Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 88bba0a..10df278 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -32,16 +32,10 @@
#define EX_CCR 52
#define EX_CFAR 56
#define EX_PPR 64
-#if defined(CONFIG_RELOCATABLE)
#define EX_CTR 72
.if EX_SIZE != 10
.error "EX_SIZE is wrong"
.endif
-#else
-.if EX_SIZE != 9
- .error "EX_SIZE is wrong"
-.endif
-#endif
/*
* Following are fixed section helper macros.
@@ -50,7 +44,6 @@
* EXC_VIRT_BEGIN/END - virt (AIL), unrelocated exception vectors
* TRAMP_REAL_BEGIN - real, unrelocated helpers (virt may call these)
* TRAMP_VIRT_BEGIN - virt, unreloc helpers (in practice, real can use)
- * TRAMP_KVM_BEGIN - KVM handlers, these are put into real, unrelocated
* EXC_COMMON - After switching to virtual, relocated mode.
*/
@@ -80,13 +73,6 @@
#define TRAMP_VIRT_BEGIN(name) \
FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define TRAMP_KVM_BEGIN(name) \
- TRAMP_VIRT_BEGIN(name)
-#else
-#define TRAMP_KVM_BEGIN(name)
-#endif
-
#define EXC_REAL_NONE(start, size) \
FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size)
@@ -119,67 +105,6 @@
ori reg,reg,(ABS_ADDR(label))@l; \
addis reg,reg,(ABS_ADDR(label))@h
-/* Exception register prefixes */
-#define EXC_HV_OR_STD 2 /* depends on HVMODE */
-#define EXC_HV 1
-#define EXC_STD 0
-
-#if defined(CONFIG_RELOCATABLE)
-/*
- * If we support interrupts with relocation on AND we're a relocatable kernel,
- * we need to use CTR to get to the 2nd level handler. So, save/restore it
- * when required.
- */
-#define SAVE_CTR(reg, area) mfctr reg ; std reg,area+EX_CTR(r13)
-#define GET_CTR(reg, area) ld reg,area+EX_CTR(r13)
-#define RESTORE_CTR(reg, area) ld reg,area+EX_CTR(r13) ; mtctr reg
-#else
-/* ...else CTR is unused and in register. */
-#define SAVE_CTR(reg, area)
-#define GET_CTR(reg, area) mfctr reg
-#define RESTORE_CTR(reg, area)
-#endif
-
-/*
- * PPR save/restore macros used in exceptions-64s.S
- * Used for P7 or later processors
- */
-#define SAVE_PPR(area, ra) \
-BEGIN_FTR_SECTION_NESTED(940) \
- ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \
- std ra,_PPR(r1); \
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940)
-
-#define RESTORE_PPR_PACA(area, ra) \
-BEGIN_FTR_SECTION_NESTED(941) \
- ld ra,area+EX_PPR(r13); \
- mtspr SPRN_PPR,ra; \
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
-
-/*
- * Get an SPR into a register if the CPU has the given feature
- */
-#define OPT_GET_SPR(ra, spr, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- mfspr ra,spr; \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Set an SPR from a register if the CPU has the given feature
- */
-#define OPT_SET_SPR(ra, spr, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- mtspr spr,ra; \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Save a register to the PACA if the CPU has the given feature
- */
-#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \
-BEGIN_FTR_SECTION_NESTED(943) \
- std ra,offset(r13); \
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
/*
* Branch to label using its 0xC000 address. This results in instruction
* address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
@@ -193,89 +118,199 @@
mtctr reg; \
bctr
-.macro INT_KVM_HANDLER name, vec, hsrr, area, skip
- TRAMP_KVM_BEGIN(\name\()_kvm)
- KVM_HANDLER \vec, \hsrr, \area, \skip
+/*
+ * Interrupt code generation macros
+ */
+#define IVEC .L_IVEC_\name\() /* Interrupt vector address */
+#define IHSRR .L_IHSRR_\name\() /* Sets SRR or HSRR registers */
+#define IHSRR_IF_HVMODE .L_IHSRR_IF_HVMODE_\name\() /* HSRR if HV else SRR */
+#define IAREA .L_IAREA_\name\() /* PACA save area */
+#define IVIRT .L_IVIRT_\name\() /* Has virt mode entry point */
+#define IISIDE .L_IISIDE_\name\() /* Uses SRR0/1 not DAR/DSISR */
+#define IDAR .L_IDAR_\name\() /* Uses DAR (or SRR0) */
+#define IDSISR .L_IDSISR_\name\() /* Uses DSISR (or SRR1) */
+#define ISET_RI .L_ISET_RI_\name\() /* Run common code w/ MSR[RI]=1 */
+#define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
+#define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
+#define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */
+#define IKVM_SKIP .L_IKVM_SKIP_\name\() /* Generate KVM skip handler */
+#define IKVM_REAL .L_IKVM_REAL_\name\() /* Real entry tests KVM */
+#define __IKVM_REAL(name) .L_IKVM_REAL_ ## name
+#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
+#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
+#define __ISTACK(name) .L_ISTACK_ ## name
+#define IRECONCILE .L_IRECONCILE_\name\() /* Do RECONCILE_IRQ_STATE */
+#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
+
+#define INT_DEFINE_BEGIN(n) \
+.macro int_define_ ## n name
+
+#define INT_DEFINE_END(n) \
+.endm ; \
+int_define_ ## n n ; \
+do_define_int n
+
+.macro do_define_int name
+ .ifndef IVEC
+ .error "IVEC not defined"
+ .endif
+ .ifndef IHSRR
+ IHSRR=0
+ .endif
+ .ifndef IHSRR_IF_HVMODE
+ IHSRR_IF_HVMODE=0
+ .endif
+ .ifndef IAREA
+ IAREA=PACA_EXGEN
+ .endif
+ .ifndef IVIRT
+ IVIRT=1
+ .endif
+ .ifndef IISIDE
+ IISIDE=0
+ .endif
+ .ifndef IDAR
+ IDAR=0
+ .endif
+ .ifndef IDSISR
+ IDSISR=0
+ .endif
+ .ifndef ISET_RI
+ ISET_RI=1
+ .endif
+ .ifndef IBRANCH_TO_COMMON
+ IBRANCH_TO_COMMON=1
+ .endif
+ .ifndef IREALMODE_COMMON
+ IREALMODE_COMMON=0
+ .else
+ .if ! IBRANCH_TO_COMMON
+ .error "IREALMODE_COMMON=1 but IBRANCH_TO_COMMON=0"
+ .endif
+ .endif
+ .ifndef IMASK
+ IMASK=0
+ .endif
+ .ifndef IKVM_SKIP
+ IKVM_SKIP=0
+ .endif
+ .ifndef IKVM_REAL
+ IKVM_REAL=0
+ .endif
+ .ifndef IKVM_VIRT
+ IKVM_VIRT=0
+ .endif
+ .ifndef ISTACK
+ ISTACK=1
+ .endif
+ .ifndef IRECONCILE
+ IRECONCILE=1
+ .endif
+ .ifndef IKUAP
+ IKUAP=1
+ .endif
.endm
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/*
- * If hv is possible, interrupts come into to the hv version
- * of the kvmppc_interrupt code, which then jumps to the PR handler,
- * kvmppc_interrupt_pr, if the guest is a PR guest.
+ * All interrupts which set HSRR registers, as well as SRESET and MCE and
+ * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
+ * so they all generally need to test whether they were taken in guest context.
+ *
+ * Note: SRESET and MCE may also be sent to the guest by the hypervisor, and be
+ * taken with MSR[HV]=0.
+ *
+ * Interrupts which set SRR registers (with the above exceptions) do not
+ * elevate to MSR[HV]=1 mode, though most can be taken when running with
+ * MSR[HV]=1 (e.g., bare metal kernel and userspace). So these interrupts do
+ * not need to test whether a guest is running because they get delivered to
+ * the guest directly, including nested HV KVM guests.
+ *
+ * The exception is PR KVM, where the guest runs with MSR[PR]=1 and the host
+ * runs with MSR[HV]=0, so the host takes all interrupts on behalf of the
+ * guest. PR KVM runs with LPCR[AIL]=0 which causes interrupts to always be
+ * delivered to the real-mode entry point, therefore such interrupts only test
+ * KVM in their real mode handlers, and only when PR KVM is possible.
+ *
+ * Interrupts that are taken in MSR[HV]=0 and escalate to MSR[HV]=1 are always
+ * delivered in real-mode when the MMU is in hash mode because the MMU
+ * registers are not set appropriately to translate host addresses. In nested
+ * radix mode these can be delivered in virt-mode as the host translations are
+ * used implicitly (see: effective LPID, effective PID).
+ */
+
+/*
+ * If an interrupt is taken while a guest is running, it is immediately routed
+ * to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first
+ * to kvmppc_interrupt_hv, which handles the PR guest case.
*/
#define kvmppc_interrupt kvmppc_interrupt_hv
#else
#define kvmppc_interrupt kvmppc_interrupt_pr
#endif
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
lbz r10,HSTATE_IN_GUEST(r13)
cmpwi r10,0
bne \name\()_kvm
.endm
-.macro KVM_HANDLER vec, hsrr, area, skip
- .if \skip
+.macro GEN_KVM name
+ .balign IFETCH_ALIGN_BYTES
+\name\()_kvm:
+
+ .if IKVM_SKIP
cmpwi r10,KVM_GUEST_MODE_SKIP
beq 89f
.else
-BEGIN_FTR_SECTION_NESTED(947)
- ld r10,\area+EX_CFAR(r13)
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_CFAR(r13)
std r10,HSTATE_CFAR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.endif
-BEGIN_FTR_SECTION_NESTED(948)
- ld r10,\area+EX_PPR(r13)
+ ld r10,IAREA+EX_CTR(r13)
+ mtctr r10
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_PPR(r13)
std r10,HSTATE_PPR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
- ld r10,\area+EX_R10(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ ld r11,IAREA+EX_R11(r13)
+ ld r12,IAREA+EX_R12(r13)
std r12,HSTATE_SCRATCH0(r13)
sldi r12,r9,32
+ ld r9,IAREA+EX_R9(r13)
+ ld r10,IAREA+EX_R10(r13)
/* HSRR variants have the 0x2 bit added to their trap number */
- .if \hsrr == EXC_HV_OR_STD
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
- ori r12,r12,(\vec + 0x2)
+ ori r12,r12,(IVEC + 0x2)
FTR_SECTION_ELSE
- ori r12,r12,(\vec)
+ ori r12,r12,(IVEC)
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- ori r12,r12,(\vec + 0x2)
+ .elseif IHSRR
+ ori r12,r12,(IVEC+ 0x2)
.else
- ori r12,r12,(\vec)
+ ori r12,r12,(IVEC)
.endif
-
-#ifdef CONFIG_RELOCATABLE
- /*
- * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
- * outside the head section. CONFIG_RELOCATABLE KVM expects CTR
- * to be saved in HSTATE_SCRATCH1.
- */
- mfctr r9
- std r9,HSTATE_SCRATCH1(r13)
- __LOAD_FAR_HANDLER(r9, kvmppc_interrupt)
- mtctr r9
- ld r9,\area+EX_R9(r13)
- bctr
-#else
- ld r9,\area+EX_R9(r13)
b kvmppc_interrupt
-#endif
-
- .if \skip
+ .if IKVM_SKIP
89: mtocrf 0x80,r9
- ld r9,\area+EX_R9(r13)
- ld r10,\area+EX_R10(r13)
- .if \hsrr == EXC_HV_OR_STD
+ ld r10,IAREA+EX_CTR(r13)
+ mtctr r10
+ ld r9,IAREA+EX_R9(r13)
+ ld r10,IAREA+EX_R10(r13)
+ ld r11,IAREA+EX_R11(r13)
+ ld r12,IAREA+EX_R12(r13)
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
b kvmppc_skip_Hinterrupt
FTR_SECTION_ELSE
b kvmppc_skip_interrupt
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
+ .elseif IHSRR
b kvmppc_skip_Hinterrupt
.else
b kvmppc_skip_interrupt
@@ -284,107 +319,12 @@
.endm
#else
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
.endm
-.macro KVM_HANDLER name, vec, hsrr, area, skip
+.macro GEN_KVM name
.endm
#endif
-.macro INT_SAVE_SRR_AND_JUMP label, hsrr, set_ri
- ld r10,PACAKMSR(r13) /* get MSR value for kernel */
- .if ! \set_ri
- xori r10,r10,MSR_RI /* Clear MSR_RI */
- .endif
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- mtspr SPRN_HSRR1,r10
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- mtspr SPRN_SRR1,r10
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- mtspr SPRN_HSRR1,r10
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- mtspr SPRN_SRR1,r10
- .endif
- LOAD_HANDLER(r10, \label\())
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mtspr SPRN_HSRR0,r10
- HRFI_TO_KERNEL
- FTR_SECTION_ELSE
- mtspr SPRN_SRR0,r10
- RFI_TO_KERNEL
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mtspr SPRN_HSRR0,r10
- HRFI_TO_KERNEL
- .else
- mtspr SPRN_SRR0,r10
- RFI_TO_KERNEL
- .endif
- b . /* prevent speculative execution */
-.endm
-
-/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */
-.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr
-#ifdef CONFIG_RELOCATABLE
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- .endif
- LOAD_HANDLER(r12, \label\())
- mtctr r12
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- FTR_SECTION_ELSE
- mfspr r12,SPRN_SRR1 /* and HSRR1 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- .else
- mfspr r12,SPRN_SRR1 /* and HSRR1 */
- .endif
- li r10,MSR_RI
- mtmsrd r10,1 /* Set RI (EE=0) */
- bctr
-#else
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- FTR_SECTION_ELSE
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* and HSRR1 */
- .else
- mfspr r11,SPRN_SRR0 /* save SRR0 */
- mfspr r12,SPRN_SRR1 /* and SRR1 */
- .endif
- li r10,MSR_RI
- mtmsrd r10,1 /* Set RI (EE=0) */
- b \label
-#endif
-.endm
-
/*
* This is the BOOK3S interrupt entry code macro.
*
@@ -405,14 +345,41 @@
* - Fall through and continue executing in real, unrelocated mode.
* This is done if early=2.
*/
-.macro INT_HANDLER name, vec, ool=0, early=0, virt=0, hsrr=0, area=PACA_EXGEN, ri=1, dar=0, dsisr=0, bitmask=0, kvm=0
+
+.macro GEN_BRANCH_TO_COMMON name, virt
+ .if IREALMODE_COMMON
+ LOAD_HANDLER(r10, \name\()_common)
+ mtctr r10
+ bctr
+ .else
+ .if \virt
+#ifndef CONFIG_RELOCATABLE
+ b \name\()_common_virt
+#else
+ LOAD_HANDLER(r10, \name\()_common_virt)
+ mtctr r10
+ bctr
+#endif
+ .else
+ LOAD_HANDLER(r10, \name\()_common_real)
+ mtctr r10
+ bctr
+ .endif
+ .endif
+.endm
+
+.macro GEN_INT_ENTRY name, virt, ool=0
SET_SCRATCH0(r13) /* save r13 */
GET_PACA(r13)
- std r9,\area\()+EX_R9(r13) /* save r9 */
- OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR)
+ std r9,IAREA+EX_R9(r13) /* save r9 */
+BEGIN_FTR_SECTION
+ mfspr r9,SPRN_PPR
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
HMT_MEDIUM
- std r10,\area\()+EX_R10(r13) /* save r10 - r12 */
- OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
+ std r10,IAREA+EX_R10(r13) /* save r10 - r12 */
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_CFAR
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.if \ool
.if !\virt
b tramp_real_\name
@@ -425,47 +392,18 @@
.endif
.endif
- OPT_SAVE_REG_TO_PACA(\area\()+EX_PPR, r9, CPU_FTR_HAS_PPR)
- OPT_SAVE_REG_TO_PACA(\area\()+EX_CFAR, r10, CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+ std r9,IAREA+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+ std r10,IAREA+EX_CFAR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
INTERRUPT_TO_KERNEL
- SAVE_CTR(r10, \area\())
+ mfctr r10
+ std r10,IAREA+EX_CTR(r13)
mfcr r9
- .if \kvm
- KVMTEST \name \hsrr \vec
- .endif
- .if \bitmask
- lbz r10,PACAIRQSOFTMASK(r13)
- andi. r10,r10,\bitmask
- /* Associate vector numbers with bits in paca->irq_happened */
- .if \vec == 0x500 || \vec == 0xea0
- li r10,PACA_IRQ_EE
- .elseif \vec == 0x900
- li r10,PACA_IRQ_DEC
- .elseif \vec == 0xa00 || \vec == 0xe80
- li r10,PACA_IRQ_DBELL
- .elseif \vec == 0xe60
- li r10,PACA_IRQ_HMI
- .elseif \vec == 0xf00
- li r10,PACA_IRQ_PMI
- .else
- .abort "Bad maskable vector"
- .endif
-
- .if \hsrr == EXC_HV_OR_STD
- BEGIN_FTR_SECTION
- bne masked_Hinterrupt
- FTR_SECTION_ELSE
- bne masked_interrupt
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
- .elseif \hsrr
- bne masked_Hinterrupt
- .else
- bne masked_interrupt
- .endif
- .endif
-
- std r11,\area\()+EX_R11(r13)
- std r12,\area\()+EX_R12(r13)
+ std r11,IAREA+EX_R11(r13)
+ std r12,IAREA+EX_R12(r13)
/*
* DAR/DSISR, SCRATCH0 must be read before setting MSR[RI],
@@ -473,51 +411,152 @@
* not recoverable if they are live.
*/
GET_SCRATCH0(r10)
- std r10,\area\()+EX_R13(r13)
- .if \dar
- .if \hsrr
+ std r10,IAREA+EX_R13(r13)
+ .if IDAR && !IISIDE
+ .if IHSRR
mfspr r10,SPRN_HDAR
.else
mfspr r10,SPRN_DAR
.endif
- std r10,\area\()+EX_DAR(r13)
+ std r10,IAREA+EX_DAR(r13)
.endif
- .if \dsisr
- .if \hsrr
+ .if IDSISR && !IISIDE
+ .if IHSRR
mfspr r10,SPRN_HDSISR
.else
mfspr r10,SPRN_DSISR
.endif
- stw r10,\area\()+EX_DSISR(r13)
+ stw r10,IAREA+EX_DSISR(r13)
.endif
- .if \early == 2
- /* nothing more */
- .elseif \early
- mfctr r10 /* save ctr, even for !RELOCATABLE */
- BRANCH_TO_C000(r11, \name\()_early_common)
- .elseif !\virt
- INT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr, \ri
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
+ FTR_SECTION_ELSE
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
.else
- INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
.endif
+
+ .if IBRANCH_TO_COMMON
+ GEN_BRANCH_TO_COMMON \name \virt
+ .endif
+
.if \ool
.popsection
.endif
.endm
/*
- * On entry r13 points to the paca, r9-r13 are saved in the paca,
- * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
- * SRR1, and relocation is on.
+ * __GEN_COMMON_ENTRY is required to receive the branch from interrupt
+ * entry, except in the case of the real-mode handlers which require
+ * __GEN_REALMODE_COMMON_ENTRY.
*
- * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
- * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ * This switches to virtual mode and sets MSR[RI].
*/
-.macro INT_COMMON vec, area, stack, kaup, reconcile, dar, dsisr
- .if \stack
+.macro __GEN_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name
+ .endif
+
+ ld r10,PACAKMSR(r13) /* get MSR value for kernel */
+ /* MSR[RI] is clear iff using SRR regs */
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ xori r10,r10,MSR_RI
+ END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+ .elseif ! IHSRR
+ xori r10,r10,MSR_RI
+ .endif
+ mtmsrd r10
+
+ .if IVIRT
+ .if IKVM_VIRT
+ b 1f /* skip the virt test coming from real */
+ .endif
+
+ .balign IFETCH_ALIGN_BYTES
+DEFINE_FIXED_SYMBOL(\name\()_common_virt)
+\name\()_common_virt:
+ .if IKVM_VIRT
+ KVMTEST \name
+1:
+ .endif
+ .endif /* IVIRT */
+.endm
+
+/*
+ * Don't switch to virt mode. Used for early MCE and HMI handlers that
+ * want to run in real mode.
+ */
+.macro __GEN_REALMODE_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name
+ .endif
+.endm
+
+.macro __GEN_COMMON_BODY name
+ .if IMASK
+ .if ! ISTACK
+ .error "No support for masked interrupt to use custom stack"
+ .endif
+
+ /* If coming from user, skip soft-mask tests. */
+ andi. r10,r12,MSR_PR
+ bne 2f
+
+ /* Kernel code running below __end_interrupts is implicitly
+ * soft-masked */
+ LOAD_HANDLER(r10, __end_interrupts)
+ cmpld r11,r10
+ li r10,IMASK
+ blt- 1f
+
+ /* Test the soft mask state against our interrupt's bit */
+ lbz r10,PACAIRQSOFTMASK(r13)
+1: andi. r10,r10,IMASK
+ /* Associate vector numbers with bits in paca->irq_happened */
+ .if IVEC == 0x500 || IVEC == 0xea0
+ li r10,PACA_IRQ_EE
+ .elseif IVEC == 0x900
+ li r10,PACA_IRQ_DEC
+ .elseif IVEC == 0xa00 || IVEC == 0xe80
+ li r10,PACA_IRQ_DBELL
+ .elseif IVEC == 0xe60
+ li r10,PACA_IRQ_HMI
+ .elseif IVEC == 0xf00
+ li r10,PACA_IRQ_PMI
+ .else
+ .abort "Bad maskable vector"
+ .endif
+
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ bne masked_Hinterrupt
+ FTR_SECTION_ELSE
+ bne masked_interrupt
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ bne masked_Hinterrupt
+ .else
+ bne masked_interrupt
+ .endif
+ .endif
+
+ .if ISTACK
andi. r10,r12,MSR_PR /* See if coming from user */
- mr r10,r1 /* Save r1 */
+2: mr r10,r1 /* Save r1 */
subi r1,r1,INT_FRAME_SIZE /* alloc frame on kernel stack */
beq- 100f
ld r1,PACAKSAVE(r13) /* kernel stack to use */
@@ -532,54 +571,67 @@
std r0,GPR0(r1) /* save r0 in stackframe */
std r10,GPR1(r1) /* save r1 in stackframe */
- .if \stack
- .if \kaup
+ .if ISET_RI
+ li r10,MSR_RI
+ mtmsrd r10,1 /* Set MSR_RI */
+ .endif
+
+ .if ISTACK
+ .if IKUAP
kuap_save_amr_and_lock r9, r10, cr1, cr0
.endif
beq 101f /* if from kernel mode */
ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
- SAVE_PPR(\area, r9)
+BEGIN_FTR_SECTION
+ ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
+ std r9,_PPR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
101:
.else
- .if \kaup
+ .if IKUAP
kuap_save_amr_and_lock r9, r10, cr1
.endif
.endif
/* Save original regs values from save area to stack frame. */
- ld r9,\area+EX_R9(r13) /* move r9, r10 to stackframe */
- ld r10,\area+EX_R10(r13)
+ ld r9,IAREA+EX_R9(r13) /* move r9, r10 to stackframe */
+ ld r10,IAREA+EX_R10(r13)
std r9,GPR9(r1)
std r10,GPR10(r1)
- ld r9,\area+EX_R11(r13) /* move r11 - r13 to stackframe */
- ld r10,\area+EX_R12(r13)
- ld r11,\area+EX_R13(r13)
+ ld r9,IAREA+EX_R11(r13) /* move r11 - r13 to stackframe */
+ ld r10,IAREA+EX_R12(r13)
+ ld r11,IAREA+EX_R13(r13)
std r9,GPR11(r1)
std r10,GPR12(r1)
std r11,GPR13(r1)
- .if \dar
- .if \dar == 2
+
+ SAVE_NVGPRS(r1)
+
+ .if IDAR
+ .if IISIDE
ld r10,_NIP(r1)
.else
- ld r10,\area+EX_DAR(r13)
+ ld r10,IAREA+EX_DAR(r13)
.endif
std r10,_DAR(r1)
.endif
- .if \dsisr
- .if \dsisr == 2
+
+ .if IDSISR
+ .if IISIDE
ld r10,_MSR(r1)
lis r11,DSISR_SRR1_MATCH_64S@h
and r10,r10,r11
.else
- lwz r10,\area+EX_DSISR(r13)
+ lwz r10,IAREA+EX_DSISR(r13)
.endif
std r10,_DSISR(r1)
.endif
-BEGIN_FTR_SECTION_NESTED(66)
- ld r10,\area+EX_CFAR(r13)
+
+BEGIN_FTR_SECTION
+ ld r10,IAREA+EX_CFAR(r13)
std r10,ORIG_GPR3(r1)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
- GET_CTR(r10, \area)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ ld r10,IAREA+EX_CTR(r13)
std r10,_CTR(r1)
std r2,GPR2(r1) /* save r2 in stackframe */
SAVE_4GPRS(3, r1) /* save r3 - r6 in stackframe */
@@ -591,32 +643,42 @@
mfspr r11,SPRN_XER /* save XER in stackframe */
std r10,SOFTE(r1)
std r11,_XER(r1)
- li r9,(\vec)+1
+ li r9,IVEC
std r9,_TRAP(r1) /* set trap number */
li r10,0
ld r11,exception_marker@toc(r2)
std r10,RESULT(r1) /* clear regs->result */
std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */
- .if \stack
+ .if ISTACK
ACCOUNT_STOLEN_TIME
.endif
- .if \reconcile
+ .if IRECONCILE
RECONCILE_IRQ_STATE(r10, r11)
.endif
.endm
/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro GEN_COMMON name
+ __GEN_COMMON_ENTRY \name
+ __GEN_COMMON_BODY \name
+.endm
+
+/*
* Restore all registers including H/SRR0/1 saved in a stack frame of a
* standard exception.
*/
-.macro EXCEPTION_RESTORE_REGS hsrr
+.macro EXCEPTION_RESTORE_REGS hsrr=0
/* Move original SRR0 and SRR1 into the respective regs */
ld r9,_MSR(r1)
- .if \hsrr == EXC_HV_OR_STD
- .error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS"
- .endif
.if \hsrr
mtspr SPRN_HSRR1,r9
.else
@@ -670,28 +732,6 @@
#define FINISH_NAP
#endif
-#define EXC_COMMON(name, realvec, hdlr) \
- EXC_COMMON_BEGIN(name); \
- INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \
- bl save_nvgprs; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
- bl hdlr; \
- b ret_from_except
-
-/*
- * Like EXC_COMMON, but for exceptions that can occur in the idle task and
- * therefore need the special idle handling (finish nap and runlatch)
- */
-#define EXC_COMMON_ASYNC(name, realvec, hdlr) \
- EXC_COMMON_BEGIN(name); \
- INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \
- FINISH_NAP; \
- RUNLATCH_ON; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
- bl hdlr; \
- b ret_from_except_lite
-
-
/*
* There are a few constraints to be concerned with.
* - Real mode exceptions code/data must be located at their physical location.
@@ -716,6 +756,9 @@
* guarantee they will be delivered virtually. Some conditions (see the ISA)
* cause exceptions to be delivered in real mode.
*
+ * The scv instructions are a special case. They get a 0x3000 offset applied.
+ * scv exceptions have unique reentrancy properties, see below.
+ *
* It's impossible to receive interrupts below 0x300 via AIL.
*
* KVM: None of the virtual exceptions are from the guest. Anything that
@@ -725,8 +768,8 @@
* We layout physical memory as follows:
* 0x0000 - 0x00ff : Secondary processor spin code
* 0x0100 - 0x18ff : Real mode pSeries interrupt vectors
- * 0x1900 - 0x3fff : Real mode trampolines
- * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
+ * 0x1900 - 0x2fff : Real mode trampolines
+ * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
* 0x5900 - 0x6fff : Relon mode trampolines
* 0x7000 - 0x7fff : FWNMI data area
* 0x8000 - .... : Common interrupt handlers, remaining early
@@ -737,8 +780,8 @@
* vectors there.
*/
OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900)
-OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x4000)
-OPEN_FIXED_SECTION(virt_vectors, 0x4000, 0x5900)
+OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x3000)
+OPEN_FIXED_SECTION(virt_vectors, 0x3000, 0x5900)
OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000)
#ifdef CONFIG_PPC_POWERNV
@@ -774,10 +817,128 @@
.globl __start_interrupts
__start_interrupts:
+/**
+ * Interrupt 0x3000 - System Call Vectored Interrupt (syscall).
+ * This is a synchronous interrupt invoked with the "scv" instruction. The
+ * system call does not alter the HV bit, so it is directed to the OS.
+ *
+ * Handling:
+ * scv instructions enter the kernel without changing EE, RI, ME, or HV.
+ * In particular, this means we can take a maskable interrupt at any point
+ * in the scv handler, which is unlike any other interrupt. This is solved
+ * by treating the instruction addresses below __end_interrupts as being
+ * soft-masked.
+ *
+ * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and
+ * ensure scv is never executed with relocation off, which means AIL-0
+ * should never happen.
+ *
+ * Before leaving the below __end_interrupts text, at least of the following
+ * must be true:
+ * - MSR[PR]=1 (i.e., return to userspace)
+ * - MSR_EE|MSR_RI is set (no reentrant exceptions)
+ * - Standard kernel environment is set up (stack, paca, etc)
+ *
+ * Call convention:
+ *
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ */
+EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
+ /* SCV 0 */
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_tramp
+#else
+ b system_call_vectored_common
+#endif
+ nop
+
+ /* SCV 1 - 127 */
+ .rept 127
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ li r0,-1 /* cause failure */
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_sigill_tramp
+#else
+ b system_call_vectored_sigill
+#endif
+ .endr
+EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
+
+#ifdef CONFIG_RELOCATABLE
+TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_common)
+ mtctr r10
+ bctr
+
+TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_sigill)
+ mtctr r10
+ bctr
+#endif
+
+
/* No virt vectors corresponding with 0x0..0x100 */
EXC_VIRT_NONE(0x4000, 0x100)
+/**
+ * Interrupt 0x100 - System Reset Interrupt (SRESET aka NMI).
+ * This is a non-maskable, asynchronous interrupt always taken in real-mode.
+ * It is caused by:
+ * - Wake from power-saving state, on powernv.
+ * - An NMI from another CPU, triggered by firmware or hypercall.
+ * - As crash/debug signal injected from BMC, firmware or hypervisor.
+ *
+ * Handling:
+ * Power-save wakeup is the only performance critical path, so this is
+ * determined quickly as possible first. In this case volatile registers
+ * can be discarded and SPRs like CFAR don't need to be read.
+ *
+ * If not a powersave wakeup, then it's run as a regular interrupt, however
+ * it uses its own stack and PACA save area to preserve the regular kernel
+ * environment for debugging.
+ *
+ * This interrupt is not maskable, so triggering it when MSR[RI] is clear,
+ * or SCRATCH0 is in use, etc. may cause a crash. It's also not entirely
+ * correct to switch to virtual mode to run the regular interrupt handler
+ * because it might be interrupted when the MMU is in a bad state (e.g., SLB
+ * is clear).
+ *
+ * FWNMI:
+ * PAPR specifies a "fwnmi" facility which sends the sreset to a different
+ * entry point with a different register set up. Some hypervisors will
+ * send the sreset to 0x100 in the guest if it is not fwnmi capable.
+ *
+ * KVM:
+ * Unlike most SRR interrupts, this may be taken by the host while executing
+ * in a guest, so a KVM test is required. KVM will pull the CPU out of guest
+ * mode and then raise the sreset.
+ */
+INT_DEFINE_BEGIN(system_reset)
+ IVEC=0x100
+ IAREA=PACA_EXNMI
+ IVIRT=0 /* no virt entry point */
+ /*
+ * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
+ * being used, so a nested NMI exception would corrupt it.
+ */
+ ISET_RI=0
+ ISTACK=0
+ IRECONCILE=0
+ IKVM_REAL=1
+INT_DEFINE_END(system_reset)
+
EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
#ifdef CONFIG_PPC_P7_NAP
/*
@@ -815,11 +976,8 @@
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif
- INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0, kvm=1
+ GEN_INT_ENTRY system_reset, virt=0
/*
- * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
- * being used, so a nested NMI exception would corrupt it.
- *
* In theory, we should not enable relocation here if it was disabled
* in SRR1, because the MMU may not be configured to support it (e.g.,
* SLB may have been cleared). In practice, there should only be a few
@@ -828,7 +986,6 @@
*/
EXC_REAL_END(system_reset, 0x100, 0x100)
EXC_VIRT_NONE(0x4100, 0x100)
-INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0
#ifdef CONFIG_PPC_P7_NAP
TRAMP_REAL_BEGIN(system_reset_idle_wake)
@@ -843,12 +1000,12 @@
* Vectors for the FWNMI option. Share common code.
*/
TRAMP_REAL_BEGIN(system_reset_fwnmi)
- /* See comment at system_reset exception, don't turn on RI */
- INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0
+ GEN_INT_ENTRY system_reset, virt=0
#endif /* CONFIG_PPC_PSERIES */
EXC_COMMON_BEGIN(system_reset_common)
+ __GEN_COMMON_ENTRY system_reset
/*
* Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
* to recover, but nested NMI will notice in_nmi and not recover
@@ -864,21 +1021,21 @@
mr r10,r1
ld r1,PACA_NMI_EMERG_SP(r13)
subi r1,r1,INT_FRAME_SIZE
- INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0
- bl save_nvgprs
+ __GEN_COMMON_BODY system_reset
/*
- * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+ * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
* the right thing. We do not want to reconcile because that goes
* through irq tracing which we don't want in NMI.
*
- * Save PACAIRQHAPPENED because some code will do a hard disable
- * (e.g., xmon). So we want to restore this back to where it was
- * when we return. DAR is unused in the stack, so save it there.
+ * Save PACAIRQHAPPENED to RESULT (otherwise unused), and set HARD_DIS
+ * as we are running with MSR[EE]=0.
*/
li r10,IRQS_ALL_DISABLED
stb r10,PACAIRQSOFTMASK(r13)
lbz r10,PACAIRQHAPPENED(r13)
- std r10,_DAR(r1)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
addi r3,r1,STACK_FRAME_OVERHEAD
bl system_reset_exception
@@ -897,33 +1054,101 @@
/*
* Restore soft mask settings.
*/
- ld r10,_DAR(r1)
+ ld r10,RESULT(r1)
stb r10,PACAIRQHAPPENED(r13)
ld r10,SOFTE(r1)
stb r10,PACAIRQSOFTMASK(r13)
- EXCEPTION_RESTORE_REGS EXC_STD
+ kuap_restore_amr r9, r10
+ EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
+ GEN_KVM system_reset
-EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
- INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+
+/**
+ * Interrupt 0x200 - Machine Check Interrupt (MCE).
+ * This is a non-maskable interrupt always taken in real-mode. It can be
+ * synchronous or asynchronous, caused by hardware or software, and it may be
+ * taken in a power-saving state.
+ *
+ * Handling:
+ * Similarly to system reset, this uses its own stack and PACA save area,
+ * the difference is re-entrancy is allowed on the machine check stack.
+ *
+ * machine_check_early is run in real mode, and carefully decodes the
+ * machine check and tries to handle it (e.g., flush the SLB if there was an
+ * error detected there), determines if it was recoverable and logs the
+ * event.
+ *
+ * This early code does not "reconcile" irq soft-mask state like SRESET or
+ * regular interrupts do, so irqs_disabled() among other things may not work
+ * properly (irq disable/enable already doesn't work because irq tracing can
+ * not work in real mode).
+ *
+ * Then, depending on the execution context when the interrupt is taken, there
+ * are 3 main actions:
+ * - Executing in kernel mode. The event is queued with irq_work, which means
+ * it is handled when it is next safe to do so (i.e., the kernel has enabled
+ * interrupts), which could be immediately when the interrupt returns. This
+ * avoids nasty issues like switching to virtual mode when the MMU is in a
+ * bad state, or when executing OPAL code. (SRESET is exposed to such issues,
+ * but it has different priorities). Check to see if the CPU was in power
+ * save, and return via the wake up code if it was.
+ *
+ * - Executing in user mode. machine_check_exception is run like a normal
+ * interrupt handler, which processes the data generated by the early handler.
+ *
+ * - Executing in guest mode. The interrupt is run with its KVM test, and
+ * branches to KVM to deal with. KVM may queue the event for the host
+ * to report later.
+ *
+ * This interrupt is not maskable, so if it triggers when MSR[RI] is clear,
+ * or SCRATCH0 is in use, it may cause a crash.
+ *
+ * KVM:
+ * See SRESET.
+ */
+INT_DEFINE_BEGIN(machine_check_early)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ IREALMODE_COMMON=1
/*
* MSR_RI is not enabled, because PACA_EXMC is being used, so a
* nested machine check corrupts it. machine_check_common enables
* MSR_RI.
*/
+ ISET_RI=0
+ ISTACK=0
+ IDAR=1
+ IDSISR=1
+ IRECONCILE=0
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+INT_DEFINE_END(machine_check_early)
+
+INT_DEFINE_BEGIN(machine_check)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ ISET_RI=0
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(machine_check)
+
+EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
+ GEN_INT_ENTRY machine_check_early, virt=0
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
#ifdef CONFIG_PPC_PSERIES
TRAMP_REAL_BEGIN(machine_check_fwnmi)
/* See comment at machine_check exception, don't turn on RI */
- INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+ GEN_INT_ENTRY machine_check_early, virt=0
#endif
-INT_KVM_HANDLER machine_check 0x200, EXC_STD, PACA_EXMC, 1
-
#define MACHINE_CHECK_HANDLER_WINDUP \
/* Clear MSR_RI before setting SRR0 and SRR1. */\
li r9,0; \
@@ -932,12 +1157,10 @@
lhz r12,PACA_IN_MCE(r13); \
subi r12,r12,1; \
sth r12,PACA_IN_MCE(r13); \
- EXCEPTION_RESTORE_REGS EXC_STD
+ EXCEPTION_RESTORE_REGS
EXC_COMMON_BEGIN(machine_check_early_common)
- mtctr r10 /* Restore ctr */
- mfspr r11,SPRN_SRR0
- mfspr r12,SPRN_SRR1
+ __GEN_REALMODE_COMMON_ENTRY machine_check_early
/*
* Switch to mc_emergency stack and handle re-entrancy (we limit
@@ -974,8 +1197,7 @@
bgt cr1,unrecoverable_mce /* Check if we hit limit of 4 */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- /* We don't touch AMR here, we never go to virtual mode */
- INT_COMMON 0x200, PACA_EXMC, 0, 0, 0, 1, 1
+ __GEN_COMMON_BODY machine_check_early
BEGIN_FTR_SECTION
bl enable_machine_check
@@ -983,12 +1205,30 @@
li r10,MSR_RI
mtmsrd r10,1
- bl save_nvgprs
+ /*
+ * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
+ * system_reset_common)
+ */
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ lbz r10,PACAIRQHAPPENED(r13)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
+ /*
+ * Restore soft mask settings.
+ */
+ ld r10,RESULT(r1)
+ stb r10,PACAIRQHAPPENED(r13)
+ ld r10,SOFTE(r1)
+ stb r10,PACAIRQSOFTMASK(r13)
+
#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
@@ -1063,23 +1303,25 @@
mtspr SPRN_CFAR,r10
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
MACHINE_CHECK_HANDLER_WINDUP
- /* See comment at machine_check exception, don't turn on RI */
- INT_HANDLER machine_check, 0x200, area=PACA_EXMC, ri=0, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY machine_check, virt=0
EXC_COMMON_BEGIN(machine_check_common)
/*
* Machine check is different because we use a different
* save area: PACA_EXMC instead of PACA_EXGEN.
*/
- INT_COMMON 0x200, PACA_EXMC, 1, 1, 1, 1, 1
+ GEN_COMMON machine_check
+
FINISH_NAP
/* Enable MSR_RI when finished with PACA_EXMC */
li r10,MSR_RI
mtmsrd r10,1
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_exception
- b ret_from_except
+ b interrupt_return
+
+ GEN_KVM machine_check
+
#ifdef CONFIG_PPC_P7_NAP
/*
@@ -1133,6 +1375,10 @@
andc r10,r10,r3
mtmsrd r10
+ lhz r12,PACA_IN_MCE(r13)
+ subi r12,r12,1
+ sth r12,PACA_IN_MCE(r13)
+
/* Invoke machine_check_exception to print MCE event and panic. */
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_exception
@@ -1146,21 +1392,51 @@
b .
+/**
+ * Interrupt 0x300 - Data Storage Interrupt (DSI).
+ * This is a synchronous interrupt generated due to a data access exception,
+ * e.g., a load orstore which does not have a valid page table entry with
+ * permissions. DAWR matches also fault here, as do RC updates, and minor misc
+ * errors e.g., copy/paste, AMO, certain invalid CI accesses, etc.
+ *
+ * Handling:
+ * - Hash MMU
+ * Go to do_hash_page first to see if the HPT can be filled from an entry in
+ * the Linux page table. Hash faults can hit in kernel mode in a fairly
+ * arbitrary state (e.g., interrupts disabled, locks held) when accessing
+ * "non-bolted" regions, e.g., vmalloc space. However these should always be
+ * backed by Linux page tables.
+ *
+ * If none is found, do a Linux page fault. Linux page faults can happen in
+ * kernel mode due to user copy operations of course.
+ *
+ * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
+ * MMU context, which may cause a DSI in the host, which must go to the
+ * KVM handler. MSR[IR] is not enabled, so the real-mode handler will
+ * always be used regardless of AIL setting.
+ *
+ * - Radix MMU
+ * The hardware loads from the Linux page table directly, so a fault goes
+ * immediately to Linux page fault.
+ *
+ * Conditions like DAWR match are handled on the way in to Linux page fault.
+ */
+INT_DEFINE_BEGIN(data_access)
+ IVEC=0x300
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access)
+
EXC_REAL_BEGIN(data_access, 0x300, 0x80)
- INT_HANDLER data_access, 0x300, ool=1, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY data_access, virt=0
EXC_REAL_END(data_access, 0x300, 0x80)
EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
- INT_HANDLER data_access, 0x300, ool=1, virt=1, dar=1, dsisr=1
+ GEN_INT_ENTRY data_access, virt=1
EXC_VIRT_END(data_access, 0x4300, 0x80)
-INT_KVM_HANDLER data_access, 0x300, EXC_STD, PACA_EXGEN, 1
EXC_COMMON_BEGIN(data_access_common)
- /*
- * Here r13 points to the paca, r9 contains the saved CR,
- * SRR0 and SRR1 are saved in r11 and r12,
- * r9 - r13 are saved in paca->exgen.
- * EX_DAR and EX_DSISR have saved DAR/DSISR
- */
- INT_COMMON 0x300, PACA_EXGEN, 1, 1, 1, 1, 1
+ GEN_COMMON data_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
BEGIN_MMU_FTR_SECTION
@@ -1171,16 +1447,46 @@
b handle_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ GEN_KVM data_access
+
+
+/**
+ * Interrupt 0x380 - Data Segment Interrupt (DSLB).
+ * This is a synchronous interrupt in response to an MMU fault missing SLB
+ * entry for HPT, or an address outside RPT translation range.
+ *
+ * Handling:
+ * - HPT:
+ * This refills the SLB, or reports an access fault similarly to a bad page
+ * fault. When coming from user-mode, the SLB handler may access any kernel
+ * data, though it may itself take a DSLB. When coming from kernel mode,
+ * recursive faults must be avoided so access is restricted to the kernel
+ * image text/data, kernel stack, and any data allocated below
+ * ppc64_bolted_size (first segment). The kernel handler must avoid stomping
+ * on user-handler data structures.
+ *
+ * KVM: Same as 0x300, DSLB must test for KVM guest.
+ *
+ * A dedicated save area EXSLB is used (XXX: but it actually need not be
+ * these days, we could use EXGEN).
+ */
+INT_DEFINE_BEGIN(data_access_slb)
+ IVEC=0x380
+ IAREA=PACA_EXSLB
+ IRECONCILE=0
+ IDAR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access_slb)
EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
- INT_HANDLER data_access_slb, 0x380, ool=1, area=PACA_EXSLB, dar=1, kvm=1
+ GEN_INT_ENTRY data_access_slb, virt=0
EXC_REAL_END(data_access_slb, 0x380, 0x80)
EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
- INT_HANDLER data_access_slb, 0x380, virt=1, area=PACA_EXSLB, dar=1
+ GEN_INT_ENTRY data_access_slb, virt=1
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
-INT_KVM_HANDLER data_access_slb, 0x380, EXC_STD, PACA_EXSLB, 1
EXC_COMMON_BEGIN(data_access_slb_common)
- INT_COMMON 0x380, PACA_EXSLB, 1, 1, 0, 1, 0
+ GEN_COMMON data_access_slb
ld r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
@@ -1188,31 +1494,50 @@
bl do_slb_fault
cmpdi r3,0
bne- 1f
- b fast_exception_return
+ b fast_interrupt_return
1: /* Error case */
MMU_FTR_SECTION_ELSE
/* Radix case, access is outside page table range */
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
ld r4,_DAR(r1)
ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
- b ret_from_except
+ b interrupt_return
+ GEN_KVM data_access_slb
+
+
+/**
+ * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSI, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR), and status in SRR1 (rather than DSISR).
+ */
+INT_DEFINE_BEGIN(instruction_access)
+ IVEC=0x400
+ IISIDE=1
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access)
EXC_REAL_BEGIN(instruction_access, 0x400, 0x80)
- INT_HANDLER instruction_access, 0x400, ool=1, kvm=1
+ GEN_INT_ENTRY instruction_access, virt=0
EXC_REAL_END(instruction_access, 0x400, 0x80)
EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
- INT_HANDLER instruction_access, 0x400, virt=1
+ GEN_INT_ENTRY instruction_access, virt=1
EXC_VIRT_END(instruction_access, 0x4400, 0x80)
-INT_KVM_HANDLER instruction_access, 0x400, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(instruction_access_common)
- INT_COMMON 0x400, PACA_EXGEN, 1, 1, 1, 2, 2
+ GEN_COMMON instruction_access
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
BEGIN_MMU_FTR_SECTION
@@ -1223,16 +1548,37 @@
b handle_page_fault
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+ GEN_KVM instruction_access
+
+
+/**
+ * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSLB, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR).
+ */
+INT_DEFINE_BEGIN(instruction_access_slb)
+ IVEC=0x480
+ IAREA=PACA_EXSLB
+ IRECONCILE=0
+ IISIDE=1
+ IDAR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access_slb)
EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
- INT_HANDLER instruction_access_slb, 0x480, ool=1, area=PACA_EXSLB, kvm=1
+ GEN_INT_ENTRY instruction_access_slb, virt=0
EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
- INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB
+ GEN_INT_ENTRY instruction_access_slb, virt=1
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
-INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0
EXC_COMMON_BEGIN(instruction_access_slb_common)
- INT_COMMON 0x480, PACA_EXSLB, 1, 1, 0, 2, 0
+ GEN_COMMON instruction_access_slb
ld r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
@@ -1240,54 +1586,125 @@
bl do_slb_fault
cmpdi r3,0
bne- 1f
- b fast_exception_return
+ b fast_interrupt_return
1: /* Error case */
MMU_FTR_SECTION_ELSE
/* Radix case, access is outside page table range */
li r3,-EFAULT
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
ld r4,_DAR(r1)
ld r5,RESULT(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_bad_slb_fault
- b ret_from_except
+ b interrupt_return
+
+ GEN_KVM instruction_access_slb
+
+
+/**
+ * Interrupt 0x500 - External Interrupt.
+ * This is an asynchronous maskable interrupt in response to an "external
+ * exception" from the interrupt controller or hypervisor (e.g., device
+ * interrupt). It is maskable in hardware by clearing MSR[EE], and
+ * soft-maskable with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * When running in HV mode, Linux sets up the LPCR[LPES] bit such that
+ * interrupts are delivered with HSRR registers, guests use SRRs, which
+ * reqiures IHSRR_IF_HVMODE.
+ *
+ * On bare metal POWER9 and later, Linux sets the LPCR[HVICE] bit such that
+ * external interrupts are delivered as Hypervisor Virtualization Interrupts
+ * rather than External Interrupts.
+ *
+ * Handling:
+ * This calls into Linux IRQ handler. NVGPRs are not saved to reduce overhead,
+ * because registers at the time of the interrupt are not so important as it is
+ * asynchronous.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(hardware_interrupt)
+ IVEC=0x500
+ IHSRR_IF_HVMODE=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(hardware_interrupt)
EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
- INT_HANDLER hardware_interrupt, 0x500, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY hardware_interrupt, virt=0
EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
- INT_HANDLER hardware_interrupt, 0x500, virt=1, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY hardware_interrupt, virt=1
EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
-INT_KVM_HANDLER hardware_interrupt, 0x500, EXC_HV_OR_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ)
+EXC_COMMON_BEGIN(hardware_interrupt_common)
+ GEN_COMMON hardware_interrupt
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_IRQ
+ b interrupt_return
+ GEN_KVM hardware_interrupt
+
+
+/**
+ * Interrupt 0x600 - Alignment Interrupt
+ * This is a synchronous interrupt in response to data alignment fault.
+ */
+INT_DEFINE_BEGIN(alignment)
+ IVEC=0x600
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(alignment)
EXC_REAL_BEGIN(alignment, 0x600, 0x100)
- INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY alignment, virt=0
EXC_REAL_END(alignment, 0x600, 0x100)
EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
- INT_HANDLER alignment, 0x600, virt=1, dar=1, dsisr=1
+ GEN_INT_ENTRY alignment, virt=1
EXC_VIRT_END(alignment, 0x4600, 0x100)
-INT_KVM_HANDLER alignment, 0x600, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(alignment_common)
- INT_COMMON 0x600, PACA_EXGEN, 1, 1, 1, 1, 1
- bl save_nvgprs
+ GEN_COMMON alignment
addi r3,r1,STACK_FRAME_OVERHEAD
bl alignment_exception
- b ret_from_except
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM alignment
+
+
+/**
+ * Interrupt 0x700 - Program Interrupt (program check).
+ * This is a synchronous interrupt in response to various instruction faults:
+ * traps, privilege errors, TM errors, floating point exceptions.
+ *
+ * Handling:
+ * This interrupt may use the "emergency stack" in some cases when being taken
+ * from kernel context, which complicates handling.
+ */
+INT_DEFINE_BEGIN(program_check)
+ IVEC=0x700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(program_check)
EXC_REAL_BEGIN(program_check, 0x700, 0x100)
- INT_HANDLER program_check, 0x700, kvm=1
+ GEN_INT_ENTRY program_check, virt=0
EXC_REAL_END(program_check, 0x700, 0x100)
EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
- INT_HANDLER program_check, 0x700, virt=1
+ GEN_INT_ENTRY program_check, virt=1
EXC_VIRT_END(program_check, 0x4700, 0x100)
-INT_KVM_HANDLER program_check, 0x700, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(program_check_common)
+ __GEN_COMMON_ENTRY program_check
+
/*
* It's possible to receive a TM Bad Thing type program check with
* userspace register values (in particular r1), but with SRR1 reporting
@@ -1298,42 +1715,64 @@
*/
andi. r10,r12,MSR_PR
- bne 2f /* If userspace, go normal path */
+ bne .Lnormal_stack /* If userspace, go normal path */
andis. r10,r12,(SRR1_PROGTM)@h
- bne 1f /* If TM, emergency */
+ bne .Lemergency_stack /* If TM, emergency */
cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */
- blt 2f /* normal path if not */
+ blt .Lnormal_stack /* normal path if not */
/* Use the emergency stack */
-1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */
+.Lemergency_stack:
+ andi. r10,r12,MSR_PR /* Set CR0 correctly for label */
/* 3 in EXCEPTION_PROLOG_COMMON */
mr r10,r1 /* Save r1 */
ld r1,PACAEMERGSP(r13) /* Use emergency stack */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0
- b 3f
-2:
- INT_COMMON 0x700, PACA_EXGEN, 1, 1, 1, 0, 0
-3:
- bl save_nvgprs
+ __ISTACK(program_check)=0
+ __GEN_COMMON_BODY program_check
+ b .Ldo_program_check
+
+.Lnormal_stack:
+ __ISTACK(program_check)=1
+ __GEN_COMMON_BODY program_check
+
+.Ldo_program_check:
addi r3,r1,STACK_FRAME_OVERHEAD
bl program_check_exception
- b ret_from_except
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM program_check
+
+
+/*
+ * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
+ * This is a synchronous interrupt in response to executing an fp instruction
+ * with MSR[FP]=0.
+ *
+ * Handling:
+ * This will load FP registers and enable the FP bit if coming from userspace,
+ * otherwise report a bad kernel use of FP.
+ */
+INT_DEFINE_BEGIN(fp_unavailable)
+ IVEC=0x800
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(fp_unavailable)
EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
- INT_HANDLER fp_unavailable, 0x800, kvm=1
+ GEN_INT_ENTRY fp_unavailable, virt=0
EXC_REAL_END(fp_unavailable, 0x800, 0x100)
EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100)
- INT_HANDLER fp_unavailable, 0x800, virt=1
+ GEN_INT_ENTRY fp_unavailable, virt=1
EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
-INT_KVM_HANDLER fp_unavailable, 0x800, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(fp_unavailable_common)
- INT_COMMON 0x800, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON fp_unavailable
bne 1f /* if from user, just load it up */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_fp_unavailable_exception
@@ -1350,88 +1789,185 @@
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
bl load_up_fpu
- b fast_exception_return
+ b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl fp_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
+ GEN_KVM fp_unavailable
+
+
+/**
+ * Interrupt 0x900 - Decrementer Interrupt.
+ * This is an asynchronous interrupt in response to a decrementer exception
+ * (e.g., DEC has wrapped below zero). It is maskable in hardware by clearing
+ * MSR[EE], and soft-maskable with IRQS_DISABLED mask (i.e.,
+ * local_irq_disable()).
+ *
+ * Handling:
+ * This calls into Linux timer handler. NVGPRs are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and bump the decrementer to a high value, leaving MSR[EE] enabled
+ * in the interrupted context.
+ * If PPC_WATCHDOG is configured, the soft masked handler will actually set
+ * things back up to run soft_nmi_interrupt as a regular interrupt handler
+ * on the emergency stack.
+ */
+INT_DEFINE_BEGIN(decrementer)
+ IVEC=0x900
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(decrementer)
EXC_REAL_BEGIN(decrementer, 0x900, 0x80)
- INT_HANDLER decrementer, 0x900, ool=1, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY decrementer, virt=0
EXC_REAL_END(decrementer, 0x900, 0x80)
EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
- INT_HANDLER decrementer, 0x900, ool=1, virt=1, bitmask=IRQS_DISABLED
+ GEN_INT_ENTRY decrementer, virt=1
EXC_VIRT_END(decrementer, 0x4900, 0x80)
-INT_KVM_HANDLER decrementer, 0x900, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
+EXC_COMMON_BEGIN(decrementer_common)
+ GEN_COMMON decrementer
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl timer_interrupt
+ b interrupt_return
+ GEN_KVM decrementer
+
+
+/**
+ * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
+ * This is an asynchronous interrupt, similar to 0x900 but for the HDEC
+ * register.
+ *
+ * Handling:
+ * Linux does not use this outside KVM where it's used to keep a host timer
+ * while the guest is given control of DEC. It should normally be caught by
+ * the KVM test and routed there.
+ */
+INT_DEFINE_BEGIN(hdecrementer)
+ IVEC=0x980
+ IHSRR=1
+ ISTACK=0
+ IRECONCILE=0
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(hdecrementer)
EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80)
- INT_HANDLER hdecrementer, 0x980, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY hdecrementer, virt=0
EXC_REAL_END(hdecrementer, 0x980, 0x80)
EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
- INT_HANDLER hdecrementer, 0x980, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY hdecrementer, virt=1
EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
-INT_KVM_HANDLER hdecrementer, 0x980, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
+EXC_COMMON_BEGIN(hdecrementer_common)
+ __GEN_COMMON_ENTRY hdecrementer
+ /*
+ * Hypervisor decrementer interrupts not caught by the KVM test
+ * shouldn't occur but are sometimes left pending on exit from a KVM
+ * guest. We don't need to do anything to clear them, as they are
+ * edge-triggered.
+ *
+ * Be careful to avoid touching the kernel stack.
+ */
+ ld r10,PACA_EXGEN+EX_CTR(r13)
+ mtctr r10
+ mtcrf 0x80,r9
+ ld r9,PACA_EXGEN+EX_R9(r13)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ HRFI_TO_KERNEL
+ GEN_KVM hdecrementer
+
+
+/**
+ * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsndp doorbell.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * Guests may use this for IPIs between threads in a core if the
+ * hypervisor supports it. NVGPRS are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, leaving MSR[EE] enabled in the interrupted context because the
+ * doorbells are edge triggered.
+ */
+INT_DEFINE_BEGIN(doorbell_super)
+ IVEC=0xa00
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(doorbell_super)
EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100)
- INT_HANDLER doorbell_super, 0xa00, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY doorbell_super, virt=0
EXC_REAL_END(doorbell_super, 0xa00, 0x100)
EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
- INT_HANDLER doorbell_super, 0xa00, virt=1, bitmask=IRQS_DISABLED
+ GEN_INT_ENTRY doorbell_super, virt=1
EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
-INT_KVM_HANDLER doorbell_super, 0xa00, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(doorbell_super_common)
+ GEN_COMMON doorbell_super
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception)
+ bl doorbell_exception
#else
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+
+ GEN_KVM doorbell_super
EXC_REAL_NONE(0xb00, 0x100)
EXC_VIRT_NONE(0x4b00, 0x100)
-/*
- * system call / hypercall (0xc00, 0x4c00)
- *
- * The system call exception is invoked with "sc 0" and does not alter HV bit.
- *
- * The hypercall is invoked with "sc 1" and sets HV=1.
+/**
+ * Interrupt 0xc00 - System Call Interrupt (syscall, hcall).
+ * This is a synchronous interrupt invoked with the "sc" instruction. The
+ * system call is invoked with "sc 0" and does not alter the HV bit, so it
+ * is directed to the currently running OS. The hypercall is invoked with
+ * "sc 1" and it sets HV=1, so it elevates to hypervisor.
*
* In HPT, sc 1 always goes to 0xc00 real mode. In RADIX, sc 1 can go to
* 0x4c00 virtual mode.
*
+ * Handling:
+ * If the KVM test fires then it was due to a hypercall and is accordingly
+ * routed to KVM. Otherwise this executes a normal Linux system call.
+ *
* Call convention:
*
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
- *
- * For hypercalls, the register convention is as follows:
- * r0 volatile
- * r1-2 nonvolatile
- * r3 volatile parameter and return value for status
- * r4-r10 volatile input and output value
- * r11 volatile hypercall number and output value
- * r12 volatile input and output value
- * r13-r31 nonvolatile
- * LR nonvolatile
- * CTR volatile
- * XER volatile
- * CR0-1 CR5-7 volatile
- * CR2-4 nonvolatile
- * Other registers nonvolatile
+ * syscall and hypercalls register conventions are documented in
+ * Documentation/powerpc/syscall64-abi.rst and
+ * Documentation/powerpc/papr_hcalls.rst respectively.
*
* The intersection of volatile registers that don't contain possible
* inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
* without saving, though xer is not a good idea to use, as hardware may
* interpret some bits so it may be costly to change them.
*/
+INT_DEFINE_BEGIN(system_call)
+ IVEC=0xc00
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(system_call)
+
.macro SYSTEM_CALL virt
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
/*
@@ -1446,7 +1982,7 @@
GET_PACA(r13)
std r10,PACA_EXGEN+EX_R10(r13)
INTERRUPT_TO_KERNEL
- KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */
+ KVMTEST system_call /* uses r10, branch to system_call_kvm */
mfctr r9
#else
mr r9,r13
@@ -1505,6 +2041,7 @@
EXC_VIRT_END(system_call, 0x4c00, 0x100)
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+TRAMP_REAL_BEGIN(system_call_kvm)
/*
* This is a hcall, so register convention is as above, with these
* differences:
@@ -1512,43 +2049,95 @@
* ctr = orig r13
* orig r10 saved in PACA
*/
-TRAMP_KVM_BEGIN(system_call_kvm)
/*
* 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).
*/
- OPT_GET_SPR(r10, SPRN_PPR, CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_PPR
+ std r10,HSTATE_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
HMT_MEDIUM
- OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r10, CPU_FTR_HAS_PPR)
mfctr r10
SET_SCRATCH0(r10)
- std r9,PACA_EXGEN+EX_R9(r13)
- mfcr r9
- KVM_HANDLER 0xc00, EXC_STD, PACA_EXGEN, 0
+ mfcr r10
+ std r12,HSTATE_SCRATCH0(r13)
+ sldi r12,r10,32
+ ori r12,r12,0xc00
+#ifdef CONFIG_RELOCATABLE
+ /*
+ * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
+ * outside the head section.
+ */
+ __LOAD_FAR_HANDLER(r10, kvmppc_interrupt)
+ mtctr r10
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ bctr
+#else
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ b kvmppc_interrupt
+#endif
#endif
+/**
+ * Interrupt 0xd00 - Trace Interrupt.
+ * This is a synchronous interrupt in response to instruction step or
+ * breakpoint faults.
+ */
+INT_DEFINE_BEGIN(single_step)
+ IVEC=0xd00
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(single_step)
+
EXC_REAL_BEGIN(single_step, 0xd00, 0x100)
- INT_HANDLER single_step, 0xd00, kvm=1
+ GEN_INT_ENTRY single_step, virt=0
EXC_REAL_END(single_step, 0xd00, 0x100)
EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
- INT_HANDLER single_step, 0xd00, virt=1
+ GEN_INT_ENTRY single_step, virt=1
EXC_VIRT_END(single_step, 0x4d00, 0x100)
-INT_KVM_HANDLER single_step, 0xd00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(single_step_common, 0xd00, single_step_exception)
+EXC_COMMON_BEGIN(single_step_common)
+ GEN_COMMON single_step
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl single_step_exception
+ b interrupt_return
+ GEN_KVM single_step
+
+
+/**
+ * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest data access.
+ *
+ * Handling:
+ * This should always get routed to KVM. In radix MMU mode, this is caused
+ * by a guest nested radix access that can't be performed due to the
+ * partition scope page table. In hash mode, this can be caused by guests
+ * running with translation disabled (virtual real mode) or with VPM enabled.
+ * KVM will update the page table structures or disallow the access.
+ */
+INT_DEFINE_BEGIN(h_data_storage)
+ IVEC=0xe00
+ IHSRR=1
+ IDAR=1
+ IDSISR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_data_storage)
EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20)
- INT_HANDLER h_data_storage, 0xe00, ool=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY h_data_storage, virt=0, ool=1
EXC_REAL_END(h_data_storage, 0xe00, 0x20)
EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
- INT_HANDLER h_data_storage, 0xe00, ool=1, virt=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+ GEN_INT_ENTRY h_data_storage, virt=1, ool=1
EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
-INT_KVM_HANDLER h_data_storage, 0xe00, EXC_HV, PACA_EXGEN, 1
EXC_COMMON_BEGIN(h_data_storage_common)
- INT_COMMON 0xe00, PACA_EXGEN, 1, 1, 1, 1, 1
- bl save_nvgprs
+ GEN_COMMON h_data_storage
addi r3,r1,STACK_FRAME_OVERHEAD
BEGIN_MMU_FTR_SECTION
ld r4,_DAR(r1)
@@ -1557,56 +2146,125 @@
MMU_FTR_SECTION_ELSE
bl unknown_exception
ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
- b ret_from_except
+ b interrupt_return
+ GEN_KVM h_data_storage
+
+
+/**
+ * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest instruction fetch, similar to HDSI.
+ */
+INT_DEFINE_BEGIN(h_instr_storage)
+ IVEC=0xe20
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_instr_storage)
EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20)
- INT_HANDLER h_instr_storage, 0xe20, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_instr_storage, virt=0, ool=1
EXC_REAL_END(h_instr_storage, 0xe20, 0x20)
EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
- INT_HANDLER h_instr_storage, 0xe20, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_instr_storage, virt=1, ool=1
EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
-INT_KVM_HANDLER h_instr_storage, 0xe20, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception)
+EXC_COMMON_BEGIN(h_instr_storage_common)
+ GEN_COMMON h_instr_storage
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b interrupt_return
+ GEN_KVM h_instr_storage
+
+
+/**
+ * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
+ */
+INT_DEFINE_BEGIN(emulation_assist)
+ IVEC=0xe40
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(emulation_assist)
EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20)
- INT_HANDLER emulation_assist, 0xe40, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY emulation_assist, virt=0, ool=1
EXC_REAL_END(emulation_assist, 0xe40, 0x20)
EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
- INT_HANDLER emulation_assist, 0xe40, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY emulation_assist, virt=1, ool=1
EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
-INT_KVM_HANDLER emulation_assist, 0xe40, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt)
+EXC_COMMON_BEGIN(emulation_assist_common)
+ GEN_COMMON emulation_assist
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl emulation_assist_interrupt
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+
+ GEN_KVM emulation_assist
-/*
- * hmi_exception trampoline is a special case. It jumps to hmi_exception_early
- * first, and then eventaully from there to the trampoline to get into virtual
- * mode.
+/**
+ * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
+ * This is an asynchronous interrupt caused by a Hypervisor Maintenance
+ * Exception. It is always taken in real mode but uses HSRR registers
+ * unlike SRESET and MCE.
+ *
+ * It is maskable in hardware by clearing MSR[EE], and partially soft-maskable
+ * with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * This is a special case, this is handled similarly to machine checks, with an
+ * initial real mode handler that is not soft-masked, which attempts to fix the
+ * problem. Then a regular handler which is soft-maskable and reports the
+ * problem.
+ *
+ * The emergency stack is used for the early real mode handler.
+ *
+ * XXX: unclear why MCE and HMI schemes could not be made common, e.g.,
+ * either use soft-masking for the MCE, or use irq_work for the HMI.
+ *
+ * KVM:
+ * Unlike MCE, this calls into KVM without calling the real mode handler
+ * first.
*/
+INT_DEFINE_BEGIN(hmi_exception_early)
+ IVEC=0xe60
+ IHSRR=1
+ IREALMODE_COMMON=1
+ ISTACK=0
+ IRECONCILE=0
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception_early)
+
+INT_DEFINE_BEGIN(hmi_exception)
+ IVEC=0xe60
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception)
+
EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20)
- INT_HANDLER hmi_exception, 0xe60, ool=1, early=1, hsrr=EXC_HV, ri=0, kvm=1
+ GEN_INT_ENTRY hmi_exception_early, virt=0, ool=1
EXC_REAL_END(hmi_exception, 0xe60, 0x20)
EXC_VIRT_NONE(0x4e60, 0x20)
-INT_KVM_HANDLER hmi_exception, 0xe60, EXC_HV, PACA_EXGEN, 0
+
EXC_COMMON_BEGIN(hmi_exception_early_common)
- mtctr r10 /* Restore ctr */
- mfspr r11,SPRN_HSRR0 /* Save HSRR0 */
- mfspr r12,SPRN_HSRR1 /* Save HSRR1 */
+ __GEN_REALMODE_COMMON_ENTRY hmi_exception_early
+
mr r10,r1 /* Save r1 */
ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
- /* We don't touch AMR here, we never go to virtual mode */
- INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0
+ __GEN_COMMON_BODY hmi_exception_early
addi r3,r1,STACK_FRAME_OVERHEAD
bl hmi_exception_realmode
cmpdi cr0,r3,0
bne 1f
- EXCEPTION_RESTORE_REGS EXC_HV
+ EXCEPTION_RESTORE_REGS hsrr=1
HRFI_TO_USER_OR_KERNEL
1:
@@ -1614,41 +2272,84 @@
* Go to virtual mode and pull the HMI event information from
* firmware.
*/
- EXCEPTION_RESTORE_REGS EXC_HV
- INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ EXCEPTION_RESTORE_REGS hsrr=1
+ GEN_INT_ENTRY hmi_exception, virt=0
+
+ GEN_KVM hmi_exception_early
EXC_COMMON_BEGIN(hmi_exception_common)
- INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0
+ GEN_COMMON hmi_exception
FINISH_NAP
RUNLATCH_ON
- bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM hmi_exception
+
+
+/**
+ * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsnd doorbell.
+ * Similar to the 0xa00 doorbell but for host rather than guest.
+ */
+INT_DEFINE_BEGIN(h_doorbell)
+ IVEC=0xe80
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_doorbell)
EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20)
- INT_HANDLER h_doorbell, 0xe80, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_doorbell, virt=0, ool=1
EXC_REAL_END(h_doorbell, 0xe80, 0x20)
EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
- INT_HANDLER h_doorbell, 0xe80, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_doorbell, virt=1, ool=1
EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
-INT_KVM_HANDLER h_doorbell, 0xe80, EXC_HV, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(h_doorbell_common)
+ GEN_COMMON h_doorbell
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception)
+ bl doorbell_exception
#else
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+ GEN_KVM h_doorbell
+
+
+/**
+ * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
+ * This is an asynchronous interrupt in response to an "external exception".
+ * Similar to 0x500 but for host only.
+ */
+INT_DEFINE_BEGIN(h_virt_irq)
+ IVEC=0xea0
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_virt_irq)
EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20)
- INT_HANDLER h_virt_irq, 0xea0, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_virt_irq, virt=0, ool=1
EXC_REAL_END(h_virt_irq, 0xea0, 0x20)
EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
- INT_HANDLER h_virt_irq, 0xea0, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+ GEN_INT_ENTRY h_virt_irq, virt=1, ool=1
EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
-INT_KVM_HANDLER h_virt_irq, 0xea0, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ)
+EXC_COMMON_BEGIN(h_virt_irq_common)
+ GEN_COMMON h_virt_irq
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_IRQ
+ b interrupt_return
+
+ GEN_KVM h_virt_irq
EXC_REAL_NONE(0xec0, 0x20)
@@ -1657,25 +2358,69 @@
EXC_VIRT_NONE(0x4ee0, 0x20)
+/*
+ * Interrupt 0xf00 - Performance Monitor Interrupt (PMI, PMU).
+ * This is an asynchronous interrupt in response to a PMU exception.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_PMI_DISABLED mask (NOTE: NOT local_irq_disable()).
+ *
+ * Handling:
+ * This calls into the perf subsystem.
+ *
+ * Like the watchdog soft-nmi, it appears an NMI interrupt to Linux, in that it
+ * runs under local_irq_disable. However it may be soft-masked in
+ * powerpc-specific code.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(performance_monitor)
+ IVEC=0xf00
+ IMASK=IRQS_PMI_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(performance_monitor)
+
EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20)
- INT_HANDLER performance_monitor, 0xf00, ool=1, bitmask=IRQS_PMI_DISABLED, kvm=1
+ GEN_INT_ENTRY performance_monitor, virt=0, ool=1
EXC_REAL_END(performance_monitor, 0xf00, 0x20)
EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
- INT_HANDLER performance_monitor, 0xf00, ool=1, virt=1, bitmask=IRQS_PMI_DISABLED
+ GEN_INT_ENTRY performance_monitor, virt=1, ool=1
EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
-INT_KVM_HANDLER performance_monitor, 0xf00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception)
+EXC_COMMON_BEGIN(performance_monitor_common)
+ GEN_COMMON performance_monitor
+ FINISH_NAP
+ RUNLATCH_ON
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl performance_monitor_exception
+ b interrupt_return
+ GEN_KVM performance_monitor
+
+
+/**
+ * Interrupt 0xf20 - Vector Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a vector (or altivec) instruction with MSR[VEC]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(altivec_unavailable)
+ IVEC=0xf20
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_unavailable)
EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
- INT_HANDLER altivec_unavailable, 0xf20, ool=1, kvm=1
+ GEN_INT_ENTRY altivec_unavailable, virt=0, ool=1
EXC_REAL_END(altivec_unavailable, 0xf20, 0x20)
EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20)
- INT_HANDLER altivec_unavailable, 0xf20, ool=1, virt=1
+ GEN_INT_ENTRY altivec_unavailable, virt=1, ool=1
EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20)
-INT_KVM_HANDLER altivec_unavailable, 0xf20, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(altivec_unavailable_common)
- INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON altivec_unavailable
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
beq 1f
@@ -1689,34 +2434,47 @@
END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
#endif
bl load_up_altivec
- b fast_exception_return
+ b fast_interrupt_return
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl altivec_unavailable_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM altivec_unavailable
+
+
+/**
+ * Interrupt 0xf40 - VSX Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a VSX instruction with MSR[VSX]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(vsx_unavailable)
+ IVEC=0xf40
+ IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(vsx_unavailable)
EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
- INT_HANDLER vsx_unavailable, 0xf40, ool=1, kvm=1
+ GEN_INT_ENTRY vsx_unavailable, virt=0, ool=1
EXC_REAL_END(vsx_unavailable, 0xf40, 0x20)
EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20)
- INT_HANDLER vsx_unavailable, 0xf40, ool=1, virt=1
+ GEN_INT_ENTRY vsx_unavailable, virt=1, ool=1
EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20)
-INT_KVM_HANDLER vsx_unavailable, 0xf40, EXC_STD, PACA_EXGEN, 0
EXC_COMMON_BEGIN(vsx_unavailable_common)
- INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0
+ GEN_COMMON vsx_unavailable
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
beq 1f
@@ -1732,40 +2490,80 @@
b load_up_vsx
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
2: /* User process was in a transaction */
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_tm
- b ret_from_except
+ b interrupt_return
#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
addi r3,r1,STACK_FRAME_OVERHEAD
bl vsx_unavailable_exception
- b ret_from_except
+ b interrupt_return
+ GEN_KVM vsx_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can be
+ * resolved by the OS (e.g., FSCR, MSR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(facility_unavailable)
+ IVEC=0xf60
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(facility_unavailable)
EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20)
- INT_HANDLER facility_unavailable, 0xf60, ool=1, kvm=1
+ GEN_INT_ENTRY facility_unavailable, virt=0, ool=1
EXC_REAL_END(facility_unavailable, 0xf60, 0x20)
EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
- INT_HANDLER facility_unavailable, 0xf60, ool=1, virt=1
+ GEN_INT_ENTRY facility_unavailable, virt=1, ool=1
EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
-INT_KVM_HANDLER facility_unavailable, 0xf60, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception)
+EXC_COMMON_BEGIN(facility_unavailable_common)
+ GEN_COMMON facility_unavailable
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl facility_unavailable_exception
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+ b interrupt_return
+ GEN_KVM facility_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can only
+ * be resolved in HV mode (e.g., HFSCR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(h_facility_unavailable)
+ IVEC=0xf80
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_facility_unavailable)
EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20)
- INT_HANDLER h_facility_unavailable, 0xf80, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_facility_unavailable, virt=0, ool=1
EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20)
EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
- INT_HANDLER h_facility_unavailable, 0xf80, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY h_facility_unavailable, virt=1, ool=1
EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
-INT_KVM_HANDLER h_facility_unavailable, 0xf80, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception)
+EXC_COMMON_BEGIN(h_facility_unavailable_common)
+ GEN_COMMON h_facility_unavailable
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl facility_unavailable_exception
+ REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
+ b interrupt_return
+
+ GEN_KVM h_facility_unavailable
EXC_REAL_NONE(0xfa0, 0x20)
@@ -1781,56 +2579,95 @@
EXC_VIRT_NONE(0x5100, 0x100)
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_system_error)
+ IVEC=0x1200
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_system_error)
+
EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
- INT_HANDLER cbe_system_error, 0x1200, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_system_error, virt=0
EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
EXC_VIRT_NONE(0x5200, 0x100)
-INT_KVM_HANDLER cbe_system_error, 0x1200, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception)
+EXC_COMMON_BEGIN(cbe_system_error_common)
+ GEN_COMMON cbe_system_error
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_system_error_exception
+ b interrupt_return
+
+ GEN_KVM cbe_system_error
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1200, 0x100)
EXC_VIRT_NONE(0x5200, 0x100)
#endif
+INT_DEFINE_BEGIN(instruction_breakpoint)
+ IVEC=0x1300
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_SKIP=1
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_breakpoint)
+
EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100)
- INT_HANDLER instruction_breakpoint, 0x1300, kvm=1
+ GEN_INT_ENTRY instruction_breakpoint, virt=0
EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100)
EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
- INT_HANDLER instruction_breakpoint, 0x1300, virt=1
+ GEN_INT_ENTRY instruction_breakpoint, virt=1
EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
-INT_KVM_HANDLER instruction_breakpoint, 0x1300, EXC_STD, PACA_EXGEN, 1
-EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception)
+EXC_COMMON_BEGIN(instruction_breakpoint_common)
+ GEN_COMMON instruction_breakpoint
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl instruction_breakpoint_exception
+ b interrupt_return
+
+ GEN_KVM instruction_breakpoint
EXC_REAL_NONE(0x1400, 0x100)
EXC_VIRT_NONE(0x5400, 0x100)
-EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
- INT_HANDLER denorm_exception_hv, 0x1500, early=2, hsrr=EXC_HV
+/**
+ * Interrupt 0x1500 - Soft Patch Interrupt
+ *
+ * Handling:
+ * This is an implementation specific interrupt which can be used for a
+ * range of exceptions.
+ *
+ * This interrupt handler is unique in that it runs the denormal assist
+ * code even for guests (and even in guest context) without going to KVM,
+ * for speed. POWER9 does not raise denorm exceptions, so this special case
+ * could be phased out in future to reduce special cases.
+ */
+INT_DEFINE_BEGIN(denorm_exception)
+ IVEC=0x1500
+ IHSRR=1
+ IBRANCH_TO_COMMON=0
+ IKVM_REAL=1
+INT_DEFINE_END(denorm_exception)
+
+EXC_REAL_BEGIN(denorm_exception, 0x1500, 0x100)
+ GEN_INT_ENTRY denorm_exception, virt=0
#ifdef CONFIG_PPC_DENORMALISATION
- mfspr r10,SPRN_HSRR1
- andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
bne+ denorm_assist
#endif
- KVMTEST denorm_exception_hv, EXC_HV 0x1500
- INT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV, 1
-EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
-
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=0
+EXC_REAL_END(denorm_exception, 0x1500, 0x100)
#ifdef CONFIG_PPC_DENORMALISATION
EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
- INT_HANDLER denorm_exception, 0x1500, 0, 2, 1, EXC_HV, PACA_EXGEN, 1, 0, 0, 0, 0
- mfspr r10,SPRN_HSRR1
- andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
+ GEN_INT_ENTRY denorm_exception, virt=1
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
bne+ denorm_assist
- INT_VIRT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=1
EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
#else
EXC_VIRT_NONE(0x5500, 0x100)
#endif
-INT_KVM_HANDLER denorm_exception_hv, 0x1500, EXC_HV, PACA_EXGEN, 0
-
#ifdef CONFIG_PPC_DENORMALISATION
TRAMP_REAL_BEGIN(denorm_assist)
BEGIN_FTR_SECTION
@@ -1887,7 +2724,10 @@
mtspr SPRN_HSRR0,r11
mtcrf 0x80,r9
ld r9,PACA_EXGEN+EX_R9(r13)
- RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+ ld r10,PACA_EXGEN+EX_PPR(r13)
+ mtspr SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
BEGIN_FTR_SECTION
ld r10,PACA_EXGEN+EX_CFAR(r13)
mtspr SPRN_CFAR,r10
@@ -1900,43 +2740,88 @@
b .
#endif
-EXC_COMMON(denorm_common, 0x1500, unknown_exception)
+EXC_COMMON_BEGIN(denorm_exception_common)
+ GEN_COMMON denorm_exception
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b interrupt_return
+
+ GEN_KVM denorm_exception
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_maintenance)
+ IVEC=0x1600
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_maintenance)
+
EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
- INT_HANDLER cbe_maintenance, 0x1600, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_maintenance, virt=0
EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
EXC_VIRT_NONE(0x5600, 0x100)
-INT_KVM_HANDLER cbe_maintenance, 0x1600, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception)
+EXC_COMMON_BEGIN(cbe_maintenance_common)
+ GEN_COMMON cbe_maintenance
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_maintenance_exception
+ b interrupt_return
+
+ GEN_KVM cbe_maintenance
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1600, 0x100)
EXC_VIRT_NONE(0x5600, 0x100)
#endif
+INT_DEFINE_BEGIN(altivec_assist)
+ IVEC=0x1700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_assist)
+
EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100)
- INT_HANDLER altivec_assist, 0x1700, kvm=1
+ GEN_INT_ENTRY altivec_assist, virt=0
EXC_REAL_END(altivec_assist, 0x1700, 0x100)
EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
- INT_HANDLER altivec_assist, 0x1700, virt=1
+ GEN_INT_ENTRY altivec_assist, virt=1
EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
-INT_KVM_HANDLER altivec_assist, 0x1700, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(altivec_assist_common)
+ GEN_COMMON altivec_assist
+ addi r3,r1,STACK_FRAME_OVERHEAD
#ifdef CONFIG_ALTIVEC
-EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception)
+ bl altivec_assist_exception
+ REST_NVGPRS(r1) /* instruction emulation may change GPRs */
#else
-EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception)
+ bl unknown_exception
#endif
+ b interrupt_return
+
+ GEN_KVM altivec_assist
#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_thermal)
+ IVEC=0x1800
+ IHSRR=1
+ IKVM_SKIP=1
+ IKVM_REAL=1
+INT_DEFINE_END(cbe_thermal)
+
EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
- INT_HANDLER cbe_thermal, 0x1800, ool=1, hsrr=EXC_HV, kvm=1
+ GEN_INT_ENTRY cbe_thermal, virt=0
EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
EXC_VIRT_NONE(0x5800, 0x100)
-INT_KVM_HANDLER cbe_thermal, 0x1800, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception)
+EXC_COMMON_BEGIN(cbe_thermal_common)
+ GEN_COMMON cbe_thermal
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl cbe_thermal_exception
+ b interrupt_return
+
+ GEN_KVM cbe_thermal
+
#else /* CONFIG_CBE_RAS */
EXC_REAL_NONE(0x1800, 0x100)
EXC_VIRT_NONE(0x5800, 0x100)
@@ -1945,14 +2830,11 @@
#ifdef CONFIG_PPC_WATCHDOG
-#define MASKED_DEC_HANDLER_LABEL 3f
-
-#define MASKED_DEC_HANDLER(_H) \
-3: /* soft-nmi */ \
- std r12,PACA_EXGEN+EX_R12(r13); \
- GET_SCRATCH0(r10); \
- std r10,PACA_EXGEN+EX_R13(r13); \
- INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1
+INT_DEFINE_BEGIN(soft_nmi)
+ IVEC=0x900
+ ISTACK=0
+ IRECONCILE=0 /* Soft-NMI may fire under local_irq_disable */
+INT_DEFINE_END(soft_nmi)
/*
* Branch to soft_nmi_interrupt using the emergency stack. The emergency
@@ -1964,18 +2846,42 @@
* and run it entirely with interrupts hard disabled.
*/
EXC_COMMON_BEGIN(soft_nmi_common)
+ mfspr r11,SPRN_SRR0
mr r10,r1
ld r1,PACAEMERGSP(r13)
subi r1,r1,INT_FRAME_SIZE
- INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0
- bl save_nvgprs
+ __GEN_COMMON_BODY soft_nmi
+
+ /*
+ * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
+ * system_reset_common)
+ */
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ lbz r10,PACAIRQHAPPENED(r13)
+ std r10,RESULT(r1)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+
addi r3,r1,STACK_FRAME_OVERHEAD
bl soft_nmi_interrupt
- b ret_from_except
-#else /* CONFIG_PPC_WATCHDOG */
-#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */
-#define MASKED_DEC_HANDLER(_H)
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+
+ /*
+ * Restore soft mask settings.
+ */
+ ld r10,RESULT(r1)
+ stb r10,PACAIRQHAPPENED(r13)
+ ld r10,SOFTE(r1)
+ stb r10,PACAIRQSOFTMASK(r13)
+
+ kuap_restore_amr r9, r10
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
+
#endif /* CONFIG_PPC_WATCHDOG */
/*
@@ -1988,13 +2894,12 @@
* - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
* This is called with r10 containing the value to OR to the paca field.
*/
-.macro MASKED_INTERRUPT hsrr
+.macro MASKED_INTERRUPT hsrr=0
.if \hsrr
masked_Hinterrupt:
.else
masked_interrupt:
.endif
- std r11,PACA_EXGEN+EX_R11(r13)
lbz r11,PACAIRQHAPPENED(r13)
or r11,r11,r10
stb r11,PACAIRQHAPPENED(r13)
@@ -2003,34 +2908,38 @@
lis r10,0x7fff
ori r10,r10,0xffff
mtspr SPRN_DEC,r10
- b MASKED_DEC_HANDLER_LABEL
+#ifdef CONFIG_PPC_WATCHDOG
+ b soft_nmi_common
+#else
+ b 2f
+#endif
1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK
beq 2f
+ xori r12,r12,MSR_EE /* clear MSR_EE */
.if \hsrr
- mfspr r10,SPRN_HSRR1
- xori r10,r10,MSR_EE /* clear MSR_EE */
- mtspr SPRN_HSRR1,r10
+ mtspr SPRN_HSRR1,r12
.else
- mfspr r10,SPRN_SRR1
- xori r10,r10,MSR_EE /* clear MSR_EE */
- mtspr SPRN_SRR1,r10
+ mtspr SPRN_SRR1,r12
.endif
ori r11,r11,PACA_IRQ_HARD_DIS
stb r11,PACAIRQHAPPENED(r13)
2: /* done */
+ ld r10,PACA_EXGEN+EX_CTR(r13)
+ mtctr r10
mtcrf 0x80,r9
std r1,PACAR1(r13)
ld r9,PACA_EXGEN+EX_R9(r13)
ld r10,PACA_EXGEN+EX_R10(r13)
ld r11,PACA_EXGEN+EX_R11(r13)
- /* returns to kernel where r13 must be set up, so don't restore it */
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ /* May return to masked low address where r13 is not set up */
.if \hsrr
HRFI_TO_KERNEL
.else
RFI_TO_KERNEL
.endif
b .
- MASKED_DEC_HANDLER(\hsrr\())
.endm
TRAMP_REAL_BEGIN(stf_barrier_fallback)
@@ -2087,6 +2996,25 @@
ld r11,PACA_EXRFI+EX_R11(r13)
blr
+/*
+ * The SCV entry flush happens with interrupts enabled, so it must disable
+ * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10
+ * (containing LR) does not need to be preserved here because scv entry
+ * puts 0 in the pt_regs, CTR can be clobbered for the same reason.
+ */
+TRAMP_REAL_BEGIN(scv_entry_flush_fallback)
+ li r10,0
+ mtmsrd r10,1
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ L1D_DISPLACEMENT_FLUSH
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ li r10,MSR_RI
+ mtmsrd r10,1
+ blr
+
TRAMP_REAL_BEGIN(rfi_flush_fallback)
SET_SCRATCH0(r13);
GET_PACA(r13);
@@ -2123,6 +3051,47 @@
GET_SCRATCH0(r13);
hrfid
+TRAMP_REAL_BEGIN(rfscv_flush_fallback)
+ /* system call volatile */
+ mr r7,r13
+ GET_PACA(r13);
+ mr r8,r1
+ ld r1,PACAKSAVE(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SIZE(r13)
+ srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+ mtctr r11
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+
+ /*
+ * The load adresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+1:
+ ld r11,(0x80 + 8)*0(r10)
+ ld r11,(0x80 + 8)*1(r10)
+ ld r11,(0x80 + 8)*2(r10)
+ ld r11,(0x80 + 8)*3(r10)
+ ld r11,(0x80 + 8)*4(r10)
+ ld r11,(0x80 + 8)*5(r10)
+ ld r11,(0x80 + 8)*6(r10)
+ ld r11,(0x80 + 8)*7(r10)
+ addi r10,r10,0x80*8
+ bdnz 1b
+
+ mtctr r9
+ li r9,0
+ li r10,0
+ li r11,0
+ mr r1,r8
+ mr r13,r7
+ RFSCV
+
USE_TEXT_SECTION()
_GLOBAL(do_uaccess_flush)
@@ -2136,17 +3105,12 @@
_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
EXPORT_SYMBOL(do_uaccess_flush)
-/*
- * Real mode exceptions actually use this too, but alternate
- * instruction code patches (which end up in the common .text area)
- * cannot reach these if they are put there.
- */
-USE_FIXED_SECTION(virt_trampolines)
- MASKED_INTERRUPT EXC_STD
- MASKED_INTERRUPT EXC_HV
+
+MASKED_INTERRUPT
+MASKED_INTERRUPT hsrr=1
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
+kvmppc_skip_interrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
@@ -2158,7 +3122,7 @@
RFI_TO_KERNEL
b .
-TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
+kvmppc_skip_Hinterrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
@@ -2171,16 +3135,6 @@
b .
#endif
-/*
- * Ensure that any handlers that get invoked from the exception prologs
- * above are below the first 64KB (0x10000) of the kernel image because
- * the prologs assemble the addresses of these handlers using the
- * LOAD_HANDLER macro, which uses an ori instruction.
- */
-
-/*** Common interrupt handlers ***/
-
-
/*
* Relocation-on interrupts: A subset of the interrupts can be delivered
* with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering
@@ -2202,6 +3156,10 @@
USE_FIXED_SECTION(virt_trampolines)
/*
+ * All code below __end_interrupts is treated as soft-masked. If
+ * any code runs here with MSR[EE]=1, it must then cope with pending
+ * soft interrupt being raised (i.e., by ensuring it is replayed).
+ *
* The __end_interrupts marker must be past the out-of-line (OOL)
* handlers, so that they are copied to real address 0x100 when running
* a relocatable kernel. This ensures they can be reached from the short
@@ -2214,11 +3172,20 @@
DEFINE_FIXED_SYMBOL(__end_interrupts)
#ifdef CONFIG_PPC_970_NAP
+ /*
+ * Called by exception entry code if _TLF_NAPPING was set, this clears
+ * the NAPPING flag, and redirects the exception exit to
+ * power4_fixup_nap_return.
+ */
+ .globl power4_fixup_nap
EXC_COMMON_BEGIN(power4_fixup_nap)
andc r9,r9,r10
std r9,TI_LOCAL_FLAGS(r11)
- ld r10,_LINK(r1) /* make idle task do the */
- std r10,_NIP(r1) /* equivalent of a blr */
+ LOAD_REG_ADDR(r10, power4_idle_nap_return)
+ std r10,_NIP(r1)
+ blr
+
+power4_idle_nap_return:
blr
#endif
@@ -2268,10 +3235,18 @@
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r5,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
+
+ /*
+ * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+ * don't call hash_page, just fail the fault. This is required to
+ * prevent re-entrancy problems in the hash code, namely perf
+ * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+ * hash fault. See the comment in hash_preload().
+ */
ld r11, PACA_THREAD_INFO(r13)
- lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
- andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
- bne 77f /* then don't call hash_page now */
+ lwz r0,TI_PREEMPT(r11)
+ andis. r0,r0,NMI_MASK@h
+ bne 77f
/*
* r3 contains the trap number
@@ -2285,7 +3260,7 @@
cmpdi r3,0 /* see if __hash_page succeeded */
/* Success */
- beq fast_exc_return_irq /* Return from exception on success */
+ beq interrupt_return /* Return from exception on success */
/* Error */
blt- 13f
@@ -2302,39 +3277,36 @@
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_page_fault
cmpdi r3,0
- beq+ ret_from_except_lite
- bl save_nvgprs
+ beq+ interrupt_return
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
bl bad_page_fault
- b ret_from_except
+ b interrupt_return
/* We have a data breakpoint exception - handle it */
handle_dabr_fault:
- bl save_nvgprs
ld r4,_DAR(r1)
ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_break
/*
* do_break() may have changed the NV GPRS while handling a breakpoint.
- * If so, we need to restore them with their updated values. Don't use
- * ret_from_except_lite here.
+ * If so, we need to restore them with their updated values.
*/
- b ret_from_except
+ REST_NVGPRS(r1)
+ b interrupt_return
#ifdef CONFIG_PPC_BOOK3S_64
/* We have a page fault that hash_page could handle but HV refused
* the PTE insertion
*/
-13: bl save_nvgprs
- mr r5,r3
+13: mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
bl low_hash_fault
- b ret_from_except
+ b interrupt_return
#endif
/*
@@ -2344,74 +3316,7 @@
* were soft-disabled. We want to invoke the exception handler for
* the access, or panic if there isn't a handler.
*/
-77: bl save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
+77: addi r3,r1,STACK_FRAME_OVERHEAD
li r5,SIGSEGV
bl bad_page_fault
- b ret_from_except
-
-/*
- * When doorbell is triggered from system reset wakeup, the message is
- * not cleared, so it would fire again when EE is enabled.
- *
- * When coming from local_irq_enable, there may be the same problem if
- * we were hard disabled.
- *
- * Execute msgclr to clear pending exceptions before handling it.
- */
-h_doorbell_common_msgclr:
- LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
- PPC_MSGCLR(3)
- b h_doorbell_common
-
-doorbell_super_common_msgclr:
- LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
- PPC_MSGCLRP(3)
- b doorbell_super_common
-
-/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
- * which kind of interrupt. MSR:EE is already off. We generate a
- * stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- *
- * Note that we don't specify LR as the NIP (return address) for
- * the interrupt because that would unbalance the return branch
- * predictor.
- */
-_GLOBAL(__replay_interrupt)
- /* We are going to jump to the exception common code which
- * will retrieve various register values from the PACA which
- * we don't give a damn about, so we don't bother storing them.
- */
- mfmsr r12
- LOAD_REG_ADDR(r11, replay_interrupt_return)
- mfcr r9
- ori r12,r12,MSR_EE
- cmpwi r3,0x900
- beq decrementer_common
- cmpwi r3,0x500
-BEGIN_FTR_SECTION
- beq h_virt_irq_common
-FTR_SECTION_ELSE
- beq hardware_interrupt_common
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
- cmpwi r3,0xf00
- beq performance_monitor_common
-BEGIN_FTR_SECTION
- cmpwi r3,0xa00
- beq h_doorbell_common_msgclr
- cmpwi r3,0xe60
- beq hmi_exception_common
-FTR_SECTION_ELSE
- cmpwi r3,0xa00
- beq doorbell_super_common_msgclr
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
-replay_interrupt_return:
- blr
-
-_ASM_NOKPROBE_SYMBOL(__replay_interrupt)
+ b interrupt_return