arm64: Nested virtualization support
v6 cover arm64: Nested virtualization support
This is v6 of the nested virt support series, fixing an endianess bug in the maintenance IRQ DT code, and rebasing.
Changelog below.
========================================================
Thanks to the imperturbable efforts from Marc, arm64 support for nested virtualization has now reached the mainline kernel, which means the respective kvmtool support should now be ready as well.
Patch 1 introduces the new "--nested" command line option, to let the VCPUs start in EL2. To allow KVM guests running in such a guest, we also need VGIC support, which patch 2 allows by setting the maintenance IRQ. Patch 3 to 6 are picked from Marc's repo, and allow to set the arch timer offset, enable non-VHE guests (at the cost of losing recursive nested virtualisation), and also advertise the virtual EL2 timer IRQ.
Tested on the FVP (with some good deal of patience) and QEMU.
Cheers,
Andre
Changelog v5 ... v6:
- rebase / drop header update patch (already merged)
- fix endianness bug in DT maintenance IRQ description
Changelog v4 ... v5:
- bump kernel headers to v6.19-rc6
- print a warning if --e2h0 is given without --nested
- fail if the maintenance IRQ setting attribute is not supported
- add tags
Changelog v3 ... v4:
- pass kvm pointer to gic__generate_fdt_nodes()
- use macros for PPI offset and DT type identifier
- properly calculate DT interrupt flags value
- add patch 7 to fix virtio endianess issues
- CAPITALISE verbs in commit message
Changelog v2 ... v3:
- adjust^Wreplace commit messages for E2H0 and counter-offset patch
- check for KVM_CAP_ARM_EL2_E2H0 when --e2h0 is requested
- update kernel headers to v6.16 release
Changelog v1 ... 2:
- add three patches from Marc:
- add --e2h0 command line option
- add --counter-offset command line option
- advertise all five arch timer interrupts in DT
Andre Przywara (2):
arm64: Initial nested virt support
arm64: nested: Add support for setting maintenance IRQ
Marc Zyngier (4):
arm64: Add counter offset control
arm64: Add FEAT_E2H0 support
arm64: Generate HYP timer interrupt specifiers
arm64: Handle virtio endianness reset when running nested
arm64/arm-cpu.c | 6 +-- arm64/fdt.c | 5 ++- arm64/gic.c | 29 ++++++++++++- arm64/include/kvm/gic.h | 2 +- arm64/include/kvm/kvm-config-arch.h | 11 ++++- arm64/include/kvm/kvm-cpu-arch.h | 5 ++- arm64/include/kvm/timer.h | 2 +- arm64/kvm-cpu.c | 64 ++++++++++++++++++++++++----- arm64/kvm.c | 20 +++++++++ arm64/timer.c | 29 ++++++------- 10 files changed, 133 insertions(+), 40 deletions(-)
Signature · 1 line
2.47.3
PATCH v6 1/6 arm64: Initial nested virt support
The ARMv8.3 architecture update includes support for nested virtualization. Allow the user to specify "--nested" to start a guest in (virtual) EL2 instead of EL1.
This will also change the PSCI conduit from HVC to SMC in the device tree.
--- arm64/fdt.c | 5 ++++- arm64/include/kvm/kvm-config-arch.h | 5 ++++- arm64/kvm-cpu.c | 12 +++++++++++- 3 files changed, 19 insertions(+), 3 deletions(-)
arm64/fdt.c +4 -1
@@ -205,7 +205,10 @@ static int setup_fdt(struct kvm *kvm)_FDT (fdt_property_string (fdt,"compatible" ,"arm,psci" )); fns = &psci_0_1_fns; } -_FDT (fdt_property_string (fdt,"method" ,"hvc" )); +if (kvm->cfg.arch.nested_virt) +_FDT (fdt_property_string (fdt,"method" ,"smc" )); +else +_FDT (fdt_property_string (fdt,"method" ,"hvc" ));_FDT (fdt_property_cell (fdt,"cpu_suspend" , fns->cpu_suspend));_FDT (fdt_property_cell (fdt,"cpu_off" , fns->cpu_off));_FDT (fdt_property_cell (fdt,"cpu_on" , fns->cpu_on));
arm64/include/kvm/kvm-config-arch.h +4 -1
@@ -10,6 +10,7 @@ struct kvm_config_arch {bool aarch32_guest;bool has_pmuv3;bool mte_disabled; +bool nested_virt;u64 kaslr_seed;enum irqchip_type irqchip;u64 fw_addr;
@@ -57,6 +58,8 @@ int sve_vl_parser(const struct option *opt, const char *arg, int unset); "Type of interrupt controller to emulate in the guest", \ irqchip_parser, NULL), \ OPT_U64('\0', "firmware-address", &(cfg)->fw_addr, \ - "Address where firmware should be loaded"), + "Address where firmware should be loaded"), \ + OPT_BOOLEAN('\0', "nested", &(cfg)->nested_virt, \ + "Start VCPUs in EL2 (for nested virt)"),#endif /* ARM_COMMON__KVM_CONFIG_ARCH_H */
arm64/kvm-cpu.c +11 -1
@@ -71,6 +71,12 @@ static void kvm_cpu__select_features(struct kvm *kvm, struct kvm_vcpu_init *init/* Enable SVE if available */ if (kvm__supports_extension (kvm,KVM_CAP_ARM_SVE )) init->features[0 ] |=1UL <<KVM_ARM_VCPU_SVE ; + +if (kvm->cfg.arch.nested_virt) { +if (!kvm__supports_extension (kvm,KVM_CAP_ARM_EL2 )) +die ("EL2 (nested virt) is not supported" ); + init->features[0 ] |=1UL <<KVM_ARM_VCPU_HAS_EL2 ; + } }static int vcpu_configure_sve (struct kvm_cpu *vcpu)
@@ -313,7 +319,11 @@ static void reset_vcpu_aarch64(struct kvm_cpu *vcpu) reg.addr = (u64)&data;/* pstate = all interrupts masked */ - data =PSR_D_BIT |PSR_A_BIT |PSR_I_BIT |PSR_F_BIT | PSR_MODE_EL1h; + data =PSR_D_BIT |PSR_A_BIT |PSR_I_BIT |PSR_F_BIT ; +if (vcpu->kvm->cfg.arch.nested_virt) + data |= PSR_MODE_EL2h; +else + data |= PSR_MODE_EL1h; reg.id =ARM64_CORE_REG (regs.pstate);if (ioctl (vcpu->vcpu_fd,KVM_SET_ONE_REG , ®) <0 )die_perror ("KVM_SET_ONE_REG failed (spsr[EL1])" );
Signature · 1 line
2.47.3
PATCH v6 2/6 arm64: nested: Add support for setting maintenance IRQ
In reply to Andre PrzywaraUses the new VGIC KVM device attribute to set the maintenance IRQ. This is fixed to use PPI 9, as a platform decision made by kvmtool, matching the SBSA recommendation.
Use the opportunity to pass the kvm pointer to gic__generate_fdt_nodes(), as this simplifies the call and allows us access to the nested_virt config variable on the way.
--- arm64/arm-cpu.c | 2 +- arm64/gic.c | 29 +++++++++++++++++++++++++++-- arm64/include/kvm/gic.h | 2 +- 3 files changed, 29 insertions(+), 4 deletions(-)
arm64/arm-cpu.c +1 -1
@@ -14,7 +14,7 @@ static void generate_fdt_nodes(void *fdt, struct kvm *kvm) {int timer_interrupts[4 ] = {13 ,14 ,11 ,10 }; -gic__generate_fdt_nodes (fdt, kvm->cfg.arch.irqchip); +gic__generate_fdt_nodes (fdt, kvm);timer__generate_fdt_nodes (fdt, kvm, timer_interrupts);pmu__generate_fdt_nodes (fdt, kvm); }
arm64/gic.c +27 -2
@@ -11,6 +11,8 @@#define IRQCHIP_GIC 0 +#define GIC_MAINT_IRQ 9 +static int gic_fd =-1 ;static u64 gic_redists_base;static u64 gic_redists_size;
@@ -302,10 +304,15 @@ static int gic__init_gic(struct kvm *kvm)int lines =irq__get_nr_allocated_lines ();u32 nr_irqs =ALIGN (lines,32 ) +GIC_SPI_IRQ_BASE ; +u32 maint_irq =GIC_PPI_IRQ_BASE +GIC_MAINT_IRQ ;struct kvm_device_attr nr_irqs_attr = { .group =KVM_DEV_ARM_VGIC_GRP_NR_IRQS , .addr = (u64 )(unsigned long )&nr_irqs, }; +struct kvm_device_attr maint_irq_attr = { + .group =KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ , + .addr = (u64 )(unsigned long )&maint_irq, + };struct kvm_device_attr vgic_init_attr = { .group =KVM_DEV_ARM_VGIC_GRP_CTRL , .attr =KVM_DEV_ARM_VGIC_CTRL_INIT ,
@@ -325,6 +332,16 @@ static int gic__init_gic(struct kvm *kvm)return ret; } +if (kvm->cfg.arch.nested_virt) { + ret =ioctl (gic_fd,KVM_HAS_DEVICE_ATTR , &maint_irq_attr); +if (!ret) + ret =ioctl (gic_fd,KVM_SET_DEVICE_ATTR , &maint_irq_attr); +if (ret) { +pr_err ("could not set maintenance IRQ\n" ); +return ret; + } + } +irq__routing_init (kvm);if (!ioctl (gic_fd,KVM_HAS_DEVICE_ATTR , &vgic_init_attr)) {
@@ -342,7 +359,7 @@ static int gic__init_gic(struct kvm *kvm) }late_init (gic__init_gic) -void gic__generate_fdt_nodes(void *fdt, enum irqchip_type type) +void gic__generate_fdt_nodes(void *fdt, struct kvm *kvm) {const char *compatible, *msi_compatible =NULL ;u64 msi_prop[2 ];
@@ -350,8 +367,12 @@ void gic__generate_fdt_nodes(void *fdt, enum irqchip_type type)cpu_to_fdt64 (ARM_GIC_DIST_BASE ),cpu_to_fdt64 (ARM_GIC_DIST_SIZE ), 0, 0, /* to be filled */ }; +u32 maint_irq[] = { +cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ),cpu_to_fdt32 (GIC_MAINT_IRQ ), +cpu_to_fdt32 (gic__get_fdt_irq_cpumask (kvm) |IRQ_TYPE_LEVEL_HIGH ) + }; -switch (type) { +switch (kvm->cfg.arch.irqchip) {case IRQCHIP_GICV2M : msi_compatible ="arm,gic-v2m-frame" ;/* fall-through */
@@ -377,6 +398,10 @@ void gic__generate_fdt_nodes(void *fdt, enum irqchip_type type)_FDT (fdt_property_cell (fdt,"#interrupt-cells" ,GIC_FDT_IRQ_NUM_CELLS ));_FDT (fdt_property (fdt,"interrupt-controller" ,NULL ,0 ));_FDT (fdt_property (fdt,"reg" , reg_prop,sizeof (reg_prop))); +if (kvm->cfg.arch.nested_virt) { +_FDT (fdt_property (fdt,"interrupts" , maint_irq, +sizeof (maint_irq))); + }_FDT (fdt_property_cell (fdt,"phandle" ,PHANDLE_GIC ));_FDT (fdt_property_cell (fdt,"#address-cells" ,2 ));_FDT (fdt_property_cell (fdt,"#size-cells" ,2 ));
arm64/include/kvm/gic.h +1 -1
@@ -36,7 +36,7 @@ struct kvm;int gic__alloc_irqnum (void );int gic__create (struct kvm *kvm,enum irqchip_type type);int gic__create_gicv2m_frame (struct kvm *kvm,u64 msi_frame_addr); -void gic__generate_fdt_nodes (void *fdt,enum irqchip_type type); +void gic__generate_fdt_nodes (void *fdt,struct kvm *kvm);u32 gic__get_fdt_irq_cpumask (struct kvm *kvm); int gic__add_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd,
Signature · 1 line
2.47.3
PATCH v6 3/6 arm64: Add counter offset control
In reply to Andre PrzywaraFrom: Marc Zyngier <[email protected]>
KVM allows the offsetting of the global counter in order to help with migration of a VM. This offset applies cumulatively with the offsets provided by the architecture.
Although kvmtool doesn't provide a way to migrate a VM, controlling this offset is useful to test the timer subsystem.
Add the command line option --counter-offset to allow setting this value when creating a VM.
--- arm64/include/kvm/kvm-config-arch.h | 3 +++ arm64/kvm.c | 17 +++++++++++++++++ 2 files changed, 20 insertions(+)
arm64/include/kvm/kvm-config-arch.h +3 -0
@@ -14,6 +14,7 @@ struct kvm_config_arch {u64 kaslr_seed;enum irqchip_type irqchip;u64 fw_addr; +u64 counter_offset;unsigned int sve_max_vq;bool no_pvtime; };
@@ -59,6 +60,8 @@ int sve_vl_parser(const struct option *opt, const char *arg, int unset); irqchip_parser, NULL), \OPT_U64 ('\0' ,"firmware-address" , &(cfg)->fw_addr, \"Address where firmware should be loaded" ), \ +OPT_U64 ('\0' ,"counter-offset" , &(cfg)->counter_offset, \ +"Specify the counter offset, defaulting to 0" ), \OPT_BOOLEAN ('\0' ,"nested" , &(cfg)->nested_virt, \ "Start VCPUs in EL2 (for nested virt)"),
arm64/kvm.c +17 -0
@@ -119,6 +119,22 @@ static void kvm__arch_enable_mte(struct kvm *kvm)pr_debug ("MTE capability enabled" ); } +static void kvm__arch_set_counter_offset (struct kvm *kvm) +{ +struct kvm_arm_counter_offset offset = { + .counter_offset = kvm->cfg.arch.counter_offset, + }; + +if (!kvm->cfg.arch.counter_offset) +return ; + +if (!kvm__supports_extension (kvm,KVM_CAP_COUNTER_OFFSET )) +die ("No support for global counter offset" ); + +if (ioctl (kvm->vm_fd,KVM_ARM_SET_COUNTER_OFFSET , &offset)) +die_perror ("KVM_ARM_SET_COUNTER_OFFSET" ); +} +void kvm__arch_init (struct kvm *kvm) {/* Create the virtual GIC. */
@@ -126,6 +142,7 @@ void kvm__arch_init(struct kvm *kvm)die ("Failed to create virtual GIC" );kvm__arch_enable_mte (kvm); +kvm__arch_set_counter_offset (kvm); }static u64 kvm__arch_get_payload_region_size (struct kvm *kvm)
Signature · 1 line
2.47.3
PATCH v6 4/6 arm64: Add FEAT_E2H0 support
In reply to Andre PrzywaraFrom: Marc Zyngier <[email protected]>
The --nested option allows a guest to boot at EL2 without FEAT_E2H0 (i.e. mandating VHE support). While this is great for "modern" operating systems and hypervisors, a few legacy guests are stuck in a distant past.
To support those, add the --e2h0 command line option, that exposes FEAT_E2H0 to the guest, at the expense of a number of other features, such as FEAT_NV2. This is conditioned on the host itself supporting FEAT_E2H0.
--- arm64/include/kvm/kvm-config-arch.h | 5 ++++- arm64/kvm-cpu.c | 5 +++++ arm64/kvm.c | 3 +++ 3 files changed, 12 insertions(+), 1 deletion(-)
arm64/include/kvm/kvm-config-arch.h +4 -1
@@ -11,6 +11,7 @@ struct kvm_config_arch {bool has_pmuv3;bool mte_disabled;bool nested_virt; +bool e2h0;u64 kaslr_seed;enum irqchip_type irqchip;u64 fw_addr;
@@ -63,6 +64,8 @@ int sve_vl_parser(const struct option *opt, const char *arg, int unset);OPT_U64 ('\0' ,"counter-offset" , &(cfg)->counter_offset, \"Specify the counter offset, defaulting to 0" ), \OPT_BOOLEAN ('\0' ,"nested" , &(cfg)->nested_virt, \ - "Start VCPUs in EL2 (for nested virt)"), +"Start VCPUs in EL2 (for nested virt)" ), \ +OPT_BOOLEAN ('\0' ,"e2h0" , &(cfg)->e2h0, \ + "Create guest without VHE support"), #endif /* ARM_COMMON__KVM_CONFIG_ARCH_H */
arm64/kvm-cpu.c +5 -0
@@ -76,6 +76,11 @@ static void kvm_cpu__select_features(struct kvm *kvm, struct kvm_vcpu_init *initif (!kvm__supports_extension (kvm,KVM_CAP_ARM_EL2 ))die ("EL2 (nested virt) is not supported" ); init->features[0 ] |=1UL <<KVM_ARM_VCPU_HAS_EL2 ; +if (kvm->cfg.arch.e2h0) { +if (!kvm__supports_extension (kvm,KVM_CAP_ARM_EL2_E2H0 )) +die ("FEAT_E2H0 is not supported" ); + init->features[0 ] |=1UL <<KVM_ARM_VCPU_HAS_EL2_E2H0 ; + } } }
arm64/kvm.c +3 -0
@@ -440,6 +440,9 @@ void kvm__arch_validate_cfg(struct kvm *kvm) kvm->cfg.ram_addr + kvm->cfg.ram_size > SZ_4G) {die ("RAM extends above 4GB" ); } + +if (kvm->cfg.arch.e2h0 && !kvm->cfg.arch.nested_virt) +pr_warning ("--e2h0 requires --nested, ignoring" ); }u64 kvm__arch_default_ram_address (void )
Signature · 1 line
2.47.3
PATCH v6 5/6 arm64: Generate HYP timer interrupt specifiers
In reply to Andre PrzywaraFrom: Marc Zyngier <[email protected]>
FEAT_VHE introduced a non-secure EL2 virtual timer, along with its interrupt line. Consequently the arch timer DT binding introduced a fifth interrupt to communicate this interrupt number.
Refactor the interrupts property generation code to deal with a variable number of interrupts, and forward five interrupts instead of four in case nested virt is enabled.
--- arm64/arm-cpu.c | 4 +--- arm64/include/kvm/timer.h | 2 +- arm64/timer.c | 29 ++++++++++++----------------- 3 files changed, 14 insertions(+), 21 deletions(-)
arm64/arm-cpu.c +1 -3
@@ -12,10 +12,8 @@static void generate_fdt_nodes (void *fdt,struct kvm *kvm) { -int timer_interrupts[4 ] = {13 ,14 ,11 ,10 }; -gic__generate_fdt_nodes (fdt, kvm); -timer__generate_fdt_nodes (fdt, kvm, timer_interrupts); +timer__generate_fdt_nodes (fdt, kvm);pmu__generate_fdt_nodes (fdt, kvm); }
arm64/include/kvm/timer.h +1 -1
@@ -1,6 +1,6 @@#ifndef ARM_COMMON__TIMER_H #define ARM_COMMON__TIMER_H -void timer__generate_fdt_nodes (void *fdt,struct kvm *kvm,int *irqs); +void timer__generate_fdt_nodes (void *fdt,struct kvm *kvm);#endif /* ARM_COMMON__TIMER_H */
arm64/timer.c +12 -17
@@ -5,31 +5,26 @@#include "kvm/timer.h" #include "kvm/util.h" -void timer__generate_fdt_nodes (void *fdt,struct kvm *kvm,int *irqs) +void timer__generate_fdt_nodes (void *fdt,struct kvm *kvm) {const char compatible[] ="arm,armv8-timer\0arm,armv7-timer" ;u32 cpu_mask =gic__get_fdt_irq_cpumask (kvm); -u32 irq_prop[] = { -cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ), -cpu_to_fdt32 (irqs[0 ]), -cpu_to_fdt32 (cpu_mask |IRQ_TYPE_LEVEL_LOW ), +int irqs[5 ] = {13 ,14 ,11 ,10 ,12 }; +int nr =ARRAY_SIZE (irqs); +u32 irq_prop[nr *3 ]; -cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ), -cpu_to_fdt32 (irqs[1 ]), -cpu_to_fdt32 (cpu_mask |IRQ_TYPE_LEVEL_LOW ), +if (!kvm->cfg.arch.nested_virt) + nr--; -cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ), -cpu_to_fdt32 (irqs[2 ]), -cpu_to_fdt32 (cpu_mask |IRQ_TYPE_LEVEL_LOW ), - -cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ), -cpu_to_fdt32 (irqs[3 ]), -cpu_to_fdt32 (cpu_mask |IRQ_TYPE_LEVEL_LOW ), - }; +for (int i =0 ; i < nr; i++) { + irq_prop[i *3 +0 ] =cpu_to_fdt32 (GIC_FDT_IRQ_TYPE_PPI ); + irq_prop[i *3 +1 ] =cpu_to_fdt32 (irqs[i]); + irq_prop[i *3 +2 ] =cpu_to_fdt32 (cpu_mask |IRQ_TYPE_LEVEL_LOW ); + }_FDT (fdt_begin_node (fdt,"timer" ));_FDT (fdt_property (fdt,"compatible" , compatible,sizeof (compatible))); -_FDT (fdt_property (fdt,"interrupts" , irq_prop,sizeof (irq_prop))); +_FDT (fdt_property (fdt,"interrupts" , irq_prop, nr *3 *sizeof (irq_prop[0 ])));_FDT (fdt_property (fdt,"always-on" ,NULL ,0 ));if (kvm->cfg.arch.force_cntfrq >0 )_FDT (fdt_property_cell (fdt,"clock-frequency" , kvm->cfg.arch.force_cntfrq));
Signature · 1 line
2.47.3
PATCH v6 6/6 arm64: Handle virtio endianness reset when running nested
In reply to Andre PrzywaraFrom: Marc Zyngier <[email protected]>
When running an EL2 guest, we need to make sure we don't sample SCTLR_EL1 to work out the virtio endianness, as this is likely to be a bit random.
--- arm64/include/kvm/kvm-cpu-arch.h | 5 ++-- arm64/kvm-cpu.c | 47 +++++++++++++++++++++++++------- 2 files changed, 40 insertions(+), 12 deletions(-)
arm64/include/kvm/kvm-cpu-arch.h +3 -2
@@ -10,8 +10,9 @@#define ARM_MPIDR_HWID_BITMASK 0xFF00FFFFFFUL#define ARM_CPU_ID 3, 0, 0, 0#define ARM_CPU_ID_MPIDR 5 -#define ARM_CPU_CTRL 3, 0, 1, 0 -#define ARM_CPU_CTRL_SCTLR_EL1 0 +#define SYS_SCTLR_EL1 3, 4, 1, 0, 0 +#define SYS_SCTLR_EL2 3, 4, 1, 0, 0 +#define SYS_HCR_EL2 3, 4, 1, 1, 0struct kvm_cpu {pthread_t thread;
arm64/kvm-cpu.c +37 -10
74 lines not on this page · raw message
Signature · 1 line
2.47.3
Marc Zyngier
maintainerRe: [PATCH kvmtool v6 6/6] arm64: Handle virtio endianness reset when running nested
Quoted 19 lines · Andre Przywara
From: Marc Zyngier <[email protected]>
When running an EL2 guest, we need to make sure we don't sample
SCTLR_EL1to work out the virtio endianness, as this is likely to be a bit random.Signed-off-by Marc Zyngier <[email protected]>Signed-off-by Andre Przywara <[email protected]>--- arm64/include/kvm/kvm-cpu-arch.h | 5 ++-- arm64/kvm-cpu.c | 47 +++++++++++++++++++++++++------- 2 files changed, 40 insertions(+), 12 deletions(-)arm64/include/kvm/kvm-cpu-arch.h +0
-0
arm64/include/kvm/kvm-cpu-arch.h line 14
Quoted 7 lines
arm64/include/kvm/kvm-cpu-arch.h +2
-2@@ -10,8 +10,9 @@#define ARM_MPIDR_HWID_BITMASK 0xFF00FFFFFFUL#define ARM_CPU_ID 3, 0, 0, 0#define ARM_CPU_ID_MPIDR 5 -#define ARM_CPU_CTRL 3, 0, 1, 0 -#define ARM_CPU_CTRL_SCTLR_EL1 0 +#define SYS_SCTLR_EL1 3, 4, 1, 0, 0 +#define SYS_SCTLR_EL2 3, 4, 1, 0, 0
Sascha pointed out this howler of a bug last time: SCTLR_EL1 and EL2 have the same encoding here, which is obviously wrong.
This is definitely introducing a regression on EL1 guests.
Quoted 48 lines
arm64/include/kvm/kvm-cpu-arch.h +1
-0+#define SYS_HCR_EL2 3, 4, 1, 1, 0struct kvm_cpu {pthread_t thread;arm64/kvm-cpu.c +11
-4@@ -12,6 +12,7 @@#define SCTLR_EL1_E0E_MASK (1 << 24)#define SCTLR_EL1_EE_MASK (1 << 25) +#define HCR_EL2_TGE (1 << 27)static int debug_fd;@@ -408,7 +409,8 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu) {struct kvm_one_reg reg;u64 psr; -u64 sctlr; +u64 sctlr, bit; +u64 hcr =0 ;/* * Quoting the definition given by Peter Maydell: @@ -419,8 +421,9 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)* We first check for an AArch32 guest: its endianness can * change when using SETEND, which affects the CPSR.E bit. * -* If we're AArch64, use SCTLR_EL1.E0E if access comes from -* EL0, and SCTLR_EL1.EE if access comes from EL1. +* If we're AArch64, determine which SCTLR register to use, +* depending on NV being used or not. Then use either the E0E +* bit for EL0, or the EE bit for EL1/EL2. */ reg.id =ARM64_CORE_REG (regs.pstate); reg.addr = (u64)&psr;@@ -430,16 +433,40 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)if (psr &PSR_MODE32_BIT )return (psr &COMPAT_PSR_E_BIT ) ?VIRTIO_ENDIAN_BE :VIRTIO_ENDIAN_LE ; - reg.id =ARM64_SYS_REG (ARM_CPU_CTRL ,ARM_CPU_CTRL_SCTLR_EL1 ); +if (vcpu->kvm->cfg.arch.nested_virt) { + reg.id =ARM64_SYS_REG (SYS_HCR_EL2 ); + reg.addr = (u64)&hcr; +if (ioctl (vcpu->vcpu_fd,KVM_GET_ONE_REG , ®) <0 ) +die ("KVM_GET_ONE_REG failed (HCR_EL2)" );
arm64/kvm-cpu.c int kvm_cpu__get_endianness(struct kvm_cpu *vcpu) · line 450
Quoted 10 lines
arm64/kvm-cpu.c +10
-0+ } + +switch (psr &PSR_MODE_MASK ) { +case PSR_MODE_EL0t: +if (hcr &HCR_EL2_TGE ) + reg.id =ARM64_SYS_REG (SYS_SCTLR_EL2 ); +else + reg.id =ARM64_SYS_REG (SYS_SCTLR_EL1 ); + bit =SCTLR_EL1_E0E_MASK ; +break ;
And this is also buggy, as I pointed out in my review of v5 -- I even provided a fix for it [1].
M.
[1] https://lore.kernel.org/all/[email protected]/
Signature · 1 line
Without deviation from the norm, progress is not possible.
Re: [PATCH kvmtool v6 6/6] arm64: Handle virtio endianness reset when running nested
Hi Marc,
Quoted 16 lines · Marc Zyngier
Quoted 14 lines · Andre Przywara
From: Marc Zyngier <[email protected]>
When running an EL2 guest, we need to make sure we don't sample
SCTLR_EL1to work out the virtio endianness, as this is likely to be a bit random.Signed-off-by Marc Zyngier <[email protected]>Signed-off-by Andre Przywara <[email protected]>--- arm64/include/kvm/kvm-cpu-arch.h | 5 ++-- arm64/kvm-cpu.c | 47 +++++++++++++++++++++++++------- 2 files changed, 40 insertions(+), 12 deletions(-)
Quoted 15 lines
arm64/include/kvm/kvm-cpu-arch.h line 14
Quoted 12 lines
arm64/include/kvm/kvm-cpu-arch.h +2
-2@@ -10,8 +10,9 @@#define ARM_MPIDR_HWID_BITMASK 0xFF00FFFFFFUL#define ARM_CPU_ID 3, 0, 0, 0#define ARM_CPU_ID_MPIDR 5 -#define ARM_CPU_CTRL 3, 0, 1, 0 -#define ARM_CPU_CTRL_SCTLR_EL1 0 +#define SYS_SCTLR_EL1 3, 4, 1, 0, 0 +#define SYS_SCTLR_EL2 3, 4, 1, 0, 0Sascha pointed out this howler of a bug last time:
SCTLR_EL1and EL2 have the same encoding here, which is obviously wrong.
Argh, indeed, I now remember, this was probably in the category of "that's a no brainer, what's next ..." so I missed actually fixing it. Done now, apologies for that.
Quoted 56 lines
This is definitely introducing a regression on EL1 guests.
Quoted 53 lines
arm64/include/kvm/kvm-cpu-arch.h +1
-0+#define SYS_HCR_EL2 3, 4, 1, 1, 0struct kvm_cpu {pthread_t thread;arm64/kvm-cpu.c +16
-4@@ -12,6 +12,7 @@#define SCTLR_EL1_E0E_MASK (1 << 24)#define SCTLR_EL1_EE_MASK (1 << 25) +#define HCR_EL2_TGE (1 << 27)static int debug_fd;@@ -408,7 +409,8 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu) {struct kvm_one_reg reg;u64 psr; -u64 sctlr; +u64 sctlr, bit; +u64 hcr =0 ;/* * Quoting the definition given by Peter Maydell: @@ -419,8 +421,9 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)* We first check for an AArch32 guest: its endianness can * change when using SETEND, which affects the CPSR.E bit. * -* If we're AArch64, use SCTLR_EL1.E0E if access comes from -* EL0, and SCTLR_EL1.EE if access comes from EL1. +* If we're AArch64, determine which SCTLR register to use, +* depending on NV being used or not. Then use either the E0E +* bit for EL0, or the EE bit for EL1/EL2. */ reg.id =ARM64_CORE_REG (regs.pstate); reg.addr = (u64)&psr;@@ -430,16 +433,40 @@ int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)if (psr &PSR_MODE32_BIT )return (psr &COMPAT_PSR_E_BIT ) ?VIRTIO_ENDIAN_BE :VIRTIO_ENDIAN_LE ; - reg.id =ARM64_SYS_REG (ARM_CPU_CTRL ,ARM_CPU_CTRL_SCTLR_EL1 ); +if (vcpu->kvm->cfg.arch.nested_virt) { + reg.id =ARM64_SYS_REG (SYS_HCR_EL2 ); + reg.addr = (u64)&hcr; +if (ioctl (vcpu->vcpu_fd,KVM_GET_ONE_REG , ®) <0 ) +die ("KVM_GET_ONE_REG failed (HCR_EL2)" ); + } + +switch (psr &PSR_MODE_MASK ) { +case PSR_MODE_EL0t: +if (hcr &HCR_EL2_TGE )
Quoted 8 lines
arm64/kvm-cpu.c int kvm_cpu__get_endianness(struct kvm_cpu *vcpu) · line 450
Quoted 5 lines
arm64/kvm-cpu.c +5
-0+ reg.id =ARM64_SYS_REG (SYS_SCTLR_EL2 ); + else + reg.id = ARM64_SYS_REG(SYS_SCTLR_EL1); + bit =SCTLR_EL1_E0E_MASK ; +break ;And this is also buggy, as I pointed out in my review of v5 -- I even provided a fix for it [1].
Right, applied now.
v7 incoming.
Cheers,
Andre
Quoted 5 lines
M.