Jinank Jain <jinankjain@xxxxxxxxxxxxxxxxxxx> writes:
> Child partitions are free to allocate SynIC message and event page but in
> case of root partition it must use the pages allocated by Microsoft
> Hypervisor (MSHV). Base address for these pages can be found using
> synthetic MSRs exposed by MSHV. There is a slight difference in those MSRs
> for nested vs non-nested root partition.
>
> Signed-off-by: Jinank Jain <jinankjain@xxxxxxxxxxxxxxxxxxx>
> ---
> arch/x86/include/asm/hyperv-tlfs.h | 11 ++++++
> drivers/hv/hv.c | 55 ++++++++++++++++++------------
> 2 files changed, 45 insertions(+), 21 deletions(-)
>
> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
> index d9a611565859..0319091e2019 100644
> --- a/arch/x86/include/asm/hyperv-tlfs.h
> +++ b/arch/x86/include/asm/hyperv-tlfs.h
> @@ -225,6 +225,17 @@ enum hv_isolation_type {
> #define HV_REGISTER_SINT14 0x4000009E
> #define HV_REGISTER_SINT15 0x4000009F
>
> +/*
> + * Define synthetic interrupt controller model specific registers for
> + * nested hypervisor.
> + */
> +#define HV_REGISTER_NESTED_SCONTROL 0x40001080
> +#define HV_REGISTER_NESTED_SVERSION 0x40001081
> +#define HV_REGISTER_NESTED_SIEFP 0x40001082
> +#define HV_REGISTER_NESTED_SIMP 0x40001083
> +#define HV_REGISTER_NESTED_EOM 0x40001084
> +#define HV_REGISTER_NESTED_SINT0 0x40001090
> +
> /*
> * Synthetic Timer MSRs. Four timers per vcpu.
> */
> diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
> index 4d6480d57546..92ee910561c4 100644
> --- a/drivers/hv/hv.c
> +++ b/drivers/hv/hv.c
> @@ -25,6 +25,11 @@
> /* The one and only */
> struct hv_context hv_context;
>
> +#define REG_SIMP (hv_nested ? HV_REGISTER_NESTED_SIMP : HV_REGISTER_SIMP)
> +#define REG_SIEFP (hv_nested ? HV_REGISTER_NESTED_SIEFP : HV_REGISTER_SIEFP)
> +#define REG_SCTRL (hv_nested ? HV_REGISTER_NESTED_SCONTROL : HV_REGISTER_SCONTROL)
> +#define REG_SINT0 (hv_nested ? HV_REGISTER_NESTED_SINT0 : HV_REGISTER_SINT0)
> +
> /*
> * hv_init - Main initialization routine.
> *
> @@ -147,7 +152,7 @@ int hv_synic_alloc(void)
> * Synic message and event pages are allocated by paravisor.
> * Skip these pages allocation here.
> */
> - if (!hv_isolation_type_snp()) {
> + if (!hv_isolation_type_snp() && !hv_root_partition) {
> hv_cpu->synic_message_page =
> (void *)get_zeroed_page(GFP_ATOMIC);
> if (hv_cpu->synic_message_page == NULL) {
> @@ -188,8 +193,16 @@ void hv_synic_free(void)
> struct hv_per_cpu_context *hv_cpu
> = per_cpu_ptr(hv_context.cpu_context, cpu);
>
> - free_page((unsigned long)hv_cpu->synic_event_page);
> - free_page((unsigned long)hv_cpu->synic_message_page);
> + if (hv_root_partition) {
> + if (hv_cpu->synic_event_page != NULL)
> + memunmap(hv_cpu->synic_event_page);
> +
> + if (hv_cpu->synic_message_page != NULL)
> + memunmap(hv_cpu->synic_message_page);
> + } else {
> + free_page((unsigned long)hv_cpu->synic_event_page);
> + free_page((unsigned long)hv_cpu->synic_message_page);
> + }
> free_page((unsigned long)hv_cpu->post_msg_page);
> }
>
> @@ -213,10 +226,10 @@ void hv_synic_enable_regs(unsigned int cpu)
> union hv_synic_scontrol sctrl;
>
> /* Setup the Synic's message page */
> - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
> + simp.as_uint64 = hv_get_register(REG_SIMP);
To avoid all this code churn (here and in the next patch dealing with
EOM), would it make sense to move the logic picking nested/non-nested
register into hv_{get,set}_register() instead?
E.g. something like (untested, incomplete):
static inline u32 hv_get_nested_reg(u32 reg) {
switch (reg) {
HV_REGISTER_SIMP: return HV_REGISTER_NESTED_SIMP;
HV_REGISTER_NESTED_SVERSION: return HV_REGISTER_NESTED_SVERSION;
...
default: return reg;
}
}
static inline u64 hv_get_register(unsigned int reg)
{
u64 value;
if (hv_nested)
reg = hv_get_nested_reg(reg);
if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
hv_ghcb_msr_read(reg, &value);
else
rdmsrl(reg, value);
return value;
}
static inline void hv_set_register(unsigned int reg, u64 value)
{
if (hv_nested)
reg = hv_get_nested_reg(reg);
if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
hv_ghcb_msr_write(reg, value);
/* Write proxy bit via wrmsl instruction */
if (reg >= HV_REGISTER_SINT0 &&
reg <= HV_REGISTER_SINT15)
wrmsrl(reg, value | 1 << 20);
} else {
wrmsrl(reg, value);
}
}
> simp.simp_enabled = 1;
>
> - if (hv_isolation_type_snp()) {
> + if (hv_isolation_type_snp() || hv_root_partition) {
> hv_cpu->synic_message_page
> = memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
> HV_HYP_PAGE_SIZE, MEMREMAP_WB);
> @@ -227,13 +240,13 @@ void hv_synic_enable_regs(unsigned int cpu)
> >> HV_HYP_PAGE_SHIFT;
> }
>
> - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
> + hv_set_register(REG_SIMP, simp.as_uint64);
>
> /* Setup the Synic's event page */
> - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
> + siefp.as_uint64 = hv_get_register(REG_SIEFP);
> siefp.siefp_enabled = 1;
>
> - if (hv_isolation_type_snp()) {
> + if (hv_isolation_type_snp() || hv_root_partition) {
> hv_cpu->synic_event_page =
> memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT,
> HV_HYP_PAGE_SIZE, MEMREMAP_WB);
> @@ -245,12 +258,12 @@ void hv_synic_enable_regs(unsigned int cpu)
> >> HV_HYP_PAGE_SHIFT;
> }
>
> - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
> + hv_set_register(REG_SIEFP, siefp.as_uint64);
>
> /* Setup the shared SINT. */
> if (vmbus_irq != -1)
> enable_percpu_irq(vmbus_irq, 0);
> - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
> + shared_sint.as_uint64 = hv_get_register(REG_SINT0 +
> VMBUS_MESSAGE_SINT);
>
> shared_sint.vector = vmbus_interrupt;
> @@ -266,14 +279,14 @@ void hv_synic_enable_regs(unsigned int cpu)
> #else
> shared_sint.auto_eoi = 0;
> #endif
> - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
> + hv_set_register(REG_SINT0 + VMBUS_MESSAGE_SINT,
> shared_sint.as_uint64);
>
> /* Enable the global synic bit */
> - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
> + sctrl.as_uint64 = hv_get_register(REG_SCTRL);
> sctrl.enable = 1;
>
> - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
> + hv_set_register(REG_SCTRL, sctrl.as_uint64);
> }
>
> int hv_synic_init(unsigned int cpu)
> @@ -297,17 +310,17 @@ void hv_synic_disable_regs(unsigned int cpu)
> union hv_synic_siefp siefp;
> union hv_synic_scontrol sctrl;
>
> - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
> + shared_sint.as_uint64 = hv_get_register(REG_SINT0 +
> VMBUS_MESSAGE_SINT);
>
> shared_sint.masked = 1;
>
> /* Need to correctly cleanup in the case of SMP!!! */
> /* Disable the interrupt */
> - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
> + hv_set_register(REG_SINT0 + VMBUS_MESSAGE_SINT,
> shared_sint.as_uint64);
>
> - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
> + simp.as_uint64 = hv_get_register(REG_SIMP);
> /*
> * In Isolation VM, sim and sief pages are allocated by
> * paravisor. These pages also will be used by kdump
> @@ -320,9 +333,9 @@ void hv_synic_disable_regs(unsigned int cpu)
> else
> simp.base_simp_gpa = 0;
>
> - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
> + hv_set_register(REG_SIMP, simp.as_uint64);
>
> - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
> + siefp.as_uint64 = hv_get_register(REG_SIEFP);
> siefp.siefp_enabled = 0;
>
> if (hv_isolation_type_snp())
> @@ -330,12 +343,12 @@ void hv_synic_disable_regs(unsigned int cpu)
> else
> siefp.base_siefp_gpa = 0;
>
> - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
> + hv_set_register(REG_SIEFP, siefp.as_uint64);
>
> /* Disable the global synic bit */
> - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
> + sctrl.as_uint64 = hv_get_register(REG_SCTRL);
> sctrl.enable = 0;
> - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
> + hv_set_register(REG_SCTRL, sctrl.as_uint64);
>
> if (vmbus_irq != -1)
> disable_percpu_irq(vmbus_irq);
--
Vitaly
