driver will print ACPI tables for AMD IOMMU during
IOMMU initialization.
+ amd_iommu_intr= [HW,X86-64]
+ Specifies one of the following AMD IOMMU interrupt
+ remapping modes:
+ legacy - Use legacy interrupt remapping mode.
+ vapic - Use virtual APIC mode, which allows IOMMU
+ to inject interrupts directly into guest.
+ This mode requires kvm-amd.avic=1.
+ (Default when IOMMU HW support is present.)
+
amijoy.map= [HW,JOY] Amiga joystick support
Map of devices attached to JOY0DAT and JOY1DAT
Format: <a>,<b>
loops can be debugged more effectively on production
systems.
+ clocksource.arm_arch_timer.fsl-a008585=
+ [ARM64]
+ Format: <bool>
+ Enable/disable the workaround of Freescale/NXP
+ erratum A-008585. This can be useful for KVM
+ guests, if the guest device tree doesn't show the
+ erratum. If unspecified, the workaround is
+ enabled based on the device tree.
+
clearcpuid=BITNUM [X86]
Disable CPUID feature X for the kernel. See
arch/x86/include/asm/cpufeatures.h for the valid bit
determined by the stdout-path property in device
tree's chosen node.
- cdns,<addr>
- Start an early, polled-mode console on a cadence serial
- port at the specified address. The cadence serial port
- must already be setup and configured. Options are not
- yet supported.
+ cdns,<addr>[,options]
+ Start an early, polled-mode console on a Cadence
+ (xuartps) serial port at the specified address. Only
+ supported option is baud rate. If baud rate is not
+ specified, the serial port must already be setup and
+ configured.
uart[8250],io,<addr>[,options]
uart[8250],mmio,<addr>[,options]
Format: <unsigned int> such that (rxsize & ~0x1fffc0) == 0.
Default: 1024
+ gpio-mockup.gpio_mockup_ranges
+ [HW] Sets the ranges of gpiochip of for this device.
+ Format: <start1>,<end1>,<start2>,<end2>...
+
hardlockup_all_cpu_backtrace=
[KNL] Should the hard-lockup detector generate
backtraces on all cpus.
intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle.
- 1 to 6 specify maximum depth of C-state.
+ 1 to 9 specify maximum depth of C-state.
intel_pstate= [X86]
disable
than or equal to this physical address is ignored.
maxcpus= [SMP] Maximum number of processors that an SMP kernel
- should make use of. maxcpus=n : n >= 0 limits the
- kernel to using 'n' processors. n=0 is a special case,
- it is equivalent to "nosmp", which also disables
- the IO APIC.
+ will bring up during bootup. maxcpus=n : n >= 0 limits
+ the kernel to bring up 'n' processors. Surely after
+ bootup you can bring up the other plugged cpu by executing
+ "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
+ only takes effect during system bootup.
+ While n=0 is a special case, it is equivalent to "nosmp",
+ which also disables the IO APIC.
max_loop= [LOOP] The number of loop block devices that get
(loop.max_loop) unconditionally pre-created at init time. The default
nodelayacct [KNL] Disable per-task delay accounting
- nodisconnect [HW,SCSI,M68K] Disables SCSI disconnects.
-
nodsp [SH] Disable hardware DSP at boot time.
noefi Disable EFI runtime services support.
nr_cpus= [SMP] Maximum number of processors that an SMP kernel
could support. nr_cpus=n : n >= 1 limits the kernel to
- supporting 'n' processors. Later in runtime you can not
- use hotplug cpu feature to put more cpu back to online.
- just like you compile the kernel NR_CPUS=n
+ support 'n' processors. It could be larger than the
+ number of already plugged CPU during bootup, later in
+ runtime you can physically add extra cpu until it reaches
+ n. So during boot up some boot time memory for per-cpu
+ variables need be pre-allocated for later physical cpu
+ hot plugging.
nr_uarts= [SERIAL] maximum number of UARTs to be registered.
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
windows need to be expanded.
+ To specify the alignment for several
+ instances of a device, the PCI vendor,
+ device, subvendor, and subdevice may be
+ specified, e.g., 4096@pci:8086:9c22:103c:198f
ecrc= Enable/disable PCIe ECRC (transaction layer
end-to-end CRC checking).
bios: Use BIOS/firmware settings. This is the
u = IGNORE_UAS (don't bind to the uas driver);
w = NO_WP_DETECT (don't test whether the
medium is write-protected).
+ y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
+ even if the device claims no cache)
Example: quirks=0419:aaf5:rl,0421:0433:rc
user_debug= [KNL,ARM]
#include <linux/io.h>
#include <asm/barrier.h>
-
- #define __ACCESS_CP15(CRn, Op1, CRm, Op2) p15, Op1, %0, CRn, CRm, Op2
- #define __ACCESS_CP15_64(Op1, CRm) p15, Op1, %Q0, %R0, CRm
+ #include <asm/cp15.h>
#define ICC_EOIR1 __ACCESS_CP15(c12, 0, c12, 1)
#define ICC_DIR __ACCESS_CP15(c12, 0, c11, 1)
#define ICC_CTLR __ACCESS_CP15(c12, 0, c12, 4)
#define ICC_SRE __ACCESS_CP15(c12, 0, c12, 5)
#define ICC_IGRPEN1 __ACCESS_CP15(c12, 0, c12, 7)
+#define ICC_BPR1 __ACCESS_CP15(c12, 0, c12, 3)
#define ICC_HSRE __ACCESS_CP15(c12, 4, c9, 5)
#define ICH_AP1R2 __AP1Rx(2)
#define ICH_AP1R3 __AP1Rx(3)
+ /* A32-to-A64 mappings used by VGIC save/restore */
+
+ #define CPUIF_MAP(a32, a64) \
+ static inline void write_ ## a64(u32 val) \
+ { \
+ write_sysreg(val, a32); \
+ } \
+ static inline u32 read_ ## a64(void) \
+ { \
+ return read_sysreg(a32); \
+ } \
+
+ #define CPUIF_MAP_LO_HI(a32lo, a32hi, a64) \
+ static inline void write_ ## a64(u64 val) \
+ { \
+ write_sysreg(lower_32_bits(val), a32lo);\
+ write_sysreg(upper_32_bits(val), a32hi);\
+ } \
+ static inline u64 read_ ## a64(void) \
+ { \
+ u64 val = read_sysreg(a32lo); \
+ \
+ val |= (u64)read_sysreg(a32hi) << 32; \
+ \
+ return val; \
+ }
+
+ CPUIF_MAP(ICH_HCR, ICH_HCR_EL2)
+ CPUIF_MAP(ICH_VTR, ICH_VTR_EL2)
+ CPUIF_MAP(ICH_MISR, ICH_MISR_EL2)
+ CPUIF_MAP(ICH_EISR, ICH_EISR_EL2)
+ CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2)
+ CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2)
+ CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2)
+ CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2)
+ CPUIF_MAP(ICH_AP0R1, ICH_AP0R1_EL2)
+ CPUIF_MAP(ICH_AP0R0, ICH_AP0R0_EL2)
+ CPUIF_MAP(ICH_AP1R3, ICH_AP1R3_EL2)
+ CPUIF_MAP(ICH_AP1R2, ICH_AP1R2_EL2)
+ CPUIF_MAP(ICH_AP1R1, ICH_AP1R1_EL2)
+ CPUIF_MAP(ICH_AP1R0, ICH_AP1R0_EL2)
+ CPUIF_MAP(ICC_HSRE, ICC_SRE_EL2)
+ CPUIF_MAP(ICC_SRE, ICC_SRE_EL1)
+
+ CPUIF_MAP_LO_HI(ICH_LR15, ICH_LRC15, ICH_LR15_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR14, ICH_LRC14, ICH_LR14_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR13, ICH_LRC13, ICH_LR13_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR12, ICH_LRC12, ICH_LR12_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR11, ICH_LRC11, ICH_LR11_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR10, ICH_LRC10, ICH_LR10_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR9, ICH_LRC9, ICH_LR9_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR8, ICH_LRC8, ICH_LR8_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR7, ICH_LRC7, ICH_LR7_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR6, ICH_LRC6, ICH_LR6_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR5, ICH_LRC5, ICH_LR5_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR4, ICH_LRC4, ICH_LR4_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR3, ICH_LRC3, ICH_LR3_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR2, ICH_LRC2, ICH_LR2_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR1, ICH_LRC1, ICH_LR1_EL2)
+ CPUIF_MAP_LO_HI(ICH_LR0, ICH_LRC0, ICH_LR0_EL2)
+
+ #define read_gicreg(r) read_##r()
+ #define write_gicreg(v, r) write_##r(v)
+
/* Low-level accessors */
static inline void gic_write_eoir(u32 irq)
{
- asm volatile("mcr " __stringify(ICC_EOIR1) : : "r" (irq));
+ write_sysreg(irq, ICC_EOIR1);
isb();
}
static inline void gic_write_dir(u32 val)
{
- asm volatile("mcr " __stringify(ICC_DIR) : : "r" (val));
+ write_sysreg(val, ICC_DIR);
isb();
}
static inline u32 gic_read_iar(void)
{
- u32 irqstat;
+ u32 irqstat = read_sysreg(ICC_IAR1);
- asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
dsb(sy);
+
return irqstat;
}
static inline void gic_write_pmr(u32 val)
{
- asm volatile("mcr " __stringify(ICC_PMR) : : "r" (val));
+ write_sysreg(val, ICC_PMR);
}
static inline void gic_write_ctlr(u32 val)
{
- asm volatile("mcr " __stringify(ICC_CTLR) : : "r" (val));
+ write_sysreg(val, ICC_CTLR);
isb();
}
static inline void gic_write_grpen1(u32 val)
{
- asm volatile("mcr " __stringify(ICC_IGRPEN1) : : "r" (val));
+ write_sysreg(val, ICC_IGRPEN1);
isb();
}
static inline void gic_write_sgi1r(u64 val)
{
- asm volatile("mcrr " __stringify(ICC_SGI1R) : : "r" (val));
+ write_sysreg(val, ICC_SGI1R);
}
static inline u32 gic_read_sre(void)
{
- u32 val;
-
- asm volatile("mrc " __stringify(ICC_SRE) : "=r" (val));
- return val;
+ return read_sysreg(ICC_SRE);
}
static inline void gic_write_sre(u32 val)
{
- asm volatile("mcr " __stringify(ICC_SRE) : : "r" (val));
+ write_sysreg(val, ICC_SRE);
isb();
}
static inline void gic_write_bpr1(u32 val)
{
- asm volatile("mcr " __stringify(ICC_BPR1) : : "r" (val));
-#if defined(__write_sysreg) && defined(ICC_BPR1)
+ write_sysreg(val, ICC_BPR1);
-#else
- asm volatile("mcr " __stringify(ICC_BPR1) : : "r" (val));
-#endif
}
/*
#define MPIDR_LEVEL_BITS 8
#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+ #define MPIDR_LEVEL_SHIFT(level) (MPIDR_LEVEL_BITS * level)
#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
#define ARM_CPU_IMP_ARM 0x41
+#define ARM_CPU_IMP_DEC 0x44
#define ARM_CPU_IMP_INTEL 0x69
/* ARM implemented processors */
#define ARM_CPU_PART_CORTEX_A15 0x4100c0f0
#define ARM_CPU_PART_MASK 0xff00fff0
+/* DEC implemented cores */
+#define ARM_CPU_PART_SA1100 0x4400a110
+
+/* Intel implemented cores */
+#define ARM_CPU_PART_SA1110 0x6900b110
+#define ARM_CPU_REV_SA1110_A0 0
+#define ARM_CPU_REV_SA1110_B0 4
+#define ARM_CPU_REV_SA1110_B1 5
+#define ARM_CPU_REV_SA1110_B2 6
+#define ARM_CPU_REV_SA1110_B4 8
+
#define ARM_CPU_XSCALE_ARCH_MASK 0xe000
#define ARM_CPU_XSCALE_ARCH_V1 0x2000
#define ARM_CPU_XSCALE_ARCH_V2 0x4000
return read_cpuid(CPUID_ID);
}
+static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
+{
+ return read_cpuid(CPUID_CACHETYPE);
+}
+
#elif defined(CONFIG_CPU_V7M)
static inline unsigned int __attribute_const__ read_cpuid_id(void)
return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID);
}
+static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
+{
+ return readl(BASEADDR_V7M_SCB + V7M_SCB_CTR);
+}
+
#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
static inline unsigned int __attribute_const__ read_cpuid_id(void)
return (read_cpuid_id() & 0xFF000000) >> 24;
}
+static inline unsigned int __attribute_const__ read_cpuid_revision(void)
+{
+ return read_cpuid_id() & 0x0000000f;
+}
+
/*
* The CPU part number is meaningless without referring to the CPU
* implementer: implementers are free to define their own part numbers
return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
}
-static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
-{
- return read_cpuid(CPUID_CACHETYPE);
-}
-
static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
{
return read_cpuid(CPUID_TCM);
return read_cpuid(CPUID_MPIDR);
}
+/* StrongARM-11x0 CPUs */
+#define cpu_is_sa1100() (read_cpuid_part() == ARM_CPU_PART_SA1100)
+#define cpu_is_sa1110() (read_cpuid_part() == ARM_CPU_PART_SA1110)
+
/*
* Intel's XScale3 core supports some v6 features (supersections, L2)
* but advertises itself as v5 as it does not support the v6 ISA. For
return ret;
}
+ bool kvm_arch_has_vcpu_debugfs(void)
+ {
+ return false;
+ }
+
+ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+ {
+ return 0;
+ }
+
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
{
int i;
- kvm_free_stage2_pgd(kvm);
-
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
return -ENOMEM;
}
+ /* set size of VMID supported by CPU */
+ kvm_vmid_bits = kvm_get_vmid_bits();
+ kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
return 0;
}
static int init_vhe_mode(void)
{
- /* set size of VMID supported by CPU */
- kvm_vmid_bits = kvm_get_vmid_bits();
- kvm_info("%d-bit VMID\n", kvm_vmid_bits);
-
kvm_info("VHE mode initialized successfully\n");
return 0;
}
}
}
- /* set size of VMID supported by CPU */
- kvm_vmid_bits = kvm_get_vmid_bits();
- kvm_info("%d-bit VMID\n", kvm_vmid_bits);
-
kvm_info("Hyp mode initialized successfully\n");
return 0;
if (!pgd)
return -ENOMEM;
- kvm_clean_pgd(pgd);
kvm->arch.pgd = pgd;
return 0;
}
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pte = mmu_memory_cache_alloc(cache);
- kvm_clean_pte(pte);
pmd_populate_kernel(NULL, pmd, pte);
get_page(virt_to_page(pmd));
}
int ret, idx;
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+ if (unlikely(!is_iabt && kvm_vcpu_dabt_isextabt(vcpu))) {
+ kvm_inject_vabt(vcpu);
+ return 1;
+ }
+
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
- hyp_idmap_start < kern_hyp_va(~0UL)) {
+ hyp_idmap_start < kern_hyp_va(~0UL) &&
+ hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
+ kvm_free_stage2_pgd(kvm);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+#define ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3)
#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
#include <linux/stringify.h>
#include <asm/barrier.h>
+ #define read_gicreg(r) \
+ ({ \
+ u64 reg; \
+ asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg)); \
+ reg; \
+ })
+
+ #define write_gicreg(v,r) \
+ do { \
+ u64 __val = (v); \
+ asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
+ } while (0)
+
/*
* Low-level accessors
*
isb();
}
+static inline void gic_write_bpr1(u32 val)
+{
+ asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val));
+}
+
#define gic_read_typer(c) readq_relaxed(c)
#define gic_write_irouter(v, c) writeq_relaxed(v, c)
.macro kern_hyp_va reg
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
and \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else
- nop
-alternative_endif
-alternative_if_not ARM64_HYP_OFFSET_LOW
- nop
-alternative_else
+alternative_else_nop_endif
+alternative_if ARM64_HYP_OFFSET_LOW
and \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_endif
+alternative_else_nop_endif
.endm
#else
#define kvm_set_pte(ptep, pte) set_pte(ptep, pte)
#define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd)
- static inline void kvm_clean_pgd(pgd_t *pgd) {}
- static inline void kvm_clean_pmd(pmd_t *pmd) {}
- static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
- static inline void kvm_clean_pte(pte_t *pte) {}
- static inline void kvm_clean_pte_entry(pte_t *pte) {}
-
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
{
pte_val(pte) |= PTE_S2_RDWR;
r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
}
+static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
+{
+ unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
+
+ return (resource_flags & flags) == flags;
+}
+
static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
{
phb->ioda.pe_array[pe_no].phb = phb;
static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
- unsigned long pe = phb->ioda.total_pe_num - 1;
+ long pe;
for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
{
struct pnv_phb *phb = pe->phb;
+ unsigned int pe_num = pe->pe_number;
WARN_ON(pe->pdev);
memset(pe, 0, sizeof(struct pnv_ioda_pe));
- clear_bit(pe->pe_number, phb->ioda.pe_alloc);
+ clear_bit(pe_num, phb->ioda.pe_alloc);
}
/* The default M64 BAR is shared by all PEs */
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
return 0;
}
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
}
#ifdef CONFIG_PCI_MSI
- static void pnv_ioda2_msi_eoi(struct irq_data *d)
+ int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
{
- unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
- struct irq_chip *chip = irq_data_get_irq_chip(d);
struct pnv_phb *phb = container_of(chip, struct pnv_phb,
ioda.irq_chip);
+
+ return opal_pci_msi_eoi(phb->opal_id, hw_irq);
+ }
+
+ static void pnv_ioda2_msi_eoi(struct irq_data *d)
+ {
int64_t rc;
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ struct irq_chip *chip = irq_data_get_irq_chip(d);
- rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
+ rc = pnv_opal_pci_msi_eoi(chip, hw_irq);
WARN_ON_ONCE(rc);
icp_native_eoi(d);
irq_set_chip(virq, &phb->ioda.irq_chip);
}
+ /*
+ * Returns true iff chip is something that we could call
+ * pnv_opal_pci_msi_eoi for.
+ */
+ bool is_pnv_opal_msi(struct irq_chip *chip)
+ {
+ return chip->irq_eoi == pnv_ioda2_msi_eoi;
+ }
+ EXPORT_SYMBOL_GPL(is_pnv_opal_msi);
+
static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg)
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
- if (!pnv_pci_is_m64(phb, res)) {
+ if (!pnv_pci_is_m64_flags(res->flags)) {
dev_warn(&pdev->dev, "Don't support SR-IOV with"
" non M64 VF BAR%d: %pR. \n",
i, res);
* alignment for any 64-bit resource, PCIe doesn't care and
* bridges only do 64-bit prefetchable anyway.
*/
- if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64))
+ if (phb->ioda.m64_segsize && pnv_pci_is_m64_flags(type))
return phb->ioda.m64_segsize;
if (type & IORESOURCE_MEM)
return phb->ioda.m32_segsize;
struct pnv_phb *phb = pe->phb;
struct pnv_ioda_pe *slave, *tmp;
- /* Release slave PEs in compound PE */
- if (pe->flags & PNV_IODA_PE_MASTER) {
- list_for_each_entry_safe(slave, tmp, &pe->slaves, list)
- pnv_ioda_release_pe(slave);
- }
-
list_del(&pe->list);
switch (phb->type) {
case PNV_PHB_IODA1:
pnv_ioda_release_pe_seg(pe);
pnv_ioda_deconfigure_pe(pe->phb, pe);
- pnv_ioda_free_pe(pe);
+
+ /* Release slave PEs in the compound PE */
+ if (pe->flags & PNV_IODA_PE_MASTER) {
+ list_for_each_entry_safe(slave, tmp, &pe->slaves, list) {
+ list_del(&slave->list);
+ pnv_ioda_free_pe(slave);
+ }
+ }
+
+ /*
+ * The PE for root bus can be removed because of hotplug in EEH
+ * recovery for fenced PHB error. We need to mark the PE dead so
+ * that it can be populated again in PCI hot add path. The PE
+ * shouldn't be destroyed as it's the global reserved resource.
+ */
+ if (phb->ioda.root_pe_populated &&
+ phb->ioda.root_pe_idx == pe->pe_number)
+ phb->ioda.root_pe_populated = false;
+ else
+ pnv_ioda_free_pe(pe);
}
static void pnv_pci_release_device(struct pci_dev *pdev)
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return;
+ /*
+ * PCI hotplug can happen as part of EEH error recovery. The @pdn
+ * isn't removed and added afterwards in this scenario. We should
+ * set the PE number in @pdn to an invalid one. Otherwise, the PE's
+ * device count is decreased on removing devices while failing to
+ * be increased on adding devices. It leads to unbalanced PE's device
+ * count and eventually make normal PCI hotplug path broken.
+ */
pe = &phb->ioda.pe_array[pdn->pe_number];
+ pdn->pe_number = IODA_INVALID_PE;
+
WARN_ON(--pe->device_count < 0);
if (pe->device_count == 0)
pnv_ioda_release_pe(pe);
PTFF_QAF);
if (test_facility(17)) { /* MSA */
- __cpacf_query(CPACF_KMAC, kvm_s390_available_subfunc.kmac);
- __cpacf_query(CPACF_KMC, kvm_s390_available_subfunc.kmc);
- __cpacf_query(CPACF_KM, kvm_s390_available_subfunc.km);
- __cpacf_query(CPACF_KIMD, kvm_s390_available_subfunc.kimd);
- __cpacf_query(CPACF_KLMD, kvm_s390_available_subfunc.klmd);
+ __cpacf_query(CPACF_KMAC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmac);
+ __cpacf_query(CPACF_KMC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmc);
+ __cpacf_query(CPACF_KM, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.km);
+ __cpacf_query(CPACF_KIMD, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kimd);
+ __cpacf_query(CPACF_KLMD, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.klmd);
}
if (test_facility(76)) /* MSA3 */
- __cpacf_query(CPACF_PCKMO, kvm_s390_available_subfunc.pckmo);
+ __cpacf_query(CPACF_PCKMO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.pckmo);
if (test_facility(77)) { /* MSA4 */
- __cpacf_query(CPACF_KMCTR, kvm_s390_available_subfunc.kmctr);
- __cpacf_query(CPACF_KMF, kvm_s390_available_subfunc.kmf);
- __cpacf_query(CPACF_KMO, kvm_s390_available_subfunc.kmo);
- __cpacf_query(CPACF_PCC, kvm_s390_available_subfunc.pcc);
+ __cpacf_query(CPACF_KMCTR, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmctr);
+ __cpacf_query(CPACF_KMF, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmf);
+ __cpacf_query(CPACF_KMO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmo);
+ __cpacf_query(CPACF_PCC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.pcc);
}
if (test_facility(57)) /* MSA5 */
- __cpacf_query(CPACF_PPNO, kvm_s390_available_subfunc.ppno);
+ __cpacf_query(CPACF_PPNO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.ppno);
if (MACHINE_HAS_ESOP)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
r = KVM_S390_BSCA_CPU_SLOTS;
- if (sclp.has_esca && sclp.has_64bscao)
+ if (!kvm_s390_use_sca_entries())
+ r = KVM_MAX_VCPUS;
+ else if (sclp.has_esca && sclp.has_64bscao)
r = KVM_S390_ESCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
return rc;
}
+ bool kvm_arch_has_vcpu_debugfs(void)
+ {
+ return false;
+ }
+
+ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+ {
+ return 0;
+ }
+
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
static void sca_del_vcpu(struct kvm_vcpu *vcpu)
{
+ if (!kvm_s390_use_sca_entries())
+ return;
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
{
+ if (!kvm_s390_use_sca_entries()) {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ /* we still need the basic sca for the ipte control */
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ }
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
{
int rc;
+ if (!kvm_s390_use_sca_entries()) {
+ if (id < KVM_MAX_VCPUS)
+ return true;
+ return false;
+ }
if (id < KVM_S390_BSCA_CPU_SLOTS)
return true;
if (!sclp.has_esca || !sclp.has_64bscao)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
- if (test_kvm_facility(vcpu->kvm, 64))
- vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
return -EINVAL;
current->thread.fpu.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
- convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+ (freg_t *) fpu->fprs);
else
- memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
- convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp((freg_t *) fpu->fprs,
+ (__vector128 *) vcpu->run->s.regs.vrs);
else
- memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = current->thread.fpu.fpc;
return 0;
}
if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
kvm_clear_async_pf_completion_queue(vcpu);
}
+ /*
+ * If userspace sets the riccb (e.g. after migration) to a valid state,
+ * we should enable RI here instead of doing the lazy enablement.
+ */
+ if ((kvm_run->kvm_dirty_regs & KVM_SYNC_RICCB) &&
+ test_kvm_facility(vcpu->kvm, 64)) {
+ struct runtime_instr_cb *riccb =
+ (struct runtime_instr_cb *) &kvm_run->s.regs.riccb;
+
+ if (riccb->valid)
+ vcpu->arch.sie_block->ecb3 |= 0x01;
+ }
+
kvm_run->kvm_dirty_regs = 0;
}
return kvm_s390_store_status_unloaded(vcpu, addr);
}
- /*
- * store additional status at address
- */
- int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
- unsigned long gpa)
- {
- /* Only bits 0-53 are used for address formation */
- if (!(gpa & ~0x3ff))
- return 0;
-
- return write_guest_abs(vcpu, gpa & ~0x3ff,
- (void *)&vcpu->run->s.regs.vrs, 512);
- }
-
- int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
- {
- if (!test_kvm_facility(vcpu->kvm, 129))
- return 0;
-
- /*
- * The guest VXRS are in the host VXRs due to the lazy
- * copying in vcpu load/put. We can simply call save_fpu_regs()
- * to save the current register state because we are in the
- * middle of a load/put cycle.
- *
- * Let's update our copies before we save it into the save area.
- */
- save_fpu_regs();
-
- return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
- }
-
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
#include <linux/sched.h>
#include <linux/trace_events.h>
#include <linux/slab.h>
+ #include <linux/amd-iommu.h>
+ #include <linux/hashtable.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
#include <asm/desc.h>
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
+ #include <asm/irq_remapping.h>
#include <asm/virtext.h>
#include "trace.h"
#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0
#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF
+ /* AVIC GATAG is encoded using VM and VCPU IDs */
+ #define AVIC_VCPU_ID_BITS 8
+ #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1)
+
+ #define AVIC_VM_ID_BITS 24
+ #define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS)
+ #define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1)
+
+ #define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
+ (y & AVIC_VCPU_ID_MASK))
+ #define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
+ #define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)
+
static bool erratum_383_found __read_mostly;
static const u32 host_save_user_msrs[] = {
struct page *avic_backing_page;
u64 *avic_physical_id_cache;
bool avic_is_running;
+
+ /*
+ * Per-vcpu list of struct amd_svm_iommu_ir:
+ * This is used mainly to store interrupt remapping information used
+ * when update the vcpu affinity. This avoids the need to scan for
+ * IRTE and try to match ga_tag in the IOMMU driver.
+ */
+ struct list_head ir_list;
+ spinlock_t ir_list_lock;
+ };
+
+ /*
+ * This is a wrapper of struct amd_iommu_ir_data.
+ */
+ struct amd_svm_iommu_ir {
+ struct list_head node; /* Used by SVM for per-vcpu ir_list */
+ void *data; /* Storing pointer to struct amd_ir_data */
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
module_param(avic, int, S_IRUGO);
#endif
+ /* AVIC VM ID bit masks and lock */
+ static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR);
+ static DEFINE_SPINLOCK(avic_vm_id_lock);
+
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
+ /* Note:
+ * This hash table is used to map VM_ID to a struct kvm_arch,
+ * when handling AMD IOMMU GALOG notification to schedule in
+ * a particular vCPU.
+ */
+ #define SVM_VM_DATA_HASH_BITS 8
+ DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
+ static spinlock_t svm_vm_data_hash_lock;
+
+ /* Note:
+ * This function is called from IOMMU driver to notify
+ * SVM to schedule in a particular vCPU of a particular VM.
+ */
+ static int avic_ga_log_notifier(u32 ga_tag)
+ {
+ unsigned long flags;
+ struct kvm_arch *ka = NULL;
+ struct kvm_vcpu *vcpu = NULL;
+ u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag);
+ u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag);
+
+ pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id);
+
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_for_each_possible(svm_vm_data_hash, ka, hnode, vm_id) {
+ struct kvm *kvm = container_of(ka, struct kvm, arch);
+ struct kvm_arch *vm_data = &kvm->arch;
+
+ if (vm_data->avic_vm_id != vm_id)
+ continue;
+ vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
+ break;
+ }
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
+
+ if (!vcpu)
+ return 0;
+
+ /* Note:
+ * At this point, the IOMMU should have already set the pending
+ * bit in the vAPIC backing page. So, we just need to schedule
+ * in the vcpu.
+ */
+ if (vcpu->mode == OUTSIDE_GUEST_MODE)
+ kvm_vcpu_wake_up(vcpu);
+
+ return 0;
+ }
+
static __init int svm_hardware_setup(void)
{
int cpu;
if (avic) {
if (!npt_enabled ||
!boot_cpu_has(X86_FEATURE_AVIC) ||
- !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+ !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
avic = false;
- else
+ } else {
pr_info("AVIC enabled\n");
+
+ hash_init(svm_vm_data_hash);
+ spin_lock_init(&svm_vm_data_hash_lock);
+ amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+ }
}
return 0;
seg->base = 0;
}
- static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu)
- {
- struct vcpu_svm *svm = to_svm(vcpu);
-
- return svm->vmcb->control.tsc_offset;
- }
-
static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
struct vcpu_svm *svm = to_svm(vcpu);
return 0;
}
+ static inline int avic_get_next_vm_id(void)
+ {
+ int id;
+
+ spin_lock(&avic_vm_id_lock);
+
+ /* AVIC VM ID is one-based. */
+ id = find_next_zero_bit(avic_vm_id_bitmap, AVIC_VM_ID_NR, 1);
+ if (id <= AVIC_VM_ID_MASK)
+ __set_bit(id, avic_vm_id_bitmap);
+ else
+ id = -EAGAIN;
+
+ spin_unlock(&avic_vm_id_lock);
+ return id;
+ }
+
+ static inline int avic_free_vm_id(int id)
+ {
+ if (id <= 0 || id > AVIC_VM_ID_MASK)
+ return -EINVAL;
+
+ spin_lock(&avic_vm_id_lock);
+ __clear_bit(id, avic_vm_id_bitmap);
+ spin_unlock(&avic_vm_id_lock);
+ return 0;
+ }
+
static void avic_vm_destroy(struct kvm *kvm)
{
+ unsigned long flags;
struct kvm_arch *vm_data = &kvm->arch;
+ avic_free_vm_id(vm_data->avic_vm_id);
+
if (vm_data->avic_logical_id_table_page)
__free_page(vm_data->avic_logical_id_table_page);
if (vm_data->avic_physical_id_table_page)
__free_page(vm_data->avic_physical_id_table_page);
+
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_del(&vm_data->hnode);
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
}
static int avic_vm_init(struct kvm *kvm)
{
- int err = -ENOMEM;
+ unsigned long flags;
+ int vm_id, err = -ENOMEM;
struct kvm_arch *vm_data = &kvm->arch;
struct page *p_page;
struct page *l_page;
if (!avic)
return 0;
+ vm_id = avic_get_next_vm_id();
+ if (vm_id < 0)
+ return vm_id;
+ vm_data->avic_vm_id = (u32)vm_id;
+
/* Allocating physical APIC ID table (4KB) */
p_page = alloc_page(GFP_KERNEL);
if (!p_page)
vm_data->avic_logical_id_table_page = l_page;
clear_page(page_address(l_page));
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_add(svm_vm_data_hash, &vm_data->hnode, vm_data->avic_vm_id);
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
+
return 0;
free_avic:
return err;
}
- /**
- * This function is called during VCPU halt/unhalt.
- */
- static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+ static inline int
+ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
{
- u64 entry;
- int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
+ int ret = 0;
+ unsigned long flags;
+ struct amd_svm_iommu_ir *ir;
struct vcpu_svm *svm = to_svm(vcpu);
- if (!kvm_vcpu_apicv_active(vcpu))
- return;
-
- svm->avic_is_running = is_run;
+ if (!kvm_arch_has_assigned_device(vcpu->kvm))
+ return 0;
- /* ID = 0xff (broadcast), ID > 0xff (reserved) */
- if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
- return;
+ /*
+ * Here, we go through the per-vcpu ir_list to update all existing
+ * interrupt remapping table entry targeting this vcpu.
+ */
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
- entry = READ_ONCE(*(svm->avic_physical_id_cache));
- WARN_ON(is_run == !!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK));
+ if (list_empty(&svm->ir_list))
+ goto out;
- entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- if (is_run)
- entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+ list_for_each_entry(ir, &svm->ir_list, node) {
+ ret = amd_iommu_update_ga(cpu, r, ir->data);
+ if (ret)
+ break;
+ }
+ out:
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ return ret;
}
static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+ avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
+ svm->avic_is_running);
}
static void avic_vcpu_put(struct kvm_vcpu *vcpu)
return;
entry = READ_ONCE(*(svm->avic_physical_id_cache));
+ if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+ avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
}
+ /**
+ * This function is called during VCPU halt/unhalt.
+ */
+ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+ {
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ svm->avic_is_running = is_run;
+ if (is_run)
+ avic_vcpu_load(vcpu, vcpu->cpu);
+ else
+ avic_vcpu_put(vcpu);
+ }
+
static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_svm *svm = to_svm(vcpu);
err = avic_init_backing_page(&svm->vcpu);
if (err)
goto free_page4;
+
+ INIT_LIST_HEAD(&svm->ir_list);
+ spin_lock_init(&svm->ir_list_lock);
}
/* We initialize this flag to true to make sure that the is_running
kvm_vcpu_wake_up(vcpu);
}
+ static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+ {
+ unsigned long flags;
+ struct amd_svm_iommu_ir *cur;
+
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+ list_for_each_entry(cur, &svm->ir_list, node) {
+ if (cur->data != pi->ir_data)
+ continue;
+ list_del(&cur->node);
+ kfree(cur);
+ break;
+ }
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ }
+
+ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+ {
+ int ret = 0;
+ unsigned long flags;
+ struct amd_svm_iommu_ir *ir;
+
+ /**
+ * In some cases, the existing irte is updaed and re-set,
+ * so we need to check here if it's already been * added
+ * to the ir_list.
+ */
+ if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ struct kvm *kvm = svm->vcpu.kvm;
+ u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
+ struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
+ struct vcpu_svm *prev_svm;
+
+ if (!prev_vcpu) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ prev_svm = to_svm(prev_vcpu);
+ svm_ir_list_del(prev_svm, pi);
+ }
+
+ /**
+ * Allocating new amd_iommu_pi_data, which will get
+ * add to the per-vcpu ir_list.
+ */
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL);
+ if (!ir) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ir->data = pi->ir_data;
+
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+ list_add(&ir->node, &svm->ir_list);
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ out:
+ return ret;
+ }
+
+ /**
+ * Note:
+ * The HW cannot support posting multicast/broadcast
+ * interrupts to a vCPU. So, we still use legacy interrupt
+ * remapping for these kind of interrupts.
+ *
+ * For lowest-priority interrupts, we only support
+ * those with single CPU as the destination, e.g. user
+ * configures the interrupts via /proc/irq or uses
+ * irqbalance to make the interrupts single-CPU.
+ */
+ static int
+ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
+ struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
+ {
+ struct kvm_lapic_irq irq;
+ struct kvm_vcpu *vcpu = NULL;
+
+ kvm_set_msi_irq(kvm, e, &irq);
+
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+ pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
+ __func__, irq.vector);
+ return -1;
+ }
+
+ pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
+ irq.vector);
+ *svm = to_svm(vcpu);
+ vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page);
+ vcpu_info->vector = irq.vector;
+
+ return 0;
+ }
+
+ /*
+ * svm_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+ uint32_t guest_irq, bool set)
+ {
+ struct kvm_kernel_irq_routing_entry *e;
+ struct kvm_irq_routing_table *irq_rt;
+ int idx, ret = -EINVAL;
+
+ if (!kvm_arch_has_assigned_device(kvm) ||
+ !irq_remapping_cap(IRQ_POSTING_CAP))
+ return 0;
+
+ pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
+ __func__, host_irq, guest_irq, set);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+ WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+ hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+ struct vcpu_data vcpu_info;
+ struct vcpu_svm *svm = NULL;
+
+ if (e->type != KVM_IRQ_ROUTING_MSI)
+ continue;
+
+ /**
+ * Here, we setup with legacy mode in the following cases:
+ * 1. When cannot target interrupt to a specific vcpu.
+ * 2. Unsetting posted interrupt.
+ * 3. APIC virtialization is disabled for the vcpu.
+ */
+ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
+ kvm_vcpu_apicv_active(&svm->vcpu)) {
+ struct amd_iommu_pi_data pi;
+
+ /* Try to enable guest_mode in IRTE */
+ pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK;
+ pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id,
+ svm->vcpu.vcpu_id);
+ pi.is_guest_mode = true;
+ pi.vcpu_data = &vcpu_info;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Here, we successfully setting up vcpu affinity in
+ * IOMMU guest mode. Now, we need to store the posted
+ * interrupt information in a per-vcpu ir_list so that
+ * we can reference to them directly when we update vcpu
+ * scheduling information in IOMMU irte.
+ */
+ if (!ret && pi.is_guest_mode)
+ svm_ir_list_add(svm, &pi);
+ } else {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
+
+ if (!ret && svm) {
+ trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
+ host_irq, e->gsi,
+ vcpu_info.vector,
+ vcpu_info.pi_desc_addr, set);
+ }
+
+ if (ret < 0) {
+ pr_err("%s: failed to update PI IRTE\n", __func__);
+ goto out;
+ }
+ }
+
+ ret = 0;
+ out:
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return ret;
+ }
+
static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
avic_handle_ldr_update(vcpu);
}
-static struct kvm_x86_ops svm_x86_ops = {
+static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
.has_wbinvd_exit = svm_has_wbinvd_exit,
- .read_tsc_offset = svm_read_tsc_offset,
.write_tsc_offset = svm_write_tsc_offset,
.adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest,
.read_l1_tsc = svm_read_l1_tsc,
.pmu_ops = &amd_pmu_ops,
.deliver_posted_interrupt = svm_deliver_avic_intr,
+ .update_pi_irte = svm_update_pi_irte,
};
static int __init svm_init(void)
static unsigned long *vmx_msr_bitmap_longmode;
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;
+ static unsigned long *vmx_msr_bitmap_legacy_x2apic_apicv_inactive;
+ static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive;
static unsigned long *vmx_vmread_bitmap;
static unsigned long *vmx_vmwrite_bitmap;
static struct vmcs_config {
int size;
int order;
+ u32 basic_cap;
u32 revision_id;
u32 pin_based_exec_ctrl;
u32 cpu_based_exec_ctrl;
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
+ static inline bool cpu_has_vmx_basic_inout(void)
+ {
+ return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT);
+ }
+
static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
{
return flexpriority_enabled && lapic_in_kernel(vcpu);
else if (cpu_has_secondary_exec_ctrls() &&
(vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
- else
- msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
+ if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) {
+ if (is_long_mode(vcpu))
+ msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
+ else
+ msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
+ } else {
+ if (is_long_mode(vcpu))
+ msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive;
+ else
+ msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive;
+ }
} else {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode;
return host_tsc + tsc_offset;
}
- static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu)
- {
- return vmcs_read64(TSC_OFFSET);
- }
-
/*
* writes 'offset' into guest's timestamp counter offset register
*/
*pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS |
((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
+ if (cpu_has_vmx_basic_inout())
+ *pdata |= VMX_BASIC_INOUT;
break;
case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
case MSR_IA32_VMX_PINBASED_CTLS:
return -EIO;
vmcs_conf->size = vmx_msr_high & 0x1fff;
- vmcs_conf->order = get_order(vmcs_config.size);
+ vmcs_conf->order = get_order(vmcs_conf->size);
+ vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
vmcs_conf->revision_id = vmx_msr_low;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
msr, MSR_TYPE_R | MSR_TYPE_W);
}
- static void vmx_enable_intercept_msr_read_x2apic(u32 msr)
+ static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active)
{
- __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_R);
- __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_R);
+ if (apicv_active) {
+ __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+ msr, MSR_TYPE_R);
+ __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+ msr, MSR_TYPE_R);
+ } else {
+ __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
+ msr, MSR_TYPE_R);
+ __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
+ msr, MSR_TYPE_R);
+ }
}
- static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+ static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active)
{
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_R);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_R);
+ if (apicv_active) {
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+ msr, MSR_TYPE_R);
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+ msr, MSR_TYPE_R);
+ } else {
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
+ msr, MSR_TYPE_R);
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
+ msr, MSR_TYPE_R);
+ }
}
- static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+ static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active)
{
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_W);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_W);
+ if (apicv_active) {
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+ msr, MSR_TYPE_W);
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+ msr, MSR_TYPE_W);
+ } else {
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
+ msr, MSR_TYPE_W);
+ __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
+ msr, MSR_TYPE_W);
+ }
}
static bool vmx_get_enable_apicv(void)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (is_guest_mode(vcpu))
- return;
+ if (!is_guest_mode(vcpu)) {
+ if (!cpu_has_virtual_nmis()) {
+ /*
+ * Tracking the NMI-blocked state in software is built upon
+ * finding the next open IRQ window. This, in turn, depends on
+ * well-behaving guests: They have to keep IRQs disabled at
+ * least as long as the NMI handler runs. Otherwise we may
+ * cause NMI nesting, maybe breaking the guest. But as this is
+ * highly unlikely, we can live with the residual risk.
+ */
+ vmx->soft_vnmi_blocked = 1;
+ vmx->vnmi_blocked_time = 0;
+ }
- if (!cpu_has_virtual_nmis()) {
- /*
- * Tracking the NMI-blocked state in software is built upon
- * finding the next open IRQ window. This, in turn, depends on
- * well-behaving guests: They have to keep IRQs disabled at
- * least as long as the NMI handler runs. Otherwise we may
- * cause NMI nesting, maybe breaking the guest. But as this is
- * highly unlikely, we can live with the residual risk.
- */
- vmx->soft_vnmi_blocked = 1;
- vmx->vnmi_blocked_time = 0;
+ ++vcpu->stat.nmi_injections;
+ vmx->nmi_known_unmasked = false;
}
- ++vcpu->stat.nmi_injections;
- vmx->nmi_known_unmasked = false;
if (vmx->rmode.vm86_active) {
if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return;
}
+
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
}
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
gla_validity = (exit_qualification >> 7) & 0x3;
- if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) {
+ if (gla_validity == 0x2) {
printk(KERN_ERR "EPT: Handling EPT violation failed!\n");
printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
(long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
if (!vmx_msr_bitmap_legacy_x2apic)
goto out2;
+ vmx_msr_bitmap_legacy_x2apic_apicv_inactive =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive)
+ goto out3;
+
vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_msr_bitmap_longmode)
- goto out3;
+ goto out4;
vmx_msr_bitmap_longmode_x2apic =
(unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_msr_bitmap_longmode_x2apic)
- goto out4;
+ goto out5;
+
+ vmx_msr_bitmap_longmode_x2apic_apicv_inactive =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive)
+ goto out6;
vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmread_bitmap)
- goto out6;
+ goto out7;
vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmwrite_bitmap)
- goto out7;
+ goto out8;
memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
- goto out8;
+ goto out9;
}
if (boot_cpu_has(X86_FEATURE_NX))
vmx_msr_bitmap_legacy, PAGE_SIZE);
memcpy(vmx_msr_bitmap_longmode_x2apic,
vmx_msr_bitmap_longmode, PAGE_SIZE);
+ memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive,
+ vmx_msr_bitmap_legacy, PAGE_SIZE);
+ memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive,
+ vmx_msr_bitmap_longmode, PAGE_SIZE);
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+ /*
+ * enable_apicv && kvm_vcpu_apicv_active()
+ */
for (msr = 0x800; msr <= 0x8ff; msr++)
- vmx_disable_intercept_msr_read_x2apic(msr);
+ vmx_disable_intercept_msr_read_x2apic(msr, true);
/* TMCCT */
- vmx_enable_intercept_msr_read_x2apic(0x839);
+ vmx_enable_intercept_msr_read_x2apic(0x839, true);
/* TPR */
- vmx_disable_intercept_msr_write_x2apic(0x808);
+ vmx_disable_intercept_msr_write_x2apic(0x808, true);
/* EOI */
- vmx_disable_intercept_msr_write_x2apic(0x80b);
+ vmx_disable_intercept_msr_write_x2apic(0x80b, true);
/* SELF-IPI */
- vmx_disable_intercept_msr_write_x2apic(0x83f);
+ vmx_disable_intercept_msr_write_x2apic(0x83f, true);
+
+ /*
+ * (enable_apicv && !kvm_vcpu_apicv_active()) ||
+ * !enable_apicv
+ */
+ /* TPR */
+ vmx_disable_intercept_msr_read_x2apic(0x808, false);
+ vmx_disable_intercept_msr_write_x2apic(0x808, false);
if (enable_ept) {
kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
return alloc_kvm_area();
- out8:
+ out9:
free_page((unsigned long)vmx_vmwrite_bitmap);
- out7:
+ out8:
free_page((unsigned long)vmx_vmread_bitmap);
+ out7:
+ free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive);
out6:
free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
- out4:
+ out5:
free_page((unsigned long)vmx_msr_bitmap_longmode);
+ out4:
+ free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive);
out3:
free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
out2:
static __exit void hardware_unsetup(void)
{
free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+ free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive);
free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
+ free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive);
free_page((unsigned long)vmx_msr_bitmap_legacy);
free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_b);
{
/* TODO: not to reset guest simply here. */
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
- pr_warn("kvm: nested vmx abort, indicator %d\n", indicator);
+ pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
}
static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
vmx->nested.vmcs02_num = 0;
hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL);
+ HRTIMER_MODE_REL_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
vmx->nested.vmxon = true;
return;
}
- /*
- * There is not point to enable virtualize x2apic without enable
- * apicv
- */
- if (!cpu_has_vmx_virtualize_x2apic_mode() ||
- !kvm_vcpu_apicv_active(vcpu))
+ if (!cpu_has_vmx_virtualize_x2apic_mode())
return;
if (!cpu_need_tpr_shadow(vcpu))
maxphyaddr = cpuid_maxphyaddr(vcpu);
if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
(addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)",
addr_field, maxphyaddr, count, addr);
return -EINVAL;
for (i = 0; i < count; i++) {
if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
&e, sizeof(e))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
goto fail;
}
if (nested_vmx_load_msr_check(vcpu, &e)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s check failed (%u, 0x%x, 0x%x)\n",
__func__, i, e.index, e.reserved);
goto fail;
msr.index = e.index;
msr.data = e.value;
if (kvm_set_msr(vcpu, &msr)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
__func__, i, e.index, e.value);
goto fail;
if (kvm_vcpu_read_guest(vcpu,
gpa + i * sizeof(e),
&e, 2 * sizeof(u32))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
return -EINVAL;
}
if (nested_vmx_store_msr_check(vcpu, &e)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s check failed (%u, 0x%x, 0x%x)\n",
__func__, i, e.index, e.reserved);
return -EINVAL;
msr_info.host_initiated = false;
msr_info.index = e.index;
if (kvm_get_msr(vcpu, &msr_info)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR (%u, 0x%x)\n",
__func__, i, e.index);
return -EINVAL;
gpa + i * sizeof(e) +
offsetof(struct vmx_msr_entry, value),
&msr_info.data, sizeof(msr_info.data))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
__func__, i, e.index, msr_info.data);
return -EINVAL;
vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
}
+ if (nested_cpu_has_ept(vmcs12))
+ vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
+
if (nested_cpu_has_vid(vmcs12))
vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);
* We are now running in L2, mmu_notifier will force to reload the
* page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
*/
- kvm_vcpu_reload_apic_access_page(vcpu);
+ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
/*
* Exiting from L2 to L1, we're now back to L1 which thinks it just
~FEATURE_CONTROL_LMCE;
}
-static struct kvm_x86_ops vmx_x86_ops = {
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.hardware_setup = hardware_setup,
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
- .read_tsc_offset = vmx_read_tsc_offset,
.write_tsc_offset = vmx_write_tsc_offset,
.adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest,
.read_l1_tsc = vmx_read_l1_tsc,
static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
{
- u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu);
+ u64 curr_offset = vcpu->arch.tsc_offset;
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
+ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+ {
+ kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ vcpu->arch.tsc_offset = offset;
+ }
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct kvm *kvm = vcpu->kvm;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
- ns = get_kernel_ns();
+ ns = ktime_get_boot_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated)
update_ia32_tsc_adjust_msr(vcpu, offset);
- kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
#endif
}
+ static u64 __get_kvmclock_ns(struct kvm *kvm)
+ {
+ struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+ struct kvm_arch *ka = &kvm->arch;
+ s64 ns;
+
+ if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
+ u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+ ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
+ } else {
+ ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+ }
+
+ return ns;
+ }
+
+ u64 get_kvmclock_ns(struct kvm *kvm)
+ {
+ unsigned long flags;
+ s64 ns;
+
+ local_irq_save(flags);
+ ns = __get_kvmclock_ns(kvm);
+ local_irq_restore(flags);
+
+ return ns;
+ }
+
+ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
+ {
+ struct kvm_vcpu_arch *vcpu = &v->arch;
+ struct pvclock_vcpu_time_info guest_hv_clock;
+
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+ &guest_hv_clock, sizeof(guest_hv_clock))))
+ return;
+
+ /* This VCPU is paused, but it's legal for a guest to read another
+ * VCPU's kvmclock, so we really have to follow the specification where
+ * it says that version is odd if data is being modified, and even after
+ * it is consistent.
+ *
+ * Version field updates must be kept separate. This is because
+ * kvm_write_guest_cached might use a "rep movs" instruction, and
+ * writes within a string instruction are weakly ordered. So there
+ * are three writes overall.
+ *
+ * As a small optimization, only write the version field in the first
+ * and third write. The vcpu->pv_time cache is still valid, because the
+ * version field is the first in the struct.
+ */
+ BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+ vcpu->hv_clock.version = guest_hv_clock.version + 1;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+
+ smp_wmb();
+
+ /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
+ vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
+
+ if (vcpu->pvclock_set_guest_stopped_request) {
+ vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
+ vcpu->pvclock_set_guest_stopped_request = false;
+ }
+
+ trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
+
+ smp_wmb();
+
+ vcpu->hv_clock.version++;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+ }
+
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags, tgt_tsc_khz;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
u64 tsc_timestamp, host_tsc;
- struct pvclock_vcpu_time_info guest_hv_clock;
u8 pvclock_flags;
bool use_master_clock;
}
if (!use_master_clock) {
host_tsc = rdtsc();
- kernel_ns = get_kernel_ns();
+ kernel_ns = ktime_get_boot_ns();
}
tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
local_irq_restore(flags);
- if (!vcpu->pv_time_enabled)
- return 0;
+ /* With all the info we got, fill in the values */
if (kvm_has_tsc_control)
tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
vcpu->hw_tsc_khz = tgt_tsc_khz;
}
- /* With all the info we got, fill in the values */
vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_guest_tsc = tsc_timestamp;
- if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
- &guest_hv_clock, sizeof(guest_hv_clock))))
- return 0;
-
- /* This VCPU is paused, but it's legal for a guest to read another
- * VCPU's kvmclock, so we really have to follow the specification where
- * it says that version is odd if data is being modified, and even after
- * it is consistent.
- *
- * Version field updates must be kept separate. This is because
- * kvm_write_guest_cached might use a "rep movs" instruction, and
- * writes within a string instruction are weakly ordered. So there
- * are three writes overall.
- *
- * As a small optimization, only write the version field in the first
- * and third write. The vcpu->pv_time cache is still valid, because the
- * version field is the first in the struct.
- */
- BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
-
- vcpu->hv_clock.version = guest_hv_clock.version + 1;
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
-
- smp_wmb();
-
- /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
- pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
-
- if (vcpu->pvclock_set_guest_stopped_request) {
- pvclock_flags |= PVCLOCK_GUEST_STOPPED;
- vcpu->pvclock_set_guest_stopped_request = false;
- }
-
/* If the host uses TSC clocksource, then it is stable */
+ pvclock_flags = 0;
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
vcpu->hv_clock.flags = pvclock_flags;
- trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
-
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
-
- smp_wmb();
-
- vcpu->hv_clock.version++;
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
+ if (vcpu->pv_time_enabled)
+ kvm_setup_pvclock_page(v);
+ if (v == kvm_get_vcpu(v->kvm, 0))
+ kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
return 0;
}
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_lapic_hv_timer_in_use(vcpu) &&
- kvm_x86_ops->set_hv_timer(vcpu,
- kvm_get_lapic_tscdeadline_msr(vcpu)))
- kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
- kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ kvm_vcpu_write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
/*
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
case KVM_SET_CLOCK: {
struct kvm_clock_data user_ns;
u64 now_ns;
- s64 delta;
r = -EFAULT;
if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
r = 0;
local_irq_disable();
- now_ns = get_kernel_ns();
- delta = user_ns.clock - now_ns;
+ now_ns = __get_kvmclock_ns(kvm);
+ kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
local_irq_enable();
- kvm->arch.kvmclock_offset = delta;
kvm_gen_update_masterclock(kvm);
break;
}
struct kvm_clock_data user_ns;
u64 now_ns;
- local_irq_disable();
- now_ns = get_kernel_ns();
- user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
- local_irq_enable();
+ now_ns = get_kvmclock_ns(kvm);
+ user_ns.clock = now_ns;
user_ns.flags = 0;
memset(&user_ns.pad, 0, sizeof(user_ns.pad));
kvm_put_guest_xcr0(vcpu);
- /* Interrupt is enabled by handle_external_intr() */
kvm_x86_ops->handle_external_intr(vcpu);
++vcpu->stat.exits;
* before any KVM threads can be running. Unfortunately, we can't
* bring the TSCs fully up to date with real time, as we aren't yet far
* enough into CPU bringup that we know how much real time has actually
- * elapsed; our helper function, get_kernel_ns() will be using boot
+ * elapsed; our helper function, ktime_get_boot_ns() will be using boot
* variables that haven't been updated yet.
*
* So we simply find the maximum observed TSC above, then record the
mutex_init(&kvm->arch.apic_map_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
pvclock_update_vm_gtod_copy(kvm);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
bool pri_tlp; /* PASID TLB required for
PPR completions */
u32 errata; /* Bitmap for errata to apply */
+ bool use_vapic; /* Enable device to use vapic mode */
};
/*
}
}
+ #ifdef CONFIG_IRQ_REMAP
+ static int (*iommu_ga_log_notifier)(u32);
+
+ int amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
+ {
+ iommu_ga_log_notifier = notifier;
+
+ return 0;
+ }
+ EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier);
+
+ static void iommu_poll_ga_log(struct amd_iommu *iommu)
+ {
+ u32 head, tail, cnt = 0;
+
+ if (iommu->ga_log == NULL)
+ return;
+
+ head = readl(iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+ tail = readl(iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
+
+ while (head != tail) {
+ volatile u64 *raw;
+ u64 log_entry;
+
+ raw = (u64 *)(iommu->ga_log + head);
+ cnt++;
+
+ /* Avoid memcpy function-call overhead */
+ log_entry = *raw;
+
+ /* Update head pointer of hardware ring-buffer */
+ head = (head + GA_ENTRY_SIZE) % GA_LOG_SIZE;
+ writel(head, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+
+ /* Handle GA entry */
+ switch (GA_REQ_TYPE(log_entry)) {
+ case GA_GUEST_NR:
+ if (!iommu_ga_log_notifier)
+ break;
+
+ pr_debug("AMD-Vi: %s: devid=%#x, ga_tag=%#x\n",
+ __func__, GA_DEVID(log_entry),
+ GA_TAG(log_entry));
+
+ if (iommu_ga_log_notifier(GA_TAG(log_entry)) != 0)
+ pr_err("AMD-Vi: GA log notifier failed.\n");
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ #endif /* CONFIG_IRQ_REMAP */
+
+ #define AMD_IOMMU_INT_MASK \
+ (MMIO_STATUS_EVT_INT_MASK | \
+ MMIO_STATUS_PPR_INT_MASK | \
+ MMIO_STATUS_GALOG_INT_MASK)
+
irqreturn_t amd_iommu_int_thread(int irq, void *data)
{
struct amd_iommu *iommu = (struct amd_iommu *) data;
u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
- while (status & (MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK)) {
- /* Enable EVT and PPR interrupts again */
- writel((MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK),
+ while (status & AMD_IOMMU_INT_MASK) {
+ /* Enable EVT and PPR and GA interrupts again */
+ writel(AMD_IOMMU_INT_MASK,
iommu->mmio_base + MMIO_STATUS_OFFSET);
if (status & MMIO_STATUS_EVT_INT_MASK) {
iommu_poll_ppr_log(iommu);
}
+ #ifdef CONFIG_IRQ_REMAP
+ if (status & MMIO_STATUS_GALOG_INT_MASK) {
+ pr_devel("AMD-Vi: Processing IOMMU GA Log\n");
+ iommu_poll_ga_log(iommu);
+ }
+ #endif
+
/*
* Hardware bug: ERBT1312
* When re-enabling interrupt (by writing 1
* Writes the command to the IOMMUs command buffer and informs the
* hardware about the new command.
*/
-static int iommu_queue_command_sync(struct amd_iommu *iommu,
- struct iommu_cmd *cmd,
- bool sync)
+static int __iommu_queue_command_sync(struct amd_iommu *iommu,
+ struct iommu_cmd *cmd,
+ bool sync)
{
u32 left, tail, head, next_tail;
- unsigned long flags;
again:
- spin_lock_irqsave(&iommu->lock, flags);
head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
if (left <= 2) {
struct iommu_cmd sync_cmd;
- volatile u64 sem = 0;
int ret;
- build_completion_wait(&sync_cmd, (u64)&sem);
- copy_cmd_to_buffer(iommu, &sync_cmd, tail);
+ iommu->cmd_sem = 0;
- spin_unlock_irqrestore(&iommu->lock, flags);
+ build_completion_wait(&sync_cmd, (u64)&iommu->cmd_sem);
+ copy_cmd_to_buffer(iommu, &sync_cmd, tail);
- if ((ret = wait_on_sem(&sem)) != 0)
+ if ((ret = wait_on_sem(&iommu->cmd_sem)) != 0)
return ret;
goto again;
/* We need to sync now to make sure all commands are processed */
iommu->need_sync = sync;
+ return 0;
+}
+
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+ struct iommu_cmd *cmd,
+ bool sync)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&iommu->lock, flags);
+ ret = __iommu_queue_command_sync(iommu, cmd, sync);
spin_unlock_irqrestore(&iommu->lock, flags);
- return 0;
+ return ret;
}
static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
static int iommu_completion_wait(struct amd_iommu *iommu)
{
struct iommu_cmd cmd;
- volatile u64 sem = 0;
+ unsigned long flags;
int ret;
if (!iommu->need_sync)
return 0;
- build_completion_wait(&cmd, (u64)&sem);
- ret = iommu_queue_command_sync(iommu, &cmd, false);
+ build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+
+ iommu->cmd_sem = 0;
+
+ ret = __iommu_queue_command_sync(iommu, &cmd, false);
if (ret)
- return ret;
+ goto out_unlock;
+
+ ret = wait_on_sem(&iommu->cmd_sem);
+
+out_unlock:
+ spin_unlock_irqrestore(&iommu->lock, flags);
- return wait_on_sem(&sem);
+ return ret;
}
static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
if (!iommu)
return;
+ #ifdef CONFIG_IRQ_REMAP
+ if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+ (dom->type == IOMMU_DOMAIN_UNMANAGED))
+ dev_data->use_vapic = 0;
+ #endif
+
iommu_completion_wait(iommu);
}
ret = attach_device(dev, domain);
+ #ifdef CONFIG_IRQ_REMAP
+ if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
+ if (dom->type == IOMMU_DOMAIN_UNMANAGED)
+ dev_data->use_vapic = 1;
+ else
+ dev_data->use_vapic = 0;
+ }
+ #endif
+
iommu_completion_wait(iommu);
return ret;
*
*****************************************************************************/
- union irte {
- u32 val;
- struct {
- u32 valid : 1,
- no_fault : 1,
- int_type : 3,
- rq_eoi : 1,
- dm : 1,
- rsvd_1 : 1,
- destination : 8,
- vector : 8,
- rsvd_2 : 8;
- } fields;
- };
-
- struct irq_2_irte {
- u16 devid; /* Device ID for IRTE table */
- u16 index; /* Index into IRTE table*/
- };
-
- struct amd_ir_data {
- struct irq_2_irte irq_2_irte;
- union irte irte_entry;
- union {
- struct msi_msg msi_entry;
- };
- };
-
static struct irq_chip amd_ir_chip;
#define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6)
amd_iommu_dev_table[devid].data[2] = dte;
}
- #define IRTE_ALLOCATED (~1U)
-
static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
{
struct irq_remap_table *table = NULL;
goto out;
}
- memset(table->table, 0, MAX_IRQS_PER_TABLE * sizeof(u32));
+ if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+ memset(table->table, 0,
+ MAX_IRQS_PER_TABLE * sizeof(u32));
+ else
+ memset(table->table, 0,
+ (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
if (ioapic) {
int i;
for (i = 0; i < 32; ++i)
- table->table[i] = IRTE_ALLOCATED;
+ iommu->irte_ops->set_allocated(table, i);
}
irq_lookup_table[devid] = table;
struct irq_remap_table *table;
unsigned long flags;
int index, c;
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ if (!iommu)
+ return -ENODEV;
table = get_irq_table(devid, false);
if (!table)
for (c = 0, index = table->min_index;
index < MAX_IRQS_PER_TABLE;
++index) {
- if (table->table[index] == 0)
+ if (!iommu->irte_ops->is_allocated(table, index))
c += 1;
else
c = 0;
if (c == count) {
for (; c != 0; --c)
- table->table[index - c + 1] = IRTE_ALLOCATED;
+ iommu->irte_ops->set_allocated(table, index - c + 1);
index -= count - 1;
goto out;
return index;
}
- static int modify_irte(u16 devid, int index, union irte irte)
+ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
+ struct amd_ir_data *data)
+ {
+ struct irq_remap_table *table;
+ struct amd_iommu *iommu;
+ unsigned long flags;
+ struct irte_ga *entry;
+
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu == NULL)
+ return -EINVAL;
+
+ table = get_irq_table(devid, false);
+ if (!table)
+ return -ENOMEM;
+
+ spin_lock_irqsave(&table->lock, flags);
+
+ entry = (struct irte_ga *)table->table;
+ entry = &entry[index];
+ entry->lo.fields_remap.valid = 0;
+ entry->hi.val = irte->hi.val;
+ entry->lo.val = irte->lo.val;
+ entry->lo.fields_remap.valid = 1;
+ if (data)
+ data->ref = entry;
+
+ spin_unlock_irqrestore(&table->lock, flags);
+
+ iommu_flush_irt(iommu, devid);
+ iommu_completion_wait(iommu);
+
+ return 0;
+ }
+
+ static int modify_irte(u16 devid, int index, union irte *irte)
{
struct irq_remap_table *table;
struct amd_iommu *iommu;
return -ENOMEM;
spin_lock_irqsave(&table->lock, flags);
- table->table[index] = irte.val;
+ table->table[index] = irte->val;
spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
return;
spin_lock_irqsave(&table->lock, flags);
- table->table[index] = 0;
+ iommu->irte_ops->clear_allocated(table, index);
spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
}
+ static void irte_prepare(void *entry,
+ u32 delivery_mode, u32 dest_mode,
+ u8 vector, u32 dest_apicid, int devid)
+ {
+ union irte *irte = (union irte *) entry;
+
+ irte->val = 0;
+ irte->fields.vector = vector;
+ irte->fields.int_type = delivery_mode;
+ irte->fields.destination = dest_apicid;
+ irte->fields.dm = dest_mode;
+ irte->fields.valid = 1;
+ }
+
+ static void irte_ga_prepare(void *entry,
+ u32 delivery_mode, u32 dest_mode,
+ u8 vector, u32 dest_apicid, int devid)
+ {
+ struct irte_ga *irte = (struct irte_ga *) entry;
+ struct iommu_dev_data *dev_data = search_dev_data(devid);
+
+ irte->lo.val = 0;
+ irte->hi.val = 0;
+ irte->lo.fields_remap.guest_mode = dev_data ? dev_data->use_vapic : 0;
+ irte->lo.fields_remap.int_type = delivery_mode;
+ irte->lo.fields_remap.dm = dest_mode;
+ irte->hi.fields.vector = vector;
+ irte->lo.fields_remap.destination = dest_apicid;
+ irte->lo.fields_remap.valid = 1;
+ }
+
+ static void irte_activate(void *entry, u16 devid, u16 index)
+ {
+ union irte *irte = (union irte *) entry;
+
+ irte->fields.valid = 1;
+ modify_irte(devid, index, irte);
+ }
+
+ static void irte_ga_activate(void *entry, u16 devid, u16 index)
+ {
+ struct irte_ga *irte = (struct irte_ga *) entry;
+
+ irte->lo.fields_remap.valid = 1;
+ modify_irte_ga(devid, index, irte, NULL);
+ }
+
+ static void irte_deactivate(void *entry, u16 devid, u16 index)
+ {
+ union irte *irte = (union irte *) entry;
+
+ irte->fields.valid = 0;
+ modify_irte(devid, index, irte);
+ }
+
+ static void irte_ga_deactivate(void *entry, u16 devid, u16 index)
+ {
+ struct irte_ga *irte = (struct irte_ga *) entry;
+
+ irte->lo.fields_remap.valid = 0;
+ modify_irte_ga(devid, index, irte, NULL);
+ }
+
+ static void irte_set_affinity(void *entry, u16 devid, u16 index,
+ u8 vector, u32 dest_apicid)
+ {
+ union irte *irte = (union irte *) entry;
+
+ irte->fields.vector = vector;
+ irte->fields.destination = dest_apicid;
+ modify_irte(devid, index, irte);
+ }
+
+ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
+ u8 vector, u32 dest_apicid)
+ {
+ struct irte_ga *irte = (struct irte_ga *) entry;
+ struct iommu_dev_data *dev_data = search_dev_data(devid);
+
+ if (!dev_data || !dev_data->use_vapic) {
+ irte->hi.fields.vector = vector;
+ irte->lo.fields_remap.destination = dest_apicid;
+ irte->lo.fields_remap.guest_mode = 0;
+ modify_irte_ga(devid, index, irte, NULL);
+ }
+ }
+
+ #define IRTE_ALLOCATED (~1U)
+ static void irte_set_allocated(struct irq_remap_table *table, int index)
+ {
+ table->table[index] = IRTE_ALLOCATED;
+ }
+
+ static void irte_ga_set_allocated(struct irq_remap_table *table, int index)
+ {
+ struct irte_ga *ptr = (struct irte_ga *)table->table;
+ struct irte_ga *irte = &ptr[index];
+
+ memset(&irte->lo.val, 0, sizeof(u64));
+ memset(&irte->hi.val, 0, sizeof(u64));
+ irte->hi.fields.vector = 0xff;
+ }
+
+ static bool irte_is_allocated(struct irq_remap_table *table, int index)
+ {
+ union irte *ptr = (union irte *)table->table;
+ union irte *irte = &ptr[index];
+
+ return irte->val != 0;
+ }
+
+ static bool irte_ga_is_allocated(struct irq_remap_table *table, int index)
+ {
+ struct irte_ga *ptr = (struct irte_ga *)table->table;
+ struct irte_ga *irte = &ptr[index];
+
+ return irte->hi.fields.vector != 0;
+ }
+
+ static void irte_clear_allocated(struct irq_remap_table *table, int index)
+ {
+ table->table[index] = 0;
+ }
+
+ static void irte_ga_clear_allocated(struct irq_remap_table *table, int index)
+ {
+ struct irte_ga *ptr = (struct irte_ga *)table->table;
+ struct irte_ga *irte = &ptr[index];
+
+ memset(&irte->lo.val, 0, sizeof(u64));
+ memset(&irte->hi.val, 0, sizeof(u64));
+ }
+
static int get_devid(struct irq_alloc_info *info)
{
int devid = -1;
{
struct irq_2_irte *irte_info = &data->irq_2_irte;
struct msi_msg *msg = &data->msi_entry;
- union irte *irte = &data->irte_entry;
struct IO_APIC_route_entry *entry;
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ if (!iommu)
+ return;
data->irq_2_irte.devid = devid;
data->irq_2_irte.index = index + sub_handle;
-
- /* Setup IRTE for IOMMU */
- irte->val = 0;
- irte->fields.vector = irq_cfg->vector;
- irte->fields.int_type = apic->irq_delivery_mode;
- irte->fields.destination = irq_cfg->dest_apicid;
- irte->fields.dm = apic->irq_dest_mode;
- irte->fields.valid = 1;
+ iommu->irte_ops->prepare(data->entry, apic->irq_delivery_mode,
+ apic->irq_dest_mode, irq_cfg->vector,
+ irq_cfg->dest_apicid, devid);
switch (info->type) {
case X86_IRQ_ALLOC_TYPE_IOAPIC:
}
}
+ struct amd_irte_ops irte_32_ops = {
+ .prepare = irte_prepare,
+ .activate = irte_activate,
+ .deactivate = irte_deactivate,
+ .set_affinity = irte_set_affinity,
+ .set_allocated = irte_set_allocated,
+ .is_allocated = irte_is_allocated,
+ .clear_allocated = irte_clear_allocated,
+ };
+
+ struct amd_irte_ops irte_128_ops = {
+ .prepare = irte_ga_prepare,
+ .activate = irte_ga_activate,
+ .deactivate = irte_ga_deactivate,
+ .set_affinity = irte_ga_set_affinity,
+ .set_allocated = irte_ga_set_allocated,
+ .is_allocated = irte_ga_is_allocated,
+ .clear_allocated = irte_ga_clear_allocated,
+ };
+
static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
struct irq_alloc_info *info = arg;
struct irq_data *irq_data;
- struct amd_ir_data *data;
+ struct amd_ir_data *data = NULL;
struct irq_cfg *cfg;
int i, ret, devid;
int index = -1;
if (!data)
goto out_free_data;
+ if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+ data->entry = kzalloc(sizeof(union irte), GFP_KERNEL);
+ else
+ data->entry = kzalloc(sizeof(struct irte_ga),
+ GFP_KERNEL);
+ if (!data->entry) {
+ kfree(data);
+ goto out_free_data;
+ }
+
irq_data->hwirq = (devid << 16) + i;
irq_data->chip_data = data;
irq_data->chip = &amd_ir_chip;
data = irq_data->chip_data;
irte_info = &data->irq_2_irte;
free_irte(irte_info->devid, irte_info->index);
+ kfree(data->entry);
kfree(data);
}
}
{
struct amd_ir_data *data = irq_data->chip_data;
struct irq_2_irte *irte_info = &data->irq_2_irte;
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
- modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+ if (iommu)
+ iommu->irte_ops->activate(data->entry, irte_info->devid,
+ irte_info->index);
}
static void irq_remapping_deactivate(struct irq_domain *domain,
{
struct amd_ir_data *data = irq_data->chip_data;
struct irq_2_irte *irte_info = &data->irq_2_irte;
- union irte entry;
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
- entry.val = 0;
- modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+ if (iommu)
+ iommu->irte_ops->deactivate(data->entry, irte_info->devid,
+ irte_info->index);
}
static struct irq_domain_ops amd_ir_domain_ops = {
.deactivate = irq_remapping_deactivate,
};
+ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+ {
+ struct amd_iommu *iommu;
+ struct amd_iommu_pi_data *pi_data = vcpu_info;
+ struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
+ struct amd_ir_data *ir_data = data->chip_data;
+ struct irte_ga *irte = (struct irte_ga *) ir_data->entry;
+ struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+ struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid);
+
+ /* Note:
+ * This device has never been set up for guest mode.
+ * we should not modify the IRTE
+ */
+ if (!dev_data || !dev_data->use_vapic)
+ return 0;
+
+ pi_data->ir_data = ir_data;
+
+ /* Note:
+ * SVM tries to set up for VAPIC mode, but we are in
+ * legacy mode. So, we force legacy mode instead.
+ */
+ if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
+ pr_debug("AMD-Vi: %s: Fall back to using intr legacy remap\n",
+ __func__);
+ pi_data->is_guest_mode = false;
+ }
+
+ iommu = amd_iommu_rlookup_table[irte_info->devid];
+ if (iommu == NULL)
+ return -EINVAL;
+
+ pi_data->prev_ga_tag = ir_data->cached_ga_tag;
+ if (pi_data->is_guest_mode) {
+ /* Setting */
+ irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
+ irte->hi.fields.vector = vcpu_pi_info->vector;
+ irte->lo.fields_vapic.guest_mode = 1;
+ irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
+
+ ir_data->cached_ga_tag = pi_data->ga_tag;
+ } else {
+ /* Un-Setting */
+ struct irq_cfg *cfg = irqd_cfg(data);
+
+ irte->hi.val = 0;
+ irte->lo.val = 0;
+ irte->hi.fields.vector = cfg->vector;
+ irte->lo.fields_remap.guest_mode = 0;
+ irte->lo.fields_remap.destination = cfg->dest_apicid;
+ irte->lo.fields_remap.int_type = apic->irq_delivery_mode;
+ irte->lo.fields_remap.dm = apic->irq_dest_mode;
+
+ /*
+ * This communicates the ga_tag back to the caller
+ * so that it can do all the necessary clean up.
+ */
+ ir_data->cached_ga_tag = 0;
+ }
+
+ return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
+ }
+
static int amd_ir_set_affinity(struct irq_data *data,
const struct cpumask *mask, bool force)
{
struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
struct irq_cfg *cfg = irqd_cfg(data);
struct irq_data *parent = data->parent_data;
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[irte_info->devid];
int ret;
+ if (!iommu)
+ return -ENODEV;
+
ret = parent->chip->irq_set_affinity(parent, mask, force);
if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
return ret;
* Atomically updates the IRTE with the new destination, vector
* and flushes the interrupt entry cache.
*/
- ir_data->irte_entry.fields.vector = cfg->vector;
- ir_data->irte_entry.fields.destination = cfg->dest_apicid;
- modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
+ iommu->irte_ops->set_affinity(ir_data->entry, irte_info->devid,
+ irte_info->index, cfg->vector, cfg->dest_apicid);
/*
* After this point, all the interrupts will start arriving
static struct irq_chip amd_ir_chip = {
.irq_ack = ir_ack_apic_edge,
.irq_set_affinity = amd_ir_set_affinity,
+ .irq_set_vcpu_affinity = amd_ir_set_vcpu_affinity,
.irq_compose_msi_msg = ir_compose_msi_msg,
};
return 0;
}
+
+ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
+ {
+ unsigned long flags;
+ struct amd_iommu *iommu;
+ struct irq_remap_table *irt;
+ struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+ int devid = ir_data->irq_2_irte.devid;
+ struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+ struct irte_ga *ref = (struct irte_ga *) ir_data->ref;
+
+ if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+ !ref || !entry || !entry->lo.fields_vapic.guest_mode)
+ return 0;
+
+ iommu = amd_iommu_rlookup_table[devid];
+ if (!iommu)
+ return -ENODEV;
+
+ irt = get_irq_table(devid, false);
+ if (!irt)
+ return -ENODEV;
+
+ spin_lock_irqsave(&irt->lock, flags);
+
+ if (ref->lo.fields_vapic.guest_mode) {
+ if (cpu >= 0)
+ ref->lo.fields_vapic.destination = cpu;
+ ref->lo.fields_vapic.is_run = is_run;
+ barrier();
+ }
+
+ spin_unlock_irqrestore(&irt->lock, flags);
+
+ iommu_flush_irt(iommu, devid);
+ iommu_completion_wait(iommu);
+ return 0;
+ }
+ EXPORT_SYMBOL(amd_iommu_update_ga);
#endif
#include <linux/types.h>
#include <linux/mutex.h>
+ #include <linux/msi.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#define MMIO_EXCL_LIMIT_OFFSET 0x0028
#define MMIO_EXT_FEATURES 0x0030
#define MMIO_PPR_LOG_OFFSET 0x0038
+ #define MMIO_GA_LOG_BASE_OFFSET 0x00e0
+ #define MMIO_GA_LOG_TAIL_OFFSET 0x00e8
#define MMIO_CMD_HEAD_OFFSET 0x2000
#define MMIO_CMD_TAIL_OFFSET 0x2008
#define MMIO_EVT_HEAD_OFFSET 0x2010
#define MMIO_STATUS_OFFSET 0x2020
#define MMIO_PPR_HEAD_OFFSET 0x2030
#define MMIO_PPR_TAIL_OFFSET 0x2038
+ #define MMIO_GA_HEAD_OFFSET 0x2040
+ #define MMIO_GA_TAIL_OFFSET 0x2048
#define MMIO_CNTR_CONF_OFFSET 0x4000
#define MMIO_CNTR_REG_OFFSET 0x40000
#define MMIO_REG_END_OFFSET 0x80000
#define FEATURE_GA (1ULL<<7)
#define FEATURE_HE (1ULL<<8)
#define FEATURE_PC (1ULL<<9)
+ #define FEATURE_GAM_VAPIC (1ULL<<21)
#define FEATURE_PASID_SHIFT 32
#define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT)
#define MMIO_STATUS_EVT_INT_MASK (1 << 1)
#define MMIO_STATUS_COM_WAIT_INT_MASK (1 << 2)
#define MMIO_STATUS_PPR_INT_MASK (1 << 6)
+ #define MMIO_STATUS_GALOG_RUN_MASK (1 << 8)
+ #define MMIO_STATUS_GALOG_OVERFLOW_MASK (1 << 9)
+ #define MMIO_STATUS_GALOG_INT_MASK (1 << 10)
/* event logging constants */
#define EVENT_ENTRY_SIZE 0x10
#define CONTROL_PPFINT_EN 0x0eULL
#define CONTROL_PPR_EN 0x0fULL
#define CONTROL_GT_EN 0x10ULL
+ #define CONTROL_GA_EN 0x11ULL
+ #define CONTROL_GAM_EN 0x19ULL
+ #define CONTROL_GALOG_EN 0x1CULL
+ #define CONTROL_GAINT_EN 0x1DULL
#define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT)
#define CTRL_INV_TO_NONE 0
#define PPR_REQ_FAULT 0x01
+ /* Constants for GA Log handling */
+ #define GA_LOG_ENTRIES 512
+ #define GA_LOG_SIZE_SHIFT 56
+ #define GA_LOG_SIZE_512 (0x8ULL << GA_LOG_SIZE_SHIFT)
+ #define GA_ENTRY_SIZE 8
+ #define GA_LOG_SIZE (GA_ENTRY_SIZE * GA_LOG_ENTRIES)
+
+ #define GA_TAG(x) (u32)(x & 0xffffffffULL)
+ #define GA_DEVID(x) (u16)(((x) >> 32) & 0xffffULL)
+ #define GA_REQ_TYPE(x) (((x) >> 60) & 0xfULL)
+
+ #define GA_GUEST_NR 0x1
+
#define PAGE_MODE_NONE 0x00
#define PAGE_MODE_1_LEVEL 0x01
#define PAGE_MODE_2_LEVEL 0x02
#define IOMMU_CAP_NPCACHE 26
#define IOMMU_CAP_EFR 27
+ /* IOMMU Feature Reporting Field (for IVHD type 10h */
+ #define IOMMU_FEAT_GASUP_SHIFT 6
+
+ /* IOMMU Extended Feature Register (EFR) */
+ #define IOMMU_EFR_GASUP_SHIFT 7
+
#define MAX_DOMAIN_ID 65536
/* Protection domain flags */
struct iommu_domain;
struct irq_domain;
+ struct amd_irte_ops;
/*
* This structure contains generic data for IOMMU protection domains
/* Base of the PPR log, if present */
u8 *ppr_log;
+ /* Base of the GA log, if present */
+ u8 *ga_log;
+
+ /* Tail of the GA log, if present */
+ u8 *ga_log_tail;
+
/* true if interrupts for this IOMMU are already enabled */
bool int_enabled;
#ifdef CONFIG_IRQ_REMAP
struct irq_domain *ir_domain;
struct irq_domain *msi_domain;
+
+ struct amd_irte_ops *irte_ops;
#endif
+
+ volatile u64 __aligned(8) cmd_sem;
};
#define ACPIHID_UID_LEN 256
return -EINVAL;
}
+ enum amd_iommu_intr_mode_type {
+ AMD_IOMMU_GUEST_IR_LEGACY,
+
+ /* This mode is not visible to users. It is used when
+ * we cannot fully enable vAPIC and fallback to only support
+ * legacy interrupt remapping via 128-bit IRTE.
+ */
+ AMD_IOMMU_GUEST_IR_LEGACY_GA,
+ AMD_IOMMU_GUEST_IR_VAPIC,
+ };
+
+ #define AMD_IOMMU_GUEST_IR_GA(x) (x == AMD_IOMMU_GUEST_IR_VAPIC || \
+ x == AMD_IOMMU_GUEST_IR_LEGACY_GA)
+
+ #define AMD_IOMMU_GUEST_IR_VAPIC(x) (x == AMD_IOMMU_GUEST_IR_VAPIC)
+
+ union irte {
+ u32 val;
+ struct {
+ u32 valid : 1,
+ no_fault : 1,
+ int_type : 3,
+ rq_eoi : 1,
+ dm : 1,
+ rsvd_1 : 1,
+ destination : 8,
+ vector : 8,
+ rsvd_2 : 8;
+ } fields;
+ };
+
+ union irte_ga_lo {
+ u64 val;
+
+ /* For int remapping */
+ struct {
+ u64 valid : 1,
+ no_fault : 1,
+ /* ------ */
+ int_type : 3,
+ rq_eoi : 1,
+ dm : 1,
+ /* ------ */
+ guest_mode : 1,
+ destination : 8,
+ rsvd : 48;
+ } fields_remap;
+
+ /* For guest vAPIC */
+ struct {
+ u64 valid : 1,
+ no_fault : 1,
+ /* ------ */
+ ga_log_intr : 1,
+ rsvd1 : 3,
+ is_run : 1,
+ /* ------ */
+ guest_mode : 1,
+ destination : 8,
+ rsvd2 : 16,
+ ga_tag : 32;
+ } fields_vapic;
+ };
+
+ union irte_ga_hi {
+ u64 val;
+ struct {
+ u64 vector : 8,
+ rsvd_1 : 4,
+ ga_root_ptr : 40,
+ rsvd_2 : 12;
+ } fields;
+ };
+
+ struct irte_ga {
+ union irte_ga_lo lo;
+ union irte_ga_hi hi;
+ };
+
+ struct irq_2_irte {
+ u16 devid; /* Device ID for IRTE table */
+ u16 index; /* Index into IRTE table*/
+ };
+
+ struct amd_ir_data {
+ u32 cached_ga_tag;
+ struct irq_2_irte irq_2_irte;
+ struct msi_msg msi_entry;
+ void *entry; /* Pointer to union irte or struct irte_ga */
+ void *ref; /* Pointer to the actual irte */
+ };
+
+ struct amd_irte_ops {
+ void (*prepare)(void *, u32, u32, u8, u32, int);
+ void (*activate)(void *, u16, u16);
+ void (*deactivate)(void *, u16, u16);
+ void (*set_affinity)(void *, u16, u16, u8, u32);
+ void *(*get)(struct irq_remap_table *, int);
+ void (*set_allocated)(struct irq_remap_table *, int);
+ bool (*is_allocated)(struct irq_remap_table *, int);
+ void (*clear_allocated)(struct irq_remap_table *, int);
+ };
+
+ #ifdef CONFIG_IRQ_REMAP
+ extern struct amd_irte_ops irte_32_ops;
+ extern struct amd_irte_ops irte_128_ops;
+ #endif
+
#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */