On Wed, Jan 17, 2018 at 05:52:21PM +0000, Julien Thierry wrote:

On 12/01/18 12:07, Christoffer Dall wrote:

quoted

We are about to defer saving and restoring some groups of system
registers to vcpu_put and vcpu_load on supported systems.  This means
that we need some infrastructure to access system registes which
supports either accessing the memory backing of the register or directly
accessing the system registers, depending on the state of the system
when we access the register.

We do this by defining a set of read/write accessors for each system
register, and letting each system register be defined as "immediate" or
"deferrable".  Immediate registers are always saved/restored in the
world-switch path, but deferrable registers are only saved/restored in
vcpu_put/vcpu_load when supported and sysregs_loaded_on_cpu will be set
in that case.

The patch is fine, however I'd suggest adding a comment in the pointing out
that the IMMEDIATE/DEFERRABLE apply to save/restore to the vcpu struct.
Instinctively I would expect the deferrable/immediate to apply to the actual
hardware register access, so a comment would prevent people like me to get
on the wrong track.

I tried to explain that a bit in the first sentence of the commit
message, but I can try to make it more clear that we introduce
terminology.

quoted

Not that we don't use the deferred mechanism yet in this patch, but only
introduce infrastructure.  This is to improve convenience of review in
the subsequent patches where it is clear which registers become
deferred.

 [ Most of this logic was contributed by Marc Zyngier ]

Signed-off-by: Marc Zyngier <redacted>
Signed-off-by: Christoffer Dall <redacted>

Reviewed-by: Julien Thierry <redacted>

quoted

---
 arch/arm64/include/asm/kvm_host.h |   8 +-
 arch/arm64/kvm/sys_regs.c         | 160 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 166 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 91272c35cc36..4b5ef82f6bdb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h

@@ -281,6 +281,10 @@ struct kvm_vcpu_arch {
 	/* Detect first run of a vcpu */
 	bool has_run_once;
+
+	/* True when deferrable sysregs are loaded on the physical CPU,
+	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+	bool sysregs_loaded_on_cpu;
 };
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)

@@ -293,8 +297,8 @@ struct kvm_vcpu_arch {
  */
 #define __vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
-#define vcpu_read_sys_reg(v,r)	__vcpu_sys_reg(v,r)
-#define vcpu_write_sys_reg(v,r,n)	do { __vcpu_sys_reg(v,r) = n; } while (0)
+u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg);
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, int reg, u64 val);
 /*
  * CP14 and CP15 live in the same array, as they are backed by the

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 96398d53b462..9d353a6a55c9 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c

@@ -35,6 +35,7 @@
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
+#include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/perf_event.h>
 #include <asm/sysreg.h>

@@ -76,6 +77,165 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
+struct sys_reg_accessor {
+	u64	(*rdsr)(struct kvm_vcpu *, int);
+	void	(*wrsr)(struct kvm_vcpu *, int, u64);

Nit:

Why use a signed integer for the register index argument?

The type name is short? ;)  No particular reason, could be an unsigned
int, but I don't think it matters here does it?

quoted

+};
+
+#define DECLARE_IMMEDIATE_SR(i)						\
+	static u64 __##i##_read(struct kvm_vcpu *vcpu, int r)		\
+	{								\
+		return __vcpu_sys_reg(vcpu, r);				\
+	}								\
+									\
+	static void __##i##_write(struct kvm_vcpu *vcpu, int r, u64 v)	\
+	{								\
+		__vcpu_sys_reg(vcpu, r) = v;				\
+	}								\
+
+#define DECLARE_DEFERRABLE_SR(i, s)					\
+	static u64 __##i##_read(struct kvm_vcpu *vcpu, int r)		\
+	{								\
+		if (vcpu->arch.sysregs_loaded_on_cpu) {			\
+			WARN_ON(kvm_arm_get_running_vcpu() != vcpu);	\
+			return read_sysreg_s((s));			\
+		}							\
+		return __vcpu_sys_reg(vcpu, r);				\
+	}								\
+									\
+	static void __##i##_write(struct kvm_vcpu *vcpu, int r, u64 v)	\
+	{								\
+		if (vcpu->arch.sysregs_loaded_on_cpu) {			\
+			WARN_ON(kvm_arm_get_running_vcpu() != vcpu);	\
+			write_sysreg_s(v, (s));				\
+		} else {						\
+			__vcpu_sys_reg(vcpu, r) = v;			\
+		}							\
+	}								\
+
+
+#define SR_HANDLER_RANGE(i,e)						\
+	[i ... e] =  (struct sys_reg_accessor) {			\
+		.rdsr = __##i##_read,					\
+		.wrsr = __##i##_write,					\

Nit:
Could we have __vcpu_##i##_read and __vcpu_##i##_write?

They don't necessarily read from the vcpu do they?

Unrelated: I also thought about just having a single function a switch
statement instead, which may make it easier to follow the code as there
would be no macros generating functions, but it would be slightly less
declarative.

For example:

u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
{
	if (!vcpu->arch.sysregs_loaded_on_cpu)
		goto immediate_read;
	
	/*
	 * All system registers listed in the switch are deferred
	 * save/restored on VHE systems.
	 */
	switch (reg) {
	case CSSELR_EL1:	return read_sysreg_s(SYS_CSSELR_EL1));
	case SCTLR_EL1:		return read_sysreg_s(sctlr_EL12));
	case ACTLR_EL1:		return read_sysreg_s(SYS_ACTLR_EL1));
	case CPACR_EL1:		return read_sysreg_s(cpacr_EL12));
	case TTBR0_EL1:		return read_sysreg_s(ttbr0_EL12));
	case TTBR1_EL1:		return read_sysreg_s(ttbr1_EL12));
	case TCR_EL1:		return read_sysreg_s(tcr_EL12));
	case ESR_EL1:		return read_sysreg_s(esr_EL12));
	case AFSR0_EL1:		return read_sysreg_s(afsr0_EL12));
	case AFSR1_EL1:		return read_sysreg_s(afsr1_EL12));
	case FAR_EL1:		return read_sysreg_s(far_EL12));
	case MAIR_EL1:		return read_sysreg_s(mair_EL12));
	case VBAR_EL1:		return read_sysreg_s(vbar_EL12));
	case CONTEXTIDR_EL1:	return read_sysreg_s(contextidr_EL12));
	case TPIDR_EL0:		return read_sysreg_s(SYS_TPIDR_EL0));
	case TPIDRRO_EL0:	return read_sysreg_s(SYS_TPIDRRO_EL0));
	case TPIDR_EL1:		return read_sysreg_s(SYS_TPIDR_EL1));
	case AMAIR_EL1:		return read_sysreg_s(amair_EL12));
	case CNTKCTL_EL1:	return read_sysreg_s(cntkctl_EL12));
	case PAR_EL1:		return read_sysreg_s(SYS_PAR_EL1));
	case DACR32_EL2:	return read_sysreg_s(SYS_DACR32_EL2));
	case IFSR32_EL2:	return read_sysreg_s(SYS_IFSR32_EL2));
	case DBGVCR32_EL2:	return read_sysreg_s(SYS_DBGVCR32_EL2));
	}

immediate_read:
	return __vcpu_sys_reg(vcpu, reg);
}

Since you're having a look at this, what are your thoughts?

Marc, what's your preference?

Thanks,
-Christoffer

quoted

+	}
+
+#define SR_HANDLER(i)	SR_HANDLER_RANGE(i, i)
+
+static void bad_sys_reg(int reg)
+{
+	WARN_ONCE(1, "Bad system register access %d\n", reg);
+}
+
+static u64 __default_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
+{
+	bad_sys_reg(reg);
+	return 0;
+}
+
+static void __default_write_sys_reg(struct kvm_vcpu *vcpu, int reg, u64 val)
+{
+	bad_sys_reg(reg);
+}
+
+/* Ordered as in enum vcpu_sysreg */
+DECLARE_IMMEDIATE_SR(MPIDR_EL1);
+DECLARE_IMMEDIATE_SR(CSSELR_EL1);
+DECLARE_IMMEDIATE_SR(SCTLR_EL1);
+DECLARE_IMMEDIATE_SR(ACTLR_EL1);
+DECLARE_IMMEDIATE_SR(CPACR_EL1);
+DECLARE_IMMEDIATE_SR(TTBR0_EL1);
+DECLARE_IMMEDIATE_SR(TTBR1_EL1);
+DECLARE_IMMEDIATE_SR(TCR_EL1);
+DECLARE_IMMEDIATE_SR(ESR_EL1);
+DECLARE_IMMEDIATE_SR(AFSR0_EL1);
+DECLARE_IMMEDIATE_SR(AFSR1_EL1);
+DECLARE_IMMEDIATE_SR(FAR_EL1);
+DECLARE_IMMEDIATE_SR(MAIR_EL1);
+DECLARE_IMMEDIATE_SR(VBAR_EL1);
+DECLARE_IMMEDIATE_SR(CONTEXTIDR_EL1);
+DECLARE_IMMEDIATE_SR(TPIDR_EL0);
+DECLARE_IMMEDIATE_SR(TPIDRRO_EL0);
+DECLARE_IMMEDIATE_SR(TPIDR_EL1);
+DECLARE_IMMEDIATE_SR(AMAIR_EL1);
+DECLARE_IMMEDIATE_SR(CNTKCTL_EL1);
+DECLARE_IMMEDIATE_SR(PAR_EL1);
+DECLARE_IMMEDIATE_SR(MDSCR_EL1);
+DECLARE_IMMEDIATE_SR(MDCCINT_EL1);
+DECLARE_IMMEDIATE_SR(PMCR_EL0);
+DECLARE_IMMEDIATE_SR(PMSELR_EL0);
+DECLARE_IMMEDIATE_SR(PMEVCNTR0_EL0);
+/* PMEVCNTR30_EL0 */
+DECLARE_IMMEDIATE_SR(PMCCNTR_EL0);
+DECLARE_IMMEDIATE_SR(PMEVTYPER0_EL0);
+/* PMEVTYPER30_EL0 */
+DECLARE_IMMEDIATE_SR(PMCCFILTR_EL0);
+DECLARE_IMMEDIATE_SR(PMCNTENSET_EL0);
+DECLARE_IMMEDIATE_SR(PMINTENSET_EL1);
+DECLARE_IMMEDIATE_SR(PMOVSSET_EL0);
+DECLARE_IMMEDIATE_SR(PMSWINC_EL0);
+DECLARE_IMMEDIATE_SR(PMUSERENR_EL0);
+DECLARE_IMMEDIATE_SR(DACR32_EL2);
+DECLARE_IMMEDIATE_SR(IFSR32_EL2);
+DECLARE_IMMEDIATE_SR(FPEXC32_EL2);
+DECLARE_IMMEDIATE_SR(DBGVCR32_EL2);
+
+static const struct sys_reg_accessor sys_reg_accessors[NR_SYS_REGS] = {
+	[0 ... NR_SYS_REGS - 1] = {
+		.rdsr = __default_read_sys_reg,
+		.wrsr = __default_write_sys_reg,
+	},
+
+	SR_HANDLER(MPIDR_EL1),
+	SR_HANDLER(CSSELR_EL1),
+	SR_HANDLER(SCTLR_EL1),
+	SR_HANDLER(ACTLR_EL1),
+	SR_HANDLER(CPACR_EL1),
+	SR_HANDLER(TTBR0_EL1),
+	SR_HANDLER(TTBR1_EL1),
+	SR_HANDLER(TCR_EL1),
+	SR_HANDLER(ESR_EL1),
+	SR_HANDLER(AFSR0_EL1),
+	SR_HANDLER(AFSR1_EL1),
+	SR_HANDLER(FAR_EL1),
+	SR_HANDLER(MAIR_EL1),
+	SR_HANDLER(VBAR_EL1),
+	SR_HANDLER(CONTEXTIDR_EL1),
+	SR_HANDLER(TPIDR_EL0),
+	SR_HANDLER(TPIDRRO_EL0),
+	SR_HANDLER(TPIDR_EL1),
+	SR_HANDLER(AMAIR_EL1),
+	SR_HANDLER(CNTKCTL_EL1),
+	SR_HANDLER(PAR_EL1),
+	SR_HANDLER(MDSCR_EL1),
+	SR_HANDLER(MDCCINT_EL1),
+	SR_HANDLER(PMCR_EL0),
+	SR_HANDLER(PMSELR_EL0),
+	SR_HANDLER_RANGE(PMEVCNTR0_EL0, PMEVCNTR30_EL0),
+	SR_HANDLER(PMCCNTR_EL0),
+	SR_HANDLER_RANGE(PMEVTYPER0_EL0, PMEVTYPER30_EL0),
+	SR_HANDLER(PMCCFILTR_EL0),
+	SR_HANDLER(PMCNTENSET_EL0),
+	SR_HANDLER(PMINTENSET_EL1),
+	SR_HANDLER(PMOVSSET_EL0),
+	SR_HANDLER(PMSWINC_EL0),
+	SR_HANDLER(PMUSERENR_EL0),
+	SR_HANDLER(DACR32_EL2),
+	SR_HANDLER(IFSR32_EL2),
+	SR_HANDLER(FPEXC32_EL2),
+	SR_HANDLER(DBGVCR32_EL2),
+};
+
+u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
+{
+	return sys_reg_accessors[reg].rdsr(vcpu, reg);
+}
+
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, int reg, u64 val)
+{
+	sys_reg_accessors[reg].wrsr(vcpu, reg, val);
+}
+
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
 static u32 cache_levels;

-- 
Julien Thierry