mode 100644 arch/arm64/kernel/relocate_kernel.S

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f0d3a2d..af03449 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -313,6 +313,15 @@ config ARCH_HAS_CACHE_LINE_SIZE
 
 source "mm/Kconfig"
 
+config KEXEC
+	depends on (!SMP || PM_SLEEP_SMP)
+	bool "kexec system call"
+	---help---
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel.  It is like a reboot
+	  but it is independent of the system firmware.   And like a reboot
+	  you can start any kernel with it, not just Linux.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
new file mode 100644
index 0000000..e7bd7ab
--- /dev/null
+++ b/arch/arm64/include/asm/kexec.h
@@ -0,0 +1,47 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#if !defined(_ARM64_KEXEC_H)
+#define _ARM64_KEXEC_H
+
+/* Maximum physical address we can use pages from */
+
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE	4096
+
+#define KEXEC_ARCH KEXEC_ARCH_ARM64
+
+#if !defined(__ASSEMBLY__)
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ *
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	/* Empty routine needed to avoid build errors. */
+}
+
+#endif /* !defined(__ASSEMBLY__) */
+
+#endif
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6e9538c..77a7351 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -30,6 +30,7 @@ arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
+arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
new file mode 100644
index 0000000..95bc8d9
--- /dev/null
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -0,0 +1,169 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#include <linux/kexec.h>
+#include <linux/of_fdt.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/system_misc.h>
+
+/* Global variables for the relocate_kernel routine. */
+
+extern const unsigned char relocate_new_kernel[];
+extern const unsigned long relocate_new_kernel_size;
+extern unsigned long arm64_kexec_dtb_addr;
+extern unsigned long arm64_kexec_kimage_head;
+extern unsigned long arm64_kexec_kimage_start;
+
+/**
+ * kexec_is_dtb - Helper routine to check the device tree header signature.
+ */
+
+static bool kexec_is_dtb(const void *dtb)
+{
+	__be32 magic;
+
+	return get_user(magic, (__be32 *)dtb) ? false :
+		(be32_to_cpu(magic) == OF_DT_HEADER);
+}
+
+/**
+ * kexec_find_dtb_seg - Helper routine to find the dtb segment.
+ */
+
+static const struct kexec_segment *kexec_find_dtb_seg(
+	const struct kimage *image)
+{
+	int i;
+
+	for (i = 0; i < image->nr_segments; i++) {
+		if (kexec_is_dtb(image->segment[i].buf))
+			return &image->segment[i];
+	}
+
+	return NULL;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+	/* Empty routine needed to avoid build errors. */
+}
+
+/**
+ * machine_kexec_prepare - Prepare for a kexec reboot.
+ *
+ * Called from the core kexec code when a kernel image is loaded.
+ */
+
+int machine_kexec_prepare(struct kimage *image)
+{
+	const struct kexec_segment *dtb_seg = kexec_find_dtb_seg(image);
+
+	if (!dtb_seg)
+		pr_warn("%s: No device tree segment found.\n", __func__);
+
+	arm64_kexec_dtb_addr = dtb_seg ? dtb_seg->mem : 0;
+	arm64_kexec_kimage_start = image->start;
+
+	return 0;
+}
+
+/**
+ * kexec_list_flush - Helper to flush the kimage list to PoC.
+ */
+
+static void kexec_list_flush(unsigned long kimage_head)
+{
+	void *dest;
+	unsigned long *entry;
+
+	for (entry = &kimage_head, dest = NULL; ; entry++) {
+		unsigned int flag = *entry &
+			(IND_DESTINATION | IND_INDIRECTION | IND_DONE |
+			IND_SOURCE);
+		void *addr = phys_to_virt(*entry & PAGE_MASK);
+
+		switch (flag) {
+		case IND_INDIRECTION:
+			entry = (unsigned long *)addr - 1;
+			__flush_dcache_area(addr, PAGE_SIZE);
+			break;
+		case IND_DESTINATION:
+			dest = addr;
+			break;
+		case IND_SOURCE:
+			__flush_dcache_area(addr, PAGE_SIZE);
+			dest += PAGE_SIZE;
+			break;
+		case IND_DONE:
+			return;
+		default:
+			break;
+		}
+	}
+}
+
+/**
+ * machine_kexec - Do the kexec reboot.
+ *
+ * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC.
+ */
+
+void machine_kexec(struct kimage *image)
+{
+	phys_addr_t reboot_code_buffer_phys;
+	void *reboot_code_buffer;
+
+	BUG_ON(num_online_cpus() > 1);
+
+	arm64_kexec_kimage_head = image->head;
+
+	reboot_code_buffer_phys = page_to_phys(image->control_code_page);
+	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
+
+	/*
+	 * Copy relocate_new_kernel to the reboot_code_buffer for use
+	 * after the kernel is shut down.
+	 */
+
+	memcpy(reboot_code_buffer, relocate_new_kernel,
+		relocate_new_kernel_size);
+
+	/* Flush the reboot_code_buffer in preparation for its execution. */
+
+	__flush_dcache_area(reboot_code_buffer, relocate_new_kernel_size);
+
+	/* Flush the kimage list. */
+
+	kexec_list_flush(image->head);
+
+	pr_info("Bye!\n");
+
+	/* Disable all DAIF exceptions. */
+
+	asm volatile ("msr daifset, #0xf" : : : "memory");
+
+	/*
+	 * soft_restart() will shutdown the MMU, disable data caches, then
+	 * transfer control to the reboot_code_buffer which contains a copy of
+	 * the relocate_new_kernel routine.  relocate_new_kernel will use
+	 * physical addressing to relocate the new kernel to its final position
+	 * and then will transfer control to the entry point of the new kernel.
+	 */
+
+	soft_restart(reboot_code_buffer_phys);
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	/* Empty routine needed to avoid build errors. */
+}
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
new file mode 100644
index 0000000..ac68322
--- /dev/null
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -0,0 +1,184 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ *
+ * 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.
+ */
+
+#include <asm/assembler.h>
+#include <asm/kexec.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+#include <asm/proc-macros.S>
+
+/* The list entry flags. */
+
+#define IND_DESTINATION_BIT 0
+#define IND_INDIRECTION_BIT 1
+#define IND_DONE_BIT        2
+#define IND_SOURCE_BIT      3
+
+/*
+ * relocate_new_kernel - Put the 2nd stage kernel image in place and boot it.
+ *
+ * The memory that the old kernel occupies may be overwritten when coping the
+ * new kernel to its final location.  To assure that the relocate_new_kernel
+ * routine which does that copy is not overwritten all code and data needed
+ * by relocate_new_kernel must be between the symbols relocate_new_kernel and
+ * relocate_new_kernel_end.  The machine_kexec() routine will copy
+ * relocate_new_kernel to the kexec control_code_page, a special page which
+ * has been set up to be preserved during the kernel copy operation.
+ */
+
+.globl relocate_new_kernel
+relocate_new_kernel:
+
+	/* Setup the list loop variables. */
+
+	ldr	x18, arm64_kexec_kimage_head	/* x18 = list entry */
+	dcache_line_size x17, x0		/* x17 = dcache line size */
+	mov	x16, xzr			/* x16 = segment start */
+	mov	x15, xzr			/* x15 = entry ptr */
+	mov	x14, xzr			/* x14 = copy dest */
+
+	/* Check if the new kernel needs relocation. */
+
+	cbz	x18, .Ldone
+	tbnz	x18, IND_DONE_BIT, .Ldone
+
+.Lloop:
+	and	x13, x18, PAGE_MASK		/* x13 = addr */
+
+	/* Test the entry flags. */
+
+.Ltest_source:
+	tbz	x18, IND_SOURCE_BIT, .Ltest_indirection
+
+	/* copy_page(x20 = dest, x21 = src) */
+
+	mov x20, x14
+	mov x21, x13
+
+1:	ldp	x22, x23, [x21]
+	ldp	x24, x25, [x21, #16]
+	ldp	x26, x27, [x21, #32]
+	ldp	x28, x29, [x21, #48]
+	add	x21, x21, #64
+	stnp	x22, x23, [x20]
+	stnp	x24, x25, [x20, #16]
+	stnp	x26, x27, [x20, #32]
+	stnp	x28, x29, [x20, #48]
+	add	x20, x20, #64
+	tst	x21, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	/* dest += PAGE_SIZE */
+
+	add	x14, x14, PAGE_SIZE
+	b	.Lnext
+
+.Ltest_indirection:
+	tbz	x18, IND_INDIRECTION_BIT, .Ltest_destination
+
+	/* ptr = addr */
+
+	mov	x15, x13
+	b	.Lnext
+
+.Ltest_destination:
+	tbz	x18, IND_DESTINATION_BIT, .Lnext
+
+	/* flush segment */
+
+	bl	.Lflush
+	mov	x16, x13
+
+	/* dest = addr */
+
+	mov	x14, x13
+
+.Lnext:
+	/* entry = *ptr++ */
+
+	ldr	x18, [x15], #8
+
+	/* while (!(entry & DONE)) */
+
+	tbz	x18, IND_DONE_BIT, .Lloop
+
+.Ldone:
+	/* flush last segment */
+
+	bl	.Lflush
+
+	dsb	sy
+	isb
+	ic	ialluis
+	dsb	sy
+	isb
+
+	/* start_new_kernel */
+
+	ldr	x4, arm64_kexec_kimage_start
+	ldr	x0, arm64_kexec_dtb_addr
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	br	x4
+
+/* flush - x17 = line size, x16 = start addr, x14 = end addr. */
+
+.Lflush:
+	cbz	x16, 2f
+	mov	x0, x16
+	sub	x1, x17, #1
+	bic	x0, x0, x1
+1:	dc	civac, x0
+	add	x0, x0, x17
+	cmp	x0, x14
+	b.lo	1b
+2:	ret
+
+.align 3	/* To keep the 64-bit values below naturally aligned. */
+
+/* The machine_kexec routines set these variables. */
+
+/*
+ * arm64_kexec_dtb_addr - Physical address of the new kernel's device tree.
+ */
+
+.globl arm64_kexec_dtb_addr
+arm64_kexec_dtb_addr:
+	.quad	0x0
+
+/*
+ * arm64_kexec_kimage_head - Copy of image->head, the list of kimage entries.
+ */
+
+.globl arm64_kexec_kimage_head
+arm64_kexec_kimage_head:
+	.quad	0x0
+
+/*
+ * arm64_kexec_kimage_start - Copy of image->start, the entry point of the new
+ * kernel.
+ */
+
+.globl arm64_kexec_kimage_start
+arm64_kexec_kimage_start:
+	.quad	0x0
+
+.Lrelocate_new_kernel_end:
+
+/*
+ * relocate_new_kernel_size - Number of bytes to copy to the control_code_page.
+ */
+
+.globl relocate_new_kernel_size
+relocate_new_kernel_size:
+	.quad .Lrelocate_new_kernel_end - relocate_new_kernel
+
+.org	KEXEC_CONTROL_PAGE_SIZE
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 6925f5b..04626b9 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -39,6 +39,7 @@
 #define KEXEC_ARCH_SH      (42 << 16)
 #define KEXEC_ARCH_MIPS_LE (10 << 16)
 #define KEXEC_ARCH_MIPS    ( 8 << 16)
+#define KEXEC_ARCH_ARM64   (183 << 16)
 
 /* The artificial cap on the number of segments passed to kexec_load. */
 #define KEXEC_SEGMENT_MAX 16
-- 
1.9.1



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 8/8] arm64/kexec: Add pr_devel output

[Geoff Levand]

To aid in debugging kexec problems or when adding new functionality to kexec add
a new routine kexec_image_info() and several inline pr_devel statements.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/kernel/machine_kexec.c | 56 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 95bc8d9..1306d33 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -37,6 +37,39 @@ static bool kexec_is_dtb(const void *dtb)
 }
 
 /**
+ * kexec_image_info - For debugging output.
+ */
+
+#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
+static void _kexec_image_info(const char *func, int line,
+	const struct kimage *image)
+{
+	unsigned long i;
+
+#if !defined(DEBUG)
+	return;
+#endif
+	pr_devel("%s:%d:\n", func, line);
+	pr_devel("  kexec image info:\n");
+	pr_devel("    type:        %d\n", image->type);
+	pr_devel("    start:       %lx\n", image->start);
+	pr_devel("    head:        %lx\n", image->head);
+	pr_devel("    nr_segments: %lu\n", image->nr_segments);
+
+	for (i = 0; i < image->nr_segments; i++) {
+		pr_devel("      segment[%lu]: %016lx - %016lx, "
+			"%lx bytes, %lu pages%s\n",
+			i,
+			image->segment[i].mem,
+			image->segment[i].mem + image->segment[i].memsz,
+			image->segment[i].memsz,
+			image->segment[i].memsz /  PAGE_SIZE,
+			(kexec_is_dtb(image->segment[i].buf) ?
+				", dtb segment" : ""));
+	}
+}
+
+/**
  * kexec_find_dtb_seg - Helper routine to find the dtb segment.
  */
 
@@ -74,6 +107,8 @@ int machine_kexec_prepare(struct kimage *image)
 	arm64_kexec_dtb_addr = dtb_seg ? dtb_seg->mem : 0;
 	arm64_kexec_kimage_start = image->start;
 
+	kexec_image_info(image);
+
 	return 0;
 }
 
@@ -130,6 +165,27 @@ void machine_kexec(struct kimage *image)
 	reboot_code_buffer_phys = page_to_phys(image->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
 
+	kexec_image_info(image);
+
+	pr_devel("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
+		image->control_code_page);
+	pr_devel("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
+		&reboot_code_buffer_phys);
+	pr_devel("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
+		reboot_code_buffer);
+	pr_devel("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
+		relocate_new_kernel);
+	pr_devel("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
+		__func__, __LINE__, relocate_new_kernel_size,
+		relocate_new_kernel_size);
+
+	pr_devel("%s:%d: kexec_dtb_addr:           %lx\n", __func__, __LINE__,
+		arm64_kexec_dtb_addr);
+	pr_devel("%s:%d: kexec_kimage_head:        %lx\n", __func__, __LINE__,
+		arm64_kexec_kimage_head);
+	pr_devel("%s:%d: kexec_kimage_start:       %lx\n", __func__, __LINE__,
+		arm64_kexec_kimage_start);
+
 	/*
 	 * Copy relocate_new_kernel to the reboot_code_buffer for use
 	 * after the kernel is shut down.
-- 
1.9.1

[PATCH 8/8] arm64/kexec: Add pr_devel output

[Geoff Levand]

To aid in debugging kexec problems or when adding new functionality to kexec add
a new routine kexec_image_info() and several inline pr_devel statements.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/kernel/machine_kexec.c | 56 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 95bc8d9..1306d33 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -37,6 +37,39 @@ static bool kexec_is_dtb(const void *dtb)
 }
 
 /**
+ * kexec_image_info - For debugging output.
+ */
+
+#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
+static void _kexec_image_info(const char *func, int line,
+	const struct kimage *image)
+{
+	unsigned long i;
+
+#if !defined(DEBUG)
+	return;
+#endif
+	pr_devel("%s:%d:\n", func, line);
+	pr_devel("  kexec image info:\n");
+	pr_devel("    type:        %d\n", image->type);
+	pr_devel("    start:       %lx\n", image->start);
+	pr_devel("    head:        %lx\n", image->head);
+	pr_devel("    nr_segments: %lu\n", image->nr_segments);
+
+	for (i = 0; i < image->nr_segments; i++) {
+		pr_devel("      segment[%lu]: %016lx - %016lx, "
+			"%lx bytes, %lu pages%s\n",
+			i,
+			image->segment[i].mem,
+			image->segment[i].mem + image->segment[i].memsz,
+			image->segment[i].memsz,
+			image->segment[i].memsz /  PAGE_SIZE,
+			(kexec_is_dtb(image->segment[i].buf) ?
+				", dtb segment" : ""));
+	}
+}
+
+/**
  * kexec_find_dtb_seg - Helper routine to find the dtb segment.
  */
 
@@ -74,6 +107,8 @@ int machine_kexec_prepare(struct kimage *image)
 	arm64_kexec_dtb_addr = dtb_seg ? dtb_seg->mem : 0;
 	arm64_kexec_kimage_start = image->start;
 
+	kexec_image_info(image);
+
 	return 0;
 }
 
@@ -130,6 +165,27 @@ void machine_kexec(struct kimage *image)
 	reboot_code_buffer_phys = page_to_phys(image->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
 
+	kexec_image_info(image);
+
+	pr_devel("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
+		image->control_code_page);
+	pr_devel("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
+		&reboot_code_buffer_phys);
+	pr_devel("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
+		reboot_code_buffer);
+	pr_devel("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
+		relocate_new_kernel);
+	pr_devel("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
+		__func__, __LINE__, relocate_new_kernel_size,
+		relocate_new_kernel_size);
+
+	pr_devel("%s:%d: kexec_dtb_addr:           %lx\n", __func__, __LINE__,
+		arm64_kexec_dtb_addr);
+	pr_devel("%s:%d: kexec_kimage_head:        %lx\n", __func__, __LINE__,
+		arm64_kexec_kimage_head);
+	pr_devel("%s:%d: kexec_kimage_start:       %lx\n", __func__, __LINE__,
+		arm64_kexec_kimage_start);
+
 	/*
 	 * Copy relocate_new_kernel to the reboot_code_buffer for use
 	 * after the kernel is shut down.
-- 
1.9.1


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Catalin,

On Tue, 2015-01-27 at 17:57 +0000, Catalin Marinas wrote:
> On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> >  ENTRY(cpu_reset)
> > -	mrs	x1, sctlr_el1
> > -	bic	x1, x1, #1
> > -	msr	sctlr_el1, x1			// disable the MMU
> > +	mrs	x2, sctlr_el1
> > +	bic	x2, x2, #1
> > +	msr	sctlr_el1, x2			// disable the MMU
> >  	isb
> > -	ret	x0
> > +
> > +	cbz	x0, 1f				// el2_switch?
> > +	mov	x0, x1
> > +	mov	x1, xzr
> > +	mov	x2, xzr
> > +	mov	x3, xzr
> > +	hvc	#HVC_CALL_FUNC			// no return
> 
> If that's the only user of HVC_CALL_FUNC, why do we bother with
> arguments, calling convention?

It was intended that HVC_CALL_FUNC be a mechanism to call a generic
function in hyp mode.  cpu_reset() is the only user of it now.

As Mark explained in another post, the use of x18 by the hyp stub
is to avoid the complication of setting up a stack for EL2.  We
thought this solution was acceptable since there are relatively
few HVC_CALL_FUNC calls and we could assure they would do the
right thing.

-Geoff 

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Catalin,

On Tue, 2015-01-27 at 17:57 +0000, Catalin Marinas wrote:
> On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> >  ENTRY(cpu_reset)
> > -	mrs	x1, sctlr_el1
> > -	bic	x1, x1, #1
> > -	msr	sctlr_el1, x1			// disable the MMU
> > +	mrs	x2, sctlr_el1
> > +	bic	x2, x2, #1
> > +	msr	sctlr_el1, x2			// disable the MMU
> >  	isb
> > -	ret	x0
> > +
> > +	cbz	x0, 1f				// el2_switch?
> > +	mov	x0, x1
> > +	mov	x1, xzr
> > +	mov	x2, xzr
> > +	mov	x3, xzr
> > +	hvc	#HVC_CALL_FUNC			// no return
> 
> If that's the only user of HVC_CALL_FUNC, why do we bother with
> arguments, calling convention?

It was intended that HVC_CALL_FUNC be a mechanism to call a generic
function in hyp mode.  cpu_reset() is the only user of it now.

As Mark explained in another post, the use of x18 by the hyp stub
is to avoid the complication of setting up a stack for EL2.  We
thought this solution was acceptable since there are relatively
few HVC_CALL_FUNC calls and we could assure they would do the
right thing.

-Geoff 





_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Mark,

On Tue, 2015-01-27 at 16:46 +0000, Mark Rutland wrote:
> On Mon, Jan 26, 2015 at 09:48:48PM +0000, Geoff Levand wrote:
> > This conditional is just if KVM, do things the old way (don't try to
> > switch exception levels).  It is to handle the system shutdown case.
> 
> Having grepped treewide for soft_restart, other than kexec there are no
> users for arm64. So surely kexec is the only case to cater for at the
> moment?

Yes, I think you're right, and so it seems we can drop this patch and
just have the 'Add checks for KVM' patch.

> > Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
> > KVM' assures kexec cannot happen when KVM is configured.
> 
> It would be better to just move this earlier (or event better, implement
> kvm teardown).

Yes, I hope we don't really need to have any KVM work-arounds.

-Geoff

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Mark,

On Tue, 2015-01-27 at 16:46 +0000, Mark Rutland wrote:
> On Mon, Jan 26, 2015 at 09:48:48PM +0000, Geoff Levand wrote:
> > This conditional is just if KVM, do things the old way (don't try to
> > switch exception levels).  It is to handle the system shutdown case.
> 
> Having grepped treewide for soft_restart, other than kexec there are no
> users for arm64. So surely kexec is the only case to cater for at the
> moment?

Yes, I think you're right, and so it seems we can drop this patch and
just have the 'Add checks for KVM' patch.

> > Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
> > KVM' assures kexec cannot happen when KVM is configured.
> 
> It would be better to just move this earlier (or event better, implement
> kvm teardown).

Yes, I hope we don't really need to have any KVM work-arounds.

-Geoff




_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Catalin Marinas]

On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
>  ENTRY(cpu_reset)
> -	mrs	x1, sctlr_el1
> -	bic	x1, x1, #1
> -	msr	sctlr_el1, x1			// disable the MMU
> +	mrs	x2, sctlr_el1
> +	bic	x2, x2, #1
> +	msr	sctlr_el1, x2			// disable the MMU
>  	isb
> -	ret	x0
> +
> +	cbz	x0, 1f				// el2_switch?
> +	mov	x0, x1
> +	mov	x1, xzr
> +	mov	x2, xzr
> +	mov	x3, xzr
> +	hvc	#HVC_CALL_FUNC			// no return

If that's the only user of HVC_CALL_FUNC, why do we bother with
arguments, calling convention?

-- 
Catalin

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Catalin Marinas]

On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
>  ENTRY(cpu_reset)
> -	mrs	x1, sctlr_el1
> -	bic	x1, x1, #1
> -	msr	sctlr_el1, x1			// disable the MMU
> +	mrs	x2, sctlr_el1
> +	bic	x2, x2, #1
> +	msr	sctlr_el1, x2			// disable the MMU
>  	isb
> -	ret	x0
> +
> +	cbz	x0, 1f				// el2_switch?
> +	mov	x0, x1
> +	mov	x1, xzr
> +	mov	x2, xzr
> +	mov	x3, xzr
> +	hvc	#HVC_CALL_FUNC			// no return

If that's the only user of HVC_CALL_FUNC, why do we bother with
arguments, calling convention?

-- 
Catalin

_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Mark Rutland]

On Mon, Jan 26, 2015 at 09:48:48PM +0000, Geoff Levand wrote:
> Hi Mark,
> 
> On Mon, 2015-01-26 at 19:02 +0000, Mark Rutland wrote:
> > On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> > > When a CPU is reset it needs to be put into the exception level it had when it
> > > entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> > > signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> > > not set the soft reset address will be entered at EL1.
> > > 
> > > Update cpu_soft_restart() and soft_restart() to pass the return of
> > > is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> > > comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> > > change.
> > > 
> > > Signed-off-by: Geoff Levand <geoff@infradead.org>
> > > ---
> > >  arch/arm64/include/asm/proc-fns.h |  4 ++--
> > >  arch/arm64/kernel/process.c       | 10 ++++++++-
> > >  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
> > >  3 files changed, 46 insertions(+), 15 deletions(-)
> > > 
> > > diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> > > index 9a8fd84..339394d 100644
> > > --- a/arch/arm64/include/asm/proc-fns.h
> > > +++ b/arch/arm64/include/asm/proc-fns.h
> > > @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
> > >  extern void cpu_do_idle(void);
> > >  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
> > >  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> > > -void cpu_soft_restart(phys_addr_t cpu_reset,
> > > -		unsigned long addr) __attribute__((noreturn));
> > > +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> > > +		      unsigned long addr) __attribute__((noreturn));
> > >  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
> > >  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
> > >  
> > > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > > index fde9923..371bbf1 100644
> > > --- a/arch/arm64/kernel/process.c
> > > +++ b/arch/arm64/kernel/process.c
> > > @@ -50,6 +50,7 @@
> > >  #include <asm/mmu_context.h>
> > >  #include <asm/processor.h>
> > >  #include <asm/stacktrace.h>
> > > +#include <asm/virt.h>
> > >  
> > >  #ifdef CONFIG_CC_STACKPROTECTOR
> > >  #include <linux/stackprotector.h>
> > > @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
> > >  void soft_restart(unsigned long addr)
> > >  {
> > >  	setup_mm_for_reboot();
> > > -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> > > +
> > > +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> > > +	if (IS_ENABLED(CONFIG_KVM))
> > > +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
> > 
> > If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
> > (with MMU and caches on) at this point?
> > 
> > If that's the case then we cannot possibly try to call kexec(), because
> > we cannot touch the memory used by the page tables for those EL2
> > mappings. Things will explode if we do.
> 
> This conditional is just if KVM, do things the old way (don't try to
> switch exception levels).  It is to handle the system shutdown case.

Having grepped treewide for soft_restart, other than kexec there are no
users for arm64. So surely kexec is the only case to cater for at the
moment?

> Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
> KVM' assures kexec cannot happen when KVM is configured.

It would be better to just move this earlier (or event better, implement
kvm teardown).

Mark.

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Mark Rutland]

On Mon, Jan 26, 2015 at 09:48:48PM +0000, Geoff Levand wrote:
> Hi Mark,
> 
> On Mon, 2015-01-26 at 19:02 +0000, Mark Rutland wrote:
> > On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> > > When a CPU is reset it needs to be put into the exception level it had when it
> > > entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> > > signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> > > not set the soft reset address will be entered at EL1.
> > > 
> > > Update cpu_soft_restart() and soft_restart() to pass the return of
> > > is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> > > comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> > > change.
> > > 
> > > Signed-off-by: Geoff Levand <geoff@infradead.org>
> > > ---
> > >  arch/arm64/include/asm/proc-fns.h |  4 ++--
> > >  arch/arm64/kernel/process.c       | 10 ++++++++-
> > >  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
> > >  3 files changed, 46 insertions(+), 15 deletions(-)
> > > 
> > > diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> > > index 9a8fd84..339394d 100644
> > > --- a/arch/arm64/include/asm/proc-fns.h
> > > +++ b/arch/arm64/include/asm/proc-fns.h
> > > @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
> > >  extern void cpu_do_idle(void);
> > >  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
> > >  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> > > -void cpu_soft_restart(phys_addr_t cpu_reset,
> > > -		unsigned long addr) __attribute__((noreturn));
> > > +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> > > +		      unsigned long addr) __attribute__((noreturn));
> > >  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
> > >  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
> > >  
> > > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > > index fde9923..371bbf1 100644
> > > --- a/arch/arm64/kernel/process.c
> > > +++ b/arch/arm64/kernel/process.c
> > > @@ -50,6 +50,7 @@
> > >  #include <asm/mmu_context.h>
> > >  #include <asm/processor.h>
> > >  #include <asm/stacktrace.h>
> > > +#include <asm/virt.h>
> > >  
> > >  #ifdef CONFIG_CC_STACKPROTECTOR
> > >  #include <linux/stackprotector.h>
> > > @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
> > >  void soft_restart(unsigned long addr)
> > >  {
> > >  	setup_mm_for_reboot();
> > > -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> > > +
> > > +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> > > +	if (IS_ENABLED(CONFIG_KVM))
> > > +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
> > 
> > If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
> > (with MMU and caches on) at this point?
> > 
> > If that's the case then we cannot possibly try to call kexec(), because
> > we cannot touch the memory used by the page tables for those EL2
> > mappings. Things will explode if we do.
> 
> This conditional is just if KVM, do things the old way (don't try to
> switch exception levels).  It is to handle the system shutdown case.

Having grepped treewide for soft_restart, other than kexec there are no
users for arm64. So surely kexec is the only case to cater for at the
moment?

> Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
> KVM' assures kexec cannot happen when KVM is configured.

It would be better to just move this earlier (or event better, implement
kvm teardown).

Mark.

_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Mark,

On Mon, 2015-01-26 at 19:02 +0000, Mark Rutland wrote:
> On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> > When a CPU is reset it needs to be put into the exception level it had when it
> > entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> > signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> > not set the soft reset address will be entered at EL1.
> > 
> > Update cpu_soft_restart() and soft_restart() to pass the return of
> > is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> > comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> > change.
> > 
> > Signed-off-by: Geoff Levand <geoff@infradead.org>
> > ---
> >  arch/arm64/include/asm/proc-fns.h |  4 ++--
> >  arch/arm64/kernel/process.c       | 10 ++++++++-
> >  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
> >  3 files changed, 46 insertions(+), 15 deletions(-)
> > 
> > diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> > index 9a8fd84..339394d 100644
> > --- a/arch/arm64/include/asm/proc-fns.h
> > +++ b/arch/arm64/include/asm/proc-fns.h
> > @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
> >  extern void cpu_do_idle(void);
> >  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
> >  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> > -void cpu_soft_restart(phys_addr_t cpu_reset,
> > -		unsigned long addr) __attribute__((noreturn));
> > +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> > +		      unsigned long addr) __attribute__((noreturn));
> >  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
> >  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
> >  
> > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > index fde9923..371bbf1 100644
> > --- a/arch/arm64/kernel/process.c
> > +++ b/arch/arm64/kernel/process.c
> > @@ -50,6 +50,7 @@
> >  #include <asm/mmu_context.h>
> >  #include <asm/processor.h>
> >  #include <asm/stacktrace.h>
> > +#include <asm/virt.h>
> >  
> >  #ifdef CONFIG_CC_STACKPROTECTOR
> >  #include <linux/stackprotector.h>
> > @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
> >  void soft_restart(unsigned long addr)
> >  {
> >  	setup_mm_for_reboot();
> > -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> > +
> > +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> > +	if (IS_ENABLED(CONFIG_KVM))
> > +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
> 
> If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
> (with MMU and caches on) at this point?
> 
> If that's the case then we cannot possibly try to call kexec(), because
> we cannot touch the memory used by the page tables for those EL2
> mappings. Things will explode if we do.

This conditional is just if KVM, do things the old way (don't try to
switch exception levels).  It is to handle the system shutdown case.

Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
KVM' assures kexec cannot happen when KVM is configured.

-Geoff

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

Hi Mark,

On Mon, 2015-01-26 at 19:02 +0000, Mark Rutland wrote:
> On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> > When a CPU is reset it needs to be put into the exception level it had when it
> > entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> > signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> > not set the soft reset address will be entered at EL1.
> > 
> > Update cpu_soft_restart() and soft_restart() to pass the return of
> > is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> > comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> > change.
> > 
> > Signed-off-by: Geoff Levand <geoff@infradead.org>
> > ---
> >  arch/arm64/include/asm/proc-fns.h |  4 ++--
> >  arch/arm64/kernel/process.c       | 10 ++++++++-
> >  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
> >  3 files changed, 46 insertions(+), 15 deletions(-)
> > 
> > diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> > index 9a8fd84..339394d 100644
> > --- a/arch/arm64/include/asm/proc-fns.h
> > +++ b/arch/arm64/include/asm/proc-fns.h
> > @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
> >  extern void cpu_do_idle(void);
> >  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
> >  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> > -void cpu_soft_restart(phys_addr_t cpu_reset,
> > -		unsigned long addr) __attribute__((noreturn));
> > +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> > +		      unsigned long addr) __attribute__((noreturn));
> >  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
> >  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
> >  
> > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > index fde9923..371bbf1 100644
> > --- a/arch/arm64/kernel/process.c
> > +++ b/arch/arm64/kernel/process.c
> > @@ -50,6 +50,7 @@
> >  #include <asm/mmu_context.h>
> >  #include <asm/processor.h>
> >  #include <asm/stacktrace.h>
> > +#include <asm/virt.h>
> >  
> >  #ifdef CONFIG_CC_STACKPROTECTOR
> >  #include <linux/stackprotector.h>
> > @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
> >  void soft_restart(unsigned long addr)
> >  {
> >  	setup_mm_for_reboot();
> > -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> > +
> > +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> > +	if (IS_ENABLED(CONFIG_KVM))
> > +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
> 
> If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
> (with MMU and caches on) at this point?
> 
> If that's the case then we cannot possibly try to call kexec(), because
> we cannot touch the memory used by the page tables for those EL2
> mappings. Things will explode if we do.

This conditional is just if KVM, do things the old way (don't try to
switch exception levels).  It is to handle the system shutdown case.

Another patch in this series '[PATCH 7/8] arm64/kexec: Add checks for
KVM' assures kexec cannot happen when KVM is configured.

-Geoff




_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Mark Rutland]

On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> When a CPU is reset it needs to be put into the exception level it had when it
> entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> not set the soft reset address will be entered at EL1.
> 
> Update cpu_soft_restart() and soft_restart() to pass the return of
> is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> change.
> 
> Signed-off-by: Geoff Levand <geoff@infradead.org>
> ---
>  arch/arm64/include/asm/proc-fns.h |  4 ++--
>  arch/arm64/kernel/process.c       | 10 ++++++++-
>  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
>  3 files changed, 46 insertions(+), 15 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> index 9a8fd84..339394d 100644
> --- a/arch/arm64/include/asm/proc-fns.h
> +++ b/arch/arm64/include/asm/proc-fns.h
> @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
>  extern void cpu_do_idle(void);
>  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
>  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> -void cpu_soft_restart(phys_addr_t cpu_reset,
> -		unsigned long addr) __attribute__((noreturn));
> +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> +		      unsigned long addr) __attribute__((noreturn));
>  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
>  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
>  
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index fde9923..371bbf1 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -50,6 +50,7 @@
>  #include <asm/mmu_context.h>
>  #include <asm/processor.h>
>  #include <asm/stacktrace.h>
> +#include <asm/virt.h>
>  
>  #ifdef CONFIG_CC_STACKPROTECTOR
>  #include <linux/stackprotector.h>
> @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
>  void soft_restart(unsigned long addr)
>  {
>  	setup_mm_for_reboot();
> -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> +
> +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> +	if (IS_ENABLED(CONFIG_KVM))
> +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);

If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
(with MMU and caches on) at this point?

If that's the case then we cannot possibly try to call kexec(), because
we cannot touch the memory used by the page tables for those EL2
mappings. Things will explode if we do.

Mark.

Re: [PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Mark Rutland]

On Sat, Jan 17, 2015 at 12:23:34AM +0000, Geoff Levand wrote:
> When a CPU is reset it needs to be put into the exception level it had when it
> entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
> signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
> not set the soft reset address will be entered at EL1.
> 
> Update cpu_soft_restart() and soft_restart() to pass the return of
> is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
> comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
> change.
> 
> Signed-off-by: Geoff Levand <geoff@infradead.org>
> ---
>  arch/arm64/include/asm/proc-fns.h |  4 ++--
>  arch/arm64/kernel/process.c       | 10 ++++++++-
>  arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
>  3 files changed, 46 insertions(+), 15 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
> index 9a8fd84..339394d 100644
> --- a/arch/arm64/include/asm/proc-fns.h
> +++ b/arch/arm64/include/asm/proc-fns.h
> @@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
>  extern void cpu_do_idle(void);
>  extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
>  extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
> -void cpu_soft_restart(phys_addr_t cpu_reset,
> -		unsigned long addr) __attribute__((noreturn));
> +void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
> +		      unsigned long addr) __attribute__((noreturn));
>  extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
>  extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
>  
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index fde9923..371bbf1 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -50,6 +50,7 @@
>  #include <asm/mmu_context.h>
>  #include <asm/processor.h>
>  #include <asm/stacktrace.h>
> +#include <asm/virt.h>
>  
>  #ifdef CONFIG_CC_STACKPROTECTOR
>  #include <linux/stackprotector.h>
> @@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
>  void soft_restart(unsigned long addr)
>  {
>  	setup_mm_for_reboot();
> -	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
> +
> +	/* TODO: Remove this conditional when KVM can support CPU restart. */
> +	if (IS_ENABLED(CONFIG_KVM))
> +		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);

If we haven't torn down KVM, doesn't that mean that KVM is active at EL2
(with MMU and caches on) at this point?

If that's the case then we cannot possibly try to call kexec(), because
we cannot touch the memory used by the page tables for those EL2
mappings. Things will explode if we do.

Mark.

_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

When a CPU is reset it needs to be put into the exception level it had when it
entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
not set the soft reset address will be entered at EL1.

Update cpu_soft_restart() and soft_restart() to pass the return of
is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
change.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-fns.h |  4 ++--
 arch/arm64/kernel/process.c       | 10 ++++++++-
 arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
 3 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..339394d 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
-		unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
+		      unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fde9923..371bbf1 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -50,6 +50,7 @@
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
+#include <asm/virt.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
 void soft_restart(unsigned long addr)
 {
 	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
+
+	/* TODO: Remove this conditional when KVM can support CPU restart. */
+	if (IS_ENABLED(CONFIG_KVM))
+		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
+	else
+		cpu_soft_restart(virt_to_phys(cpu_reset),
+				 is_hyp_mode_available(), addr);
+
 	/* Should never get here */
 	BUG();
 }
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c507e25..b767032 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -26,6 +26,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/proc-macros.S>
+#include <asm/virt.h>
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
@@ -58,27 +59,48 @@ ENTRY(cpu_cache_off)
 ENDPROC(cpu_cache_off)
 
 /*
- *	cpu_reset(loc)
+ * cpu_reset(el2_switch, loc) - Helper for cpu_soft_restart.
  *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @addr: Location to jump to for soft reset.
  *
- *	- loc   - location to jump to for soft reset
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
  */
+
 	.align	5
+
 ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
+	mrs	x2, sctlr_el1
+	bic	x2, x2, #1
+	msr	sctlr_el1, x2			// disable the MMU
 	isb
-	ret	x0
+
+	cbz	x0, 1f				// el2_switch?
+	mov	x0, x1
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	hvc	#HVC_CALL_FUNC			// no return
+
+1:	ret	x1
 ENDPROC(cpu_reset)
 
+/*
+ * cpu_soft_restart(cpu_reset, el2_switch, addr) - Perform a cpu soft reset.
+ *
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed, passed to cpu_reset.
+ * @addr: Location to jump to for soft reset, passed to cpu_reset.
+ *
+ */
+
 ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
+	mov	x19, x0				// cpu_reset
+	mov	x20, x1				// el2_switch
+	mov	x21, x2				// addr
 
 	/* Turn D-cache off */
 	bl	cpu_cache_off
@@ -87,6 +109,7 @@ ENTRY(cpu_soft_restart)
 	bl	flush_cache_all
 
 	mov	x0, x20
+	mov	x1, x21
 	ret	x19
 ENDPROC(cpu_soft_restart)
 
-- 
2.1.0

[PATCH 4/8] arm64: Add EL2 switch to soft_restart

[Geoff Levand]

When a CPU is reset it needs to be put into the exception level it had when it
entered the kernel.  Update cpu_reset() to accept an argument el2_switch which
signals cpu_reset() to enter the soft reset address at EL2.  If el2_switch is
not set the soft reset address will be entered at EL1.

Update cpu_soft_restart() and soft_restart() to pass the return of
is_hyp_mode_available() as the el2_switch value to cpu_reset().  Also update the
comments of cpu_reset(), cpu_soft_restart() and soft_restart() to reflect this
change.

Signed-off-by: Geoff Levand <geoff@infradead.org>
---
 arch/arm64/include/asm/proc-fns.h |  4 ++--
 arch/arm64/kernel/process.c       | 10 ++++++++-
 arch/arm64/mm/proc.S              | 47 +++++++++++++++++++++++++++++----------
 3 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..339394d 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -32,8 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
-		unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset, unsigned long el2_switch,
+		      unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fde9923..371bbf1 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -50,6 +50,7 @@
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
+#include <asm/virt.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -60,7 +61,14 @@ EXPORT_SYMBOL(__stack_chk_guard);
 void soft_restart(unsigned long addr)
 {
 	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
+
+	/* TODO: Remove this conditional when KVM can support CPU restart. */
+	if (IS_ENABLED(CONFIG_KVM))
+		cpu_soft_restart(virt_to_phys(cpu_reset), 0, addr);
+	else
+		cpu_soft_restart(virt_to_phys(cpu_reset),
+				 is_hyp_mode_available(), addr);
+
 	/* Should never get here */
 	BUG();
 }
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c507e25..b767032 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -26,6 +26,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/proc-macros.S>
+#include <asm/virt.h>
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
@@ -58,27 +59,48 @@ ENTRY(cpu_cache_off)
 ENDPROC(cpu_cache_off)
 
 /*
- *	cpu_reset(loc)
+ * cpu_reset(el2_switch, loc) - Helper for cpu_soft_restart.
  *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @addr: Location to jump to for soft reset.
  *
- *	- loc   - location to jump to for soft reset
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
  */
+
 	.align	5
+
 ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
+	mrs	x2, sctlr_el1
+	bic	x2, x2, #1
+	msr	sctlr_el1, x2			// disable the MMU
 	isb
-	ret	x0
+
+	cbz	x0, 1f				// el2_switch?
+	mov	x0, x1
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	hvc	#HVC_CALL_FUNC			// no return
+
+1:	ret	x1
 ENDPROC(cpu_reset)
 
+/*
+ * cpu_soft_restart(cpu_reset, el2_switch, addr) - Perform a cpu soft reset.
+ *
+ * @cpu_reset: Physical address of the cpu_reset routine.
+ * @el2_switch: Flag to indicate a swich to EL2 is needed, passed to cpu_reset.
+ * @addr: Location to jump to for soft reset, passed to cpu_reset.
+ *
+ */
+
 ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
+	mov	x19, x0				// cpu_reset
+	mov	x20, x1				// el2_switch
+	mov	x21, x2				// addr
 
 	/* Turn D-cache off */
 	bl	cpu_cache_off
@@ -87,6 +109,7 @@ ENTRY(cpu_soft_restart)
 	bl	flush_cache_all
 
 	mov	x0, x20
+	mov	x1, x21
 	ret	x19
 ENDPROC(cpu_soft_restart)
 
-- 
2.1.0



_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec