* [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
@ 2014-06-20 12:59 ` Marc Zyngier
2014-07-09 9:27 ` Christoffer Dall
2014-06-20 13:00 ` [PATCH v3 2/9] arm64: move DBG_MDSCR_* to asm/debug-monitors.h Marc Zyngier
` (7 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 12:59 UTC (permalink / raw)
To: linux-arm-kernel
pm_fake doesn't quite describe what the handler does (ignoring writes
and returning 0 for reads).
As we're about to use it (a lot) in a different context, rename it
with a (admitedly cryptic) name that make sense for all users.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/kvm/sys_regs.c | 83 ++++++++++++++++++++++++-----------------------
1 file changed, 43 insertions(+), 40 deletions(-)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c59a1bd..4abd84e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -163,18 +163,9 @@ static bool access_sctlr(struct kvm_vcpu *vcpu,
return true;
}
-/*
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters. Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- */
-static bool pm_fake(struct kvm_vcpu *vcpu,
- const struct sys_reg_params *p,
- const struct sys_reg_desc *r)
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
{
if (p->is_write)
return ignore_write(vcpu, p);
@@ -201,6 +192,17 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
/*
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * We could trap ID_DFR0 and tell the guest we don't support performance
+ * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
+ * NAKed, so it will read the PMCR anyway.
+ *
+ * Therefore we tell the guest we have 0 counters. Unfortunately, we
+ * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
+ * all PM registers, which doesn't crash the guest kernel at least.
+ *
+ * Same goes for the whole debug infrastructure, which probably breaks
+ * some guest functionnality. This should be fixed.
*/
static const struct sys_reg_desc sys_reg_descs[] = {
/* DC ISW */
@@ -260,10 +262,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
/* PMINTENSET_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
- pm_fake },
+ trap_raz_wi },
/* PMINTENCLR_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
- pm_fake },
+ trap_raz_wi },
/* MAIR_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
@@ -292,43 +294,43 @@ static const struct sys_reg_desc sys_reg_descs[] = {
/* PMCR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
- pm_fake },
+ trap_raz_wi },
/* PMCNTENSET_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
- pm_fake },
+ trap_raz_wi },
/* PMCNTENCLR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
- pm_fake },
+ trap_raz_wi },
/* PMOVSCLR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
- pm_fake },
+ trap_raz_wi },
/* PMSWINC_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
- pm_fake },
+ trap_raz_wi },
/* PMSELR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
- pm_fake },
+ trap_raz_wi },
/* PMCEID0_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
- pm_fake },
+ trap_raz_wi },
/* PMCEID1_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
- pm_fake },
+ trap_raz_wi },
/* PMCCNTR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
- pm_fake },
+ trap_raz_wi },
/* PMXEVTYPER_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
- pm_fake },
+ trap_raz_wi },
/* PMXEVCNTR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
- pm_fake },
+ trap_raz_wi },
/* PMUSERENR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
- pm_fake },
+ trap_raz_wi },
/* PMOVSSET_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
- pm_fake },
+ trap_raz_wi },
/* TPIDR_EL0 */
{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
@@ -374,19 +376,20 @@ static const struct sys_reg_desc cp15_regs[] = {
{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
- { Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 3), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 5), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 6), pm_fake },
- { Op1( 0), CRn( 9), CRm(12), Op2( 7), pm_fake },
- { Op1( 0), CRn( 9), CRm(13), Op2( 0), pm_fake },
- { Op1( 0), CRn( 9), CRm(13), Op2( 1), pm_fake },
- { Op1( 0), CRn( 9), CRm(13), Op2( 2), pm_fake },
- { Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake },
- { Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake },
- { Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake },
+ /* PMU */
+ { Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi
2014-06-20 12:59 ` [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi Marc Zyngier
@ 2014-07-09 9:27 ` Christoffer Dall
2014-07-09 9:36 ` Marc Zyngier
0 siblings, 1 reply; 19+ messages in thread
From: Christoffer Dall @ 2014-07-09 9:27 UTC (permalink / raw)
To: linux-arm-kernel
On Fri, Jun 20, 2014 at 01:59:59PM +0100, Marc Zyngier wrote:
> pm_fake doesn't quite describe what the handler does (ignoring writes
> and returning 0 for reads).
>
> As we're about to use it (a lot) in a different context, rename it
> with a (admitedly cryptic) name that make sense for all users.
>
> Reviewed-by: Anup Patel <anup.patel@linaro.org>
> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
didn't I already review this? Did something change, it doesn't look
like it from the changelog....
/me confused.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi
2014-07-09 9:27 ` Christoffer Dall
@ 2014-07-09 9:36 ` Marc Zyngier
0 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-07-09 9:36 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jul 09 2014 at 10:27:12 am BST, Christoffer Dall <christoffer.dall@linaro.org> wrote:
> On Fri, Jun 20, 2014 at 01:59:59PM +0100, Marc Zyngier wrote:
>> pm_fake doesn't quite describe what the handler does (ignoring writes
>> and returning 0 for reads).
>>
>> As we're about to use it (a lot) in a different context, rename it
>> with a (admitedly cryptic) name that make sense for all users.
>>
>> Reviewed-by: Anup Patel <anup.patel@linaro.org>
>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
>
> didn't I already review this? Did something change, it doesn't look
> like it from the changelog....
>
> /me confused.
Nothing changed, just me forgetting to add your Reviewed-by tag.
Sorry about that.
M.
--
Without deviation from the norm, progress is not possible.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 2/9] arm64: move DBG_MDSCR_* to asm/debug-monitors.h
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
2014-06-20 12:59 ` [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers Marc Zyngier
` (6 subsequent siblings)
8 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
In order to be able to use the DBG_MDSCR_* macros from the KVM code,
move the relevant definitions to the obvious include file.
Also move the debug_el enum to a portion of the file that is guarded
by #ifndef __ASSEMBLY__ in order to use that file from assembly code.
Acked-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/include/asm/debug-monitors.h | 19 ++++++++++++++-----
arch/arm64/kernel/debug-monitors.c | 9 ---------
2 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 6e9b5b3..7fb3437 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -18,6 +18,15 @@
#ifdef __KERNEL__
+/* Low-level stepping controls. */
+#define DBG_MDSCR_SS (1 << 0)
+#define DBG_SPSR_SS (1 << 21)
+
+/* MDSCR_EL1 enabling bits */
+#define DBG_MDSCR_KDE (1 << 13)
+#define DBG_MDSCR_MDE (1 << 15)
+#define DBG_MDSCR_MASK ~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
+
#define DBG_ESR_EVT(x) (((x) >> 27) & 0x7)
/* AArch64 */
@@ -73,11 +82,6 @@
#define CACHE_FLUSH_IS_SAFE 1
-enum debug_el {
- DBG_ACTIVE_EL0 = 0,
- DBG_ACTIVE_EL1,
-};
-
/* AArch32 */
#define DBG_ESR_EVT_BKPT 0x4
#define DBG_ESR_EVT_VECC 0x5
@@ -115,6 +119,11 @@ void unregister_break_hook(struct break_hook *hook);
u8 debug_monitors_arch(void);
+enum debug_el {
+ DBG_ACTIVE_EL0 = 0,
+ DBG_ACTIVE_EL1,
+};
+
void enable_debug_monitors(enum debug_el el);
void disable_debug_monitors(enum debug_el el);
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index a7fb874..e022f87 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -30,15 +30,6 @@
#include <asm/cputype.h>
#include <asm/system_misc.h>
-/* Low-level stepping controls. */
-#define DBG_MDSCR_SS (1 << 0)
-#define DBG_SPSR_SS (1 << 21)
-
-/* MDSCR_EL1 enabling bits */
-#define DBG_MDSCR_KDE (1 << 13)
-#define DBG_MDSCR_MDE (1 << 15)
-#define DBG_MDSCR_MASK ~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
-
/* Determine debug architecture. */
u8 debug_monitors_arch(void)
{
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
2014-06-20 12:59 ` [PATCH v3 1/9] arm64: KVM: rename pm_fake handler to trap_raz_wi Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 2/9] arm64: move DBG_MDSCR_* to asm/debug-monitors.h Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-07-09 9:38 ` Christoffer Dall
2014-06-20 13:00 ` [PATCH v3 4/9] arm64: KVM: common infrastructure for handling AArch32 CP14/CP15 Marc Zyngier
` (5 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
Add handlers for all the AArch64 debug registers that are accessible
from EL0 or EL1. The trapping code keeps track of the state of the
debug registers, allowing for the switch code to implement a lazy
switching strategy.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/include/asm/kvm_asm.h | 28 ++++++--
arch/arm64/include/asm/kvm_host.h | 3 +
arch/arm64/kvm/sys_regs.c | 137 +++++++++++++++++++++++++++++++++++++-
3 files changed, 159 insertions(+), 9 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 9fcd54b..e6b159a 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -43,14 +43,25 @@
#define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */
#define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */
#define PAR_EL1 21 /* Physical Address Register */
+#define MDSCR_EL1 22 /* Monitor Debug System Control Register */
+#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */
+#define DBGBCR15_EL1 38
+#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */
+#define DBGBVR15_EL1 54
+#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */
+#define DBGWCR15_EL1 70
+#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */
+#define DBGWVR15_EL1 86
+#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */
+
/* 32bit specific registers. Keep them at the end of the range */
-#define DACR32_EL2 22 /* Domain Access Control Register */
-#define IFSR32_EL2 23 /* Instruction Fault Status Register */
-#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */
-#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */
-#define TEECR32_EL1 26 /* ThumbEE Configuration Register */
-#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */
-#define NR_SYS_REGS 28
+#define DACR32_EL2 88 /* Domain Access Control Register */
+#define IFSR32_EL2 89 /* Instruction Fault Status Register */
+#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */
+#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */
+#define TEECR32_EL1 92 /* ThumbEE Configuration Register */
+#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */
+#define NR_SYS_REGS 94
/* 32bit mapping */
#define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
@@ -87,6 +98,9 @@
#define ARM_EXCEPTION_IRQ 0
#define ARM_EXCEPTION_TRAP 1
+#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
+#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
+
#ifndef __ASSEMBLY__
struct kvm;
struct kvm_vcpu;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 92242ce..79573c86 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -101,6 +101,9 @@ struct kvm_vcpu_arch {
/* Exception Information */
struct kvm_vcpu_fault_info fault;
+ /* Debug state */
+ u64 debug_flags;
+
/* Pointer to host CPU context */
kvm_cpu_context_t *host_cpu_context;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4abd84e..808e3b2 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -30,6 +30,7 @@
#include <asm/kvm_mmu.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
+#include <asm/debug-monitors.h>
#include <trace/events/kvm.h>
#include "sys_regs.h"
@@ -173,6 +174,60 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
return read_zero(vcpu, p);
}
+static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = (1 << 3);
+ return true;
+ }
+}
+
+static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ u32 val;
+ asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
+ *vcpu_reg(vcpu, p->Rt) = val;
+ return true;
+ }
+}
+
+/*
+ * We want to avoid world-switching all the DBG registers all the
+ * time. For this, we use a DIRTY but, indicating the guest has
+ * modified the debug registers, and only restore the registers once,
+ * disabling traps.
+ *
+ * The best thing to do would be to trap MDSCR_EL1 independently, test
+ * if DBG_MDSCR_KDE or DBG_MDSCR_MDE is getting set, and only set the
+ * DIRTY bit in that case.
+ *
+ * Unfortunately, "old" Linux kernels tend to hit MDSCR_EL1 like a
+ * woodpecker on a tree, and it is better to disable trapping as soon
+ * as possible in this case. Some day, make this a tuneable...
+ */
+static bool trap_debug_regs(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+ vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+ }
+
+ return true;
+}
+
static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 amair;
@@ -189,6 +244,21 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
}
+/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
+#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
+ /* DBGBVRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
+ trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \
+ /* DBGBCRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
+ trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \
+ /* DBGWVRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
+ trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \
+ /* DBGWCRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
+ trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
+
/*
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -201,8 +271,12 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
* must always support PMCCNTR (the cycle counter): we just RAZ/WI for
* all PM registers, which doesn't crash the guest kernel at least.
*
- * Same goes for the whole debug infrastructure, which probably breaks
- * some guest functionnality. This should be fixed.
+ * Debug handling: We do trap most, if not all debug related system
+ * registers. The implementation is good enough to ensure that a guest
+ * can use these with minimal performance degradation. The drawback is
+ * that we don't implement any of the external debug, none of the
+ * OSlock protocol. This should be revisited if we ever encounter a
+ * more demanding guest...
*/
static const struct sys_reg_desc sys_reg_descs[] = {
/* DC ISW */
@@ -215,12 +289,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
access_dcsw },
+ DBG_BCR_BVR_WCR_WVR_EL1(0),
+ DBG_BCR_BVR_WCR_WVR_EL1(1),
+ /* MDCCINT_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+ trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+ /* MDSCR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+ trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+ DBG_BCR_BVR_WCR_WVR_EL1(2),
+ DBG_BCR_BVR_WCR_WVR_EL1(3),
+ DBG_BCR_BVR_WCR_WVR_EL1(4),
+ DBG_BCR_BVR_WCR_WVR_EL1(5),
+ DBG_BCR_BVR_WCR_WVR_EL1(6),
+ DBG_BCR_BVR_WCR_WVR_EL1(7),
+ DBG_BCR_BVR_WCR_WVR_EL1(8),
+ DBG_BCR_BVR_WCR_WVR_EL1(9),
+ DBG_BCR_BVR_WCR_WVR_EL1(10),
+ DBG_BCR_BVR_WCR_WVR_EL1(11),
+ DBG_BCR_BVR_WCR_WVR_EL1(12),
+ DBG_BCR_BVR_WCR_WVR_EL1(13),
+ DBG_BCR_BVR_WCR_WVR_EL1(14),
+ DBG_BCR_BVR_WCR_WVR_EL1(15),
+
+ /* MDRAR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+ trap_raz_wi },
+ /* OSLAR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
+ trap_raz_wi },
+ /* OSLSR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
+ trap_oslsr_el1 },
+ /* OSDLR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
+ trap_raz_wi },
+ /* DBGPRCR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
+ trap_raz_wi },
+ /* DBGCLAIMSET_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
+ trap_raz_wi },
+ /* DBGCLAIMCLR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
+ trap_raz_wi },
+ /* DBGAUTHSTATUS_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
+ trap_dbgauthstatus_el1 },
+
/* TEECR32_EL1 */
{ Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
NULL, reset_val, TEECR32_EL1, 0 },
/* TEEHBR32_EL1 */
{ Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
NULL, reset_val, TEEHBR32_EL1, 0 },
+
+ /* MDCCSR_EL1 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
+ trap_raz_wi },
+ /* DBGDTR_EL0 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
+ trap_raz_wi },
+ /* DBGDTR[TR]X_EL0 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
+ trap_raz_wi },
+
/* DBGVCR32_EL2 */
{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
NULL, reset_val, DBGVCR32_EL2, 0 },
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers
2014-06-20 13:00 ` [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers Marc Zyngier
@ 2014-07-09 9:38 ` Christoffer Dall
2014-07-09 11:09 ` Marc Zyngier
0 siblings, 1 reply; 19+ messages in thread
From: Christoffer Dall @ 2014-07-09 9:38 UTC (permalink / raw)
To: linux-arm-kernel
On Fri, Jun 20, 2014 at 02:00:01PM +0100, Marc Zyngier wrote:
> Add handlers for all the AArch64 debug registers that are accessible
> from EL0 or EL1. The trapping code keeps track of the state of the
> debug registers, allowing for the switch code to implement a lazy
> switching strategy.
>
> Reviewed-by: Anup Patel <anup.patel@linaro.org>
> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> ---
> arch/arm64/include/asm/kvm_asm.h | 28 ++++++--
> arch/arm64/include/asm/kvm_host.h | 3 +
> arch/arm64/kvm/sys_regs.c | 137 +++++++++++++++++++++++++++++++++++++-
> 3 files changed, 159 insertions(+), 9 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 9fcd54b..e6b159a 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -43,14 +43,25 @@
> #define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */
> #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */
> #define PAR_EL1 21 /* Physical Address Register */
> +#define MDSCR_EL1 22 /* Monitor Debug System Control Register */
> +#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */
> +#define DBGBCR15_EL1 38
> +#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */
> +#define DBGBVR15_EL1 54
> +#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */
> +#define DBGWCR15_EL1 70
> +#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */
> +#define DBGWVR15_EL1 86
> +#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */
> +
> /* 32bit specific registers. Keep them at the end of the range */
> -#define DACR32_EL2 22 /* Domain Access Control Register */
> -#define IFSR32_EL2 23 /* Instruction Fault Status Register */
> -#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */
> -#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */
> -#define TEECR32_EL1 26 /* ThumbEE Configuration Register */
> -#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */
> -#define NR_SYS_REGS 28
> +#define DACR32_EL2 88 /* Domain Access Control Register */
> +#define IFSR32_EL2 89 /* Instruction Fault Status Register */
> +#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */
> +#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */
> +#define TEECR32_EL1 92 /* ThumbEE Configuration Register */
> +#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */
> +#define NR_SYS_REGS 94
>
> /* 32bit mapping */
> #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
> @@ -87,6 +98,9 @@
> #define ARM_EXCEPTION_IRQ 0
> #define ARM_EXCEPTION_TRAP 1
>
> +#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
> +#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
> +
> #ifndef __ASSEMBLY__
> struct kvm;
> struct kvm_vcpu;
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 92242ce..79573c86 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -101,6 +101,9 @@ struct kvm_vcpu_arch {
> /* Exception Information */
> struct kvm_vcpu_fault_info fault;
>
> + /* Debug state */
> + u64 debug_flags;
> +
> /* Pointer to host CPU context */
> kvm_cpu_context_t *host_cpu_context;
>
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index 4abd84e..808e3b2 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -30,6 +30,7 @@
> #include <asm/kvm_mmu.h>
> #include <asm/cacheflush.h>
> #include <asm/cputype.h>
> +#include <asm/debug-monitors.h>
> #include <trace/events/kvm.h>
>
> #include "sys_regs.h"
> @@ -173,6 +174,60 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
> return read_zero(vcpu, p);
> }
>
> +static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
> + const struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + if (p->is_write) {
> + return ignore_write(vcpu, p);
> + } else {
> + *vcpu_reg(vcpu, p->Rt) = (1 << 3);
> + return true;
> + }
> +}
> +
> +static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
> + const struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + if (p->is_write) {
> + return ignore_write(vcpu, p);
> + } else {
> + u32 val;
> + asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
> + *vcpu_reg(vcpu, p->Rt) = val;
> + return true;
> + }
> +}
> +
> +/*
> + * We want to avoid world-switching all the DBG registers all the
> + * time. For this, we use a DIRTY but, indicating the guest has
a DIRTY but? (at least there's only one t in there).
> + * modified the debug registers, and only restore the registers once,
> + * disabling traps.
I don't think I understand the "only restore the registers once" bit
here. I know I'm being incredibly stupid, but I forgot since the last
review round how this actually works; when we return from the guest and
the guest has somehow enabled certain DBG functionality, then we set the dirty
flag, which means we should stop trapping and context switch all the
registers on world-switches, but if we see when returning from the guest
that the guest doesn't appear to be using the registers we enable
trapping and stop world-switching, right?
Do we clearly define which state triggers the world-switching and why
that's a good rationale? (sorry, the debug architecture is not my
favorite part of the ARM ARM).
> + *
> + * The best thing to do would be to trap MDSCR_EL1 independently, test
> + * if DBG_MDSCR_KDE or DBG_MDSCR_MDE is getting set, and only set the
> + * DIRTY bit in that case.
> + *
> + * Unfortunately, "old" Linux kernels tend to hit MDSCR_EL1 like a
> + * woodpecker on a tree, and it is better to disable trapping as soon
> + * as possible in this case. Some day, make this a tuneable...
> + */
> +static bool trap_debug_regs(struct kvm_vcpu *vcpu,
> + const struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + if (p->is_write) {
> + vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
> + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
> + } else {
> + *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
> + }
> +
> + return true;
> +}
> +
> static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> {
> u64 amair;
> @@ -189,6 +244,21 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
> }
>
> +/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
> +#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
> + /* DBGBVRn_EL1 */ \
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
> + trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \
> + /* DBGBCRn_EL1 */ \
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
> + trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \
> + /* DBGWVRn_EL1 */ \
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
> + trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \
> + /* DBGWCRn_EL1 */ \
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
> + trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
> +
> /*
> * Architected system registers.
> * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
> @@ -201,8 +271,12 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
> * all PM registers, which doesn't crash the guest kernel at least.
> *
> - * Same goes for the whole debug infrastructure, which probably breaks
> - * some guest functionnality. This should be fixed.
> + * Debug handling: We do trap most, if not all debug related system
> + * registers. The implementation is good enough to ensure that a guest
> + * can use these with minimal performance degradation. The drawback is
> + * that we don't implement any of the external debug, none of the
> + * OSlock protocol. This should be revisited if we ever encounter a
> + * more demanding guest...
> */
> static const struct sys_reg_desc sys_reg_descs[] = {
> /* DC ISW */
> @@ -215,12 +289,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
> { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
> access_dcsw },
>
> + DBG_BCR_BVR_WCR_WVR_EL1(0),
> + DBG_BCR_BVR_WCR_WVR_EL1(1),
> + /* MDCCINT_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
> + trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
> + /* MDSCR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
> + trap_debug_regs, reset_val, MDSCR_EL1, 0 },
> + DBG_BCR_BVR_WCR_WVR_EL1(2),
> + DBG_BCR_BVR_WCR_WVR_EL1(3),
> + DBG_BCR_BVR_WCR_WVR_EL1(4),
> + DBG_BCR_BVR_WCR_WVR_EL1(5),
> + DBG_BCR_BVR_WCR_WVR_EL1(6),
> + DBG_BCR_BVR_WCR_WVR_EL1(7),
> + DBG_BCR_BVR_WCR_WVR_EL1(8),
> + DBG_BCR_BVR_WCR_WVR_EL1(9),
> + DBG_BCR_BVR_WCR_WVR_EL1(10),
> + DBG_BCR_BVR_WCR_WVR_EL1(11),
> + DBG_BCR_BVR_WCR_WVR_EL1(12),
> + DBG_BCR_BVR_WCR_WVR_EL1(13),
> + DBG_BCR_BVR_WCR_WVR_EL1(14),
> + DBG_BCR_BVR_WCR_WVR_EL1(15),
> +
> + /* MDRAR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
> + trap_raz_wi },
> + /* OSLAR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
> + trap_raz_wi },
> + /* OSLSR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
> + trap_oslsr_el1 },
> + /* OSDLR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
> + trap_raz_wi },
> + /* DBGPRCR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
> + trap_raz_wi },
> + /* DBGCLAIMSET_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
> + trap_raz_wi },
> + /* DBGCLAIMCLR_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
> + trap_raz_wi },
> + /* DBGAUTHSTATUS_EL1 */
> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
> + trap_dbgauthstatus_el1 },
> +
> /* TEECR32_EL1 */
> { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
> NULL, reset_val, TEECR32_EL1, 0 },
> /* TEEHBR32_EL1 */
> { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
> NULL, reset_val, TEEHBR32_EL1, 0 },
> +
> + /* MDCCSR_EL1 */
> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
> + trap_raz_wi },
> + /* DBGDTR_EL0 */
> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
> + trap_raz_wi },
> + /* DBGDTR[TR]X_EL0 */
> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
> + trap_raz_wi },
> +
> /* DBGVCR32_EL2 */
> { Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
> NULL, reset_val, DBGVCR32_EL2, 0 },
> --
> 1.8.3.4
>
Besides the commenting stuff above:
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers
2014-07-09 9:38 ` Christoffer Dall
@ 2014-07-09 11:09 ` Marc Zyngier
2014-07-09 14:52 ` Christoffer Dall
0 siblings, 1 reply; 19+ messages in thread
From: Marc Zyngier @ 2014-07-09 11:09 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jul 09 2014 at 10:38:13 am BST, Christoffer Dall <christoffer.dall@linaro.org> wrote:
> On Fri, Jun 20, 2014 at 02:00:01PM +0100, Marc Zyngier wrote:
>> Add handlers for all the AArch64 debug registers that are accessible
>> from EL0 or EL1. The trapping code keeps track of the state of the
>> debug registers, allowing for the switch code to implement a lazy
>> switching strategy.
>>
>> Reviewed-by: Anup Patel <anup.patel@linaro.org>
>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
>> ---
>> arch/arm64/include/asm/kvm_asm.h | 28 ++++++--
>> arch/arm64/include/asm/kvm_host.h | 3 +
>> arch/arm64/kvm/sys_regs.c | 137 +++++++++++++++++++++++++++++++++++++-
>> 3 files changed, 159 insertions(+), 9 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
>> index 9fcd54b..e6b159a 100644
>> --- a/arch/arm64/include/asm/kvm_asm.h
>> +++ b/arch/arm64/include/asm/kvm_asm.h
>> @@ -43,14 +43,25 @@
>> #define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */
>> #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */
>> #define PAR_EL1 21 /* Physical Address Register */
>> +#define MDSCR_EL1 22 /* Monitor Debug System Control Register */
>> +#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */
>> +#define DBGBCR15_EL1 38
>> +#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */
>> +#define DBGBVR15_EL1 54
>> +#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */
>> +#define DBGWCR15_EL1 70
>> +#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */
>> +#define DBGWVR15_EL1 86
>> +#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */
>> +
>> /* 32bit specific registers. Keep them at the end of the range */
>> -#define DACR32_EL2 22 /* Domain Access Control Register */
>> -#define IFSR32_EL2 23 /* Instruction Fault Status Register */
>> -#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */
>> -#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */
>> -#define TEECR32_EL1 26 /* ThumbEE Configuration Register */
>> -#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */
>> -#define NR_SYS_REGS 28
>> +#define DACR32_EL2 88 /* Domain Access Control Register */
>> +#define IFSR32_EL2 89 /* Instruction Fault Status Register */
>> +#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */
>> +#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */
>> +#define TEECR32_EL1 92 /* ThumbEE Configuration Register */
>> +#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */
>> +#define NR_SYS_REGS 94
>>
>> /* 32bit mapping */
>> #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
>> @@ -87,6 +98,9 @@
>> #define ARM_EXCEPTION_IRQ 0
>> #define ARM_EXCEPTION_TRAP 1
>>
>> +#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
>> +#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
>> +
>> #ifndef __ASSEMBLY__
>> struct kvm;
>> struct kvm_vcpu;
>> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
>> index 92242ce..79573c86 100644
>> --- a/arch/arm64/include/asm/kvm_host.h
>> +++ b/arch/arm64/include/asm/kvm_host.h
>> @@ -101,6 +101,9 @@ struct kvm_vcpu_arch {
>> /* Exception Information */
>> struct kvm_vcpu_fault_info fault;
>>
>> + /* Debug state */
>> + u64 debug_flags;
>> +
>> /* Pointer to host CPU context */
>> kvm_cpu_context_t *host_cpu_context;
>>
>> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
>> index 4abd84e..808e3b2 100644
>> --- a/arch/arm64/kvm/sys_regs.c
>> +++ b/arch/arm64/kvm/sys_regs.c
>> @@ -30,6 +30,7 @@
>> #include <asm/kvm_mmu.h>
>> #include <asm/cacheflush.h>
>> #include <asm/cputype.h>
>> +#include <asm/debug-monitors.h>
>> #include <trace/events/kvm.h>
>>
>> #include "sys_regs.h"
>> @@ -173,6 +174,60 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
>> return read_zero(vcpu, p);
>> }
>>
>> +static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
>> + const struct sys_reg_params *p,
>> + const struct sys_reg_desc *r)
>> +{
>> + if (p->is_write) {
>> + return ignore_write(vcpu, p);
>> + } else {
>> + *vcpu_reg(vcpu, p->Rt) = (1 << 3);
>> + return true;
>> + }
>> +}
>> +
>> +static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
>> + const struct sys_reg_params *p,
>> + const struct sys_reg_desc *r)
>> +{
>> + if (p->is_write) {
>> + return ignore_write(vcpu, p);
>> + } else {
>> + u32 val;
>> + asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
>> + *vcpu_reg(vcpu, p->Rt) = val;
>> + return true;
>> + }
>> +}
>> +
>> +/*
>> + * We want to avoid world-switching all the DBG registers all the
>> + * time. For this, we use a DIRTY but, indicating the guest has
>
> a DIRTY but? (at least there's only one t in there).
The whole debug architecture makes me feel very dirty.
>> + * modified the debug registers, and only restore the registers once,
>> + * disabling traps.
>
> I don't think I understand the "only restore the registers once" bit
> here. I know I'm being incredibly stupid, but I forgot since the last
> review round how this actually works; when we return from the guest and
> the guest has somehow enabled certain DBG functionality, then we set the dirty
> flag, which means we should stop trapping and context switch all the
> registers on world-switches, but if we see when returning from the guest
> that the guest doesn't appear to be using the registers we enable
> trapping and stop world-switching, right?
Almost. We always decide on the trapping when entering the guest:
- If the dirty bit is set (because we're coming back from trapping),
disable the traps, restore the registers
- If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
disable the traps, restore the registers
- Otherwise, enable the traps
When exiting the guest: If the dirty bit is set, save the registers and
clear the dirty bit.
> Do we clearly define which state triggers the world-switching and why
> that's a good rationale? (sorry, the debug architecture is not my
> favorite part of the ARM ARM).
I thing the above comment describes the state precisely. My rational is:
- If we've touched any debug register, it is likely that we're going to
touch more of them. It then makes sense to disable the traps and start
doing the save/restore dance
- If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is then
mandatory to save/restore the registers, as the guest depends on them.
Does this make the process clearer? If so, I can add it to the comment.
>> + *
>> + * The best thing to do would be to trap MDSCR_EL1 independently, test
>> + * if DBG_MDSCR_KDE or DBG_MDSCR_MDE is getting set, and only set the
>> + * DIRTY bit in that case.
>> + *
>> + * Unfortunately, "old" Linux kernels tend to hit MDSCR_EL1 like a
>> + * woodpecker on a tree, and it is better to disable trapping as soon
>> + * as possible in this case. Some day, make this a tuneable...
>> + */
>> +static bool trap_debug_regs(struct kvm_vcpu *vcpu,
>> + const struct sys_reg_params *p,
>> + const struct sys_reg_desc *r)
>> +{
>> + if (p->is_write) {
>> + vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
>> + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
>> + } else {
>> + *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
>> + }
>> +
>> + return true;
>> +}
>> +
>> static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
>> {
>> u64 amair;
>> @@ -189,6 +244,21 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
>> vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
>> }
>>
>> +/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
>> +#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
>> + /* DBGBVRn_EL1 */ \
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
>> + trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \
>> + /* DBGBCRn_EL1 */ \
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
>> + trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \
>> + /* DBGWVRn_EL1 */ \
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
>> + trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \
>> + /* DBGWCRn_EL1 */ \
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
>> + trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
>> +
>> /*
>> * Architected system registers.
>> * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
>> @@ -201,8 +271,12 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
>> * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
>> * all PM registers, which doesn't crash the guest kernel at least.
>> *
>> - * Same goes for the whole debug infrastructure, which probably breaks
>> - * some guest functionnality. This should be fixed.
>> + * Debug handling: We do trap most, if not all debug related system
>> + * registers. The implementation is good enough to ensure that a guest
>> + * can use these with minimal performance degradation. The drawback is
>> + * that we don't implement any of the external debug, none of the
>> + * OSlock protocol. This should be revisited if we ever encounter a
>> + * more demanding guest...
>> */
>> static const struct sys_reg_desc sys_reg_descs[] = {
>> /* DC ISW */
>> @@ -215,12 +289,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>> { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
>> access_dcsw },
>>
>> + DBG_BCR_BVR_WCR_WVR_EL1(0),
>> + DBG_BCR_BVR_WCR_WVR_EL1(1),
>> + /* MDCCINT_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
>> + trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
>> + /* MDSCR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
>> + trap_debug_regs, reset_val, MDSCR_EL1, 0 },
>> + DBG_BCR_BVR_WCR_WVR_EL1(2),
>> + DBG_BCR_BVR_WCR_WVR_EL1(3),
>> + DBG_BCR_BVR_WCR_WVR_EL1(4),
>> + DBG_BCR_BVR_WCR_WVR_EL1(5),
>> + DBG_BCR_BVR_WCR_WVR_EL1(6),
>> + DBG_BCR_BVR_WCR_WVR_EL1(7),
>> + DBG_BCR_BVR_WCR_WVR_EL1(8),
>> + DBG_BCR_BVR_WCR_WVR_EL1(9),
>> + DBG_BCR_BVR_WCR_WVR_EL1(10),
>> + DBG_BCR_BVR_WCR_WVR_EL1(11),
>> + DBG_BCR_BVR_WCR_WVR_EL1(12),
>> + DBG_BCR_BVR_WCR_WVR_EL1(13),
>> + DBG_BCR_BVR_WCR_WVR_EL1(14),
>> + DBG_BCR_BVR_WCR_WVR_EL1(15),
>> +
>> + /* MDRAR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
>> + trap_raz_wi },
>> + /* OSLAR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
>> + trap_raz_wi },
>> + /* OSLSR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
>> + trap_oslsr_el1 },
>> + /* OSDLR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
>> + trap_raz_wi },
>> + /* DBGPRCR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
>> + trap_raz_wi },
>> + /* DBGCLAIMSET_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
>> + trap_raz_wi },
>> + /* DBGCLAIMCLR_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
>> + trap_raz_wi },
>> + /* DBGAUTHSTATUS_EL1 */
>> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
>> + trap_dbgauthstatus_el1 },
>> +
>> /* TEECR32_EL1 */
>> { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
>> NULL, reset_val, TEECR32_EL1, 0 },
>> /* TEEHBR32_EL1 */
>> { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
>> NULL, reset_val, TEEHBR32_EL1, 0 },
>> +
>> + /* MDCCSR_EL1 */
>> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
>> + trap_raz_wi },
>> + /* DBGDTR_EL0 */
>> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
>> + trap_raz_wi },
>> + /* DBGDTR[TR]X_EL0 */
>> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
>> + trap_raz_wi },
>> +
>> /* DBGVCR32_EL2 */
>> { Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
>> NULL, reset_val, DBGVCR32_EL2, 0 },
>> --
>> 1.8.3.4
>>
>
> Besides the commenting stuff above:
>
> Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Thanks,
M.
--
Without deviation from the norm, progress is not possible.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers
2014-07-09 11:09 ` Marc Zyngier
@ 2014-07-09 14:52 ` Christoffer Dall
2014-07-09 16:20 ` Marc Zyngier
0 siblings, 1 reply; 19+ messages in thread
From: Christoffer Dall @ 2014-07-09 14:52 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jul 09, 2014 at 12:09:29PM +0100, Marc Zyngier wrote:
> On Wed, Jul 09 2014 at 10:38:13 am BST, Christoffer Dall <christoffer.dall@linaro.org> wrote:
> > On Fri, Jun 20, 2014 at 02:00:01PM +0100, Marc Zyngier wrote:
> >> Add handlers for all the AArch64 debug registers that are accessible
> >> from EL0 or EL1. The trapping code keeps track of the state of the
> >> debug registers, allowing for the switch code to implement a lazy
> >> switching strategy.
> >>
> >> Reviewed-by: Anup Patel <anup.patel@linaro.org>
> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> >> ---
> >> arch/arm64/include/asm/kvm_asm.h | 28 ++++++--
> >> arch/arm64/include/asm/kvm_host.h | 3 +
> >> arch/arm64/kvm/sys_regs.c | 137 +++++++++++++++++++++++++++++++++++++-
> >> 3 files changed, 159 insertions(+), 9 deletions(-)
> >>
> >> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> >> index 9fcd54b..e6b159a 100644
> >> --- a/arch/arm64/include/asm/kvm_asm.h
> >> +++ b/arch/arm64/include/asm/kvm_asm.h
> >> @@ -43,14 +43,25 @@
> >> #define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */
> >> #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */
> >> #define PAR_EL1 21 /* Physical Address Register */
> >> +#define MDSCR_EL1 22 /* Monitor Debug System Control Register */
> >> +#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */
> >> +#define DBGBCR15_EL1 38
> >> +#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */
> >> +#define DBGBVR15_EL1 54
> >> +#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */
> >> +#define DBGWCR15_EL1 70
> >> +#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */
> >> +#define DBGWVR15_EL1 86
> >> +#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */
> >> +
> >> /* 32bit specific registers. Keep them at the end of the range */
> >> -#define DACR32_EL2 22 /* Domain Access Control Register */
> >> -#define IFSR32_EL2 23 /* Instruction Fault Status Register */
> >> -#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */
> >> -#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */
> >> -#define TEECR32_EL1 26 /* ThumbEE Configuration Register */
> >> -#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */
> >> -#define NR_SYS_REGS 28
> >> +#define DACR32_EL2 88 /* Domain Access Control Register */
> >> +#define IFSR32_EL2 89 /* Instruction Fault Status Register */
> >> +#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */
> >> +#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */
> >> +#define TEECR32_EL1 92 /* ThumbEE Configuration Register */
> >> +#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */
> >> +#define NR_SYS_REGS 94
> >>
> >> /* 32bit mapping */
> >> #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
> >> @@ -87,6 +98,9 @@
> >> #define ARM_EXCEPTION_IRQ 0
> >> #define ARM_EXCEPTION_TRAP 1
> >>
> >> +#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
> >> +#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
> >> +
> >> #ifndef __ASSEMBLY__
> >> struct kvm;
> >> struct kvm_vcpu;
> >> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> >> index 92242ce..79573c86 100644
> >> --- a/arch/arm64/include/asm/kvm_host.h
> >> +++ b/arch/arm64/include/asm/kvm_host.h
> >> @@ -101,6 +101,9 @@ struct kvm_vcpu_arch {
> >> /* Exception Information */
> >> struct kvm_vcpu_fault_info fault;
> >>
> >> + /* Debug state */
> >> + u64 debug_flags;
> >> +
> >> /* Pointer to host CPU context */
> >> kvm_cpu_context_t *host_cpu_context;
> >>
> >> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> >> index 4abd84e..808e3b2 100644
> >> --- a/arch/arm64/kvm/sys_regs.c
> >> +++ b/arch/arm64/kvm/sys_regs.c
> >> @@ -30,6 +30,7 @@
> >> #include <asm/kvm_mmu.h>
> >> #include <asm/cacheflush.h>
> >> #include <asm/cputype.h>
> >> +#include <asm/debug-monitors.h>
> >> #include <trace/events/kvm.h>
> >>
> >> #include "sys_regs.h"
> >> @@ -173,6 +174,60 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
> >> return read_zero(vcpu, p);
> >> }
> >>
> >> +static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
> >> + const struct sys_reg_params *p,
> >> + const struct sys_reg_desc *r)
> >> +{
> >> + if (p->is_write) {
> >> + return ignore_write(vcpu, p);
> >> + } else {
> >> + *vcpu_reg(vcpu, p->Rt) = (1 << 3);
> >> + return true;
> >> + }
> >> +}
> >> +
> >> +static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
> >> + const struct sys_reg_params *p,
> >> + const struct sys_reg_desc *r)
> >> +{
> >> + if (p->is_write) {
> >> + return ignore_write(vcpu, p);
> >> + } else {
> >> + u32 val;
> >> + asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
> >> + *vcpu_reg(vcpu, p->Rt) = val;
> >> + return true;
> >> + }
> >> +}
> >> +
> >> +/*
> >> + * We want to avoid world-switching all the DBG registers all the
> >> + * time. For this, we use a DIRTY but, indicating the guest has
> >
> > a DIRTY but? (at least there's only one t in there).
>
> The whole debug architecture makes me feel very dirty.
>
> >> + * modified the debug registers, and only restore the registers once,
> >> + * disabling traps.
> >
> > I don't think I understand the "only restore the registers once" bit
> > here. I know I'm being incredibly stupid, but I forgot since the last
> > review round how this actually works; when we return from the guest and
> > the guest has somehow enabled certain DBG functionality, then we set the dirty
> > flag, which means we should stop trapping and context switch all the
> > registers on world-switches, but if we see when returning from the guest
> > that the guest doesn't appear to be using the registers we enable
> > trapping and stop world-switching, right?
>
> Almost. We always decide on the trapping when entering the guest:
> - If the dirty bit is set (because we're coming back from trapping),
> disable the traps, restore the registers
> - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
> disable the traps, restore the registers
this also sets the dirty bit then?
> - Otherwise, enable the traps
>
> When exiting the guest: If the dirty bit is set, save the registers and
> clear the dirty bit.
because the host should always be able to freely use the debug registers
so we always have to restore the host registers on coming out of the VM,
right?
>
> > Do we clearly define which state triggers the world-switching and why
> > that's a good rationale? (sorry, the debug architecture is not my
> > favorite part of the ARM ARM).
>
> I thing the above comment describes the state precisely. My rational is:
> - If we've touched any debug register, it is likely that we're going to
> touch more of them. It then makes sense to disable the traps and start
> doing the save/restore dance
> - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is then
> mandatory to save/restore the registers, as the guest depends on them.
>
> Does this make the process clearer? If so, I can add it to the comment.
>
yes, the above comments help a lot. thanks!!
[if I don't see your response because you already left for vacation, I'm
going to incorporate your comments in the patches to apply to
kvmarm/next].
> >> + *
> >> + * The best thing to do would be to trap MDSCR_EL1 independently, test
> >> + * if DBG_MDSCR_KDE or DBG_MDSCR_MDE is getting set, and only set the
> >> + * DIRTY bit in that case.
> >> + *
> >> + * Unfortunately, "old" Linux kernels tend to hit MDSCR_EL1 like a
> >> + * woodpecker on a tree, and it is better to disable trapping as soon
> >> + * as possible in this case. Some day, make this a tuneable...
> >> + */
> >> +static bool trap_debug_regs(struct kvm_vcpu *vcpu,
> >> + const struct sys_reg_params *p,
> >> + const struct sys_reg_desc *r)
> >> +{
> >> + if (p->is_write) {
> >> + vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
> >> + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
> >> + } else {
> >> + *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
> >> + }
> >> +
> >> + return true;
> >> +}
> >> +
> >> static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> >> {
> >> u64 amair;
> >> @@ -189,6 +244,21 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> >> vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
> >> }
> >>
> >> +/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
> >> +#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
> >> + /* DBGBVRn_EL1 */ \
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
> >> + trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \
> >> + /* DBGBCRn_EL1 */ \
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
> >> + trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \
> >> + /* DBGWVRn_EL1 */ \
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
> >> + trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \
> >> + /* DBGWCRn_EL1 */ \
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
> >> + trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
> >> +
> >> /*
> >> * Architected system registers.
> >> * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
> >> @@ -201,8 +271,12 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
> >> * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
> >> * all PM registers, which doesn't crash the guest kernel at least.
> >> *
> >> - * Same goes for the whole debug infrastructure, which probably breaks
> >> - * some guest functionnality. This should be fixed.
> >> + * Debug handling: We do trap most, if not all debug related system
> >> + * registers. The implementation is good enough to ensure that a guest
> >> + * can use these with minimal performance degradation. The drawback is
> >> + * that we don't implement any of the external debug, none of the
> >> + * OSlock protocol. This should be revisited if we ever encounter a
> >> + * more demanding guest...
> >> */
> >> static const struct sys_reg_desc sys_reg_descs[] = {
> >> /* DC ISW */
> >> @@ -215,12 +289,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
> >> { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
> >> access_dcsw },
> >>
> >> + DBG_BCR_BVR_WCR_WVR_EL1(0),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(1),
> >> + /* MDCCINT_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
> >> + trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
> >> + /* MDSCR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
> >> + trap_debug_regs, reset_val, MDSCR_EL1, 0 },
> >> + DBG_BCR_BVR_WCR_WVR_EL1(2),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(3),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(4),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(5),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(6),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(7),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(8),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(9),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(10),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(11),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(12),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(13),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(14),
> >> + DBG_BCR_BVR_WCR_WVR_EL1(15),
> >> +
> >> + /* MDRAR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
> >> + trap_raz_wi },
> >> + /* OSLAR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
> >> + trap_raz_wi },
> >> + /* OSLSR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
> >> + trap_oslsr_el1 },
> >> + /* OSDLR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
> >> + trap_raz_wi },
> >> + /* DBGPRCR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
> >> + trap_raz_wi },
> >> + /* DBGCLAIMSET_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
> >> + trap_raz_wi },
> >> + /* DBGCLAIMCLR_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
> >> + trap_raz_wi },
> >> + /* DBGAUTHSTATUS_EL1 */
> >> + { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
> >> + trap_dbgauthstatus_el1 },
> >> +
> >> /* TEECR32_EL1 */
> >> { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
> >> NULL, reset_val, TEECR32_EL1, 0 },
> >> /* TEEHBR32_EL1 */
> >> { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
> >> NULL, reset_val, TEEHBR32_EL1, 0 },
> >> +
> >> + /* MDCCSR_EL1 */
> >> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
> >> + trap_raz_wi },
> >> + /* DBGDTR_EL0 */
> >> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
> >> + trap_raz_wi },
> >> + /* DBGDTR[TR]X_EL0 */
> >> + { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
> >> + trap_raz_wi },
> >> +
> >> /* DBGVCR32_EL2 */
> >> { Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
> >> NULL, reset_val, DBGVCR32_EL2, 0 },
> >> --
> >> 1.8.3.4
> >>
> >
> > Besides the commenting stuff above:
> >
> > Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
>
> Thanks,
>
> M.
> --
> Without deviation from the norm, progress is not possible.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers
2014-07-09 14:52 ` Christoffer Dall
@ 2014-07-09 16:20 ` Marc Zyngier
0 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-07-09 16:20 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jul 09 2014 at 3:52:32 pm BST, Christoffer Dall <christoffer.dall@linaro.org> wrote:
> On Wed, Jul 09, 2014 at 12:09:29PM +0100, Marc Zyngier wrote:
>> On Wed, Jul 09 2014 at 10:38:13 am BST, Christoffer Dall
>> <christoffer.dall@linaro.org> wrote:
>> > On Fri, Jun 20, 2014 at 02:00:01PM +0100, Marc Zyngier wrote:
>> >> Add handlers for all the AArch64 debug registers that are accessible
>> >> from EL0 or EL1. The trapping code keeps track of the state of the
>> >> debug registers, allowing for the switch code to implement a lazy
>> >> switching strategy.
>> >>
>> >> Reviewed-by: Anup Patel <anup.patel@linaro.org>
>> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
>> >> ---
>> >> arch/arm64/include/asm/kvm_asm.h | 28 ++++++--
>> >> arch/arm64/include/asm/kvm_host.h | 3 +
>> >> arch/arm64/kvm/sys_regs.c | 137 +++++++++++++++++++++++++++++++++++++-
>> >> 3 files changed, 159 insertions(+), 9 deletions(-)
[...]
>> >> +/*
>> >> + * We want to avoid world-switching all the DBG registers all the
>> >> + * time. For this, we use a DIRTY but, indicating the guest has
>> >
>> > a DIRTY but? (at least there's only one t in there).
>>
>> The whole debug architecture makes me feel very dirty.
>>
>> >> + * modified the debug registers, and only restore the registers once,
>> >> + * disabling traps.
>> >
>> > I don't think I understand the "only restore the registers once" bit
>> > here. I know I'm being incredibly stupid, but I forgot since the last
>> > review round how this actually works; when we return from the guest and
>> > the guest has somehow enabled certain DBG functionality, then we
>> > set the dirty
>> > flag, which means we should stop trapping and context switch all the
>> > registers on world-switches, but if we see when returning from the guest
>> > that the guest doesn't appear to be using the registers we enable
>> > trapping and stop world-switching, right?
>>
>> Almost. We always decide on the trapping when entering the guest:
>> - If the dirty bit is set (because we're coming back from trapping),
>> disable the traps, restore the registers
>> - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
>> disable the traps, restore the registers
>
> this also sets the dirty bit then?
Indeed. I'll mention it.
>
>> - Otherwise, enable the traps
>>
>> When exiting the guest: If the dirty bit is set, save the registers and
>> clear the dirty bit.
>
> because the host should always be able to freely use the debug registers
> so we always have to restore the host registers on coming out of the VM,
> right?
Yes. The host may have its own debug state active, and we want to
preserve that.
>>
>> > Do we clearly define which state triggers the world-switching and why
>> > that's a good rationale? (sorry, the debug architecture is not my
>> > favorite part of the ARM ARM).
>>
>> I thing the above comment describes the state precisely. My rational is:
>> - If we've touched any debug register, it is likely that we're going to
>> touch more of them. It then makes sense to disable the traps and start
>> doing the save/restore dance
>> - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is then
>> mandatory to save/restore the registers, as the guest depends on them.
>>
>> Does this make the process clearer? If so, I can add it to the comment.
>>
>
> yes, the above comments help a lot. thanks!!
>
> [if I don't see your response because you already left for vacation, I'm
> going to incorporate your comments in the patches to apply to
> kvmarm/next].
I'm not quite gone yet! ;-) Just enough time left to respin the branch
on top of what's already queued, push it out and post the series.
M.
--
Without deviation from the norm, progress is not possible.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 4/9] arm64: KVM: common infrastructure for handling AArch32 CP14/CP15
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (2 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 3/9] arm64: KVM: add trap handlers for AArch64 debug registers Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 5/9] arm64: KVM: use separate tables for AArch32 32 and 64bit traps Marc Zyngier
` (4 subsequent siblings)
8 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
As we're about to trap a bunch of CP14 registers, let's rework
the CP15 handling so it can be generalized and work with multiple
tables.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/include/asm/kvm_asm.h | 2 +-
arch/arm64/include/asm/kvm_coproc.h | 3 +-
arch/arm64/include/asm/kvm_host.h | 9 ++-
arch/arm64/kvm/handle_exit.c | 4 +-
arch/arm64/kvm/sys_regs.c | 133 +++++++++++++++++++++++++++++-------
5 files changed, 122 insertions(+), 29 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index e6b159a..12f9dd7 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -93,7 +93,7 @@
#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */
#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
-#define NR_CP15_REGS (NR_SYS_REGS * 2)
+#define NR_COPRO_REGS (NR_SYS_REGS * 2)
#define ARM_EXCEPTION_IRQ 0
#define ARM_EXCEPTION_TRAP 1
diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 9a59301..0b52377 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -39,7 +39,8 @@ void kvm_register_target_sys_reg_table(unsigned int target,
struct kvm_sys_reg_target_table *table);
int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 79573c86..108a297 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -86,7 +86,7 @@ struct kvm_cpu_context {
struct kvm_regs gp_regs;
union {
u64 sys_regs[NR_SYS_REGS];
- u32 cp15[NR_CP15_REGS];
+ u32 copro[NR_COPRO_REGS];
};
};
@@ -141,7 +141,12 @@ struct kvm_vcpu_arch {
#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs)
#define vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)])
-#define vcpu_cp15(v,r) ((v)->arch.ctxt.cp15[(r)])
+/*
+ * CP14 and CP15 live in the same array, as they are backed by the
+ * same system registers.
+ */
+#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)])
+#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)])
struct kvm_vm_stat {
u32 remote_tlb_flush;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 182415e..e28be51 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -73,9 +73,9 @@ static exit_handle_fn arm_exit_handlers[] = {
[ESR_EL2_EC_WFI] = kvm_handle_wfx,
[ESR_EL2_EC_CP15_32] = kvm_handle_cp15_32,
[ESR_EL2_EC_CP15_64] = kvm_handle_cp15_64,
- [ESR_EL2_EC_CP14_MR] = kvm_handle_cp14_access,
+ [ESR_EL2_EC_CP14_MR] = kvm_handle_cp14_32,
[ESR_EL2_EC_CP14_LS] = kvm_handle_cp14_load_store,
- [ESR_EL2_EC_CP14_64] = kvm_handle_cp14_access,
+ [ESR_EL2_EC_CP14_64] = kvm_handle_cp14_64,
[ESR_EL2_EC_HVC32] = handle_hvc,
[ESR_EL2_EC_SMC32] = handle_smc,
[ESR_EL2_EC_HVC64] = handle_hvc,
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 808e3b2..fb6eece 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -483,6 +483,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
NULL, reset_val, FPEXC32_EL2, 0x70 },
};
+/* Trapped cp14 registers */
+static const struct sys_reg_desc cp14_regs[] = {
+};
+
/*
* Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
* depending on the way they are accessed (as a 32bit or a 64bit
@@ -590,26 +594,29 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
return 1;
}
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
- kvm_inject_undefined(vcpu);
- return 1;
-}
-
-static void emulate_cp15(struct kvm_vcpu *vcpu,
- const struct sys_reg_params *params)
+/*
+ * emulate_cp -- tries to match a sys_reg access in a handling table, and
+ * call the corresponding trap handler.
+ *
+ * @params: pointer to the descriptor of the access
+ * @table: array of trap descriptors
+ * @num: size of the trap descriptor array
+ *
+ * Return 0 if the access has been handled, and -1 if not.
+ */
+static int emulate_cp(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params,
+ const struct sys_reg_desc *table,
+ size_t num)
{
- size_t num;
- const struct sys_reg_desc *table, *r;
+ const struct sys_reg_desc *r;
- table = get_target_table(vcpu->arch.target, false, &num);
+ if (!table)
+ return -1; /* Not handled */
- /* Search target-specific then generic table. */
r = find_reg(params, table, num);
- if (!r)
- r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs));
- if (likely(r)) {
+ if (r) {
/*
* Not having an accessor means that we have
* configured a trap that we don't know how to
@@ -621,22 +628,51 @@ static void emulate_cp15(struct kvm_vcpu *vcpu,
if (likely(r->access(vcpu, params, r))) {
/* Skip instruction, since it was emulated */
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
- return;
}
- /* If access function fails, it should complain. */
+
+ /* Handled */
+ return 0;
}
- kvm_err("Unsupported guest CP15 access at: %08lx\n", *vcpu_pc(vcpu));
+ /* Not handled */
+ return -1;
+}
+
+static void unhandled_cp_access(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *params)
+{
+ u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+ int cp;
+
+ switch(hsr_ec) {
+ case ESR_EL2_EC_CP15_32:
+ case ESR_EL2_EC_CP15_64:
+ cp = 15;
+ break;
+ case ESR_EL2_EC_CP14_MR:
+ case ESR_EL2_EC_CP14_64:
+ cp = 14;
+ break;
+ default:
+ WARN_ON((cp = -1));
+ }
+
+ kvm_err("Unsupported guest CP%d access at: %08lx\n",
+ cp, *vcpu_pc(vcpu));
print_sys_reg_instr(params);
kvm_inject_undefined(vcpu);
}
/**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
* @vcpu: The VCPU pointer
* @run: The kvm_run struct
*/
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *global,
+ size_t nr_global,
+ const struct sys_reg_desc *target_specific,
+ size_t nr_specific)
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -665,8 +701,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
*vcpu_reg(vcpu, params.Rt) = val;
}
- emulate_cp15(vcpu, ¶ms);
+ if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific))
+ goto out;
+ if (!emulate_cp(vcpu, ¶ms, global, nr_global))
+ goto out;
+ unhandled_cp_access(vcpu, ¶ms);
+
+out:
/* Do the opposite hack for the read side */
if (!params.is_write) {
u64 val = *vcpu_reg(vcpu, params.Rt);
@@ -682,7 +724,11 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
* @vcpu: The VCPU pointer
* @run: The kvm_run struct
*/
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *global,
+ size_t nr_global,
+ const struct sys_reg_desc *target_specific,
+ size_t nr_specific)
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -697,10 +743,51 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
params.Op1 = (hsr >> 14) & 0x7;
params.Op2 = (hsr >> 17) & 0x7;
- emulate_cp15(vcpu, ¶ms);
+ if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific))
+ return 1;
+ if (!emulate_cp(vcpu, ¶ms, global, nr_global))
+ return 1;
+
+ unhandled_cp_access(vcpu, ¶ms);
return 1;
}
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ const struct sys_reg_desc *target_specific;
+ size_t num;
+
+ target_specific = get_target_table(vcpu->arch.target, false, &num);
+ return kvm_handle_cp_64(vcpu,
+ cp15_regs, ARRAY_SIZE(cp15_regs),
+ target_specific, num);
+}
+
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ const struct sys_reg_desc *target_specific;
+ size_t num;
+
+ target_specific = get_target_table(vcpu->arch.target, false, &num);
+ return kvm_handle_cp_32(vcpu,
+ cp15_regs, ARRAY_SIZE(cp15_regs),
+ target_specific, num);
+}
+
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ return kvm_handle_cp_64(vcpu,
+ cp14_regs, ARRAY_SIZE(cp14_regs),
+ NULL, 0);
+}
+
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ return kvm_handle_cp_32(vcpu,
+ cp14_regs, ARRAY_SIZE(cp14_regs),
+ NULL, 0);
+}
+
static int emulate_sys_reg(struct kvm_vcpu *vcpu,
const struct sys_reg_params *params)
{
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 5/9] arm64: KVM: use separate tables for AArch32 32 and 64bit traps
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (3 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 4/9] arm64: KVM: common infrastructure for handling AArch32 CP14/CP15 Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 6/9] arm64: KVM: check ordering of all system register tables Marc Zyngier
` (3 subsequent siblings)
8 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
An interesting "feature" of the CP14 encoding is that there is
an overlap between 32 and 64bit registers, meaning they cannot
live in the same table as we did for CP15.
Create separate tables for 64bit CP14 and CP15 registers, and
let the top level handler use the right one.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/kvm/sys_regs.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fb6eece..1fb1bff 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -487,13 +487,16 @@ static const struct sys_reg_desc sys_reg_descs[] = {
static const struct sys_reg_desc cp14_regs[] = {
};
+/* Trapped cp14 64bit registers */
+static const struct sys_reg_desc cp14_64_regs[] = {
+};
+
/*
* Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
* depending on the way they are accessed (as a 32bit or a 64bit
* register).
*/
static const struct sys_reg_desc cp15_regs[] = {
- { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
@@ -534,6 +537,10 @@ static const struct sys_reg_desc cp15_regs[] = {
{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+};
+
+static const struct sys_reg_desc cp15_64_regs[] = {
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
};
@@ -759,7 +766,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
target_specific = get_target_table(vcpu->arch.target, false, &num);
return kvm_handle_cp_64(vcpu,
- cp15_regs, ARRAY_SIZE(cp15_regs),
+ cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
target_specific, num);
}
@@ -777,7 +784,7 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
return kvm_handle_cp_64(vcpu,
- cp14_regs, ARRAY_SIZE(cp14_regs),
+ cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
NULL, 0);
}
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 6/9] arm64: KVM: check ordering of all system register tables
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (4 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 5/9] arm64: KVM: use separate tables for AArch32 32 and 64bit traps Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 7/9] arm64: KVM: add trap handlers for AArch32 debug registers Marc Zyngier
` (2 subsequent siblings)
8 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
We now have multiple tables for the various system registers
we trap. Make sure we check the order of all of them, as it is
critical that we get the order right (been there, done that...).
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/kvm/sys_regs.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1fb1bff..9147b0c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1299,14 +1299,32 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
return write_demux_regids(uindices);
}
+static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
+{
+ unsigned int i;
+
+ for (i = 1; i < n; i++) {
+ if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
+ kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
void kvm_sys_reg_table_init(void)
{
unsigned int i;
struct sys_reg_desc clidr;
/* Make sure tables are unique and in order. */
- for (i = 1; i < ARRAY_SIZE(sys_reg_descs); i++)
- BUG_ON(cmp_sys_reg(&sys_reg_descs[i-1], &sys_reg_descs[i]) >= 0);
+ BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
+ BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
+ BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
+ BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+ BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
+ BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
/* We abuse the reset function to overwrite the table itself. */
for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 7/9] arm64: KVM: add trap handlers for AArch32 debug registers
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (5 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 6/9] arm64: KVM: check ordering of all system register tables Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-07-09 9:43 ` Christoffer Dall
2014-06-20 13:00 ` [PATCH v3 8/9] arm64: KVM: implement lazy world switch for " Marc Zyngier
2014-06-20 13:00 ` [PATCH v3 9/9] arm64: KVM: enable trapping of all " Marc Zyngier
8 siblings, 1 reply; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
Add handlers for all the AArch32 debug registers that are accessible
from EL0 or EL1. The code follow the same strategy as the AArch64
counterpart with regards to tracking the dirty state of the debug
registers.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/include/asm/kvm_asm.h | 9 +++
arch/arm64/kvm/sys_regs.c | 144 ++++++++++++++++++++++++++++++++++++++-
2 files changed, 151 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 12f9dd7..993a7db 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -93,6 +93,15 @@
#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */
#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
+
+#define cp14_DBGDSCRext (MDSCR_EL1 * 2)
+#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2)
+#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2)
+#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1)
+#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2)
+#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2)
+#define cp14_DBGDCCINT (MDCCINT_EL1 * 2)
+
#define NR_COPRO_REGS (NR_SYS_REGS * 2)
#define ARM_EXCEPTION_IRQ 0
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 9147b0c..daa635e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -483,12 +483,153 @@ static const struct sys_reg_desc sys_reg_descs[] = {
NULL, reset_val, FPEXC32_EL2, 0x70 },
};
-/* Trapped cp14 registers */
+static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
+ u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
+ u32 el3 = !!((pfr >> 12) & 0xf);
+
+ *vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
+ (((dfr >> 12) & 0xf) << 24) |
+ (((dfr >> 28) & 0xf) << 20) |
+ (6 << 16) | (el3 << 14) | (el3 << 12));
+ return true;
+ }
+}
+
+static bool trap_debug32(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+ vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+ }
+
+ return true;
+}
+
+#define DBG_BCR_BVR_WCR_WVR(n) \
+ /* DBGBVRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32, \
+ NULL, (cp14_DBGBVR0 + (n) * 2) }, \
+ /* DBGBCRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32, \
+ NULL, (cp14_DBGBCR0 + (n) * 2) }, \
+ /* DBGWVRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32, \
+ NULL, (cp14_DBGWVR0 + (n) * 2) }, \
+ /* DBGWCRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32, \
+ NULL, (cp14_DBGWCR0 + (n) * 2) }
+
+#define DBGBXVR(n) \
+ { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32, \
+ NULL, cp14_DBGBXVR0 + n * 2 }
+
+/*
+ * Trapped cp14 registers. We generally ignore most of the external
+ * debug, on the principle that they don't really make sense to a
+ * guest. Revisit this one day, whould this principle change.
+ */
static const struct sys_reg_desc cp14_regs[] = {
+ /* DBGIDR */
+ { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+ /* DBGDTRRXext */
+ { Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
+
+ DBG_BCR_BVR_WCR_WVR(0),
+ /* DBGDSCRint */
+ { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(1),
+ /* DBGDCCINT */
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+ /* DBGDSCRext */
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+ DBG_BCR_BVR_WCR_WVR(2),
+ /* DBGDTR[RT]Xint */
+ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
+ /* DBGDTR[RT]Xext */
+ { Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(3),
+ DBG_BCR_BVR_WCR_WVR(4),
+ DBG_BCR_BVR_WCR_WVR(5),
+ /* DBGWFAR */
+ { Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
+ /* DBGOSECCR */
+ { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(6),
+ /* DBGVCR */
+ { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+ DBG_BCR_BVR_WCR_WVR(7),
+ DBG_BCR_BVR_WCR_WVR(8),
+ DBG_BCR_BVR_WCR_WVR(9),
+ DBG_BCR_BVR_WCR_WVR(10),
+ DBG_BCR_BVR_WCR_WVR(11),
+ DBG_BCR_BVR_WCR_WVR(12),
+ DBG_BCR_BVR_WCR_WVR(13),
+ DBG_BCR_BVR_WCR_WVR(14),
+ DBG_BCR_BVR_WCR_WVR(15),
+
+ /* DBGDRAR (32bit) */
+ { Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
+
+ DBGBXVR(0),
+ /* DBGOSLAR */
+ { Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+ DBGBXVR(1),
+ /* DBGOSLSR */
+ { Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+ DBGBXVR(2),
+ DBGBXVR(3),
+ /* DBGOSDLR */
+ { Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
+ DBGBXVR(4),
+ /* DBGPRCR */
+ { Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
+ DBGBXVR(5),
+ DBGBXVR(6),
+ DBGBXVR(7),
+ DBGBXVR(8),
+ DBGBXVR(9),
+ DBGBXVR(10),
+ DBGBXVR(11),
+ DBGBXVR(12),
+ DBGBXVR(13),
+ DBGBXVR(14),
+ DBGBXVR(15),
+
+ /* DBGDSAR (32bit) */
+ { Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
+
+ /* DBGDEVID2 */
+ { Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
+ /* DBGDEVID1 */
+ { Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
+ /* DBGDEVID */
+ { Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
+ /* DBGCLAIMSET */
+ { Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
+ /* DBGCLAIMCLR */
+ { Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
+ /* DBGAUTHSTATUS */
+ { Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
};
/* Trapped cp14 64bit registers */
static const struct sys_reg_desc cp14_64_regs[] = {
+ /* DBGDRAR (64bit) */
+ { Op1( 0), CRm( 1), .access = trap_raz_wi },
+
+ /* DBGDSAR (64bit) */
+ { Op1( 0), CRm( 2), .access = trap_raz_wi },
};
/*
@@ -536,7 +677,6 @@ static const struct sys_reg_desc cp15_regs[] = {
{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
-
};
static const struct sys_reg_desc cp15_64_regs[] = {
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 7/9] arm64: KVM: add trap handlers for AArch32 debug registers
2014-06-20 13:00 ` [PATCH v3 7/9] arm64: KVM: add trap handlers for AArch32 debug registers Marc Zyngier
@ 2014-07-09 9:43 ` Christoffer Dall
0 siblings, 0 replies; 19+ messages in thread
From: Christoffer Dall @ 2014-07-09 9:43 UTC (permalink / raw)
To: linux-arm-kernel
On Fri, Jun 20, 2014 at 02:00:05PM +0100, Marc Zyngier wrote:
> Add handlers for all the AArch32 debug registers that are accessible
> from EL0 or EL1. The code follow the same strategy as the AArch64
> counterpart with regards to tracking the dirty state of the debug
> registers.
>
> Reviewed-by: Anup Patel <anup.patel@linaro.org>
> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> ---
> arch/arm64/include/asm/kvm_asm.h | 9 +++
> arch/arm64/kvm/sys_regs.c | 144 ++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 151 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 12f9dd7..993a7db 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -93,6 +93,15 @@
> #define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */
> #define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
> #define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
> +
> +#define cp14_DBGDSCRext (MDSCR_EL1 * 2)
> +#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2)
> +#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2)
> +#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1)
> +#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2)
> +#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2)
> +#define cp14_DBGDCCINT (MDCCINT_EL1 * 2)
> +
> #define NR_COPRO_REGS (NR_SYS_REGS * 2)
>
> #define ARM_EXCEPTION_IRQ 0
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index 9147b0c..daa635e 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -483,12 +483,153 @@ static const struct sys_reg_desc sys_reg_descs[] = {
> NULL, reset_val, FPEXC32_EL2, 0x70 },
> };
>
> -/* Trapped cp14 registers */
> +static bool trap_dbgidr(struct kvm_vcpu *vcpu,
> + const struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + if (p->is_write) {
> + return ignore_write(vcpu, p);
> + } else {
> + u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
> + u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
> + u32 el3 = !!((pfr >> 12) & 0xf);
> +
> + *vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
> + (((dfr >> 12) & 0xf) << 24) |
> + (((dfr >> 28) & 0xf) << 20) |
> + (6 << 16) | (el3 << 14) | (el3 << 12));
> + return true;
> + }
> +}
> +
> +static bool trap_debug32(struct kvm_vcpu *vcpu,
> + const struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + if (p->is_write) {
> + vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
> + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
> + } else {
> + *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
> + }
> +
> + return true;
> +}
> +
> +#define DBG_BCR_BVR_WCR_WVR(n) \
> + /* DBGBVRn */ \
> + { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32, \
> + NULL, (cp14_DBGBVR0 + (n) * 2) }, \
> + /* DBGBCRn */ \
> + { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32, \
> + NULL, (cp14_DBGBCR0 + (n) * 2) }, \
> + /* DBGWVRn */ \
> + { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32, \
> + NULL, (cp14_DBGWVR0 + (n) * 2) }, \
> + /* DBGWCRn */ \
> + { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32, \
> + NULL, (cp14_DBGWCR0 + (n) * 2) }
> +
> +#define DBGBXVR(n) \
> + { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32, \
> + NULL, cp14_DBGBXVR0 + n * 2 }
> +
> +/*
> + * Trapped cp14 registers. We generally ignore most of the external
> + * debug, on the principle that they don't really make sense to a
> + * guest. Revisit this one day, whould this principle change.
> + */
> static const struct sys_reg_desc cp14_regs[] = {
> + /* DBGIDR */
> + { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
> + /* DBGDTRRXext */
> + { Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
> +
> + DBG_BCR_BVR_WCR_WVR(0),
> + /* DBGDSCRint */
> + { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
> + DBG_BCR_BVR_WCR_WVR(1),
> + /* DBGDCCINT */
> + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
> + /* DBGDSCRext */
> + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
> + DBG_BCR_BVR_WCR_WVR(2),
> + /* DBGDTR[RT]Xint */
> + { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
> + /* DBGDTR[RT]Xext */
> + { Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
> + DBG_BCR_BVR_WCR_WVR(3),
> + DBG_BCR_BVR_WCR_WVR(4),
> + DBG_BCR_BVR_WCR_WVR(5),
> + /* DBGWFAR */
> + { Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
> + /* DBGOSECCR */
> + { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
> + DBG_BCR_BVR_WCR_WVR(6),
> + /* DBGVCR */
> + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
> + DBG_BCR_BVR_WCR_WVR(7),
> + DBG_BCR_BVR_WCR_WVR(8),
> + DBG_BCR_BVR_WCR_WVR(9),
> + DBG_BCR_BVR_WCR_WVR(10),
> + DBG_BCR_BVR_WCR_WVR(11),
> + DBG_BCR_BVR_WCR_WVR(12),
> + DBG_BCR_BVR_WCR_WVR(13),
> + DBG_BCR_BVR_WCR_WVR(14),
> + DBG_BCR_BVR_WCR_WVR(15),
> +
> + /* DBGDRAR (32bit) */
> + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
> +
> + DBGBXVR(0),
> + /* DBGOSLAR */
> + { Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
> + DBGBXVR(1),
> + /* DBGOSLSR */
> + { Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
> + DBGBXVR(2),
> + DBGBXVR(3),
> + /* DBGOSDLR */
> + { Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
> + DBGBXVR(4),
> + /* DBGPRCR */
> + { Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
> + DBGBXVR(5),
> + DBGBXVR(6),
> + DBGBXVR(7),
> + DBGBXVR(8),
> + DBGBXVR(9),
> + DBGBXVR(10),
> + DBGBXVR(11),
> + DBGBXVR(12),
> + DBGBXVR(13),
> + DBGBXVR(14),
> + DBGBXVR(15),
> +
> + /* DBGDSAR (32bit) */
> + { Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
> +
> + /* DBGDEVID2 */
> + { Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
> + /* DBGDEVID1 */
> + { Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
> + /* DBGDEVID */
> + { Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
> + /* DBGCLAIMSET */
> + { Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
> + /* DBGCLAIMCLR */
> + { Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
> + /* DBGAUTHSTATUS */
> + { Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
> };
>
> /* Trapped cp14 64bit registers */
> static const struct sys_reg_desc cp14_64_regs[] = {
> + /* DBGDRAR (64bit) */
> + { Op1( 0), CRm( 1), .access = trap_raz_wi },
> +
> + /* DBGDSAR (64bit) */
> + { Op1( 0), CRm( 2), .access = trap_raz_wi },
> };
>
> /*
> @@ -536,7 +677,6 @@ static const struct sys_reg_desc cp15_regs[] = {
> { Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
> { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
> { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
> -
> };
>
> static const struct sys_reg_desc cp15_64_regs[] = {
> --
> 1.8.3.4
>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 8/9] arm64: KVM: implement lazy world switch for debug registers
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (6 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 7/9] arm64: KVM: add trap handlers for AArch32 debug registers Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
2014-07-09 9:45 ` Christoffer Dall
2014-06-20 13:00 ` [PATCH v3 9/9] arm64: KVM: enable trapping of all " Marc Zyngier
8 siblings, 1 reply; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
Implement switching of the debug registers. While the number
of registers is massive, CPUs usually don't implement them all
(A57 has 6 breakpoints and 4 watchpoints, which gives us a total
of 22 registers "only").
Also, we only save/restore them when MDSCR_EL1 has debug enabled,
or when we've flagged the debug registers as dirty. It means that
most of the time, we only save/restore MDSCR_EL1.
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/kernel/asm-offsets.c | 1 +
arch/arm64/kvm/hyp.S | 462 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 457 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 646f888..ae73a83 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -120,6 +120,7 @@ int main(void)
DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2));
DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2));
DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
+ DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags));
DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2));
DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines));
DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context));
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index b0d1512..727087c 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -21,6 +21,7 @@
#include <asm/assembler.h>
#include <asm/memory.h>
#include <asm/asm-offsets.h>
+#include <asm/debug-monitors.h>
#include <asm/fpsimdmacros.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
@@ -215,6 +216,7 @@ __kvm_hyp_code_start:
mrs x22, amair_el1
mrs x23, cntkctl_el1
mrs x24, par_el1
+ mrs x25, mdscr_el1
stp x4, x5, [x3]
stp x6, x7, [x3, #16]
@@ -226,7 +228,202 @@ __kvm_hyp_code_start:
stp x18, x19, [x3, #112]
stp x20, x21, [x3, #128]
stp x22, x23, [x3, #144]
- str x24, [x3, #160]
+ stp x24, x25, [x3, #160]
+.endm
+
+.macro save_debug
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ mrs x26, id_aa64dfr0_el1
+ ubfx x24, x26, #12, #4 // Extract BRPs
+ ubfx x25, x26, #20, #4 // Extract WRPs
+ mov w26, #15
+ sub w24, w26, w24 // How many BPs to skip
+ sub w25, w26, w25 // How many WPs to skip
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ mrs x20, dbgbcr15_el1
+ mrs x19, dbgbcr14_el1
+ mrs x18, dbgbcr13_el1
+ mrs x17, dbgbcr12_el1
+ mrs x16, dbgbcr11_el1
+ mrs x15, dbgbcr10_el1
+ mrs x14, dbgbcr9_el1
+ mrs x13, dbgbcr8_el1
+ mrs x12, dbgbcr7_el1
+ mrs x11, dbgbcr6_el1
+ mrs x10, dbgbcr5_el1
+ mrs x9, dbgbcr4_el1
+ mrs x8, dbgbcr3_el1
+ mrs x7, dbgbcr2_el1
+ mrs x6, dbgbcr1_el1
+ mrs x5, dbgbcr0_el1
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ mrs x20, dbgbvr15_el1
+ mrs x19, dbgbvr14_el1
+ mrs x18, dbgbvr13_el1
+ mrs x17, dbgbvr12_el1
+ mrs x16, dbgbvr11_el1
+ mrs x15, dbgbvr10_el1
+ mrs x14, dbgbvr9_el1
+ mrs x13, dbgbvr8_el1
+ mrs x12, dbgbvr7_el1
+ mrs x11, dbgbvr6_el1
+ mrs x10, dbgbvr5_el1
+ mrs x9, dbgbvr4_el1
+ mrs x8, dbgbvr3_el1
+ mrs x7, dbgbvr2_el1
+ mrs x6, dbgbvr1_el1
+ mrs x5, dbgbvr0_el1
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ mrs x20, dbgwcr15_el1
+ mrs x19, dbgwcr14_el1
+ mrs x18, dbgwcr13_el1
+ mrs x17, dbgwcr12_el1
+ mrs x16, dbgwcr11_el1
+ mrs x15, dbgwcr10_el1
+ mrs x14, dbgwcr9_el1
+ mrs x13, dbgwcr8_el1
+ mrs x12, dbgwcr7_el1
+ mrs x11, dbgwcr6_el1
+ mrs x10, dbgwcr5_el1
+ mrs x9, dbgwcr4_el1
+ mrs x8, dbgwcr3_el1
+ mrs x7, dbgwcr2_el1
+ mrs x6, dbgwcr1_el1
+ mrs x5, dbgwcr0_el1
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ mrs x20, dbgwvr15_el1
+ mrs x19, dbgwvr14_el1
+ mrs x18, dbgwvr13_el1
+ mrs x17, dbgwvr12_el1
+ mrs x16, dbgwvr11_el1
+ mrs x15, dbgwvr10_el1
+ mrs x14, dbgwvr9_el1
+ mrs x13, dbgwvr8_el1
+ mrs x12, dbgwvr7_el1
+ mrs x11, dbgwvr6_el1
+ mrs x10, dbgwvr5_el1
+ mrs x9, dbgwvr4_el1
+ mrs x8, dbgwvr3_el1
+ mrs x7, dbgwvr2_el1
+ mrs x6, dbgwvr1_el1
+ mrs x5, dbgwvr0_el1
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ mrs x21, mdccint_el1
+ str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
.endm
.macro restore_sysregs
@@ -245,7 +442,7 @@ __kvm_hyp_code_start:
ldp x18, x19, [x3, #112]
ldp x20, x21, [x3, #128]
ldp x22, x23, [x3, #144]
- ldr x24, [x3, #160]
+ ldp x24, x25, [x3, #160]
msr vmpidr_el2, x4
msr csselr_el1, x5
@@ -268,6 +465,198 @@ __kvm_hyp_code_start:
msr amair_el1, x22
msr cntkctl_el1, x23
msr par_el1, x24
+ msr mdscr_el1, x25
+.endm
+
+.macro restore_debug
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ mrs x26, id_aa64dfr0_el1
+ ubfx x24, x26, #12, #4 // Extract BRPs
+ ubfx x25, x26, #20, #4 // Extract WRPs
+ mov w26, #15
+ sub w24, w26, w24 // How many BPs to skip
+ sub w25, w26, w25 // How many WPs to skip
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ msr dbgbcr15_el1, x20
+ msr dbgbcr14_el1, x19
+ msr dbgbcr13_el1, x18
+ msr dbgbcr12_el1, x17
+ msr dbgbcr11_el1, x16
+ msr dbgbcr10_el1, x15
+ msr dbgbcr9_el1, x14
+ msr dbgbcr8_el1, x13
+ msr dbgbcr7_el1, x12
+ msr dbgbcr6_el1, x11
+ msr dbgbcr5_el1, x10
+ msr dbgbcr4_el1, x9
+ msr dbgbcr3_el1, x8
+ msr dbgbcr2_el1, x7
+ msr dbgbcr1_el1, x6
+ msr dbgbcr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ msr dbgbvr15_el1, x20
+ msr dbgbvr14_el1, x19
+ msr dbgbvr13_el1, x18
+ msr dbgbvr12_el1, x17
+ msr dbgbvr11_el1, x16
+ msr dbgbvr10_el1, x15
+ msr dbgbvr9_el1, x14
+ msr dbgbvr8_el1, x13
+ msr dbgbvr7_el1, x12
+ msr dbgbvr6_el1, x11
+ msr dbgbvr5_el1, x10
+ msr dbgbvr4_el1, x9
+ msr dbgbvr3_el1, x8
+ msr dbgbvr2_el1, x7
+ msr dbgbvr1_el1, x6
+ msr dbgbvr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ msr dbgwcr15_el1, x20
+ msr dbgwcr14_el1, x19
+ msr dbgwcr13_el1, x18
+ msr dbgwcr12_el1, x17
+ msr dbgwcr11_el1, x16
+ msr dbgwcr10_el1, x15
+ msr dbgwcr9_el1, x14
+ msr dbgwcr8_el1, x13
+ msr dbgwcr7_el1, x12
+ msr dbgwcr6_el1, x11
+ msr dbgwcr5_el1, x10
+ msr dbgwcr4_el1, x9
+ msr dbgwcr3_el1, x8
+ msr dbgwcr2_el1, x7
+ msr dbgwcr1_el1, x6
+ msr dbgwcr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ msr dbgwvr15_el1, x20
+ msr dbgwvr14_el1, x19
+ msr dbgwvr13_el1, x18
+ msr dbgwvr12_el1, x17
+ msr dbgwvr11_el1, x16
+ msr dbgwvr10_el1, x15
+ msr dbgwvr9_el1, x14
+ msr dbgwvr8_el1, x13
+ msr dbgwvr7_el1, x12
+ msr dbgwvr6_el1, x11
+ msr dbgwvr5_el1, x10
+ msr dbgwvr4_el1, x9
+ msr dbgwvr3_el1, x8
+ msr dbgwvr2_el1, x7
+ msr dbgwvr1_el1, x6
+ msr dbgwvr0_el1, x5
+
+ ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+ msr mdccint_el1, x21
.endm
.macro skip_32bit_state tmp, target
@@ -282,6 +671,35 @@ __kvm_hyp_code_start:
tbz \tmp, #12, \target
.endm
+.macro skip_debug_state tmp, target
+ ldr \tmp, [x0, #VCPU_DEBUG_FLAGS]
+ tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
+.endm
+
+.macro compute_debug_state target
+ // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
+ // is set, we do a full save/restore cycle and disable trapping.
+ add x25, x0, #VCPU_CONTEXT
+
+ // Check the state of MDSCR_EL1
+ ldr x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
+ and x26, x25, #DBG_MDSCR_KDE
+ and x25, x25, #DBG_MDSCR_MDE
+ adds xzr, x25, x26
+ b.eq 9998f // Nothing to see there
+
+ // If any interesting bits was set, we must set the flag
+ mov x26, #KVM_ARM64_DEBUG_DIRTY
+ str x26, [x0, #VCPU_DEBUG_FLAGS]
+ b 9999f // Don't skip restore
+
+9998:
+ // Otherwise load the flags from memory in case we recently
+ // trapped
+ skip_debug_state x25, \target
+9999:
+.endm
+
.macro save_guest_32bit_state
skip_32bit_state x3, 1f
@@ -297,10 +715,13 @@ __kvm_hyp_code_start:
mrs x4, dacr32_el2
mrs x5, ifsr32_el2
mrs x6, fpexc32_el2
- mrs x7, dbgvcr32_el2
stp x4, x5, [x3]
- stp x6, x7, [x3, #16]
+ str x6, [x3, #16]
+ skip_debug_state x8, 2f
+ mrs x7, dbgvcr32_el2
+ str x7, [x3, #24]
+2:
skip_tee_state x8, 1f
add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -323,12 +744,15 @@ __kvm_hyp_code_start:
add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
ldp x4, x5, [x3]
- ldp x6, x7, [x3, #16]
+ ldr x6, [x3, #16]
msr dacr32_el2, x4
msr ifsr32_el2, x5
msr fpexc32_el2, x6
- msr dbgvcr32_el2, x7
+ skip_debug_state x8, 2f
+ ldr x7, [x3, #24]
+ msr dbgvcr32_el2, x7
+2:
skip_tee_state x8, 1f
add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -537,6 +961,14 @@ __restore_sysregs:
restore_sysregs
ret
+__save_debug:
+ save_debug
+ ret
+
+__restore_debug:
+ restore_debug
+ ret
+
__save_fpsimd:
save_fpsimd
ret
@@ -568,6 +1000,9 @@ ENTRY(__kvm_vcpu_run)
bl __save_fpsimd
bl __save_sysregs
+ compute_debug_state 1f
+ bl __save_debug
+1:
activate_traps
activate_vm
@@ -579,6 +1014,10 @@ ENTRY(__kvm_vcpu_run)
bl __restore_sysregs
bl __restore_fpsimd
+
+ skip_debug_state x3, 1f
+ bl __restore_debug
+1:
restore_guest_32bit_state
restore_guest_regs
@@ -595,6 +1034,10 @@ __kvm_vcpu_return:
save_guest_regs
bl __save_fpsimd
bl __save_sysregs
+
+ skip_debug_state x3, 1f
+ bl __save_debug
+1:
save_guest_32bit_state
save_timer_state
@@ -609,6 +1052,13 @@ __kvm_vcpu_return:
bl __restore_sysregs
bl __restore_fpsimd
+
+ skip_debug_state x3, 1f
+ // Clear the dirty flag for the next run, as all the state has
+ // already been saved.
+ str xzr, [x0, #VCPU_DEBUG_FLAGS]
+ bl __restore_debug
+1:
restore_host_regs
mov x0, x1
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH v3 8/9] arm64: KVM: implement lazy world switch for debug registers
2014-06-20 13:00 ` [PATCH v3 8/9] arm64: KVM: implement lazy world switch for " Marc Zyngier
@ 2014-07-09 9:45 ` Christoffer Dall
2014-07-09 11:18 ` Marc Zyngier
0 siblings, 1 reply; 19+ messages in thread
From: Christoffer Dall @ 2014-07-09 9:45 UTC (permalink / raw)
To: linux-arm-kernel
On Fri, Jun 20, 2014 at 02:00:06PM +0100, Marc Zyngier wrote:
> Implement switching of the debug registers. While the number
> of registers is massive, CPUs usually don't implement them all
> (A57 has 6 breakpoints and 4 watchpoints, which gives us a total
> of 22 registers "only").
>
> Also, we only save/restore them when MDSCR_EL1 has debug enabled,
> or when we've flagged the debug registers as dirty. It means that
> most of the time, we only save/restore MDSCR_EL1.
>
> Reviewed-by: Anup Patel <anup.patel@linaro.org>
> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
> ---
> arch/arm64/kernel/asm-offsets.c | 1 +
> arch/arm64/kvm/hyp.S | 462 +++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 457 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
> index 646f888..ae73a83 100644
> --- a/arch/arm64/kernel/asm-offsets.c
> +++ b/arch/arm64/kernel/asm-offsets.c
> @@ -120,6 +120,7 @@ int main(void)
> DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2));
> DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2));
> DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
> + DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags));
> DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2));
> DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines));
> DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context));
> diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
> index b0d1512..727087c 100644
> --- a/arch/arm64/kvm/hyp.S
> +++ b/arch/arm64/kvm/hyp.S
> @@ -21,6 +21,7 @@
> #include <asm/assembler.h>
> #include <asm/memory.h>
> #include <asm/asm-offsets.h>
> +#include <asm/debug-monitors.h>
> #include <asm/fpsimdmacros.h>
> #include <asm/kvm.h>
> #include <asm/kvm_asm.h>
> @@ -215,6 +216,7 @@ __kvm_hyp_code_start:
> mrs x22, amair_el1
> mrs x23, cntkctl_el1
> mrs x24, par_el1
> + mrs x25, mdscr_el1
>
> stp x4, x5, [x3]
> stp x6, x7, [x3, #16]
> @@ -226,7 +228,202 @@ __kvm_hyp_code_start:
> stp x18, x19, [x3, #112]
> stp x20, x21, [x3, #128]
> stp x22, x23, [x3, #144]
> - str x24, [x3, #160]
> + stp x24, x25, [x3, #160]
> +.endm
> +
> +.macro save_debug
> + // x2: base address for cpu context
> + // x3: tmp register
> +
> + mrs x26, id_aa64dfr0_el1
> + ubfx x24, x26, #12, #4 // Extract BRPs
> + ubfx x25, x26, #20, #4 // Extract WRPs
> + mov w26, #15
> + sub w24, w26, w24 // How many BPs to skip
> + sub w25, w26, w25 // How many WPs to skip
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + mrs x20, dbgbcr15_el1
> + mrs x19, dbgbcr14_el1
> + mrs x18, dbgbcr13_el1
> + mrs x17, dbgbcr12_el1
> + mrs x16, dbgbcr11_el1
> + mrs x15, dbgbcr10_el1
> + mrs x14, dbgbcr9_el1
> + mrs x13, dbgbcr8_el1
> + mrs x12, dbgbcr7_el1
> + mrs x11, dbgbcr6_el1
> + mrs x10, dbgbcr5_el1
> + mrs x9, dbgbcr4_el1
> + mrs x8, dbgbcr3_el1
> + mrs x7, dbgbcr2_el1
> + mrs x6, dbgbcr1_el1
> + mrs x5, dbgbcr0_el1
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +
> +1:
> + str x20, [x3, #(15 * 8)]
> + str x19, [x3, #(14 * 8)]
> + str x18, [x3, #(13 * 8)]
> + str x17, [x3, #(12 * 8)]
> + str x16, [x3, #(11 * 8)]
> + str x15, [x3, #(10 * 8)]
> + str x14, [x3, #(9 * 8)]
> + str x13, [x3, #(8 * 8)]
> + str x12, [x3, #(7 * 8)]
> + str x11, [x3, #(6 * 8)]
> + str x10, [x3, #(5 * 8)]
> + str x9, [x3, #(4 * 8)]
> + str x8, [x3, #(3 * 8)]
> + str x7, [x3, #(2 * 8)]
> + str x6, [x3, #(1 * 8)]
> + str x5, [x3, #(0 * 8)]
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + mrs x20, dbgbvr15_el1
> + mrs x19, dbgbvr14_el1
> + mrs x18, dbgbvr13_el1
> + mrs x17, dbgbvr12_el1
> + mrs x16, dbgbvr11_el1
> + mrs x15, dbgbvr10_el1
> + mrs x14, dbgbvr9_el1
> + mrs x13, dbgbvr8_el1
> + mrs x12, dbgbvr7_el1
> + mrs x11, dbgbvr6_el1
> + mrs x10, dbgbvr5_el1
> + mrs x9, dbgbvr4_el1
> + mrs x8, dbgbvr3_el1
> + mrs x7, dbgbvr2_el1
> + mrs x6, dbgbvr1_el1
> + mrs x5, dbgbvr0_el1
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +
> +1:
> + str x20, [x3, #(15 * 8)]
> + str x19, [x3, #(14 * 8)]
> + str x18, [x3, #(13 * 8)]
> + str x17, [x3, #(12 * 8)]
> + str x16, [x3, #(11 * 8)]
> + str x15, [x3, #(10 * 8)]
> + str x14, [x3, #(9 * 8)]
> + str x13, [x3, #(8 * 8)]
> + str x12, [x3, #(7 * 8)]
> + str x11, [x3, #(6 * 8)]
> + str x10, [x3, #(5 * 8)]
> + str x9, [x3, #(4 * 8)]
> + str x8, [x3, #(3 * 8)]
> + str x7, [x3, #(2 * 8)]
> + str x6, [x3, #(1 * 8)]
> + str x5, [x3, #(0 * 8)]
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + mrs x20, dbgwcr15_el1
> + mrs x19, dbgwcr14_el1
> + mrs x18, dbgwcr13_el1
> + mrs x17, dbgwcr12_el1
> + mrs x16, dbgwcr11_el1
> + mrs x15, dbgwcr10_el1
> + mrs x14, dbgwcr9_el1
> + mrs x13, dbgwcr8_el1
> + mrs x12, dbgwcr7_el1
> + mrs x11, dbgwcr6_el1
> + mrs x10, dbgwcr5_el1
> + mrs x9, dbgwcr4_el1
> + mrs x8, dbgwcr3_el1
> + mrs x7, dbgwcr2_el1
> + mrs x6, dbgwcr1_el1
> + mrs x5, dbgwcr0_el1
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +
> +1:
> + str x20, [x3, #(15 * 8)]
> + str x19, [x3, #(14 * 8)]
> + str x18, [x3, #(13 * 8)]
> + str x17, [x3, #(12 * 8)]
> + str x16, [x3, #(11 * 8)]
> + str x15, [x3, #(10 * 8)]
> + str x14, [x3, #(9 * 8)]
> + str x13, [x3, #(8 * 8)]
> + str x12, [x3, #(7 * 8)]
> + str x11, [x3, #(6 * 8)]
> + str x10, [x3, #(5 * 8)]
> + str x9, [x3, #(4 * 8)]
> + str x8, [x3, #(3 * 8)]
> + str x7, [x3, #(2 * 8)]
> + str x6, [x3, #(1 * 8)]
> + str x5, [x3, #(0 * 8)]
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + mrs x20, dbgwvr15_el1
> + mrs x19, dbgwvr14_el1
> + mrs x18, dbgwvr13_el1
> + mrs x17, dbgwvr12_el1
> + mrs x16, dbgwvr11_el1
> + mrs x15, dbgwvr10_el1
> + mrs x14, dbgwvr9_el1
> + mrs x13, dbgwvr8_el1
> + mrs x12, dbgwvr7_el1
> + mrs x11, dbgwvr6_el1
> + mrs x10, dbgwvr5_el1
> + mrs x9, dbgwvr4_el1
> + mrs x8, dbgwvr3_el1
> + mrs x7, dbgwvr2_el1
> + mrs x6, dbgwvr1_el1
> + mrs x5, dbgwvr0_el1
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +
> +1:
> + str x20, [x3, #(15 * 8)]
> + str x19, [x3, #(14 * 8)]
> + str x18, [x3, #(13 * 8)]
> + str x17, [x3, #(12 * 8)]
> + str x16, [x3, #(11 * 8)]
> + str x15, [x3, #(10 * 8)]
> + str x14, [x3, #(9 * 8)]
> + str x13, [x3, #(8 * 8)]
> + str x12, [x3, #(7 * 8)]
> + str x11, [x3, #(6 * 8)]
> + str x10, [x3, #(5 * 8)]
> + str x9, [x3, #(4 * 8)]
> + str x8, [x3, #(3 * 8)]
> + str x7, [x3, #(2 * 8)]
> + str x6, [x3, #(1 * 8)]
> + str x5, [x3, #(0 * 8)]
> +
> + mrs x21, mdccint_el1
> + str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
> .endm
>
> .macro restore_sysregs
> @@ -245,7 +442,7 @@ __kvm_hyp_code_start:
> ldp x18, x19, [x3, #112]
> ldp x20, x21, [x3, #128]
> ldp x22, x23, [x3, #144]
> - ldr x24, [x3, #160]
> + ldp x24, x25, [x3, #160]
>
> msr vmpidr_el2, x4
> msr csselr_el1, x5
> @@ -268,6 +465,198 @@ __kvm_hyp_code_start:
> msr amair_el1, x22
> msr cntkctl_el1, x23
> msr par_el1, x24
> + msr mdscr_el1, x25
> +.endm
> +
> +.macro restore_debug
> + // x2: base address for cpu context
> + // x3: tmp register
> +
> + mrs x26, id_aa64dfr0_el1
> + ubfx x24, x26, #12, #4 // Extract BRPs
> + ubfx x25, x26, #20, #4 // Extract WRPs
> + mov w26, #15
> + sub w24, w26, w24 // How many BPs to skip
> + sub w25, w26, w25 // How many WPs to skip
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + ldr x20, [x3, #(15 * 8)]
> + ldr x19, [x3, #(14 * 8)]
> + ldr x18, [x3, #(13 * 8)]
> + ldr x17, [x3, #(12 * 8)]
> + ldr x16, [x3, #(11 * 8)]
> + ldr x15, [x3, #(10 * 8)]
> + ldr x14, [x3, #(9 * 8)]
> + ldr x13, [x3, #(8 * 8)]
> + ldr x12, [x3, #(7 * 8)]
> + ldr x11, [x3, #(6 * 8)]
> + ldr x10, [x3, #(5 * 8)]
> + ldr x9, [x3, #(4 * 8)]
> + ldr x8, [x3, #(3 * 8)]
> + ldr x7, [x3, #(2 * 8)]
> + ldr x6, [x3, #(1 * 8)]
> + ldr x5, [x3, #(0 * 8)]
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + msr dbgbcr15_el1, x20
> + msr dbgbcr14_el1, x19
> + msr dbgbcr13_el1, x18
> + msr dbgbcr12_el1, x17
> + msr dbgbcr11_el1, x16
> + msr dbgbcr10_el1, x15
> + msr dbgbcr9_el1, x14
> + msr dbgbcr8_el1, x13
> + msr dbgbcr7_el1, x12
> + msr dbgbcr6_el1, x11
> + msr dbgbcr5_el1, x10
> + msr dbgbcr4_el1, x9
> + msr dbgbcr3_el1, x8
> + msr dbgbcr2_el1, x7
> + msr dbgbcr1_el1, x6
> + msr dbgbcr0_el1, x5
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + ldr x20, [x3, #(15 * 8)]
> + ldr x19, [x3, #(14 * 8)]
> + ldr x18, [x3, #(13 * 8)]
> + ldr x17, [x3, #(12 * 8)]
> + ldr x16, [x3, #(11 * 8)]
> + ldr x15, [x3, #(10 * 8)]
> + ldr x14, [x3, #(9 * 8)]
> + ldr x13, [x3, #(8 * 8)]
> + ldr x12, [x3, #(7 * 8)]
> + ldr x11, [x3, #(6 * 8)]
> + ldr x10, [x3, #(5 * 8)]
> + ldr x9, [x3, #(4 * 8)]
> + ldr x8, [x3, #(3 * 8)]
> + ldr x7, [x3, #(2 * 8)]
> + ldr x6, [x3, #(1 * 8)]
> + ldr x5, [x3, #(0 * 8)]
> +
> + adr x26, 1f
> + add x26, x26, x24, lsl #2
> + br x26
> +1:
> + msr dbgbvr15_el1, x20
> + msr dbgbvr14_el1, x19
> + msr dbgbvr13_el1, x18
> + msr dbgbvr12_el1, x17
> + msr dbgbvr11_el1, x16
> + msr dbgbvr10_el1, x15
> + msr dbgbvr9_el1, x14
> + msr dbgbvr8_el1, x13
> + msr dbgbvr7_el1, x12
> + msr dbgbvr6_el1, x11
> + msr dbgbvr5_el1, x10
> + msr dbgbvr4_el1, x9
> + msr dbgbvr3_el1, x8
> + msr dbgbvr2_el1, x7
> + msr dbgbvr1_el1, x6
> + msr dbgbvr0_el1, x5
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + ldr x20, [x3, #(15 * 8)]
> + ldr x19, [x3, #(14 * 8)]
> + ldr x18, [x3, #(13 * 8)]
> + ldr x17, [x3, #(12 * 8)]
> + ldr x16, [x3, #(11 * 8)]
> + ldr x15, [x3, #(10 * 8)]
> + ldr x14, [x3, #(9 * 8)]
> + ldr x13, [x3, #(8 * 8)]
> + ldr x12, [x3, #(7 * 8)]
> + ldr x11, [x3, #(6 * 8)]
> + ldr x10, [x3, #(5 * 8)]
> + ldr x9, [x3, #(4 * 8)]
> + ldr x8, [x3, #(3 * 8)]
> + ldr x7, [x3, #(2 * 8)]
> + ldr x6, [x3, #(1 * 8)]
> + ldr x5, [x3, #(0 * 8)]
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + msr dbgwcr15_el1, x20
> + msr dbgwcr14_el1, x19
> + msr dbgwcr13_el1, x18
> + msr dbgwcr12_el1, x17
> + msr dbgwcr11_el1, x16
> + msr dbgwcr10_el1, x15
> + msr dbgwcr9_el1, x14
> + msr dbgwcr8_el1, x13
> + msr dbgwcr7_el1, x12
> + msr dbgwcr6_el1, x11
> + msr dbgwcr5_el1, x10
> + msr dbgwcr4_el1, x9
> + msr dbgwcr3_el1, x8
> + msr dbgwcr2_el1, x7
> + msr dbgwcr1_el1, x6
> + msr dbgwcr0_el1, x5
> +
> + add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + ldr x20, [x3, #(15 * 8)]
> + ldr x19, [x3, #(14 * 8)]
> + ldr x18, [x3, #(13 * 8)]
> + ldr x17, [x3, #(12 * 8)]
> + ldr x16, [x3, #(11 * 8)]
> + ldr x15, [x3, #(10 * 8)]
> + ldr x14, [x3, #(9 * 8)]
> + ldr x13, [x3, #(8 * 8)]
> + ldr x12, [x3, #(7 * 8)]
> + ldr x11, [x3, #(6 * 8)]
> + ldr x10, [x3, #(5 * 8)]
> + ldr x9, [x3, #(4 * 8)]
> + ldr x8, [x3, #(3 * 8)]
> + ldr x7, [x3, #(2 * 8)]
> + ldr x6, [x3, #(1 * 8)]
> + ldr x5, [x3, #(0 * 8)]
> +
> + adr x26, 1f
> + add x26, x26, x25, lsl #2
> + br x26
> +1:
> + msr dbgwvr15_el1, x20
> + msr dbgwvr14_el1, x19
> + msr dbgwvr13_el1, x18
> + msr dbgwvr12_el1, x17
> + msr dbgwvr11_el1, x16
> + msr dbgwvr10_el1, x15
> + msr dbgwvr9_el1, x14
> + msr dbgwvr8_el1, x13
> + msr dbgwvr7_el1, x12
> + msr dbgwvr6_el1, x11
> + msr dbgwvr5_el1, x10
> + msr dbgwvr4_el1, x9
> + msr dbgwvr3_el1, x8
> + msr dbgwvr2_el1, x7
> + msr dbgwvr1_el1, x6
> + msr dbgwvr0_el1, x5
> +
> + ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
> + msr mdccint_el1, x21
> .endm
>
> .macro skip_32bit_state tmp, target
> @@ -282,6 +671,35 @@ __kvm_hyp_code_start:
> tbz \tmp, #12, \target
> .endm
>
> +.macro skip_debug_state tmp, target
> + ldr \tmp, [x0, #VCPU_DEBUG_FLAGS]
> + tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
> +.endm
> +
> +.macro compute_debug_state target
> + // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
> + // is set, we do a full save/restore cycle and disable trapping.
> + add x25, x0, #VCPU_CONTEXT
> +
> + // Check the state of MDSCR_EL1
> + ldr x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
> + and x26, x25, #DBG_MDSCR_KDE
> + and x25, x25, #DBG_MDSCR_MDE
> + adds xzr, x25, x26
> + b.eq 9998f // Nothing to see there
> +
> + // If any interesting bits was set, we must set the flag
> + mov x26, #KVM_ARM64_DEBUG_DIRTY
> + str x26, [x0, #VCPU_DEBUG_FLAGS]
> + b 9999f // Don't skip restore
> +
> +9998:
> + // Otherwise load the flags from memory in case we recently
> + // trapped
> + skip_debug_state x25, \target
> +9999:
> +.endm
> +
> .macro save_guest_32bit_state
> skip_32bit_state x3, 1f
>
> @@ -297,10 +715,13 @@ __kvm_hyp_code_start:
> mrs x4, dacr32_el2
> mrs x5, ifsr32_el2
> mrs x6, fpexc32_el2
> - mrs x7, dbgvcr32_el2
> stp x4, x5, [x3]
> - stp x6, x7, [x3, #16]
> + str x6, [x3, #16]
>
> + skip_debug_state x8, 2f
> + mrs x7, dbgvcr32_el2
> + str x7, [x3, #24]
> +2:
> skip_tee_state x8, 1f
>
> add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
> @@ -323,12 +744,15 @@ __kvm_hyp_code_start:
>
> add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
> ldp x4, x5, [x3]
> - ldp x6, x7, [x3, #16]
> + ldr x6, [x3, #16]
> msr dacr32_el2, x4
> msr ifsr32_el2, x5
> msr fpexc32_el2, x6
> - msr dbgvcr32_el2, x7
>
> + skip_debug_state x8, 2f
> + ldr x7, [x3, #24]
> + msr dbgvcr32_el2, x7
> +2:
> skip_tee_state x8, 1f
>
> add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
> @@ -537,6 +961,14 @@ __restore_sysregs:
> restore_sysregs
> ret
>
> +__save_debug:
> + save_debug
> + ret
> +
> +__restore_debug:
> + restore_debug
> + ret
> +
> __save_fpsimd:
> save_fpsimd
> ret
> @@ -568,6 +1000,9 @@ ENTRY(__kvm_vcpu_run)
> bl __save_fpsimd
> bl __save_sysregs
>
> + compute_debug_state 1f
> + bl __save_debug
> +1:
> activate_traps
> activate_vm
>
> @@ -579,6 +1014,10 @@ ENTRY(__kvm_vcpu_run)
>
> bl __restore_sysregs
> bl __restore_fpsimd
> +
> + skip_debug_state x3, 1f
> + bl __restore_debug
> +1:
> restore_guest_32bit_state
> restore_guest_regs
>
> @@ -595,6 +1034,10 @@ __kvm_vcpu_return:
> save_guest_regs
> bl __save_fpsimd
> bl __save_sysregs
> +
> + skip_debug_state x3, 1f
> + bl __save_debug
> +1:
> save_guest_32bit_state
>
> save_timer_state
> @@ -609,6 +1052,13 @@ __kvm_vcpu_return:
>
> bl __restore_sysregs
> bl __restore_fpsimd
> +
> + skip_debug_state x3, 1f
> + // Clear the dirty flag for the next run, as all the state has
> + // already been saved.
> + str xzr, [x0, #VCPU_DEBUG_FLAGS]
> + bl __restore_debug
> +1:
> restore_host_regs
>
> mov x0, x1
> --
> 1.8.3.4
>
let's just try to remember the fact that we overwrite the entire bitmask
here if we add more bits to that value some time:
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 8/9] arm64: KVM: implement lazy world switch for debug registers
2014-07-09 9:45 ` Christoffer Dall
@ 2014-07-09 11:18 ` Marc Zyngier
0 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-07-09 11:18 UTC (permalink / raw)
To: linux-arm-kernel
On Wed, Jul 09 2014 at 10:45:05 am BST, Christoffer Dall <christoffer.dall@linaro.org> wrote:
> On Fri, Jun 20, 2014 at 02:00:06PM +0100, Marc Zyngier wrote:
>> Implement switching of the debug registers. While the number
>> of registers is massive, CPUs usually don't implement them all
>> (A57 has 6 breakpoints and 4 watchpoints, which gives us a total
>> of 22 registers "only").
>>
>> Also, we only save/restore them when MDSCR_EL1 has debug enabled,
>> or when we've flagged the debug registers as dirty. It means that
>> most of the time, we only save/restore MDSCR_EL1.
>>
>> Reviewed-by: Anup Patel <anup.patel@linaro.org>
>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
>> ---
>> arch/arm64/kernel/asm-offsets.c | 1 +
>> arch/arm64/kvm/hyp.S | 462 +++++++++++++++++++++++++++++++++++++++-
>> 2 files changed, 457 insertions(+), 6 deletions(-)
>>
[...]
>> @@ -609,6 +1052,13 @@ __kvm_vcpu_return:
>>
>> bl __restore_sysregs
>> bl __restore_fpsimd
>> +
>> + skip_debug_state x3, 1f
>> + // Clear the dirty flag for the next run, as all the state has
>> + // already been saved.
>> + str xzr, [x0, #VCPU_DEBUG_FLAGS]
>> + bl __restore_debug
>> +1:
>> restore_host_regs
>>
>> mov x0, x1
>> --
>> 1.8.3.4
>>
>
> let's just try to remember the fact that we overwrite the entire bitmask
> here if we add more bits to that value some time:
I'll add a comment to that effect.
> Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Thanks!
M.
--
Without deviation from the norm, progress is not possible.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v3 9/9] arm64: KVM: enable trapping of all debug registers
2014-06-20 12:59 [PATCH v3 0/9] arm64: KVM: debug infrastructure support Marc Zyngier
` (7 preceding siblings ...)
2014-06-20 13:00 ` [PATCH v3 8/9] arm64: KVM: implement lazy world switch for " Marc Zyngier
@ 2014-06-20 13:00 ` Marc Zyngier
8 siblings, 0 replies; 19+ messages in thread
From: Marc Zyngier @ 2014-06-20 13:00 UTC (permalink / raw)
To: linux-arm-kernel
Enable trapping of the debug registers, preventing the guests to
mess with the host state (and allowing guests to use the debug
infrastructure as well).
Reviewed-by: Anup Patel <anup.patel@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
arch/arm64/kvm/hyp.S | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 727087c..e36ca91 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -777,6 +777,14 @@ __kvm_hyp_code_start:
mrs x2, mdcr_el2
and x2, x2, #MDCR_EL2_HPMN_MASK
orr x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
+ orr x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
+
+ // Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
+ // if not dirty.
+ ldr x3, [x0, #VCPU_DEBUG_FLAGS]
+ tbnz x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
+ orr x2, x2, #MDCR_EL2_TDA
+1:
msr mdcr_el2, x2
.endm
--
1.8.3.4
^ permalink raw reply related [flat|nested] 19+ messages in thread