UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/powerpc/kvm/book3s_hv_nested.c

1400 lines
35 KiB
C
Raw Normal View History

KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corporation, 2018
* Authors Suraj Jitindar Singh <sjitindarsingh@gmail.com>
* Paul Mackerras <paulus@ozlabs.org>
*
* Description: KVM functions specific to running nested KVM-HV guests
* on Book3S processors (specifically POWER9 and later).
*/
#include <linux/kernel.h>
#include <linux/kvm_host.h>
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
#include <linux/llist.h>
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
#include <asm/kvm_ppc.h>
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
#include <asm/kvm_book3s.h>
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
#include <asm/pte-walk.h>
#include <asm/reg.h>
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
static struct patb_entry *pseries_partition_tb;
static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free);
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
hr->pcr = vc->pcr;
hr->dpdes = vc->dpdes;
hr->hfscr = vcpu->arch.hfscr;
hr->tb_offset = vc->tb_offset;
hr->dawr0 = vcpu->arch.dawr;
hr->dawrx0 = vcpu->arch.dawrx;
hr->ciabr = vcpu->arch.ciabr;
hr->purr = vcpu->arch.purr;
hr->spurr = vcpu->arch.spurr;
hr->ic = vcpu->arch.ic;
hr->vtb = vc->vtb;
hr->srr0 = vcpu->arch.shregs.srr0;
hr->srr1 = vcpu->arch.shregs.srr1;
hr->sprg[0] = vcpu->arch.shregs.sprg0;
hr->sprg[1] = vcpu->arch.shregs.sprg1;
hr->sprg[2] = vcpu->arch.shregs.sprg2;
hr->sprg[3] = vcpu->arch.shregs.sprg3;
hr->pidr = vcpu->arch.pid;
hr->cfar = vcpu->arch.cfar;
hr->ppr = vcpu->arch.ppr;
}
KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED The hcall H_ENTER_NESTED takes two parameters: the address in L1 guest memory of a hv_regs struct and the address of a pt_regs struct. The hcall requests the L0 hypervisor to use the register values in these structs to run a L2 guest and to return the exit state of the L2 guest in these structs. These are in the endianness of the L1 guest, rather than being always big-endian as is usually the case for PAPR hypercalls. This is convenient because it means that the L1 guest can pass the address of the regs field in its kvm_vcpu_arch struct. This also improves performance slightly by avoiding the need for two copies of the pt_regs struct. When reading/writing these structures, this patch handles the case where the endianness of the L1 guest differs from that of the L0 hypervisor, by byteswapping the structures after reading and before writing them back. Since all the fields of the pt_regs are of the same type, i.e., unsigned long, we treat it as an array of unsigned longs. The fields of struct hv_guest_state are not all the same, so its fields are byteswapped individually. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:15 +08:00
static void byteswap_pt_regs(struct pt_regs *regs)
{
unsigned long *addr = (unsigned long *) regs;
for (; addr < ((unsigned long *) (regs + 1)); addr++)
*addr = swab64(*addr);
}
static void byteswap_hv_regs(struct hv_guest_state *hr)
{
hr->version = swab64(hr->version);
hr->lpid = swab32(hr->lpid);
hr->vcpu_token = swab32(hr->vcpu_token);
hr->lpcr = swab64(hr->lpcr);
hr->pcr = swab64(hr->pcr);
hr->amor = swab64(hr->amor);
hr->dpdes = swab64(hr->dpdes);
hr->hfscr = swab64(hr->hfscr);
hr->tb_offset = swab64(hr->tb_offset);
hr->dawr0 = swab64(hr->dawr0);
hr->dawrx0 = swab64(hr->dawrx0);
hr->ciabr = swab64(hr->ciabr);
hr->hdec_expiry = swab64(hr->hdec_expiry);
hr->purr = swab64(hr->purr);
hr->spurr = swab64(hr->spurr);
hr->ic = swab64(hr->ic);
hr->vtb = swab64(hr->vtb);
hr->hdar = swab64(hr->hdar);
hr->hdsisr = swab64(hr->hdsisr);
hr->heir = swab64(hr->heir);
hr->asdr = swab64(hr->asdr);
hr->srr0 = swab64(hr->srr0);
hr->srr1 = swab64(hr->srr1);
hr->sprg[0] = swab64(hr->sprg[0]);
hr->sprg[1] = swab64(hr->sprg[1]);
hr->sprg[2] = swab64(hr->sprg[2]);
hr->sprg[3] = swab64(hr->sprg[3]);
hr->pidr = swab64(hr->pidr);
hr->cfar = swab64(hr->cfar);
hr->ppr = swab64(hr->ppr);
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
hr->dpdes = vc->dpdes;
hr->hfscr = vcpu->arch.hfscr;
hr->purr = vcpu->arch.purr;
hr->spurr = vcpu->arch.spurr;
hr->ic = vcpu->arch.ic;
hr->vtb = vc->vtb;
hr->srr0 = vcpu->arch.shregs.srr0;
hr->srr1 = vcpu->arch.shregs.srr1;
hr->sprg[0] = vcpu->arch.shregs.sprg0;
hr->sprg[1] = vcpu->arch.shregs.sprg1;
hr->sprg[2] = vcpu->arch.shregs.sprg2;
hr->sprg[3] = vcpu->arch.shregs.sprg3;
hr->pidr = vcpu->arch.pid;
hr->cfar = vcpu->arch.cfar;
hr->ppr = vcpu->arch.ppr;
switch (trap) {
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
hr->hdar = vcpu->arch.fault_dar;
hr->hdsisr = vcpu->arch.fault_dsisr;
hr->asdr = vcpu->arch.fault_gpa;
break;
case BOOK3S_INTERRUPT_H_INST_STORAGE:
hr->asdr = vcpu->arch.fault_gpa;
break;
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
hr->heir = vcpu->arch.emul_inst;
break;
}
}
KVM: PPC: Book3S HV: Sanitise hv_regs on nested guest entry restore_hv_regs() is used to copy the hv_regs L1 wants to set to run the nested (L2) guest into the vcpu structure. We need to sanitise these values to ensure we don't let the L1 guest hypervisor do things we don't want it to. We don't let data address watchpoints or completed instruction address breakpoints be set to match in hypervisor state. We also don't let L1 enable features in the hypervisor facility status and control register (HFSCR) for L2 which we have disabled for L1. That is L2 will get the subset of features which the L0 hypervisor has enabled for L1 and the features L1 wants to enable for L2. This could mean we give L1 a hypervisor facility unavailable interrupt for a facility it thinks it has enabled, however it shouldn't have enabled a facility it itself doesn't have for the L2 guest. We sanitise the registers when copying in the L2 hv_regs. We don't need to sanitise when copying back the L1 hv_regs since these shouldn't be able to contain invalid values as they're just what was copied out. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:14 +08:00
static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
/*
* Don't let L1 enable features for L2 which we've disabled for L1,
* but preserve the interrupt cause field.
*/
hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
/* Don't let data address watchpoint match in hypervisor state */
hr->dawrx0 &= ~DAWRX_HYP;
/* Don't let completed instruction address breakpt match in HV state */
if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
hr->ciabr &= ~CIABR_PRIV;
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
vc->pcr = hr->pcr;
vc->dpdes = hr->dpdes;
vcpu->arch.hfscr = hr->hfscr;
vcpu->arch.dawr = hr->dawr0;
vcpu->arch.dawrx = hr->dawrx0;
vcpu->arch.ciabr = hr->ciabr;
vcpu->arch.purr = hr->purr;
vcpu->arch.spurr = hr->spurr;
vcpu->arch.ic = hr->ic;
vc->vtb = hr->vtb;
vcpu->arch.shregs.srr0 = hr->srr0;
vcpu->arch.shregs.srr1 = hr->srr1;
vcpu->arch.shregs.sprg0 = hr->sprg[0];
vcpu->arch.shregs.sprg1 = hr->sprg[1];
vcpu->arch.shregs.sprg2 = hr->sprg[2];
vcpu->arch.shregs.sprg3 = hr->sprg[3];
vcpu->arch.pid = hr->pidr;
vcpu->arch.cfar = hr->cfar;
vcpu->arch.ppr = hr->ppr;
}
void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
vc->dpdes = hr->dpdes;
vcpu->arch.hfscr = hr->hfscr;
vcpu->arch.purr = hr->purr;
vcpu->arch.spurr = hr->spurr;
vcpu->arch.ic = hr->ic;
vc->vtb = hr->vtb;
vcpu->arch.fault_dar = hr->hdar;
vcpu->arch.fault_dsisr = hr->hdsisr;
vcpu->arch.fault_gpa = hr->asdr;
vcpu->arch.emul_inst = hr->heir;
vcpu->arch.shregs.srr0 = hr->srr0;
vcpu->arch.shregs.srr1 = hr->srr1;
vcpu->arch.shregs.sprg0 = hr->sprg[0];
vcpu->arch.shregs.sprg1 = hr->sprg[1];
vcpu->arch.shregs.sprg2 = hr->sprg[2];
vcpu->arch.shregs.sprg3 = hr->sprg[3];
vcpu->arch.pid = hr->pidr;
vcpu->arch.cfar = hr->cfar;
vcpu->arch.ppr = hr->ppr;
}
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
static void kvmhv_nested_mmio_needed(struct kvm_vcpu *vcpu, u64 regs_ptr)
{
/* No need to reflect the page fault to L1, we've handled it */
vcpu->arch.trap = 0;
/*
* Since the L2 gprs have already been written back into L1 memory when
* we complete the mmio, store the L1 memory location of the L2 gpr
* being loaded into by the mmio so that the loaded value can be
* written there in kvmppc_complete_mmio_load()
*/
if (((vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) == KVM_MMIO_REG_GPR)
&& (vcpu->mmio_is_write == 0)) {
vcpu->arch.nested_io_gpr = (gpa_t) regs_ptr +
offsetof(struct pt_regs,
gpr[vcpu->arch.io_gpr]);
vcpu->arch.io_gpr = KVM_MMIO_REG_NESTED_GPR;
}
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
{
long int err, r;
struct kvm_nested_guest *l2;
struct pt_regs l2_regs, saved_l1_regs;
struct hv_guest_state l2_hv, saved_l1_hv;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
u64 hv_ptr, regs_ptr;
u64 hdec_exp;
s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
u64 mask;
unsigned long lpcr;
if (vcpu->kvm->arch.l1_ptcr == 0)
return H_NOT_AVAILABLE;
/* copy parameters in */
hv_ptr = kvmppc_get_gpr(vcpu, 4);
err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
sizeof(struct hv_guest_state));
if (err)
return H_PARAMETER;
KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED The hcall H_ENTER_NESTED takes two parameters: the address in L1 guest memory of a hv_regs struct and the address of a pt_regs struct. The hcall requests the L0 hypervisor to use the register values in these structs to run a L2 guest and to return the exit state of the L2 guest in these structs. These are in the endianness of the L1 guest, rather than being always big-endian as is usually the case for PAPR hypercalls. This is convenient because it means that the L1 guest can pass the address of the regs field in its kvm_vcpu_arch struct. This also improves performance slightly by avoiding the need for two copies of the pt_regs struct. When reading/writing these structures, this patch handles the case where the endianness of the L1 guest differs from that of the L0 hypervisor, by byteswapping the structures after reading and before writing them back. Since all the fields of the pt_regs are of the same type, i.e., unsigned long, we treat it as an array of unsigned longs. The fields of struct hv_guest_state are not all the same, so its fields are byteswapped individually. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:15 +08:00
if (kvmppc_need_byteswap(vcpu))
byteswap_hv_regs(&l2_hv);
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
if (l2_hv.version != HV_GUEST_STATE_VERSION)
return H_P2;
regs_ptr = kvmppc_get_gpr(vcpu, 5);
err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
sizeof(struct pt_regs));
if (err)
return H_PARAMETER;
KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED The hcall H_ENTER_NESTED takes two parameters: the address in L1 guest memory of a hv_regs struct and the address of a pt_regs struct. The hcall requests the L0 hypervisor to use the register values in these structs to run a L2 guest and to return the exit state of the L2 guest in these structs. These are in the endianness of the L1 guest, rather than being always big-endian as is usually the case for PAPR hypercalls. This is convenient because it means that the L1 guest can pass the address of the regs field in its kvm_vcpu_arch struct. This also improves performance slightly by avoiding the need for two copies of the pt_regs struct. When reading/writing these structures, this patch handles the case where the endianness of the L1 guest differs from that of the L0 hypervisor, by byteswapping the structures after reading and before writing them back. Since all the fields of the pt_regs are of the same type, i.e., unsigned long, we treat it as an array of unsigned longs. The fields of struct hv_guest_state are not all the same, so its fields are byteswapped individually. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:15 +08:00
if (kvmppc_need_byteswap(vcpu))
byteswap_pt_regs(&l2_regs);
KVM: PPC: Book3S HV: Invalidate TLB when nested vcpu moves physical cpu This is only done at level 0, since only level 0 knows which physical CPU a vcpu is running on. This does for nested guests what L0 already did for its own guests, which is to flush the TLB on a pCPU when it goes to run a vCPU there, and there is another vCPU in the same VM which previously ran on this pCPU and has now started to run on another pCPU. This is to handle the situation where the other vCPU touched a mapping, moved to another pCPU and did a tlbiel (local-only tlbie) on that new pCPU and thus left behind a stale TLB entry on this pCPU. This introduces a limit on the the vcpu_token values used in the H_ENTER_NESTED hcall -- they must now be less than NR_CPUS. [paulus@ozlabs.org - made prev_cpu array be short[] to reduce memory consumption.] Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:11 +08:00
if (l2_hv.vcpu_token >= NR_CPUS)
return H_PARAMETER;
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
/* translate lpid */
l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
if (!l2)
return H_PARAMETER;
if (!l2->l1_gr_to_hr) {
mutex_lock(&l2->tlb_lock);
kvmhv_update_ptbl_cache(l2);
mutex_unlock(&l2->tlb_lock);
}
/* save l1 values of things */
vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
saved_l1_regs = vcpu->arch.regs;
kvmhv_save_hv_regs(vcpu, &saved_l1_hv);
/* convert TB values/offsets to host (L0) values */
hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
vc->tb_offset += l2_hv.tb_offset;
/* set L1 state to L2 state */
vcpu->arch.nested = l2;
vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
vcpu->arch.regs = l2_regs;
vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
LPCR_LPES | LPCR_MER;
lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
KVM: PPC: Book3S HV: Sanitise hv_regs on nested guest entry restore_hv_regs() is used to copy the hv_regs L1 wants to set to run the nested (L2) guest into the vcpu structure. We need to sanitise these values to ensure we don't let the L1 guest hypervisor do things we don't want it to. We don't let data address watchpoints or completed instruction address breakpoints be set to match in hypervisor state. We also don't let L1 enable features in the hypervisor facility status and control register (HFSCR) for L2 which we have disabled for L1. That is L2 will get the subset of features which the L0 hypervisor has enabled for L1 and the features L1 wants to enable for L2. This could mean we give L1 a hypervisor facility unavailable interrupt for a facility it thinks it has enabled, however it shouldn't have enabled a facility it itself doesn't have for the L2 guest. We sanitise the registers when copying in the L2 hv_regs. We don't need to sanitise when copying back the L1 hv_regs since these shouldn't be able to contain invalid values as they're just what was copied out. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:14 +08:00
sanitise_hv_regs(vcpu, &l2_hv);
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
restore_hv_regs(vcpu, &l2_hv);
vcpu->arch.ret = RESUME_GUEST;
vcpu->arch.trap = 0;
do {
if (mftb() >= hdec_exp) {
vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
r = RESUME_HOST;
break;
}
r = kvmhv_run_single_vcpu(vcpu->arch.kvm_run, vcpu, hdec_exp,
lpcr);
} while (is_kvmppc_resume_guest(r));
/* save L2 state for return */
l2_regs = vcpu->arch.regs;
l2_regs.msr = vcpu->arch.shregs.msr;
delta_purr = vcpu->arch.purr - l2_hv.purr;
delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
delta_ic = vcpu->arch.ic - l2_hv.ic;
delta_vtb = vc->vtb - l2_hv.vtb;
save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
/* restore L1 state */
vcpu->arch.nested = NULL;
vcpu->arch.regs = saved_l1_regs;
vcpu->arch.shregs.msr = saved_l1_regs.msr & ~MSR_TS_MASK;
/* set L1 MSR TS field according to L2 transaction state */
if (l2_regs.msr & MSR_TS_MASK)
vcpu->arch.shregs.msr |= MSR_TS_S;
vc->tb_offset = saved_l1_hv.tb_offset;
restore_hv_regs(vcpu, &saved_l1_hv);
vcpu->arch.purr += delta_purr;
vcpu->arch.spurr += delta_spurr;
vcpu->arch.ic += delta_ic;
vc->vtb += delta_vtb;
kvmhv_put_nested(l2);
/* copy l2_hv_state and regs back to guest */
KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED The hcall H_ENTER_NESTED takes two parameters: the address in L1 guest memory of a hv_regs struct and the address of a pt_regs struct. The hcall requests the L0 hypervisor to use the register values in these structs to run a L2 guest and to return the exit state of the L2 guest in these structs. These are in the endianness of the L1 guest, rather than being always big-endian as is usually the case for PAPR hypercalls. This is convenient because it means that the L1 guest can pass the address of the regs field in its kvm_vcpu_arch struct. This also improves performance slightly by avoiding the need for two copies of the pt_regs struct. When reading/writing these structures, this patch handles the case where the endianness of the L1 guest differs from that of the L0 hypervisor, by byteswapping the structures after reading and before writing them back. Since all the fields of the pt_regs are of the same type, i.e., unsigned long, we treat it as an array of unsigned longs. The fields of struct hv_guest_state are not all the same, so its fields are byteswapped individually. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:15 +08:00
if (kvmppc_need_byteswap(vcpu)) {
byteswap_hv_regs(&l2_hv);
byteswap_pt_regs(&l2_regs);
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
sizeof(struct hv_guest_state));
if (err)
return H_AUTHORITY;
err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
sizeof(struct pt_regs));
if (err)
return H_AUTHORITY;
if (r == -EINTR)
return H_INTERRUPT;
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
if (vcpu->mmio_needed) {
kvmhv_nested_mmio_needed(vcpu, regs_ptr);
return H_TOO_HARD;
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
return vcpu->arch.trap;
}
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
long kvmhv_nested_init(void)
{
long int ptb_order;
unsigned long ptcr;
long rc;
if (!kvmhv_on_pseries())
return 0;
if (!radix_enabled())
return -ENODEV;
/* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
if (ptb_order < 8)
ptb_order = 8;
pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
GFP_KERNEL);
if (!pseries_partition_tb) {
pr_err("kvm-hv: failed to allocated nested partition table\n");
return -ENOMEM;
}
ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
if (rc != H_SUCCESS) {
pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
rc);
kfree(pseries_partition_tb);
pseries_partition_tb = NULL;
return -ENODEV;
}
return 0;
}
void kvmhv_nested_exit(void)
{
/*
* N.B. the kvmhv_on_pseries() test is there because it enables
* the compiler to remove the call to plpar_hcall_norets()
* when CONFIG_PPC_PSERIES=n.
*/
if (kvmhv_on_pseries() && pseries_partition_tb) {
plpar_hcall_norets(H_SET_PARTITION_TABLE, 0);
kfree(pseries_partition_tb);
pseries_partition_tb = NULL;
}
}
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
static void kvmhv_flush_lpid(unsigned int lpid)
{
long rc;
if (!kvmhv_on_pseries()) {
radix__flush_tlb_lpid(lpid);
return;
}
rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
lpid, TLBIEL_INVAL_SET_LPID);
if (rc)
pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
}
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
{
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
if (!kvmhv_on_pseries()) {
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
mmu_partition_table_set_entry(lpid, dw0, dw1);
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
return;
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
}
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
/* L0 will do the necessary barriers */
kvmhv_flush_lpid(lpid);
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
}
static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
{
unsigned long dw0;
dw0 = PATB_HR | radix__get_tree_size() |
__pa(gp->shadow_pgtable) | RADIX_PGD_INDEX_SIZE;
kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
}
void kvmhv_vm_nested_init(struct kvm *kvm)
{
kvm->arch.max_nested_lpid = -1;
}
/*
* Handle the H_SET_PARTITION_TABLE hcall.
* r4 = guest real address of partition table + log_2(size) - 12
* (formatted as for the PTCR).
*/
long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
unsigned long ptcr = kvmppc_get_gpr(vcpu, 4);
int srcu_idx;
long ret = H_SUCCESS;
srcu_idx = srcu_read_lock(&kvm->srcu);
/*
* Limit the partition table to 4096 entries (because that's what
* hardware supports), and check the base address.
*/
if ((ptcr & PRTS_MASK) > 12 - 8 ||
!kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
ret = H_PARAMETER;
srcu_read_unlock(&kvm->srcu, srcu_idx);
if (ret == H_SUCCESS)
kvm->arch.l1_ptcr = ptcr;
return ret;
}
KVM: PPC: Book3S: Introduce new hcall H_COPY_TOFROM_GUEST to access quadrants 1 & 2 A guest cannot access quadrants 1 or 2 as this would result in an exception. Thus introduce the hcall H_COPY_TOFROM_GUEST to be used by a guest when it wants to perform an access to quadrants 1 or 2, for example when it wants to access memory for one of its nested guests. Also provide an implementation for the kvm-hv module. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:09 +08:00
/*
* Handle the H_COPY_TOFROM_GUEST hcall.
* r4 = L1 lpid of nested guest
* r5 = pid
* r6 = eaddr to access
* r7 = to buffer (L1 gpa)
* r8 = from buffer (L1 gpa)
* r9 = n bytes to copy
*/
long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu)
{
struct kvm_nested_guest *gp;
int l1_lpid = kvmppc_get_gpr(vcpu, 4);
int pid = kvmppc_get_gpr(vcpu, 5);
gva_t eaddr = kvmppc_get_gpr(vcpu, 6);
gpa_t gp_to = (gpa_t) kvmppc_get_gpr(vcpu, 7);
gpa_t gp_from = (gpa_t) kvmppc_get_gpr(vcpu, 8);
void *buf;
unsigned long n = kvmppc_get_gpr(vcpu, 9);
bool is_load = !!gp_to;
long rc;
if (gp_to && gp_from) /* One must be NULL to determine the direction */
return H_PARAMETER;
if (eaddr & (0xFFFUL << 52))
return H_PARAMETER;
buf = kzalloc(n, GFP_KERNEL);
if (!buf)
return H_NO_MEM;
gp = kvmhv_get_nested(vcpu->kvm, l1_lpid, false);
if (!gp) {
rc = H_PARAMETER;
goto out_free;
}
mutex_lock(&gp->tlb_lock);
if (is_load) {
/* Load from the nested guest into our buffer */
rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
eaddr, buf, NULL, n);
if (rc)
goto not_found;
/* Write what was loaded into our buffer back to the L1 guest */
rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n);
if (rc)
goto not_found;
} else {
/* Load the data to be stored from the L1 guest into our buf */
rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n);
if (rc)
goto not_found;
/* Store from our buffer into the nested guest */
rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
eaddr, NULL, buf, n);
if (rc)
goto not_found;
}
out_unlock:
mutex_unlock(&gp->tlb_lock);
kvmhv_put_nested(gp);
out_free:
kfree(buf);
return rc;
not_found:
rc = H_NOT_FOUND;
goto out_unlock;
}
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
/*
* Reload the partition table entry for a guest.
* Caller must hold gp->tlb_lock.
*/
static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
{
int ret;
struct patb_entry ptbl_entry;
unsigned long ptbl_addr;
struct kvm *kvm = gp->l1_host;
ret = -EFAULT;
ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
ret = kvm_read_guest(kvm, ptbl_addr,
&ptbl_entry, sizeof(ptbl_entry));
if (ret) {
gp->l1_gr_to_hr = 0;
gp->process_table = 0;
} else {
gp->l1_gr_to_hr = be64_to_cpu(ptbl_entry.patb0);
gp->process_table = be64_to_cpu(ptbl_entry.patb1);
}
kvmhv_set_nested_ptbl(gp);
}
struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
{
struct kvm_nested_guest *gp;
long shadow_lpid;
gp = kzalloc(sizeof(*gp), GFP_KERNEL);
if (!gp)
return NULL;
gp->l1_host = kvm;
gp->l1_lpid = lpid;
mutex_init(&gp->tlb_lock);
gp->shadow_pgtable = pgd_alloc(kvm->mm);
if (!gp->shadow_pgtable)
goto out_free;
shadow_lpid = kvmppc_alloc_lpid();
if (shadow_lpid < 0)
goto out_free2;
gp->shadow_lpid = shadow_lpid;
KVM: PPC: Book3S HV: Add function kvmhv_vcpu_is_radix() There exists a function kvm_is_radix() which is used to determine if a kvm instance is using the radix mmu. However this only applies to the first level (L1) guest. Add a function kvmhv_vcpu_is_radix() which can be used to determine if the current execution context of the vcpu is radix, accounting for if the vcpu is running a nested guest. Currently all nested guests must be radix but this may change in the future. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:04 +08:00
gp->radix = 1;
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
KVM: PPC: Book3S HV: Invalidate TLB when nested vcpu moves physical cpu This is only done at level 0, since only level 0 knows which physical CPU a vcpu is running on. This does for nested guests what L0 already did for its own guests, which is to flush the TLB on a pCPU when it goes to run a vCPU there, and there is another vCPU in the same VM which previously ran on this pCPU and has now started to run on another pCPU. This is to handle the situation where the other vCPU touched a mapping, moved to another pCPU and did a tlbiel (local-only tlbie) on that new pCPU and thus left behind a stale TLB entry on this pCPU. This introduces a limit on the the vcpu_token values used in the H_ENTER_NESTED hcall -- they must now be less than NR_CPUS. [paulus@ozlabs.org - made prev_cpu array be short[] to reduce memory consumption.] Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:11 +08:00
memset(gp->prev_cpu, -1, sizeof(gp->prev_cpu));
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
return gp;
out_free2:
pgd_free(kvm->mm, gp->shadow_pgtable);
out_free:
kfree(gp);
return NULL;
}
/*
* Free up any resources allocated for a nested guest.
*/
static void kvmhv_release_nested(struct kvm_nested_guest *gp)
{
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
struct kvm *kvm = gp->l1_host;
if (gp->shadow_pgtable) {
/*
* No vcpu is using this struct and no call to
* kvmhv_get_nested can find this struct,
* so we don't need to hold kvm->mmu_lock.
*/
kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
gp->shadow_lpid);
pgd_free(kvm->mm, gp->shadow_pgtable);
}
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
kvmppc_free_lpid(gp->shadow_lpid);
kfree(gp);
}
static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
{
struct kvm *kvm = gp->l1_host;
int lpid = gp->l1_lpid;
long ref;
spin_lock(&kvm->mmu_lock);
if (gp == kvm->arch.nested_guests[lpid]) {
kvm->arch.nested_guests[lpid] = NULL;
if (lpid == kvm->arch.max_nested_lpid) {
while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
;
kvm->arch.max_nested_lpid = lpid;
}
--gp->refcnt;
}
ref = gp->refcnt;
spin_unlock(&kvm->mmu_lock);
if (ref == 0)
kvmhv_release_nested(gp);
}
/*
* Free up all nested resources allocated for this guest.
* This is called with no vcpus of the guest running, when
* switching the guest to HPT mode or when destroying the
* guest.
*/
void kvmhv_release_all_nested(struct kvm *kvm)
{
int i;
struct kvm_nested_guest *gp;
struct kvm_nested_guest *freelist = NULL;
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
struct kvm_memory_slot *memslot;
int srcu_idx;
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
spin_lock(&kvm->mmu_lock);
for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
gp = kvm->arch.nested_guests[i];
if (!gp)
continue;
kvm->arch.nested_guests[i] = NULL;
if (--gp->refcnt == 0) {
gp->next = freelist;
freelist = gp;
}
}
kvm->arch.max_nested_lpid = -1;
spin_unlock(&kvm->mmu_lock);
while ((gp = freelist) != NULL) {
freelist = gp->next;
kvmhv_release_nested(gp);
}
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
srcu_idx = srcu_read_lock(&kvm->srcu);
kvm_for_each_memslot(memslot, kvm_memslots(kvm))
kvmhv_free_memslot_nest_rmap(memslot);
srcu_read_unlock(&kvm->srcu, srcu_idx);
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
}
/* caller must hold gp->tlb_lock */
KVM: PPC: Book3S HV: Implement H_TLB_INVALIDATE hcall When running a nested (L2) guest the guest (L1) hypervisor will use the H_TLB_INVALIDATE hcall when it needs to change the partition scoped page tables or the partition table which it manages. It will use this hcall in the situations where it would use a partition-scoped tlbie instruction if it were running in hypervisor mode. The H_TLB_INVALIDATE hcall can invalidate different scopes: Invalidate TLB for a given target address: - This invalidates a single L2 -> L1 pte - We need to invalidate any L2 -> L0 shadow_pgtable ptes which map the L2 address space which is being invalidated. This is because a single L2 -> L1 pte may have been mapped with more than one pte in the L2 -> L0 page tables. Invalidate the entire TLB for a given LPID or for all LPIDs: - Invalidate the entire shadow_pgtable for a given nested guest, or for all nested guests. Invalidate the PWC (page walk cache) for a given LPID or for all LPIDs: - We don't cache the PWC, so nothing to do. Invalidate the entire TLB, PWC and partition table for a given/all LPIDs: - Here we re-read the partition table entry and remove the nested state for any nested guest for which the first doubleword of the partition table entry is now zero. The H_TLB_INVALIDATE hcall takes as parameters the tlbie instruction word (of which only the RIC, PRS and R fields are used), the rS value (giving the lpid, where required) and the rB value (giving the IS, AP and EPN values). [paulus@ozlabs.org - adapted to having the partition table in guest memory, added the H_TLB_INVALIDATE implementation, removed tlbie instruction emulation, reworded the commit message.] Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:09 +08:00
static void kvmhv_flush_nested(struct kvm_nested_guest *gp)
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
{
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
struct kvm *kvm = gp->l1_host;
spin_lock(&kvm->mmu_lock);
kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
spin_unlock(&kvm->mmu_lock);
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
kvmhv_flush_lpid(gp->shadow_lpid);
KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization This starts the process of adding the code to support nested HV-style virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which a nested hypervisor can use to set the base address and size of a partition table in its memory (analogous to the PTCR register). On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE hypercall from the guest is handled by code that saves the virtual PTCR value for the guest. This also adds code for creating and destroying nested guests and for reading the partition table entry for a nested guest from L1 memory. Each nested guest has its own shadow LPID value, different in general from the LPID value used by the nested hypervisor to refer to it. The shadow LPID value is allocated at nested guest creation time. Nested hypervisor functionality is only available for a radix guest, which therefore means a radix host on a POWER9 (or later) processor. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:03 +08:00
kvmhv_update_ptbl_cache(gp);
if (gp->l1_gr_to_hr == 0)
kvmhv_remove_nested(gp);
}
struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
bool create)
{
struct kvm_nested_guest *gp, *newgp;
if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
return NULL;
spin_lock(&kvm->mmu_lock);
gp = kvm->arch.nested_guests[l1_lpid];
if (gp)
++gp->refcnt;
spin_unlock(&kvm->mmu_lock);
if (gp || !create)
return gp;
newgp = kvmhv_alloc_nested(kvm, l1_lpid);
if (!newgp)
return NULL;
spin_lock(&kvm->mmu_lock);
if (kvm->arch.nested_guests[l1_lpid]) {
/* someone else beat us to it */
gp = kvm->arch.nested_guests[l1_lpid];
} else {
kvm->arch.nested_guests[l1_lpid] = newgp;
++newgp->refcnt;
gp = newgp;
newgp = NULL;
if (l1_lpid > kvm->arch.max_nested_lpid)
kvm->arch.max_nested_lpid = l1_lpid;
}
++gp->refcnt;
spin_unlock(&kvm->mmu_lock);
if (newgp)
kvmhv_release_nested(newgp);
return gp;
}
void kvmhv_put_nested(struct kvm_nested_guest *gp)
{
struct kvm *kvm = gp->l1_host;
long ref;
spin_lock(&kvm->mmu_lock);
ref = --gp->refcnt;
spin_unlock(&kvm->mmu_lock);
if (ref == 0)
kvmhv_release_nested(gp);
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
static struct kvm_nested_guest *kvmhv_find_nested(struct kvm *kvm, int lpid)
{
if (lpid > kvm->arch.max_nested_lpid)
return NULL;
return kvm->arch.nested_guests[lpid];
}
static inline bool kvmhv_n_rmap_is_equal(u64 rmap_1, u64 rmap_2)
{
return !((rmap_1 ^ rmap_2) & (RMAP_NESTED_LPID_MASK |
RMAP_NESTED_GPA_MASK));
}
void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
struct rmap_nested **n_rmap)
{
struct llist_node *entry = ((struct llist_head *) rmapp)->first;
struct rmap_nested *cursor;
u64 rmap, new_rmap = (*n_rmap)->rmap;
/* Are there any existing entries? */
if (!(*rmapp)) {
/* No -> use the rmap as a single entry */
*rmapp = new_rmap | RMAP_NESTED_IS_SINGLE_ENTRY;
return;
}
/* Do any entries match what we're trying to insert? */
for_each_nest_rmap_safe(cursor, entry, &rmap) {
if (kvmhv_n_rmap_is_equal(rmap, new_rmap))
return;
}
/* Do we need to create a list or just add the new entry? */
rmap = *rmapp;
if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
*rmapp = 0UL;
llist_add(&((*n_rmap)->list), (struct llist_head *) rmapp);
if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
(*n_rmap)->list.next = (struct llist_node *) rmap;
/* Set NULL so not freed by caller */
*n_rmap = NULL;
}
static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
unsigned long hpa, unsigned long mask)
{
struct kvm_nested_guest *gp;
unsigned long gpa;
unsigned int shift, lpid;
pte_t *ptep;
gpa = n_rmap & RMAP_NESTED_GPA_MASK;
lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
gp = kvmhv_find_nested(kvm, lpid);
if (!gp)
return;
/* Find and invalidate the pte */
ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
/* Don't spuriously invalidate ptes if the pfn has changed */
if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa))
kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
}
static void kvmhv_remove_nest_rmap_list(struct kvm *kvm, unsigned long *rmapp,
unsigned long hpa, unsigned long mask)
{
struct llist_node *entry = llist_del_all((struct llist_head *) rmapp);
struct rmap_nested *cursor;
unsigned long rmap;
for_each_nest_rmap_safe(cursor, entry, &rmap) {
kvmhv_remove_nest_rmap(kvm, rmap, hpa, mask);
kfree(cursor);
}
}
/* called with kvm->mmu_lock held */
void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
KVM: PPC: Book3S HV: Cleanups - constify memslots, fix comments This adds 'const' to the declarations for the struct kvm_memory_slot pointer parameters of some functions, which will make it possible to call those functions from kvmppc_core_commit_memory_region_hv() in the next patch. This also fixes some comments about locking. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-12 12:16:48 +08:00
const struct kvm_memory_slot *memslot,
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
unsigned long gpa, unsigned long hpa,
unsigned long nbytes)
{
unsigned long gfn, end_gfn;
unsigned long addr_mask;
if (!memslot)
return;
gfn = (gpa >> PAGE_SHIFT) - memslot->base_gfn;
end_gfn = gfn + (nbytes >> PAGE_SHIFT);
addr_mask = PTE_RPN_MASK & ~(nbytes - 1);
hpa &= addr_mask;
for (; gfn < end_gfn; gfn++) {
unsigned long *rmap = &memslot->arch.rmap[gfn];
kvmhv_remove_nest_rmap_list(kvm, rmap, hpa, addr_mask);
}
}
static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free)
{
unsigned long page;
for (page = 0; page < free->npages; page++) {
unsigned long rmap, *rmapp = &free->arch.rmap[page];
struct rmap_nested *cursor;
struct llist_node *entry;
entry = llist_del_all((struct llist_head *) rmapp);
for_each_nest_rmap_safe(cursor, entry, &rmap)
kfree(cursor);
}
}
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp,
long gpa, int *shift_ret)
{
struct kvm *kvm = vcpu->kvm;
bool ret = false;
pte_t *ptep;
int shift;
spin_lock(&kvm->mmu_lock);
ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
if (!shift)
shift = PAGE_SHIFT;
if (ptep && pte_present(*ptep)) {
kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
ret = true;
}
spin_unlock(&kvm->mmu_lock);
if (shift_ret)
*shift_ret = shift;
return ret;
}
KVM: PPC: Book3S HV: Implement H_TLB_INVALIDATE hcall When running a nested (L2) guest the guest (L1) hypervisor will use the H_TLB_INVALIDATE hcall when it needs to change the partition scoped page tables or the partition table which it manages. It will use this hcall in the situations where it would use a partition-scoped tlbie instruction if it were running in hypervisor mode. The H_TLB_INVALIDATE hcall can invalidate different scopes: Invalidate TLB for a given target address: - This invalidates a single L2 -> L1 pte - We need to invalidate any L2 -> L0 shadow_pgtable ptes which map the L2 address space which is being invalidated. This is because a single L2 -> L1 pte may have been mapped with more than one pte in the L2 -> L0 page tables. Invalidate the entire TLB for a given LPID or for all LPIDs: - Invalidate the entire shadow_pgtable for a given nested guest, or for all nested guests. Invalidate the PWC (page walk cache) for a given LPID or for all LPIDs: - We don't cache the PWC, so nothing to do. Invalidate the entire TLB, PWC and partition table for a given/all LPIDs: - Here we re-read the partition table entry and remove the nested state for any nested guest for which the first doubleword of the partition table entry is now zero. The H_TLB_INVALIDATE hcall takes as parameters the tlbie instruction word (of which only the RIC, PRS and R fields are used), the rS value (giving the lpid, where required) and the rB value (giving the IS, AP and EPN values). [paulus@ozlabs.org - adapted to having the partition table in guest memory, added the H_TLB_INVALIDATE implementation, removed tlbie instruction emulation, reworded the commit message.] Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:09 +08:00
static inline int get_ric(unsigned int instr)
{
return (instr >> 18) & 0x3;
}
static inline int get_prs(unsigned int instr)
{
return (instr >> 17) & 0x1;
}
static inline int get_r(unsigned int instr)
{
return (instr >> 16) & 0x1;
}
static inline int get_lpid(unsigned long r_val)
{
return r_val & 0xffffffff;
}
static inline int get_is(unsigned long r_val)
{
return (r_val >> 10) & 0x3;
}
static inline int get_ap(unsigned long r_val)
{
return (r_val >> 5) & 0x7;
}
static inline long get_epn(unsigned long r_val)
{
return r_val >> 12;
}
static int kvmhv_emulate_tlbie_tlb_addr(struct kvm_vcpu *vcpu, int lpid,
int ap, long epn)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_nested_guest *gp;
long npages;
int shift, shadow_shift;
unsigned long addr;
shift = ap_to_shift(ap);
addr = epn << 12;
if (shift < 0)
/* Invalid ap encoding */
return -EINVAL;
addr &= ~((1UL << shift) - 1);
npages = 1UL << (shift - PAGE_SHIFT);
gp = kvmhv_get_nested(kvm, lpid, false);
if (!gp) /* No such guest -> nothing to do */
return 0;
mutex_lock(&gp->tlb_lock);
/* There may be more than one host page backing this single guest pte */
do {
kvmhv_invalidate_shadow_pte(vcpu, gp, addr, &shadow_shift);
npages -= 1UL << (shadow_shift - PAGE_SHIFT);
addr += 1UL << shadow_shift;
} while (npages > 0);
mutex_unlock(&gp->tlb_lock);
kvmhv_put_nested(gp);
return 0;
}
static void kvmhv_emulate_tlbie_lpid(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp, int ric)
{
struct kvm *kvm = vcpu->kvm;
mutex_lock(&gp->tlb_lock);
switch (ric) {
case 0:
/* Invalidate TLB */
spin_lock(&kvm->mmu_lock);
kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
gp->shadow_lpid);
KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested This adds code to call the H_TLB_INVALIDATE hypercall when running as a guest, in the cases where we need to invalidate TLBs (or other MMU caches) as part of managing the mappings for a nested guest. Calling H_TLB_INVALIDATE lets the nested hypervisor inform the parent hypervisor about changes to partition-scoped page tables or the partition table without needing to do hypervisor-privileged tlbie instructions. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:10 +08:00
kvmhv_flush_lpid(gp->shadow_lpid);
KVM: PPC: Book3S HV: Implement H_TLB_INVALIDATE hcall When running a nested (L2) guest the guest (L1) hypervisor will use the H_TLB_INVALIDATE hcall when it needs to change the partition scoped page tables or the partition table which it manages. It will use this hcall in the situations where it would use a partition-scoped tlbie instruction if it were running in hypervisor mode. The H_TLB_INVALIDATE hcall can invalidate different scopes: Invalidate TLB for a given target address: - This invalidates a single L2 -> L1 pte - We need to invalidate any L2 -> L0 shadow_pgtable ptes which map the L2 address space which is being invalidated. This is because a single L2 -> L1 pte may have been mapped with more than one pte in the L2 -> L0 page tables. Invalidate the entire TLB for a given LPID or for all LPIDs: - Invalidate the entire shadow_pgtable for a given nested guest, or for all nested guests. Invalidate the PWC (page walk cache) for a given LPID or for all LPIDs: - We don't cache the PWC, so nothing to do. Invalidate the entire TLB, PWC and partition table for a given/all LPIDs: - Here we re-read the partition table entry and remove the nested state for any nested guest for which the first doubleword of the partition table entry is now zero. The H_TLB_INVALIDATE hcall takes as parameters the tlbie instruction word (of which only the RIC, PRS and R fields are used), the rS value (giving the lpid, where required) and the rB value (giving the IS, AP and EPN values). [paulus@ozlabs.org - adapted to having the partition table in guest memory, added the H_TLB_INVALIDATE implementation, removed tlbie instruction emulation, reworded the commit message.] Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:09 +08:00
spin_unlock(&kvm->mmu_lock);
break;
case 1:
/*
* Invalidate PWC
* We don't cache this -> nothing to do
*/
break;
case 2:
/* Invalidate TLB, PWC and caching of partition table entries */
kvmhv_flush_nested(gp);
break;
default:
break;
}
mutex_unlock(&gp->tlb_lock);
}
static void kvmhv_emulate_tlbie_all_lpid(struct kvm_vcpu *vcpu, int ric)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_nested_guest *gp;
int i;
spin_lock(&kvm->mmu_lock);
for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
gp = kvm->arch.nested_guests[i];
if (gp) {
spin_unlock(&kvm->mmu_lock);
kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
spin_lock(&kvm->mmu_lock);
}
}
spin_unlock(&kvm->mmu_lock);
}
static int kvmhv_emulate_priv_tlbie(struct kvm_vcpu *vcpu, unsigned int instr,
unsigned long rsval, unsigned long rbval)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_nested_guest *gp;
int r, ric, prs, is, ap;
int lpid;
long epn;
int ret = 0;
ric = get_ric(instr);
prs = get_prs(instr);
r = get_r(instr);
lpid = get_lpid(rsval);
is = get_is(rbval);
/*
* These cases are invalid and are not handled:
* r != 1 -> Only radix supported
* prs == 1 -> Not HV privileged
* ric == 3 -> No cluster bombs for radix
* is == 1 -> Partition scoped translations not associated with pid
* (!is) && (ric == 1 || ric == 2) -> Not supported by ISA
*/
if ((!r) || (prs) || (ric == 3) || (is == 1) ||
((!is) && (ric == 1 || ric == 2)))
return -EINVAL;
switch (is) {
case 0:
/*
* We know ric == 0
* Invalidate TLB for a given target address
*/
epn = get_epn(rbval);
ap = get_ap(rbval);
ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap, epn);
break;
case 2:
/* Invalidate matching LPID */
gp = kvmhv_get_nested(kvm, lpid, false);
if (gp) {
kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
kvmhv_put_nested(gp);
}
break;
case 3:
/* Invalidate ALL LPIDs */
kvmhv_emulate_tlbie_all_lpid(vcpu, ric);
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
/*
* This handles the H_TLB_INVALIDATE hcall.
* Parameters are (r4) tlbie instruction code, (r5) rS contents,
* (r6) rB contents.
*/
long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
{
int ret;
ret = kvmhv_emulate_priv_tlbie(vcpu, kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6));
if (ret)
return H_PARAMETER;
return H_SUCCESS;
}
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
/* Used to convert a nested guest real address to a L1 guest real address */
static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp,
unsigned long n_gpa, unsigned long dsisr,
struct kvmppc_pte *gpte_p)
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
{
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
u64 fault_addr, flags = dsisr & DSISR_ISSTORE;
int ret;
ret = kvmppc_mmu_walk_radix_tree(vcpu, n_gpa, gpte_p, gp->l1_gr_to_hr,
&fault_addr);
if (ret) {
/* We didn't find a pte */
if (ret == -EINVAL) {
/* Unsupported mmu config */
flags |= DSISR_UNSUPP_MMU;
} else if (ret == -ENOENT) {
/* No translation found */
flags |= DSISR_NOHPTE;
} else if (ret == -EFAULT) {
/* Couldn't access L1 real address */
flags |= DSISR_PRTABLE_FAULT;
vcpu->arch.fault_gpa = fault_addr;
} else {
/* Unknown error */
return ret;
}
goto forward_to_l1;
} else {
/* We found a pte -> check permissions */
if (dsisr & DSISR_ISSTORE) {
/* Can we write? */
if (!gpte_p->may_write) {
flags |= DSISR_PROTFAULT;
goto forward_to_l1;
}
} else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
/* Can we execute? */
if (!gpte_p->may_execute) {
flags |= SRR1_ISI_N_OR_G;
goto forward_to_l1;
}
} else {
/* Can we read? */
if (!gpte_p->may_read && !gpte_p->may_write) {
flags |= DSISR_PROTFAULT;
goto forward_to_l1;
}
}
}
return 0;
forward_to_l1:
vcpu->arch.fault_dsisr = flags;
if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
vcpu->arch.shregs.msr &= ~0x783f0000ul;
vcpu->arch.shregs.msr |= flags;
}
KVM: PPC: Book3S HV: Nested guest entry via hypercall This adds a new hypercall, H_ENTER_NESTED, which is used by a nested hypervisor to enter one of its nested guests. The hypercall supplies register values in two structs. Those values are copied by the level 0 (L0) hypervisor (the one which is running in hypervisor mode) into the vcpu struct of the L1 guest, and then the guest is run until an interrupt or error occurs which needs to be reported to L1 via the hypercall return value. Currently this assumes that the L0 and L1 hypervisors are the same endianness, and the structs passed as arguments are in native endianness. If they are of different endianness, the version number check will fail and the hcall will be rejected. Nested hypervisors do not support indep_threads_mode=N, so this adds code to print a warning message if the administrator has set indep_threads_mode=N, and treat it as Y. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:04 +08:00
return RESUME_HOST;
}
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp,
unsigned long n_gpa,
struct kvmppc_pte gpte,
unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
bool writing = !!(dsisr & DSISR_ISSTORE);
u64 pgflags;
KVM: PPC: Book3S HV: Hold kvm->mmu_lock across updating nested pte rc bits We already hold the kvm->mmu_lock spin lock across updating the rc bits in the pte for the L1 guest. Continue to hold the lock across updating the rc bits in the pte for the nested guest as well to prevent invalidations from occurring. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-21 11:28:39 +08:00
long ret;
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
/* Are the rc bits set in the L1 partition scoped pte? */
pgflags = _PAGE_ACCESSED;
if (writing)
pgflags |= _PAGE_DIRTY;
if (pgflags & ~gpte.rc)
return RESUME_HOST;
spin_lock(&kvm->mmu_lock);
/* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
gpte.raddr, kvm->arch.lpid);
KVM: PPC: Book3S HV: Hold kvm->mmu_lock across updating nested pte rc bits We already hold the kvm->mmu_lock spin lock across updating the rc bits in the pte for the L1 guest. Continue to hold the lock across updating the rc bits in the pte for the nested guest as well to prevent invalidations from occurring. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-21 11:28:39 +08:00
if (!ret) {
ret = -EINVAL;
goto out_unlock;
}
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
/* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
gp->shadow_lpid);
if (!ret)
KVM: PPC: Book3S HV: Hold kvm->mmu_lock across updating nested pte rc bits We already hold the kvm->mmu_lock spin lock across updating the rc bits in the pte for the L1 guest. Continue to hold the lock across updating the rc bits in the pte for the nested guest as well to prevent invalidations from occurring. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-21 11:28:39 +08:00
ret = -EINVAL;
else
ret = 0;
out_unlock:
spin_unlock(&kvm->mmu_lock);
return ret;
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
}
static inline int kvmppc_radix_level_to_shift(int level)
{
switch (level) {
case 2:
return PUD_SHIFT;
case 1:
return PMD_SHIFT;
default:
return PAGE_SHIFT;
}
}
static inline int kvmppc_radix_shift_to_level(int shift)
{
if (shift == PUD_SHIFT)
return 2;
if (shift == PMD_SHIFT)
return 1;
if (shift == PAGE_SHIFT)
return 0;
WARN_ON_ONCE(1);
return 0;
}
/* called with gp->tlb_lock held */
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
static long int __kvmhv_nested_page_fault(struct kvm_run *run,
struct kvm_vcpu *vcpu,
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
struct kvm_nested_guest *gp)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_memory_slot *memslot;
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
struct rmap_nested *n_rmap;
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
struct kvmppc_pte gpte;
pte_t pte, *pte_p;
unsigned long mmu_seq;
unsigned long dsisr = vcpu->arch.fault_dsisr;
unsigned long ea = vcpu->arch.fault_dar;
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
unsigned long *rmapp;
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
unsigned long n_gpa, gpa, gfn, perm = 0UL;
unsigned int shift, l1_shift, level;
bool writing = !!(dsisr & DSISR_ISSTORE);
bool kvm_ro = false;
long int ret;
if (!gp->l1_gr_to_hr) {
kvmhv_update_ptbl_cache(gp);
if (!gp->l1_gr_to_hr)
return RESUME_HOST;
}
/* Convert the nested guest real address into a L1 guest real address */
n_gpa = vcpu->arch.fault_gpa & ~0xF000000000000FFFULL;
if (!(dsisr & DSISR_PRTABLE_FAULT))
n_gpa |= ea & 0xFFF;
ret = kvmhv_translate_addr_nested(vcpu, gp, n_gpa, dsisr, &gpte);
/*
* If the hardware found a translation but we don't now have a usable
* translation in the l1 partition-scoped tree, remove the shadow pte
* and let the guest retry.
*/
if (ret == RESUME_HOST &&
(dsisr & (DSISR_PROTFAULT | DSISR_BADACCESS | DSISR_NOEXEC_OR_G |
DSISR_BAD_COPYPASTE)))
goto inval;
if (ret)
return ret;
/* Failed to set the reference/change bits */
if (dsisr & DSISR_SET_RC) {
ret = kvmhv_handle_nested_set_rc(vcpu, gp, n_gpa, gpte, dsisr);
if (ret == RESUME_HOST)
return ret;
if (ret)
goto inval;
dsisr &= ~DSISR_SET_RC;
if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
DSISR_PROTFAULT)))
return RESUME_GUEST;
}
/*
* We took an HISI or HDSI while we were running a nested guest which
* means we have no partition scoped translation for that. This means
* we need to insert a pte for the mapping into our shadow_pgtable.
*/
l1_shift = gpte.page_shift;
if (l1_shift < PAGE_SHIFT) {
/* We don't support l1 using a page size smaller than our own */
pr_err("KVM: L1 guest page shift (%d) less than our own (%d)\n",
l1_shift, PAGE_SHIFT);
return -EINVAL;
}
gpa = gpte.raddr;
gfn = gpa >> PAGE_SHIFT;
/* 1. Get the corresponding host memslot */
memslot = gfn_to_memslot(kvm, gfn);
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) {
/* unusual error -> reflect to the guest as a DSI */
kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
return RESUME_GUEST;
}
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
/* passthrough of emulated MMIO case */
return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
}
if (memslot->flags & KVM_MEM_READONLY) {
if (writing) {
/* Give the guest a DSI */
kvmppc_core_queue_data_storage(vcpu, ea,
DSISR_ISSTORE | DSISR_PROTFAULT);
return RESUME_GUEST;
}
kvm_ro = true;
}
/* 2. Find the host pte for this L1 guest real address */
/* Used to check for invalidations in progress */
mmu_seq = kvm->mmu_notifier_seq;
smp_rmb();
/* See if can find translation in our partition scoped tables for L1 */
pte = __pte(0);
spin_lock(&kvm->mmu_lock);
pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (!shift)
shift = PAGE_SHIFT;
if (pte_p)
pte = *pte_p;
spin_unlock(&kvm->mmu_lock);
if (!pte_present(pte) || (writing && !(pte_val(pte) & _PAGE_WRITE))) {
/* No suitable pte found -> try to insert a mapping */
ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot,
writing, kvm_ro, &pte, &level);
if (ret == -EAGAIN)
return RESUME_GUEST;
else if (ret)
return ret;
shift = kvmppc_radix_level_to_shift(level);
}
/* 3. Compute the pte we need to insert for nest_gpa -> host r_addr */
/* The permissions is the combination of the host and l1 guest ptes */
perm |= gpte.may_read ? 0UL : _PAGE_READ;
perm |= gpte.may_write ? 0UL : _PAGE_WRITE;
perm |= gpte.may_execute ? 0UL : _PAGE_EXEC;
pte = __pte(pte_val(pte) & ~perm);
/* What size pte can we insert? */
if (shift > l1_shift) {
u64 mask;
unsigned int actual_shift = PAGE_SHIFT;
if (PMD_SHIFT < l1_shift)
actual_shift = PMD_SHIFT;
mask = (1UL << shift) - (1UL << actual_shift);
pte = __pte(pte_val(pte) | (gpa & mask));
shift = actual_shift;
}
level = kvmppc_radix_shift_to_level(shift);
n_gpa &= ~((1UL << shift) - 1);
/* 4. Insert the pte into our shadow_pgtable */
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
n_rmap = kzalloc(sizeof(*n_rmap), GFP_KERNEL);
if (!n_rmap)
return RESUME_GUEST; /* Let the guest try again */
n_rmap->rmap = (n_gpa & RMAP_NESTED_GPA_MASK) |
(((unsigned long) gp->l1_lpid) << RMAP_NESTED_LPID_SHIFT);
rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
ret = kvmppc_create_pte(kvm, gp->shadow_pgtable, pte, n_gpa, level,
KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings When a host (L0) page which is mapped into a (L1) guest is in turn mapped through to a nested (L2) guest we keep a reverse mapping (rmap) so that these mappings can be retrieved later. Whenever we create an entry in a shadow_pgtable for a nested guest we create a corresponding rmap entry and add it to the list for the L1 guest memslot at the index of the L1 guest page it maps. This means at the L1 guest memslot we end up with lists of rmaps. When we are notified of a host page being invalidated which has been mapped through to a (L1) guest, we can then walk the rmap list for that guest page, and find and invalidate all of the corresponding shadow_pgtable entries. In order to reduce memory consumption, we compress the information for each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits for the guest real page frame number -- which will fit in a single unsigned long. To avoid a scenario where a guest can trigger unbounded memory allocations, we scan the list when adding an entry to see if there is already an entry with the contents we need. This can occur, because we don't ever remove entries from the middle of a list. A struct nested guest rmap is a list pointer and an rmap entry; ---------------- | next pointer | ---------------- | rmap entry | ---------------- Thus the rmap pointer for each guest frame number in the memslot can be either NULL, a single entry, or a pointer to a list of nested rmap entries. gfn memslot rmap array ------------------------- 0 | NULL | (no rmap entry) ------------------------- 1 | single rmap entry | (rmap entry with low bit set) ------------------------- 2 | list head pointer | (list of rmap entries) ------------------------- The final entry always has the lowest bit set and is stored in the next pointer of the last list entry, or as a single rmap entry. With a list of rmap entries looking like; ----------------- ----------------- ------------------------- | list head ptr | ----> | next pointer | ----> | single rmap entry | ----------------- ----------------- ------------------------- | rmap entry | | rmap entry | ----------------- ------------------------- Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:08 +08:00
mmu_seq, gp->shadow_lpid, rmapp, &n_rmap);
if (n_rmap)
kfree(n_rmap);
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
if (ret == -EAGAIN)
ret = RESUME_GUEST; /* Let the guest try again */
return ret;
inval:
kvmhv_invalidate_shadow_pte(vcpu, gp, n_gpa, NULL);
return RESUME_GUEST;
}
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu)
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
{
struct kvm_nested_guest *gp = vcpu->arch.nested;
long int ret;
mutex_lock(&gp->tlb_lock);
KVM: PPC: Book3S HV: Allow passthrough of an emulated device to an L2 guest Allow for a device which is being emulated at L0 (the host) for an L1 guest to be passed through to a nested (L2) guest. The existing kvmppc_hv_emulate_mmio function can be used here. The main challenge is that for a load the result must be stored into the L2 gpr, not an L1 gpr as would normally be the case after going out to qemu to complete the operation. This presents a challenge as at this point the L2 gpr state has been written back into L1 memory. To work around this we store the address in L1 memory of the L2 gpr where the result of the load is to be stored and use the new io_gpr value KVM_MMIO_REG_NESTED_GPR to indicate that this is a nested load for which completion must be done when returning back into the kernel. Then in kvmppc_complete_mmio_load() the resultant value is written into L1 memory at the location of the indicated L2 gpr. Note that we don't currently let an L1 guest emulate a device for an L2 guest which is then passed through to an L3 guest. Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
2018-12-14 13:29:08 +08:00
ret = __kvmhv_nested_page_fault(run, vcpu, gp);
KVM: PPC: Book3S HV: Handle page fault for a nested guest Consider a normal (L1) guest running under the main hypervisor (L0), and then a nested guest (L2) running under the L1 guest which is acting as a nested hypervisor. L0 has page tables to map the address space for L1 providing the translation from L1 real address -> L0 real address; L1 | | (L1 -> L0) | ----> L0 There are also page tables in L1 used to map the address space for L2 providing the translation from L2 real address -> L1 read address. Since the hardware can only walk a single level of page table, we need to maintain in L0 a "shadow_pgtable" for L2 which provides the translation from L2 real address -> L0 real address. Which looks like; L2 L2 | | | (L2 -> L1) | | | ----> L1 | (L2 -> L0) | | | (L1 -> L0) | | | ----> L0 --------> L0 When a page fault occurs while running a nested (L2) guest we need to insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To do this we need to: 1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and provide a page fault to L1 if this mapping doesn't exist. 2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address, or try to insert a pte for that mapping if it doesn't exist. 3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable Once this mapping exists we can take rc faults when hardware is unable to automatically set the reference and change bits in the pte. On these we need to: 1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect the fault down to L1. 2. Set the rc bits in the L1 -> L0 pte which corresponds to the same host page. 3. Set the rc bits in the L2 -> L0 pte. As we reuse a large number of functions in book3s_64_mmu_radix.c for this we also needed to refactor a number of these functions to take an lpid parameter so that the correct lpid is used for tlb invalidations. The functionality however has remained the same. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:07 +08:00
mutex_unlock(&gp->tlb_lock);
return ret;
}
KVM: PPC: Book3S HV: Add nested shadow page tables to debugfs This adds a list of valid shadow PTEs for each nested guest to the 'radix' file for the guest in debugfs. This can be useful for debugging. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-08 13:31:17 +08:00
int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid)
{
int ret = -1;
spin_lock(&kvm->mmu_lock);
while (++lpid <= kvm->arch.max_nested_lpid) {
if (kvm->arch.nested_guests[lpid]) {
ret = lpid;
break;
}
}
spin_unlock(&kvm->mmu_lock);
return ret;
}