Merge the topic branch we're sharing with the kvm-ppc tree.
FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define TRAMP_KVM_BEGIN(name) \
+#define TRAMP_KVM_BEGIN(name) \
- TRAMP_REAL_BEGIN(name)
+ TRAMP_VIRT_BEGIN(name)
#else
#define TRAMP_KVM_BEGIN(name)
#endif
#define H_GET_MPP_X 0x314
#define H_SET_MODE 0x31C
#define H_CLEAR_HPT 0x358
+#define H_RESIZE_HPT_PREPARE 0x36C
+#define H_RESIZE_HPT_COMMIT 0x370
+ #define H_REGISTER_PROC_TBL 0x37C
#define H_SIGNAL_SYS_RESET 0x380
#define MAX_HCALL_OPCODE H_SIGNAL_SYS_RESET
int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
uint32_t pe_num, uint32_t tce_size,
uint64_t dma_addr, uint32_t npages);
- int64_t opal_rm_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
- uint32_t pe_num, uint32_t tce_size,
- uint64_t dma_addr, uint32_t npages);
+int64_t opal_nmmu_set_ptcr(uint64_t chip_id, uint64_t ptcr);
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
#define OV5_XCMO 0x0440 /* Page Coalescing */
#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */
#define OV5_PRRN 0x0540 /* Platform Resource Reassignment */
- #define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */
- #define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */
- #define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */
- #define OV5_SUB_PROCESSORS 0x0F01 /* 1,2,or 4 Sub-Processors supported */
+#define OV5_RESIZE_HPT 0x0601 /* Hash Page Table resizing */
+ #define OV5_PFO_HW_RNG 0x1180 /* PFO Random Number Generator */
+ #define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */
+ #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */
+ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */
+ #define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */
+ #define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */
+ #define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */
+ #define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */
+ #define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */
+ #define OV5_MMU_SLB 0x1800 /* always use SLB */
+ #define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */
/* Option Vector 6: IBM PAPR hints */
#define OV6_LINUX 0x02 /* Linux is our OS */
FTR_SECTION_ELSE
_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common,
EXC_STD, SOFTEN_TEST_PR)
- do_kvm_0x500:
- KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-EXC_REAL_END(hardware_interrupt, 0x500, 0x600)
+EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
-EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x4600)
+EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
.globl hardware_interrupt_relon_hv;
hardware_interrupt_relon_hv:
BEGIN_FTR_SECTION
FTR_SECTION_ELSE
_MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR)
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
-EXC_VIRT_END(hardware_interrupt, 0x4500, 0x4600)
+EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
+ TRAMP_KVM(PACA_EXGEN, 0x500)
+ TRAMP_KVM_HV(PACA_EXGEN, 0x500)
EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ)
b system_call_common ;
#endif
-EXC_REAL_BEGIN(system_call, 0xc00, 0xd00)
+EXC_REAL_BEGIN(system_call, 0xc00, 0x100)
- /*
- * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems
- * that support it) before changing to HMT_MEDIUM. That allows the KVM
- * code to save that value into the guest state (it is the guest's PPR
- * value). Otherwise just change to HMT_MEDIUM as userspace has
- * already saved the PPR.
- */
- #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
- SET_SCRATCH0(r13)
- GET_PACA(r13)
- std r9,PACA_EXGEN+EX_R9(r13)
- OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);
- HMT_MEDIUM;
- std r10,PACA_EXGEN+EX_R10(r13)
- OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR);
- mfcr r9
- KVMTEST_PR(0xc00)
- GET_SCRATCH0(r13)
- #else
- HMT_MEDIUM;
- #endif
+ SYSCALL_KVMTEST
SYSCALL_PSERIES_1
SYSCALL_PSERIES_2_RFID
SYSCALL_PSERIES_3
-EXC_REAL_END(system_call, 0xc00, 0xd00)
+EXC_REAL_END(system_call, 0xc00, 0x100)
-EXC_VIRT_BEGIN(system_call, 0x4c00, 0x4d00)
+EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100)
- HMT_MEDIUM
+ SYSCALL_KVMTEST
SYSCALL_PSERIES_1
SYSCALL_PSERIES_2_DIRECT
SYSCALL_PSERIES_3
TRAMP_KVM(PACA_EXGEN, 0xd00)
EXC_COMMON(single_step_common, 0xd00, single_step_exception)
-EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0xe20)
-EXC_VIRT_OOL_HV(h_data_storage, 0x4e00, 0x4e20, 0xe00)
+EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0x20)
- EXC_VIRT_NONE(0x4e00, 0x20)
++EXC_VIRT_OOL_HV(h_data_storage, 0x4e00, 0x20, 0xe00)
TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00)
EXC_COMMON_BEGIN(h_data_storage_common)
mfspr r10,SPRN_HDAR
b ret_from_except
-EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0xe40)
-EXC_VIRT_OOL_HV(h_instr_storage, 0x4e20, 0x4e40, 0xe20)
+EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0x20)
- EXC_VIRT_NONE(0x4e20, 0x20)
++EXC_VIRT_OOL_HV(h_instr_storage, 0x4e20, 0x20, 0xe20)
TRAMP_KVM_HV(PACA_EXGEN, 0xe20)
EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception)
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
new = kmem_cache_create(name, table_size, align, 0, ctor);
+ if (!new)
+ panic("Could not allocate pgtable cache for order %d", shift);
+
kfree(name);
pgtable_cache[shift - 1] = new;
+
pr_debug("Allocated pgtable cache for order %d\n", shift);
}
-
+ EXPORT_SYMBOL_GPL(pgtable_cache_add); /* used by kvm_hv module */
void pgtable_cache_init(void)
{
OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE);
OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE);
OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR);
- OPAL_CALL_REAL(opal_rm_int_get_xirr, OPAL_INT_GET_XIRR);
OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR);
OPAL_CALL(opal_int_eoi, OPAL_INT_EOI);
- OPAL_CALL_REAL(opal_rm_int_eoi, OPAL_INT_EOI);
OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR);
- OPAL_CALL_REAL(opal_rm_int_set_mfrr, OPAL_INT_SET_MFRR);
OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL);
- OPAL_CALL_REAL(opal_rm_pci_tce_kill, OPAL_PCI_TCE_KILL);
+OPAL_CALL(opal_nmmu_set_ptcr, OPAL_NMMU_SET_PTCR);
__setup("bulk_remove=", disable_bulk_remove);
+#define HPT_RESIZE_TIMEOUT 10000 /* ms */
+
+struct hpt_resize_state {
+ unsigned long shift;
+ int commit_rc;
+};
+
+static int pseries_lpar_resize_hpt_commit(void *data)
+{
+ struct hpt_resize_state *state = data;
+
+ state->commit_rc = plpar_resize_hpt_commit(0, state->shift);
+ if (state->commit_rc != H_SUCCESS)
+ return -EIO;
+
+ /* Hypervisor has transitioned the HTAB, update our globals */
+ ppc64_pft_size = state->shift;
+ htab_size_bytes = 1UL << ppc64_pft_size;
+ htab_hash_mask = (htab_size_bytes >> 7) - 1;
+
+ return 0;
+}
+
+/* Must be called in user context */
+static int pseries_lpar_resize_hpt(unsigned long shift)
+{
+ struct hpt_resize_state state = {
+ .shift = shift,
+ .commit_rc = H_FUNCTION,
+ };
+ unsigned int delay, total_delay = 0;
+ int rc;
+ ktime_t t0, t1, t2;
+
+ might_sleep();
+
+ if (!firmware_has_feature(FW_FEATURE_HPT_RESIZE))
+ return -ENODEV;
+
+ printk(KERN_INFO "lpar: Attempting to resize HPT to shift %lu\n",
+ shift);
+
+ t0 = ktime_get();
+
+ rc = plpar_resize_hpt_prepare(0, shift);
+ while (H_IS_LONG_BUSY(rc)) {
+ delay = get_longbusy_msecs(rc);
+ total_delay += delay;
+ if (total_delay > HPT_RESIZE_TIMEOUT) {
+ /* prepare with shift==0 cancels an in-progress resize */
+ rc = plpar_resize_hpt_prepare(0, 0);
+ if (rc != H_SUCCESS)
+ printk(KERN_WARNING
+ "lpar: Unexpected error %d cancelling timed out HPT resize\n",
+ rc);
+ return -ETIMEDOUT;
+ }
+ msleep(delay);
+ rc = plpar_resize_hpt_prepare(0, shift);
+ };
+
+ switch (rc) {
+ case H_SUCCESS:
+ /* Continue on */
+ break;
+
+ case H_PARAMETER:
+ return -EINVAL;
+ case H_RESOURCE:
+ return -EPERM;
+ default:
+ printk(KERN_WARNING
+ "lpar: Unexpected error %d from H_RESIZE_HPT_PREPARE\n",
+ rc);
+ return -EIO;
+ }
+
+ t1 = ktime_get();
+
+ rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL);
+
+ t2 = ktime_get();
+
+ if (rc != 0) {
+ switch (state.commit_rc) {
+ case H_PTEG_FULL:
+ printk(KERN_WARNING
+ "lpar: Hash collision while resizing HPT\n");
+ return -ENOSPC;
+
+ default:
+ printk(KERN_WARNING
+ "lpar: Unexpected error %d from H_RESIZE_HPT_COMMIT\n",
+ state.commit_rc);
+ return -EIO;
+ };
+ }
+
+ printk(KERN_INFO
+ "lpar: HPT resize to shift %lu complete (%lld ms / %lld ms)\n",
+ shift, (long long) ktime_ms_delta(t1, t0),
+ (long long) ktime_ms_delta(t2, t1));
+
+ return 0;
+}
+
+ /* Actually only used for radix, so far */
+ static int pseries_lpar_register_process_table(unsigned long base,
+ unsigned long page_size, unsigned long table_size)
+ {
+ long rc;
+ unsigned long flags = PROC_TABLE_NEW;
+
+ if (radix_enabled())
+ flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE;
+ for (;;) {
+ rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base,
+ page_size, table_size);
+ if (!H_IS_LONG_BUSY(rc))
+ break;
+ mdelay(get_longbusy_msecs(rc));
+ }
+ if (rc != H_SUCCESS) {
+ pr_err("Failed to register process table (rc=%ld)\n", rc);
+ BUG();
+ }
+ return rc;
+ }
+
void __init hpte_init_pseries(void)
{
mmu_hash_ops.hpte_invalidate = pSeries_lpar_hpte_invalidate;
mmu_hash_ops.flush_hash_range = pSeries_lpar_flush_hash_range;
mmu_hash_ops.hpte_clear_all = pseries_hpte_clear_all;
mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
+ mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
}
+ void radix_init_pseries(void)
+ {
+ pr_info("Using radix MMU under hypervisor\n");
+ register_process_table = pseries_lpar_register_process_table;
+ }
+
#ifdef CONFIG_PPC_SMLPAR
#define CMO_FREE_HINT_DEFAULT 1
static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT;