Series comparison

-[PULL 00/28] riscv-to-apply queue
+[PULL v2 00/45] riscv-to-apply queue
-The following changes since commit ad10b4badc1dd5b28305f9b9f1168cf0aa3ae946:
+The following changes since commit c5ea91da443b458352c1b629b490ee6631775cb4:
-  Merge tag 'pull-error-2024-05-27' of https://repo.or.cz/qemu/armbru into staging (2024-05-27 06:40:42 -0700)
+  Merge tag 'pull-trivial-patches' of https://gitlab.com/mjt0k/qemu into staging (2023-09-08 10:06:25 -0400)
 are available in the Git repository at:
-  https://github.com/alistair23/qemu.git tags/pull-riscv-to-apply-20240528
+  https://github.com/alistair23/qemu.git tags/pull-riscv-to-apply-20230911
-for you to fetch changes up to 1806da76cb81088ea026ca3441551782b850e393:
+for you to fetch changes up to e7a03409f29e2da59297d55afbaec98c96e43e3a:
-  target/riscv: raise an exception when CSRRS/CSRRC writes a read-only CSR (2024-05-28 12:20:27 +1000)
+  target/riscv: don't read CSR in riscv_csrrw_do64 (2023-09-11 11:45:55 +1000)
 ----------------------------------------------------------------
-RISC-V PR for 9.1
+First RISC-V PR for 8.2
-* APLICs add child earlier than realize
+ * Remove 'host' CPU from TCG
-* Fix exposure of Zkr
+ * riscv_htif Fixup printing on big endian hosts
-* Raise exceptions on wrs.nto
+ * Add zmmul isa string
-* Implement SBI debug console (DBCN) calls for KVM
+ * Add smepmp isa string
-* Support 64-bit addresses for initrd
+ * Fix page_check_range use in fault-only-first
-* Change RISCV_EXCP_SEMIHOST exception number to 63
+ * Use existing lookup tables for MixColumns
-* Tolerate KVM disable ext errors
+ * Add RISC-V vector cryptographic instruction set support
-* Set tval in breakpoints
+ * Implement WARL behaviour for mcountinhibit/mcounteren
-* Add support for Zve32x extension
+ * Add Zihintntl extension ISA string to DTS
-* Add support for Zve64x extension
+ * Fix zfa fleq.d and fltq.d
-* Relax vector register check in RISCV gdbstub
+ * Fix upper/lower mtime write calculation
-* Fix the element agnostic Vector function problem
+ * Make rtc variable names consistent
-* Fix Zvkb extension config
+ * Use abi type for linux-user target_ucontext
-* Implement dynamic establishment of custom decoder
+ * Add RISC-V KVM AIA Support
-* Add th.sxstatus CSR emulation
+ * Fix riscv,pmu DT node path in the virt machine
-* Fix Zvfhmin checking for vfwcvt.f.f.v and vfncvt.f.f.w instructions
+ * Update CSR bits name for svadu extension
-* Check single width operator for vector fp widen instructions
+ * Mark zicond non-experimental
-* Check single width operator for vfncvt.rod.f.f.w
+ * Fix satp_mode_finalize() when satp_mode.supported = 0
-* Remove redudant SEW checking for vector fp narrow/widen instructions
+ * Fix non-KVM --enable-debug build
-* Prioritize pmp errors in raise_mmu_exception()
+ * Add new extensions to hwprobe
-* Do not set mtval2 for non guest-page faults
+ * Use accelerated helper for AES64KS1I
-* Remove experimental prefix from "B" extension
+ * Allocate itrigger timers only once
-* Fixup CBO extension register calculation
+ * Respect mseccfg.RLB for pmpaddrX changes
-* Fix the hart bit setting of AIA
+ * Align the AIA model to v1.0 ratified spec
-* Fix reg_width in ricsv_gen_dynamic_vector_feature()
+ * Don't read the CSR in riscv_csrrw_do64
 * Decode all of the pmpcfg and pmpaddr CSRs
 * Raise an exception when CSRRS/CSRRC writes a read-only CSR
 ----------------------------------------------------------------
-Alexei Filippov (1):
+Akihiko Odaki (1):
-      target/riscv: do not set mtval2 for non guest-page faults
+      target/riscv: Allocate itrigger timers only once
-Alistair Francis (2):
+Ard Biesheuvel (2):
-      target/riscv: rvzicbo: Fixup CBO extension register calculation
+      target/riscv: Use existing lookup tables for MixColumns
-      disas/riscv: Decode all of the pmpcfg and pmpaddr CSRs
+      target/riscv: Use accelerated helper for AES64KS1I
-Andrew Jones (2):
+Conor Dooley (1):
-      target/riscv/kvm: Fix exposure of Zkr
+      hw/riscv: virt: Fix riscv,pmu DT node path
       target/riscv: Raise exceptions on wrs.nto
 Cheng Yang (1):
       hw/riscv/boot.c: Support 64-bit address for initrd
 Christoph Müllner (1):
       riscv: thead: Add th.sxstatus CSR emulation
 Clément Léger (1):
       target/riscv: change RISCV_EXCP_SEMIHOST exception number to 63
 Daniel Henrique Barboza (6):
-      target/riscv/kvm: implement SBI debug console (DBCN) calls
+      target/riscv/cpu.c: do not run 'host' CPU with TCG
-      target/riscv/kvm: tolerate KVM disable ext errors
+      target/riscv/cpu.c: add zmmul isa string
-      target/riscv/debug: set tval=pc in breakpoint exceptions
+      target/riscv/cpu.c: add smepmp isa string
-      trans_privileged.c.inc: set (m|s)tval on ebreak breakpoint
+      target/riscv: fix satp_mode_finalize() when satp_mode.supported = 0
-      target/riscv: prioritize pmp errors in raise_mmu_exception()
+      hw/riscv/virt.c: fix non-KVM --enable-debug build
-      riscv, gdbstub.c: fix reg_width in ricsv_gen_dynamic_vector_feature()
+      hw/intc/riscv_aplic.c fix non-KVM --enable-debug build
-Huang Tao (2):
+Dickon Hood (2):
-      target/riscv: Fix the element agnostic function problem
+      target/riscv: Refactor translation of vector-widening instruction
-      target/riscv: Implement dynamic establishment of custom decoder
+      target/riscv: Add Zvbb ISA extension support
 Jason Chien (3):
-      target/riscv: Add support for Zve32x extension
+      target/riscv: Add Zihintntl extension ISA string to DTS
-      target/riscv: Add support for Zve64x extension
+      hw/intc: Fix upper/lower mtime write calculation
-      target/riscv: Relax vector register check in RISCV gdbstub
+      hw/intc: Make rtc variable names consistent
-Max Chou (4):
+Kiran Ostrolenk (4):
-      target/riscv: rvv: Fix Zvfhmin checking for vfwcvt.f.f.v and vfncvt.f.f.w instructions
+      target/riscv: Refactor some of the generic vector functionality
-      target/riscv: rvv: Check single width operator for vector fp widen instructions
+      target/riscv: Refactor vector-vector translation macro
-      target/riscv: rvv: Check single width operator for vfncvt.rod.f.f.w
+      target/riscv: Refactor some of the generic vector functionality
-      target/riscv: rvv: Remove redudant SEW checking for vector fp narrow/widen instructions
+      target/riscv: Add Zvknh ISA extension support
 LIU Zhiwei (3):
       target/riscv: Fix page_check_range use in fault-only-first
       target/riscv: Fix zfa fleq.d and fltq.d
       linux-user/riscv: Use abi type for target_ucontext
 Lawrence Hunter (2):
       target/riscv: Add Zvbc ISA extension support
       target/riscv: Add Zvksh ISA extension support
 Leon Schuermann (1):
       target/riscv/pmp.c: respect mseccfg.RLB for pmpaddrX changes
 Max Chou (3):
       crypto: Create sm4_subword
       crypto: Add SM4 constant parameter CK
       target/riscv: Add Zvksed ISA extension support
 Nazar Kazakov (4):
       target/riscv: Remove redundant "cpu_vl == 0" checks
       target/riscv: Move vector translation checks
       target/riscv: Add Zvkned ISA extension support
       target/riscv: Add Zvkg ISA extension support
 Nikita Shubin (1):
       target/riscv: don't read CSR in riscv_csrrw_do64
 Rob Bradford (1):
-      target/riscv: Remove experimental prefix from "B" extension
+      target/riscv: Implement WARL behaviour for mcountinhibit/mcounteren
-Yangyu Chen (1):
+Robbin Ehn (1):
-      target/riscv/cpu.c: fix Zvkb extension config
+      linux-user/riscv: Add new extensions to hwprobe
-Yong-Xuan Wang (1):
+Thomas Huth (2):
-      target/riscv/kvm.c: Fix the hart bit setting of AIA
+      hw/char/riscv_htif: Fix printing of console characters on big endian hosts
       hw/char/riscv_htif: Fix the console syscall on big endian hosts
-Yu-Ming Chang (1):
+Tommy Wu (1):
-      target/riscv: raise an exception when CSRRS/CSRRC writes a read-only CSR
+      target/riscv: Align the AIA model to v1.0 ratified spec
-yang.zhang (1):
+Vineet Gupta (1):
-      hw/intc/riscv_aplic: APLICs should add child earlier than realize
+      riscv: zicond: make non-experimental
- MAINTAINERS                                    |   1 +
+Weiwei Li (1):
- target/riscv/cpu.h                             |  11 ++
+      target/riscv: Update CSR bits name for svadu extension
  target/riscv/cpu_bits.h                        |   2 +-
  target/riscv/cpu_cfg.h                         |   2 +
  target/riscv/helper.h                          |   1 +
  target/riscv/sbi_ecall_interface.h             |  17 +++
  target/riscv/tcg/tcg-cpu.h                     |  15 +++
  disas/riscv.c                                  |  65 +++++++++-
  hw/intc/riscv_aplic.c                          |   8 +-
  hw/riscv/boot.c                                |   4 +-
  target/riscv/cpu.c                             |  10 +-
  target/riscv/cpu_helper.c                      |  37 +++---
  target/riscv/csr.c                             |  71 +++++++++--
  target/riscv/debug.c                           |   3 +
  target/riscv/gdbstub.c                         |   8 +-
  target/riscv/kvm/kvm-cpu.c                     | 157 ++++++++++++++++++++++++-
  target/riscv/op_helper.c                       |  17 ++-
  target/riscv/tcg/tcg-cpu.c                     |  50 +++++---
  target/riscv/th_csr.c                          |  79 +++++++++++++
  target/riscv/translate.c                       |  31 +++--
  target/riscv/vector_internals.c                |  22 ++++
  target/riscv/insn_trans/trans_privileged.c.inc |   2 +
  target/riscv/insn_trans/trans_rvv.c.inc        |  46 +++++---
  target/riscv/insn_trans/trans_rvzawrs.c.inc    |  29 +++--
  target/riscv/insn_trans/trans_rvzicbo.c.inc    |  16 ++-
  target/riscv/meson.build                       |   1 +
 files changed, 596 insertions(+), 109 deletions(-)
  create mode 100644 target/riscv/th_csr.c
+Yong-Xuan Wang (5):
+      target/riscv: support the AIA device emulation with KVM enabled
+      target/riscv: check the in-kernel irqchip support
+      target/riscv: Create an KVM AIA irqchip
+      target/riscv: update APLIC and IMSIC to support KVM AIA
+      target/riscv: select KVM AIA in riscv virt machine
+ include/crypto/aes.h                      |   7 +
+ include/crypto/sm4.h                      |   9 +
+ target/riscv/cpu_bits.h                   |   8 +-
+ target/riscv/cpu_cfg.h                    |   9 +
+ target/riscv/debug.h                      |   3 +-
+ target/riscv/helper.h                     |  98 +++
+ target/riscv/kvm_riscv.h                  |   5 +
+ target/riscv/vector_internals.h           | 228 +++++++
+ target/riscv/insn32.decode                |  58 ++
+ crypto/aes.c                              |   4 +-
+ crypto/sm4.c                              |  10 +
+ hw/char/riscv_htif.c                      |  12 +-
+ hw/intc/riscv_aclint.c                    |  11 +-
+ hw/intc/riscv_aplic.c                     |  52 +-
+ hw/intc/riscv_imsic.c                     |  25 +-
+ hw/riscv/virt.c                           | 374 ++++++------
+ linux-user/riscv/signal.c                 |   4 +-
+ linux-user/syscall.c                      |  14 +-
+ target/arm/tcg/crypto_helper.c            |  10 +-
+ target/riscv/cpu.c                        |  83 ++-
+ target/riscv/cpu_helper.c                 |   6 +-
+ target/riscv/crypto_helper.c              |  51 +-
+ target/riscv/csr.c                        |  54 +-
+ target/riscv/debug.c                      |  15 +-
+ target/riscv/kvm.c                        | 201 ++++++-
+ target/riscv/pmp.c                        |   4 +
+ target/riscv/translate.c                  |   1 +
+ target/riscv/vcrypto_helper.c             | 970 ++++++++++++++++++++++++++++++
+ target/riscv/vector_helper.c              | 245 +-------
+ target/riscv/vector_internals.c           |  81 +++
+ target/riscv/insn_trans/trans_rvv.c.inc   | 171 +++---
+ target/riscv/insn_trans/trans_rvvk.c.inc  | 606 +++++++++++++++++++
+ target/riscv/insn_trans/trans_rvzfa.c.inc |   4 +-
+ target/riscv/meson.build                  |   4 +-
+files changed, 2785 insertions(+), 652 deletions(-)
+ create mode 100644 target/riscv/vector_internals.h
+ create mode 100644 target/riscv/vcrypto_helper.c
+ create mode 100644 target/riscv/vector_internals.c
+ create mode 100644 target/riscv/insn_trans/trans_rvvk.c.inc

-[PULL 21/28] target/riscv: prioritize pmp errors in raise_mmu_exception()
+[PULL v2 01/45] target/riscv/cpu.c: do not run 'host' CPU with TCG
 From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-raise_mmu_exception(), as is today, is prioritizing guest page faults by
+The 'host' CPU is available in a CONFIG_KVM build and it's currently
-checking first if virt_enabled && !first_stage, and then considering the
+available for all accels, but is a KVM only CPU. This means that in a
-regular inst/load/store faults.
+RISC-V KVM capable host we can do things like this:
-There's no mention in the spec about guest page fault being a higher
+$ ./build/qemu-system-riscv64 -M virt,accel=tcg -cpu host --nographic
-priority that PMP faults. In fact, privileged spec section 3.7.1 says:
+qemu-system-riscv64: H extension requires priv spec 1.12.0
-"Attempting to fetch an instruction from a PMP region that does not have
+This CPU does not have a priv spec because we don't filter its extensions
-execute permissions raises an instruction access-fault exception.
+via priv spec. We shouldn't be reaching riscv_cpu_realize_tcg() at all
-Attempting to execute a load or load-reserved instruction which accesses
+with the 'host' CPU.
 a physical address within a PMP region without read permissions raises a
 load access-fault exception. Attempting to execute a store,
 store-conditional, or AMO instruction which accesses a physical address
 within a PMP region without write permissions raises a store
 access-fault exception."
-So, in fact, we're doing it wrong - PMP faults should always be thrown,
+We don't have a way to filter the 'host' CPU out of the available CPU
-regardless of also being a first or second stage fault.
+options (-cpu help) if the build includes both KVM and TCG. What we can
 do is to error out during riscv_cpu_realize_tcg() if the user chooses
 the 'host' CPU with accel=tcg:
-The way riscv_cpu_tlb_fill() and get_physical_address() work is
+$ ./build/qemu-system-riscv64 -M virt,accel=tcg -cpu host --nographic
-adequate: a TRANSLATE_PMP_FAIL error is immediately reported and
+qemu-system-riscv64: 'host' CPU is not compatible with TCG acceleration
 reflected in the 'pmp_violation' flag. What we need is to change
 raise_mmu_exception() to prioritize it.
-Reported-by: Joseph Chan <jchan@ventanamicro.com>
-Fixes: 82d53adfbb ("target/riscv/cpu_helper.c: Invalid exception on MMU translation stage")
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Message-ID: <20240413105929.7030-1-alexei.filippov@syntacore.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-Id: <20230721133411.474105-1-dbarboza@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_helper.c | 22 ++++++++++++----------
+ target/riscv/cpu.c | 5 +++++
-file changed, 12 insertions(+), 10 deletions(-)
+file changed, 5 insertions(+)
-diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
+diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu_helper.c
+--- a/target/riscv/cpu.c
-+++ b/target/riscv/cpu_helper.c
++++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ static void raise_mmu_exception(CPURISCVState *env, target_ulong address,
+@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_realize_tcg(DeviceState *dev, Error **errp)
+     CPURISCVState *env = &cpu->env;
-     switch (access_type) {
+     Error *local_err = NULL;
-     case MMU_INST_FETCH:
--        if (env->virt_enabled && !first_stage) {
++    if (object_dynamic_cast(OBJECT(dev), TYPE_RISCV_CPU_HOST)) {
-+        if (pmp_violation) {
++        error_setg(errp, "'host' CPU is not compatible with TCG acceleration");
-+            cs->exception_index = RISCV_EXCP_INST_ACCESS_FAULT;
++        return;
-+        } else if (env->virt_enabled && !first_stage) {
++    }
-             cs->exception_index = RISCV_EXCP_INST_GUEST_PAGE_FAULT;
++
-         } else {
+     riscv_cpu_validate_misa_mxl(cpu, &local_err);
--            cs->exception_index = pmp_violation ?
+     if (local_err != NULL) {
--                RISCV_EXCP_INST_ACCESS_FAULT : RISCV_EXCP_INST_PAGE_FAULT;
+         error_propagate(errp, local_err);
 +            cs->exception_index = RISCV_EXCP_INST_PAGE_FAULT;
          }
          break;
      case MMU_DATA_LOAD:
 -        if (two_stage && !first_stage) {
 +        if (pmp_violation) {
 +            cs->exception_index = RISCV_EXCP_LOAD_ACCESS_FAULT;
 +        } else if (two_stage && !first_stage) {
              cs->exception_index = RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT;
          } else {
 -            cs->exception_index = pmp_violation ?
 -                RISCV_EXCP_LOAD_ACCESS_FAULT : RISCV_EXCP_LOAD_PAGE_FAULT;
 +            cs->exception_index = RISCV_EXCP_LOAD_PAGE_FAULT;
          }
          break;
      case MMU_DATA_STORE:
 -        if (two_stage && !first_stage) {
 +        if (pmp_violation) {
 +            cs->exception_index = RISCV_EXCP_STORE_AMO_ACCESS_FAULT;
 +        } else if (two_stage && !first_stage) {
              cs->exception_index = RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT;
          } else {
 -            cs->exception_index = pmp_violation ?
 -                RISCV_EXCP_STORE_AMO_ACCESS_FAULT :
 -                RISCV_EXCP_STORE_PAGE_FAULT;
 +            cs->exception_index = RISCV_EXCP_STORE_PAGE_FAULT;
          }
          break;
      default:
 --
-.45.1
+.41.0

-New patch
+[PULL v2 02/45] hw/char/riscv_htif: Fix printing of console characters on big endian hosts
+From: Thomas Huth <thuth@redhat.com>
+The character that should be printed is stored in the 64 bit "payload"
+variable. The code currently tries to print it by taking the address
+of the variable and passing this pointer to qemu_chr_fe_write(). However,
+this only works on little endian hosts where the least significant bits
+are stored on the lowest address. To do this in a portable way, we have
+to store the value in an uint8_t variable instead.
+Fixes: 5033606780 ("RISC-V HTIF Console")
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Bin Meng <bmeng@tinylab.org>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Message-Id: <20230721094720.902454-2-thuth@redhat.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ hw/char/riscv_htif.c | 3 ++-
+file changed, 2 insertions(+), 1 deletion(-)
+diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/char/riscv_htif.c
++++ b/hw/char/riscv_htif.c
+@@ -XXX,XX +XXX,XX @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
+             s->tohost = 0; /* clear to indicate we read */
+             return;
+         } else if (cmd == HTIF_CONSOLE_CMD_PUTC) {
+-            qemu_chr_fe_write(&s->chr, (uint8_t *)&payload, 1);
++            uint8_t ch = (uint8_t)payload;
++            qemu_chr_fe_write(&s->chr, &ch, 1);
+             resp = 0x100 | (uint8_t)payload;
+         } else {
+             qemu_log("HTIF device %d: unknown command\n", device);
+--
+.41.0

-New patch
+[PULL v2 03/45] hw/char/riscv_htif: Fix the console syscall on big endian hosts
+From: Thomas Huth <thuth@redhat.com>
+Values that have been read via cpu_physical_memory_read() from the
+guest's memory have to be swapped in case the host endianess differs
+from the guest.
+Fixes: a6e13e31d5 ("riscv_htif: Support console output via proxy syscall")
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Bin Meng <bmeng@tinylab.org>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-Id: <20230721094720.902454-3-thuth@redhat.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ hw/char/riscv_htif.c | 9 +++++----
+file changed, 5 insertions(+), 4 deletions(-)
+diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/char/riscv_htif.c
++++ b/hw/char/riscv_htif.c
+@@ -XXX,XX +XXX,XX @@
+ #include "qemu/timer.h"
+ #include "qemu/error-report.h"
+ #include "exec/address-spaces.h"
++#include "exec/tswap.h"
+ #include "sysemu/dma.h"
+ #define RISCV_DEBUG_HTIF 0
+@@ -XXX,XX +XXX,XX @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
+             } else {
+                 uint64_t syscall[8];
+                 cpu_physical_memory_read(payload, syscall, sizeof(syscall));
+-                if (syscall[0] == PK_SYS_WRITE &&
+-                    syscall[1] == HTIF_DEV_CONSOLE &&
+-                    syscall[3] == HTIF_CONSOLE_CMD_PUTC) {
++                if (tswap64(syscall[0]) == PK_SYS_WRITE &&
++                    tswap64(syscall[1]) == HTIF_DEV_CONSOLE &&
++                    tswap64(syscall[3]) == HTIF_CONSOLE_CMD_PUTC) {
+                     uint8_t ch;
+-                    cpu_physical_memory_read(syscall[2], &ch, 1);
++                    cpu_physical_memory_read(tswap64(syscall[2]), &ch, 1);
+                     qemu_chr_fe_write(&s->chr, &ch, 1);
+                     resp = 0x100 | (uint8_t)payload;
+                 } else {
+--
+.41.0

-New patch
+[PULL v2 04/45] target/riscv/cpu.c: add zmmul isa string
+From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+zmmul was promoted from experimental to ratified in commit 6d00ffad4e95.
+Add a riscv,isa string for it.
+Fixes: 6d00ffad4e95 ("target/riscv: move zmmul out of the experimental properties")
+Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Message-Id: <20230720132424.371132-2-dbarboza@ventanamicro.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/cpu.c | 1 +
+file changed, 1 insertion(+)
+diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/cpu.c
++++ b/target/riscv/cpu.c
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
+     ISA_EXT_DATA_ENTRY(zicsr, PRIV_VERSION_1_10_0, ext_icsr),
+     ISA_EXT_DATA_ENTRY(zifencei, PRIV_VERSION_1_10_0, ext_ifencei),
+     ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause),
++    ISA_EXT_DATA_ENTRY(zmmul, PRIV_VERSION_1_12_0, ext_zmmul),
+     ISA_EXT_DATA_ENTRY(zawrs, PRIV_VERSION_1_12_0, ext_zawrs),
+     ISA_EXT_DATA_ENTRY(zfa, PRIV_VERSION_1_12_0, ext_zfa),
+     ISA_EXT_DATA_ENTRY(zfbfmin, PRIV_VERSION_1_12_0, ext_zfbfmin),
+--
+.41.0

-[PULL 23/28] target/riscv: Remove experimental prefix from "B" extension
+[PULL v2 05/45] target/riscv/cpu.c: add smepmp isa string
-From: Rob Bradford <rbradford@rivosinc.com>
+From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-This extension has now been ratified:
+The cpu->cfg.epmp extension is still experimental, but it already has a
-https://jira.riscv.org/browse/RVS-2006 so the "x-" prefix can be
+'smepmp' riscv,isa string. Add it.
 removed.
-Since this is now a ratified extension add it to the list of extensions
+Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-included in the "max" CPU variant.
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
 Signed-off-by: Rob Bradford <rbradford@rivosinc.com>
 Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-Id: <20230720132424.371132-3-dbarboza@ventanamicro.com>
 Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
 Message-ID: <20240514110217.22516-1-rbradford@rivosinc.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu.c         | 2 +-
+ target/riscv/cpu.c | 1 +
- target/riscv/tcg/tcg-cpu.c | 2 +-
+file changed, 1 insertion(+)
 files changed, 2 insertions(+), 2 deletions(-)
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ static const MISAExtInfo misa_ext_info_arr[] = {
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
-     MISA_EXT_INFO(RVJ, "x-j", "Dynamic translated languages"),
+     ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
-     MISA_EXT_INFO(RVV, "v", "Vector operations"),
+     ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
-     MISA_EXT_INFO(RVG, "g", "General purpose (IMAFD_Zicsr_Zifencei)"),
+     ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
--    MISA_EXT_INFO(RVB, "x-b", "Bit manipulation (Zba_Zbb_Zbs)")
++    ISA_EXT_DATA_ENTRY(smepmp, PRIV_VERSION_1_12_0, epmp),
-+    MISA_EXT_INFO(RVB, "b", "Bit manipulation (Zba_Zbb_Zbs)")
+     ISA_EXT_DATA_ENTRY(smstateen, PRIV_VERSION_1_12_0, ext_smstateen),
- };
+     ISA_EXT_DATA_ENTRY(ssaia, PRIV_VERSION_1_12_0, ext_ssaia),
+     ISA_EXT_DATA_ENTRY(sscofpmf, PRIV_VERSION_1_12_0, ext_sscofpmf),
  static void riscv_cpu_validate_misa_mxl(RISCVCPUClass *mcc)
 diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/tcg/tcg-cpu.c
 +++ b/target/riscv/tcg/tcg-cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_init_max_cpu_extensions(Object *obj)
      const RISCVCPUMultiExtConfig *prop;
      /* Enable RVG, RVJ and RVV that are disabled by default */
 -    riscv_cpu_set_misa_ext(env, env->misa_ext | RVG | RVJ | RVV);
 +    riscv_cpu_set_misa_ext(env, env->misa_ext | RVB | RVG | RVJ | RVV);
      for (prop = riscv_cpu_extensions; prop && prop->name; prop++) {
          isa_ext_update_enabled(cpu, prop->offset, true);
 --
-.45.1
+.41.0

-New patch
+[PULL v2 06/45] target/riscv: Fix page_check_range use in fault-only-first
+From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Commit bef6f008b98(accel/tcg: Return bool from page_check_range) converts
+integer return value to bool type. However, it wrongly converted the use
+of the API in riscv fault-only-first, where page_check_range < = 0, should
+be converted to !page_check_range.
+Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-ID: <20230729031618.821-1-zhiwei_liu@linux.alibaba.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/vector_helper.c | 2 +-
+file changed, 1 insertion(+), 1 deletion(-)
+diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/vector_helper.c
++++ b/target/riscv/vector_helper.c
+@@ -XXX,XX +XXX,XX @@ vext_ldff(void *vd, void *v0, target_ulong base,
+                                          cpu_mmu_index(env, false));
+                 if (host) {
+ #ifdef CONFIG_USER_ONLY
+-                    if (page_check_range(addr, offset, PAGE_READ)) {
++                    if (!page_check_range(addr, offset, PAGE_READ)) {
+                         vl = i;
+                         goto ProbeSuccess;
+                     }
+--
+.41.0

-[PULL 22/28] target/riscv: do not set mtval2 for non guest-page faults
+[PULL v2 07/45] target/riscv: Use existing lookup tables for MixColumns
-From: Alexei Filippov <alexei.filippov@syntacore.com>
+From: Ard Biesheuvel <ardb@kernel.org>
-Previous patch fixed the PMP priority in raise_mmu_exception() but we're still
+The AES MixColumns and InvMixColumns operations are relatively
-setting mtval2 incorrectly. In riscv_cpu_tlb_fill(), after pmp check in 2 stage
+expensive 4x4 matrix multiplications in GF(2^8), which is why C
-translation part, mtval2 will be set in case of successes 2 stage translation but
+implementations usually rely on precomputed lookup tables rather than
-failed pmp check.
+performing the calculations on demand.
-In this case we gonna set mtval2 via env->guest_phys_fault_addr in context of
+Given that we already carry those tables in QEMU, we can just grab the
-riscv_cpu_tlb_fill(), as this was a guest-page-fault, but it didn't and mtval2
+right value in the implementation of the RISC-V AES32 instructions. Note
-should be zero, according to RISCV privileged spec sect. 9.4.4: When a guest
+that the tables in question are permuted according to the respective
-page-fault is taken into M-mode, mtval2 is written with either zero or guest
+Sbox, so we can omit the Sbox lookup as well in this case.
 physical address that faulted, shifted by 2 bits. *For other traps, mtval2
 is set to zero...*
-Signed-off-by: Alexei Filippov <alexei.filippov@syntacore.com>
+Cc: Richard Henderson <richard.henderson@linaro.org>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Cc: Zewen Ye <lustrew@foxmail.com>
-Message-ID: <20240503103052.6819-1-alexei.filippov@syntacore.com>
+Cc: Weiwei Li <liweiwei@iscas.ac.cn>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Cc: Junqiang Wang <wangjunqiang@iscas.ac.cn>
 Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
 Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
 Message-ID: <20230731084043.1791984-1-ardb@kernel.org>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_helper.c | 12 ++++++------
+ include/crypto/aes.h         |  7 +++++++
-file changed, 6 insertions(+), 6 deletions(-)
+ crypto/aes.c                 |  4 ++--
  target/riscv/crypto_helper.c | 34 ++++------------------------------
 files changed, 13 insertions(+), 32 deletions(-)
-diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
+diff --git a/include/crypto/aes.h b/include/crypto/aes.h
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu_helper.c
+--- a/include/crypto/aes.h
-+++ b/target/riscv/cpu_helper.c
++++ b/include/crypto/aes.h
-@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+@@ -XXX,XX +XXX,XX @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
-                               __func__, pa, ret, prot_pmp, tlb_size);
+ extern const uint8_t AES_sbox[256];
+ extern const uint8_t AES_isbox[256];
-                 prot &= prot_pmp;
--            }
++/*
 +AES_Te0[x] = S [x].[02, 01, 01, 03];
 +AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
 +*/
 +
 +extern const uint32_t AES_Te0[256], AES_Td0[256];
 +
  #endif
 diff --git a/crypto/aes.c b/crypto/aes.c
 index XXXXXXX..XXXXXXX 100644
 --- a/crypto/aes.c
 +++ b/crypto/aes.c
@@ -XXX,XX +XXX,XX @@ AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
  AES_Td4[x] = Si[x].[01, 01, 01, 01];
  */
 -static const uint32_t AES_Te0[256] = {
 +const uint32_t AES_Te0[256] = {
 xc66363a5U, 0xf87c7c84U, 0xee777799U, 0xf67b7b8dU,
 xfff2f20dU, 0xd66b6bbdU, 0xde6f6fb1U, 0x91c5c554U,
 x60303050U, 0x02010103U, 0xce6767a9U, 0x562b2b7dU,
@@ -XXX,XX +XXX,XX @@ static const uint32_t AES_Te4[256] = {
 xb0b0b0b0U, 0x54545454U, 0xbbbbbbbbU, 0x16161616U,
  };
 -static const uint32_t AES_Td0[256] = {
 +const uint32_t AES_Td0[256] = {
 x51f4a750U, 0x7e416553U, 0x1a17a4c3U, 0x3a275e96U,
 x3bab6bcbU, 0x1f9d45f1U, 0xacfa58abU, 0x4be30393U,
 x2030fa55U, 0xad766df6U, 0x88cc7691U, 0xf5024c25U,
 diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/crypto_helper.c
 +++ b/target/riscv/crypto_helper.c
@@ -XXX,XX +XXX,XX @@
  #include "crypto/aes-round.h"
  #include "crypto/sm4.h"
 -#define AES_XTIME(a) \
 -    ((a << 1) ^ ((a & 0x80) ? 0x1b : 0))
 -
--            if (ret != TRANSLATE_SUCCESS) {
+-#define AES_GFMUL(a, b) (( \
-+            } else {
+-    (((b) & 0x1) ? (a) : 0) ^ \
-                 /*
+-    (((b) & 0x2) ? AES_XTIME(a) : 0) ^ \
-                  * Guest physical address translation failed, this is a HS
+-    (((b) & 0x4) ? AES_XTIME(AES_XTIME(a)) : 0) ^ \
-                  * level exception
+-    (((b) & 0x8) ? AES_XTIME(AES_XTIME(AES_XTIME(a))) : 0)) & 0xFF)
-                  */
+-
-                 first_stage_error = false;
+-static inline uint32_t aes_mixcolumn_byte(uint8_t x, bool fwd)
--                env->guest_phys_fault_addr = (im_address |
+-{
--                                              (address &
+-    uint32_t u;
--                                               (TARGET_PAGE_SIZE - 1))) >> 2;
+-
-+                if (ret != TRANSLATE_PMP_FAIL) {
+-    if (fwd) {
-+                    env->guest_phys_fault_addr = (im_address |
+-        u = (AES_GFMUL(x, 3) << 24) | (x << 16) | (x << 8) |
-+                                                  (address &
+-            (AES_GFMUL(x, 2) << 0);
-+                                                   (TARGET_PAGE_SIZE - 1))) >> 2;
+-    } else {
-+                }
+-        u = (AES_GFMUL(x, 0xb) << 24) | (AES_GFMUL(x, 0xd) << 16) |
-             }
+-            (AES_GFMUL(x, 0x9) << 8) | (AES_GFMUL(x, 0xe) << 0);
 -    }
 -    return u;
 -}
 -
  #define sext32_xlen(x) (target_ulong)(int32_t)(x)
  static inline target_ulong aes32_operation(target_ulong shamt,
@@ -XXX,XX +XXX,XX @@ static inline target_ulong aes32_operation(target_ulong shamt,
                                             bool enc, bool mix)
  {
      uint8_t si = rs2 >> shamt;
 -    uint8_t so;
      uint32_t mixed;
      target_ulong res;
      if (enc) {
 -        so = AES_sbox[si];
          if (mix) {
 -            mixed = aes_mixcolumn_byte(so, true);
 +            mixed = be32_to_cpu(AES_Te0[si]);
          } else {
 -            mixed = so;
 +            mixed = AES_sbox[si];
          }
      } else {
+-        so = AES_isbox[si];
+         if (mix) {
+-            mixed = aes_mixcolumn_byte(so, false);
++            mixed = be32_to_cpu(AES_Td0[si]);
+         } else {
+-            mixed = so;
++            mixed = AES_isbox[si];
+         }
+     }
+     mixed = rol32(mixed, shamt);
 --
-.45.1
+.41.0

-[PULL 05/28] hw/riscv/boot.c: Support 64-bit address for initrd
+[PULL v2 08/45] target/riscv: Refactor some of the generic vector functionality
-From: Cheng Yang <yangcheng.work@foxmail.com>
+From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
-Use qemu_fdt_setprop_u64() instead of qemu_fdt_setprop_cell()
+Take some functions/macros out of `vector_helper` and put them in a new
-to set the address of initrd in FDT to support 64-bit address.
+module called `vector_internals`. This ensures they can be used by both
 vector and vector-crypto helpers (latter implemented in proceeding
 commits).
-Signed-off-by: Cheng Yang <yangcheng.work@foxmail.com>
+Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
-Message-ID: <tencent_A4482251DD0890F312758FA6B33F60815609@qq.com>
+Signed-off-by: Max Chou <max.chou@sifive.com>
 Acked-by: Alistair Francis <alistair.francis@wdc.com>
 Message-ID: <20230711165917.2629866-2-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- hw/riscv/boot.c | 4 ++--
+ target/riscv/vector_internals.h | 182 +++++++++++++++++++++++++++++
-file changed, 2 insertions(+), 2 deletions(-)
+ target/riscv/vector_helper.c    | 201 +-------------------------------
  target/riscv/vector_internals.c |  81 +++++++++++++
  target/riscv/meson.build        |   1 +
 files changed, 265 insertions(+), 200 deletions(-)
  create mode 100644 target/riscv/vector_internals.h
  create mode 100644 target/riscv/vector_internals.c
-diff --git a/hw/riscv/boot.c b/hw/riscv/boot.c
+diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
 +++ b/target/riscv/vector_internals.h
@@ -XXX,XX +XXX,XX @@
 +/*
 + * RISC-V Vector Extension Internals
 + *
 + * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved.
 + *
 + * This program is free software; you can redistribute it and/or modify it
 + * under the terms and conditions of the GNU General Public License,
 + * version 2 or later, as published by the Free Software Foundation.
 + *
 + * This program is distributed in the hope it will be useful, but WITHOUT
 + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 + * more details.
 + *
 + * You should have received a copy of the GNU General Public License along with
 + * this program.  If not, see <http://www.gnu.org/licenses/>.
 + */
 +
 +#ifndef TARGET_RISCV_VECTOR_INTERNALS_H
 +#define TARGET_RISCV_VECTOR_INTERNALS_H
 +
 +#include "qemu/osdep.h"
 +#include "qemu/bitops.h"
 +#include "cpu.h"
 +#include "tcg/tcg-gvec-desc.h"
 +#include "internals.h"
 +
 +static inline uint32_t vext_nf(uint32_t desc)
 +{
 +    return FIELD_EX32(simd_data(desc), VDATA, NF);
 +}
 +
 +/*
 + * Note that vector data is stored in host-endian 64-bit chunks,
 + * so addressing units smaller than that needs a host-endian fixup.
 + */
 +#if HOST_BIG_ENDIAN
 +#define H1(x)   ((x) ^ 7)
 +#define H1_2(x) ((x) ^ 6)
 +#define H1_4(x) ((x) ^ 4)
 +#define H2(x)   ((x) ^ 3)
 +#define H4(x)   ((x) ^ 1)
 +#define H8(x)   ((x))
 +#else
 +#define H1(x)   (x)
 +#define H1_2(x) (x)
 +#define H1_4(x) (x)
 +#define H2(x)   (x)
 +#define H4(x)   (x)
 +#define H8(x)   (x)
 +#endif
 +
 +/*
 + * Encode LMUL to lmul as following:
 + *     LMUL    vlmul    lmul
 + *      1       000       0
 + *      2       001       1
 + *      4       010       2
 + *      8       011       3
 + *      -       100       -
 + *     1/8      101      -3
 + *     1/4      110      -2
 + *     1/2      111      -1
 + */
 +static inline int32_t vext_lmul(uint32_t desc)
 +{
 +    return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
 +}
 +
 +static inline uint32_t vext_vm(uint32_t desc)
 +{
 +    return FIELD_EX32(simd_data(desc), VDATA, VM);
 +}
 +
 +static inline uint32_t vext_vma(uint32_t desc)
 +{
 +    return FIELD_EX32(simd_data(desc), VDATA, VMA);
 +}
 +
 +static inline uint32_t vext_vta(uint32_t desc)
 +{
 +    return FIELD_EX32(simd_data(desc), VDATA, VTA);
 +}
 +
 +static inline uint32_t vext_vta_all_1s(uint32_t desc)
 +{
 +    return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
 +}
 +
 +/*
 + * Earlier designs (pre-0.9) had a varying number of bits
 + * per mask value (MLEN). In the 0.9 design, MLEN=1.
 + * (Section 4.5)
 + */
 +static inline int vext_elem_mask(void *v0, int index)
 +{
 +    int idx = index / 64;
 +    int pos = index  % 64;
 +    return (((uint64_t *)v0)[idx] >> pos) & 1;
 +}
 +
 +/*
 + * Get number of total elements, including prestart, body and tail elements.
 + * Note that when LMUL < 1, the tail includes the elements past VLMAX that
 + * are held in the same vector register.
 + */
 +static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
 +                                            uint32_t esz)
 +{
 +    uint32_t vlenb = simd_maxsz(desc);
 +    uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
 +    int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
 +                  ctzl(esz) - ctzl(sew) + vext_lmul(desc);
 +    return (vlenb << emul) / esz;
 +}
 +
 +/* set agnostic elements to 1s */
 +void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
 +                       uint32_t tot);
 +
 +/* expand macro args before macro */
 +#define RVVCALL(macro, ...)  macro(__VA_ARGS__)
 +
 +/* (TD, T1, T2, TX1, TX2) */
 +#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
 +#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
 +#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
 +#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
 +
 +/* operation of two vector elements */
 +typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
 +
 +#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
 +static void do_##NAME(void *vd, void *vs1, void *vs2, int i)    \
 +{                                                               \
 +    TX1 s1 = *((T1 *)vs1 + HS1(i));                             \
 +    TX2 s2 = *((T2 *)vs2 + HS2(i));                             \
 +    *((TD *)vd + HD(i)) = OP(s2, s1);                           \
 +}
 +
 +void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
 +                CPURISCVState *env, uint32_t desc,
 +                opivv2_fn *fn, uint32_t esz);
 +
 +/* generate the helpers for OPIVV */
 +#define GEN_VEXT_VV(NAME, ESZ)                            \
 +void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
 +                  void *vs2, CPURISCVState *env,          \
 +                  uint32_t desc)                          \
 +{                                                         \
 +    do_vext_vv(vd, v0, vs1, vs2, env, desc,               \
 +               do_##NAME, ESZ);                           \
 +}
 +
 +typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
 +
 +/*
 + * (T1)s1 gives the real operator type.
 + * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
 + */
 +#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)             \
 +static void do_##NAME(void *vd, target_long s1, void *vs2, int i)   \
 +{                                                                   \
 +    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
 +    *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1);                      \
 +}
 +
 +void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
 +                CPURISCVState *env, uint32_t desc,
 +                opivx2_fn fn, uint32_t esz);
 +
 +/* generate the helpers for OPIVX */
 +#define GEN_VEXT_VX(NAME, ESZ)                            \
 +void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
 +                  void *vs2, CPURISCVState *env,          \
 +                  uint32_t desc)                          \
 +{                                                         \
 +    do_vext_vx(vd, v0, s1, vs2, env, desc,                \
 +               do_##NAME, ESZ);                           \
 +}
 +
 +#endif /* TARGET_RISCV_VECTOR_INTERNALS_H */
 diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/riscv/boot.c
+--- a/target/riscv/vector_helper.c
-+++ b/hw/riscv/boot.c
++++ b/target/riscv/vector_helper.c
-@@ -XXX,XX +XXX,XX @@ static void riscv_load_initrd(MachineState *machine, uint64_t kernel_entry)
+@@ -XXX,XX +XXX,XX @@
-     /* Some RISC-V machines (e.g. opentitan) don't have a fdt. */
+ #include "fpu/softfloat.h"
-     if (fdt) {
+ #include "tcg/tcg-gvec-desc.h"
-         end = start + size;
+ #include "internals.h"
--        qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-start", start);
++#include "vector_internals.h"
--        qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-end", end);
+ #include <math.h>
-+        qemu_fdt_setprop_u64(fdt, "/chosen", "linux,initrd-start", start);
-+        qemu_fdt_setprop_u64(fdt, "/chosen", "linux,initrd-end", end);
+ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
@@ -XXX,XX +XXX,XX @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
      return vl;
  }
 -/*
 - * Note that vector data is stored in host-endian 64-bit chunks,
 - * so addressing units smaller than that needs a host-endian fixup.
 - */
 -#if HOST_BIG_ENDIAN
 -#define H1(x)   ((x) ^ 7)
 -#define H1_2(x) ((x) ^ 6)
 -#define H1_4(x) ((x) ^ 4)
 -#define H2(x)   ((x) ^ 3)
 -#define H4(x)   ((x) ^ 1)
 -#define H8(x)   ((x))
 -#else
 -#define H1(x)   (x)
 -#define H1_2(x) (x)
 -#define H1_4(x) (x)
 -#define H2(x)   (x)
 -#define H4(x)   (x)
 -#define H8(x)   (x)
 -#endif
 -
 -static inline uint32_t vext_nf(uint32_t desc)
 -{
 -    return FIELD_EX32(simd_data(desc), VDATA, NF);
 -}
 -
 -static inline uint32_t vext_vm(uint32_t desc)
 -{
 -    return FIELD_EX32(simd_data(desc), VDATA, VM);
 -}
 -
 -/*
 - * Encode LMUL to lmul as following:
 - *     LMUL    vlmul    lmul
 - *      1       000       0
 - *      2       001       1
 - *      4       010       2
 - *      8       011       3
 - *      -       100       -
 - *     1/8      101      -3
 - *     1/4      110      -2
 - *     1/2      111      -1
 - */
 -static inline int32_t vext_lmul(uint32_t desc)
 -{
 -    return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
 -}
 -
 -static inline uint32_t vext_vta(uint32_t desc)
 -{
 -    return FIELD_EX32(simd_data(desc), VDATA, VTA);
 -}
 -
 -static inline uint32_t vext_vma(uint32_t desc)
 -{
 -    return FIELD_EX32(simd_data(desc), VDATA, VMA);
 -}
 -
 -static inline uint32_t vext_vta_all_1s(uint32_t desc)
 -{
 -    return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
 -}
 -
  /*
   * Get the maximum number of elements can be operated.
   *
@@ -XXX,XX +XXX,XX @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
      return scale < 0 ? vlenb >> -scale : vlenb << scale;
  }
 -/*
 - * Get number of total elements, including prestart, body and tail elements.
 - * Note that when LMUL < 1, the tail includes the elements past VLMAX that
 - * are held in the same vector register.
 - */
 -static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
 -                                            uint32_t esz)
 -{
 -    uint32_t vlenb = simd_maxsz(desc);
 -    uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
 -    int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
 -                  ctzl(esz) - ctzl(sew) + vext_lmul(desc);
 -    return (vlenb << emul) / esz;
 -}
 -
  static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
  {
      return (addr & ~env->cur_pmmask) | env->cur_pmbase;
@@ -XXX,XX +XXX,XX @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
      }
  }
+-/* set agnostic elements to 1s */
+-static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+-                              uint32_t tot)
+-{
+-    if (is_agnostic == 0) {
+-        /* policy undisturbed */
+-        return;
+-    }
+-    if (tot - cnt == 0) {
+-        return;
+-    }
+-    memset(base + cnt, -1, tot - cnt);
+-}
+-
+ static inline void vext_set_elem_mask(void *v0, int index,
+                                       uint8_t value)
+ {
+@@ -XXX,XX +XXX,XX @@ static inline void vext_set_elem_mask(void *v0, int index,
+     ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value);
+ }
+-/*
+- * Earlier designs (pre-0.9) had a varying number of bits
+- * per mask value (MLEN). In the 0.9 design, MLEN=1.
+- * (Section 4.5)
+- */
+-static inline int vext_elem_mask(void *v0, int index)
+-{
+-    int idx = index / 64;
+-    int pos = index  % 64;
+-    return (((uint64_t *)v0)[idx] >> pos) & 1;
+-}
+-
+ /* elements operations for load and store */
+ typedef void vext_ldst_elem_fn(CPURISCVState *env, abi_ptr addr,
+                                uint32_t idx, void *vd, uintptr_t retaddr);
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
+  * Vector Integer Arithmetic Instructions
+  */
+-/* expand macro args before macro */
+-#define RVVCALL(macro, ...)  macro(__VA_ARGS__)
+-
+ /* (TD, T1, T2, TX1, TX2) */
+ #define OP_SSS_B int8_t, int8_t, int8_t, int8_t, int8_t
+ #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
+ #define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
+ #define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
+-#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+-#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+-#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+-#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
+ #define OP_SUS_B int8_t, uint8_t, int8_t, uint8_t, int8_t
+ #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
+ #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
+ #define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
+ #define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
+-/* operation of two vector elements */
+-typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
+-
+-#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
+-static void do_##NAME(void *vd, void *vs1, void *vs2, int i)    \
+-{                                                               \
+-    TX1 s1 = *((T1 *)vs1 + HS1(i));                             \
+-    TX2 s2 = *((T2 *)vs2 + HS2(i));                             \
+-    *((TD *)vd + HD(i)) = OP(s2, s1);                           \
+-}
+ #define DO_SUB(N, M) (N - M)
+ #define DO_RSUB(N, M) (M - N)
+@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVV2, vsub_vv_h, OP_SSS_H, H2, H2, H2, DO_SUB)
+ RVVCALL(OPIVV2, vsub_vv_w, OP_SSS_W, H4, H4, H4, DO_SUB)
+ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
+-static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
+-                       CPURISCVState *env, uint32_t desc,
+-                       opivv2_fn *fn, uint32_t esz)
+-{
+-    uint32_t vm = vext_vm(desc);
+-    uint32_t vl = env->vl;
+-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+-    uint32_t vta = vext_vta(desc);
+-    uint32_t vma = vext_vma(desc);
+-    uint32_t i;
+-
+-    for (i = env->vstart; i < vl; i++) {
+-        if (!vm && !vext_elem_mask(v0, i)) {
+-            /* set masked-off elements to 1s */
+-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
+-            continue;
+-        }
+-        fn(vd, vs1, vs2, i);
+-    }
+-    env->vstart = 0;
+-    /* set tail elements to 1s */
+-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+-}
+-
+-/* generate the helpers for OPIVV */
+-#define GEN_VEXT_VV(NAME, ESZ)                            \
+-void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
+-                  void *vs2, CPURISCVState *env,          \
+-                  uint32_t desc)                          \
+-{                                                         \
+-    do_vext_vv(vd, v0, vs1, vs2, env, desc,               \
+-               do_##NAME, ESZ);                           \
+-}
+-
+ GEN_VEXT_VV(vadd_vv_b, 1)
+ GEN_VEXT_VV(vadd_vv_h, 2)
+ GEN_VEXT_VV(vadd_vv_w, 4)
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_VV(vsub_vv_h, 2)
+ GEN_VEXT_VV(vsub_vv_w, 4)
+ GEN_VEXT_VV(vsub_vv_d, 8)
+-typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
+-
+-/*
+- * (T1)s1 gives the real operator type.
+- * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
+- */
+-#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)             \
+-static void do_##NAME(void *vd, target_long s1, void *vs2, int i)   \
+-{                                                                   \
+-    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
+-    *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1);                      \
+-}
+ RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD)
+ RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD)
+@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVX2, vrsub_vx_h, OP_SSS_H, H2, H2, DO_RSUB)
+ RVVCALL(OPIVX2, vrsub_vx_w, OP_SSS_W, H4, H4, DO_RSUB)
+ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
+-static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
+-                       CPURISCVState *env, uint32_t desc,
+-                       opivx2_fn fn, uint32_t esz)
+-{
+-    uint32_t vm = vext_vm(desc);
+-    uint32_t vl = env->vl;
+-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+-    uint32_t vta = vext_vta(desc);
+-    uint32_t vma = vext_vma(desc);
+-    uint32_t i;
+-
+-    for (i = env->vstart; i < vl; i++) {
+-        if (!vm && !vext_elem_mask(v0, i)) {
+-            /* set masked-off elements to 1s */
+-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
+-            continue;
+-        }
+-        fn(vd, s1, vs2, i);
+-    }
+-    env->vstart = 0;
+-    /* set tail elements to 1s */
+-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+-}
+-
+-/* generate the helpers for OPIVX */
+-#define GEN_VEXT_VX(NAME, ESZ)                            \
+-void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
+-                  void *vs2, CPURISCVState *env,          \
+-                  uint32_t desc)                          \
+-{                                                         \
+-    do_vext_vx(vd, v0, s1, vs2, env, desc,                \
+-               do_##NAME, ESZ);                           \
+-}
+-
+ GEN_VEXT_VX(vadd_vx_b, 1)
+ GEN_VEXT_VX(vadd_vx_h, 2)
+ GEN_VEXT_VX(vadd_vx_w, 4)
+diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
+new file mode 100644
+index XXXXXXX..XXXXXXX
+--- /dev/null
++++ b/target/riscv/vector_internals.c
+@@ -XXX,XX +XXX,XX @@
++/*
++ * RISC-V Vector Extension Internals
++ *
++ * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify it
++ * under the terms and conditions of the GNU General Public License,
++ * version 2 or later, as published by the Free Software Foundation.
++ *
++ * This program is distributed in the hope it will be useful, but WITHOUT
++ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
++ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
++ * more details.
++ *
++ * You should have received a copy of the GNU General Public License along with
++ * this program.  If not, see <http://www.gnu.org/licenses/>.
++ */
++
++#include "vector_internals.h"
++
++/* set agnostic elements to 1s */
++void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
++                       uint32_t tot)
++{
++    if (is_agnostic == 0) {
++        /* policy undisturbed */
++        return;
++    }
++    if (tot - cnt == 0) {
++        return ;
++    }
++    memset(base + cnt, -1, tot - cnt);
++}
++
++void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
++                CPURISCVState *env, uint32_t desc,
++                opivv2_fn *fn, uint32_t esz)
++{
++    uint32_t vm = vext_vm(desc);
++    uint32_t vl = env->vl;
++    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
++    uint32_t vta = vext_vta(desc);
++    uint32_t vma = vext_vma(desc);
++    uint32_t i;
++
++    for (i = env->vstart; i < vl; i++) {
++        if (!vm && !vext_elem_mask(v0, i)) {
++            /* set masked-off elements to 1s */
++            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
++            continue;
++        }
++        fn(vd, vs1, vs2, i);
++    }
++    env->vstart = 0;
++    /* set tail elements to 1s */
++    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
++}
++
++void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
++                CPURISCVState *env, uint32_t desc,
++                opivx2_fn fn, uint32_t esz)
++{
++    uint32_t vm = vext_vm(desc);
++    uint32_t vl = env->vl;
++    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
++    uint32_t vta = vext_vta(desc);
++    uint32_t vma = vext_vma(desc);
++    uint32_t i;
++
++    for (i = env->vstart; i < vl; i++) {
++        if (!vm && !vext_elem_mask(v0, i)) {
++            /* set masked-off elements to 1s */
++            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
++            continue;
++        }
++        fn(vd, s1, vs2, i);
++    }
++    env->vstart = 0;
++    /* set tail elements to 1s */
++    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
++}
+diff --git a/target/riscv/meson.build b/target/riscv/meson.build
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/meson.build
++++ b/target/riscv/meson.build
+@@ -XXX,XX +XXX,XX @@ riscv_ss.add(files(
+   'gdbstub.c',
+   'op_helper.c',
+   'vector_helper.c',
++  'vector_internals.c',
+   'bitmanip_helper.c',
+   'translate.c',
+   'm128_helper.c',
 --
-.45.1
+.41.0

-[PULL 19/28] target/riscv: rvv: Check single width operator for vfncvt.rod.f.f.w
+[PULL v2 09/45] target/riscv: Refactor vector-vector translation macro
-From: Max Chou <max.chou@sifive.com>
+From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
-The opfv_narrow_check needs to check the single width float operator by
+Refactor the non SEW-specific stuff out of `GEN_OPIVV_TRANS` into
-require_rvf.
+function `opivv_trans` (similar to `opivi_trans`). `opivv_trans` will be
 used in proceeding vector-crypto commits.
+Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
 Signed-off-by: Max Chou <max.chou@sifive.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-ID: <20230711165917.2629866-3-max.chou@sifive.com>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240322092600.1198921-4-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_rvv.c.inc | 1 +
+ target/riscv/insn_trans/trans_rvv.c.inc | 62 +++++++++++++------------
-file changed, 1 insertion(+)
+file changed, 32 insertions(+), 30 deletions(-)
 diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvv.c.inc
 +++ b/target/riscv/insn_trans/trans_rvv.c.inc
-@@ -XXX,XX +XXX,XX @@ static bool opffv_narrow_check(DisasContext *s, arg_rmr *a)
+@@ -XXX,XX +XXX,XX @@ GEN_OPIWX_WIDEN_TRANS(vwadd_wx)
- static bool opffv_rod_narrow_check(DisasContext *s, arg_rmr *a)
+ GEN_OPIWX_WIDEN_TRANS(vwsubu_wx)
- {
+ GEN_OPIWX_WIDEN_TRANS(vwsub_wx)
-     return opfv_narrow_check(s, a) &&
-+           require_rvf(s) &&
++static bool opivv_trans(uint32_t vd, uint32_t vs1, uint32_t vs2, uint32_t vm,
-            require_scale_rvf(s) &&
++                        gen_helper_gvec_4_ptr *fn, DisasContext *s)
-            (s->sew != MO_8);
++{
 +    uint32_t data = 0;
 +    TCGLabel *over = gen_new_label();
 +    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
 +    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 +
 +    data = FIELD_DP32(data, VDATA, VM, vm);
 +    data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
 +    data = FIELD_DP32(data, VDATA, VTA, s->vta);
 +    data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
 +    data = FIELD_DP32(data, VDATA, VMA, s->vma);
 +    tcg_gen_gvec_4_ptr(vreg_ofs(s, vd), vreg_ofs(s, 0), vreg_ofs(s, vs1),
 +                       vreg_ofs(s, vs2), cpu_env, s->cfg_ptr->vlen / 8,
 +                       s->cfg_ptr->vlen / 8, data, fn);
 +    mark_vs_dirty(s);
 +    gen_set_label(over);
 +    return true;
 +}
 +
  /* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
  /* OPIVV without GVEC IR */
 -#define GEN_OPIVV_TRANS(NAME, CHECK)                               \
 -static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
 -{                                                                  \
 -    if (CHECK(s, a)) {                                             \
 -        uint32_t data = 0;                                         \
 -        static gen_helper_gvec_4_ptr * const fns[4] = {            \
 -            gen_helper_##NAME##_b, gen_helper_##NAME##_h,          \
 -            gen_helper_##NAME##_w, gen_helper_##NAME##_d,          \
 -        };                                                         \
 -        TCGLabel *over = gen_new_label();                          \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
 -        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
 -                                                                   \
 -        data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
 -        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
 -        data = FIELD_DP32(data, VDATA, VTA, s->vta);               \
 -        data =                                                     \
 -            FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
 -        data = FIELD_DP32(data, VDATA, VMA, s->vma);               \
 -        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
 -                           vreg_ofs(s, a->rs1),                    \
 -                           vreg_ofs(s, a->rs2), cpu_env,           \
 -                           s->cfg_ptr->vlen / 8,                   \
 -                           s->cfg_ptr->vlen / 8, data,             \
 -                           fns[s->sew]);                           \
 -        mark_vs_dirty(s);                                          \
 -        gen_set_label(over);                                       \
 -        return true;                                               \
 -    }                                                              \
 -    return false;                                                  \
 +#define GEN_OPIVV_TRANS(NAME, CHECK)                                     \
 +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
 +{                                                                        \
 +    if (CHECK(s, a)) {                                                   \
 +        static gen_helper_gvec_4_ptr * const fns[4] = {                  \
 +            gen_helper_##NAME##_b, gen_helper_##NAME##_h,                \
 +            gen_helper_##NAME##_w, gen_helper_##NAME##_d,                \
 +        };                                                               \
 +        return opivv_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);\
 +    }                                                                    \
 +    return false;                                                        \
  }
+ /*
 --
-.45.1
+.41.0

-[PULL 18/28] target/riscv: rvv: Check single width operator for vector fp widen instructions
+[PULL v2 10/45] target/riscv: Remove redundant "cpu_vl == 0" checks
-From: Max Chou <max.chou@sifive.com>
+From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-The require_scale_rvf function only checks the double width operator for
+Remove the redundant "vl == 0" check which is already included within the  vstart >= vl check, when vl == 0.
 the vector floating point widen instructions, so most of the widen
 checking functions need to add require_rvf for single width operator.
-The vfwcvt.f.x.v and vfwcvt.f.xu.v instructions convert single width
+Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-integer to double width float, so the opfxv_widen_check function doesn’t
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
 need require_rvf for the single width operator(integer).
 Signed-off-by: Max Chou <max.chou@sifive.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Acked-by: Alistair Francis <alistair.francis@wdc.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-ID: <20230711165917.2629866-4-max.chou@sifive.com>
 Message-ID: <20240322092600.1198921-3-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_rvv.c.inc | 5 +++++
+ target/riscv/insn_trans/trans_rvv.c.inc | 31 +------------------------
-file changed, 5 insertions(+)
+file changed, 1 insertion(+), 30 deletions(-)
 diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvv.c.inc
 +++ b/target/riscv/insn_trans/trans_rvv.c.inc
-@@ -XXX,XX +XXX,XX @@ GEN_OPFVF_TRANS(vfrsub_vf,  opfvf_check)
+@@ -XXX,XX +XXX,XX @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
- static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+     TCGv_i32 desc;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
      TCGv_i32 desc;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
      TCGv_i32 desc;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
      TCGv_i32 desc;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
          return false;
      }
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
@@ -XXX,XX +XXX,XX @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
      uint32_t data = 0;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
      uint32_t data = 0;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
      if (checkfn(s, a)) {
          uint32_t data = 0;
          TCGLabel *over = gen_new_label();
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
      if (opiwv_widen_check(s, a)) {
          uint32_t data = 0;
          TCGLabel *over = gen_new_label();
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool opivv_trans(uint32_t vd, uint32_t vs1, uint32_t vs2, uint32_t vm,
  {
-     return require_rvv(s) &&
+     uint32_t data = 0;
-+           require_rvf(s) &&
+     TCGLabel *over = gen_new_label();
-            require_scale_rvf(s) &&
+-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
-            (s->sew != MO_8) &&
+     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-            vext_check_isa_ill(s) &&
-@@ -XXX,XX +XXX,XX @@ GEN_OPFVV_WIDEN_TRANS(vfwsub_vv, opfvv_widen_check)
+     data = FIELD_DP32(data, VDATA, VM, vm);
- static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a)
+@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
- {
+             gen_helper_##NAME##_w,                                 \
-     return require_rvv(s) &&
+         };                                                         \
-+           require_rvf(s) &&
+         TCGLabel *over = gen_new_label();                          \
-            require_scale_rvf(s) &&
+-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
-            (s->sew != MO_8) &&
+         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
-            vext_check_isa_ill(s) &&
+                                                                    \
-@@ -XXX,XX +XXX,XX @@ GEN_OPFVF_WIDEN_TRANS(vfwsub_vf)
+         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
- static bool opfwv_widen_check(DisasContext *s, arg_rmrr *a)
+@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
- {
+                 gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
-     return require_rvv(s) &&
+             };
-+           require_rvf(s) &&
+             TCGLabel *over = gen_new_label();
-            require_scale_rvf(s) &&
+-            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
-            (s->sew != MO_8) &&
+             tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-            vext_check_isa_ill(s) &&
-@@ -XXX,XX +XXX,XX @@ GEN_OPFWV_WIDEN_TRANS(vfwsub_wv)
+             tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
- static bool opfwf_widen_check(DisasContext *s, arg_rmrr *a)
+@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
- {
+         vext_check_ss(s, a->rd, 0, 1)) {
-     return require_rvv(s) &&
+         TCGv s1;
-+           require_rvf(s) &&
+         TCGLabel *over = gen_new_label();
-            require_scale_rvf(s) &&
+-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
-            (s->sew != MO_8) &&
+         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-            vext_check_isa_ill(s) &&
-@@ -XXX,XX +XXX,XX @@ GEN_OPFVV_TRANS(vfredmin_vs, freduction_check)
+         s1 = get_gpr(s, a->rs1, EXT_SIGN);
- static bool freduction_widen_check(DisasContext *s, arg_rmrr *a)
+@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
- {
+                 gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
-     return reduction_widen_check(s, a) &&
+             };
-+           require_rvf(s) &&
+             TCGLabel *over = gen_new_label();
-            require_scale_rvf(s) &&
+-            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
-            (s->sew != MO_8);
+             tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
- }
              s1 = tcg_constant_i64(simm);
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm(s, RISCV_FRM_DYN);                              \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
      TCGv_i64 t1;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
          };                                                       \
          TCGLabel *over = gen_new_label();                        \
          gen_set_rm(s, RISCV_FRM_DYN);                            \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);        \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
                                                                   \
          data = FIELD_DP32(data, VDATA, VM, a->vm);               \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm(s, RISCV_FRM_DYN);                              \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
          uint32_t data = 0;
          TCGLabel *over = gen_new_label();
          gen_set_rm_chkfrm(s, rm);
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
                  gen_helper_vmv_v_x_d,
              };
              TCGLabel *over = gen_new_label();
 -            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
              tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
              t1 = tcg_temp_new_i64();
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm_chkfrm(s, FRM);                                 \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm(s, RISCV_FRM_DYN);                              \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm_chkfrm(s, FRM);                                 \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
          };                                                         \
          TCGLabel *over = gen_new_label();                          \
          gen_set_rm_chkfrm(s, FRM);                                 \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_r *a)                \
          uint32_t data = 0;                                         \
          gen_helper_gvec_4_ptr *fn = gen_helper_##NAME;             \
          TCGLabel *over = gen_new_label();                          \
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                     \
          data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -XXX,XX +XXX,XX @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
          require_vm(a->vm, a->rd)) {
          uint32_t data = 0;
          TCGLabel *over = gen_new_label();
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
          TCGv s1;
          TCGLabel *over = gen_new_label();
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          t1 = tcg_temp_new_i64();
@@ -XXX,XX +XXX,XX @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
          TCGv_i64 t1;
          TCGLabel *over = gen_new_label();
 -        /* if vl == 0 or vstart >= vl, skip vector register write back */
 -        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
 +        /* if vstart >= vl, skip vector register write back */
          tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
          /* NaN-box f[rs1] */
@@ -XXX,XX +XXX,XX @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
      uint32_t data = 0;
      gen_helper_gvec_3_ptr *fn;
      TCGLabel *over = gen_new_label();
 -    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
      static gen_helper_gvec_3_ptr * const fns[6][4] = {
 --
-.45.1
+.41.0

-[PULL 16/28] riscv: thead: Add th.sxstatus CSR emulation
+[PULL v2 11/45] target/riscv: Add Zvbc ISA extension support
-From: Christoph Müllner <christoph.muellner@vrull.eu>
+From: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
-The th.sxstatus CSR can be used to identify available custom extension
+This commit adds support for the Zvbc vector-crypto extension, which
-on T-Head CPUs. The CSR is documented here:
+consists of the following instructions:
-  https://github.com/T-head-Semi/thead-extension-spec/blob/master/xtheadsxstatus.adoc
+* vclmulh.[vx,vv]
-An important property of this patch is, that the th.sxstatus MAEE field
+* vclmul.[vx,vv]
-is not set (indicating that XTheadMae is not available).
-XTheadMae is a memory attribute extension (similar to Svpbmt) which is
+Translation functions are defined in
-implemented in many T-Head CPUs (C906, C910, etc.) and utilizes bits
+`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
-in PTEs that are marked as reserved. QEMU maintainers prefer to not
+`target/riscv/vcrypto_helper.c`.
-implement XTheadMae, so we need give kernels a mechanism to identify
-if XTheadMae is available in a system or not. And this patch introduces
+Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-this mechanism in QEMU in a way that's compatible with real HW
+Co-authored-by: Max Chou <max.chou@sifive.com>
-(i.e., probing the th.sxstatus.MAEE bit).
+Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
+Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
-Further context can be found on the list:
+Signed-off-by: Max Chou <max.chou@sifive.com>
-https://lists.gnu.org/archive/html/qemu-devel/2024-02/msg00775.html
+[max.chou@sifive.com: Exposed x-zvbc property]
+Message-ID: <20230711165917.2629866-5-max.chou@sifive.com>
 Reviewed-by: LIU Zhiwei <zhiwe_liu@linux.alibaba.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
 Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
 Message-ID: <20240429073656.2486732-1-christoph.muellner@vrull.eu>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- MAINTAINERS              |  1 +
+ target/riscv/cpu_cfg.h                   |  1 +
- target/riscv/cpu.h       |  3 ++
+ target/riscv/helper.h                    |  6 +++
- target/riscv/cpu.c       |  1 +
+ target/riscv/insn32.decode               |  6 +++
- target/riscv/th_csr.c    | 79 ++++++++++++++++++++++++++++++++++++++++
+ target/riscv/cpu.c                       |  9 ++++
- target/riscv/meson.build |  1 +
+ target/riscv/translate.c                 |  1 +
-files changed, 85 insertions(+)
+ target/riscv/vcrypto_helper.c            | 59 ++++++++++++++++++++++
- create mode 100644 target/riscv/th_csr.c
+ target/riscv/insn_trans/trans_rvvk.c.inc | 62 ++++++++++++++++++++++++
+ target/riscv/meson.build                 |  3 +-
-diff --git a/MAINTAINERS b/MAINTAINERS
+files changed, 146 insertions(+), 1 deletion(-)
-index XXXXXXX..XXXXXXX 100644
+ create mode 100644 target/riscv/vcrypto_helper.c
---- a/MAINTAINERS
+ create mode 100644 target/riscv/insn_trans/trans_rvvk.c.inc
-+++ b/MAINTAINERS
-@@ -XXX,XX +XXX,XX @@ L: qemu-riscv@nongnu.org
+diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
- S: Supported
+index XXXXXXX..XXXXXXX 100644
- F: target/riscv/insn_trans/trans_xthead.c.inc
+--- a/target/riscv/cpu_cfg.h
- F: target/riscv/xthead*.decode
++++ b/target/riscv/cpu_cfg.h
-+F: target/riscv/th_*
+@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
- F: disas/riscv-xthead*
+     bool ext_zve32f;
+     bool ext_zve64f;
- RISC-V XVentanaCondOps extension
+     bool ext_zve64d;
-diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
++    bool ext_zvbc;
-index XXXXXXX..XXXXXXX 100644
+     bool ext_zmmul;
---- a/target/riscv/cpu.h
+     bool ext_zvfbfmin;
-+++ b/target/riscv/cpu.h
+     bool ext_zvfbfwma;
-@@ -XXX,XX +XXX,XX @@ target_ulong riscv_new_csr_seed(target_ulong new_value,
+diff --git a/target/riscv/helper.h b/target/riscv/helper.h
- uint8_t satp_mode_max_from_map(uint32_t map);
+index XXXXXXX..XXXXXXX 100644
- const char *satp_mode_str(uint8_t satp_mode, bool is_32_bit);
+--- a/target/riscv/helper.h
++++ b/target/riscv/helper.h
-+/* Implemented in th_csr.c */
+@@ -XXX,XX +XXX,XX @@ DEF_HELPER_5(vfwcvtbf16_f_f_v, void, ptr, ptr, ptr, env, i32)
-+void th_register_custom_csrs(RISCVCPU *cpu);
-+
+ DEF_HELPER_6(vfwmaccbf16_vv, void, ptr, ptr, ptr, ptr, env, i32)
- #endif /* RISCV_CPU_H */
+ DEF_HELPER_6(vfwmaccbf16_vf, void, ptr, ptr, i64, ptr, env, i32)
 +
 +/* Vector crypto functions */
 +DEF_HELPER_6(vclmul_vv, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vclmul_vx, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vclmulh_vv, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vclmulh_vx, void, ptr, ptr, tl, ptr, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vfwcvtbf16_f_f_v  010010 . ..... 01101 001 ..... 1010111 @r2_vm
  # *** Zvfbfwma Standard Extension ***
  vfwmaccbf16_vv    111011 . ..... ..... 001 ..... 1010111 @r_vm
  vfwmaccbf16_vf    111011 . ..... ..... 101 ..... 1010111 @r_vm
 +
 +# *** Zvbc vector crypto extension ***
 +vclmul_vv   001100 . ..... ..... 010 ..... 1010111 @r_vm
 +vclmul_vx   001100 . ..... ..... 110 ..... 1010111 @r_vm
 +vclmulh_vv  001101 . ..... ..... 010 ..... 1010111 @r_vm
 +vclmulh_vx  001101 . ..... ..... 110 ..... 1010111 @r_vm
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ static void rv64_thead_c906_cpu_init(Object *obj)
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
-     cpu->cfg.mvendorid = THEAD_VENDOR_ID;
+     ISA_EXT_DATA_ENTRY(zksed, PRIV_VERSION_1_12_0, ext_zksed),
- #ifndef CONFIG_USER_ONLY
+     ISA_EXT_DATA_ENTRY(zksh, PRIV_VERSION_1_12_0, ext_zksh),
-     set_satp_mode_max_supported(cpu, VM_1_10_SV39);
+     ISA_EXT_DATA_ENTRY(zkt, PRIV_VERSION_1_12_0, ext_zkt),
-+    th_register_custom_csrs(cpu);
++    ISA_EXT_DATA_ENTRY(zvbc, PRIV_VERSION_1_12_0, ext_zvbc),
- #endif
+     ISA_EXT_DATA_ENTRY(zve32f, PRIV_VERSION_1_10_0, ext_zve32f),
+     ISA_EXT_DATA_ENTRY(zve64f, PRIV_VERSION_1_10_0, ext_zve64f),
-     /* inherited from parent obj via riscv_cpu_init() */
+     ISA_EXT_DATA_ENTRY(zve64d, PRIV_VERSION_1_10_0, ext_zve64d),
-diff --git a/target/riscv/th_csr.c b/target/riscv/th_csr.c
+@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
          return;
      }
 +    if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) {
 +        error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions");
 +        return;
 +    }
 +
      if (cpu->cfg.ext_zk) {
          cpu->cfg.ext_zkn = true;
          cpu->cfg.ext_zkr = true;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      DEFINE_PROP_BOOL("x-zvfbfmin", RISCVCPU, cfg.ext_zvfbfmin, false),
      DEFINE_PROP_BOOL("x-zvfbfwma", RISCVCPU, cfg.ext_zvfbfwma, false),
 +    /* Vector cryptography extensions */
 +    DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
 +
      DEFINE_PROP_END_OF_LIST(),
  };
 diff --git a/target/riscv/translate.c b/target/riscv/translate.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/translate.c
 +++ b/target/riscv/translate.c
@@ -XXX,XX +XXX,XX @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc)
  #include "insn_trans/trans_rvzfa.c.inc"
  #include "insn_trans/trans_rvzfh.c.inc"
  #include "insn_trans/trans_rvk.c.inc"
 +#include "insn_trans/trans_rvvk.c.inc"
  #include "insn_trans/trans_privileged.c.inc"
  #include "insn_trans/trans_svinval.c.inc"
  #include "insn_trans/trans_rvbf16.c.inc"
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
-+++ b/target/riscv/th_csr.c
++++ b/target/riscv/vcrypto_helper.c
 @@ -XXX,XX +XXX,XX @@
 +/*
-+ * T-Head-specific CSRs.
++ * RISC-V Vector Crypto Extension Helpers for QEMU.
 + *
-+ * Copyright (c) 2024 VRULL GmbH
++ * Copyright (C) 2023 SiFive, Inc.
 + * Written by Codethink Ltd and SiFive.
 + *
 + * This program is free software; you can redistribute it and/or modify it
 + * under the terms and conditions of the GNU General Public License,
 + * version 2 or later, as published by the Free Software Foundation.
 + *
 ...
 + * You should have received a copy of the GNU General Public License along with
 + * this program.  If not, see <http://www.gnu.org/licenses/>.
 + */
 +
 +#include "qemu/osdep.h"
++#include "qemu/host-utils.h"
++#include "qemu/bitops.h"
 +#include "cpu.h"
-+#include "cpu_vendorid.h"
++#include "exec/memop.h"
-+
++#include "exec/exec-all.h"
-+#define CSR_TH_SXSTATUS 0x5c0
++#include "exec/helper-proto.h"
-+
++#include "internals.h"
-+/* TH_SXSTATUS bits */
++#include "vector_internals.h"
-+#define TH_SXSTATUS_UCME        BIT(16)
++
-+#define TH_SXSTATUS_MAEE        BIT(21)
++static uint64_t clmul64(uint64_t y, uint64_t x)
-+#define TH_SXSTATUS_THEADISAEE  BIT(22)
++{
-+
++    uint64_t result = 0;
-+typedef struct {
++    for (int j = 63; j >= 0; j--) {
-+    int csrno;
++        if ((y >> j) & 1) {
-+    int (*insertion_test)(RISCVCPU *cpu);
++            result ^= (x << j);
 +    riscv_csr_operations csr_ops;
 +} riscv_csr;
 +
 +static RISCVException smode(CPURISCVState *env, int csrno)
 +{
 +    if (riscv_has_ext(env, RVS)) {
 +        return RISCV_EXCP_NONE;
 +    }
 +
 +    return RISCV_EXCP_ILLEGAL_INST;
 +}
 +
 +static int test_thead_mvendorid(RISCVCPU *cpu)
 +{
 +    if (cpu->cfg.mvendorid != THEAD_VENDOR_ID) {
 +        return -1;
 +    }
 +
 +    return 0;
 +}
 +
 +static RISCVException read_th_sxstatus(CPURISCVState *env, int csrno,
 +                                       target_ulong *val)
 +{
 +    /* We don't set MAEE here, because QEMU does not implement MAEE. */
 +    *val = TH_SXSTATUS_UCME | TH_SXSTATUS_THEADISAEE;
 +    return RISCV_EXCP_NONE;
 +}
 +
 +static riscv_csr th_csr_list[] = {
 +    {
 +        .csrno = CSR_TH_SXSTATUS,
 +        .insertion_test = test_thead_mvendorid,
 +        .csr_ops = { "th.sxstatus", smode, read_th_sxstatus }
 +    }
 +};
 +
 +void th_register_custom_csrs(RISCVCPU *cpu)
 +{
 +    for (size_t i = 0; i < ARRAY_SIZE(th_csr_list); i++) {
 +        int csrno = th_csr_list[i].csrno;
 +        riscv_csr_operations *csr_ops = &th_csr_list[i].csr_ops;
 +        if (!th_csr_list[i].insertion_test(cpu)) {
 +            riscv_set_csr_ops(csrno, csr_ops);
 +        }
 +    }
-+}
++    return result;
 +}
 +
 +static uint64_t clmulh64(uint64_t y, uint64_t x)
 +{
 +    uint64_t result = 0;
 +    for (int j = 63; j >= 1; j--) {
 +        if ((y >> j) & 1) {
 +            result ^= (x >> (64 - j));
 +        }
 +    }
 +    return result;
 +}
 +
 +RVVCALL(OPIVV2, vclmul_vv, OP_UUU_D, H8, H8, H8, clmul64)
 +GEN_VEXT_VV(vclmul_vv, 8)
 +RVVCALL(OPIVX2, vclmul_vx, OP_UUU_D, H8, H8, clmul64)
 +GEN_VEXT_VX(vclmul_vx, 8)
 +RVVCALL(OPIVV2, vclmulh_vv, OP_UUU_D, H8, H8, H8, clmulh64)
 +GEN_VEXT_VV(vclmulh_vv, 8)
 +RVVCALL(OPIVX2, vclmulh_vx, OP_UUU_D, H8, H8, clmulh64)
 +GEN_VEXT_VX(vclmulh_vx, 8)
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
 +++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@
 +/*
 + * RISC-V translation routines for the vector crypto extension.
 + *
 + * Copyright (C) 2023 SiFive, Inc.
 + * Written by Codethink Ltd and SiFive.
 + *
 + * This program is free software; you can redistribute it and/or modify it
 + * under the terms and conditions of the GNU General Public License,
 + * version 2 or later, as published by the Free Software Foundation.
 + *
 + * This program is distributed in the hope it will be useful, but WITHOUT
 + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 + * more details.
 + *
 + * You should have received a copy of the GNU General Public License along with
 + * this program.  If not, see <http://www.gnu.org/licenses/>.
 + */
 +
 +/*
 + * Zvbc
 + */
 +
 +#define GEN_VV_MASKED_TRANS(NAME, CHECK)                     \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)   \
 +    {                                                        \
 +        if (CHECK(s, a)) {                                   \
 +            return opivv_trans(a->rd, a->rs1, a->rs2, a->vm, \
 +                               gen_helper_##NAME, s);        \
 +        }                                                    \
 +        return false;                                        \
 +    }
 +
 +static bool vclmul_vv_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return opivv_check(s, a) &&
 +           s->cfg_ptr->ext_zvbc == true &&
 +           s->sew == MO_64;
 +}
 +
 +GEN_VV_MASKED_TRANS(vclmul_vv, vclmul_vv_check)
 +GEN_VV_MASKED_TRANS(vclmulh_vv, vclmul_vv_check)
 +
 +#define GEN_VX_MASKED_TRANS(NAME, CHECK)                     \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)   \
 +    {                                                        \
 +        if (CHECK(s, a)) {                                   \
 +            return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, \
 +                               gen_helper_##NAME, s);        \
 +        }                                                    \
 +        return false;                                        \
 +    }
 +
 +static bool vclmul_vx_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return opivx_check(s, a) &&
 +           s->cfg_ptr->ext_zvbc == true &&
 +           s->sew == MO_64;
 +}
 +
 +GEN_VX_MASKED_TRANS(vclmul_vx, vclmul_vx_check)
 +GEN_VX_MASKED_TRANS(vclmulh_vx, vclmul_vx_check)
 diff --git a/target/riscv/meson.build b/target/riscv/meson.build
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/meson.build
 +++ b/target/riscv/meson.build
-@@ -XXX,XX +XXX,XX @@ riscv_system_ss.add(files(
+@@ -XXX,XX +XXX,XX @@ riscv_ss.add(files(
-   'monitor.c',
+   'translate.c',
-   'machine.c',
+   'm128_helper.c',
-   'pmu.c',
+   'crypto_helper.c',
-+  'th_csr.c',
+-  'zce_helper.c'
-   'time_helper.c',
++  'zce_helper.c',
-   'riscv-qmp-cmds.c',
++  'vcrypto_helper.c'
  ))
+ riscv_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c'), if_false: files('kvm-stub.c'))
 --
-.45.1
+.41.0

-[PULL 17/28] target/riscv: rvv: Fix Zvfhmin checking for vfwcvt.f.f.v and vfncvt.f.f.w instructions
+[PULL v2 12/45] target/riscv: Move vector translation checks
-From: Max Chou <max.chou@sifive.com>
+From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-According v spec 18.4, only the vfwcvt.f.f.v and vfncvt.f.f.w
+Move the checks out of `do_opiv{v,x,i}_gvec{,_shift}` functions
-instructions will be affected by Zvfhmin extension.
+and into the corresponding macros. This enables the functions to be
-And the vfwcvt.f.f.v and vfncvt.f.f.w instructions only support the
+reused in proceeding commits without check duplication.
 conversions of
-* From 1*SEW(16/32) to 2*SEW(32/64)
+Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-* From 2*SEW(32/64) to 1*SEW(16/32)
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
 Signed-off-by: Max Chou <max.chou@sifive.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-ID: <20230711165917.2629866-6-max.chou@sifive.com>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240322092600.1198921-2-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_rvv.c.inc | 20 ++++++++++++++++++--
+ target/riscv/insn_trans/trans_rvv.c.inc | 28 +++++++++++--------------
-file changed, 18 insertions(+), 2 deletions(-)
+file changed, 12 insertions(+), 16 deletions(-)
 diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvv.c.inc
 +++ b/target/riscv/insn_trans/trans_rvv.c.inc
-@@ -XXX,XX +XXX,XX @@ static bool require_rvf(DisasContext *s)
+@@ -XXX,XX +XXX,XX @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
-     }
+               gen_helper_gvec_4_ptr *fn)
  {
      TCGLabel *over = gen_new_label();
 -    if (!opivv_check(s, a)) {
 -        return false;
 -    }
      tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
          gen_helper_##NAME##_b, gen_helper_##NAME##_h,              \
          gen_helper_##NAME##_w, gen_helper_##NAME##_d,              \
      };                                                             \
 +    if (!opivv_check(s, a)) {                                      \
 +        return false;                                              \
 +    }                                                              \
      return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]);   \
  }
-+static bool require_rvfmin(DisasContext *s)
+@@ -XXX,XX +XXX,XX @@ static inline bool
-+{
+ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
-+    if (s->mstatus_fs == EXT_STATUS_DISABLED) {
+               gen_helper_opivx *fn)
 +        return false;
 +    }
 +
 +    switch (s->sew) {
 +    case MO_16:
 +        return s->cfg_ptr->ext_zvfhmin;
 +    case MO_32:
 +        return s->cfg_ptr->ext_zve32f;
 +    default:
 +        return false;
 +    }
 +}
 +
  static bool require_scale_rvf(DisasContext *s)
  {
-     if (s->mstatus_fs == EXT_STATUS_DISABLED) {
+-    if (!opivx_check(s, a)) {
-@@ -XXX,XX +XXX,XX @@ static bool require_scale_rvfmin(DisasContext *s)
+-        return false;
-     }
+-    }
+-
-     switch (s->sew) {
+     if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
--    case MO_8:
+         TCGv_i64 src1 = tcg_temp_new_i64();
--        return s->cfg_ptr->ext_zvfhmin;
-     case MO_16:
+@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
-         return s->cfg_ptr->ext_zve32f;
+         gen_helper_##NAME##_b, gen_helper_##NAME##_h,              \
-     case MO_32:
+         gen_helper_##NAME##_w, gen_helper_##NAME##_d,              \
-@@ -XXX,XX +XXX,XX @@ static bool opxfv_widen_check(DisasContext *s, arg_rmr *a)
+     };                                                             \
- static bool opffv_widen_check(DisasContext *s, arg_rmr *a)
++    if (!opivx_check(s, a)) {                                      \
 +        return false;                                              \
 +    }                                                              \
      return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]);   \
  }
@@ -XXX,XX +XXX,XX @@ static inline bool
  do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
                gen_helper_opivx *fn, imm_mode_t imm_mode)
  {
-     return opfv_widen_check(s, a) &&
+-    if (!opivx_check(s, a)) {
-+           require_rvfmin(s) &&
+-        return false;
-            require_scale_rvfmin(s) &&
+-    }
-            (s->sew != MO_8);
+-
      if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
          gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
                  extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
          gen_helper_##OPIVX##_b, gen_helper_##OPIVX##_h,            \
          gen_helper_##OPIVX##_w, gen_helper_##OPIVX##_d,            \
      };                                                             \
 +    if (!opivx_check(s, a)) {                                      \
 +        return false;                                              \
 +    }                                                              \
      return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF,                 \
                           fns[s->sew], IMM_MODE);                   \
  }
-@@ -XXX,XX +XXX,XX @@ static bool opfxv_narrow_check(DisasContext *s, arg_rmr *a)
+@@ -XXX,XX +XXX,XX @@ static inline bool
- static bool opffv_narrow_check(DisasContext *s, arg_rmr *a)
+ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
                      gen_helper_opivx *fn)
  {
-     return opfv_narrow_check(s, a) &&
+-    if (!opivx_check(s, a)) {
-+           require_rvfmin(s) &&
+-        return false;
-            require_scale_rvfmin(s) &&
+-    }
-            (s->sew != MO_8);
+-
      if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
          TCGv_i32 src1 = tcg_temp_new_i32();
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                    \
          gen_helper_##NAME##_b, gen_helper_##NAME##_h,                     \
          gen_helper_##NAME##_w, gen_helper_##NAME##_d,                     \
      };                                                                    \
 -                                                                          \
 +    if (!opivx_check(s, a)) {                                             \
 +        return false;                                                     \
 +    }                                                                     \
      return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, fns[s->sew]);    \
  }
 --
-.45.1
+.41.0

-[PULL 20/28] target/riscv: rvv: Remove redudant SEW checking for vector fp narrow/widen instructions
+[PULL v2 13/45] target/riscv: Refactor translation of vector-widening instruction
-From: Max Chou <max.chou@sifive.com>
+From: Dickon Hood <dickon.hood@codethink.co.uk>
-If the checking functions check both the single and double width
+Zvbb (implemented in later commit) has a widening instruction, which
-operators at the same time, then the single width operator checking
+requires an extra check on the enabled extensions.  Refactor
-functions (require_rvf[min]) will check whether the SEW is 8.
+GEN_OPIVX_WIDEN_TRANS() to take a check function to avoid reimplementing
 it.
+Signed-off-by: Dickon Hood <dickon.hood@codethink.co.uk>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
 Signed-off-by: Max Chou <max.chou@sifive.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-ID: <20230711165917.2629866-7-max.chou@sifive.com>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240322092600.1198921-5-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_rvv.c.inc | 16 ++++------------
+ target/riscv/insn_trans/trans_rvv.c.inc | 52 +++++++++++--------------
-file changed, 4 insertions(+), 12 deletions(-)
+file changed, 23 insertions(+), 29 deletions(-)
 diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvv.c.inc
 +++ b/target/riscv/insn_trans/trans_rvv.c.inc
-@@ -XXX,XX +XXX,XX @@ static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a)
+@@ -XXX,XX +XXX,XX @@ static bool opivx_widen_check(DisasContext *s, arg_rmrr *a)
      return require_rvv(s) &&
             require_rvf(s) &&
             require_scale_rvf(s) &&
 -           (s->sew != MO_8) &&
             vext_check_isa_ill(s) &&
             vext_check_dss(s, a->rd, a->rs1, a->rs2, a->vm);
  }
@@ -XXX,XX +XXX,XX @@ static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a)
      return require_rvv(s) &&
             require_rvf(s) &&
             require_scale_rvf(s) &&
 -           (s->sew != MO_8) &&
             vext_check_isa_ill(s) &&
             vext_check_ds(s, a->rd, a->rs2, a->vm);
  }
-@@ -XXX,XX +XXX,XX @@ static bool opfwv_widen_check(DisasContext *s, arg_rmrr *a)
-     return require_rvv(s) &&
+-static bool do_opivx_widen(DisasContext *s, arg_rmrr *a,
-            require_rvf(s) &&
+-                           gen_helper_opivx *fn)
-            require_scale_rvf(s) &&
+-{
--           (s->sew != MO_8) &&
+-    if (opivx_widen_check(s, a)) {
-            vext_check_isa_ill(s) &&
+-        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
-            vext_check_dds(s, a->rd, a->rs1, a->rs2, a->vm);
+-    }
 -    return false;
 -}
 -
 -#define GEN_OPIVX_WIDEN_TRANS(NAME) \
 -static bool trans_##NAME(DisasContext *s, arg_rmrr *a)       \
 -{                                                            \
 -    static gen_helper_opivx * const fns[3] = {               \
 -        gen_helper_##NAME##_b,                               \
 -        gen_helper_##NAME##_h,                               \
 -        gen_helper_##NAME##_w                                \
 -    };                                                       \
 -    return do_opivx_widen(s, a, fns[s->sew]);                \
 +#define GEN_OPIVX_WIDEN_TRANS(NAME, CHECK) \
 +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                    \
 +{                                                                         \
 +    if (CHECK(s, a)) {                                                    \
 +        static gen_helper_opivx * const fns[3] = {                        \
 +            gen_helper_##NAME##_b,                                        \
 +            gen_helper_##NAME##_h,                                        \
 +            gen_helper_##NAME##_w                                         \
 +        };                                                                \
 +        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s); \
 +    }                                                                     \
 +    return false;                                                         \
  }
-@@ -XXX,XX +XXX,XX @@ static bool opfwf_widen_check(DisasContext *s, arg_rmrr *a)
-     return require_rvv(s) &&
+-GEN_OPIVX_WIDEN_TRANS(vwaddu_vx)
-            require_rvf(s) &&
+-GEN_OPIVX_WIDEN_TRANS(vwadd_vx)
-            require_scale_rvf(s) &&
+-GEN_OPIVX_WIDEN_TRANS(vwsubu_vx)
--           (s->sew != MO_8) &&
+-GEN_OPIVX_WIDEN_TRANS(vwsub_vx)
-            vext_check_isa_ill(s) &&
++GEN_OPIVX_WIDEN_TRANS(vwaddu_vx, opivx_widen_check)
-            vext_check_dd(s, a->rd, a->rs2, a->vm);
++GEN_OPIVX_WIDEN_TRANS(vwadd_vx, opivx_widen_check)
- }
++GEN_OPIVX_WIDEN_TRANS(vwsubu_vx, opivx_widen_check)
-@@ -XXX,XX +XXX,XX @@ static bool opffv_widen_check(DisasContext *s, arg_rmr *a)
++GEN_OPIVX_WIDEN_TRANS(vwsub_vx, opivx_widen_check)
- {
-     return opfv_widen_check(s, a) &&
+ /* WIDEN OPIVV with WIDEN */
-            require_rvfmin(s) &&
+ static bool opiwv_widen_check(DisasContext *s, arg_rmrr *a)
--           require_scale_rvfmin(s) &&
+@@ -XXX,XX +XXX,XX @@ GEN_OPIVX_TRANS(vrem_vx, opivx_check)
--           (s->sew != MO_8);
+ GEN_OPIVV_WIDEN_TRANS(vwmul_vv, opivv_widen_check)
-+           require_scale_rvfmin(s);
+ GEN_OPIVV_WIDEN_TRANS(vwmulu_vv, opivv_widen_check)
- }
+ GEN_OPIVV_WIDEN_TRANS(vwmulsu_vv, opivv_widen_check)
+-GEN_OPIVX_WIDEN_TRANS(vwmul_vx)
- #define GEN_OPFV_WIDEN_TRANS(NAME, CHECK, HELPER, FRM)             \
+-GEN_OPIVX_WIDEN_TRANS(vwmulu_vx)
-@@ -XXX,XX +XXX,XX @@ static bool opffv_narrow_check(DisasContext *s, arg_rmr *a)
+-GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx)
- {
++GEN_OPIVX_WIDEN_TRANS(vwmul_vx, opivx_widen_check)
-     return opfv_narrow_check(s, a) &&
++GEN_OPIVX_WIDEN_TRANS(vwmulu_vx, opivx_widen_check)
-            require_rvfmin(s) &&
++GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx, opivx_widen_check)
--           require_scale_rvfmin(s) &&
--           (s->sew != MO_8);
+ /* Vector Single-Width Integer Multiply-Add Instructions */
-+           require_scale_rvfmin(s);
+ GEN_OPIVV_TRANS(vmacc_vv, opivv_check)
- }
+@@ -XXX,XX +XXX,XX @@ GEN_OPIVX_TRANS(vnmsub_vx, opivx_check)
+ GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_widen_check)
- static bool opffv_rod_narrow_check(DisasContext *s, arg_rmr *a)
+ GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_widen_check)
- {
+ GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_widen_check)
-     return opfv_narrow_check(s, a) &&
+-GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx)
-            require_rvf(s) &&
+-GEN_OPIVX_WIDEN_TRANS(vwmacc_vx)
--           require_scale_rvf(s) &&
+-GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx)
--           (s->sew != MO_8);
+-GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx)
-+           require_scale_rvf(s);
++GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx, opivx_widen_check)
- }
++GEN_OPIVX_WIDEN_TRANS(vwmacc_vx, opivx_widen_check)
++GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx, opivx_widen_check)
- #define GEN_OPFV_NARROW_TRANS(NAME, CHECK, HELPER, FRM)            \
++GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx, opivx_widen_check)
-@@ -XXX,XX +XXX,XX @@ static bool freduction_widen_check(DisasContext *s, arg_rmrr *a)
- {
+ /* Vector Integer Merge and Move Instructions */
-     return reduction_widen_check(s, a) &&
+ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
             require_rvf(s) &&
 -           require_scale_rvf(s) &&
 -           (s->sew != MO_8);
 +           require_scale_rvf(s);
  }
  GEN_OPFVV_WIDEN_TRANS(vfwredusum_vs, freduction_widen_check)
 --
-.45.1
+.41.0

-New patch
+[PULL v2 14/45] target/riscv: Refactor some of the generic vector functionality
+From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
+Move some macros out of `vector_helper` and into `vector_internals`.
+This ensures they can be used by both vector and vector-crypto helpers
+(latter implemented in proceeding commits).
+Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
+Signed-off-by: Max Chou <max.chou@sifive.com>
+Message-ID: <20230711165917.2629866-8-max.chou@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/vector_internals.h | 46 +++++++++++++++++++++++++++++++++
+ target/riscv/vector_helper.c    | 42 ------------------------------
+files changed, 46 insertions(+), 42 deletions(-)
+diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/vector_internals.h
++++ b/target/riscv/vector_internals.h
+@@ -XXX,XX +XXX,XX @@ void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+ /* expand macro args before macro */
+ #define RVVCALL(macro, ...)  macro(__VA_ARGS__)
++/* (TD, T2, TX2) */
++#define OP_UU_B uint8_t, uint8_t, uint8_t
++#define OP_UU_H uint16_t, uint16_t, uint16_t
++#define OP_UU_W uint32_t, uint32_t, uint32_t
++#define OP_UU_D uint64_t, uint64_t, uint64_t
++
+ /* (TD, T1, T2, TX1, TX2) */
+ #define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+ #define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+ #define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+ #define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
++#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
++static void do_##NAME(void *vd, void *vs2, int i)      \
++{                                                      \
++    TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
++    *((TD *)vd + HD(i)) = OP(s2);                      \
++}
++
++#define GEN_VEXT_V(NAME, ESZ)                          \
++void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
++                  CPURISCVState *env, uint32_t desc)   \
++{                                                      \
++    uint32_t vm = vext_vm(desc);                       \
++    uint32_t vl = env->vl;                             \
++    uint32_t total_elems =                             \
++        vext_get_total_elems(env, desc, ESZ);          \
++    uint32_t vta = vext_vta(desc);                     \
++    uint32_t vma = vext_vma(desc);                     \
++    uint32_t i;                                        \
++                                                       \
++    for (i = env->vstart; i < vl; i++) {               \
++        if (!vm && !vext_elem_mask(v0, i)) {           \
++            /* set masked-off elements to 1s */        \
++            vext_set_elems_1s(vd, vma, i * ESZ,        \
++                              (i + 1) * ESZ);          \
++            continue;                                  \
++        }                                              \
++        do_##NAME(vd, vs2, i);                         \
++    }                                                  \
++    env->vstart = 0;                                   \
++    /* set tail elements to 1s */                      \
++    vext_set_elems_1s(vd, vta, vl * ESZ,               \
++                      total_elems * ESZ);              \
++}
++
+ /* operation of two vector elements */
+ typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
+@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
+                do_##NAME, ESZ);                           \
+ }
++/* Three of the widening shortening macros: */
++/* (TD, T1, T2, TX1, TX2) */
++#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
++#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
++#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
++
+ #endif /* TARGET_RISCV_VECTOR_INTERNALS_H */
+diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/vector_helper.c
++++ b/target/riscv/vector_helper.c
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
+ #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
+ #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
+ #define OP_SUS_D int64_t, uint64_t, int64_t, uint64_t, int64_t
+-#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
+-#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
+-#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
+ #define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t
+ #define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t
+ #define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_VF(vfwnmsac_vf_h, 4)
+ GEN_VEXT_VF(vfwnmsac_vf_w, 8)
+ /* Vector Floating-Point Square-Root Instruction */
+-/* (TD, T2, TX2) */
+-#define OP_UU_H uint16_t, uint16_t, uint16_t
+-#define OP_UU_W uint32_t, uint32_t, uint32_t
+-#define OP_UU_D uint64_t, uint64_t, uint64_t
+-
+ #define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
+ static void do_##NAME(void *vd, void *vs2, int i,      \
+                       CPURISCVState *env)              \
+@@ -XXX,XX +XXX,XX @@ GEN_VEXT_CMP_VF(vmfge_vf_w, uint32_t, H4, vmfge32)
+ GEN_VEXT_CMP_VF(vmfge_vf_d, uint64_t, H8, vmfge64)
+ /* Vector Floating-Point Classify Instruction */
+-#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
+-static void do_##NAME(void *vd, void *vs2, int i)      \
+-{                                                      \
+-    TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
+-    *((TD *)vd + HD(i)) = OP(s2);                      \
+-}
+-
+-#define GEN_VEXT_V(NAME, ESZ)                          \
+-void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
+-                  CPURISCVState *env, uint32_t desc)   \
+-{                                                      \
+-    uint32_t vm = vext_vm(desc);                       \
+-    uint32_t vl = env->vl;                             \
+-    uint32_t total_elems =                             \
+-        vext_get_total_elems(env, desc, ESZ);          \
+-    uint32_t vta = vext_vta(desc);                     \
+-    uint32_t vma = vext_vma(desc);                     \
+-    uint32_t i;                                        \
+-                                                       \
+-    for (i = env->vstart; i < vl; i++) {               \
+-        if (!vm && !vext_elem_mask(v0, i)) {           \
+-            /* set masked-off elements to 1s */        \
+-            vext_set_elems_1s(vd, vma, i * ESZ,        \
+-                              (i + 1) * ESZ);          \
+-            continue;                                  \
+-        }                                              \
+-        do_##NAME(vd, vs2, i);                         \
+-    }                                                  \
+-    env->vstart = 0;                                   \
+-    /* set tail elements to 1s */                      \
+-    vext_set_elems_1s(vd, vta, vl * ESZ,               \
+-                      total_elems * ESZ);              \
+-}
+-
+ target_ulong fclass_h(uint64_t frs1)
+ {
+     float16 f = frs1;
+--
+.41.0

-[PULL 10/28] target/riscv: Add support for Zve32x extension
+[PULL v2 15/45] target/riscv: Add Zvbb ISA extension support
-From: Jason Chien <jason.chien@sifive.com>
+From: Dickon Hood <dickon.hood@codethink.co.uk>
-Add support for Zve32x extension and replace some checks for Zve32f with
+This commit adds support for the Zvbb vector-crypto extension, which
-Zve32x, since Zve32f depends on Zve32x.
+consists of the following instructions:
-Signed-off-by: Jason Chien <jason.chien@sifive.com>
+* vrol.[vv,vx]
-Reviewed-by: Frank Chang <frank.chang@sifive.com>
+* vror.[vv,vx,vi]
-Reviewed-by: Max Chou <max.chou@sifive.com>
+* vbrev8.v
 * vrev8.v
 * vandn.[vv,vx]
 * vbrev.v
 * vclz.v
 * vctz.v
 * vcpop.v
 * vwsll.[vv,vx,vi]
 Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Co-authored-by: William Salmon <will.salmon@codethink.co.uk>
 Co-authored-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
 [max.chou@sifive.com: Fix imm mode of vror.vi]
 Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Signed-off-by: William Salmon <will.salmon@codethink.co.uk>
 Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
 Signed-off-by: Dickon Hood <dickon.hood@codethink.co.uk>
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Message-ID: <20240328022343.6871-2-jason.chien@sifive.com>
+[max.chou@sifive.com: Exposed x-zvbb property]
 Message-ID: <20230711165917.2629866-9-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_cfg.h                  |  1 +
+ target/riscv/cpu_cfg.h                   |   1 +
- target/riscv/cpu.c                      |  2 ++
+ target/riscv/helper.h                    |  62 +++++++++
- target/riscv/cpu_helper.c               |  2 +-
+ target/riscv/insn32.decode               |  20 +++
- target/riscv/csr.c                      |  2 +-
+ target/riscv/cpu.c                       |  12 ++
- target/riscv/tcg/tcg-cpu.c              | 16 ++++++++--------
+ target/riscv/vcrypto_helper.c            | 138 +++++++++++++++++++
- target/riscv/insn_trans/trans_rvv.c.inc |  4 ++--
+ target/riscv/insn_trans/trans_rvvk.c.inc | 164 +++++++++++++++++++++++
-files changed, 15 insertions(+), 12 deletions(-)
+files changed, 397 insertions(+)
 diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_cfg.h
 +++ b/target/riscv/cpu_cfg.h
 @@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
-     bool ext_zhinx;
-     bool ext_zhinxmin;
      bool ext_zve32f;
-+    bool ext_zve32x;
      bool ext_zve64f;
      bool ext_zve64d;
-     bool ext_zvbb;
++    bool ext_zvbb;
      bool ext_zvbc;
      bool ext_zmmul;
      bool ext_zvfbfmin;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(vclmul_vv, void, ptr, ptr, ptr, ptr, env, i32)
  DEF_HELPER_6(vclmul_vx, void, ptr, ptr, tl, ptr, env, i32)
  DEF_HELPER_6(vclmulh_vv, void, ptr, ptr, ptr, ptr, env, i32)
  DEF_HELPER_6(vclmulh_vx, void, ptr, ptr, tl, ptr, env, i32)
 +
 +DEF_HELPER_6(vror_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vror_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vror_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vror_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
 +
 +DEF_HELPER_6(vror_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vror_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vror_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vror_vx_d, void, ptr, ptr, tl, ptr, env, i32)
 +
 +DEF_HELPER_6(vrol_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vrol_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vrol_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vrol_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
 +
 +DEF_HELPER_6(vrol_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vrol_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vrol_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vrol_vx_d, void, ptr, ptr, tl, ptr, env, i32)
 +
 +DEF_HELPER_5(vrev8_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vrev8_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vrev8_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vrev8_v_d, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev8_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev8_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev8_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev8_v_d, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vbrev_v_d, void, ptr, ptr, ptr, env, i32)
 +
 +DEF_HELPER_5(vclz_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vclz_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vclz_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vclz_v_d, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vctz_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vctz_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vctz_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vctz_v_d, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vcpop_v_b, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vcpop_v_h, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vcpop_v_w, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vcpop_v_d, void, ptr, ptr, ptr, env, i32)
 +
 +DEF_HELPER_6(vwsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vwsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vwsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vwsll_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vwsll_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vwsll_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 +
 +DEF_HELPER_6(vandn_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vandn_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vandn_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vandn_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 +DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@
  %imm_u    12:s20                 !function=ex_shift_12
  %imm_bs   30:2                   !function=ex_shift_3
  %imm_rnum 20:4
 +%imm_z6   26:1 15:5
  # Argument sets:
  &empty
@@ -XXX,XX +XXX,XX @@
  @r_vm    ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd
  @r_vm_1  ...... . ..... ..... ... ..... .......    &rmrr vm=1 %rs2 %rs1 %rd
  @r_vm_0  ...... . ..... ..... ... ..... .......    &rmrr vm=0 %rs2 %rs1 %rd
 +@r2_zimm6  ..... . vm:1 ..... ..... ... ..... .......  &rmrr %rs2 rs1=%imm_z6 %rd
  @r2_zimm11 . zimm:11  ..... ... ..... ....... %rs1 %rd
  @r2_zimm10 .. zimm:10  ..... ... ..... ....... %rs1 %rd
  @r2_s    .......   ..... ..... ... ..... ....... %rs2 %rs1
@@ -XXX,XX +XXX,XX @@ vclmul_vv   001100 . ..... ..... 010 ..... 1010111 @r_vm
  vclmul_vx   001100 . ..... ..... 110 ..... 1010111 @r_vm
  vclmulh_vv  001101 . ..... ..... 010 ..... 1010111 @r_vm
  vclmulh_vx  001101 . ..... ..... 110 ..... 1010111 @r_vm
 +
 +# *** Zvbb vector crypto extension ***
 +vrol_vv     010101 . ..... ..... 000 ..... 1010111 @r_vm
 +vrol_vx     010101 . ..... ..... 100 ..... 1010111 @r_vm
 +vror_vv     010100 . ..... ..... 000 ..... 1010111 @r_vm
 +vror_vx     010100 . ..... ..... 100 ..... 1010111 @r_vm
 +vror_vi     01010. . ..... ..... 011 ..... 1010111 @r2_zimm6
 +vbrev8_v    010010 . ..... 01000 010 ..... 1010111 @r2_vm
 +vrev8_v     010010 . ..... 01001 010 ..... 1010111 @r2_vm
 +vandn_vv    000001 . ..... ..... 000 ..... 1010111 @r_vm
 +vandn_vx    000001 . ..... ..... 100 ..... 1010111 @r_vm
 +vbrev_v     010010 . ..... 01010 010 ..... 1010111 @r2_vm
 +vclz_v      010010 . ..... 01100 010 ..... 1010111 @r2_vm
 +vctz_v      010010 . ..... 01101 010 ..... 1010111 @r2_vm
 +vcpop_v     010010 . ..... 01110 010 ..... 1010111 @r2_vm
 +vwsll_vv    110101 . ..... ..... 000 ..... 1010111 @r_vm
 +vwsll_vx    110101 . ..... ..... 100 ..... 1010111 @r_vm
 +vwsll_vi    110101 . ..... ..... 011 ..... 1010111 @r_vm
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ const RISCVIsaExtData isa_edata_arr[] = {
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
-     ISA_EXT_DATA_ENTRY(zvbb, PRIV_VERSION_1_12_0, ext_zvbb),
+     ISA_EXT_DATA_ENTRY(zksed, PRIV_VERSION_1_12_0, ext_zksed),
      ISA_EXT_DATA_ENTRY(zksh, PRIV_VERSION_1_12_0, ext_zksh),
      ISA_EXT_DATA_ENTRY(zkt, PRIV_VERSION_1_12_0, ext_zkt),
 +    ISA_EXT_DATA_ENTRY(zvbb, PRIV_VERSION_1_12_0, ext_zvbb),
      ISA_EXT_DATA_ENTRY(zvbc, PRIV_VERSION_1_12_0, ext_zvbc),
      ISA_EXT_DATA_ENTRY(zve32f, PRIV_VERSION_1_10_0, ext_zve32f),
-+    ISA_EXT_DATA_ENTRY(zve32x, PRIV_VERSION_1_10_0, ext_zve32x),
      ISA_EXT_DATA_ENTRY(zve64f, PRIV_VERSION_1_10_0, ext_zve64f),
-     ISA_EXT_DATA_ENTRY(zve64d, PRIV_VERSION_1_10_0, ext_zve64d),
-     ISA_EXT_DATA_ENTRY(zvfbfmin, PRIV_VERSION_1_12_0, ext_zvfbfmin),
-@@ -XXX,XX +XXX,XX @@ const RISCVCPUMultiExtConfig riscv_cpu_extensions[] = {
-     MULTI_EXT_CFG_BOOL("zfh", ext_zfh, false),
-     MULTI_EXT_CFG_BOOL("zfhmin", ext_zfhmin, false),
-     MULTI_EXT_CFG_BOOL("zve32f", ext_zve32f, false),
-+    MULTI_EXT_CFG_BOOL("zve32x", ext_zve32x, false),
-     MULTI_EXT_CFG_BOOL("zve64f", ext_zve64f, false),
-     MULTI_EXT_CFG_BOOL("zve64d", ext_zve64d, false),
-     MULTI_EXT_CFG_BOOL("zvfbfmin", ext_zvfbfmin, false),
-diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
-index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu_helper.c
-+++ b/target/riscv/cpu_helper.c
-@@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPURISCVState *env, vaddr *pc,
-     *pc = env->xl == MXL_RV32 ? env->pc & UINT32_MAX : env->pc;
-     *cs_base = 0;
--    if (cpu->cfg.ext_zve32f) {
-+    if (cpu->cfg.ext_zve32x) {
-         /*
-          * If env->vl equals to VLMAX, we can use generic vector operation
-          * expanders (GVEC) to accerlate the vector operations.
-diff --git a/target/riscv/csr.c b/target/riscv/csr.c
-index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/csr.c
-+++ b/target/riscv/csr.c
-@@ -XXX,XX +XXX,XX @@ static RISCVException fs(CPURISCVState *env, int csrno)
- static RISCVException vs(CPURISCVState *env, int csrno)
- {
--    if (riscv_cpu_cfg(env)->ext_zve32f) {
-+    if (riscv_cpu_cfg(env)->ext_zve32x) {
- #if !defined(CONFIG_USER_ONLY)
-         if (!env->debugger && !riscv_cpu_vector_enabled(env)) {
-             return RISCV_EXCP_ILLEGAL_INST;
-diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
-index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/tcg/tcg-cpu.c
-+++ b/target/riscv/tcg/tcg-cpu.c
 @@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
          return;
      }
--    if (cpu->cfg.ext_zve32f && !riscv_has_ext(env, RVF)) {
++    /*
--        error_setg(errp, "Zve32f/Zve64f extensions require F extension");
++     * In principle Zve*x would also suffice here, were they supported
--        return;
++     * in qemu
-+    /* The Zve32f extension depends on the Zve32x extension */
++     */
-+    if (cpu->cfg.ext_zve32f) {
++    if (cpu->cfg.ext_zvbb && !cpu->cfg.ext_zve32f) {
-+        if (!riscv_has_ext(env, RVF)) {
++        error_setg(errp,
-+            error_setg(errp, "Zve32f/Zve64f extensions require F extension");
++                   "Vector crypto extensions require V or Zve* extensions");
-+            return;
++        return;
-+        }
++    }
-+        cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zve32x), true);
++
-     }
+     if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) {
+         error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions");
      if (cpu->cfg.ext_zvfh) {
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
          cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zvbc), true);
      }
 -    /*
 -     * In principle Zve*x would also suffice here, were they supported
 -     * in qemu
 -     */
      if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkb || cpu->cfg.ext_zvkg ||
           cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksed ||
 -         cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
 +         cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32x) {
          error_setg(errp,
                     "Vector crypto extensions require V or Zve* extensions");
          return;
-diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
+@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      DEFINE_PROP_BOOL("x-zvfbfwma", RISCVCPU, cfg.ext_zvfbfwma, false),
      /* Vector cryptography extensions */
 +    DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
      DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
      DEFINE_PROP_END_OF_LIST(),
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/insn_trans/trans_rvv.c.inc
+--- a/target/riscv/vcrypto_helper.c
-+++ b/target/riscv/insn_trans/trans_rvv.c.inc
++++ b/target/riscv/vcrypto_helper.c
-@@ -XXX,XX +XXX,XX @@ static bool do_vsetvl(DisasContext *s, int rd, int rs1, TCGv s2)
+@@ -XXX,XX +XXX,XX @@
- {
+ #include "qemu/osdep.h"
-     TCGv s1, dst;
+ #include "qemu/host-utils.h"
+ #include "qemu/bitops.h"
--    if (!require_rvv(s) || !s->cfg_ptr->ext_zve32f) {
++#include "qemu/bswap.h"
-+    if (!require_rvv(s) || !s->cfg_ptr->ext_zve32x) {
+ #include "cpu.h"
-         return false;
+ #include "exec/memop.h"
-     }
+ #include "exec/exec-all.h"
+@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVV2, vclmulh_vv, OP_UUU_D, H8, H8, H8, clmulh64)
-@@ -XXX,XX +XXX,XX @@ static bool do_vsetivli(DisasContext *s, int rd, TCGv s1, TCGv s2)
+ GEN_VEXT_VV(vclmulh_vv, 8)
- {
+ RVVCALL(OPIVX2, vclmulh_vx, OP_UUU_D, H8, H8, clmulh64)
-     TCGv dst;
+ GEN_VEXT_VX(vclmulh_vx, 8)
++
--    if (!require_rvv(s) || !s->cfg_ptr->ext_zve32f) {
++RVVCALL(OPIVV2, vror_vv_b, OP_UUU_B, H1, H1, H1, ror8)
-+    if (!require_rvv(s) || !s->cfg_ptr->ext_zve32x) {
++RVVCALL(OPIVV2, vror_vv_h, OP_UUU_H, H2, H2, H2, ror16)
-         return false;
++RVVCALL(OPIVV2, vror_vv_w, OP_UUU_W, H4, H4, H4, ror32)
-     }
++RVVCALL(OPIVV2, vror_vv_d, OP_UUU_D, H8, H8, H8, ror64)
++GEN_VEXT_VV(vror_vv_b, 1)
 +GEN_VEXT_VV(vror_vv_h, 2)
 +GEN_VEXT_VV(vror_vv_w, 4)
 +GEN_VEXT_VV(vror_vv_d, 8)
 +
 +RVVCALL(OPIVX2, vror_vx_b, OP_UUU_B, H1, H1, ror8)
 +RVVCALL(OPIVX2, vror_vx_h, OP_UUU_H, H2, H2, ror16)
 +RVVCALL(OPIVX2, vror_vx_w, OP_UUU_W, H4, H4, ror32)
 +RVVCALL(OPIVX2, vror_vx_d, OP_UUU_D, H8, H8, ror64)
 +GEN_VEXT_VX(vror_vx_b, 1)
 +GEN_VEXT_VX(vror_vx_h, 2)
 +GEN_VEXT_VX(vror_vx_w, 4)
 +GEN_VEXT_VX(vror_vx_d, 8)
 +
 +RVVCALL(OPIVV2, vrol_vv_b, OP_UUU_B, H1, H1, H1, rol8)
 +RVVCALL(OPIVV2, vrol_vv_h, OP_UUU_H, H2, H2, H2, rol16)
 +RVVCALL(OPIVV2, vrol_vv_w, OP_UUU_W, H4, H4, H4, rol32)
 +RVVCALL(OPIVV2, vrol_vv_d, OP_UUU_D, H8, H8, H8, rol64)
 +GEN_VEXT_VV(vrol_vv_b, 1)
 +GEN_VEXT_VV(vrol_vv_h, 2)
 +GEN_VEXT_VV(vrol_vv_w, 4)
 +GEN_VEXT_VV(vrol_vv_d, 8)
 +
 +RVVCALL(OPIVX2, vrol_vx_b, OP_UUU_B, H1, H1, rol8)
 +RVVCALL(OPIVX2, vrol_vx_h, OP_UUU_H, H2, H2, rol16)
 +RVVCALL(OPIVX2, vrol_vx_w, OP_UUU_W, H4, H4, rol32)
 +RVVCALL(OPIVX2, vrol_vx_d, OP_UUU_D, H8, H8, rol64)
 +GEN_VEXT_VX(vrol_vx_b, 1)
 +GEN_VEXT_VX(vrol_vx_h, 2)
 +GEN_VEXT_VX(vrol_vx_w, 4)
 +GEN_VEXT_VX(vrol_vx_d, 8)
 +
 +static uint64_t brev8(uint64_t val)
 +{
 +    val = ((val & 0x5555555555555555ull) << 1) |
 +          ((val & 0xAAAAAAAAAAAAAAAAull) >> 1);
 +    val = ((val & 0x3333333333333333ull) << 2) |
 +          ((val & 0xCCCCCCCCCCCCCCCCull) >> 2);
 +    val = ((val & 0x0F0F0F0F0F0F0F0Full) << 4) |
 +          ((val & 0xF0F0F0F0F0F0F0F0ull) >> 4);
 +
 +    return val;
 +}
 +
 +RVVCALL(OPIVV1, vbrev8_v_b, OP_UU_B, H1, H1, brev8)
 +RVVCALL(OPIVV1, vbrev8_v_h, OP_UU_H, H2, H2, brev8)
 +RVVCALL(OPIVV1, vbrev8_v_w, OP_UU_W, H4, H4, brev8)
 +RVVCALL(OPIVV1, vbrev8_v_d, OP_UU_D, H8, H8, brev8)
 +GEN_VEXT_V(vbrev8_v_b, 1)
 +GEN_VEXT_V(vbrev8_v_h, 2)
 +GEN_VEXT_V(vbrev8_v_w, 4)
 +GEN_VEXT_V(vbrev8_v_d, 8)
 +
 +#define DO_IDENTITY(a) (a)
 +RVVCALL(OPIVV1, vrev8_v_b, OP_UU_B, H1, H1, DO_IDENTITY)
 +RVVCALL(OPIVV1, vrev8_v_h, OP_UU_H, H2, H2, bswap16)
 +RVVCALL(OPIVV1, vrev8_v_w, OP_UU_W, H4, H4, bswap32)
 +RVVCALL(OPIVV1, vrev8_v_d, OP_UU_D, H8, H8, bswap64)
 +GEN_VEXT_V(vrev8_v_b, 1)
 +GEN_VEXT_V(vrev8_v_h, 2)
 +GEN_VEXT_V(vrev8_v_w, 4)
 +GEN_VEXT_V(vrev8_v_d, 8)
 +
 +#define DO_ANDN(a, b) ((a) & ~(b))
 +RVVCALL(OPIVV2, vandn_vv_b, OP_UUU_B, H1, H1, H1, DO_ANDN)
 +RVVCALL(OPIVV2, vandn_vv_h, OP_UUU_H, H2, H2, H2, DO_ANDN)
 +RVVCALL(OPIVV2, vandn_vv_w, OP_UUU_W, H4, H4, H4, DO_ANDN)
 +RVVCALL(OPIVV2, vandn_vv_d, OP_UUU_D, H8, H8, H8, DO_ANDN)
 +GEN_VEXT_VV(vandn_vv_b, 1)
 +GEN_VEXT_VV(vandn_vv_h, 2)
 +GEN_VEXT_VV(vandn_vv_w, 4)
 +GEN_VEXT_VV(vandn_vv_d, 8)
 +
 +RVVCALL(OPIVX2, vandn_vx_b, OP_UUU_B, H1, H1, DO_ANDN)
 +RVVCALL(OPIVX2, vandn_vx_h, OP_UUU_H, H2, H2, DO_ANDN)
 +RVVCALL(OPIVX2, vandn_vx_w, OP_UUU_W, H4, H4, DO_ANDN)
 +RVVCALL(OPIVX2, vandn_vx_d, OP_UUU_D, H8, H8, DO_ANDN)
 +GEN_VEXT_VX(vandn_vx_b, 1)
 +GEN_VEXT_VX(vandn_vx_h, 2)
 +GEN_VEXT_VX(vandn_vx_w, 4)
 +GEN_VEXT_VX(vandn_vx_d, 8)
 +
 +RVVCALL(OPIVV1, vbrev_v_b, OP_UU_B, H1, H1, revbit8)
 +RVVCALL(OPIVV1, vbrev_v_h, OP_UU_H, H2, H2, revbit16)
 +RVVCALL(OPIVV1, vbrev_v_w, OP_UU_W, H4, H4, revbit32)
 +RVVCALL(OPIVV1, vbrev_v_d, OP_UU_D, H8, H8, revbit64)
 +GEN_VEXT_V(vbrev_v_b, 1)
 +GEN_VEXT_V(vbrev_v_h, 2)
 +GEN_VEXT_V(vbrev_v_w, 4)
 +GEN_VEXT_V(vbrev_v_d, 8)
 +
 +RVVCALL(OPIVV1, vclz_v_b, OP_UU_B, H1, H1, clz8)
 +RVVCALL(OPIVV1, vclz_v_h, OP_UU_H, H2, H2, clz16)
 +RVVCALL(OPIVV1, vclz_v_w, OP_UU_W, H4, H4, clz32)
 +RVVCALL(OPIVV1, vclz_v_d, OP_UU_D, H8, H8, clz64)
 +GEN_VEXT_V(vclz_v_b, 1)
 +GEN_VEXT_V(vclz_v_h, 2)
 +GEN_VEXT_V(vclz_v_w, 4)
 +GEN_VEXT_V(vclz_v_d, 8)
 +
 +RVVCALL(OPIVV1, vctz_v_b, OP_UU_B, H1, H1, ctz8)
 +RVVCALL(OPIVV1, vctz_v_h, OP_UU_H, H2, H2, ctz16)
 +RVVCALL(OPIVV1, vctz_v_w, OP_UU_W, H4, H4, ctz32)
 +RVVCALL(OPIVV1, vctz_v_d, OP_UU_D, H8, H8, ctz64)
 +GEN_VEXT_V(vctz_v_b, 1)
 +GEN_VEXT_V(vctz_v_h, 2)
 +GEN_VEXT_V(vctz_v_w, 4)
 +GEN_VEXT_V(vctz_v_d, 8)
 +
 +RVVCALL(OPIVV1, vcpop_v_b, OP_UU_B, H1, H1, ctpop8)
 +RVVCALL(OPIVV1, vcpop_v_h, OP_UU_H, H2, H2, ctpop16)
 +RVVCALL(OPIVV1, vcpop_v_w, OP_UU_W, H4, H4, ctpop32)
 +RVVCALL(OPIVV1, vcpop_v_d, OP_UU_D, H8, H8, ctpop64)
 +GEN_VEXT_V(vcpop_v_b, 1)
 +GEN_VEXT_V(vcpop_v_h, 2)
 +GEN_VEXT_V(vcpop_v_w, 4)
 +GEN_VEXT_V(vcpop_v_d, 8)
 +
 +#define DO_SLL(N, M) (N << (M & (sizeof(N) * 8 - 1)))
 +RVVCALL(OPIVV2, vwsll_vv_b, WOP_UUU_B, H2, H1, H1, DO_SLL)
 +RVVCALL(OPIVV2, vwsll_vv_h, WOP_UUU_H, H4, H2, H2, DO_SLL)
 +RVVCALL(OPIVV2, vwsll_vv_w, WOP_UUU_W, H8, H4, H4, DO_SLL)
 +GEN_VEXT_VV(vwsll_vv_b, 2)
 +GEN_VEXT_VV(vwsll_vv_h, 4)
 +GEN_VEXT_VV(vwsll_vv_w, 8)
 +
 +RVVCALL(OPIVX2, vwsll_vx_b, WOP_UUU_B, H2, H1, DO_SLL)
 +RVVCALL(OPIVX2, vwsll_vx_h, WOP_UUU_H, H4, H2, DO_SLL)
 +RVVCALL(OPIVX2, vwsll_vx_w, WOP_UUU_W, H8, H4, DO_SLL)
 +GEN_VEXT_VX(vwsll_vx_b, 2)
 +GEN_VEXT_VX(vwsll_vx_h, 4)
 +GEN_VEXT_VX(vwsll_vx_w, 8)
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvvk.c.inc
 +++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool vclmul_vx_check(DisasContext *s, arg_rmrr *a)
  GEN_VX_MASKED_TRANS(vclmul_vx, vclmul_vx_check)
  GEN_VX_MASKED_TRANS(vclmulh_vx, vclmul_vx_check)
 +
 +/*
 + * Zvbb
 + */
 +
 +#define GEN_OPIVI_GVEC_TRANS_CHECK(NAME, IMM_MODE, OPIVX, SUF, CHECK)   \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)              \
 +    {                                                                   \
 +        if (CHECK(s, a)) {                                              \
 +            static gen_helper_opivx *const fns[4] = {                   \
 +                gen_helper_##OPIVX##_b,                                 \
 +                gen_helper_##OPIVX##_h,                                 \
 +                gen_helper_##OPIVX##_w,                                 \
 +                gen_helper_##OPIVX##_d,                                 \
 +            };                                                          \
 +            return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew], \
 +                                 IMM_MODE);                             \
 +        }                                                               \
 +        return false;                                                   \
 +    }
 +
 +#define GEN_OPIVV_GVEC_TRANS_CHECK(NAME, SUF, CHECK)                     \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)               \
 +    {                                                                    \
 +        if (CHECK(s, a)) {                                               \
 +            static gen_helper_gvec_4_ptr *const fns[4] = {               \
 +                gen_helper_##NAME##_b,                                   \
 +                gen_helper_##NAME##_h,                                   \
 +                gen_helper_##NAME##_w,                                   \
 +                gen_helper_##NAME##_d,                                   \
 +            };                                                           \
 +            return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
 +        }                                                                \
 +        return false;                                                    \
 +    }
 +
 +#define GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(NAME, SUF, CHECK)       \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)       \
 +    {                                                            \
 +        if (CHECK(s, a)) {                                       \
 +            static gen_helper_opivx *const fns[4] = {            \
 +                gen_helper_##NAME##_b,                           \
 +                gen_helper_##NAME##_h,                           \
 +                gen_helper_##NAME##_w,                           \
 +                gen_helper_##NAME##_d,                           \
 +            };                                                   \
 +            return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, \
 +                                       fns[s->sew]);             \
 +        }                                                        \
 +        return false;                                            \
 +    }
 +
 +static bool zvbb_vv_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return opivv_check(s, a) && s->cfg_ptr->ext_zvbb == true;
 +}
 +
 +static bool zvbb_vx_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return opivx_check(s, a) && s->cfg_ptr->ext_zvbb == true;
 +}
 +
 +/* vrol.v[vx] */
 +GEN_OPIVV_GVEC_TRANS_CHECK(vrol_vv, rotlv, zvbb_vv_check)
 +GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vrol_vx, rotls, zvbb_vx_check)
 +
 +/* vror.v[vxi] */
 +GEN_OPIVV_GVEC_TRANS_CHECK(vror_vv, rotrv, zvbb_vv_check)
 +GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vror_vx, rotrs, zvbb_vx_check)
 +GEN_OPIVI_GVEC_TRANS_CHECK(vror_vi, IMM_TRUNC_SEW, vror_vx, rotri, zvbb_vx_check)
 +
 +#define GEN_OPIVX_GVEC_TRANS_CHECK(NAME, SUF, CHECK)                     \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)               \
 +    {                                                                    \
 +        if (CHECK(s, a)) {                                               \
 +            static gen_helper_opivx *const fns[4] = {                    \
 +                gen_helper_##NAME##_b,                                   \
 +                gen_helper_##NAME##_h,                                   \
 +                gen_helper_##NAME##_w,                                   \
 +                gen_helper_##NAME##_d,                                   \
 +            };                                                           \
 +            return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
 +        }                                                                \
 +        return false;                                                    \
 +    }
 +
 +/* vandn.v[vx] */
 +GEN_OPIVV_GVEC_TRANS_CHECK(vandn_vv, andc, zvbb_vv_check)
 +GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvbb_vx_check)
 +
 +#define GEN_OPIV_TRANS(NAME, CHECK)                                        \
 +    static bool trans_##NAME(DisasContext *s, arg_rmr *a)                  \
 +    {                                                                      \
 +        if (CHECK(s, a)) {                                                 \
 +            uint32_t data = 0;                                             \
 +            static gen_helper_gvec_3_ptr *const fns[4] = {                 \
 +                gen_helper_##NAME##_b,                                     \
 +                gen_helper_##NAME##_h,                                     \
 +                gen_helper_##NAME##_w,                                     \
 +                gen_helper_##NAME##_d,                                     \
 +            };                                                             \
 +            TCGLabel *over = gen_new_label();                              \
 +            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);     \
 +                                                                           \
 +            data = FIELD_DP32(data, VDATA, VM, a->vm);                     \
 +            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                 \
 +            data = FIELD_DP32(data, VDATA, VTA, s->vta);                   \
 +            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \
 +            data = FIELD_DP32(data, VDATA, VMA, s->vma);                   \
 +            tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),         \
 +                               vreg_ofs(s, a->rs2), cpu_env,               \
 +                               s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, \
 +                               data, fns[s->sew]);                         \
 +            mark_vs_dirty(s);                                              \
 +            gen_set_label(over);                                           \
 +            return true;                                                   \
 +        }                                                                  \
 +        return false;                                                      \
 +    }
 +
 +static bool zvbb_opiv_check(DisasContext *s, arg_rmr *a)
 +{
 +    return s->cfg_ptr->ext_zvbb == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           vext_check_ss(s, a->rd, a->rs2, a->vm);
 +}
 +
 +GEN_OPIV_TRANS(vbrev8_v, zvbb_opiv_check)
 +GEN_OPIV_TRANS(vrev8_v, zvbb_opiv_check)
 +GEN_OPIV_TRANS(vbrev_v, zvbb_opiv_check)
 +GEN_OPIV_TRANS(vclz_v, zvbb_opiv_check)
 +GEN_OPIV_TRANS(vctz_v, zvbb_opiv_check)
 +GEN_OPIV_TRANS(vcpop_v, zvbb_opiv_check)
 +
 +static bool vwsll_vv_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return s->cfg_ptr->ext_zvbb && opivv_widen_check(s, a);
 +}
 +
 +static bool vwsll_vx_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return s->cfg_ptr->ext_zvbb && opivx_widen_check(s, a);
 +}
 +
 +/* OPIVI without GVEC IR */
 +#define GEN_OPIVI_WIDEN_TRANS(NAME, IMM_MODE, OPIVX, CHECK)                  \
 +    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
 +    {                                                                        \
 +        if (CHECK(s, a)) {                                                   \
 +            static gen_helper_opivx *const fns[3] = {                        \
 +                gen_helper_##OPIVX##_b,                                      \
 +                gen_helper_##OPIVX##_h,                                      \
 +                gen_helper_##OPIVX##_w,                                      \
 +            };                                                               \
 +            return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, \
 +                               IMM_MODE);                                    \
 +        }                                                                    \
 +        return false;                                                        \
 +    }
 +
 +GEN_OPIVV_WIDEN_TRANS(vwsll_vv, vwsll_vv_check)
 +GEN_OPIVX_WIDEN_TRANS(vwsll_vx, vwsll_vx_check)
 +GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll_vx_check)
 --
-.45.1
+.41.0

-[PULL 03/28] target/riscv: Raise exceptions on wrs.nto
+[PULL v2 16/45] target/riscv: Add Zvkned ISA extension support
-From: Andrew Jones <ajones@ventanamicro.com>
+From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
-Implementing wrs.nto to always just return is consistent with the
+This commit adds support for the Zvkned vector-crypto extension, which
-specification, as the instruction is permitted to terminate the
+consists of the following instructions:
 stall for any reason, but it's not useful for virtualization, where
 we'd like the guest to trap to the hypervisor in order to allow
 scheduling of the lock holding VCPU. Change to always immediately
 raise exceptions when the appropriate conditions are present,
 otherwise continue to just return. Note, immediately raising
 exceptions is also consistent with the specification since the
 time limit that should expire prior to the exception is
 implementation-specific.
-Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
+* vaesef.[vv,vs]
-Reviewed-by: Christoph Müllner <christoph.muellner@vrull.eu>
+* vaesdf.[vv,vs]
 * vaesdm.[vv,vs]
 * vaesz.vs
 * vaesem.[vv,vs]
 * vaeskf1.vi
 * vaeskf2.vi
 Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 Co-authored-by: William Salmon <will.salmon@codethink.co.uk>
 [max.chou@sifive.com: Replaced vstart checking by TCG op]
 Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 Signed-off-by: William Salmon <will.salmon@codethink.co.uk>
 Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+[max.chou@sifive.com: Imported aes-round.h and exposed x-zvkned
-Message-ID: <20240424142808.62936-2-ajones@ventanamicro.com>
+property]
 [max.chou@sifive.com: Fixed endian issues and replaced the vstart & vl
 egs checking by helper function]
 [max.chou@sifive.com: Replaced bswap32 calls in aes key expanding]
 Message-ID: <20230711165917.2629866-10-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/helper.h                       |  1 +
+ target/riscv/cpu_cfg.h                   |   1 +
- target/riscv/op_helper.c                    | 11 ++++++++
+ target/riscv/helper.h                    |  14 ++
- target/riscv/insn_trans/trans_rvzawrs.c.inc | 29 ++++++++++++++-------
+ target/riscv/insn32.decode               |  14 ++
-files changed, 32 insertions(+), 9 deletions(-)
+ target/riscv/cpu.c                       |   4 +-
  target/riscv/vcrypto_helper.c            | 202 +++++++++++++++++++++++
  target/riscv/insn_trans/trans_rvvk.c.inc | 147 +++++++++++++++++
 files changed, 381 insertions(+), 1 deletion(-)
+diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/cpu_cfg.h
++++ b/target/riscv/cpu_cfg.h
+@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
+     bool ext_zve64d;
+     bool ext_zvbb;
+     bool ext_zvbc;
++    bool ext_zvkned;
+     bool ext_zmmul;
+     bool ext_zvfbfmin;
+     bool ext_zvfbfwma;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
-@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(csrrw_i128, tl, env, int, tl, tl, tl, tl)
+@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32)
- DEF_HELPER_1(sret, tl, env)
+ DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32)
- DEF_HELPER_1(mret, tl, env)
+ DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32)
- DEF_HELPER_1(wfi, void, env)
+ DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32)
-+DEF_HELPER_1(wrs_nto, void, env)
++
- DEF_HELPER_1(tlb_flush, void, env)
++DEF_HELPER_2(egs_check, void, i32, env)
- DEF_HELPER_1(tlb_flush_all, void, env)
++
- /* Native Debug */
++DEF_HELPER_4(vaesef_vv, void, ptr, ptr, env, i32)
-diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
++DEF_HELPER_4(vaesef_vs, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesdf_vv, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesdf_vs, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesem_vv, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesem_vs, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesdm_vv, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32)
 +DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32)
 +DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/op_helper.c
+--- a/target/riscv/insn32.decode
-+++ b/target/riscv/op_helper.c
++++ b/target/riscv/insn32.decode
-@@ -XXX,XX +XXX,XX @@ void helper_wfi(CPURISCVState *env)
+@@ -XXX,XX +XXX,XX @@
-     }
+ @r_rm    .......   ..... ..... ... ..... ....... %rs2 %rs1 %rm %rd
- }
+ @r2_rm   .......   ..... ..... ... ..... ....... %rs1 %rm %rd
+ @r2      .......   ..... ..... ... ..... ....... &r2 %rs1 %rd
-+void helper_wrs_nto(CPURISCVState *env)
++@r2_vm_1 ...... . ..... ..... ... ..... ....... &rmr vm=1 %rs2 %rd
-+{
+ @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
-+    if (env->virt_enabled && (env->priv == PRV_S || env->priv == PRV_U) &&
+ @r2_vm   ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd
-+        get_field(env->hstatus, HSTATUS_VTW) &&
+ @r1_vm   ...... vm:1 ..... ..... ... ..... ....... %rd
-+        !get_field(env->mstatus, MSTATUS_TW)) {
+@@ -XXX,XX +XXX,XX @@ vcpop_v     010010 . ..... 01110 010 ..... 1010111 @r2_vm
-+        riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC());
+ vwsll_vv    110101 . ..... ..... 000 ..... 1010111 @r_vm
-+    } else if (env->priv != PRV_M && get_field(env->mstatus, MSTATUS_TW)) {
+ vwsll_vx    110101 . ..... ..... 100 ..... 1010111 @r_vm
  vwsll_vi    110101 . ..... ..... 011 ..... 1010111 @r_vm
 +
 +# *** Zvkned vector crypto extension ***
 +vaesef_vv   101000 1 ..... 00011 010 ..... 1110111 @r2_vm_1
 +vaesef_vs   101001 1 ..... 00011 010 ..... 1110111 @r2_vm_1
 +vaesdf_vv   101000 1 ..... 00001 010 ..... 1110111 @r2_vm_1
 +vaesdf_vs   101001 1 ..... 00001 010 ..... 1110111 @r2_vm_1
 +vaesem_vv   101000 1 ..... 00010 010 ..... 1110111 @r2_vm_1
 +vaesem_vs   101001 1 ..... 00010 010 ..... 1110111 @r2_vm_1
 +vaesdm_vv   101000 1 ..... 00000 010 ..... 1110111 @r2_vm_1
 +vaesdm_vs   101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1
 +vaesz_vs    101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1
 +vaeskf1_vi  100010 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vaeskf2_vi  101010 1 ..... ..... 010 ..... 1110111 @r_vm_1
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
      ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma),
      ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
      ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
 +    ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
      ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
      ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
      ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
       * In principle Zve*x would also suffice here, were they supported
       * in qemu
       */
 -    if (cpu->cfg.ext_zvbb && !cpu->cfg.ext_zve32f) {
 +    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned) && !cpu->cfg.ext_zve32f) {
          error_setg(errp,
                     "Vector crypto extensions require V or Zve* extensions");
          return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      /* Vector cryptography extensions */
      DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
      DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
 +    DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
      DEFINE_PROP_END_OF_LIST(),
  };
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/vcrypto_helper.c
 +++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@
  #include "qemu/bitops.h"
  #include "qemu/bswap.h"
  #include "cpu.h"
 +#include "crypto/aes.h"
 +#include "crypto/aes-round.h"
  #include "exec/memop.h"
  #include "exec/exec-all.h"
  #include "exec/helper-proto.h"
@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVX2, vwsll_vx_w, WOP_UUU_W, H8, H4, DO_SLL)
  GEN_VEXT_VX(vwsll_vx_b, 2)
  GEN_VEXT_VX(vwsll_vx_h, 4)
  GEN_VEXT_VX(vwsll_vx_w, 8)
 +
 +void HELPER(egs_check)(uint32_t egs, CPURISCVState *env)
 +{
 +    uint32_t vl = env->vl;
 +    uint32_t vstart = env->vstart;
 +
 +    if (vl % egs != 0 || vstart % egs != 0) {
 +        riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
 +    }
 +}
 +
- void helper_tlb_flush(CPURISCVState *env)
++static inline void xor_round_key(AESState *round_state, AESState *round_key)
- {
++{
-     CPUState *cs = env_cpu(env);
++    round_state->v = round_state->v ^ round_key->v;
-diff --git a/target/riscv/insn_trans/trans_rvzawrs.c.inc b/target/riscv/insn_trans/trans_rvzawrs.c.inc
++}
 +
 +#define GEN_ZVKNED_HELPER_VV(NAME, ...)                                   \
 +    void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env,            \
 +                      uint32_t desc)                                      \
 +    {                                                                     \
 +        uint32_t vl = env->vl;                                            \
 +        uint32_t total_elems = vext_get_total_elems(env, desc, 4);        \
 +        uint32_t vta = vext_vta(desc);                                    \
 +                                                                          \
 +        for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {        \
 +            AESState round_key;                                           \
 +            round_key.d[0] = *((uint64_t *)vs2 + H8(i * 2 + 0));          \
 +            round_key.d[1] = *((uint64_t *)vs2 + H8(i * 2 + 1));          \
 +            AESState round_state;                                         \
 +            round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0));         \
 +            round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1));         \
 +            __VA_ARGS__;                                                  \
 +            *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0];         \
 +            *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1];         \
 +        }                                                                 \
 +        env->vstart = 0;                                                  \
 +        /* set tail elements to 1s */                                     \
 +        vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);              \
 +    }
 +
 +#define GEN_ZVKNED_HELPER_VS(NAME, ...)                                   \
 +    void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env,            \
 +                      uint32_t desc)                                      \
 +    {                                                                     \
 +        uint32_t vl = env->vl;                                            \
 +        uint32_t total_elems = vext_get_total_elems(env, desc, 4);        \
 +        uint32_t vta = vext_vta(desc);                                    \
 +                                                                          \
 +        for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {        \
 +            AESState round_key;                                           \
 +            round_key.d[0] = *((uint64_t *)vs2 + H8(0));                  \
 +            round_key.d[1] = *((uint64_t *)vs2 + H8(1));                  \
 +            AESState round_state;                                         \
 +            round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0));         \
 +            round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1));         \
 +            __VA_ARGS__;                                                  \
 +            *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0];         \
 +            *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1];         \
 +        }                                                                 \
 +        env->vstart = 0;                                                  \
 +        /* set tail elements to 1s */                                     \
 +        vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);              \
 +    }
 +
 +GEN_ZVKNED_HELPER_VV(vaesef_vv, aesenc_SB_SR_AK(&round_state,
 +                                                &round_state,
 +                                                &round_key,
 +                                                false);)
 +GEN_ZVKNED_HELPER_VS(vaesef_vs, aesenc_SB_SR_AK(&round_state,
 +                                                &round_state,
 +                                                &round_key,
 +                                                false);)
 +GEN_ZVKNED_HELPER_VV(vaesdf_vv, aesdec_ISB_ISR_AK(&round_state,
 +                                                  &round_state,
 +                                                  &round_key,
 +                                                  false);)
 +GEN_ZVKNED_HELPER_VS(vaesdf_vs, aesdec_ISB_ISR_AK(&round_state,
 +                                                  &round_state,
 +                                                  &round_key,
 +                                                  false);)
 +GEN_ZVKNED_HELPER_VV(vaesem_vv, aesenc_SB_SR_MC_AK(&round_state,
 +                                                   &round_state,
 +                                                   &round_key,
 +                                                   false);)
 +GEN_ZVKNED_HELPER_VS(vaesem_vs, aesenc_SB_SR_MC_AK(&round_state,
 +                                                   &round_state,
 +                                                   &round_key,
 +                                                   false);)
 +GEN_ZVKNED_HELPER_VV(vaesdm_vv, aesdec_ISB_ISR_AK_IMC(&round_state,
 +                                                      &round_state,
 +                                                      &round_key,
 +                                                      false);)
 +GEN_ZVKNED_HELPER_VS(vaesdm_vs, aesdec_ISB_ISR_AK_IMC(&round_state,
 +                                                      &round_state,
 +                                                      &round_key,
 +                                                      false);)
 +GEN_ZVKNED_HELPER_VS(vaesz_vs, xor_round_key(&round_state, &round_key);)
 +
 +void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
 +                        CPURISCVState *env, uint32_t desc)
 +{
 +    uint32_t *vd = vd_vptr;
 +    uint32_t *vs2 = vs2_vptr;
 +    uint32_t vl = env->vl;
 +    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
 +    uint32_t vta = vext_vta(desc);
 +
 +    uimm &= 0b1111;
 +    if (uimm > 10 || uimm == 0) {
 +        uimm ^= 0b1000;
 +    }
 +
 +    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
 +        uint32_t rk[8], tmp;
 +        static const uint32_t rcon[] = {
 +            0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010,
 +            0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036,
 +        };
 +
 +        rk[0] = vs2[i * 4 + H4(0)];
 +        rk[1] = vs2[i * 4 + H4(1)];
 +        rk[2] = vs2[i * 4 + H4(2)];
 +        rk[3] = vs2[i * 4 + H4(3)];
 +        tmp = ror32(rk[3], 8);
 +
 +        rk[4] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) |
 +                         ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) |
 +                         ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) |
 +                         ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0))
 +                      ^ rcon[uimm - 1];
 +        rk[5] = rk[1] ^ rk[4];
 +        rk[6] = rk[2] ^ rk[5];
 +        rk[7] = rk[3] ^ rk[6];
 +
 +        vd[i * 4 + H4(0)] = rk[4];
 +        vd[i * 4 + H4(1)] = rk[5];
 +        vd[i * 4 + H4(2)] = rk[6];
 +        vd[i * 4 + H4(3)] = rk[7];
 +    }
 +    env->vstart = 0;
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
 +}
 +
 +void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
 +                        CPURISCVState *env, uint32_t desc)
 +{
 +    uint32_t *vd = vd_vptr;
 +    uint32_t *vs2 = vs2_vptr;
 +    uint32_t vl = env->vl;
 +    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
 +    uint32_t vta = vext_vta(desc);
 +
 +    uimm &= 0b1111;
 +    if (uimm > 14 || uimm < 2) {
 +        uimm ^= 0b1000;
 +    }
 +
 +    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
 +        uint32_t rk[12], tmp;
 +        static const uint32_t rcon[] = {
 +            0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010,
 +            0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036,
 +        };
 +
 +        rk[0] = vd[i * 4 + H4(0)];
 +        rk[1] = vd[i * 4 + H4(1)];
 +        rk[2] = vd[i * 4 + H4(2)];
 +        rk[3] = vd[i * 4 + H4(3)];
 +        rk[4] = vs2[i * 4 + H4(0)];
 +        rk[5] = vs2[i * 4 + H4(1)];
 +        rk[6] = vs2[i * 4 + H4(2)];
 +        rk[7] = vs2[i * 4 + H4(3)];
 +
 +        if (uimm % 2 == 0) {
 +            tmp = ror32(rk[7], 8);
 +            rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) |
 +                             ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) |
 +                             ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) |
 +                             ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0))
 +                          ^ rcon[(uimm - 1) / 2];
 +        } else {
 +            rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(rk[7] >> 24) & 0xff] << 24) |
 +                             ((uint32_t)AES_sbox[(rk[7] >> 16) & 0xff] << 16) |
 +                             ((uint32_t)AES_sbox[(rk[7] >> 8) & 0xff] << 8) |
 +                             ((uint32_t)AES_sbox[(rk[7] >> 0) & 0xff] << 0));
 +        }
 +        rk[9] = rk[1] ^ rk[8];
 +        rk[10] = rk[2] ^ rk[9];
 +        rk[11] = rk[3] ^ rk[10];
 +
 +        vd[i * 4 + H4(0)] = rk[8];
 +        vd[i * 4 + H4(1)] = rk[9];
 +        vd[i * 4 + H4(2)] = rk[10];
 +        vd[i * 4 + H4(3)] = rk[11];
 +    }
 +    env->vstart = 0;
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
 +}
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/insn_trans/trans_rvzawrs.c.inc
+--- a/target/riscv/insn_trans/trans_rvvk.c.inc
-+++ b/target/riscv/insn_trans/trans_rvzawrs.c.inc
++++ b/target/riscv/insn_trans/trans_rvvk.c.inc
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ static bool vwsll_vx_check(DisasContext *s, arg_rmrr *a)
-  * this program.  If not, see <http://www.gnu.org/licenses/>.
+ GEN_OPIVV_WIDEN_TRANS(vwsll_vv, vwsll_vv_check)
-  */
+ GEN_OPIVX_WIDEN_TRANS(vwsll_vx, vwsll_vx_check)
+ GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll_vx_check)
--static bool trans_wrs(DisasContext *ctx)
++
-+static bool trans_wrs_sto(DisasContext *ctx, arg_wrs_sto *a)
++/*
- {
++ * Zvkned
-     if (!ctx->cfg_ptr->ext_zawrs) {
++ */
-         return false;
++
-@@ -XXX,XX +XXX,XX @@ static bool trans_wrs(DisasContext *ctx)
++#define ZVKNED_EGS 4
-     return true;
++
- }
++#define GEN_V_UNMASKED_TRANS(NAME, CHECK, EGS)                                \
++    static bool trans_##NAME(DisasContext *s, arg_##NAME *a)                  \
--#define GEN_TRANS_WRS(insn)                                     \
++    {                                                                         \
--static bool trans_ ## insn(DisasContext *ctx, arg_ ## insn *a)  \
++        if (CHECK(s, a)) {                                                    \
--{                                                               \
++            TCGv_ptr rd_v, rs2_v;                                             \
--    (void)a;                                                    \
++            TCGv_i32 desc, egs;                                               \
--    return trans_wrs(ctx);                                      \
++            uint32_t data = 0;                                                \
--}
++            TCGLabel *over = gen_new_label();                                 \
-+static bool trans_wrs_nto(DisasContext *ctx, arg_wrs_nto *a)
++                                                                              \
-+{
++            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
-+    if (!ctx->cfg_ptr->ext_zawrs) {
++                /* save opcode for unwinding in case we throw an exception */ \
-+        return false;
++                decode_save_opc(s);                                           \
-+    }
++                egs = tcg_constant_i32(EGS);                                  \
++                gen_helper_egs_check(egs, cpu_env);                           \
--GEN_TRANS_WRS(wrs_nto)
++                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
--GEN_TRANS_WRS(wrs_sto)
++            }                                                                 \
-+    /*
++                                                                              \
-+     * Depending on the mode of execution, mstatus.TW and hstatus.VTW, wrs.nto
++            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
-+     * should raise an exception when the implementation-specific bounded time
++            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
-+     * limit has expired. Our time limit is zero, so we either return
++            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
-+     * immediately, as does our implementation of wrs.sto, or raise an
++            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
-+     * exception, as handled by the wrs.nto helper.
++            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
-+     */
++            rd_v = tcg_temp_new_ptr();                                        \
-+#ifndef CONFIG_USER_ONLY
++            rs2_v = tcg_temp_new_ptr();                                       \
-+    gen_helper_wrs_nto(tcg_env);
++            desc = tcg_constant_i32(                                          \
-+#endif
++                simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \
-+
++            tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd));              \
-+    /* We only get here when helper_wrs_nto() doesn't raise an exception. */
++            tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2));            \
-+    return trans_wrs_sto(ctx, NULL);
++            gen_helper_##NAME(rd_v, rs2_v, cpu_env, desc);                    \
-+}
++            mark_vs_dirty(s);                                                 \
 +            gen_set_label(over);                                              \
 +            return true;                                                      \
 +        }                                                                     \
 +        return false;                                                         \
 +    }
 +
 +static bool vaes_check_vv(DisasContext *s, arg_rmr *a)
 +{
 +    int egw_bytes = ZVKNED_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvkned == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           require_align(a->rd, s->lmul) &&
 +           require_align(a->rs2, s->lmul) &&
 +           s->sew == MO_32;
 +}
 +
 +static bool vaes_check_overlap(DisasContext *s, int vd, int vs2)
 +{
 +    int8_t op_size = s->lmul <= 0 ? 1 : 1 << s->lmul;
 +    return !is_overlapped(vd, op_size, vs2, 1);
 +}
 +
 +static bool vaes_check_vs(DisasContext *s, arg_rmr *a)
 +{
 +    int egw_bytes = ZVKNED_EGS << s->sew;
 +    return vaes_check_overlap(s, a->rd, a->rs2) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->cfg_ptr->ext_zvkned == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           require_align(a->rd, s->lmul) &&
 +           s->sew == MO_32;
 +}
 +
 +GEN_V_UNMASKED_TRANS(vaesef_vv, vaes_check_vv, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesef_vs, vaes_check_vs, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesdf_vv, vaes_check_vv, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesdf_vs, vaes_check_vs, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesdm_vv, vaes_check_vv, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesdm_vs, vaes_check_vs, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesz_vs, vaes_check_vs, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesem_vv, vaes_check_vv, ZVKNED_EGS)
 +GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED_EGS)
 +
 +#define GEN_VI_UNMASKED_TRANS(NAME, CHECK, EGS)                               \
 +    static bool trans_##NAME(DisasContext *s, arg_##NAME *a)                  \
 +    {                                                                         \
 +        if (CHECK(s, a)) {                                                    \
 +            TCGv_ptr rd_v, rs2_v;                                             \
 +            TCGv_i32 uimm_v, desc, egs;                                       \
 +            uint32_t data = 0;                                                \
 +            TCGLabel *over = gen_new_label();                                 \
 +                                                                              \
 +            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
 +                /* save opcode for unwinding in case we throw an exception */ \
 +                decode_save_opc(s);                                           \
 +                egs = tcg_constant_i32(EGS);                                  \
 +                gen_helper_egs_check(egs, cpu_env);                           \
 +                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
 +            }                                                                 \
 +                                                                              \
 +            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
 +            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
 +            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
 +            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
 +            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
 +                                                                              \
 +            rd_v = tcg_temp_new_ptr();                                        \
 +            rs2_v = tcg_temp_new_ptr();                                       \
 +            uimm_v = tcg_constant_i32(a->rs1);                                \
 +            desc = tcg_constant_i32(                                          \
 +                simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \
 +            tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd));              \
 +            tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2));            \
 +            gen_helper_##NAME(rd_v, rs2_v, uimm_v, cpu_env, desc);            \
 +            mark_vs_dirty(s);                                                 \
 +            gen_set_label(over);                                              \
 +            return true;                                                      \
 +        }                                                                     \
 +        return false;                                                         \
 +    }
 +
 +static bool vaeskf1_check(DisasContext *s, arg_vaeskf1_vi *a)
 +{
 +    int egw_bytes = ZVKNED_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvkned == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->sew == MO_32 &&
 +           require_align(a->rd, s->lmul) &&
 +           require_align(a->rs2, s->lmul);
 +}
 +
 +static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a)
 +{
 +    int egw_bytes = ZVKNED_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvkned == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->sew == MO_32 &&
 +           require_align(a->rd, s->lmul) &&
 +           require_align(a->rs2, s->lmul);
 +}
 +
 +GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS)
 +GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS)
 --
-.45.1
+.41.0

-[PULL 11/28] target/riscv: Add support for Zve64x extension
+[PULL v2 17/45] target/riscv: Add Zvknh ISA extension support
-From: Jason Chien <jason.chien@sifive.com>
+From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
-Add support for Zve64x extension. Enabling Zve64f enables Zve64x and
+This commit adds support for the Zvknh vector-crypto extension, which
-enabling Zve64x enables Zve32x according to their dependency.
+consists of the following instructions:
-Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2107
+* vsha2ms.vv
-Signed-off-by: Jason Chien <jason.chien@sifive.com>
+* vsha2c[hl].vv
-Reviewed-by: Frank Chang <frank.chang@sifive.com>
-Reviewed-by: Max Chou <max.chou@sifive.com>
+Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 [max.chou@sifive.com: Replaced vstart checking by TCG op]
 Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Message-ID: <20240328022343.6871-3-jason.chien@sifive.com>
+[max.chou@sifive.com: Exposed x-zvknha & x-zvknhb properties]
 [max.chou@sifive.com: Replaced SEW selection to happened during
 translation]
 Message-ID: <20230711165917.2629866-11-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_cfg.h     |  1 +
+ target/riscv/cpu_cfg.h                   |   2 +
- target/riscv/cpu.c         |  2 ++
+ target/riscv/helper.h                    |   6 +
- target/riscv/tcg/tcg-cpu.c | 17 +++++++++++------
+ target/riscv/insn32.decode               |   5 +
-files changed, 14 insertions(+), 6 deletions(-)
+ target/riscv/cpu.c                       |  13 +-
  target/riscv/vcrypto_helper.c            | 238 +++++++++++++++++++++++
  target/riscv/insn_trans/trans_rvvk.c.inc | 129 ++++++++++++
 files changed, 390 insertions(+), 3 deletions(-)
 diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_cfg.h
 +++ b/target/riscv/cpu_cfg.h
 @@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
-     bool ext_zve32x;
-     bool ext_zve64f;
-     bool ext_zve64d;
-+    bool ext_zve64x;
      bool ext_zvbb;
      bool ext_zvbc;
-     bool ext_zvkb;
+     bool ext_zvkned;
 +    bool ext_zvknha;
 +    bool ext_zvknhb;
      bool ext_zmmul;
      bool ext_zvfbfmin;
      bool ext_zvfbfwma;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32)
  DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32)
  DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32)
  DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32)
 +
 +DEF_HELPER_5(vsha2ms_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vsha2ch32_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vsha2ch64_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vsha2cl32_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vaesdm_vs   101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1
  vaesz_vs    101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1
  vaeskf1_vi  100010 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vaeskf2_vi  101010 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +
 +# *** Zvknh vector crypto extension ***
 +vsha2ms_vv  101101 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vsha2ch_vv  101110 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vsha2cl_vv  101111 1 ..... ..... 010 ..... 1110111 @r_vm_1
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ const RISCVIsaExtData isa_edata_arr[] = {
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
      ISA_EXT_DATA_ENTRY(zve32x, PRIV_VERSION_1_10_0, ext_zve32x),
      ISA_EXT_DATA_ENTRY(zve64f, PRIV_VERSION_1_10_0, ext_zve64f),
      ISA_EXT_DATA_ENTRY(zve64d, PRIV_VERSION_1_10_0, ext_zve64d),
 +    ISA_EXT_DATA_ENTRY(zve64x, PRIV_VERSION_1_10_0, ext_zve64x),
      ISA_EXT_DATA_ENTRY(zvfbfmin, PRIV_VERSION_1_12_0, ext_zvfbfmin),
      ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma),
      ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
-@@ -XXX,XX +XXX,XX @@ const RISCVCPUMultiExtConfig riscv_cpu_extensions[] = {
+     ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
-     MULTI_EXT_CFG_BOOL("zve32x", ext_zve32x, false),
+     ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
-     MULTI_EXT_CFG_BOOL("zve64f", ext_zve64f, false),
++    ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
-     MULTI_EXT_CFG_BOOL("zve64d", ext_zve64d, false),
++    ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
-+    MULTI_EXT_CFG_BOOL("zve64x", ext_zve64x, false),
+     ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
-     MULTI_EXT_CFG_BOOL("zvfbfmin", ext_zvfbfmin, false),
+     ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
-     MULTI_EXT_CFG_BOOL("zvfbfwma", ext_zvfbfwma, false),
+     ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
      MULTI_EXT_CFG_BOOL("zvfh", ext_zvfh, false),
 diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/tcg/tcg-cpu.c
 +++ b/target/riscv/tcg/tcg-cpu.c
 @@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
+      * In principle Zve*x would also suffice here, were they supported
-     /* The Zve64d extension depends on the Zve64f extension */
+      * in qemu
-     if (cpu->cfg.ext_zve64d) {
+      */
-+        if (!riscv_has_ext(env, RVD)) {
+-    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned) && !cpu->cfg.ext_zve32f) {
-+            error_setg(errp, "Zve64d/V extensions require D extension");
++    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha) &&
-+            return;
++        !cpu->cfg.ext_zve32f) {
-+        }
+         error_setg(errp,
-         cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zve64f), true);
+                    "Vector crypto extensions require V or Zve* extensions");
      }
 -    /* The Zve64f extension depends on the Zve32f extension */
 +    /* The Zve64f extension depends on the Zve64x and Zve32f extensions */
      if (cpu->cfg.ext_zve64f) {
 +        cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zve64x), true);
          cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zve32f), true);
      }
 -    if (cpu->cfg.ext_zve64d && !riscv_has_ext(env, RVD)) {
 -        error_setg(errp, "Zve64d/V extensions require D extension");
 -        return;
 +    /* The Zve64x extension depends on the Zve32x extension */
 +    if (cpu->cfg.ext_zve64x) {
 +        cpu_cfg_ext_auto_update(cpu, CPU_CFG_OFFSET(ext_zve32x), true);
      }
      /* The Zve32f extension depends on the Zve32x extension */
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
          return;
      }
--    if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64f) {
+-    if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) {
-+    if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64x) {
+-        error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions");
-         error_setg(
++    if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64f) {
-             errp,
++        error_setg(
--            "Zvbc and Zvknhb extensions require V or Zve64{f,d} extensions");
++            errp,
-+            "Zvbc and Zvknhb extensions require V or Zve64x extensions");
++            "Zvbc and Zvknhb extensions require V or Zve64{f,d} extensions");
          return;
      }
+@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
+     DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
+     DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
+     DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
++    DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
++    DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),
+     DEFINE_PROP_END_OF_LIST(),
+ };
+diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/vcrypto_helper.c
++++ b/target/riscv/vcrypto_helper.c
+@@ -XXX,XX +XXX,XX @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
+     /* set tail elements to 1s */
+     vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
+ }
++
++static inline uint32_t sig0_sha256(uint32_t x)
++{
++    return ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3);
++}
++
++static inline uint32_t sig1_sha256(uint32_t x)
++{
++    return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10);
++}
++
++static inline uint64_t sig0_sha512(uint64_t x)
++{
++    return ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7);
++}
++
++static inline uint64_t sig1_sha512(uint64_t x)
++{
++    return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6);
++}
++
++static inline void vsha2ms_e32(uint32_t *vd, uint32_t *vs1, uint32_t *vs2)
++{
++    uint32_t res[4];
++    res[0] = sig1_sha256(vs1[H4(2)]) + vs2[H4(1)] + sig0_sha256(vd[H4(1)]) +
++             vd[H4(0)];
++    res[1] = sig1_sha256(vs1[H4(3)]) + vs2[H4(2)] + sig0_sha256(vd[H4(2)]) +
++             vd[H4(1)];
++    res[2] =
++        sig1_sha256(res[0]) + vs2[H4(3)] + sig0_sha256(vd[H4(3)]) + vd[H4(2)];
++    res[3] =
++        sig1_sha256(res[1]) + vs1[H4(0)] + sig0_sha256(vs2[H4(0)]) + vd[H4(3)];
++    vd[H4(3)] = res[3];
++    vd[H4(2)] = res[2];
++    vd[H4(1)] = res[1];
++    vd[H4(0)] = res[0];
++}
++
++static inline void vsha2ms_e64(uint64_t *vd, uint64_t *vs1, uint64_t *vs2)
++{
++    uint64_t res[4];
++    res[0] = sig1_sha512(vs1[2]) + vs2[1] + sig0_sha512(vd[1]) + vd[0];
++    res[1] = sig1_sha512(vs1[3]) + vs2[2] + sig0_sha512(vd[2]) + vd[1];
++    res[2] = sig1_sha512(res[0]) + vs2[3] + sig0_sha512(vd[3]) + vd[2];
++    res[3] = sig1_sha512(res[1]) + vs1[0] + sig0_sha512(vs2[0]) + vd[3];
++    vd[3] = res[3];
++    vd[2] = res[2];
++    vd[1] = res[1];
++    vd[0] = res[0];
++}
++
++void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
++                        uint32_t desc)
++{
++    uint32_t sew = FIELD_EX64(env->vtype, VTYPE, VSEW);
++    uint32_t esz = sew == MO_32 ? 4 : 8;
++    uint32_t total_elems;
++    uint32_t vta = vext_vta(desc);
++
++    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
++        if (sew == MO_32) {
++            vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4,
++                        ((uint32_t *)vs2) + i * 4);
++        } else {
++            /* If not 32 then SEW should be 64 */
++            vsha2ms_e64(((uint64_t *)vd) + i * 4, ((uint64_t *)vs1) + i * 4,
++                        ((uint64_t *)vs2) + i * 4);
++        }
++    }
++    /* set tail elements to 1s */
++    total_elems = vext_get_total_elems(env, desc, esz);
++    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
++    env->vstart = 0;
++}
++
++static inline uint64_t sum0_64(uint64_t x)
++{
++    return ror64(x, 28) ^ ror64(x, 34) ^ ror64(x, 39);
++}
++
++static inline uint32_t sum0_32(uint32_t x)
++{
++    return ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22);
++}
++
++static inline uint64_t sum1_64(uint64_t x)
++{
++    return ror64(x, 14) ^ ror64(x, 18) ^ ror64(x, 41);
++}
++
++static inline uint32_t sum1_32(uint32_t x)
++{
++    return ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25);
++}
++
++#define ch(x, y, z) ((x & y) ^ ((~x) & z))
++
++#define maj(x, y, z) ((x & y) ^ (x & z) ^ (y & z))
++
++static void vsha2c_64(uint64_t *vs2, uint64_t *vd, uint64_t *vs1)
++{
++    uint64_t a = vs2[3], b = vs2[2], e = vs2[1], f = vs2[0];
++    uint64_t c = vd[3], d = vd[2], g = vd[1], h = vd[0];
++    uint64_t W0 = vs1[0], W1 = vs1[1];
++    uint64_t T1 = h + sum1_64(e) + ch(e, f, g) + W0;
++    uint64_t T2 = sum0_64(a) + maj(a, b, c);
++
++    h = g;
++    g = f;
++    f = e;
++    e = d + T1;
++    d = c;
++    c = b;
++    b = a;
++    a = T1 + T2;
++
++    T1 = h + sum1_64(e) + ch(e, f, g) + W1;
++    T2 = sum0_64(a) + maj(a, b, c);
++    h = g;
++    g = f;
++    f = e;
++    e = d + T1;
++    d = c;
++    c = b;
++    b = a;
++    a = T1 + T2;
++
++    vd[0] = f;
++    vd[1] = e;
++    vd[2] = b;
++    vd[3] = a;
++}
++
++static void vsha2c_32(uint32_t *vs2, uint32_t *vd, uint32_t *vs1)
++{
++    uint32_t a = vs2[H4(3)], b = vs2[H4(2)], e = vs2[H4(1)], f = vs2[H4(0)];
++    uint32_t c = vd[H4(3)], d = vd[H4(2)], g = vd[H4(1)], h = vd[H4(0)];
++    uint32_t W0 = vs1[H4(0)], W1 = vs1[H4(1)];
++    uint32_t T1 = h + sum1_32(e) + ch(e, f, g) + W0;
++    uint32_t T2 = sum0_32(a) + maj(a, b, c);
++
++    h = g;
++    g = f;
++    f = e;
++    e = d + T1;
++    d = c;
++    c = b;
++    b = a;
++    a = T1 + T2;
++
++    T1 = h + sum1_32(e) + ch(e, f, g) + W1;
++    T2 = sum0_32(a) + maj(a, b, c);
++    h = g;
++    g = f;
++    f = e;
++    e = d + T1;
++    d = c;
++    c = b;
++    b = a;
++    a = T1 + T2;
++
++    vd[H4(0)] = f;
++    vd[H4(1)] = e;
++    vd[H4(2)] = b;
++    vd[H4(3)] = a;
++}
++
++void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
++                          uint32_t desc)
++{
++    const uint32_t esz = 4;
++    uint32_t total_elems;
++    uint32_t vta = vext_vta(desc);
++
++    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
++        vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
++                  ((uint32_t *)vs1) + 4 * i + 2);
++    }
++
++    /* set tail elements to 1s */
++    total_elems = vext_get_total_elems(env, desc, esz);
++    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
++    env->vstart = 0;
++}
++
++void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
++                          uint32_t desc)
++{
++    const uint32_t esz = 8;
++    uint32_t total_elems;
++    uint32_t vta = vext_vta(desc);
++
++    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
++        vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
++                  ((uint64_t *)vs1) + 4 * i + 2);
++    }
++
++    /* set tail elements to 1s */
++    total_elems = vext_get_total_elems(env, desc, esz);
++    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
++    env->vstart = 0;
++}
++
++void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
++                          uint32_t desc)
++{
++    const uint32_t esz = 4;
++    uint32_t total_elems;
++    uint32_t vta = vext_vta(desc);
++
++    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
++        vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
++                  (((uint32_t *)vs1) + 4 * i));
++    }
++
++    /* set tail elements to 1s */
++    total_elems = vext_get_total_elems(env, desc, esz);
++    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
++    env->vstart = 0;
++}
++
++void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
++                          uint32_t desc)
++{
++    uint32_t esz = 8;
++    uint32_t total_elems;
++    uint32_t vta = vext_vta(desc);
++
++    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
++        vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
++                  (((uint64_t *)vs1) + 4 * i));
++    }
++
++    /* set tail elements to 1s */
++    total_elems = vext_get_total_elems(env, desc, esz);
++    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
++    env->vstart = 0;
++}
+diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/insn_trans/trans_rvvk.c.inc
++++ b/target/riscv/insn_trans/trans_rvvk.c.inc
+@@ -XXX,XX +XXX,XX @@ static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a)
+ GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS)
+ GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS)
++
++/*
++ * Zvknh
++ */
++
++#define ZVKNH_EGS 4
++
++#define GEN_VV_UNMASKED_TRANS(NAME, CHECK, EGS)                               \
++    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                    \
++    {                                                                         \
++        if (CHECK(s, a)) {                                                    \
++            uint32_t data = 0;                                                \
++            TCGLabel *over = gen_new_label();                                 \
++            TCGv_i32 egs;                                                     \
++                                                                              \
++            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
++                /* save opcode for unwinding in case we throw an exception */ \
++                decode_save_opc(s);                                           \
++                egs = tcg_constant_i32(EGS);                                  \
++                gen_helper_egs_check(egs, cpu_env);                           \
++                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
++            }                                                                 \
++                                                                              \
++            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
++            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
++            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
++            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
++            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
++                                                                              \
++            tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),       \
++                               vreg_ofs(s, a->rs2), cpu_env,                  \
++                               s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8,    \
++                               data, gen_helper_##NAME);                      \
++                                                                              \
++            mark_vs_dirty(s);                                                 \
++            gen_set_label(over);                                              \
++            return true;                                                      \
++        }                                                                     \
++        return false;                                                         \
++    }
++
++static bool vsha_check_sew(DisasContext *s)
++{
++    return (s->cfg_ptr->ext_zvknha == true && s->sew == MO_32) ||
++           (s->cfg_ptr->ext_zvknhb == true &&
++            (s->sew == MO_32 || s->sew == MO_64));
++}
++
++static bool vsha_check(DisasContext *s, arg_rmrr *a)
++{
++    int egw_bytes = ZVKNH_EGS << s->sew;
++    int mult = 1 << MAX(s->lmul, 0);
++    return opivv_check(s, a) &&
++           vsha_check_sew(s) &&
++           MAXSZ(s) >= egw_bytes &&
++           !is_overlapped(a->rd, mult, a->rs1, mult) &&
++           !is_overlapped(a->rd, mult, a->rs2, mult) &&
++           s->lmul >= 0;
++}
++
++GEN_VV_UNMASKED_TRANS(vsha2ms_vv, vsha_check, ZVKNH_EGS)
++
++static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr *a)
++{
++    if (vsha_check(s, a)) {
++        uint32_t data = 0;
++        TCGLabel *over = gen_new_label();
++        TCGv_i32 egs;
++
++        if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
++            /* save opcode for unwinding in case we throw an exception */
++            decode_save_opc(s);
++            egs = tcg_constant_i32(ZVKNH_EGS);
++            gen_helper_egs_check(egs, cpu_env);
++            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
++        }
++
++        data = FIELD_DP32(data, VDATA, VM, a->vm);
++        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
++        data = FIELD_DP32(data, VDATA, VTA, s->vta);
++        data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
++        data = FIELD_DP32(data, VDATA, VMA, s->vma);
++
++        tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
++            vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8,
++            s->cfg_ptr->vlen / 8, data,
++            s->sew == MO_32 ?
++                gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv);
++
++        mark_vs_dirty(s);
++        gen_set_label(over);
++        return true;
++    }
++    return false;
++}
++
++static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr *a)
++{
++    if (vsha_check(s, a)) {
++        uint32_t data = 0;
++        TCGLabel *over = gen_new_label();
++        TCGv_i32 egs;
++
++        if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
++            /* save opcode for unwinding in case we throw an exception */
++            decode_save_opc(s);
++            egs = tcg_constant_i32(ZVKNH_EGS);
++            gen_helper_egs_check(egs, cpu_env);
++            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
++        }
++
++        data = FIELD_DP32(data, VDATA, VM, a->vm);
++        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
++        data = FIELD_DP32(data, VDATA, VTA, s->vta);
++        data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
++        data = FIELD_DP32(data, VDATA, VMA, s->vma);
++
++        tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
++            vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8,
++            s->cfg_ptr->vlen / 8, data,
++            s->sew == MO_32 ?
++                gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv);
++
++        mark_vs_dirty(s);
++        gen_set_label(over);
++        return true;
++    }
++    return false;
++}
 --
-.45.1
+.41.0

-New patch
+[PULL v2 18/45] target/riscv: Add Zvksh ISA extension support
+From: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 This commit adds support for the Zvksh vector-crypto extension, which
 consists of the following instructions:
 * vsm3me.vv
 * vsm3c.vi
 Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Co-authored-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
 [max.chou@sifive.com: Replaced vstart checking by TCG op]
 Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
 Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 [max.chou@sifive.com: Exposed x-zvksh property]
 Message-ID: <20230711165917.2629866-12-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
  target/riscv/cpu_cfg.h                   |   1 +
  target/riscv/helper.h                    |   3 +
  target/riscv/insn32.decode               |   4 +
  target/riscv/cpu.c                       |   6 +-
  target/riscv/vcrypto_helper.c            | 134 +++++++++++++++++++++++
  target/riscv/insn_trans/trans_rvvk.c.inc |  31 ++++++
 files changed, 177 insertions(+), 2 deletions(-)
 diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_cfg.h
 +++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
      bool ext_zvkned;
      bool ext_zvknha;
      bool ext_zvknhb;
 +    bool ext_zvksh;
      bool ext_zmmul;
      bool ext_zvfbfmin;
      bool ext_zvfbfwma;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_5(vsha2ch32_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_5(vsha2ch64_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_5(vsha2cl32_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32)
 +
 +DEF_HELPER_5(vsm3me_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_5(vsm3c_vi, void, ptr, ptr, i32, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vaeskf2_vi  101010 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vsha2ms_vv  101101 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vsha2ch_vv  101110 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vsha2cl_vv  101111 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +
 +# *** Zvksh vector crypto extension ***
 +vsm3me_vv   100000 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vsm3c_vi    101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
      ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
      ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
      ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
 +    ISA_EXT_DATA_ENTRY(zvksh, PRIV_VERSION_1_12_0, ext_zvksh),
      ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
      ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
      ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
       * In principle Zve*x would also suffice here, were they supported
       * in qemu
       */
 -    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha) &&
 -        !cpu->cfg.ext_zve32f) {
 +    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha ||
 +         cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
          error_setg(errp,
                     "Vector crypto extensions require V or Zve* extensions");
          return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
      DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
      DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),
 +    DEFINE_PROP_BOOL("x-zvksh", RISCVCPU, cfg.ext_zvksh, false),
      DEFINE_PROP_END_OF_LIST(),
  };
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/vcrypto_helper.c
 +++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
      vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
      env->vstart = 0;
  }
 +
 +static inline uint32_t p1(uint32_t x)
 +{
 +    return x ^ rol32(x, 15) ^ rol32(x, 23);
 +}
 +
 +static inline uint32_t zvksh_w(uint32_t m16, uint32_t m9, uint32_t m3,
 +                               uint32_t m13, uint32_t m6)
 +{
 +    return p1(m16 ^ m9 ^ rol32(m3, 15)) ^ rol32(m13, 7) ^ m6;
 +}
 +
 +void HELPER(vsm3me_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr,
 +                       CPURISCVState *env, uint32_t desc)
 +{
 +    uint32_t esz = memop_size(FIELD_EX64(env->vtype, VTYPE, VSEW));
 +    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
 +    uint32_t vta = vext_vta(desc);
 +    uint32_t *vd = vd_vptr;
 +    uint32_t *vs1 = vs1_vptr;
 +    uint32_t *vs2 = vs2_vptr;
 +
 +    for (int i = env->vstart / 8; i < env->vl / 8; i++) {
 +        uint32_t w[24];
 +        for (int j = 0; j < 8; j++) {
 +            w[j] = bswap32(vs1[H4((i * 8) + j)]);
 +            w[j + 8] = bswap32(vs2[H4((i * 8) + j)]);
 +        }
 +        for (int j = 0; j < 8; j++) {
 +            w[j + 16] =
 +                zvksh_w(w[j], w[j + 7], w[j + 13], w[j + 3], w[j + 10]);
 +        }
 +        for (int j = 0; j < 8; j++) {
 +            vd[(i * 8) + j] = bswap32(w[H4(j + 16)]);
 +        }
 +    }
 +    vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz);
 +    env->vstart = 0;
 +}
 +
 +static inline uint32_t ff1(uint32_t x, uint32_t y, uint32_t z)
 +{
 +    return x ^ y ^ z;
 +}
 +
 +static inline uint32_t ff2(uint32_t x, uint32_t y, uint32_t z)
 +{
 +    return (x & y) | (x & z) | (y & z);
 +}
 +
 +static inline uint32_t ff_j(uint32_t x, uint32_t y, uint32_t z, uint32_t j)
 +{
 +    return (j <= 15) ? ff1(x, y, z) : ff2(x, y, z);
 +}
 +
 +static inline uint32_t gg1(uint32_t x, uint32_t y, uint32_t z)
 +{
 +    return x ^ y ^ z;
 +}
 +
 +static inline uint32_t gg2(uint32_t x, uint32_t y, uint32_t z)
 +{
 +    return (x & y) | (~x & z);
 +}
 +
 +static inline uint32_t gg_j(uint32_t x, uint32_t y, uint32_t z, uint32_t j)
 +{
 +    return (j <= 15) ? gg1(x, y, z) : gg2(x, y, z);
 +}
 +
 +static inline uint32_t t_j(uint32_t j)
 +{
 +    return (j <= 15) ? 0x79cc4519 : 0x7a879d8a;
 +}
 +
 +static inline uint32_t p_0(uint32_t x)
 +{
 +    return x ^ rol32(x, 9) ^ rol32(x, 17);
 +}
 +
 +static void sm3c(uint32_t *vd, uint32_t *vs1, uint32_t *vs2, uint32_t uimm)
 +{
 +    uint32_t x0, x1;
 +    uint32_t j;
 +    uint32_t ss1, ss2, tt1, tt2;
 +    x0 = vs2[0] ^ vs2[4];
 +    x1 = vs2[1] ^ vs2[5];
 +    j = 2 * uimm;
 +    ss1 = rol32(rol32(vs1[0], 12) + vs1[4] + rol32(t_j(j), j % 32), 7);
 +    ss2 = ss1 ^ rol32(vs1[0], 12);
 +    tt1 = ff_j(vs1[0], vs1[1], vs1[2], j) + vs1[3] + ss2 + x0;
 +    tt2 = gg_j(vs1[4], vs1[5], vs1[6], j) + vs1[7] + ss1 + vs2[0];
 +    vs1[3] = vs1[2];
 +    vd[3] = rol32(vs1[1], 9);
 +    vs1[1] = vs1[0];
 +    vd[1] = tt1;
 +    vs1[7] = vs1[6];
 +    vd[7] = rol32(vs1[5], 19);
 +    vs1[5] = vs1[4];
 +    vd[5] = p_0(tt2);
 +    j = 2 * uimm + 1;
 +    ss1 = rol32(rol32(vd[1], 12) + vd[5] + rol32(t_j(j), j % 32), 7);
 +    ss2 = ss1 ^ rol32(vd[1], 12);
 +    tt1 = ff_j(vd[1], vs1[1], vd[3], j) + vs1[3] + ss2 + x1;
 +    tt2 = gg_j(vd[5], vs1[5], vd[7], j) + vs1[7] + ss1 + vs2[1];
 +    vd[2] = rol32(vs1[1], 9);
 +    vd[0] = tt1;
 +    vd[6] = rol32(vs1[5], 19);
 +    vd[4] = p_0(tt2);
 +}
 +
 +void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
 +                      CPURISCVState *env, uint32_t desc)
 +{
 +    uint32_t esz = memop_size(FIELD_EX64(env->vtype, VTYPE, VSEW));
 +    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
 +    uint32_t vta = vext_vta(desc);
 +    uint32_t *vd = vd_vptr;
 +    uint32_t *vs2 = vs2_vptr;
 +    uint32_t v1[8], v2[8], v3[8];
 +
 +    for (int i = env->vstart / 8; i < env->vl / 8; i++) {
 +        for (int k = 0; k < 8; k++) {
 +            v2[k] = bswap32(vd[H4(i * 8 + k)]);
 +            v3[k] = bswap32(vs2[H4(i * 8 + k)]);
 +        }
 +        sm3c(v1, v2, v3, uimm);
 +        for (int k = 0; k < 8; k++) {
 +            vd[i * 8 + k] = bswap32(v1[H4(k)]);
 +        }
 +    }
 +    vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz);
 +    env->vstart = 0;
 +}
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvvk.c.inc
 +++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr *a)
      }
      return false;
  }
 +
 +/*
 + * Zvksh
 + */
 +
 +#define ZVKSH_EGS 8
 +
 +static inline bool vsm3_check(DisasContext *s, arg_rmrr *a)
 +{
 +    int egw_bytes = ZVKSH_EGS << s->sew;
 +    int mult = 1 << MAX(s->lmul, 0);
 +    return s->cfg_ptr->ext_zvksh == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           !is_overlapped(a->rd, mult, a->rs2, mult) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->sew == MO_32;
 +}
 +
 +static inline bool vsm3me_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return vsm3_check(s, a) && vext_check_sss(s, a->rd, a->rs1, a->rs2, a->vm);
 +}
 +
 +static inline bool vsm3c_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return vsm3_check(s, a) && vext_check_ss(s, a->rd, a->rs2, a->vm);
 +}
 +
 +GEN_VV_UNMASKED_TRANS(vsm3me_vv, vsm3me_check, ZVKSH_EGS)
 +GEN_VI_UNMASKED_TRANS(vsm3c_vi, vsm3c_check, ZVKSH_EGS)
 --
 .41.0

-New patch
+[PULL v2 19/45] target/riscv: Add Zvkg ISA extension support
+From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 This commit adds support for the Zvkg vector-crypto extension, which
 consists of the following instructions:
 * vgmul.vv
 * vghsh.vv
 Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 [max.chou@sifive.com: Replaced vstart checking by TCG op]
 Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
 Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 [max.chou@sifive.com: Exposed x-zvkg property]
 [max.chou@sifive.com: Replaced uint by int for cross win32 build]
 Message-ID: <20230711165917.2629866-13-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
  target/riscv/cpu_cfg.h                   |  1 +
  target/riscv/helper.h                    |  3 +
  target/riscv/insn32.decode               |  4 ++
  target/riscv/cpu.c                       |  6 +-
  target/riscv/vcrypto_helper.c            | 72 ++++++++++++++++++++++++
  target/riscv/insn_trans/trans_rvvk.c.inc | 30 ++++++++++
 files changed, 114 insertions(+), 2 deletions(-)
 diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_cfg.h
 +++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
      bool ext_zve64d;
      bool ext_zvbb;
      bool ext_zvbc;
 +    bool ext_zvkg;
      bool ext_zvkned;
      bool ext_zvknha;
      bool ext_zvknhb;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_5(vsm3me_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_5(vsm3c_vi, void, ptr, ptr, i32, env, i32)
 +
 +DEF_HELPER_5(vghsh_vv, void, ptr, ptr, ptr, env, i32)
 +DEF_HELPER_4(vgmul_vv, void, ptr, ptr, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vsha2cl_vv  101111 1 ..... ..... 010 ..... 1110111 @r_vm_1
  # *** Zvksh vector crypto extension ***
  vsm3me_vv   100000 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vsm3c_vi    101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +
 +# *** Zvkg vector crypto extension ***
 +vghsh_vv    101100 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vgmul_vv    101000 1 ..... 10001 010 ..... 1110111 @r2_vm_1
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
      ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma),
      ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
      ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
 +    ISA_EXT_DATA_ENTRY(zvkg, PRIV_VERSION_1_12_0, ext_zvkg),
      ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
      ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
      ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
       * In principle Zve*x would also suffice here, were they supported
       * in qemu
       */
 -    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha ||
 -         cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
 +    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkg || cpu->cfg.ext_zvkned ||
 +         cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
          error_setg(errp,
                     "Vector crypto extensions require V or Zve* extensions");
          return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      /* Vector cryptography extensions */
      DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
      DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
 +    DEFINE_PROP_BOOL("x-zvkg", RISCVCPU, cfg.ext_zvkg, false),
      DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
      DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
      DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/vcrypto_helper.c
 +++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
      vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz);
      env->vstart = 0;
  }
 +
 +void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr,
 +                      CPURISCVState *env, uint32_t desc)
 +{
 +    uint64_t *vd = vd_vptr;
 +    uint64_t *vs1 = vs1_vptr;
 +    uint64_t *vs2 = vs2_vptr;
 +    uint32_t vta = vext_vta(desc);
 +    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
 +
 +    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
 +        uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]};
 +        uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
 +        uint64_t X[2] = {vs1[i * 2 + 0], vs1[i * 2 + 1]};
 +        uint64_t Z[2] = {0, 0};
 +
 +        uint64_t S[2] = {brev8(Y[0] ^ X[0]), brev8(Y[1] ^ X[1])};
 +
 +        for (int j = 0; j < 128; j++) {
 +            if ((S[j / 64] >> (j % 64)) & 1) {
 +                Z[0] ^= H[0];
 +                Z[1] ^= H[1];
 +            }
 +            bool reduce = ((H[1] >> 63) & 1);
 +            H[1] = H[1] << 1 | H[0] >> 63;
 +            H[0] = H[0] << 1;
 +            if (reduce) {
 +                H[0] ^= 0x87;
 +            }
 +        }
 +
 +        vd[i * 2 + 0] = brev8(Z[0]);
 +        vd[i * 2 + 1] = brev8(Z[1]);
 +    }
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
 +    env->vstart = 0;
 +}
 +
 +void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env,
 +                      uint32_t desc)
 +{
 +    uint64_t *vd = vd_vptr;
 +    uint64_t *vs2 = vs2_vptr;
 +    uint32_t vta = vext_vta(desc);
 +    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
 +
 +    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
 +        uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])};
 +        uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
 +        uint64_t Z[2] = {0, 0};
 +
 +        for (int j = 0; j < 128; j++) {
 +            if ((Y[j / 64] >> (j % 64)) & 1) {
 +                Z[0] ^= H[0];
 +                Z[1] ^= H[1];
 +            }
 +            bool reduce = ((H[1] >> 63) & 1);
 +            H[1] = H[1] << 1 | H[0] >> 63;
 +            H[0] = H[0] << 1;
 +            if (reduce) {
 +                H[0] ^= 0x87;
 +            }
 +        }
 +
 +        vd[i * 2 + 0] = brev8(Z[0]);
 +        vd[i * 2 + 1] = brev8(Z[1]);
 +    }
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
 +    env->vstart = 0;
 +}
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvvk.c.inc
 +++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static inline bool vsm3c_check(DisasContext *s, arg_rmrr *a)
  GEN_VV_UNMASKED_TRANS(vsm3me_vv, vsm3me_check, ZVKSH_EGS)
  GEN_VI_UNMASKED_TRANS(vsm3c_vi, vsm3c_check, ZVKSH_EGS)
 +
 +/*
 + * Zvkg
 + */
 +
 +#define ZVKG_EGS 4
 +
 +static bool vgmul_check(DisasContext *s, arg_rmr *a)
 +{
 +    int egw_bytes = ZVKG_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvkg == true &&
 +           vext_check_isa_ill(s) &&
 +           require_rvv(s) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           vext_check_ss(s, a->rd, a->rs2, a->vm) &&
 +           s->sew == MO_32;
 +}
 +
 +GEN_V_UNMASKED_TRANS(vgmul_vv, vgmul_check, ZVKG_EGS)
 +
 +static bool vghsh_check(DisasContext *s, arg_rmrr *a)
 +{
 +    int egw_bytes = ZVKG_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvkg == true &&
 +           opivv_check(s, a) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->sew == MO_32;
 +}
 +
 +GEN_VV_UNMASKED_TRANS(vghsh_vv, vghsh_check, ZVKG_EGS)
 --
 .41.0

-New patch
+[PULL v2 20/45] crypto: Create sm4_subword
+From: Max Chou <max.chou@sifive.com>
+Allows sharing of sm4_subword between different targets.
+Signed-off-by: Max Chou <max.chou@sifive.com>
+Reviewed-by: Frank Chang <frank.chang@sifive.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Signed-off-by: Max Chou <max.chou@sifive.com>
+Message-ID: <20230711165917.2629866-14-max.chou@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ include/crypto/sm4.h           |  8 ++++++++
+ target/arm/tcg/crypto_helper.c | 10 ++--------
+files changed, 10 insertions(+), 8 deletions(-)
+diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/crypto/sm4.h
++++ b/include/crypto/sm4.h
+@@ -XXX,XX +XXX,XX @@
+ extern const uint8_t sm4_sbox[256];
++static inline uint32_t sm4_subword(uint32_t word)
++{
++    return sm4_sbox[word & 0xff] |
++           sm4_sbox[(word >> 8) & 0xff] << 8 |
++           sm4_sbox[(word >> 16) & 0xff] << 16 |
++           sm4_sbox[(word >> 24) & 0xff] << 24;
++}
++
+ #endif
+diff --git a/target/arm/tcg/crypto_helper.c b/target/arm/tcg/crypto_helper.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/arm/tcg/crypto_helper.c
++++ b/target/arm/tcg/crypto_helper.c
+@@ -XXX,XX +XXX,XX @@ static void do_crypto_sm4e(uint64_t *rd, uint64_t *rn, uint64_t *rm)
+             CR_ST_WORD(d, (i + 3) % 4) ^
+             CR_ST_WORD(n, i);
+-        t = sm4_sbox[t & 0xff] |
+-            sm4_sbox[(t >> 8) & 0xff] << 8 |
+-            sm4_sbox[(t >> 16) & 0xff] << 16 |
+-            sm4_sbox[(t >> 24) & 0xff] << 24;
++        t = sm4_subword(t);
+         CR_ST_WORD(d, i) ^= t ^ rol32(t, 2) ^ rol32(t, 10) ^ rol32(t, 18) ^
+                             rol32(t, 24);
+@@ -XXX,XX +XXX,XX @@ static void do_crypto_sm4ekey(uint64_t *rd, uint64_t *rn, uint64_t *rm)
+             CR_ST_WORD(d, (i + 3) % 4) ^
+             CR_ST_WORD(m, i);
+-        t = sm4_sbox[t & 0xff] |
+-            sm4_sbox[(t >> 8) & 0xff] << 8 |
+-            sm4_sbox[(t >> 16) & 0xff] << 16 |
+-            sm4_sbox[(t >> 24) & 0xff] << 24;
++        t = sm4_subword(t);
+         CR_ST_WORD(d, i) ^= t ^ rol32(t, 13) ^ rol32(t, 23);
+     }
+--
+.41.0

-New patch
+[PULL v2 21/45] crypto: Add SM4 constant parameter CK
+From: Max Chou <max.chou@sifive.com>
+Adds sm4_ck constant for use in sm4 cryptography across different targets.
+Signed-off-by: Max Chou <max.chou@sifive.com>
+Reviewed-by: Frank Chang <frank.chang@sifive.com>
+Signed-off-by: Max Chou <max.chou@sifive.com>
+Message-ID: <20230711165917.2629866-15-max.chou@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ include/crypto/sm4.h |  1 +
+ crypto/sm4.c         | 10 ++++++++++
+files changed, 11 insertions(+)
+diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/crypto/sm4.h
++++ b/include/crypto/sm4.h
+@@ -XXX,XX +XXX,XX @@
+ #define QEMU_SM4_H
+ extern const uint8_t sm4_sbox[256];
++extern const uint32_t sm4_ck[32];
+ static inline uint32_t sm4_subword(uint32_t word)
+ {
+diff --git a/crypto/sm4.c b/crypto/sm4.c
+index XXXXXXX..XXXXXXX 100644
+--- a/crypto/sm4.c
++++ b/crypto/sm4.c
+@@ -XXX,XX +XXX,XX @@ uint8_t const sm4_sbox[] = {
+x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48,
+ };
++uint32_t const sm4_ck[] = {
++    0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269,
++    0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9,
++    0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249,
++    0x50575e65, 0x6c737a81, 0x888f969d, 0xa4abb2b9,
++    0xc0c7ced5, 0xdce3eaf1, 0xf8ff060d, 0x141b2229,
++    0x30373e45, 0x4c535a61, 0x686f767d, 0x848b9299,
++    0xa0a7aeb5, 0xbcc3cad1, 0xd8dfe6ed, 0xf4fb0209,
++    0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279
++};
+--
+.41.0

-New patch
+[PULL v2 22/45] target/riscv: Add Zvksed ISA extension support
+From: Max Chou <max.chou@sifive.com>
 This commit adds support for the Zvksed vector-crypto extension, which
 consists of the following instructions:
 * vsm4k.vi
 * vsm4r.[vv,vs]
 Translation functions are defined in
 `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
 `target/riscv/vcrypto_helper.c`.
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Reviewed-by: Frank Chang <frank.chang@sifive.com>
 [lawrence.hunter@codethink.co.uk: Moved SM4 functions from
 crypto_helper.c to vcrypto_helper.c]
 [nazar.kazakov@codethink.co.uk: Added alignment checks, refactored code to
 use macros, and minor style changes]
 Signed-off-by: Max Chou <max.chou@sifive.com>
 Message-ID: <20230711165917.2629866-16-max.chou@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
  target/riscv/cpu_cfg.h                   |   1 +
  target/riscv/helper.h                    |   4 +
  target/riscv/insn32.decode               |   5 +
  target/riscv/cpu.c                       |   5 +-
  target/riscv/vcrypto_helper.c            | 127 +++++++++++++++++++++++
  target/riscv/insn_trans/trans_rvvk.c.inc |  43 ++++++++
 files changed, 184 insertions(+), 1 deletion(-)
 diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_cfg.h
 +++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
      bool ext_zvkned;
      bool ext_zvknha;
      bool ext_zvknhb;
 +    bool ext_zvksed;
      bool ext_zvksh;
      bool ext_zmmul;
      bool ext_zvfbfmin;
 diff --git a/target/riscv/helper.h b/target/riscv/helper.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/helper.h
 +++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_5(vsm3c_vi, void, ptr, ptr, i32, env, i32)
  DEF_HELPER_5(vghsh_vv, void, ptr, ptr, ptr, env, i32)
  DEF_HELPER_4(vgmul_vv, void, ptr, ptr, env, i32)
 +
 +DEF_HELPER_5(vsm4k_vi, void, ptr, ptr, i32, env, i32)
 +DEF_HELPER_4(vsm4r_vv, void, ptr, ptr, env, i32)
 +DEF_HELPER_4(vsm4r_vs, void, ptr, ptr, env, i32)
 diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn32.decode
 +++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vsm3c_vi    101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
  # *** Zvkg vector crypto extension ***
  vghsh_vv    101100 1 ..... ..... 010 ..... 1110111 @r_vm_1
  vgmul_vv    101000 1 ..... 10001 010 ..... 1110111 @r2_vm_1
 +
 +# *** Zvksed vector crypto extension ***
 +vsm4k_vi    100001 1 ..... ..... 010 ..... 1110111 @r_vm_1
 +vsm4r_vv    101000 1 ..... 10000 010 ..... 1110111 @r2_vm_1
 +vsm4r_vs    101001 1 ..... 10000 010 ..... 1110111 @r2_vm_1
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
      ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
      ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
      ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
 +    ISA_EXT_DATA_ENTRY(zvksed, PRIV_VERSION_1_12_0, ext_zvksed),
      ISA_EXT_DATA_ENTRY(zvksh, PRIV_VERSION_1_12_0, ext_zvksh),
      ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
      ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
       * in qemu
       */
      if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkg || cpu->cfg.ext_zvkned ||
 -         cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
 +         cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksed || cpu->cfg.ext_zvksh) &&
 +        !cpu->cfg.ext_zve32f) {
          error_setg(errp,
                     "Vector crypto extensions require V or Zve* extensions");
          return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
      DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
      DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),
 +    DEFINE_PROP_BOOL("x-zvksed", RISCVCPU, cfg.ext_zvksed, false),
      DEFINE_PROP_BOOL("x-zvksh", RISCVCPU, cfg.ext_zvksh, false),
      DEFINE_PROP_END_OF_LIST(),
 diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/vcrypto_helper.c
 +++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@
  #include "cpu.h"
  #include "crypto/aes.h"
  #include "crypto/aes-round.h"
 +#include "crypto/sm4.h"
  #include "exec/memop.h"
  #include "exec/exec-all.h"
  #include "exec/helper-proto.h"
@@ -XXX,XX +XXX,XX @@ void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env,
      vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
      env->vstart = 0;
  }
 +
 +void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uimm5, CPURISCVState *env,
 +                      uint32_t desc)
 +{
 +    const uint32_t egs = 4;
 +    uint32_t rnd = uimm5 & 0x7;
 +    uint32_t group_start = env->vstart / egs;
 +    uint32_t group_end = env->vl / egs;
 +    uint32_t esz = sizeof(uint32_t);
 +    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
 +
 +    for (uint32_t i = group_start; i < group_end; ++i) {
 +        uint32_t vstart = i * egs;
 +        uint32_t vend = (i + 1) * egs;
 +        uint32_t rk[4] = {0};
 +        uint32_t tmp[8] = {0};
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            rk[j - vstart] = *((uint32_t *)vs2 + H4(j));
 +        }
 +
 +        for (uint32_t j = 0; j < egs; ++j) {
 +            tmp[j] = rk[j];
 +        }
 +
 +        for (uint32_t j = 0; j < egs; ++j) {
 +            uint32_t b, s;
 +            b = tmp[j + 1] ^ tmp[j + 2] ^ tmp[j + 3] ^ sm4_ck[rnd * 4 + j];
 +
 +            s = sm4_subword(b);
 +
 +            tmp[j + 4] = tmp[j] ^ (s ^ rol32(s, 13) ^ rol32(s, 23));
 +        }
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
 +        }
 +    }
 +
 +    env->vstart = 0;
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
 +}
 +
 +static void do_sm4_round(uint32_t *rk, uint32_t *buf)
 +{
 +    const uint32_t egs = 4;
 +    uint32_t s, b;
 +
 +    for (uint32_t j = egs; j < egs * 2; ++j) {
 +        b = buf[j - 3] ^ buf[j - 2] ^ buf[j - 1] ^ rk[j - 4];
 +
 +        s = sm4_subword(b);
 +
 +        buf[j] = buf[j - 4] ^ (s ^ rol32(s, 2) ^ rol32(s, 10) ^ rol32(s, 18) ^
 +                               rol32(s, 24));
 +    }
 +}
 +
 +void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
 +{
 +    const uint32_t egs = 4;
 +    uint32_t group_start = env->vstart / egs;
 +    uint32_t group_end = env->vl / egs;
 +    uint32_t esz = sizeof(uint32_t);
 +    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
 +
 +    for (uint32_t i = group_start; i < group_end; ++i) {
 +        uint32_t vstart = i * egs;
 +        uint32_t vend = (i + 1) * egs;
 +        uint32_t rk[4] = {0};
 +        uint32_t tmp[8] = {0};
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            rk[j - vstart] = *((uint32_t *)vs2 + H4(j));
 +        }
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            tmp[j - vstart] = *((uint32_t *)vd + H4(j));
 +        }
 +
 +        do_sm4_round(rk, tmp);
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
 +        }
 +    }
 +
 +    env->vstart = 0;
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
 +}
 +
 +void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
 +{
 +    const uint32_t egs = 4;
 +    uint32_t group_start = env->vstart / egs;
 +    uint32_t group_end = env->vl / egs;
 +    uint32_t esz = sizeof(uint32_t);
 +    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
 +
 +    for (uint32_t i = group_start; i < group_end; ++i) {
 +        uint32_t vstart = i * egs;
 +        uint32_t vend = (i + 1) * egs;
 +        uint32_t rk[4] = {0};
 +        uint32_t tmp[8] = {0};
 +
 +        for (uint32_t j = 0; j < egs; ++j) {
 +            rk[j] = *((uint32_t *)vs2 + H4(j));
 +        }
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            tmp[j - vstart] = *((uint32_t *)vd + H4(j));
 +        }
 +
 +        do_sm4_round(rk, tmp);
 +
 +        for (uint32_t j = vstart; j < vend; ++j) {
 +            *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
 +        }
 +    }
 +
 +    env->vstart = 0;
 +    /* set tail elements to 1s */
 +    vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
 +}
 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/insn_trans/trans_rvvk.c.inc
 +++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool vghsh_check(DisasContext *s, arg_rmrr *a)
  }
  GEN_VV_UNMASKED_TRANS(vghsh_vv, vghsh_check, ZVKG_EGS)
 +
 +/*
 + * Zvksed
 + */
 +
 +#define ZVKSED_EGS 4
 +
 +static bool zvksed_check(DisasContext *s)
 +{
 +    int egw_bytes = ZVKSED_EGS << s->sew;
 +    return s->cfg_ptr->ext_zvksed == true &&
 +           require_rvv(s) &&
 +           vext_check_isa_ill(s) &&
 +           MAXSZ(s) >= egw_bytes &&
 +           s->sew == MO_32;
 +}
 +
 +static bool vsm4k_vi_check(DisasContext *s, arg_rmrr *a)
 +{
 +    return zvksed_check(s) &&
 +           require_align(a->rd, s->lmul) &&
 +           require_align(a->rs2, s->lmul);
 +}
 +
 +GEN_VI_UNMASKED_TRANS(vsm4k_vi, vsm4k_vi_check, ZVKSED_EGS)
 +
 +static bool vsm4r_vv_check(DisasContext *s, arg_rmr *a)
 +{
 +    return zvksed_check(s) &&
 +           require_align(a->rd, s->lmul) &&
 +           require_align(a->rs2, s->lmul);
 +}
 +
 +GEN_V_UNMASKED_TRANS(vsm4r_vv, vsm4r_vv_check, ZVKSED_EGS)
 +
 +static bool vsm4r_vs_check(DisasContext *s, arg_rmr *a)
 +{
 +    return zvksed_check(s) &&
 +           !is_overlapped(a->rd, 1 << MAX(s->lmul, 0), a->rs2, 1) &&
 +           require_align(a->rd, s->lmul);
 +}
 +
 +GEN_V_UNMASKED_TRANS(vsm4r_vs, vsm4r_vs_check, ZVKSED_EGS)
 --
 .41.0

-[PULL 13/28] target/riscv: Fix the element agnostic function problem
+[PULL v2 23/45] target/riscv: Implement WARL behaviour for mcountinhibit/mcounteren
-From: Huang Tao <eric.huang@linux.alibaba.com>
+From: Rob Bradford <rbradford@rivosinc.com>
-In RVV and vcrypto instructions, the masked and tail elements are set to 1s
+These are WARL fields - zero out the bits for unavailable counters and
-using vext_set_elems_1s function if the vma/vta bit is set. It is the element
+special case the TM bit in mcountinhibit which is hardwired to zero.
-agnostic policy.
+This patch achieves this by modifying the value written so that any use
 of the field will see the correctly masked bits.
-However, this function can't deal the big endian situation. This patch fixes
+Tested by modifying OpenSBI to write max value to these CSRs and upon
-the problem by adding handling of such case.
+subsequent read the appropriate number of bits for number of PMUs is
 enabled and the TM bit is zero in mcountinhibit.
-Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
+Signed-off-by: Rob Bradford <rbradford@rivosinc.com>
-Suggested-by: Richard Henderson <richard.henderson@linaro.org>
+Acked-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Atish Patra <atishp@rivosinc.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-ID: <20230802124906.24197-1-rbradford@rivosinc.com>
 Message-ID: <20240325021654.6594-1-eric.huang@linux.alibaba.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/vector_internals.c | 22 ++++++++++++++++++++++
+ target/riscv/csr.c | 11 +++++++++--
-file changed, 22 insertions(+)
+file changed, 9 insertions(+), 2 deletions(-)
-diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
+diff --git a/target/riscv/csr.c b/target/riscv/csr.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/vector_internals.c
+--- a/target/riscv/csr.c
-+++ b/target/riscv/vector_internals.c
++++ b/target/riscv/csr.c
-@@ -XXX,XX +XXX,XX @@ void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+@@ -XXX,XX +XXX,XX @@ static RISCVException write_mcountinhibit(CPURISCVState *env, int csrno,
-     if (tot - cnt == 0) {
+ {
-         return ;
+     int cidx;
-     }
+     PMUCTRState *counter;
 +    RISCVCPU *cpu = env_archcpu(env);
 -    env->mcountinhibit = val;
 +    /* WARL register - disable unavailable counters; TM bit is always 0 */
 +    env->mcountinhibit =
 +        val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_IR);
      /* Check if any other counter is also monitoring cycles/instructions */
      for (cidx = 0; cidx < RV_MAX_MHPMCOUNTERS; cidx++) {
@@ -XXX,XX +XXX,XX @@ static RISCVException read_mcounteren(CPURISCVState *env, int csrno,
  static RISCVException write_mcounteren(CPURISCVState *env, int csrno,
                                         target_ulong val)
  {
 -    env->mcounteren = val;
 +    RISCVCPU *cpu = env_archcpu(env);
 +
-+    if (HOST_BIG_ENDIAN) {
++    /* WARL register - disable unavailable counters */
-+        /*
++    env->mcounteren = val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_TM |
-+         * Deal the situation when the elements are insdie
++                             COUNTEREN_IR);
-+         * only one uint64 block including setting the
+     return RISCV_EXCP_NONE;
 +         * masked-off element.
 +         */
 +        if (((tot - 1) ^ cnt) < 8) {
 +            memset(base + H1(tot - 1), -1, tot - cnt);
 +            return;
 +        }
 +        /*
 +         * Otherwise, at least cross two uint64_t blocks.
 +         * Set first unaligned block.
 +         */
 +        if (cnt % 8 != 0) {
 +            uint32_t j = ROUND_UP(cnt, 8);
 +            memset(base + H1(j - 1), -1, j - cnt);
 +            cnt = j;
 +        }
 +        /* Set other 64bit aligend blocks */
 +    }
      memset(base + cnt, -1, tot - cnt);
  }
 --
-.45.1
+.41.0

-New patch
+[PULL v2 24/45] target/riscv: Add Zihintntl extension ISA string to DTS
+From: Jason Chien <jason.chien@sifive.com>
+RVA23 Profiles states:
+The RVA23 profiles are intended to be used for 64-bit application
+processors that will run rich OS stacks from standard binary OS
+distributions and with a substantial number of third-party binary user
+applications that will be supported over a considerable length of time
+in the field.
+The chapter 4 of the unprivileged spec introduces the Zihintntl extension
+and Zihintntl is a mandatory extension presented in RVA23 Profiles, whose
+purpose is to enable application and operating system portability across
+different implementations. Thus the DTS should contain the Zihintntl ISA
+string in order to pass to software.
+The unprivileged spec states:
+Like any HINTs, these instructions may be freely ignored. Hence, although
+they are described in terms of cache-based memory hierarchies, they do not
+mandate the provision of caches.
+These instructions are encoded with non-used opcode, e.g. ADD x0, x0, x2,
+which QEMU already supports, and QEMU does not emulate cache. Therefore
+these instructions can be considered as a no-op, and we only need to add
+a new property for the Zihintntl extension.
+Reviewed-by: Frank Chang <frank.chang@sifive.com>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Signed-off-by: Jason Chien <jason.chien@sifive.com>
+Message-ID: <20230726074049.19505-2-jason.chien@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/cpu_cfg.h | 1 +
+ target/riscv/cpu.c     | 2 ++
+files changed, 3 insertions(+)
+diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/cpu_cfg.h
++++ b/target/riscv/cpu_cfg.h
+@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
+     bool ext_icbom;
+     bool ext_icboz;
+     bool ext_zicond;
++    bool ext_zihintntl;
+     bool ext_zihintpause;
+     bool ext_smstateen;
+     bool ext_sstc;
+diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/cpu.c
++++ b/target/riscv/cpu.c
+@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
+     ISA_EXT_DATA_ENTRY(zicond, PRIV_VERSION_1_12_0, ext_zicond),
+     ISA_EXT_DATA_ENTRY(zicsr, PRIV_VERSION_1_10_0, ext_icsr),
+     ISA_EXT_DATA_ENTRY(zifencei, PRIV_VERSION_1_10_0, ext_ifencei),
++    ISA_EXT_DATA_ENTRY(zihintntl, PRIV_VERSION_1_10_0, ext_zihintntl),
+     ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause),
+     ISA_EXT_DATA_ENTRY(zmmul, PRIV_VERSION_1_12_0, ext_zmmul),
+     ISA_EXT_DATA_ENTRY(zawrs, PRIV_VERSION_1_12_0, ext_zawrs),
+@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
+     DEFINE_PROP_BOOL("sscofpmf", RISCVCPU, cfg.ext_sscofpmf, false),
+     DEFINE_PROP_BOOL("Zifencei", RISCVCPU, cfg.ext_ifencei, true),
+     DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, true),
++    DEFINE_PROP_BOOL("Zihintntl", RISCVCPU, cfg.ext_zihintntl, true),
+     DEFINE_PROP_BOOL("Zihintpause", RISCVCPU, cfg.ext_zihintpause, true),
+     DEFINE_PROP_BOOL("Zawrs", RISCVCPU, cfg.ext_zawrs, true),
+     DEFINE_PROP_BOOL("Zfa", RISCVCPU, cfg.ext_zfa, true),
+--
+.41.0

-[PULL 24/28] target/riscv: rvzicbo: Fixup CBO extension register calculation
+[PULL v2 25/45] target/riscv: Fix zfa fleq.d and fltq.d
-From: Alistair Francis <alistair23@gmail.com>
+From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
-When running the instruction
+Commit a47842d ("riscv: Add support for the Zfa extension") implemented the zfa extension.
 However, it has some typos for fleq.d and fltq.d. Both of them misused the fltq.s
 helper function.
-```
+Fixes: a47842d ("riscv: Add support for the Zfa extension")
-    cbo.flush 0(x0)
+Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
-```
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
-QEMU would segfault.
+Message-ID: <20230728003906.768-1-zhiwei_liu@linux.alibaba.com>
 The issue was in cpu_gpr[a->rs1] as QEMU does not have cpu_gpr[0]
 allocated.
 In order to fix this let's use the existing get_address()
 helper. This also has the benefit of performing pointer mask
 calculations on the address specified in rs1.
 The pointer masking specificiation specifically states:
 """
 Cache Management Operations: All instructions in Zicbom, Zicbop and Zicboz
 """
 So this is the correct behaviour and we previously have been incorrectly
 not masking the address.
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 Reported-by: Fabian Thomas <fabian.thomas@cispa.de>
 Fixes: e05da09b7cfd ("target/riscv: implement Zicbom extension")
 Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240514023910.301766-1-alistair.francis@wdc.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_rvzicbo.c.inc | 16 ++++++++++++----
+ target/riscv/insn_trans/trans_rvzfa.c.inc | 4 ++--
-file changed, 12 insertions(+), 4 deletions(-)
+file changed, 2 insertions(+), 2 deletions(-)
-diff --git a/target/riscv/insn_trans/trans_rvzicbo.c.inc b/target/riscv/insn_trans/trans_rvzicbo.c.inc
+diff --git a/target/riscv/insn_trans/trans_rvzfa.c.inc b/target/riscv/insn_trans/trans_rvzfa.c.inc
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/insn_trans/trans_rvzicbo.c.inc
+--- a/target/riscv/insn_trans/trans_rvzfa.c.inc
-+++ b/target/riscv/insn_trans/trans_rvzicbo.c.inc
++++ b/target/riscv/insn_trans/trans_rvzfa.c.inc
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ bool trans_fleq_d(DisasContext *ctx, arg_fleq_d *a)
- static bool trans_cbo_clean(DisasContext *ctx, arg_cbo_clean *a)
+     TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
- {
+     TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
-     REQUIRE_ZICBOM(ctx);
--    gen_helper_cbo_clean_flush(tcg_env, cpu_gpr[a->rs1]);
+-    gen_helper_fltq_s(dest, cpu_env, src1, src2);
-+    TCGv src = get_address(ctx, a->rs1, 0);
++    gen_helper_fleq_d(dest, cpu_env, src1, src2);
-+
+     gen_set_gpr(ctx, a->rd, dest);
 +    gen_helper_cbo_clean_flush(tcg_env, src);
      return true;
  }
+@@ -XXX,XX +XXX,XX @@ bool trans_fltq_d(DisasContext *ctx, arg_fltq_d *a)
- static bool trans_cbo_flush(DisasContext *ctx, arg_cbo_flush *a)
+     TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
- {
+     TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
-     REQUIRE_ZICBOM(ctx);
--    gen_helper_cbo_clean_flush(tcg_env, cpu_gpr[a->rs1]);
+-    gen_helper_fltq_s(dest, cpu_env, src1, src2);
-+    TCGv src = get_address(ctx, a->rs1, 0);
++    gen_helper_fltq_d(dest, cpu_env, src1, src2);
-+
+     gen_set_gpr(ctx, a->rd, dest);
 +    gen_helper_cbo_clean_flush(tcg_env, src);
      return true;
  }
  static bool trans_cbo_inval(DisasContext *ctx, arg_cbo_inval *a)
  {
      REQUIRE_ZICBOM(ctx);
 -    gen_helper_cbo_inval(tcg_env, cpu_gpr[a->rs1]);
 +    TCGv src = get_address(ctx, a->rs1, 0);
 +
 +    gen_helper_cbo_inval(tcg_env, src);
      return true;
  }
  static bool trans_cbo_zero(DisasContext *ctx, arg_cbo_zero *a)
  {
      REQUIRE_ZICBOZ(ctx);
 -    gen_helper_cbo_zero(tcg_env, cpu_gpr[a->rs1]);
 +    TCGv src = get_address(ctx, a->rs1, 0);
 +
 +    gen_helper_cbo_zero(tcg_env, src);
      return true;
  }
 --
-.45.1
+.41.0

-New patch
+[PULL v2 26/45] hw/intc: Fix upper/lower mtime write calculation
+From: Jason Chien <jason.chien@sifive.com>
+When writing the upper mtime, we should keep the original lower mtime
+whose value is given by cpu_riscv_read_rtc() instead of
+cpu_riscv_read_rtc_raw(). The same logic applies to writes to lower mtime.
+Signed-off-by: Jason Chien <jason.chien@sifive.com>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Message-ID: <20230728082502.26439-1-jason.chien@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ hw/intc/riscv_aclint.c | 5 +++--
+file changed, 3 insertions(+), 2 deletions(-)
+diff --git a/hw/intc/riscv_aclint.c b/hw/intc/riscv_aclint.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/intc/riscv_aclint.c
++++ b/hw/intc/riscv_aclint.c
+@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
+         return;
+     } else if (addr == mtimer->time_base || addr == mtimer->time_base + 4) {
+         uint64_t rtc_r = cpu_riscv_read_rtc_raw(mtimer->timebase_freq);
++        uint64_t rtc = cpu_riscv_read_rtc(mtimer);
+         if (addr == mtimer->time_base) {
+             if (size == 4) {
+                 /* time_lo for RV32/RV64 */
+-                mtimer->time_delta = ((rtc_r & ~0xFFFFFFFFULL) | value) - rtc_r;
++                mtimer->time_delta = ((rtc & ~0xFFFFFFFFULL) | value) - rtc_r;
+             } else {
+                 /* time for RV64 */
+                 mtimer->time_delta = value - rtc_r;
+@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
+         } else {
+             if (size == 4) {
+                 /* time_hi for RV32/RV64 */
+-                mtimer->time_delta = (value << 32 | (rtc_r & 0xFFFFFFFF)) - rtc_r;
++                mtimer->time_delta = (value << 32 | (rtc & 0xFFFFFFFF)) - rtc_r;
+             } else {
+                 qemu_log_mask(LOG_GUEST_ERROR,
+                               "aclint-mtimer: invalid time_hi write: %08x",
+--
+.41.0

-[PULL 12/28] target/riscv: Relax vector register check in RISCV gdbstub
+[PULL v2 27/45] hw/intc: Make rtc variable names consistent
 From: Jason Chien <jason.chien@sifive.com>
-In current implementation, the gdbstub allows reading vector registers
+The variables whose values are given by cpu_riscv_read_rtc() should be named
-only if V extension is supported. However, all vector extensions and
+"rtc". The variables whose value are given by cpu_riscv_read_rtc_raw()
-vector crypto extensions have the vector registers and they all depend
+should be named "rtc_r".
 on Zve32x. The gdbstub should check for Zve32x instead.
 Signed-off-by: Jason Chien <jason.chien@sifive.com>
-Reviewed-by: Frank Chang <frank.chang@sifive.com>
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: Max Chou <max.chou@sifive.com>
+Message-ID: <20230728082502.26439-2-jason.chien@sifive.com>
 Message-ID: <20240328022343.6871-4-jason.chien@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/gdbstub.c | 2 +-
+ hw/intc/riscv_aclint.c | 6 +++---
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 3 insertions(+), 3 deletions(-)
-diff --git a/target/riscv/gdbstub.c b/target/riscv/gdbstub.c
+diff --git a/hw/intc/riscv_aclint.c b/hw/intc/riscv_aclint.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/gdbstub.c
+--- a/hw/intc/riscv_aclint.c
-+++ b/target/riscv/gdbstub.c
++++ b/hw/intc/riscv_aclint.c
-@@ -XXX,XX +XXX,XX @@ void riscv_cpu_register_gdb_regs_for_features(CPUState *cs)
+@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
-                                  gdb_find_static_feature("riscv-32bit-fpu.xml"),
+     uint64_t next;
-);
+     uint64_t diff;
-     }
--    if (env->misa_ext & RVV) {
+-    uint64_t rtc_r = cpu_riscv_read_rtc(mtimer);
-+    if (cpu->cfg.ext_zve32x) {
++    uint64_t rtc = cpu_riscv_read_rtc(mtimer);
-         gdb_register_coprocessor(cs, riscv_gdb_get_vector,
-                                  riscv_gdb_set_vector,
+     /* Compute the relative hartid w.r.t the socket */
-                                  ricsv_gen_dynamic_vector_feature(cs, cs->gdb_num_regs),
+     hartid = hartid - mtimer->hartid_base;
      mtimer->timecmp[hartid] = value;
 -    if (mtimer->timecmp[hartid] <= rtc_r) {
 +    if (mtimer->timecmp[hartid] <= rtc) {
          /*
           * If we're setting an MTIMECMP value in the "past",
           * immediately raise the timer interrupt
@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
      /* otherwise, set up the future timer interrupt */
      qemu_irq_lower(mtimer->timer_irqs[hartid]);
 -    diff = mtimer->timecmp[hartid] - rtc_r;
 +    diff = mtimer->timecmp[hartid] - rtc;
      /* back to ns (note args switched in muldiv64) */
      uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq);
 --
-.45.1
+.41.0

-New patch
+[PULL v2 28/45] linux-user/riscv: Use abi type for target_ucontext
+From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+We should not use types dependend on host arch for target_ucontext.
+This bug is found when run rv32 applications.
+Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Message-ID: <20230811055438.1945-1-zhiwei_liu@linux.alibaba.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ linux-user/riscv/signal.c | 4 ++--
+file changed, 2 insertions(+), 2 deletions(-)
+diff --git a/linux-user/riscv/signal.c b/linux-user/riscv/signal.c
+index XXXXXXX..XXXXXXX 100644
+--- a/linux-user/riscv/signal.c
++++ b/linux-user/riscv/signal.c
+@@ -XXX,XX +XXX,XX @@ struct target_sigcontext {
+ }; /* cf. riscv-linux:arch/riscv/include/uapi/asm/ptrace.h */
+ struct target_ucontext {
+-    unsigned long uc_flags;
+-    struct target_ucontext *uc_link;
++    abi_ulong uc_flags;
++    abi_ptr uc_link;
+     target_stack_t uc_stack;
+     target_sigset_t uc_sigmask;
+     uint8_t   __unused[1024 / 8 - sizeof(target_sigset_t)];
+--
+.41.0

-[PULL 15/28] target/riscv: Implement dynamic establishment of custom decoder
+[PULL v2 29/45] target/riscv: support the AIA device emulation with KVM enabled
-From: Huang Tao <eric.huang@linux.alibaba.com>
+From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-In this patch, we modify the decoder to be a freely composable data
+In this patch, we create the APLIC and IMSIC FDT helper functions and
-structure instead of a hardcoded one. It can be dynamically builded up
+remove M mode AIA devices when using KVM acceleration.
 according to the extensions.
 This approach has several benefits:
 . Provides support for heterogeneous cpu architectures. As we add decoder in
    RISCVCPU, each cpu can have their own decoder, and the decoders can be
    different due to cpu's features.
 . Improve the decoding efficiency. We run the guard_func to see if the decoder
    can be added to the dynamic_decoder when building up the decoder. Therefore,
    there is no need to run the guard_func when decoding each instruction. It can
    improve the decoding efficiency
 . For vendor or dynamic cpus, it allows them to customize their own decoder
    functions to improve decoding efficiency, especially when vendor-defined
    instruction sets increase. Because of dynamic building up, it can skip the other
    decoder guard functions when decoding.
 . Pre patch for allowing adding a vendor decoder before decode_insn32() with minimal
    overhead for users that don't need this particular vendor decoder.
-Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
+Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-Suggested-by: Christoph Muellner <christoph.muellner@vrull.eu>
+Reviewed-by: Jim Shu <jim.shu@sifive.com>
-Co-authored-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Message-ID: <20230727102439.22554-2-yongxuan.wang@sifive.com>
 Message-ID: <20240506023607.29544-1-eric.huang@linux.alibaba.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu.h         |  1 +
+ hw/riscv/virt.c | 290 +++++++++++++++++++++++-------------------------
- target/riscv/tcg/tcg-cpu.h | 15 +++++++++++++++
+file changed, 137 insertions(+), 153 deletions(-)
  target/riscv/cpu.c         |  1 +
  target/riscv/tcg/tcg-cpu.c | 15 +++++++++++++++
  target/riscv/translate.c   | 31 +++++++++++++++----------------
 files changed, 47 insertions(+), 16 deletions(-)
-diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
+diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu.h
+--- a/hw/riscv/virt.c
-+++ b/target/riscv/cpu.h
++++ b/hw/riscv/virt.c
-@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
+@@ -XXX,XX +XXX,XX @@ static uint32_t imsic_num_bits(uint32_t count)
-     uint32_t pmu_avail_ctrs;
+     return ret;
-     /* Mapping of events to counters */
+ }
-     GHashTable *pmu_event_ctr_map;
-+    const GPtrArray *decoders;
+-static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
- };
+-                             uint32_t *phandle, uint32_t *intc_phandles,
+-                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
- /**
++static void create_fdt_one_imsic(RISCVVirtState *s, hwaddr base_addr,
-diff --git a/target/riscv/tcg/tcg-cpu.h b/target/riscv/tcg/tcg-cpu.h
++                                 uint32_t *intc_phandles, uint32_t msi_phandle,
-index XXXXXXX..XXXXXXX 100644
++                                 bool m_mode, uint32_t imsic_guest_bits)
---- a/target/riscv/tcg/tcg-cpu.h
+ {
-+++ b/target/riscv/tcg/tcg-cpu.h
+     int cpu, socket;
-@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp);
+     char *imsic_name;
- void riscv_tcg_cpu_finalize_features(RISCVCPU *cpu, Error **errp);
+     MachineState *ms = MACHINE(s);
- bool riscv_cpu_tcg_compatible(RISCVCPU *cpu);
+     int socket_count = riscv_socket_count(ms);
+-    uint32_t imsic_max_hart_per_socket, imsic_guest_bits;
-+struct DisasContext;
++    uint32_t imsic_max_hart_per_socket;
-+struct RISCVCPUConfig;
+     uint32_t *imsic_cells, *imsic_regs, imsic_addr, imsic_size;
-+typedef struct RISCVDecoder {
-+    bool (*guard_func)(const struct RISCVCPUConfig *);
+-    *msi_m_phandle = (*phandle)++;
-+    bool (*riscv_cpu_decode_fn)(struct DisasContext *, uint32_t);
+-    *msi_s_phandle = (*phandle)++;
-+} RISCVDecoder;
+     imsic_cells = g_new0(uint32_t, ms->smp.cpus * 2);
-+
+     imsic_regs = g_new0(uint32_t, socket_count * 4);
-+typedef bool (*riscv_cpu_decode_fn)(struct DisasContext *, uint32_t);
-+
+-    /* M-level IMSIC node */
-+extern const size_t decoder_table_size;
+     for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
-+
+         imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-+extern const RISCVDecoder decoder_table[];
+-        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
-+
++        imsic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
-+void riscv_tcg_cpu_finalize_dynamic_decoder(RISCVCPU *cpu);
+     }
-+
+-    imsic_max_hart_per_socket = 0;
- #endif
+-    for (socket = 0; socket < socket_count; socket++) {
-diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
+-        imsic_addr = memmap[VIRT_IMSIC_M].base +
-index XXXXXXX..XXXXXXX 100644
+-                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
---- a/target/riscv/cpu.c
+-        imsic_size = IMSIC_HART_SIZE(0) * s->soc[socket].num_harts;
-+++ b/target/riscv/cpu.c
+-        imsic_regs[socket * 4 + 0] = 0;
-@@ -XXX,XX +XXX,XX @@ void riscv_cpu_finalize_features(RISCVCPU *cpu, Error **errp)
+-        imsic_regs[socket * 4 + 1] = cpu_to_be32(imsic_addr);
-             error_propagate(errp, local_err);
+-        imsic_regs[socket * 4 + 2] = 0;
-             return;
+-        imsic_regs[socket * 4 + 3] = cpu_to_be32(imsic_size);
 -        if (imsic_max_hart_per_socket < s->soc[socket].num_harts) {
 -            imsic_max_hart_per_socket = s->soc[socket].num_harts;
 -        }
 -    }
 -    imsic_name = g_strdup_printf("/soc/imsics@%lx",
 -        (unsigned long)memmap[VIRT_IMSIC_M].base);
 -    qemu_fdt_add_subnode(ms->fdt, imsic_name);
 -    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
 -        "riscv,imsics");
 -    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
 -        FDT_IMSIC_INT_CELLS);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
 -        NULL, 0);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
 -        NULL, 0);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
 -        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
 -        socket_count * sizeof(uint32_t) * 4);
 -    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
 -        VIRT_IRQCHIP_NUM_MSIS);
 -    if (socket_count > 1) {
 -        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
 -            imsic_num_bits(imsic_max_hart_per_socket));
 -        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
 -            imsic_num_bits(socket_count));
 -        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
 -            IMSIC_MMIO_GROUP_MIN_SHIFT);
 -    }
 -    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_m_phandle);
 -
 -    g_free(imsic_name);
 -    /* S-level IMSIC node */
 -    for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
 -        imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
 -        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
 -    }
 -    imsic_guest_bits = imsic_num_bits(s->aia_guests + 1);
      imsic_max_hart_per_socket = 0;
      for (socket = 0; socket < socket_count; socket++) {
 -        imsic_addr = memmap[VIRT_IMSIC_S].base +
 -                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
 +        imsic_addr = base_addr + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
          imsic_size = IMSIC_HART_SIZE(imsic_guest_bits) *
                       s->soc[socket].num_harts;
          imsic_regs[socket * 4 + 0] = 0;
@@ -XXX,XX +XXX,XX @@ static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
              imsic_max_hart_per_socket = s->soc[socket].num_harts;
          }
-+        riscv_tcg_cpu_finalize_dynamic_decoder(cpu);
+     }
-     } else if (kvm_enabled()) {
+-    imsic_name = g_strdup_printf("/soc/imsics@%lx",
-         riscv_kvm_cpu_finalize_features(cpu, &local_err);
+-        (unsigned long)memmap[VIRT_IMSIC_S].base);
-         if (local_err != NULL) {
++
-diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
++    imsic_name = g_strdup_printf("/soc/imsics@%lx", (unsigned long)base_addr);
-index XXXXXXX..XXXXXXX 100644
+     qemu_fdt_add_subnode(ms->fdt, imsic_name);
---- a/target/riscv/tcg/tcg-cpu.c
+-    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
-+++ b/target/riscv/tcg/tcg-cpu.c
+-        "riscv,imsics");
-@@ -XXX,XX +XXX,XX @@ void riscv_tcg_cpu_finalize_features(RISCVCPU *cpu, Error **errp)
++    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible", "riscv,imsics");
-     }
+     qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
 -        FDT_IMSIC_INT_CELLS);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
 -        NULL, 0);
 -    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
 -        NULL, 0);
 +                          FDT_IMSIC_INT_CELLS);
 +    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller", NULL, 0);
 +    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller", NULL, 0);
      qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
 -        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
 +                     imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
      qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
 -        socket_count * sizeof(uint32_t) * 4);
 +                     socket_count * sizeof(uint32_t) * 4);
      qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
 -        VIRT_IRQCHIP_NUM_MSIS);
 +                     VIRT_IRQCHIP_NUM_MSIS);
 +
      if (imsic_guest_bits) {
          qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,guest-index-bits",
 -            imsic_guest_bits);
 +                              imsic_guest_bits);
      }
 +
      if (socket_count > 1) {
          qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
 -            imsic_num_bits(imsic_max_hart_per_socket));
 +                              imsic_num_bits(imsic_max_hart_per_socket));
          qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
 -            imsic_num_bits(socket_count));
 +                              imsic_num_bits(socket_count));
          qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
 -            IMSIC_MMIO_GROUP_MIN_SHIFT);
 +                              IMSIC_MMIO_GROUP_MIN_SHIFT);
      }
 -    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_s_phandle);
 -    g_free(imsic_name);
 +    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", msi_phandle);
 +    g_free(imsic_name);
      g_free(imsic_regs);
      g_free(imsic_cells);
  }
-+void riscv_tcg_cpu_finalize_dynamic_decoder(RISCVCPU *cpu)
+-static void create_fdt_socket_aplic(RISCVVirtState *s,
 -                                    const MemMapEntry *memmap, int socket,
 -                                    uint32_t msi_m_phandle,
 -                                    uint32_t msi_s_phandle,
 -                                    uint32_t *phandle,
 -                                    uint32_t *intc_phandles,
 -                                    uint32_t *aplic_phandles)
 +static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
 +                             uint32_t *phandle, uint32_t *intc_phandles,
 +                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
 +{
-+    GPtrArray *dynamic_decoders;
++    *msi_m_phandle = (*phandle)++;
-+    dynamic_decoders = g_ptr_array_sized_new(decoder_table_size);
++    *msi_s_phandle = (*phandle)++;
-+    for (size_t i = 0; i < decoder_table_size; ++i) {
++
-+        if (decoder_table[i].guard_func &&
++    if (!kvm_enabled()) {
-+            decoder_table[i].guard_func(&cpu->cfg)) {
++        /* M-level IMSIC node */
-+            g_ptr_array_add(dynamic_decoders,
++        create_fdt_one_imsic(s, memmap[VIRT_IMSIC_M].base, intc_phandles,
-+                            (gpointer)decoder_table[i].riscv_cpu_decode_fn);
++                             *msi_m_phandle, true, 0);
 +        }
 +    }
 +
-+    cpu->decoders = dynamic_decoders;
++    /* S-level IMSIC node */
 +    create_fdt_one_imsic(s, memmap[VIRT_IMSIC_S].base, intc_phandles,
 +                         *msi_s_phandle, false,
 +                         imsic_num_bits(s->aia_guests + 1));
 +
 +}
 +
- bool riscv_cpu_tcg_compatible(RISCVCPU *cpu)
++static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
 +                                 unsigned long aplic_addr, uint32_t aplic_size,
 +                                 uint32_t msi_phandle,
 +                                 uint32_t *intc_phandles,
 +                                 uint32_t aplic_phandle,
 +                                 uint32_t aplic_child_phandle,
 +                                 bool m_mode)
  {
-     return object_dynamic_cast(OBJECT(cpu), TYPE_RISCV_CPU_HOST) == NULL;
+     int cpu;
-diff --git a/target/riscv/translate.c b/target/riscv/translate.c
+     char *aplic_name;
-index XXXXXXX..XXXXXXX 100644
+     uint32_t *aplic_cells;
---- a/target/riscv/translate.c
+-    unsigned long aplic_addr;
-+++ b/target/riscv/translate.c
+     MachineState *ms = MACHINE(s);
-@@ -XXX,XX +XXX,XX @@
+-    uint32_t aplic_m_phandle, aplic_s_phandle;
- #include "exec/helper-info.c.inc"
- #undef  HELPER_H
+-    aplic_m_phandle = (*phandle)++;
+-    aplic_s_phandle = (*phandle)++;
-+#include "tcg/tcg-cpu.h"
+     aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2);
-+
- /* global register indices */
+-    /* M-level APLIC node */
- static TCGv cpu_gpr[32], cpu_gprh[32], cpu_pc, cpu_vl, cpu_vstart;
+     for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
- static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */
+         aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-@@ -XXX,XX +XXX,XX @@ typedef struct DisasContext {
+-        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
-     /* FRM is known to contain a valid value. */
++        aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
-     bool frm_valid;
+     }
-     bool insn_start_updated;
+-    aplic_addr = memmap[VIRT_APLIC_M].base +
-+    const GPtrArray *decoders;
+-                 (memmap[VIRT_APLIC_M].size * socket);
- } DisasContext;
++
+     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
- static inline bool has_ext(DisasContext *ctx, uint32_t ext)
+     qemu_fdt_add_subnode(ms->fdt, aplic_name);
-@@ -XXX,XX +XXX,XX @@ static inline int insn_len(uint16_t first_word)
+     qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
-     return (first_word & 3) == 3 ? 4 : 2;
+     qemu_fdt_setprop_cell(ms->fdt, aplic_name,
 -        "#interrupt-cells", FDT_APLIC_INT_CELLS);
 +                          "#interrupt-cells", FDT_APLIC_INT_CELLS);
      qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
 +
      if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
          qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
 -            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
 +                         aplic_cells,
 +                         s->soc[socket].num_harts * sizeof(uint32_t) * 2);
      } else {
 -        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
 -            msi_m_phandle);
 +        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle);
      }
 +
      qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
 -        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_M].size);
 +                           0x0, aplic_addr, 0x0, aplic_size);
      qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
 -        VIRT_IRQCHIP_NUM_SOURCES);
 -    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
 -        aplic_s_phandle);
 -    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
 -        aplic_s_phandle, 0x1, VIRT_IRQCHIP_NUM_SOURCES);
 +                          VIRT_IRQCHIP_NUM_SOURCES);
 +
 +    if (aplic_child_phandle) {
 +        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
 +                              aplic_child_phandle);
 +        qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
 +                               aplic_child_phandle, 0x1,
 +                               VIRT_IRQCHIP_NUM_SOURCES);
 +    }
 +
      riscv_socket_fdt_write_id(ms, aplic_name, socket);
 -    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_m_phandle);
 +    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_phandle);
 +
      g_free(aplic_name);
 +    g_free(aplic_cells);
 +}
 -    /* S-level APLIC node */
 -    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
 -        aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
 -        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
 +static void create_fdt_socket_aplic(RISCVVirtState *s,
 +                                    const MemMapEntry *memmap, int socket,
 +                                    uint32_t msi_m_phandle,
 +                                    uint32_t msi_s_phandle,
 +                                    uint32_t *phandle,
 +                                    uint32_t *intc_phandles,
 +                                    uint32_t *aplic_phandles)
 +{
 +    char *aplic_name;
 +    unsigned long aplic_addr;
 +    MachineState *ms = MACHINE(s);
 +    uint32_t aplic_m_phandle, aplic_s_phandle;
 +
 +    aplic_m_phandle = (*phandle)++;
 +    aplic_s_phandle = (*phandle)++;
 +
 +    if (!kvm_enabled()) {
 +        /* M-level APLIC node */
 +        aplic_addr = memmap[VIRT_APLIC_M].base +
 +                     (memmap[VIRT_APLIC_M].size * socket);
 +        create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size,
 +                             msi_m_phandle, intc_phandles,
 +                             aplic_m_phandle, aplic_s_phandle,
 +                             true);
      }
 +
 +    /* S-level APLIC node */
      aplic_addr = memmap[VIRT_APLIC_S].base +
                   (memmap[VIRT_APLIC_S].size * socket);
 +    create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size,
 +                         msi_s_phandle, intc_phandles,
 +                         aplic_s_phandle, 0,
 +                         false);
 +
      aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
 -    qemu_fdt_add_subnode(ms->fdt, aplic_name);
 -    qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
 -    qemu_fdt_setprop_cell(ms->fdt, aplic_name,
 -        "#interrupt-cells", FDT_APLIC_INT_CELLS);
 -    qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
 -    if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
 -        qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
 -            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
 -    } else {
 -        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
 -            msi_s_phandle);
 -    }
 -    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
 -        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_S].size);
 -    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
 -        VIRT_IRQCHIP_NUM_SOURCES);
 -    riscv_socket_fdt_write_id(ms, aplic_name, socket);
 -    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_s_phandle);
      if (!socket) {
          platform_bus_add_all_fdt_nodes(ms->fdt, aplic_name,
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
      g_free(aplic_name);
 -    g_free(aplic_cells);
      aplic_phandles[socket] = aplic_s_phandle;
  }
-+const RISCVDecoder decoder_table[] = {
+@@ -XXX,XX +XXX,XX @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
-+    { always_true_p, decode_insn32 },
+     int i;
-+    { has_xthead_p, decode_xthead},
+     hwaddr addr;
-+    { has_XVentanaCondOps_p, decode_XVentanaCodeOps},
+     uint32_t guest_bits;
-+};
+-    DeviceState *aplic_m;
-+
+-    bool msimode = (aia_type == VIRT_AIA_TYPE_APLIC_IMSIC) ? true : false;
-+const size_t decoder_table_size = ARRAY_SIZE(decoder_table);
++    DeviceState *aplic_s = NULL;
-+
++    DeviceState *aplic_m = NULL;
- static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode)
++    bool msimode = aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
- {
--    /*
+     if (msimode) {
--     * A table with predicate (i.e., guard) functions and decoder functions
+-        /* Per-socket M-level IMSICs */
--     * that are tested in-order until a decoder matches onto the opcode.
+-        addr = memmap[VIRT_IMSIC_M].base + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
--     */
+-        for (i = 0; i < hart_count; i++) {
--    static const struct {
+-            riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
--        bool (*guard_func)(const RISCVCPUConfig *);
+-                               base_hartid + i, true, 1,
--        bool (*decode_func)(DisasContext *, uint32_t);
+-                               VIRT_IRQCHIP_NUM_MSIS);
--    } decoders[] = {
++        if (!kvm_enabled()) {
--        { always_true_p,  decode_insn32 },
++            /* Per-socket M-level IMSICs */
--        { has_xthead_p, decode_xthead },
++            addr = memmap[VIRT_IMSIC_M].base +
--        { has_XVentanaCondOps_p,  decode_XVentanaCodeOps },
++                   socket * VIRT_IMSIC_GROUP_MAX_SIZE;
--    };
++            for (i = 0; i < hart_count; i++) {
 +                riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
 +                                   base_hartid + i, true, 1,
 +                                   VIRT_IRQCHIP_NUM_MSIS);
 +            }
          }
          /* Per-socket S-level IMSICs */
@@ -XXX,XX +XXX,XX @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
          }
      }
 -    /* Per-socket M-level APLIC */
 -    aplic_m = riscv_aplic_create(
 -        memmap[VIRT_APLIC_M].base + socket * memmap[VIRT_APLIC_M].size,
 -        memmap[VIRT_APLIC_M].size,
 -        (msimode) ? 0 : base_hartid,
 -        (msimode) ? 0 : hart_count,
 -        VIRT_IRQCHIP_NUM_SOURCES,
 -        VIRT_IRQCHIP_NUM_PRIO_BITS,
 -        msimode, true, NULL);
 -
-     ctx->virt_inst_excp = false;
+-    if (aplic_m) {
-     ctx->cur_insn_len = insn_len(opcode);
+-        /* Per-socket S-level APLIC */
-     /* Check for compressed insn */
+-        riscv_aplic_create(
-@@ -XXX,XX +XXX,XX @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode)
+-            memmap[VIRT_APLIC_S].base + socket * memmap[VIRT_APLIC_S].size,
-                                              ctx->base.pc_next + 2));
+-            memmap[VIRT_APLIC_S].size,
-         ctx->opcode = opcode32;
+-            (msimode) ? 0 : base_hartid,
+-            (msimode) ? 0 : hart_count,
--        for (size_t i = 0; i < ARRAY_SIZE(decoders); ++i) {
+-            VIRT_IRQCHIP_NUM_SOURCES,
--            if (decoders[i].guard_func(ctx->cfg_ptr) &&
+-            VIRT_IRQCHIP_NUM_PRIO_BITS,
--                decoders[i].decode_func(ctx, opcode32)) {
+-            msimode, false, aplic_m);
-+        for (guint i = 0; i < ctx->decoders->len; ++i) {
++    if (!kvm_enabled()) {
-+            riscv_cpu_decode_fn func = g_ptr_array_index(ctx->decoders, i);
++        /* Per-socket M-level APLIC */
-+            if (func(ctx, opcode32)) {
++        aplic_m = riscv_aplic_create(memmap[VIRT_APLIC_M].base +
-                 return;
++                                     socket * memmap[VIRT_APLIC_M].size,
-             }
++                                     memmap[VIRT_APLIC_M].size,
-         }
++                                     (msimode) ? 0 : base_hartid,
-@@ -XXX,XX +XXX,XX @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
++                                     (msimode) ? 0 : hart_count,
-     ctx->itrigger = FIELD_EX32(tb_flags, TB_FLAGS, ITRIGGER);
++                                     VIRT_IRQCHIP_NUM_SOURCES,
-     ctx->zero = tcg_constant_tl(0);
++                                     VIRT_IRQCHIP_NUM_PRIO_BITS,
-     ctx->virt_inst_excp = false;
++                                     msimode, true, NULL);
-+    ctx->decoders = cpu->decoders;
+     }
 -    return aplic_m;
 +    /* Per-socket S-level APLIC */
 +    aplic_s = riscv_aplic_create(memmap[VIRT_APLIC_S].base +
 +                                 socket * memmap[VIRT_APLIC_S].size,
 +                                 memmap[VIRT_APLIC_S].size,
 +                                 (msimode) ? 0 : base_hartid,
 +                                 (msimode) ? 0 : hart_count,
 +                                 VIRT_IRQCHIP_NUM_SOURCES,
 +                                 VIRT_IRQCHIP_NUM_PRIO_BITS,
 +                                 msimode, false, aplic_m);
 +
 +    return kvm_enabled() ? aplic_s : aplic_m;
  }
- static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu)
+ static void create_platform_bus(RISCVVirtState *s, DeviceState *irqchip)
 --
-.45.1
+.41.0

-New patch
+[PULL v2 30/45] target/riscv: check the in-kernel irqchip support
+From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
+We check the in-kernel irqchip support when using KVM acceleration.
+Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
+Reviewed-by: Jim Shu <jim.shu@sifive.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
+Message-ID: <20230727102439.22554-3-yongxuan.wang@sifive.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/kvm.c | 10 +++++++++-
+file changed, 9 insertions(+), 1 deletion(-)
+diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/kvm.c
++++ b/target/riscv/kvm.c
+@@ -XXX,XX +XXX,XX @@ int kvm_arch_init(MachineState *ms, KVMState *s)
+ int kvm_arch_irqchip_create(KVMState *s)
+ {
+-    return 0;
++    if (kvm_kernel_irqchip_split()) {
++        error_report("-machine kernel_irqchip=split is not supported on RISC-V.");
++        exit(1);
++    }
++
++    /*
++     * We can create the VAIA using the newer device control API.
++     */
++    return kvm_check_extension(s, KVM_CAP_DEVICE_CTRL);
+ }
+ int kvm_arch_process_async_events(CPUState *cs)
+--
+.41.0

-[PULL 04/28] target/riscv/kvm: implement SBI debug console (DBCN) calls
+[PULL v2 31/45] target/riscv: Create an KVM AIA irqchip
-From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-SBI defines a Debug Console extension "DBCN" that will, in time, replace
+We create a vAIA chip by using the KVM_DEV_TYPE_RISCV_AIA and then set up
-the legacy console putchar and getchar SBI extensions.
+the chip with the KVM_DEV_RISCV_AIA_GRP_* APIs.
 We also extend KVM accelerator to specify the KVM AIA mode. The "riscv-aia"
 parameter is passed along with --accel in QEMU command-line.
 ) "riscv-aia=emul": IMSIC is emulated by hypervisor
 ) "riscv-aia=hwaccel": use hardware guest IMSIC
 ) "riscv-aia=auto": use the hardware guest IMSICs whenever available
                      otherwise we fallback to software emulation.
-The appeal of the DBCN extension is that it allows multiple bytes to be
+Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-read/written in the SBI console in a single SBI call.
+Reviewed-by: Jim Shu <jim.shu@sifive.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 As far as KVM goes, the DBCN calls are forwarded by an in-kernel KVM
 module to userspace. But this will only happens if the KVM module
 actually supports this SBI extension and we activate it.
 We'll check for DBCN support during init time, checking if get-reg-list
 is advertising KVM_RISCV_SBI_EXT_DBCN. In that case, we'll enable it via
 kvm_set_one_reg() during kvm_arch_init_vcpu().
 Finally, change kvm_riscv_handle_sbi() to handle the incoming calls for
 SBI_EXT_DBCN, reading and writing as required.
 A simple KVM guest with 'earlycon=sbi', running in an emulated RISC-V
 host, takes around 20 seconds to boot without using DBCN. With this
 patch we're taking around 14 seconds to boot due to the speed-up in the
 terminal output.  There's no change in boot time if the guest isn't
 using earlycon.
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Message-ID: <20240425155012.581366-1-dbarboza@ventanamicro.com>
+Message-ID: <20230727102439.22554-4-yongxuan.wang@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/sbi_ecall_interface.h |  17 +++++
+ target/riscv/kvm_riscv.h |   4 +
- target/riscv/kvm/kvm-cpu.c         | 111 +++++++++++++++++++++++++++++
+ target/riscv/kvm.c       | 186 +++++++++++++++++++++++++++++++++++++++
-files changed, 128 insertions(+)
+files changed, 190 insertions(+)
-diff --git a/target/riscv/sbi_ecall_interface.h b/target/riscv/sbi_ecall_interface.h
+diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/sbi_ecall_interface.h
+--- a/target/riscv/kvm_riscv.h
-+++ b/target/riscv/sbi_ecall_interface.h
++++ b/target/riscv/kvm_riscv.h
 @@ -XXX,XX +XXX,XX @@
+ void kvm_riscv_init_user_properties(Object *cpu_obj);
- /* clang-format off */
+ void kvm_riscv_reset_vcpu(RISCVCPU *cpu);
+ void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level);
-+#define SBI_SUCCESS                      0
++void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
-+#define SBI_ERR_FAILED                  -1
++                          uint64_t aia_irq_num, uint64_t aia_msi_num,
-+#define SBI_ERR_NOT_SUPPORTED           -2
++                          uint64_t aplic_base, uint64_t imsic_base,
-+#define SBI_ERR_INVALID_PARAM           -3
++                          uint64_t guest_num);
-+#define SBI_ERR_DENIED                  -4
-+#define SBI_ERR_INVALID_ADDRESS         -5
+ #endif
-+#define SBI_ERR_ALREADY_AVAILABLE       -6
+diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
-+#define SBI_ERR_ALREADY_STARTED         -7
+index XXXXXXX..XXXXXXX 100644
-+#define SBI_ERR_ALREADY_STOPPED         -8
+--- a/target/riscv/kvm.c
-+#define SBI_ERR_NO_SHMEM                -9
++++ b/target/riscv/kvm.c
 +
  /* SBI Extension IDs */
  #define SBI_EXT_0_1_SET_TIMER           0x0
  #define SBI_EXT_0_1_CONSOLE_PUTCHAR     0x1
 @@ -XXX,XX +XXX,XX @@
- #define SBI_EXT_IPI                     0x735049
+ #include "exec/address-spaces.h"
- #define SBI_EXT_RFENCE                  0x52464E43
+ #include "hw/boards.h"
- #define SBI_EXT_HSM                     0x48534D
+ #include "hw/irq.h"
-+#define SBI_EXT_DBCN                    0x4442434E
++#include "hw/intc/riscv_imsic.h"
+ #include "qemu/log.h"
- /* SBI function IDs for BASE extension */
+ #include "hw/loader.h"
- #define SBI_EXT_BASE_GET_SPEC_VERSION   0x0
+ #include "kvm_riscv.h"
 @@ -XXX,XX +XXX,XX @@
- #define SBI_EXT_HSM_HART_STOP           0x1
+ #include "chardev/char-fe.h"
- #define SBI_EXT_HSM_HART_GET_STATUS     0x2
+ #include "migration/migration.h"
+ #include "sysemu/runstate.h"
-+/* SBI function IDs for DBCN extension */
++#include "hw/riscv/numa.h"
-+#define SBI_EXT_DBCN_CONSOLE_WRITE      0x0
-+#define SBI_EXT_DBCN_CONSOLE_READ       0x1
+ static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type,
-+#define SBI_EXT_DBCN_CONSOLE_WRITE_BYTE 0x2
+                                  uint64_t idx)
-+
+@@ -XXX,XX +XXX,XX @@ bool kvm_arch_cpu_check_are_resettable(void)
  #define SBI_HSM_HART_STATUS_STARTED     0x0
  #define SBI_HSM_HART_STATUS_STOPPED     0x1
  #define SBI_HSM_HART_STATUS_START_PENDING   0x2
 diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/kvm/kvm-cpu.c
 +++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ static KVMCPUConfig kvm_v_vlenb = {
                     KVM_REG_RISCV_VECTOR_CSR_REG(vlenb)
  };
 +static KVMCPUConfig kvm_sbi_dbcn = {
 +    .name = "sbi_dbcn",
 +    .kvm_reg_id = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
 +                  KVM_REG_RISCV_SBI_EXT | KVM_RISCV_SBI_EXT_DBCN
 +};
 +
  static void kvm_riscv_update_cpu_cfg_isa_ext(RISCVCPU *cpu, CPUState *cs)
  {
      CPURISCVState *env = &cpu->env;
@@ -XXX,XX +XXX,XX @@ static int uint64_cmp(const void *a, const void *b)
      return 0;
  }
 +static void kvm_riscv_check_sbi_dbcn_support(RISCVCPU *cpu,
 +                                             KVMScratchCPU *kvmcpu,
 +                                             struct kvm_reg_list *reglist)
 +{
 +    struct kvm_reg_list *reg_search;
 +
 +    reg_search = bsearch(&kvm_sbi_dbcn.kvm_reg_id, reglist->reg, reglist->n,
 +                         sizeof(uint64_t), uint64_cmp);
 +
 +    if (reg_search) {
 +        kvm_sbi_dbcn.supported = true;
 +    }
 +}
 +
  static void kvm_riscv_read_vlenb(RISCVCPU *cpu, KVMScratchCPU *kvmcpu,
                                   struct kvm_reg_list *reglist)
  {
@@ -XXX,XX +XXX,XX @@ static void kvm_riscv_init_multiext_cfg(RISCVCPU *cpu, KVMScratchCPU *kvmcpu)
      if (riscv_has_ext(&cpu->env, RVV)) {
          kvm_riscv_read_vlenb(cpu, kvmcpu, reglist);
      }
 +
 +    kvm_riscv_check_sbi_dbcn_support(cpu, kvmcpu, reglist);
  }
  static void riscv_init_kvm_registers(Object *cpu_obj)
@@ -XXX,XX +XXX,XX @@ static int kvm_vcpu_set_machine_ids(RISCVCPU *cpu, CPUState *cs)
      return ret;
  }
 +static int kvm_vcpu_enable_sbi_dbcn(RISCVCPU *cpu, CPUState *cs)
 +{
 +    target_ulong reg = 1;
 +
 +    if (!kvm_sbi_dbcn.supported) {
 +        return 0;
 +    }
 +
 +    return kvm_set_one_reg(cs, kvm_sbi_dbcn.kvm_reg_id, &reg);
 +}
 +
  int kvm_arch_init_vcpu(CPUState *cs)
  {
      int ret = 0;
@@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs)
      kvm_riscv_update_cpu_misa_ext(cpu, cs);
      kvm_riscv_update_cpu_cfg_isa_ext(cpu, cs);
 +    ret = kvm_vcpu_enable_sbi_dbcn(cpu, cs);
 +
      return ret;
  }
@@ -XXX,XX +XXX,XX @@ bool kvm_arch_stop_on_emulation_error(CPUState *cs)
      return true;
  }
-+static void kvm_riscv_handle_sbi_dbcn(CPUState *cs, struct kvm_run *run)
++static int aia_mode;
-+{
++
-+    g_autofree uint8_t *buf = NULL;
++static const char *kvm_aia_mode_str(uint64_t mode)
-+    RISCVCPU *cpu = RISCV_CPU(cs);
++{
-+    target_ulong num_bytes;
++    switch (mode) {
-+    uint64_t addr;
++    case KVM_DEV_RISCV_AIA_MODE_EMUL:
-+    unsigned char ch;
++        return "emul";
-+    int ret;
++    case KVM_DEV_RISCV_AIA_MODE_HWACCEL:
-+
++        return "hwaccel";
-+    switch (run->riscv_sbi.function_id) {
++    case KVM_DEV_RISCV_AIA_MODE_AUTO:
-+    case SBI_EXT_DBCN_CONSOLE_READ:
++    default:
-+    case SBI_EXT_DBCN_CONSOLE_WRITE:
++        return "auto";
-+        num_bytes = run->riscv_sbi.args[0];
++    };
-+
++}
-+        if (num_bytes == 0) {
++
-+            run->riscv_sbi.ret[0] = SBI_SUCCESS;
++static char *riscv_get_kvm_aia(Object *obj, Error **errp)
-+            run->riscv_sbi.ret[1] = 0;
++{
-+            break;
++    return g_strdup(kvm_aia_mode_str(aia_mode));
 +}
 +
 +static void riscv_set_kvm_aia(Object *obj, const char *val, Error **errp)
 +{
 +    if (!strcmp(val, "emul")) {
 +        aia_mode = KVM_DEV_RISCV_AIA_MODE_EMUL;
 +    } else if (!strcmp(val, "hwaccel")) {
 +        aia_mode = KVM_DEV_RISCV_AIA_MODE_HWACCEL;
 +    } else if (!strcmp(val, "auto")) {
 +        aia_mode = KVM_DEV_RISCV_AIA_MODE_AUTO;
 +    } else {
 +        error_setg(errp, "Invalid KVM AIA mode");
 +        error_append_hint(errp, "Valid values are emul, hwaccel, and auto.\n");
 +    }
 +}
 +
  void kvm_arch_accel_class_init(ObjectClass *oc)
  {
 +    object_class_property_add_str(oc, "riscv-aia", riscv_get_kvm_aia,
 +                                  riscv_set_kvm_aia);
 +    object_class_property_set_description(oc, "riscv-aia",
 +                                          "Set KVM AIA mode. Valid values are "
 +                                          "emul, hwaccel, and auto. Default "
 +                                          "is auto.");
 +    object_property_set_default_str(object_class_property_find(oc, "riscv-aia"),
 +                                    "auto");
 +}
 +
 +void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
 +                          uint64_t aia_irq_num, uint64_t aia_msi_num,
 +                          uint64_t aplic_base, uint64_t imsic_base,
 +                          uint64_t guest_num)
 +{
 +    int ret, i;
 +    int aia_fd = -1;
 +    uint64_t default_aia_mode;
 +    uint64_t socket_count = riscv_socket_count(machine);
 +    uint64_t max_hart_per_socket = 0;
 +    uint64_t socket, base_hart, hart_count, socket_imsic_base, imsic_addr;
 +    uint64_t socket_bits, hart_bits, guest_bits;
 +
 +    aia_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_RISCV_AIA, false);
 +
 +    if (aia_fd < 0) {
 +        error_report("Unable to create in-kernel irqchip");
 +        exit(1);
 +    }
 +
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_MODE,
 +                            &default_aia_mode, false, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to get current KVM AIA mode");
 +        exit(1);
 +    }
 +    qemu_log("KVM AIA: default mode is %s\n",
 +             kvm_aia_mode_str(default_aia_mode));
 +
 +    if (default_aia_mode != aia_mode) {
 +        ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                                KVM_DEV_RISCV_AIA_CONFIG_MODE,
 +                                &aia_mode, true, NULL);
 +        if (ret < 0)
 +            warn_report("KVM AIA: failed to set KVM AIA mode");
 +        else
 +            qemu_log("KVM AIA: set current mode to %s\n",
 +                     kvm_aia_mode_str(aia_mode));
 +    }
 +
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_SRCS,
 +                            &aia_irq_num, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set number of input irq lines");
 +        exit(1);
 +    }
 +
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_IDS,
 +                            &aia_msi_num, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set number of msi");
 +        exit(1);
 +    }
 +
 +    socket_bits = find_last_bit(&socket_count, BITS_PER_LONG) + 1;
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS,
 +                            &socket_bits, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set group_bits");
 +        exit(1);
 +    }
 +
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT,
 +                            &group_shift, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set group_shift");
 +        exit(1);
 +    }
 +
 +    guest_bits = guest_num == 0 ? 0 :
 +                 find_last_bit(&guest_num, BITS_PER_LONG) + 1;
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
 +                            KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS,
 +                            &guest_bits, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set guest_bits");
 +        exit(1);
 +    }
 +
 +    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR,
 +                            KVM_DEV_RISCV_AIA_ADDR_APLIC,
 +                            &aplic_base, true, NULL);
 +    if (ret < 0) {
 +        error_report("KVM AIA: failed to set the base address of APLIC");
 +        exit(1);
 +    }
 +
 +    for (socket = 0; socket < socket_count; socket++) {
 +        socket_imsic_base = imsic_base + socket * (1U << group_shift);
 +        hart_count = riscv_socket_hart_count(machine, socket);
 +        base_hart = riscv_socket_first_hartid(machine, socket);
 +
 +        if (max_hart_per_socket < hart_count) {
 +            max_hart_per_socket = hart_count;
 +        }
 +
-+        addr = run->riscv_sbi.args[1];
++        for (i = 0; i < hart_count; i++) {
-+
++            imsic_addr = socket_imsic_base + i * IMSIC_HART_SIZE(guest_bits);
-+        /*
++            ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR,
-+         * Handle the case where a 32 bit CPU is running in a
++                                    KVM_DEV_RISCV_AIA_ADDR_IMSIC(i + base_hart),
-+         * 64 bit addressing env.
++                                    &imsic_addr, true, NULL);
 +         */
 +        if (riscv_cpu_mxl(&cpu->env) == MXL_RV32) {
 +            addr |= (uint64_t)run->riscv_sbi.args[2] << 32;
 +        }
 +
 +        buf = g_malloc0(num_bytes);
 +
 +        if (run->riscv_sbi.function_id == SBI_EXT_DBCN_CONSOLE_READ) {
 +            ret = qemu_chr_fe_read_all(serial_hd(0)->be, buf, num_bytes);
 +            if (ret < 0) {
-+                error_report("SBI_EXT_DBCN_CONSOLE_READ: error when "
++                error_report("KVM AIA: failed to set the IMSIC address for hart %d", i);
 +                             "reading chardev");
 +                exit(1);
 +            }
 +
 +            cpu_physical_memory_write(addr, buf, ret);
 +        } else {
 +            cpu_physical_memory_read(addr, buf, num_bytes);
 +
 +            ret = qemu_chr_fe_write_all(serial_hd(0)->be, buf, num_bytes);
 +            if (ret < 0) {
 +                error_report("SBI_EXT_DBCN_CONSOLE_WRITE: error when "
 +                             "writing chardev");
 +                exit(1);
 +            }
 +        }
-+
++    }
-+        run->riscv_sbi.ret[0] = SBI_SUCCESS;
++
-+        run->riscv_sbi.ret[1] = ret;
++    hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
-+        break;
++    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
-+    case SBI_EXT_DBCN_CONSOLE_WRITE_BYTE:
++                            KVM_DEV_RISCV_AIA_CONFIG_HART_BITS,
-+        ch = run->riscv_sbi.args[0];
++                            &hart_bits, true, NULL);
-+        ret = qemu_chr_fe_write(serial_hd(0)->be, &ch, sizeof(ch));
++    if (ret < 0) {
-+
++        error_report("KVM AIA: failed to set hart_bits");
-+        if (ret < 0) {
++        exit(1);
-+            error_report("SBI_EXT_DBCN_CONSOLE_WRITE_BYTE: error when "
++    }
-+                         "writing chardev");
++
-+            exit(1);
++    if (kvm_has_gsi_routing()) {
 +        for (uint64_t idx = 0; idx < aia_irq_num + 1; ++idx) {
 +            /* KVM AIA only has one APLIC instance */
 +            kvm_irqchip_add_irq_route(kvm_state, idx, 0, idx);
 +        }
-+
++        kvm_gsi_routing_allowed = true;
-+        run->riscv_sbi.ret[0] = SBI_SUCCESS;
++        kvm_irqchip_commit_routes(kvm_state);
-+        run->riscv_sbi.ret[1] = 0;
++    }
-+        break;
++
-+    default:
++    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CTRL,
-+        run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED;
++                            KVM_DEV_RISCV_AIA_CTRL_INIT,
-+    }
++                            NULL, true, NULL);
-+}
++    if (ret < 0) {
-+
++        error_report("KVM AIA: initialized fail");
- static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
++        exit(1);
- {
++    }
-     int ret = 0;
++
-@@ -XXX,XX +XXX,XX @@ static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
++    kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled();
-         }
+ }
          ret = 0;
          break;
 +    case SBI_EXT_DBCN:
 +        kvm_riscv_handle_sbi_dbcn(cs, run);
 +        break;
      default:
          qemu_log_mask(LOG_UNIMP,
                        "%s: un-handled SBI EXIT, specific reasons is %lu\n",
 --
-.45.1
+.41.0

-[PULL 01/28] hw/intc/riscv_aplic: APLICs should add child earlier than realize
+[PULL v2 32/45] target/riscv: update APLIC and IMSIC to support KVM AIA
-From: "yang.zhang" <yang.zhang@hexintek.com>
+From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-Since only root APLICs can have hw IRQ lines, aplic->parent should
+KVM AIA can't emulate APLIC only. When "aia=aplic" parameter is passed,
-be initialized first.
+APLIC devices is emulated by QEMU. For "aia=aplic-imsic", remove the
 mmio operations of APLIC when using KVM AIA and send wired interrupt
 signal via KVM_IRQ_LINE API.
 After KVM AIA enabled, MSI messages are delivered by KVM_SIGNAL_MSI API
 when the IMSICs receive mmio write requests.
-Fixes: e8f79343cf ("hw/intc: Add RISC-V AIA APLIC device emulation")
+Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
 Reviewed-by: Jim Shu <jim.shu@sifive.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Signed-off-by: yang.zhang <yang.zhang@hexintek.com>
+Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-ID: <20230727102439.22554-5-yongxuan.wang@sifive.com>
 Message-ID: <20240409014445.278-1-gaoshanliukou@163.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- hw/intc/riscv_aplic.c | 8 ++++----
+ hw/intc/riscv_aplic.c | 56 ++++++++++++++++++++++++++++++-------------
-file changed, 4 insertions(+), 4 deletions(-)
+ hw/intc/riscv_imsic.c | 25 +++++++++++++++----
 files changed, 61 insertions(+), 20 deletions(-)
 diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
 index XXXXXXX..XXXXXXX 100644
 --- a/hw/intc/riscv_aplic.c
 +++ b/hw/intc/riscv_aplic.c
+@@ -XXX,XX +XXX,XX @@
+ #include "hw/irq.h"
+ #include "target/riscv/cpu.h"
+ #include "sysemu/sysemu.h"
++#include "sysemu/kvm.h"
+ #include "migration/vmstate.h"
+ #define APLIC_MAX_IDC                  (1UL << 14)
+@@ -XXX,XX +XXX,XX @@
+ #define APLIC_IDC_CLAIMI               0x1c
++/*
++ * KVM AIA only supports APLIC MSI, fallback to QEMU emulation if we want to use
++ * APLIC Wired.
++ */
++static bool is_kvm_aia(bool msimode)
++{
++    return kvm_irqchip_in_kernel() && msimode;
++}
++
+ static uint32_t riscv_aplic_read_input_word(RISCVAPLICState *aplic,
+                                             uint32_t word)
+ {
+@@ -XXX,XX +XXX,XX @@ static uint32_t riscv_aplic_idc_claimi(RISCVAPLICState *aplic, uint32_t idc)
+     return topi;
+ }
++static void riscv_kvm_aplic_request(void *opaque, int irq, int level)
++{
++    kvm_set_irq(kvm_state, irq, !!level);
++}
++
+ static void riscv_aplic_request(void *opaque, int irq, int level)
+ {
+     bool update = false;
+@@ -XXX,XX +XXX,XX @@ static void riscv_aplic_realize(DeviceState *dev, Error **errp)
+     uint32_t i;
+     RISCVAPLICState *aplic = RISCV_APLIC(dev);
+-    aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
+-    aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
+-    aplic->state = g_new0(uint32_t, aplic->num_irqs);
+-    aplic->target = g_new0(uint32_t, aplic->num_irqs);
+-    if (!aplic->msimode) {
+-        for (i = 0; i < aplic->num_irqs; i++) {
+-            aplic->target[i] = 1;
++    if (!is_kvm_aia(aplic->msimode)) {
++        aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
++        aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
++        aplic->state = g_new0(uint32_t, aplic->num_irqs);
++        aplic->target = g_new0(uint32_t, aplic->num_irqs);
++        if (!aplic->msimode) {
++            for (i = 0; i < aplic->num_irqs; i++) {
++                aplic->target[i] = 1;
++            }
+         }
+-    }
+-    aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
+-    aplic->iforce = g_new0(uint32_t, aplic->num_harts);
+-    aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
++        aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
++        aplic->iforce = g_new0(uint32_t, aplic->num_harts);
++        aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
+-    memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops, aplic,
+-                          TYPE_RISCV_APLIC, aplic->aperture_size);
+-    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
++        memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops,
++                              aplic, TYPE_RISCV_APLIC, aplic->aperture_size);
++        sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
++    }
+     /*
+      * Only root APLICs have hardware IRQ lines. All non-root APLICs
+      * have IRQ lines delegated by their parent APLIC.
+      */
+     if (!aplic->parent) {
+-        qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
++        if (is_kvm_aia(aplic->msimode)) {
++            qdev_init_gpio_in(dev, riscv_kvm_aplic_request, aplic->num_irqs);
++        } else {
++            qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
++        }
+     }
+     /* Create output IRQ lines for non-MSI mode */
 @@ -XXX,XX +XXX,XX @@ DeviceState *riscv_aplic_create(hwaddr addr, hwaddr size,
-     qdev_prop_set_bit(dev, "msimode", msimode);
      qdev_prop_set_bit(dev, "mmode", mmode);
-+    if (parent) {
+     sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
-+        riscv_aplic_add_child(parent, dev);
+-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
 +
 +    if (!is_kvm_aia(msimode)) {
 +        sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
 +    }
+     if (parent) {
+         riscv_aplic_add_child(parent, dev);
+diff --git a/hw/intc/riscv_imsic.c b/hw/intc/riscv_imsic.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/intc/riscv_imsic.c
++++ b/hw/intc/riscv_imsic.c
+@@ -XXX,XX +XXX,XX @@
+ #include "target/riscv/cpu.h"
+ #include "target/riscv/cpu_bits.h"
+ #include "sysemu/sysemu.h"
++#include "sysemu/kvm.h"
+ #include "migration/vmstate.h"
+ #define IMSIC_MMIO_PAGE_LE             0x00
+@@ -XXX,XX +XXX,XX @@ static void riscv_imsic_write(void *opaque, hwaddr addr, uint64_t value,
+         goto err;
+     }
++#if defined(CONFIG_KVM)
++    if (kvm_irqchip_in_kernel()) {
++        struct kvm_msi msi;
 +
-     sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
++        msi.address_lo = extract64(imsic->mmio.addr + addr, 0, 32);
++        msi.address_hi = extract64(imsic->mmio.addr + addr, 32, 32);
-     if (!is_kvm_aia(msimode)) {
++        msi.data = le32_to_cpu(value);
-         sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
++
-     }
++        kvm_vm_ioctl(kvm_state, KVM_SIGNAL_MSI, &msi);
++
--    if (parent) {
++        return;
--        riscv_aplic_add_child(parent, dev);
++    }
--    }
++#endif
--
++
-     if (!msimode) {
+     /* Writes only supported for MSI little-endian registers */
-         for (i = 0; i < num_harts; i++) {
+     page = addr >> IMSIC_MMIO_PAGE_SHIFT;
-             CPUState *cpu = cpu_by_arch_id(hartid_base + i);
+     if ((addr & (IMSIC_MMIO_PAGE_SZ - 1)) == IMSIC_MMIO_PAGE_LE) {
@@ -XXX,XX +XXX,XX @@ static void riscv_imsic_realize(DeviceState *dev, Error **errp)
      CPUState *cpu = cpu_by_arch_id(imsic->hartid);
      CPURISCVState *env = cpu ? cpu->env_ptr : NULL;
 -    imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
 -    imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
 -    imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
 -    imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
 +    if (!kvm_irqchip_in_kernel()) {
 +        imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
 +        imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
 +        imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
 +        imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
 +    }
      memory_region_init_io(&imsic->mmio, OBJECT(dev), &riscv_imsic_ops,
                            imsic, TYPE_RISCV_IMSIC,
 --
-.45.1
+.41.0

-[PULL 25/28] target/riscv/kvm.c: Fix the hart bit setting of AIA
+[PULL v2 33/45] target/riscv: select KVM AIA in riscv virt machine
 From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
-In AIA spec, each hart (or each hart within a group) has a unique hart
+Select KVM AIA when the host kernel has in-kernel AIA chip support.
-number to locate the memory pages of interrupt files in the address
+Since KVM AIA only has one APLIC instance, we map the QEMU APLIC
-space. The number of bits required to represent any hart number is equal
+devices to KVM APLIC.
 to ceil(log2(hmax + 1)), where hmax is the largest hart number among
 groups.
 However, if the largest hart number among groups is a power of 2, QEMU
 will pass an inaccurate hart-index-bit setting to Linux. For example, when
 the guest OS has 4 harts, only ceil(log2(3 + 1)) = 2 bits are sufficient
 to represent 4 harts, but we passes 3 to Linux. The code needs to be
 updated to ensure accurate hart-index-bit settings.
 Additionally, a Linux patch[1] is necessary to correctly recover the hart
 index when the guest OS has only 1 hart, where the hart-index-bit is 0.
 [1] https://lore.kernel.org/lkml/20240415064905.25184-1-yongxuan.wang@sifive.com/t/
 Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
+Reviewed-by: Jim Shu <jim.shu@sifive.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-ID: <20230727102439.22554-6-yongxuan.wang@sifive.com>
 Message-ID: <20240515091129.28116-1-yongxuan.wang@sifive.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/kvm/kvm-cpu.c | 9 ++++++++-
+ hw/riscv/virt.c | 94 +++++++++++++++++++++++++++++++++----------------
-file changed, 8 insertions(+), 1 deletion(-)
+file changed, 63 insertions(+), 31 deletions(-)
-diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
+diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/kvm/kvm-cpu.c
+--- a/hw/riscv/virt.c
-+++ b/target/riscv/kvm/kvm-cpu.c
++++ b/hw/riscv/virt.c
-@@ -XXX,XX +XXX,XX @@ void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
+@@ -XXX,XX +XXX,XX @@
  #include "hw/riscv/virt.h"
  #include "hw/riscv/boot.h"
  #include "hw/riscv/numa.h"
 +#include "kvm_riscv.h"
  #include "hw/intc/riscv_aclint.h"
  #include "hw/intc/riscv_aplic.h"
  #include "hw/intc/riscv_imsic.h"
@@ -XXX,XX +XXX,XX @@
  #error "Can't accommodate all IMSIC groups in address space"
  #endif
 +/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */
 +static bool virt_use_kvm_aia(RISCVVirtState *s)
 +{
 +    return kvm_irqchip_in_kernel() && s->aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
 +}
 +
  static const MemMapEntry virt_memmap[] = {
      [VIRT_DEBUG] =        {        0x0,         0x100 },
      [VIRT_MROM] =         {     0x1000,        0xf000 },
@@ -XXX,XX +XXX,XX @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
                                   uint32_t *intc_phandles,
                                   uint32_t aplic_phandle,
                                   uint32_t aplic_child_phandle,
 -                                 bool m_mode)
 +                                 bool m_mode, int num_harts)
  {
      int cpu;
      char *aplic_name;
      uint32_t *aplic_cells;
      MachineState *ms = MACHINE(s);
 -    aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2);
 +    aplic_cells = g_new0(uint32_t, num_harts * 2);
 -    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
 +    for (cpu = 0; cpu < num_harts; cpu++) {
          aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
          aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
      }
@@ -XXX,XX +XXX,XX @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
      if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
          qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
 -                         aplic_cells,
 -                         s->soc[socket].num_harts * sizeof(uint32_t) * 2);
 +                         aplic_cells, num_harts * sizeof(uint32_t) * 2);
      } else {
          qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle);
      }
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
                                      uint32_t msi_s_phandle,
                                      uint32_t *phandle,
                                      uint32_t *intc_phandles,
 -                                    uint32_t *aplic_phandles)
 +                                    uint32_t *aplic_phandles,
 +                                    int num_harts)
  {
      char *aplic_name;
      unsigned long aplic_addr;
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
          create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size,
                               msi_m_phandle, intc_phandles,
                               aplic_m_phandle, aplic_s_phandle,
 -                             true);
 +                             true, num_harts);
      }
      /* S-level APLIC node */
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
      create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size,
                           msi_s_phandle, intc_phandles,
                           aplic_s_phandle, 0,
 -                         false);
 +                         false, num_harts);
      aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
          *msi_pcie_phandle = msi_s_phandle;
      }
 -    phandle_pos = ms->smp.cpus;
 -    for (socket = (socket_count - 1); socket >= 0; socket--) {
 -        phandle_pos -= s->soc[socket].num_harts;
 -
 -        if (s->aia_type == VIRT_AIA_TYPE_NONE) {
 -            create_fdt_socket_plic(s, memmap, socket, phandle,
 -                &intc_phandles[phandle_pos], xplic_phandles);
 -        } else {
 -            create_fdt_socket_aplic(s, memmap, socket,
 -                msi_m_phandle, msi_s_phandle, phandle,
 -                &intc_phandles[phandle_pos], xplic_phandles);
 +    /* KVM AIA only has one APLIC instance */
 +    if (virt_use_kvm_aia(s)) {
 +        create_fdt_socket_aplic(s, memmap, 0,
 +                                msi_m_phandle, msi_s_phandle, phandle,
 +                                &intc_phandles[0], xplic_phandles,
 +                                ms->smp.cpus);
 +    } else {
 +        phandle_pos = ms->smp.cpus;
 +        for (socket = (socket_count - 1); socket >= 0; socket--) {
 +            phandle_pos -= s->soc[socket].num_harts;
 +
 +            if (s->aia_type == VIRT_AIA_TYPE_NONE) {
 +                create_fdt_socket_plic(s, memmap, socket, phandle,
 +                                       &intc_phandles[phandle_pos],
 +                                       xplic_phandles);
 +            } else {
 +                create_fdt_socket_aplic(s, memmap, socket,
 +                                        msi_m_phandle, msi_s_phandle, phandle,
 +                                        &intc_phandles[phandle_pos],
 +                                        xplic_phandles,
 +                                        s->soc[socket].num_harts);
 +            }
          }
      }
--    hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
+     g_free(intc_phandles);
-+
-+    if (max_hart_per_socket > 1) {
+-    for (socket = 0; socket < socket_count; socket++) {
-+        max_hart_per_socket--;
+-        if (socket == 0) {
-+        hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
+-            *irq_mmio_phandle = xplic_phandles[socket];
 -            *irq_virtio_phandle = xplic_phandles[socket];
 -            *irq_pcie_phandle = xplic_phandles[socket];
 -        }
 -        if (socket == 1) {
 -            *irq_virtio_phandle = xplic_phandles[socket];
 -            *irq_pcie_phandle = xplic_phandles[socket];
 -        }
 -        if (socket == 2) {
 -            *irq_pcie_phandle = xplic_phandles[socket];
 +    if (virt_use_kvm_aia(s)) {
 +        *irq_mmio_phandle = xplic_phandles[0];
 +        *irq_virtio_phandle = xplic_phandles[0];
 +        *irq_pcie_phandle = xplic_phandles[0];
 +    } else {
-+        hart_bits = 0;
++        for (socket = 0; socket < socket_count; socket++) {
 +            if (socket == 0) {
 +                *irq_mmio_phandle = xplic_phandles[socket];
 +                *irq_virtio_phandle = xplic_phandles[socket];
 +                *irq_pcie_phandle = xplic_phandles[socket];
 +            }
 +            if (socket == 1) {
 +                *irq_virtio_phandle = xplic_phandles[socket];
 +                *irq_pcie_phandle = xplic_phandles[socket];
 +            }
 +            if (socket == 2) {
 +                *irq_pcie_phandle = xplic_phandles[socket];
 +            }
          }
      }
@@ -XXX,XX +XXX,XX @@ static void virt_machine_init(MachineState *machine)
          }
      }
 +    if (virt_use_kvm_aia(s)) {
 +        kvm_riscv_aia_create(machine, IMSIC_MMIO_GROUP_MIN_SHIFT,
 +                             VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS,
 +                             memmap[VIRT_APLIC_S].base,
 +                             memmap[VIRT_IMSIC_S].base,
 +                             s->aia_guests);
 +    }
 +
-     ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+     if (riscv_is_32bit(&s->soc[0])) {
-                             KVM_DEV_RISCV_AIA_CONFIG_HART_BITS,
+ #if HOST_LONG_BITS == 64
-                             &hart_bits, true, NULL);
+         /* limit RAM size in a 32-bit system */
 --
-.45.1
+.41.0

-New patch
+[PULL v2 34/45] hw/riscv: virt: Fix riscv,pmu DT node path
+From: Conor Dooley <conor.dooley@microchip.com>
+On a dtb dumped from the virt machine, dt-validate complains:
+soc: pmu: {'riscv,event-to-mhpmcounters': [[1, 1, 524281], [2, 2, 524284], [65561, 65561, 524280], [65563, 65563, 524280], [65569, 65569, 524280]], 'compatible': ['riscv,pmu']} should not be valid under {'type': 'object'}
+        from schema $id: http://devicetree.org/schemas/simple-bus.yaml#
+That's pretty cryptic, but running the dtb back through dtc produces
+something a lot more reasonable:
+Warning (simple_bus_reg): /soc/pmu: missing or empty reg/ranges property
+Moving the riscv,pmu node out of the soc bus solves the problem.
+Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
+Acked-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-ID: <20230727-groom-decline-2c57ce42841c@spud>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ hw/riscv/virt.c | 2 +-
+file changed, 1 insertion(+), 1 deletion(-)
+diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/riscv/virt.c
++++ b/hw/riscv/virt.c
+@@ -XXX,XX +XXX,XX @@ static void create_fdt_pmu(RISCVVirtState *s)
+     MachineState *ms = MACHINE(s);
+     RISCVCPU hart = s->soc[0].harts[0];
+-    pmu_name = g_strdup_printf("/soc/pmu");
++    pmu_name = g_strdup_printf("/pmu");
+     qemu_fdt_add_subnode(ms->fdt, pmu_name);
+     qemu_fdt_setprop_string(ms->fdt, pmu_name, "compatible", "riscv,pmu");
+     riscv_pmu_generate_fdt_node(ms->fdt, hart.cfg.pmu_num, pmu_name);
+--
+.41.0

-[PULL 06/28] target/riscv: change RISCV_EXCP_SEMIHOST exception number to 63
+[PULL v2 35/45] target/riscv: Update CSR bits name for svadu extension
-From: Clément Léger <cleger@rivosinc.com>
+From: Weiwei Li <liweiwei@iscas.ac.cn>
-The current semihost exception number (16) is a reserved number (range
+The Svadu specification updated the name of the *envcfg bit from
-[16-17]). The upcoming double trap specification uses that number for
+HADE to ADUE.
 the double trap exception. Since the privileged spec (Table 22) defines
 ranges for custom uses change the semihosting exception number to 63
 which belongs to the range [48-63] in order to avoid any future
 collisions with reserved exception.
-Signed-off-by: Clément Léger <cleger@rivosinc.com>
+Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>
+Signed-off-by: Junqiang Wang <wangjunqiang@iscas.ac.cn>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Message-ID: <20240422135840.1959967-1-cleger@rivosinc.com>
+Message-ID: <20230816141916.66898-1-liweiwei@iscas.ac.cn>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_bits.h | 2 +-
+ target/riscv/cpu_bits.h   |  8 ++++----
-file changed, 1 insertion(+), 1 deletion(-)
+ target/riscv/cpu.c        |  4 ++--
  target/riscv/cpu_helper.c |  6 +++---
  target/riscv/csr.c        | 12 ++++++------
 files changed, 15 insertions(+), 15 deletions(-)
 diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_bits.h
 +++ b/target/riscv/cpu_bits.h
 @@ -XXX,XX +XXX,XX @@ typedef enum RISCVException {
-     RISCV_EXCP_INST_PAGE_FAULT = 0xc, /* since: priv-1.10.0 */
+ #define MENVCFG_CBIE                       (3UL << 4)
-     RISCV_EXCP_LOAD_PAGE_FAULT = 0xd, /* since: priv-1.10.0 */
+ #define MENVCFG_CBCFE                      BIT(6)
-     RISCV_EXCP_STORE_PAGE_FAULT = 0xf, /* since: priv-1.10.0 */
+ #define MENVCFG_CBZE                       BIT(7)
--    RISCV_EXCP_SEMIHOST = 0x10,
+-#define MENVCFG_HADE                       (1ULL << 61)
-     RISCV_EXCP_INST_GUEST_PAGE_FAULT = 0x14,
++#define MENVCFG_ADUE                       (1ULL << 61)
-     RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT = 0x15,
+ #define MENVCFG_PBMTE                      (1ULL << 62)
-     RISCV_EXCP_VIRT_INSTRUCTION_FAULT = 0x16,
+ #define MENVCFG_STCE                       (1ULL << 63)
-     RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT = 0x17,
-+    RISCV_EXCP_SEMIHOST = 0x3f,
+ /* For RV32 */
- } RISCVException;
+-#define MENVCFGH_HADE                      BIT(29)
++#define MENVCFGH_ADUE                      BIT(29)
- #define RISCV_EXCP_INT_FLAG                0x80000000
+ #define MENVCFGH_PBMTE                     BIT(30)
  #define MENVCFGH_STCE                      BIT(31)
@@ -XXX,XX +XXX,XX @@ typedef enum RISCVException {
  #define HENVCFG_CBIE                       MENVCFG_CBIE
  #define HENVCFG_CBCFE                      MENVCFG_CBCFE
  #define HENVCFG_CBZE                       MENVCFG_CBZE
 -#define HENVCFG_HADE                       MENVCFG_HADE
 +#define HENVCFG_ADUE                       MENVCFG_ADUE
  #define HENVCFG_PBMTE                      MENVCFG_PBMTE
  #define HENVCFG_STCE                       MENVCFG_STCE
  /* For RV32 */
 -#define HENVCFGH_HADE                       MENVCFGH_HADE
 +#define HENVCFGH_ADUE                       MENVCFGH_ADUE
  #define HENVCFGH_PBMTE                      MENVCFGH_PBMTE
  #define HENVCFGH_STCE                       MENVCFGH_STCE
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj)
      env->two_stage_lookup = false;
      env->menvcfg = (cpu->cfg.ext_svpbmt ? MENVCFG_PBMTE : 0) |
 -                   (cpu->cfg.ext_svadu ? MENVCFG_HADE : 0);
 +                   (cpu->cfg.ext_svadu ? MENVCFG_ADUE : 0);
      env->henvcfg = (cpu->cfg.ext_svpbmt ? HENVCFG_PBMTE : 0) |
 -                   (cpu->cfg.ext_svadu ? HENVCFG_HADE : 0);
 +                   (cpu->cfg.ext_svadu ? HENVCFG_ADUE : 0);
      /* Initialized default priorities of local interrupts. */
      for (i = 0; i < ARRAY_SIZE(env->miprio); i++) {
 diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu_helper.c
 +++ b/target/riscv/cpu_helper.c
@@ -XXX,XX +XXX,XX @@ static int get_physical_address(CPURISCVState *env, hwaddr *physical,
      }
      bool pbmte = env->menvcfg & MENVCFG_PBMTE;
 -    bool hade = env->menvcfg & MENVCFG_HADE;
 +    bool adue = env->menvcfg & MENVCFG_ADUE;
      if (first_stage && two_stage && env->virt_enabled) {
          pbmte = pbmte && (env->henvcfg & HENVCFG_PBMTE);
 -        hade = hade && (env->henvcfg & HENVCFG_HADE);
 +        adue = adue && (env->henvcfg & HENVCFG_ADUE);
      }
      int ptshift = (levels - 1) * ptidxbits;
@@ -XXX,XX +XXX,XX @@ restart:
      /* Page table updates need to be atomic with MTTCG enabled */
      if (updated_pte != pte && !is_debug) {
 -        if (!hade) {
 +        if (!adue) {
              return TRANSLATE_FAIL;
          }
 diff --git a/target/riscv/csr.c b/target/riscv/csr.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/csr.c
 +++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException write_menvcfg(CPURISCVState *env, int csrno,
      if (riscv_cpu_mxl(env) == MXL_RV64) {
          mask |= (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) |
                  (cfg->ext_sstc ? MENVCFG_STCE : 0) |
 -                (cfg->ext_svadu ? MENVCFG_HADE : 0);
 +                (cfg->ext_svadu ? MENVCFG_ADUE : 0);
      }
      env->menvcfg = (env->menvcfg & ~mask) | (val & mask);
@@ -XXX,XX +XXX,XX @@ static RISCVException write_menvcfgh(CPURISCVState *env, int csrno,
      const RISCVCPUConfig *cfg = riscv_cpu_cfg(env);
      uint64_t mask = (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) |
                      (cfg->ext_sstc ? MENVCFG_STCE : 0) |
 -                    (cfg->ext_svadu ? MENVCFG_HADE : 0);
 +                    (cfg->ext_svadu ? MENVCFG_ADUE : 0);
      uint64_t valh = (uint64_t)val << 32;
      env->menvcfg = (env->menvcfg & ~mask) | (valh & mask);
@@ -XXX,XX +XXX,XX @@ static RISCVException read_henvcfg(CPURISCVState *env, int csrno,
       * henvcfg.stce is read_only 0 when menvcfg.stce = 0
       * henvcfg.hade is read_only 0 when menvcfg.hade = 0
       */
 -    *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) |
 +    *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) |
                             env->menvcfg);
      return RISCV_EXCP_NONE;
  }
@@ -XXX,XX +XXX,XX @@ static RISCVException write_henvcfg(CPURISCVState *env, int csrno,
      }
      if (riscv_cpu_mxl(env) == MXL_RV64) {
 -        mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE);
 +        mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE);
      }
      env->henvcfg = (env->henvcfg & ~mask) | (val & mask);
@@ -XXX,XX +XXX,XX @@ static RISCVException read_henvcfgh(CPURISCVState *env, int csrno,
          return ret;
      }
 -    *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) |
 +    *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) |
                              env->menvcfg)) >> 32;
      return RISCV_EXCP_NONE;
  }
@@ -XXX,XX +XXX,XX @@ static RISCVException write_henvcfgh(CPURISCVState *env, int csrno,
                                       target_ulong val)
  {
      uint64_t mask = env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE |
 -                                    HENVCFG_HADE);
 +                                    HENVCFG_ADUE);
      uint64_t valh = (uint64_t)val << 32;
      RISCVException ret;
 --
-.45.1
+.41.0

-[PULL 07/28] target/riscv/kvm: tolerate KVM disable ext errors
+[PULL v2 36/45] target/riscv: fix satp_mode_finalize() when satp_mode.supported = 0
 From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Running a KVM guest using a 6.9-rc3 kernel, in a 6.8 host that has zkr
+In the same emulated RISC-V host, the 'host' KVM CPU takes 4 times
-enabled, will fail with a kernel oops SIGILL right at the start. The
+longer to boot than the 'rv64' KVM CPU.
 reason is that we can't expose zkr without implementing the SEED CSR.
 Disabling zkr in the guest would be a workaround, but if the KVM doesn't
 allow it we'll error out and never boot.
-In hindsight this is too strict. If we keep proceeding, despite not
+The reason is an unintended behavior of riscv_cpu_satp_mode_finalize()
-disabling the extension in the KVM vcpu, we'll not add the extension in
+when satp_mode.supported = 0, i.e. when cpu_init() does not set
-the riscv,isa. The guest kernel will be unaware of the extension, i.e.
+satp_mode_max_supported(). satp_mode_max_from_map(map) does:
 it doesn't matter if the KVM vcpu has it enabled underneath or not. So
 it's ok to keep booting in this case.
-Change our current logic to not error out if we fail to disable an
+- __builtin_clz(map)
 extension in kvm_set_one_reg(), but show a warning and keep booting. It
 is important to throw a warning because we must make the user aware that
 the extension is still available in the vcpu, meaning that an
 ill-behaved guest can ignore the riscv,isa settings and  use the
 extension.
-The case we're handling happens with an EINVAL error code. If we fail to
+This means that, if satp_mode.supported = 0, satp_mode_supported_max
-disable the extension in KVM for any other reason, error out.
+wil be '31 - 32'. But this is C, so satp_mode_supported_max will gladly
 set it to UINT_MAX (4294967295). After that, if the user didn't set a
 satp_mode, set_satp_mode_default_map(cpu) will make
-We'll also keep erroring out when we fail to enable an extension in KVM,
+cfg.satp_mode.map = cfg.satp_mode.supported
 since adding the extension in riscv,isa at this point will cause a guest
 malfunction because the extension isn't enabled in the vcpu.
-Suggested-by: Andrew Jones <ajones@ventanamicro.com>
+So satp_mode.map = 0. And then satp_mode_map_max will be set to
 satp_mode_max_from_map(cpu->cfg.satp_mode.map), i.e. also UINT_MAX. The
 guard "satp_mode_map_max > satp_mode_supported_max" doesn't protect us
 here since both are UINT_MAX.
 And finally we have 2 loops:
         for (int i = satp_mode_map_max - 1; i >= 0; --i) {
 Which are, in fact, 2 loops from UINT_MAX -1 to -1. This is where the
 extra delay when booting the 'host' CPU is coming from.
 Commit 43d1de32f8 already set a precedence for satp_mode.supported = 0
 in a different manner. We're doing the same here. If supported == 0,
 interpret as 'the CPU wants the OS to handle satp mode alone' and skip
 satp_mode_finalize().
 We'll also put a guard in satp_mode_max_from_map() to assert out if map
 is 0 since the function is not ready to deal with it.
 Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
 Fixes: 6f23aaeb9b ("riscv: Allow user to set the satp mode")
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
+Message-ID: <20230817152903.694926-1-dbarboza@ventanamicro.com>
 Message-ID: <20240422171425.333037-2-dbarboza@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/kvm/kvm-cpu.c | 12 ++++++++----
+ target/riscv/cpu.c | 23 ++++++++++++++++++++---
-file changed, 8 insertions(+), 4 deletions(-)
+file changed, 20 insertions(+), 3 deletions(-)
-diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
+diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/kvm/kvm-cpu.c
+--- a/target/riscv/cpu.c
-+++ b/target/riscv/kvm/kvm-cpu.c
++++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ static void kvm_riscv_update_cpu_cfg_isa_ext(RISCVCPU *cpu, CPUState *cs)
+@@ -XXX,XX +XXX,XX @@ static uint8_t satp_mode_from_str(const char *satp_mode_str)
-         reg = kvm_cpu_cfg_get(cpu, multi_ext_cfg);
-         ret = kvm_set_one_reg(cs, id, &reg);
+ uint8_t satp_mode_max_from_map(uint32_t map)
-         if (ret != 0) {
+ {
--            error_report("Unable to %s extension %s in KVM, error %d",
++    /*
--                         reg ? "enable" : "disable",
++     * 'map = 0' will make us return (31 - 32), which C will
--                         multi_ext_cfg->name, ret);
++     * happily overflow to UINT_MAX. There's no good result to
--            exit(EXIT_FAILURE);
++     * return if 'map = 0' (e.g. returning 0 will be ambiguous
-+            if (!reg && ret == -EINVAL) {
++     * with the result for 'map = 1').
-+                warn_report("KVM cannot disable extension %s",
++     *
-+                            multi_ext_cfg->name);
++     * Assert out if map = 0. Callers will have to deal with
-+            } else {
++     * it outside of this function.
-+                error_report("Unable to enable extension %s in KVM, error %d",
++     */
-+                             multi_ext_cfg->name, ret);
++    g_assert(map > 0);
-+                exit(EXIT_FAILURE);
++
-+            }
+     /* map here has at least one bit set, so no problem with clz */
-         }
+     return 31 - __builtin_clz(map);
      }
  }
+@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
+ static void riscv_cpu_satp_mode_finalize(RISCVCPU *cpu, Error **errp)
+ {
+     bool rv32 = riscv_cpu_mxl(&cpu->env) == MXL_RV32;
+-    uint8_t satp_mode_map_max;
+-    uint8_t satp_mode_supported_max =
+-                        satp_mode_max_from_map(cpu->cfg.satp_mode.supported);
++    uint8_t satp_mode_map_max, satp_mode_supported_max;
++
++    /* The CPU wants the OS to decide which satp mode to use */
++    if (cpu->cfg.satp_mode.supported == 0) {
++        return;
++    }
++
++    satp_mode_supported_max =
++                    satp_mode_max_from_map(cpu->cfg.satp_mode.supported);
+     if (cpu->cfg.satp_mode.map == 0) {
+         if (cpu->cfg.satp_mode.init == 0) {
 --
-.45.1
+.41.0

-[PULL 14/28] target/riscv/cpu.c: fix Zvkb extension config
+[PULL v2 37/45] riscv: zicond: make non-experimental
-From: Yangyu Chen <cyy@cyyself.name>
+From: Vineet Gupta <vineetg@rivosinc.com>
-This code has a typo that writes zvkb to zvkg, causing users can't
+zicond is now codegen supported in both llvm and gcc.
 enable zvkb through the config. This patch gets this fixed.
-Signed-off-by: Yangyu Chen <cyy@cyyself.name>
+This change allows seamless enabling/testing of zicond in downstream
-Fixes: ea61ef7097d0 ("target/riscv: Move vector crypto extensions to riscv_cpu_extensions")
+projects. e.g. currently riscv-gnu-toolchain parses elf attributes
-Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+to create a cmdline for qemu but fails short of enabling it because of
 the "x-" prefix.
 Signed-off-by: Vineet Gupta <vineetg@rivosinc.com>
 Message-ID: <20230808181715.436395-1-vineetg@rivosinc.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: Max Chou <max.chou@sifive.com>
-Reviewed-by:  Weiwei Li <liwei1518@gmail.com>
-Message-ID: <tencent_7E34EEF0F90B9A68BF38BEE09EC6D4877C0A@qq.com>
-Cc: qemu-stable <qemu-stable@nongnu.org>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
  target/riscv/cpu.c | 2 +-
 file changed, 1 insertion(+), 1 deletion(-)
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
-@@ -XXX,XX +XXX,XX @@ const RISCVCPUMultiExtConfig riscv_cpu_extensions[] = {
+@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
-     /* Vector cryptography extensions */
+     DEFINE_PROP_BOOL("zcf", RISCVCPU, cfg.ext_zcf, false),
-     MULTI_EXT_CFG_BOOL("zvbb", ext_zvbb, false),
+     DEFINE_PROP_BOOL("zcmp", RISCVCPU, cfg.ext_zcmp, false),
-     MULTI_EXT_CFG_BOOL("zvbc", ext_zvbc, false),
+     DEFINE_PROP_BOOL("zcmt", RISCVCPU, cfg.ext_zcmt, false),
--    MULTI_EXT_CFG_BOOL("zvkb", ext_zvkg, false),
++    DEFINE_PROP_BOOL("zicond", RISCVCPU, cfg.ext_zicond, false),
-+    MULTI_EXT_CFG_BOOL("zvkb", ext_zvkb, false),
-     MULTI_EXT_CFG_BOOL("zvkg", ext_zvkg, false),
+     /* Vendor-specific custom extensions */
-     MULTI_EXT_CFG_BOOL("zvkned", ext_zvkned, false),
+     DEFINE_PROP_BOOL("xtheadba", RISCVCPU, cfg.ext_xtheadba, false),
-     MULTI_EXT_CFG_BOOL("zvknha", ext_zvknha, false),
+@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
      DEFINE_PROP_BOOL("xventanacondops", RISCVCPU, cfg.ext_XVentanaCondOps, false),
      /* These are experimental so mark with 'x-' */
 -    DEFINE_PROP_BOOL("x-zicond", RISCVCPU, cfg.ext_zicond, false),
      /* ePMP 0.9.3 */
      DEFINE_PROP_BOOL("x-epmp", RISCVCPU, cfg.epmp, false),
 --
-.45.1
+.41.0

-[PULL 26/28] riscv, gdbstub.c: fix reg_width in ricsv_gen_dynamic_vector_feature()
+[PULL v2 38/45] hw/riscv/virt.c: fix non-KVM --enable-debug build
 From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Commit 33a24910ae changed 'reg_width' to use 'vlenb', i.e. vector length
+A build with --enable-debug and without KVM will fail as follows:
 in bytes, when in this context we want 'reg_width' as the length in
 bits.
-Fix 'reg_width' back to the value in bits like 7cb59921c05a
+/usr/bin/ld: libqemu-riscv64-softmmu.fa.p/hw_riscv_virt.c.o: in function `virt_machine_init':
-("target/riscv/gdbstub.c: use 'vlenb' instead of shifting 'vlen'") set
+./qemu/build/../hw/riscv/virt.c:1465: undefined reference to `kvm_riscv_aia_create'
 beforehand.
-While we're at it, rename 'reg_width' to 'bitsize' to provide a bit more
+This happens because the code block with "if virt_use_kvm_aia(s)" isn't
-clarity about what the variable represents. 'bitsize' is also used in
+being ignored by the debug build, resulting in an undefined reference to
-riscv_gen_dynamic_csr_feature() with the same purpose, i.e. as an input to
+a KVM only function.
 gdb_feature_builder_append_reg().
-Cc: Akihiko Odaki <akihiko.odaki@daynix.com>
+Add a 'kvm_enabled()' conditional together with virt_use_kvm_aia() will
-Cc: Alex Bennée <alex.bennee@linaro.org>
+make the compiler crop the kvm_riscv_aia_create() call entirely from a
-Reported-by: Robin Dapp <rdapp.gcc@gmail.com>
+non-KVM build. Note that adding the 'kvm_enabled()' conditional inside
-Fixes: 33a24910ae ("target/riscv: Use GDBFeature for dynamic XML")
+virt_use_kvm_aia() won't fix the build because this function would need
 to be inlined multiple times to make the compiler zero out the entire
 block.
 While we're at it, use kvm_enabled() in all instances where
 virt_use_kvm_aia() is checked to allow the compiler to elide these other
 kvm-only instances as well.
 Suggested-by: Richard Henderson <richard.henderson@linaro.org>
 Fixes: dbdb99948e ("target/riscv: select KVM AIA in riscv virt machine")
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Acked-by: Alex Bennée <alex.bennee@linaro.org>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
-Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Message-ID: <20230830133503.711138-2-dbarboza@ventanamicro.com>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240517203054.880861-2-dbarboza@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/gdbstub.c | 6 +++---
+ hw/riscv/virt.c | 6 +++---
 file changed, 3 insertions(+), 3 deletions(-)
-diff --git a/target/riscv/gdbstub.c b/target/riscv/gdbstub.c
+diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/gdbstub.c
+--- a/hw/riscv/virt.c
-+++ b/target/riscv/gdbstub.c
++++ b/hw/riscv/virt.c
-@@ -XXX,XX +XXX,XX @@ static GDBFeature *riscv_gen_dynamic_csr_feature(CPUState *cs, int base_reg)
+@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
  static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
  {
      RISCVCPU *cpu = RISCV_CPU(cs);
 -    int reg_width = cpu->cfg.vlenb;
 +    int bitsize = cpu->cfg.vlenb << 3;
      GDBFeatureBuilder builder;
      int i;
@@ -XXX,XX +XXX,XX @@ static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
      /* First define types and totals in a whole VL */
      for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) {
 -        int count = reg_width / vec_lanes[i].size;
 +        int count = bitsize / vec_lanes[i].size;
          gdb_feature_builder_append_tag(
              &builder, "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>",
              vec_lanes[i].id, vec_lanes[i].gdb_type, count);
@@ -XXX,XX +XXX,XX @@ static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
      /* Define vector registers */
      for (i = 0; i < 32; i++) {
          gdb_feature_builder_append_reg(&builder, g_strdup_printf("v%d", i),
 -                                       reg_width, i, "riscv_vector", "vector");
 +                                       bitsize, i, "riscv_vector", "vector");
      }
-     gdb_feature_builder_end(&builder);
+     /* KVM AIA only has one APLIC instance */
 -    if (virt_use_kvm_aia(s)) {
 +    if (kvm_enabled() && virt_use_kvm_aia(s)) {
          create_fdt_socket_aplic(s, memmap, 0,
                                  msi_m_phandle, msi_s_phandle, phandle,
                                  &intc_phandles[0], xplic_phandles,
@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
      g_free(intc_phandles);
 -    if (virt_use_kvm_aia(s)) {
 +    if (kvm_enabled() && virt_use_kvm_aia(s)) {
          *irq_mmio_phandle = xplic_phandles[0];
          *irq_virtio_phandle = xplic_phandles[0];
          *irq_pcie_phandle = xplic_phandles[0];
@@ -XXX,XX +XXX,XX @@ static void virt_machine_init(MachineState *machine)
          }
      }
 -    if (virt_use_kvm_aia(s)) {
 +    if (kvm_enabled() && virt_use_kvm_aia(s)) {
          kvm_riscv_aia_create(machine, IMSIC_MMIO_GROUP_MIN_SHIFT,
                               VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS,
                               memmap[VIRT_APLIC_S].base,
 --
-.45.1
+.41.0

-[PULL 09/28] trans_privileged.c.inc: set (m|s)tval on ebreak breakpoint
+[PULL v2 39/45] hw/intc/riscv_aplic.c fix non-KVM --enable-debug build
 From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Privileged spec section 4.1.9 mentions:
+Commit 6df0b37e2ab breaks a --enable-debug build in a non-KVM
 environment with the following error:
-"When a trap is taken into S-mode, stval is written with
+/usr/bin/ld: libqemu-riscv64-softmmu.fa.p/hw_intc_riscv_aplic.c.o: in function `riscv_kvm_aplic_request':
-exception-specific information to assist software in handling the trap.
+./qemu/build/../hw/intc/riscv_aplic.c:486: undefined reference to `kvm_set_irq'
-(...)
+collect2: error: ld returned 1 exit status
-If stval is written with a nonzero value when a breakpoint,
+This happens because the debug build will poke into the
-address-misaligned, access-fault, or page-fault exception occurs on an
+'if (is_kvm_aia(aplic->msimode))' block and fail to find a reference to
-instruction fetch, load, or store, then stval will contain the faulting
+the KVM only function riscv_kvm_aplic_request().
 virtual address."
-A similar text is found for mtval in section 3.1.16.
+There are multiple solutions to fix this. We'll go with the same
 solution from the previous patch, i.e. add a kvm_enabled() conditional
 to filter out the block. But there's a catch: riscv_kvm_aplic_request()
 is a local function that would end up being used if the compiler crops
 the block, and this won't work. Quoting Richard Henderson's explanation
 in [1]:
-Setting mtval/stval in this scenario is optional, but some softwares read
+"(...) the compiler won't eliminate entire unused functions with -O0"
 these regs when handling ebreaks.
-Write 'badaddr' in all ebreak breakpoints to write the appropriate
+We'll solve it by moving riscv_kvm_aplic_request() to kvm.c and add its
-'tval' during riscv_do_cpu_interrrupt().
+declaration in kvm_riscv.h, where all other KVM specific public
 functions are already declared. Other archs handles KVM specific code in
 this manner and we expect to do the same from now on.
 [1] https://lore.kernel.org/qemu-riscv/d2f1ad02-eb03-138f-9d08-db676deeed05@linaro.org/
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
-Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
-Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
 Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
-Message-ID: <20240416230437.1869024-3-dbarboza@ventanamicro.com>
+Message-ID: <20230830133503.711138-3-dbarboza@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/insn_trans/trans_privileged.c.inc | 2 ++
+ target/riscv/kvm_riscv.h | 1 +
-file changed, 2 insertions(+)
+ hw/intc/riscv_aplic.c    | 8 ++------
  target/riscv/kvm.c       | 5 +++++
 files changed, 8 insertions(+), 6 deletions(-)
-diff --git a/target/riscv/insn_trans/trans_privileged.c.inc b/target/riscv/insn_trans/trans_privileged.c.inc
+diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/insn_trans/trans_privileged.c.inc
+--- a/target/riscv/kvm_riscv.h
-+++ b/target/riscv/insn_trans/trans_privileged.c.inc
++++ b/target/riscv/kvm_riscv.h
-@@ -XXX,XX +XXX,XX @@ static bool trans_ebreak(DisasContext *ctx, arg_ebreak *a)
+@@ -XXX,XX +XXX,XX @@ void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
-     if (pre == 0x01f01013 && ebreak == 0x00100073 && post == 0x40705013) {
+                           uint64_t aia_irq_num, uint64_t aia_msi_num,
-         generate_exception(ctx, RISCV_EXCP_SEMIHOST);
+                           uint64_t aplic_base, uint64_t imsic_base,
-     } else {
+                           uint64_t guest_num);
-+        tcg_gen_st_tl(tcg_constant_tl(ebreak_addr), tcg_env,
++void riscv_kvm_aplic_request(void *opaque, int irq, int level);
-+                      offsetof(CPURISCVState, badaddr));
-         generate_exception(ctx, RISCV_EXCP_BREAKPOINT);
+ #endif
-     }
+diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
-     return true;
+index XXXXXXX..XXXXXXX 100644
 --- a/hw/intc/riscv_aplic.c
 +++ b/hw/intc/riscv_aplic.c
@@ -XXX,XX +XXX,XX @@
  #include "target/riscv/cpu.h"
  #include "sysemu/sysemu.h"
  #include "sysemu/kvm.h"
 +#include "kvm_riscv.h"
  #include "migration/vmstate.h"
  #define APLIC_MAX_IDC                  (1UL << 14)
@@ -XXX,XX +XXX,XX @@ static uint32_t riscv_aplic_idc_claimi(RISCVAPLICState *aplic, uint32_t idc)
      return topi;
  }
 -static void riscv_kvm_aplic_request(void *opaque, int irq, int level)
 -{
 -    kvm_set_irq(kvm_state, irq, !!level);
 -}
 -
  static void riscv_aplic_request(void *opaque, int irq, int level)
  {
      bool update = false;
@@ -XXX,XX +XXX,XX @@ static void riscv_aplic_realize(DeviceState *dev, Error **errp)
       * have IRQ lines delegated by their parent APLIC.
       */
      if (!aplic->parent) {
 -        if (is_kvm_aia(aplic->msimode)) {
 +        if (kvm_enabled() && is_kvm_aia(aplic->msimode)) {
              qdev_init_gpio_in(dev, riscv_kvm_aplic_request, aplic->num_irqs);
          } else {
              qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
 diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/kvm.c
 +++ b/target/riscv/kvm.c
@@ -XXX,XX +XXX,XX @@
  #include "sysemu/runstate.h"
  #include "hw/riscv/numa.h"
 +void riscv_kvm_aplic_request(void *opaque, int irq, int level)
 +{
 +    kvm_set_irq(kvm_state, irq, !!level);
 +}
 +
  static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type,
                                   uint64_t idx)
  {
 --
-.45.1
+.41.0

-New patch
+[PULL v2 40/45] linux-user/riscv: Add new extensions to hwprobe
+From: Robbin Ehn <rehn@rivosinc.com>
+This patch adds the new extensions in
+linux 6.5 to the hwprobe syscall.
+And fixes RVC check to OR with correct value.
+The previous variable contains 0 therefore it
+did work.
+Signed-off-by: Robbin Ehn <rehn@rivosinc.com>
+Acked-by: Richard Henderson <richard.henderson@linaro.org>
+Acked-by: Alistair Francis <alistair.francis@wdc.com>
+Message-ID: <bc82203b72d7efb30f1b4a8f9eb3d94699799dc8.camel@rivosinc.com>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ linux-user/syscall.c | 14 +++++++++++++-
+file changed, 13 insertions(+), 1 deletion(-)
+diff --git a/linux-user/syscall.c b/linux-user/syscall.c
+index XXXXXXX..XXXXXXX 100644
+--- a/linux-user/syscall.c
++++ b/linux-user/syscall.c
+@@ -XXX,XX +XXX,XX @@ static int do_getdents64(abi_long dirfd, abi_long arg2, abi_long count)
+ #define RISCV_HWPROBE_KEY_IMA_EXT_0     4
+ #define     RISCV_HWPROBE_IMA_FD       (1 << 0)
+ #define     RISCV_HWPROBE_IMA_C        (1 << 1)
++#define     RISCV_HWPROBE_IMA_V        (1 << 2)
++#define     RISCV_HWPROBE_EXT_ZBA      (1 << 3)
++#define     RISCV_HWPROBE_EXT_ZBB      (1 << 4)
++#define     RISCV_HWPROBE_EXT_ZBS      (1 << 5)
+ #define RISCV_HWPROBE_KEY_CPUPERF_0     5
+ #define     RISCV_HWPROBE_MISALIGNED_UNKNOWN     (0 << 0)
+@@ -XXX,XX +XXX,XX @@ static void risc_hwprobe_fill_pairs(CPURISCVState *env,
+                     riscv_has_ext(env, RVD) ?
+                     RISCV_HWPROBE_IMA_FD : 0;
+             value |= riscv_has_ext(env, RVC) ?
+-                     RISCV_HWPROBE_IMA_C : pair->value;
++                     RISCV_HWPROBE_IMA_C : 0;
++            value |= riscv_has_ext(env, RVV) ?
++                     RISCV_HWPROBE_IMA_V : 0;
++            value |= cfg->ext_zba ?
++                     RISCV_HWPROBE_EXT_ZBA : 0;
++            value |= cfg->ext_zbb ?
++                     RISCV_HWPROBE_EXT_ZBB : 0;
++            value |= cfg->ext_zbs ?
++                     RISCV_HWPROBE_EXT_ZBS : 0;
+             __put_user(value, &pair->value);
+             break;
+         case RISCV_HWPROBE_KEY_CPUPERF_0:
+--
+.41.0

-New patch
+[PULL v2 41/45] target/riscv: Use accelerated helper for AES64KS1I
+From: Ard Biesheuvel <ardb@kernel.org>
+Use the accelerated SubBytes/ShiftRows/AddRoundKey AES helper to
+implement the first half of the key schedule derivation. This does not
+actually involve shifting rows, so clone the same value into all four
+columns of the AES vector to counter that operation.
+Cc: Richard Henderson <richard.henderson@linaro.org>
+Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
+Cc: Palmer Dabbelt <palmer@dabbelt.com>
+Cc: Alistair Francis <alistair.francis@wdc.com>
+Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-ID: <20230831154118.138727-1-ardb@kernel.org>
+Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+---
+ target/riscv/crypto_helper.c | 17 +++++------------
+file changed, 5 insertions(+), 12 deletions(-)
+diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c
+index XXXXXXX..XXXXXXX 100644
+--- a/target/riscv/crypto_helper.c
++++ b/target/riscv/crypto_helper.c
+@@ -XXX,XX +XXX,XX @@ target_ulong HELPER(aes64ks1i)(target_ulong rs1, target_ulong rnum)
+     uint8_t enc_rnum = rnum;
+     uint32_t temp = (RS1 >> 32) & 0xFFFFFFFF;
+-    uint8_t rcon_ = 0;
+-    target_ulong result;
++    AESState t, rc = {};
+     if (enc_rnum != 0xA) {
+         temp = ror32(temp, 8); /* Rotate right by 8 */
+-        rcon_ = round_consts[enc_rnum];
++        rc.w[0] = rc.w[1] = round_consts[enc_rnum];
+     }
+-    temp = ((uint32_t)AES_sbox[(temp >> 24) & 0xFF] << 24) |
+-           ((uint32_t)AES_sbox[(temp >> 16) & 0xFF] << 16) |
+-           ((uint32_t)AES_sbox[(temp >> 8) & 0xFF] << 8) |
+-           ((uint32_t)AES_sbox[(temp >> 0) & 0xFF] << 0);
++    t.w[0] = t.w[1] = t.w[2] = t.w[3] = temp;
++    aesenc_SB_SR_AK(&t, &t, &rc, false);
+-    temp ^= rcon_;
+-
+-    result = ((uint64_t)temp << 32) | temp;
+-
+-    return result;
++    return t.d[0];
+ }
+ target_ulong HELPER(aes64im)(target_ulong rs1)
+--
+.41.0

-[PULL 08/28] target/riscv/debug: set tval=pc in breakpoint exceptions
+[PULL v2 42/45] target/riscv: Allocate itrigger timers only once
-From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-We're not setting (s/m)tval when triggering breakpoints of type 2
+riscv_trigger_init() had been called on reset events that can happen
-(mcontrol) and 6 (mcontrol6). According to the debug spec section
+several times for a CPU and it allocated timers for itrigger. If old
-.7.12, "Match Control Type 6":
+timers were present, they were simply overwritten by the new timers,
 resulting in a memory leak.
-"The Privileged Spec says that breakpoint exceptions that occur on
+Divide riscv_trigger_init() into two functions, namely
-instruction fetches, loads, or stores update the tval CSR with either
+riscv_trigger_realize() and riscv_trigger_reset() and call them in
-zero or the faulting virtual address. The faulting virtual address for
+appropriate timing. The timer allocation will happen only once for a
-an mcontrol6 trigger with action = 0 is the address being accessed and
+CPU in riscv_trigger_realize().
 which caused that trigger to fire."
-A similar text is also found in the Debug spec section 5.7.11 w.r.t.
+Fixes: 5a4ae64cac ("target/riscv: Add itrigger support when icount is enabled")
-mcontrol.
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
-Note that what we're doing ATM is not violating the spec, but it's
+Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
 simple enough to set mtval/stval and it makes life easier for any
 software that relies on this info.
 Given that we always use action = 0, save the faulting address for the
 mcontrol and mcontrol6 trigger breakpoints into env->badaddr, which is
 used as as scratch area for traps with address information. 'tval' is
 then set during riscv_cpu_do_interrupt().
 Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
+Message-ID: <20230818034059.9146-1-akihiko.odaki@daynix.com>
 Message-ID: <20240416230437.1869024-2-dbarboza@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu_helper.c | 1 +
+ target/riscv/debug.h |  3 ++-
- target/riscv/debug.c      | 3 +++
+ target/riscv/cpu.c   |  8 +++++++-
-files changed, 4 insertions(+)
+ target/riscv/debug.c | 15 ++++++++++++---
 files changed, 21 insertions(+), 5 deletions(-)
-diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
+diff --git a/target/riscv/debug.h b/target/riscv/debug.h
 index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu_helper.c
+--- a/target/riscv/debug.h
-+++ b/target/riscv/cpu_helper.c
++++ b/target/riscv/debug.h
-@@ -XXX,XX +XXX,XX @@ void riscv_cpu_do_interrupt(CPUState *cs)
+@@ -XXX,XX +XXX,XX @@ void riscv_cpu_debug_excp_handler(CPUState *cs);
-             tval = env->bins;
+ bool riscv_cpu_debug_check_breakpoint(CPUState *cs);
-             break;
+ bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp);
-         case RISCV_EXCP_BREAKPOINT:
-+            tval = env->badaddr;
+-void riscv_trigger_init(CPURISCVState *env);
-             if (cs->watchpoint_hit) {
++void riscv_trigger_realize(CPURISCVState *env);
-                 tval = cs->watchpoint_hit->hitaddr;
++void riscv_trigger_reset_hold(CPURISCVState *env);
-                 cs->watchpoint_hit = NULL;
  bool riscv_itrigger_enabled(CPURISCVState *env);
  void riscv_itrigger_update_priv(CPURISCVState *env);
 diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/cpu.c
 +++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj)
  #ifndef CONFIG_USER_ONLY
      if (cpu->cfg.debug) {
 -        riscv_trigger_init(env);
 +        riscv_trigger_reset_hold(env);
      }
      if (kvm_enabled()) {
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp)
      riscv_cpu_register_gdb_regs_for_features(cs);
 +#ifndef CONFIG_USER_ONLY
 +    if (cpu->cfg.debug) {
 +        riscv_trigger_realize(&cpu->env);
 +    }
 +#endif
 +
      qemu_init_vcpu(cs);
      cpu_reset(cs);
 diff --git a/target/riscv/debug.c b/target/riscv/debug.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/debug.c
 +++ b/target/riscv/debug.c
-@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_breakpoint(CPUState *cs)
+@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp)
-                 if ((ctrl & TYPE2_EXEC) && (bp->pc == pc)) {
+     return false;
-                     /* check U/S/M bit against current privilege level */
+ }
-                     if ((ctrl >> 3) & BIT(env->priv)) {
-+                        env->badaddr = pc;
+-void riscv_trigger_init(CPURISCVState *env)
-                         return true;
++void riscv_trigger_realize(CPURISCVState *env)
-                     }
++{
-                 }
++    int i;
-@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_breakpoint(CPUState *cs)
++
-                     if (env->virt_enabled) {
++    for (i = 0; i < RV_MAX_TRIGGERS; i++) {
-                         /* check VU/VS bit against current privilege level */
++        env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                         if ((ctrl >> 23) & BIT(env->priv)) {
++                                              riscv_itrigger_timer_cb, env);
-+                            env->badaddr = pc;
++    }
-                             return true;
++}
-                         }
++
-                     } else {
++void riscv_trigger_reset_hold(CPURISCVState *env)
-                         /* check U/S/M bit against current privilege level */
+ {
-                         if ((ctrl >> 3) & BIT(env->priv)) {
+     target_ulong tdata1 = build_tdata1(env, TRIGGER_TYPE_AD_MATCH, 0, 0);
-+                            env->badaddr = pc;
+     int i;
-                             return true;
+@@ -XXX,XX +XXX,XX @@ void riscv_trigger_init(CPURISCVState *env)
-                         }
+         env->tdata3[i] = 0;
-                     }
+         env->cpu_breakpoint[i] = NULL;
          env->cpu_watchpoint[i] = NULL;
 -        env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL,
 -                                              riscv_itrigger_timer_cb, env);
 +        timer_del(env->itrigger_timer[i]);
      }
  }
 --
-.45.1
+.41.0

-[PULL 27/28] disas/riscv: Decode all of the pmpcfg and pmpaddr CSRs
+[PULL v2 43/45] target/riscv/pmp.c: respect mseccfg.RLB for pmpaddrX changes
-From: Alistair Francis <alistair23@gmail.com>
+From: Leon Schuermann <leons@opentitan.org>
-Previously we only listed a single pmpcfg CSR and the first 16 pmpaddr
+When the rule-lock bypass (RLB) bit is set in the mseccfg CSR, the PMP
-CSRs. This patch fixes this to list all 16 pmpcfg and all 64 pmpaddr
+configuration lock bits must not apply. While this behavior is
-CSRs are part of the disassembly.
+implemented for the pmpcfgX CSRs, this bit is not respected for
 changes to the pmpaddrX CSRs. This patch ensures that pmpaddrX CSR
 writes work even on locked regions when the global rule-lock bypass is
 enabled.
-Reported-by: Eric DeVolder <eric_devolder@yahoo.com>
+Signed-off-by: Leon Schuermann <leons@opentitan.org>
-Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
+Reviewed-by: Mayuresh Chitale <mchitale@ventanamicro.com>
-Fixes: ea10325917 ("RISC-V Disassembler")
+Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
+Message-ID: <20230829215046.1430463-1-leon@is.currently.online>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240514051615.330979-1-alistair.francis@wdc.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- disas/riscv.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++-
+ target/riscv/pmp.c | 4 ++++
-file changed, 64 insertions(+), 1 deletion(-)
+file changed, 4 insertions(+)
-diff --git a/disas/riscv.c b/disas/riscv.c
+diff --git a/target/riscv/pmp.c b/target/riscv/pmp.c
 index XXXXXXX..XXXXXXX 100644
---- a/disas/riscv.c
+--- a/target/riscv/pmp.c
-+++ b/disas/riscv.c
++++ b/target/riscv/pmp.c
-@@ -XXX,XX +XXX,XX @@ static const char *csr_name(int csrno)
+@@ -XXX,XX +XXX,XX @@ static inline uint8_t pmp_get_a_field(uint8_t cfg)
-     case 0x0383: return "mibound";
+  */
-     case 0x0384: return "mdbase";
+ static inline int pmp_is_locked(CPURISCVState *env, uint32_t pmp_index)
-     case 0x0385: return "mdbound";
+ {
--    case 0x03a0: return "pmpcfg3";
++    /* mseccfg.RLB is set */
-+    case 0x03a0: return "pmpcfg0";
++    if (MSECCFG_RLB_ISSET(env)) {
-+    case 0x03a1: return "pmpcfg1";
++        return 0;
-+    case 0x03a2: return "pmpcfg2";
++    }
-+    case 0x03a3: return "pmpcfg3";
-+    case 0x03a4: return "pmpcfg4";
+     if (env->pmp_state.pmp[pmp_index].cfg_reg & PMP_LOCK) {
-+    case 0x03a5: return "pmpcfg5";
+         return 1;
 +    case 0x03a6: return "pmpcfg6";
 +    case 0x03a7: return "pmpcfg7";
 +    case 0x03a8: return "pmpcfg8";
 +    case 0x03a9: return "pmpcfg9";
 +    case 0x03aa: return "pmpcfg10";
 +    case 0x03ab: return "pmpcfg11";
 +    case 0x03ac: return "pmpcfg12";
 +    case 0x03ad: return "pmpcfg13";
 +    case 0x03ae: return "pmpcfg14";
 +    case 0x03af: return "pmpcfg15";
      case 0x03b0: return "pmpaddr0";
      case 0x03b1: return "pmpaddr1";
      case 0x03b2: return "pmpaddr2";
@@ -XXX,XX +XXX,XX @@ static const char *csr_name(int csrno)
      case 0x03bd: return "pmpaddr13";
      case 0x03be: return "pmpaddr14";
      case 0x03bf: return "pmpaddr15";
 +    case 0x03c0: return "pmpaddr16";
 +    case 0x03c1: return "pmpaddr17";
 +    case 0x03c2: return "pmpaddr18";
 +    case 0x03c3: return "pmpaddr19";
 +    case 0x03c4: return "pmpaddr20";
 +    case 0x03c5: return "pmpaddr21";
 +    case 0x03c6: return "pmpaddr22";
 +    case 0x03c7: return "pmpaddr23";
 +    case 0x03c8: return "pmpaddr24";
 +    case 0x03c9: return "pmpaddr25";
 +    case 0x03ca: return "pmpaddr26";
 +    case 0x03cb: return "pmpaddr27";
 +    case 0x03cc: return "pmpaddr28";
 +    case 0x03cd: return "pmpaddr29";
 +    case 0x03ce: return "pmpaddr30";
 +    case 0x03cf: return "pmpaddr31";
 +    case 0x03d0: return "pmpaddr32";
 +    case 0x03d1: return "pmpaddr33";
 +    case 0x03d2: return "pmpaddr34";
 +    case 0x03d3: return "pmpaddr35";
 +    case 0x03d4: return "pmpaddr36";
 +    case 0x03d5: return "pmpaddr37";
 +    case 0x03d6: return "pmpaddr38";
 +    case 0x03d7: return "pmpaddr39";
 +    case 0x03d8: return "pmpaddr40";
 +    case 0x03d9: return "pmpaddr41";
 +    case 0x03da: return "pmpaddr42";
 +    case 0x03db: return "pmpaddr43";
 +    case 0x03dc: return "pmpaddr44";
 +    case 0x03dd: return "pmpaddr45";
 +    case 0x03de: return "pmpaddr46";
 +    case 0x03df: return "pmpaddr47";
 +    case 0x03e0: return "pmpaddr48";
 +    case 0x03e1: return "pmpaddr49";
 +    case 0x03e2: return "pmpaddr50";
 +    case 0x03e3: return "pmpaddr51";
 +    case 0x03e4: return "pmpaddr52";
 +    case 0x03e5: return "pmpaddr53";
 +    case 0x03e6: return "pmpaddr54";
 +    case 0x03e7: return "pmpaddr55";
 +    case 0x03e8: return "pmpaddr56";
 +    case 0x03e9: return "pmpaddr57";
 +    case 0x03ea: return "pmpaddr58";
 +    case 0x03eb: return "pmpaddr59";
 +    case 0x03ec: return "pmpaddr60";
 +    case 0x03ed: return "pmpaddr61";
 +    case 0x03ee: return "pmpaddr62";
 +    case 0x03ef: return "pmpaddr63";
      case 0x0780: return "mtohost";
      case 0x0781: return "mfromhost";
      case 0x0782: return "mreset";
 --
-.45.1
+.41.0

-[PULL 02/28] target/riscv/kvm: Fix exposure of Zkr
+[PULL v2 44/45] target/riscv: Align the AIA model to v1.0 ratified spec
-From: Andrew Jones <ajones@ventanamicro.com>
+From: Tommy Wu <tommy.wu@sifive.com>
-The Zkr extension may only be exposed to KVM guests if the VMM
+According to the new spec, when vsiselect has a reserved value, attempts
-implements the SEED CSR. Use the same implementation as TCG.
+from M-mode or HS-mode to access vsireg, or from VS-mode to access
 sireg, should preferably raise an illegal instruction exception.
-Without this patch, running with a KVM which does not forward the
+Signed-off-by: Tommy Wu <tommy.wu@sifive.com>
-SEED CSR access to QEMU will result in an ILL exception being
+Reviewed-by: Frank Chang <frank.chang@sifive.com>
-injected into the guest (this results in Linux guests crashing on
+Message-ID: <20230816061647.600672-1-tommy.wu@sifive.com>
 boot). And, when running with a KVM which does forward the access,
 QEMU will crash, since QEMU doesn't know what to do with the exit.
 Fixes: 3108e2f1c69d ("target/riscv/kvm: update KVM exts to Linux 6.8")
 Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
 Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
 Cc: qemu-stable <qemu-stable@nongnu.org>
 Message-ID: <20240422134605.534207-2-ajones@ventanamicro.com>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu.h         |  3 +++
+ target/riscv/csr.c | 7 +++++--
- target/riscv/csr.c         | 18 ++++++++++++++----
+file changed, 5 insertions(+), 2 deletions(-)
  target/riscv/kvm/kvm-cpu.c | 25 +++++++++++++++++++++++++
 files changed, 42 insertions(+), 4 deletions(-)
-diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
-index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu.h
-+++ b/target/riscv/cpu.h
-@@ -XXX,XX +XXX,XX @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops);
- void riscv_cpu_register_gdb_regs_for_features(CPUState *cs);
-+target_ulong riscv_new_csr_seed(target_ulong new_value,
-+                                target_ulong write_mask);
-+
- uint8_t satp_mode_max_from_map(uint32_t map);
- const char *satp_mode_str(uint8_t satp_mode, bool is_32_bit);
 diff --git a/target/riscv/csr.c b/target/riscv/csr.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/csr.c
 +++ b/target/riscv/csr.c
-@@ -XXX,XX +XXX,XX @@ static RISCVException write_upmbase(CPURISCVState *env, int csrno,
+@@ -XXX,XX +XXX,XX @@ static int rmw_iprio(target_ulong xlen,
- #endif
+ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
+                      target_ulong new_val, target_ulong wr_mask)
  /* Crypto Extension */
 -static RISCVException rmw_seed(CPURISCVState *env, int csrno,
 -                               target_ulong *ret_value,
 -                               target_ulong new_value,
 -                               target_ulong write_mask)
 +target_ulong riscv_new_csr_seed(target_ulong new_value,
 +                                target_ulong write_mask)
  {
-     uint16_t random_v;
+-    bool virt;
-     Error *random_e = NULL;
++    bool virt, isel_reserved;
-@@ -XXX,XX +XXX,XX @@ static RISCVException rmw_seed(CPURISCVState *env, int csrno,
+     uint8_t *iprio;
-         rval = random_v | SEED_OPST_ES16;
+     int ret = -EINVAL;
      target_ulong priv, isel, vgein;
@@ -XXX,XX +XXX,XX @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
      /* Decode register details from CSR number */
      virt = false;
 +    isel_reserved = false;
      switch (csrno) {
      case CSR_MIREG:
          iprio = env->miprio;
@@ -XXX,XX +XXX,XX @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
                                                    riscv_cpu_mxl_bits(env)),
                                      val, new_val, wr_mask);
          }
 +    } else {
 +        isel_reserved = true;
      }
-+    return rval;
+ done:
-+}
+     if (ret) {
-+
+-        return (env->virt_enabled && virt) ?
-+static RISCVException rmw_seed(CPURISCVState *env, int csrno,
++        return (env->virt_enabled && virt && !isel_reserved) ?
-+                               target_ulong *ret_value,
+                RISCV_EXCP_VIRT_INSTRUCTION_FAULT : RISCV_EXCP_ILLEGAL_INST;
 +                               target_ulong new_value,
 +                               target_ulong write_mask)
 +{
 +    target_ulong rval;
 +
 +    rval = riscv_new_csr_seed(new_value, write_mask);
 +
      if (ret_value) {
          *ret_value = rval;
      }
-diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
+     return RISCV_EXCP_NONE;
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/kvm/kvm-cpu.c
 +++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
      return ret;
  }
 +static int kvm_riscv_handle_csr(CPUState *cs, struct kvm_run *run)
 +{
 +    target_ulong csr_num = run->riscv_csr.csr_num;
 +    target_ulong new_value = run->riscv_csr.new_value;
 +    target_ulong write_mask = run->riscv_csr.write_mask;
 +    int ret = 0;
 +
 +    switch (csr_num) {
 +    case CSR_SEED:
 +        run->riscv_csr.ret_value = riscv_new_csr_seed(new_value, write_mask);
 +        break;
 +    default:
 +        qemu_log_mask(LOG_UNIMP,
 +                      "%s: un-handled CSR EXIT for CSR %lx\n",
 +                      __func__, csr_num);
 +        ret = -1;
 +        break;
 +    }
 +
 +    return ret;
 +}
 +
  int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
  {
      int ret = 0;
@@ -XXX,XX +XXX,XX @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
      case KVM_EXIT_RISCV_SBI:
          ret = kvm_riscv_handle_sbi(cs, run);
          break;
 +    case KVM_EXIT_RISCV_CSR:
 +        ret = kvm_riscv_handle_csr(cs, run);
 +        break;
      default:
          qemu_log_mask(LOG_UNIMP, "%s: un-handled exit reason %d\n",
                        __func__, run->exit_reason);
 --
-.45.1
+.41.0

-[PULL 28/28] target/riscv: raise an exception when CSRRS/CSRRC writes a read-only CSR
+[PULL v2 45/45] target/riscv: don't read CSR in riscv_csrrw_do64
-From: Yu-Ming Chang <yumin686@andestech.com>
+From: Nikita Shubin <n.shubin@yadro.com>
-Both CSRRS and CSRRC always read the addressed CSR and cause any read side
+As per ISA:
 effects regardless of rs1 and rd fields. Note that if rs1 specifies a register
 holding a zero value other than x0, the instruction will still attempt to write
 the unmodified value back to the CSR and will cause any attendant side effects.
-So if CSRRS or CSRRC tries to write a read-only CSR with rs1 which specifies
+"For CSRRWI, if rd=x0, then the instruction shall not read the CSR and
-a register holding a zero value, an illegal instruction exception should be
+shall not cause any of the side effects that might occur on a CSR read."
 raised.
-Signed-off-by: Yu-Ming Chang <yumin686@andestech.com>
+trans_csrrwi() and trans_csrrw() call do_csrw() if rd=x0, do_csrw() calls
 riscv_csrrw_do64(), via helper_csrw() passing NULL as *ret_value.
 Signed-off-by: Nikita Shubin <n.shubin@yadro.com>
 Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
-Message-ID: <20240403070823.80897-1-yumin686@andestech.com>
+Message-ID: <20230808090914.17634-1-nikita.shubin@maquefel.me>
 Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
 ---
- target/riscv/cpu.h       |  4 ++++
+ target/riscv/csr.c | 24 +++++++++++++++---------
- target/riscv/csr.c       | 51 ++++++++++++++++++++++++++++++++++++----
+file changed, 15 insertions(+), 9 deletions(-)
  target/riscv/op_helper.c |  6 ++---
 files changed, 53 insertions(+), 8 deletions(-)
-diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
-index XXXXXXX..XXXXXXX 100644
---- a/target/riscv/cpu.h
-+++ b/target/riscv/cpu.h
-@@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPURISCVState *env, vaddr *pc,
- void riscv_cpu_update_mask(CPURISCVState *env);
- bool riscv_cpu_is_32bit(RISCVCPU *cpu);
-+RISCVException riscv_csrr(CPURISCVState *env, int csrno,
-+                          target_ulong *ret_value);
- RISCVException riscv_csrrw(CPURISCVState *env, int csrno,
-                            target_ulong *ret_value,
-                            target_ulong new_value, target_ulong write_mask);
-@@ -XXX,XX +XXX,XX @@ typedef RISCVException (*riscv_csr_op_fn)(CPURISCVState *env, int csrno,
-                                           target_ulong new_value,
-                                           target_ulong write_mask);
-+RISCVException riscv_csrr_i128(CPURISCVState *env, int csrno,
-+                               Int128 *ret_value);
- RISCVException riscv_csrrw_i128(CPURISCVState *env, int csrno,
-                                 Int128 *ret_value,
-                                 Int128 new_value, Int128 write_mask);
 diff --git a/target/riscv/csr.c b/target/riscv/csr.c
 index XXXXXXX..XXXXXXX 100644
 --- a/target/riscv/csr.c
 +++ b/target/riscv/csr.c
-@@ -XXX,XX +XXX,XX @@ static RISCVException rmw_seed(CPURISCVState *env, int csrno,
- static inline RISCVException riscv_csrrw_check(CPURISCVState *env,
-                                                int csrno,
--                                               bool write_mask)
-+                                               bool write)
- {
-     /* check privileges and return RISCV_EXCP_ILLEGAL_INST if check fails */
-     bool read_only = get_field(csrno, 0xC00) == 3;
-@@ -XXX,XX +XXX,XX @@ static inline RISCVException riscv_csrrw_check(CPURISCVState *env,
-     }
-     /* read / write check */
--    if (write_mask && read_only) {
-+    if (write && read_only) {
-         return RISCV_EXCP_ILLEGAL_INST;
-     }
 @@ -XXX,XX +XXX,XX @@ static RISCVException riscv_csrrw_do64(CPURISCVState *env, int csrno,
-     return RISCV_EXCP_NONE;
+                                        target_ulong write_mask)
  }
 +RISCVException riscv_csrr(CPURISCVState *env, int csrno,
 +                           target_ulong *ret_value)
 +{
 +    RISCVException ret = riscv_csrrw_check(env, csrno, false);
 +    if (ret != RISCV_EXCP_NONE) {
 +        return ret;
 +    }
 +
 +    return riscv_csrrw_do64(env, csrno, ret_value, 0, 0);
 +}
 +
  RISCVException riscv_csrrw(CPURISCVState *env, int csrno,
                             target_ulong *ret_value,
                             target_ulong new_value, target_ulong write_mask)
  {
 -    RISCVException ret = riscv_csrrw_check(env, csrno, write_mask);
 +    RISCVException ret = riscv_csrrw_check(env, csrno, true);
      if (ret != RISCV_EXCP_NONE) {
          return ret;
      }
@@ -XXX,XX +XXX,XX @@ static RISCVException riscv_csrrw_do128(CPURISCVState *env, int csrno,
      return RISCV_EXCP_NONE;
  }
 +RISCVException riscv_csrr_i128(CPURISCVState *env, int csrno,
 +                               Int128 *ret_value)
 +{
 +    RISCVException ret;
 +
 +    ret = riscv_csrrw_check(env, csrno, false);
 +    if (ret != RISCV_EXCP_NONE) {
 +        return ret;
 +    }
 +
 +    if (csr_ops[csrno].read128) {
 +        return riscv_csrrw_do128(env, csrno, ret_value,
 +                                 int128_zero(), int128_zero());
 +    }
 +
 +    /*
 +     * Fall back to 64-bit version for now, if the 128-bit alternative isn't
 +     * at all defined.
 +     * Note, some CSRs don't need to extend to MXLEN (64 upper bits non
 +     * significant), for those, this fallback is correctly handling the
 +     * accesses
 +     */
 +    target_ulong old_value;
 +    ret = riscv_csrrw_do64(env, csrno, &old_value,
 +                           (target_ulong)0,
 +                           (target_ulong)0);
 +    if (ret == RISCV_EXCP_NONE && ret_value) {
 +        *ret_value = int128_make64(old_value);
 +    }
 +    return ret;
 +}
 +
  RISCVException riscv_csrrw_i128(CPURISCVState *env, int csrno,
                                  Int128 *ret_value,
                                  Int128 new_value, Int128 write_mask)
  {
      RISCVException ret;
+-    target_ulong old_value;
--    ret = riscv_csrrw_check(env, csrno, int128_nz(write_mask));
++    target_ulong old_value = 0;
-+    ret = riscv_csrrw_check(env, csrno, true);
-     if (ret != RISCV_EXCP_NONE) {
+     /* execute combined read/write operation if it exists */
-         return ret;
+     if (csr_ops[csrno].op) {
          return csr_ops[csrno].op(env, csrno, ret_value, new_value, write_mask);
      }
-diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
-index XXXXXXX..XXXXXXX 100644
+-    /* if no accessor exists then return failure */
---- a/target/riscv/op_helper.c
+-    if (!csr_ops[csrno].read) {
-+++ b/target/riscv/op_helper.c
+-        return RISCV_EXCP_ILLEGAL_INST;
-@@ -XXX,XX +XXX,XX @@ target_ulong helper_csrr(CPURISCVState *env, int csr)
+-    }
 -    /* read old value */
 -    ret = csr_ops[csrno].read(env, csrno, &old_value);
 -    if (ret != RISCV_EXCP_NONE) {
 -        return ret;
 +    /*
 +     * ret_value == NULL means that rd=x0 and we're coming from helper_csrw()
 +     * and we can't throw side effects caused by CSR reads.
 +     */
 +    if (ret_value) {
 +        /* if no accessor exists then return failure */
 +        if (!csr_ops[csrno].read) {
 +            return RISCV_EXCP_ILLEGAL_INST;
 +        }
 +        /* read old value */
 +        ret = csr_ops[csrno].read(env, csrno, &old_value);
 +        if (ret != RISCV_EXCP_NONE) {
 +            return ret;
 +        }
      }
-     target_ulong val = 0;
+     /* write value if writable and write mask set, otherwise drop writes */
 -    RISCVException ret = riscv_csrrw(env, csr, &val, 0, 0);
 +    RISCVException ret = riscv_csrr(env, csr, &val);
      if (ret != RISCV_EXCP_NONE) {
          riscv_raise_exception(env, ret, GETPC());
@@ -XXX,XX +XXX,XX @@ target_ulong helper_csrrw(CPURISCVState *env, int csr,
  target_ulong helper_csrr_i128(CPURISCVState *env, int csr)
  {
      Int128 rv = int128_zero();
 -    RISCVException ret = riscv_csrrw_i128(env, csr, &rv,
 -                                          int128_zero(),
 -                                          int128_zero());
 +    RISCVException ret = riscv_csrr_i128(env, csr, &rv);
      if (ret != RISCV_EXCP_NONE) {
          riscv_raise_exception(env, ret, GETPC());
 --
-.45.1
+.41.0

The following changes since commit ad10b4badc1dd5b28305f9b9f1168cf0aa3ae946:

Merge tag 'pull-error-2024-05-27' of https://repo.or.cz/qemu/armbru into staging (2024-05-27 06:40:42 -0700)

are available in the Git repository at:

https://github.com/alistair23/qemu.git tags/pull-riscv-to-apply-20240528

for you to fetch changes up to 1806da76cb81088ea026ca3441551782b850e393:

target/riscv: raise an exception when CSRRS/CSRRC writes a read-only CSR (2024-05-28 12:20:27 +1000)

----------------------------------------------------------------
RISC-V PR for 9.1

* APLICs add child earlier than realize
* Fix exposure of Zkr
* Raise exceptions on wrs.nto
* Implement SBI debug console (DBCN) calls for KVM
* Support 64-bit addresses for initrd
* Change RISCV_EXCP_SEMIHOST exception number to 63
* Tolerate KVM disable ext errors
* Set tval in breakpoints
* Add support for Zve32x extension
* Add support for Zve64x extension
* Relax vector register check in RISCV gdbstub
* Fix the element agnostic Vector function problem
* Fix Zvkb extension config
* Implement dynamic establishment of custom decoder
* Add th.sxstatus CSR emulation
* Fix Zvfhmin checking for vfwcvt.f.f.v and vfncvt.f.f.w instructions
* Check single width operator for vector fp widen instructions
* Check single width operator for vfncvt.rod.f.f.w
* Remove redudant SEW checking for vector fp narrow/widen instructions
* Prioritize pmp errors in raise_mmu_exception()
* Do not set mtval2 for non guest-page faults
* Remove experimental prefix from "B" extension
* Fixup CBO extension register calculation
* Fix the hart bit setting of AIA
* Fix reg_width in ricsv_gen_dynamic_vector_feature()
* Decode all of the pmpcfg and pmpaddr CSRs
* Raise an exception when CSRRS/CSRRC writes a read-only CSR

----------------------------------------------------------------
Alexei Filippov (1):
      target/riscv: do not set mtval2 for non guest-page faults

Alistair Francis (2):
      target/riscv: rvzicbo: Fixup CBO extension register calculation
      disas/riscv: Decode all of the pmpcfg and pmpaddr CSRs

Andrew Jones (2):
      target/riscv/kvm: Fix exposure of Zkr
      target/riscv: Raise exceptions on wrs.nto

Cheng Yang (1):
      hw/riscv/boot.c: Support 64-bit address for initrd

Christoph Müllner (1):
      riscv: thead: Add th.sxstatus CSR emulation

Clément Léger (1):
      target/riscv: change RISCV_EXCP_SEMIHOST exception number to 63

Daniel Henrique Barboza (6):
      target/riscv/kvm: implement SBI debug console (DBCN) calls
      target/riscv/kvm: tolerate KVM disable ext errors
      target/riscv/debug: set tval=pc in breakpoint exceptions
      trans_privileged.c.inc: set (m|s)tval on ebreak breakpoint
      target/riscv: prioritize pmp errors in raise_mmu_exception()
      riscv, gdbstub.c: fix reg_width in ricsv_gen_dynamic_vector_feature()

Huang Tao (2):
      target/riscv: Fix the element agnostic function problem
      target/riscv: Implement dynamic establishment of custom decoder

Jason Chien (3):
      target/riscv: Add support for Zve32x extension
      target/riscv: Add support for Zve64x extension
      target/riscv: Relax vector register check in RISCV gdbstub

Max Chou (4):
      target/riscv: rvv: Fix Zvfhmin checking for vfwcvt.f.f.v and vfncvt.f.f.w instructions
      target/riscv: rvv: Check single width operator for vector fp widen instructions
      target/riscv: rvv: Check single width operator for vfncvt.rod.f.f.w
      target/riscv: rvv: Remove redudant SEW checking for vector fp narrow/widen instructions

Rob Bradford (1):
      target/riscv: Remove experimental prefix from "B" extension

Yangyu Chen (1):
      target/riscv/cpu.c: fix Zvkb extension config

Yong-Xuan Wang (1):
      target/riscv/kvm.c: Fix the hart bit setting of AIA

Yu-Ming Chang (1):
      target/riscv: raise an exception when CSRRS/CSRRC writes a read-only CSR

yang.zhang (1):
      hw/intc/riscv_aplic: APLICs should add child earlier than realize

From: "yang.zhang" <yang.zhang@hexintek.com>

Since only root APLICs can have hw IRQ lines, aplic->parent should
be initialized first.

Fixes: e8f79343cf ("hw/intc: Add RISC-V AIA APLIC device emulation")
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Signed-off-by: yang.zhang <yang.zhang@hexintek.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240409014445.278-1-gaoshanliukou@163.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/intc/riscv_aplic.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_aplic.c
+++ b/hw/intc/riscv_aplic.c
@@ -XXX,XX +XXX,XX @@ DeviceState *riscv_aplic_create(hwaddr addr, hwaddr size,
     qdev_prop_set_bit(dev, "msimode", msimode);
     qdev_prop_set_bit(dev, "mmode", mmode);
 
+    if (parent) {
+        riscv_aplic_add_child(parent, dev);
+    }
+
     sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
 
     if (!is_kvm_aia(msimode)) {
         sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
     }
 
-    if (parent) {
-        riscv_aplic_add_child(parent, dev);
-    }
-
     if (!msimode) {
         for (i = 0; i < num_harts; i++) {
             CPUState *cpu = cpu_by_arch_id(hartid_base + i);
-- 
2.45.1

From: Andrew Jones <ajones@ventanamicro.com>

The Zkr extension may only be exposed to KVM guests if the VMM
implements the SEED CSR. Use the same implementation as TCG.

Without this patch, running with a KVM which does not forward the
SEED CSR access to QEMU will result in an ILL exception being
injected into the guest (this results in Linux guests crashing on
boot). And, when running with a KVM which does forward the access,
QEMU will crash, since QEMU doesn't know what to do with the exit.

Fixes: 3108e2f1c69d ("target/riscv/kvm: update KVM exts to Linux 6.8")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240422134605.534207-2-ajones@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.h         |  3 +++
 target/riscv/csr.c         | 18 ++++++++++++++----
 target/riscv/kvm/kvm-cpu.c | 25 +++++++++++++++++++++++++
 3 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -XXX,XX +XXX,XX @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops);
 
 void riscv_cpu_register_gdb_regs_for_features(CPUState *cs);
 
+target_ulong riscv_new_csr_seed(target_ulong new_value,
+                                target_ulong write_mask);
+
 uint8_t satp_mode_max_from_map(uint32_t map);
 const char *satp_mode_str(uint8_t satp_mode, bool is_32_bit);
 
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException write_upmbase(CPURISCVState *env, int csrno,
 #endif
 
 /* Crypto Extension */
-static RISCVException rmw_seed(CPURISCVState *env, int csrno,
-                               target_ulong *ret_value,
-                               target_ulong new_value,
-                               target_ulong write_mask)
+target_ulong riscv_new_csr_seed(target_ulong new_value,
+                                target_ulong write_mask)
 {
     uint16_t random_v;
     Error *random_e = NULL;
@@ -XXX,XX +XXX,XX @@ static RISCVException rmw_seed(CPURISCVState *env, int csrno,
         rval = random_v | SEED_OPST_ES16;
     }
 
+    return rval;
+}
+
+static RISCVException rmw_seed(CPURISCVState *env, int csrno,
+                               target_ulong *ret_value,
+                               target_ulong new_value,
+                               target_ulong write_mask)
+{
+    target_ulong rval;
+
+    rval = riscv_new_csr_seed(new_value, write_mask);
+
     if (ret_value) {
         *ret_value = rval;
     }
diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
     return ret;
 }
 
+static int kvm_riscv_handle_csr(CPUState *cs, struct kvm_run *run)
+{
+    target_ulong csr_num = run->riscv_csr.csr_num;
+    target_ulong new_value = run->riscv_csr.new_value;
+    target_ulong write_mask = run->riscv_csr.write_mask;
+    int ret = 0;
+
+    switch (csr_num) {
+    case CSR_SEED:
+        run->riscv_csr.ret_value = riscv_new_csr_seed(new_value, write_mask);
+        break;
+    default:
+        qemu_log_mask(LOG_UNIMP,
+                      "%s: un-handled CSR EXIT for CSR %lx\n",
+                      __func__, csr_num);
+        ret = -1;
+        break;
+    }
+
+    return ret;
+}
+
 int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
 {
     int ret = 0;
@@ -XXX,XX +XXX,XX @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
     case KVM_EXIT_RISCV_SBI:
         ret = kvm_riscv_handle_sbi(cs, run);
         break;
+    case KVM_EXIT_RISCV_CSR:
+        ret = kvm_riscv_handle_csr(cs, run);
+        break;
     default:
         qemu_log_mask(LOG_UNIMP, "%s: un-handled exit reason %d\n",
                       __func__, run->exit_reason);
-- 
2.45.1

From: Andrew Jones <ajones@ventanamicro.com>

Implementing wrs.nto to always just return is consistent with the
specification, as the instruction is permitted to terminate the
stall for any reason, but it's not useful for virtualization, where
we'd like the guest to trap to the hypervisor in order to allow
scheduling of the lock holding VCPU. Change to always immediately
raise exceptions when the appropriate conditions are present,
otherwise continue to just return. Note, immediately raising
exceptions is also consistent with the specification since the
time limit that should expire prior to the exception is
implementation-specific.

Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Christoph Müllner <christoph.muellner@vrull.eu>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240424142808.62936-2-ajones@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/helper.h                       |  1 +
 target/riscv/op_helper.c                    | 11 ++++++++
 target/riscv/insn_trans/trans_rvzawrs.c.inc | 29 ++++++++++++++-------
 3 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(csrrw_i128, tl, env, int, tl, tl, tl, tl)
 DEF_HELPER_1(sret, tl, env)
 DEF_HELPER_1(mret, tl, env)
 DEF_HELPER_1(wfi, void, env)
+DEF_HELPER_1(wrs_nto, void, env)
 DEF_HELPER_1(tlb_flush, void, env)
 DEF_HELPER_1(tlb_flush_all, void, env)
 /* Native Debug */
diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/op_helper.c
+++ b/target/riscv/op_helper.c
@@ -XXX,XX +XXX,XX @@ void helper_wfi(CPURISCVState *env)
     }
 }
 
+void helper_wrs_nto(CPURISCVState *env)
+{
+    if (env->virt_enabled && (env->priv == PRV_S || env->priv == PRV_U) &&
+        get_field(env->hstatus, HSTATUS_VTW) &&
+        !get_field(env->mstatus, MSTATUS_TW)) {
+        riscv_raise_exception(env, RISCV_EXCP_VIRT_INSTRUCTION_FAULT, GETPC());
+    } else if (env->priv != PRV_M && get_field(env->mstatus, MSTATUS_TW)) {
+        riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+    }
+}
+
 void helper_tlb_flush(CPURISCVState *env)
 {
     CPUState *cs = env_cpu(env);
diff --git a/target/riscv/insn_trans/trans_rvzawrs.c.inc b/target/riscv/insn_trans/trans_rvzawrs.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvzawrs.c.inc
+++ b/target/riscv/insn_trans/trans_rvzawrs.c.inc
@@ -XXX,XX +XXX,XX @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-static bool trans_wrs(DisasContext *ctx)
+static bool trans_wrs_sto(DisasContext *ctx, arg_wrs_sto *a)
 {
     if (!ctx->cfg_ptr->ext_zawrs) {
         return false;
@@ -XXX,XX +XXX,XX @@ static bool trans_wrs(DisasContext *ctx)
     return true;
 }
 
-#define GEN_TRANS_WRS(insn)                                     \
-static bool trans_ ## insn(DisasContext *ctx, arg_ ## insn *a)  \
-{                                                               \
-    (void)a;                                                    \
-    return trans_wrs(ctx);                                      \
-}
+static bool trans_wrs_nto(DisasContext *ctx, arg_wrs_nto *a)
+{
+    if (!ctx->cfg_ptr->ext_zawrs) {
+        return false;
+    }
 
-GEN_TRANS_WRS(wrs_nto)
-GEN_TRANS_WRS(wrs_sto)
+    /*
+     * Depending on the mode of execution, mstatus.TW and hstatus.VTW, wrs.nto
+     * should raise an exception when the implementation-specific bounded time
+     * limit has expired. Our time limit is zero, so we either return
+     * immediately, as does our implementation of wrs.sto, or raise an
+     * exception, as handled by the wrs.nto helper.
+     */
+#ifndef CONFIG_USER_ONLY
+    gen_helper_wrs_nto(tcg_env);
+#endif
+
+    /* We only get here when helper_wrs_nto() doesn't raise an exception. */
+    return trans_wrs_sto(ctx, NULL);
+}
-- 
2.45.1

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

SBI defines a Debug Console extension "DBCN" that will, in time, replace
the legacy console putchar and getchar SBI extensions.

The appeal of the DBCN extension is that it allows multiple bytes to be
read/written in the SBI console in a single SBI call.

As far as KVM goes, the DBCN calls are forwarded by an in-kernel KVM
module to userspace. But this will only happens if the KVM module
actually supports this SBI extension and we activate it.

We'll check for DBCN support during init time, checking if get-reg-list
is advertising KVM_RISCV_SBI_EXT_DBCN. In that case, we'll enable it via
kvm_set_one_reg() during kvm_arch_init_vcpu().

Finally, change kvm_riscv_handle_sbi() to handle the incoming calls for
SBI_EXT_DBCN, reading and writing as required.

A simple KVM guest with 'earlycon=sbi', running in an emulated RISC-V
host, takes around 20 seconds to boot without using DBCN. With this
patch we're taking around 14 seconds to boot due to the speed-up in the
terminal output.  There's no change in boot time if the guest isn't
using earlycon.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20240425155012.581366-1-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/sbi_ecall_interface.h |  17 +++++
 target/riscv/kvm/kvm-cpu.c         | 111 +++++++++++++++++++++++++++++
 2 files changed, 128 insertions(+)

diff --git a/target/riscv/sbi_ecall_interface.h b/target/riscv/sbi_ecall_interface.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/sbi_ecall_interface.h
+++ b/target/riscv/sbi_ecall_interface.h
@@ -XXX,XX +XXX,XX @@
 
 /* clang-format off */
 
+#define SBI_SUCCESS                      0
+#define SBI_ERR_FAILED                  -1
+#define SBI_ERR_NOT_SUPPORTED           -2
+#define SBI_ERR_INVALID_PARAM           -3
+#define SBI_ERR_DENIED                  -4
+#define SBI_ERR_INVALID_ADDRESS         -5
+#define SBI_ERR_ALREADY_AVAILABLE       -6
+#define SBI_ERR_ALREADY_STARTED         -7
+#define SBI_ERR_ALREADY_STOPPED         -8
+#define SBI_ERR_NO_SHMEM                -9
+
 /* SBI Extension IDs */
 #define SBI_EXT_0_1_SET_TIMER           0x0
 #define SBI_EXT_0_1_CONSOLE_PUTCHAR     0x1
@@ -XXX,XX +XXX,XX @@
 #define SBI_EXT_IPI                     0x735049
 #define SBI_EXT_RFENCE                  0x52464E43
 #define SBI_EXT_HSM                     0x48534D
+#define SBI_EXT_DBCN                    0x4442434E
 
 /* SBI function IDs for BASE extension */
 #define SBI_EXT_BASE_GET_SPEC_VERSION   0x0
@@ -XXX,XX +XXX,XX @@
 #define SBI_EXT_HSM_HART_STOP           0x1
 #define SBI_EXT_HSM_HART_GET_STATUS     0x2
 
+/* SBI function IDs for DBCN extension */
+#define SBI_EXT_DBCN_CONSOLE_WRITE      0x0
+#define SBI_EXT_DBCN_CONSOLE_READ       0x1
+#define SBI_EXT_DBCN_CONSOLE_WRITE_BYTE 0x2
+
 #define SBI_HSM_HART_STATUS_STARTED     0x0
 #define SBI_HSM_HART_STATUS_STOPPED     0x1
 #define SBI_HSM_HART_STATUS_START_PENDING   0x2
diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ static KVMCPUConfig kvm_v_vlenb = {
                    KVM_REG_RISCV_VECTOR_CSR_REG(vlenb)
 };
 
+static KVMCPUConfig kvm_sbi_dbcn = {
+    .name = "sbi_dbcn",
+    .kvm_reg_id = KVM_REG_RISCV | KVM_REG_SIZE_U64 |
+                  KVM_REG_RISCV_SBI_EXT | KVM_RISCV_SBI_EXT_DBCN
+};
+
 static void kvm_riscv_update_cpu_cfg_isa_ext(RISCVCPU *cpu, CPUState *cs)
 {
     CPURISCVState *env = &cpu->env;
@@ -XXX,XX +XXX,XX @@ static int uint64_cmp(const void *a, const void *b)
     return 0;
 }
 
+static void kvm_riscv_check_sbi_dbcn_support(RISCVCPU *cpu,
+                                             KVMScratchCPU *kvmcpu,
+                                             struct kvm_reg_list *reglist)
+{
+    struct kvm_reg_list *reg_search;
+
+    reg_search = bsearch(&kvm_sbi_dbcn.kvm_reg_id, reglist->reg, reglist->n,
+                         sizeof(uint64_t), uint64_cmp);
+
+    if (reg_search) {
+        kvm_sbi_dbcn.supported = true;
+    }
+}
+
 static void kvm_riscv_read_vlenb(RISCVCPU *cpu, KVMScratchCPU *kvmcpu,
                                  struct kvm_reg_list *reglist)
 {
@@ -XXX,XX +XXX,XX @@ static void kvm_riscv_init_multiext_cfg(RISCVCPU *cpu, KVMScratchCPU *kvmcpu)
     if (riscv_has_ext(&cpu->env, RVV)) {
         kvm_riscv_read_vlenb(cpu, kvmcpu, reglist);
     }
+
+    kvm_riscv_check_sbi_dbcn_support(cpu, kvmcpu, reglist);
 }
 
 static void riscv_init_kvm_registers(Object *cpu_obj)
@@ -XXX,XX +XXX,XX @@ static int kvm_vcpu_set_machine_ids(RISCVCPU *cpu, CPUState *cs)
     return ret;
 }
 
+static int kvm_vcpu_enable_sbi_dbcn(RISCVCPU *cpu, CPUState *cs)
+{
+    target_ulong reg = 1;
+
+    if (!kvm_sbi_dbcn.supported) {
+        return 0;
+    }
+
+    return kvm_set_one_reg(cs, kvm_sbi_dbcn.kvm_reg_id, &reg);
+}
+
 int kvm_arch_init_vcpu(CPUState *cs)
 {
     int ret = 0;
@@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs)
     kvm_riscv_update_cpu_misa_ext(cpu, cs);
     kvm_riscv_update_cpu_cfg_isa_ext(cpu, cs);
 
+    ret = kvm_vcpu_enable_sbi_dbcn(cpu, cs);
+
     return ret;
 }
 
@@ -XXX,XX +XXX,XX @@ bool kvm_arch_stop_on_emulation_error(CPUState *cs)
     return true;
 }
 
+static void kvm_riscv_handle_sbi_dbcn(CPUState *cs, struct kvm_run *run)
+{
+    g_autofree uint8_t *buf = NULL;
+    RISCVCPU *cpu = RISCV_CPU(cs);
+    target_ulong num_bytes;
+    uint64_t addr;
+    unsigned char ch;
+    int ret;
+
+    switch (run->riscv_sbi.function_id) {
+    case SBI_EXT_DBCN_CONSOLE_READ:
+    case SBI_EXT_DBCN_CONSOLE_WRITE:
+        num_bytes = run->riscv_sbi.args[0];
+
+        if (num_bytes == 0) {
+            run->riscv_sbi.ret[0] = SBI_SUCCESS;
+            run->riscv_sbi.ret[1] = 0;
+            break;
+        }
+
+        addr = run->riscv_sbi.args[1];
+
+        /*
+         * Handle the case where a 32 bit CPU is running in a
+         * 64 bit addressing env.
+         */
+        if (riscv_cpu_mxl(&cpu->env) == MXL_RV32) {
+            addr |= (uint64_t)run->riscv_sbi.args[2] << 32;
+        }
+
+        buf = g_malloc0(num_bytes);
+
+        if (run->riscv_sbi.function_id == SBI_EXT_DBCN_CONSOLE_READ) {
+            ret = qemu_chr_fe_read_all(serial_hd(0)->be, buf, num_bytes);
+            if (ret < 0) {
+                error_report("SBI_EXT_DBCN_CONSOLE_READ: error when "
+                             "reading chardev");
+                exit(1);
+            }
+
+            cpu_physical_memory_write(addr, buf, ret);
+        } else {
+            cpu_physical_memory_read(addr, buf, num_bytes);
+
+            ret = qemu_chr_fe_write_all(serial_hd(0)->be, buf, num_bytes);
+            if (ret < 0) {
+                error_report("SBI_EXT_DBCN_CONSOLE_WRITE: error when "
+                             "writing chardev");
+                exit(1);
+            }
+        }
+
+        run->riscv_sbi.ret[0] = SBI_SUCCESS;
+        run->riscv_sbi.ret[1] = ret;
+        break;
+    case SBI_EXT_DBCN_CONSOLE_WRITE_BYTE:
+        ch = run->riscv_sbi.args[0];
+        ret = qemu_chr_fe_write(serial_hd(0)->be, &ch, sizeof(ch));
+
+        if (ret < 0) {
+            error_report("SBI_EXT_DBCN_CONSOLE_WRITE_BYTE: error when "
+                         "writing chardev");
+            exit(1);
+        }
+
+        run->riscv_sbi.ret[0] = SBI_SUCCESS;
+        run->riscv_sbi.ret[1] = 0;
+        break;
+    default:
+        run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED;
+    }
+}
+
 static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
 {
     int ret = 0;
@@ -XXX,XX +XXX,XX @@ static int kvm_riscv_handle_sbi(CPUState *cs, struct kvm_run *run)
         }
         ret = 0;
         break;
+    case SBI_EXT_DBCN:
+        kvm_riscv_handle_sbi_dbcn(cs, run);
+        break;
     default:
         qemu_log_mask(LOG_UNIMP,
                       "%s: un-handled SBI EXIT, specific reasons is %lu\n",
-- 
2.45.1

From: Cheng Yang <yangcheng.work@foxmail.com>

Use qemu_fdt_setprop_u64() instead of qemu_fdt_setprop_cell()
to set the address of initrd in FDT to support 64-bit address.

Signed-off-by: Cheng Yang <yangcheng.work@foxmail.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <tencent_A4482251DD0890F312758FA6B33F60815609@qq.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/riscv/boot.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/hw/riscv/boot.c b/hw/riscv/boot.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/riscv/boot.c
+++ b/hw/riscv/boot.c
@@ -XXX,XX +XXX,XX @@ static void riscv_load_initrd(MachineState *machine, uint64_t kernel_entry)
     /* Some RISC-V machines (e.g. opentitan) don't have a fdt. */
     if (fdt) {
         end = start + size;
-        qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-start", start);
-        qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-end", end);
+        qemu_fdt_setprop_u64(fdt, "/chosen", "linux,initrd-start", start);
+        qemu_fdt_setprop_u64(fdt, "/chosen", "linux,initrd-end", end);
     }
 }
 
-- 
2.45.1

From: Clément Léger <cleger@rivosinc.com>

The current semihost exception number (16) is a reserved number (range
[16-17]). The upcoming double trap specification uses that number for
the double trap exception. Since the privileged spec (Table 22) defines
ranges for custom uses change the semihosting exception number to 63
which belongs to the range [48-63] in order to avoid any future
collisions with reserved exception.

Signed-off-by: Clément Léger <cleger@rivosinc.com>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240422135840.1959967-1-cleger@rivosinc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_bits.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_bits.h
+++ b/target/riscv/cpu_bits.h
@@ -XXX,XX +XXX,XX @@ typedef enum RISCVException {
     RISCV_EXCP_INST_PAGE_FAULT = 0xc, /* since: priv-1.10.0 */
     RISCV_EXCP_LOAD_PAGE_FAULT = 0xd, /* since: priv-1.10.0 */
     RISCV_EXCP_STORE_PAGE_FAULT = 0xf, /* since: priv-1.10.0 */
-    RISCV_EXCP_SEMIHOST = 0x10,
     RISCV_EXCP_INST_GUEST_PAGE_FAULT = 0x14,
     RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT = 0x15,
     RISCV_EXCP_VIRT_INSTRUCTION_FAULT = 0x16,
     RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT = 0x17,
+    RISCV_EXCP_SEMIHOST = 0x3f,
 } RISCVException;
 
 #define RISCV_EXCP_INT_FLAG                0x80000000
-- 
2.45.1

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

Running a KVM guest using a 6.9-rc3 kernel, in a 6.8 host that has zkr
enabled, will fail with a kernel oops SIGILL right at the start. The
reason is that we can't expose zkr without implementing the SEED CSR.
Disabling zkr in the guest would be a workaround, but if the KVM doesn't
allow it we'll error out and never boot.

In hindsight this is too strict. If we keep proceeding, despite not
disabling the extension in the KVM vcpu, we'll not add the extension in
the riscv,isa. The guest kernel will be unaware of the extension, i.e.
it doesn't matter if the KVM vcpu has it enabled underneath or not. So
it's ok to keep booting in this case.

Change our current logic to not error out if we fail to disable an
extension in kvm_set_one_reg(), but show a warning and keep booting. It
is important to throw a warning because we must make the user aware that
the extension is still available in the vcpu, meaning that an
ill-behaved guest can ignore the riscv,isa settings and  use the
extension.

The case we're handling happens with an EINVAL error code. If we fail to
disable the extension in KVM for any other reason, error out.

We'll also keep erroring out when we fail to enable an extension in KVM,
since adding the extension in riscv,isa at this point will cause a guest
malfunction because the extension isn't enabled in the vcpu.

Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240422171425.333037-2-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/kvm/kvm-cpu.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ static void kvm_riscv_update_cpu_cfg_isa_ext(RISCVCPU *cpu, CPUState *cs)
         reg = kvm_cpu_cfg_get(cpu, multi_ext_cfg);
         ret = kvm_set_one_reg(cs, id, &reg);
         if (ret != 0) {
-            error_report("Unable to %s extension %s in KVM, error %d",
-                         reg ? "enable" : "disable",
-                         multi_ext_cfg->name, ret);
-            exit(EXIT_FAILURE);
+            if (!reg && ret == -EINVAL) {
+                warn_report("KVM cannot disable extension %s",
+                            multi_ext_cfg->name);
+            } else {
+                error_report("Unable to enable extension %s in KVM, error %d",
+                             multi_ext_cfg->name, ret);
+                exit(EXIT_FAILURE);
+            }
         }
     }
 }
-- 
2.45.1

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

We're not setting (s/m)tval when triggering breakpoints of type 2
(mcontrol) and 6 (mcontrol6). According to the debug spec section
5.7.12, "Match Control Type 6":

"The Privileged Spec says that breakpoint exceptions that occur on
instruction fetches, loads, or stores update the tval CSR with either
zero or the faulting virtual address. The faulting virtual address for
an mcontrol6 trigger with action = 0 is the address being accessed and
which caused that trigger to fire."

A similar text is also found in the Debug spec section 5.7.11 w.r.t.
mcontrol.

Note that what we're doing ATM is not violating the spec, but it's
simple enough to set mtval/stval and it makes life easier for any
software that relies on this info.

Given that we always use action = 0, save the faulting address for the
mcontrol and mcontrol6 trigger breakpoints into env->badaddr, which is
used as as scratch area for traps with address information. 'tval' is
then set during riscv_cpu_do_interrupt().

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Message-ID: <20240416230437.1869024-2-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_helper.c | 1 +
 target/riscv/debug.c      | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_do_interrupt(CPUState *cs)
             tval = env->bins;
             break;
         case RISCV_EXCP_BREAKPOINT:
+            tval = env->badaddr;
             if (cs->watchpoint_hit) {
                 tval = cs->watchpoint_hit->hitaddr;
                 cs->watchpoint_hit = NULL;
diff --git a/target/riscv/debug.c b/target/riscv/debug.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/debug.c
+++ b/target/riscv/debug.c
@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_breakpoint(CPUState *cs)
                 if ((ctrl & TYPE2_EXEC) && (bp->pc == pc)) {
                     /* check U/S/M bit against current privilege level */
                     if ((ctrl >> 3) & BIT(env->priv)) {
+                        env->badaddr = pc;
                         return true;
                     }
                 }
@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_breakpoint(CPUState *cs)
                     if (env->virt_enabled) {
                         /* check VU/VS bit against current privilege level */
                         if ((ctrl >> 23) & BIT(env->priv)) {
+                            env->badaddr = pc;
                             return true;
                         }
                     } else {
                         /* check U/S/M bit against current privilege level */
                         if ((ctrl >> 3) & BIT(env->priv)) {
+                            env->badaddr = pc;
                             return true;
                         }
                     }
-- 
2.45.1

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

Privileged spec section 4.1.9 mentions:

"When a trap is taken into S-mode, stval is written with
exception-specific information to assist software in handling the trap.
(...)

If stval is written with a nonzero value when a breakpoint,
address-misaligned, access-fault, or page-fault exception occurs on an
instruction fetch, load, or store, then stval will contain the faulting
virtual address."

A similar text is found for mtval in section 3.1.16.

Setting mtval/stval in this scenario is optional, but some softwares read
these regs when handling ebreaks.

Write 'badaddr' in all ebreak breakpoints to write the appropriate
'tval' during riscv_do_cpu_interrrupt().

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20240416230437.1869024-3-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_privileged.c.inc | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/target/riscv/insn_trans/trans_privileged.c.inc b/target/riscv/insn_trans/trans_privileged.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_privileged.c.inc
+++ b/target/riscv/insn_trans/trans_privileged.c.inc
@@ -XXX,XX +XXX,XX @@ static bool trans_ebreak(DisasContext *ctx, arg_ebreak *a)
     if (pre == 0x01f01013 && ebreak == 0x00100073 && post == 0x40705013) {
         generate_exception(ctx, RISCV_EXCP_SEMIHOST);
     } else {
+        tcg_gen_st_tl(tcg_constant_tl(ebreak_addr), tcg_env,
+                      offsetof(CPURISCVState, badaddr));
         generate_exception(ctx, RISCV_EXCP_BREAKPOINT);
     }
     return true;
-- 
2.45.1

From: Jason Chien <jason.chien@sifive.com>

Add support for Zve32x extension and replace some checks for Zve32f with
Zve32x, since Zve32f depends on Zve32x.

Signed-off-by: Jason Chien <jason.chien@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <20240328022343.6871-2-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                  |  1 +
 target/riscv/cpu.c                      |  2 ++
 target/riscv/cpu_helper.c               |  2 +-
 target/riscv/csr.c                      |  2 +-
 target/riscv/tcg/tcg-cpu.c              | 16 ++++++++--------
 target/riscv/insn_trans/trans_rvv.c.inc |  4 ++--
 6 files changed, 15 insertions(+), 12 deletions(-)

From: Jason Chien <jason.chien@sifive.com>

Add support for Zve64x extension. Enabling Zve64f enables Zve64x and
enabling Zve64x enables Zve32x according to their dependency.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2107
Signed-off-by: Jason Chien <jason.chien@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <20240328022343.6871-3-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h     |  1 +
 target/riscv/cpu.c         |  2 ++
 target/riscv/tcg/tcg-cpu.c | 17 +++++++++++------
 3 files changed, 14 insertions(+), 6 deletions(-)

From: Jason Chien <jason.chien@sifive.com>

In current implementation, the gdbstub allows reading vector registers
only if V extension is supported. However, all vector extensions and
vector crypto extensions have the vector registers and they all depend
on Zve32x. The gdbstub should check for Zve32x instead.

Signed-off-by: Jason Chien <jason.chien@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Max Chou <max.chou@sifive.com>
Message-ID: <20240328022343.6871-4-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/gdbstub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/riscv/gdbstub.c b/target/riscv/gdbstub.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/gdbstub.c
+++ b/target/riscv/gdbstub.c
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_register_gdb_regs_for_features(CPUState *cs)
                                  gdb_find_static_feature("riscv-32bit-fpu.xml"),
                                  0);
     }
-    if (env->misa_ext & RVV) {
+    if (cpu->cfg.ext_zve32x) {
         gdb_register_coprocessor(cs, riscv_gdb_get_vector,
                                  riscv_gdb_set_vector,
                                  ricsv_gen_dynamic_vector_feature(cs, cs->gdb_num_regs),
-- 
2.45.1

From: Huang Tao <eric.huang@linux.alibaba.com>

In RVV and vcrypto instructions, the masked and tail elements are set to 1s
using vext_set_elems_1s function if the vma/vta bit is set. It is the element
agnostic policy.

However, this function can't deal the big endian situation. This patch fixes
the problem by adding handling of such case.

Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240325021654.6594-1-eric.huang@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/vector_internals.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vector_internals.c
+++ b/target/riscv/vector_internals.c
@@ -XXX,XX +XXX,XX @@ void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
     if (tot - cnt == 0) {
         return ;
     }
+
+    if (HOST_BIG_ENDIAN) {
+        /*
+         * Deal the situation when the elements are insdie
+         * only one uint64 block including setting the
+         * masked-off element.
+         */
+        if (((tot - 1) ^ cnt) < 8) {
+            memset(base + H1(tot - 1), -1, tot - cnt);
+            return;
+        }
+        /*
+         * Otherwise, at least cross two uint64_t blocks.
+         * Set first unaligned block.
+         */
+        if (cnt % 8 != 0) {
+            uint32_t j = ROUND_UP(cnt, 8);
+            memset(base + H1(j - 1), -1, j - cnt);
+            cnt = j;
+        }
+        /* Set other 64bit aligend blocks */
+    }
     memset(base + cnt, -1, tot - cnt);
 }
 
-- 
2.45.1

From: Yangyu Chen <cyy@cyyself.name>

This code has a typo that writes zvkb to zvkg, causing users can't
enable zvkb through the config. This patch gets this fixed.

Signed-off-by: Yangyu Chen <cyy@cyyself.name>
Fixes: ea61ef7097d0 ("target/riscv: Move vector crypto extensions to riscv_cpu_extensions")
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Max Chou <max.chou@sifive.com>
Reviewed-by:  Weiwei Li <liwei1518@gmail.com>
Message-ID: <tencent_7E34EEF0F90B9A68BF38BEE09EC6D4877C0A@qq.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ const RISCVCPUMultiExtConfig riscv_cpu_extensions[] = {
     /* Vector cryptography extensions */
     MULTI_EXT_CFG_BOOL("zvbb", ext_zvbb, false),
     MULTI_EXT_CFG_BOOL("zvbc", ext_zvbc, false),
-    MULTI_EXT_CFG_BOOL("zvkb", ext_zvkg, false),
+    MULTI_EXT_CFG_BOOL("zvkb", ext_zvkb, false),
     MULTI_EXT_CFG_BOOL("zvkg", ext_zvkg, false),
     MULTI_EXT_CFG_BOOL("zvkned", ext_zvkned, false),
     MULTI_EXT_CFG_BOOL("zvknha", ext_zvknha, false),
-- 
2.45.1

From: Huang Tao <eric.huang@linux.alibaba.com>

In this patch, we modify the decoder to be a freely composable data
structure instead of a hardcoded one. It can be dynamically builded up
according to the extensions.
This approach has several benefits:
1. Provides support for heterogeneous cpu architectures. As we add decoder in
   RISCVCPU, each cpu can have their own decoder, and the decoders can be
   different due to cpu's features.
2. Improve the decoding efficiency. We run the guard_func to see if the decoder
   can be added to the dynamic_decoder when building up the decoder. Therefore,
   there is no need to run the guard_func when decoding each instruction. It can
   improve the decoding efficiency
3. For vendor or dynamic cpus, it allows them to customize their own decoder
   functions to improve decoding efficiency, especially when vendor-defined
   instruction sets increase. Because of dynamic building up, it can skip the other
   decoder guard functions when decoding.
4. Pre patch for allowing adding a vendor decoder before decode_insn32() with minimal
   overhead for users that don't need this particular vendor decoder.

Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
Suggested-by: Christoph Muellner <christoph.muellner@vrull.eu>
Co-authored-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240506023607.29544-1-eric.huang@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.h         |  1 +
 target/riscv/tcg/tcg-cpu.h | 15 +++++++++++++++
 target/riscv/cpu.c         |  1 +
 target/riscv/tcg/tcg-cpu.c | 15 +++++++++++++++
 target/riscv/translate.c   | 31 +++++++++++++++----------------
 5 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
     uint32_t pmu_avail_ctrs;
     /* Mapping of events to counters */
     GHashTable *pmu_event_ctr_map;
+    const GPtrArray *decoders;
 };
 
 /**
diff --git a/target/riscv/tcg/tcg-cpu.h b/target/riscv/tcg/tcg-cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/tcg/tcg-cpu.h
+++ b/target/riscv/tcg/tcg-cpu.h
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp);
 void riscv_tcg_cpu_finalize_features(RISCVCPU *cpu, Error **errp);
 bool riscv_cpu_tcg_compatible(RISCVCPU *cpu);
 
+struct DisasContext;
+struct RISCVCPUConfig;
+typedef struct RISCVDecoder {
+    bool (*guard_func)(const struct RISCVCPUConfig *);
+    bool (*riscv_cpu_decode_fn)(struct DisasContext *, uint32_t);
+} RISCVDecoder;
+
+typedef bool (*riscv_cpu_decode_fn)(struct DisasContext *, uint32_t);
+
+extern const size_t decoder_table_size;
+
+extern const RISCVDecoder decoder_table[];
+
+void riscv_tcg_cpu_finalize_dynamic_decoder(RISCVCPU *cpu);
+
 #endif
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_finalize_features(RISCVCPU *cpu, Error **errp)
             error_propagate(errp, local_err);
             return;
         }
+        riscv_tcg_cpu_finalize_dynamic_decoder(cpu);
     } else if (kvm_enabled()) {
         riscv_kvm_cpu_finalize_features(cpu, &local_err);
         if (local_err != NULL) {
diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/tcg/tcg-cpu.c
+++ b/target/riscv/tcg/tcg-cpu.c
@@ -XXX,XX +XXX,XX @@ void riscv_tcg_cpu_finalize_features(RISCVCPU *cpu, Error **errp)
     }
 }
 
+void riscv_tcg_cpu_finalize_dynamic_decoder(RISCVCPU *cpu)
+{
+    GPtrArray *dynamic_decoders;
+    dynamic_decoders = g_ptr_array_sized_new(decoder_table_size);
+    for (size_t i = 0; i < decoder_table_size; ++i) {
+        if (decoder_table[i].guard_func &&
+            decoder_table[i].guard_func(&cpu->cfg)) {
+            g_ptr_array_add(dynamic_decoders,
+                            (gpointer)decoder_table[i].riscv_cpu_decode_fn);
+        }
+    }
+
+    cpu->decoders = dynamic_decoders;
+}
+
 bool riscv_cpu_tcg_compatible(RISCVCPU *cpu)
 {
     return object_dynamic_cast(OBJECT(cpu), TYPE_RISCV_CPU_HOST) == NULL;
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -XXX,XX +XXX,XX @@
 #include "exec/helper-info.c.inc"
 #undef  HELPER_H
 
+#include "tcg/tcg-cpu.h"
+
 /* global register indices */
 static TCGv cpu_gpr[32], cpu_gprh[32], cpu_pc, cpu_vl, cpu_vstart;
 static TCGv_i64 cpu_fpr[32]; /* assume F and D extensions */
@@ -XXX,XX +XXX,XX @@ typedef struct DisasContext {
     /* FRM is known to contain a valid value. */
     bool frm_valid;
     bool insn_start_updated;
+    const GPtrArray *decoders;
 } DisasContext;
 
 static inline bool has_ext(DisasContext *ctx, uint32_t ext)
@@ -XXX,XX +XXX,XX @@ static inline int insn_len(uint16_t first_word)
     return (first_word & 3) == 3 ? 4 : 2;
 }
 
+const RISCVDecoder decoder_table[] = {
+    { always_true_p, decode_insn32 },
+    { has_xthead_p, decode_xthead},
+    { has_XVentanaCondOps_p, decode_XVentanaCodeOps},
+};
+
+const size_t decoder_table_size = ARRAY_SIZE(decoder_table);
+
 static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode)
 {
-    /*
-     * A table with predicate (i.e., guard) functions and decoder functions
-     * that are tested in-order until a decoder matches onto the opcode.
-     */
-    static const struct {
-        bool (*guard_func)(const RISCVCPUConfig *);
-        bool (*decode_func)(DisasContext *, uint32_t);
-    } decoders[] = {
-        { always_true_p,  decode_insn32 },
-        { has_xthead_p, decode_xthead },
-        { has_XVentanaCondOps_p,  decode_XVentanaCodeOps },
-    };
-
     ctx->virt_inst_excp = false;
     ctx->cur_insn_len = insn_len(opcode);
     /* Check for compressed insn */
@@ -XXX,XX +XXX,XX @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode)
                                              ctx->base.pc_next + 2));
         ctx->opcode = opcode32;
 
-        for (size_t i = 0; i < ARRAY_SIZE(decoders); ++i) {
-            if (decoders[i].guard_func(ctx->cfg_ptr) &&
-                decoders[i].decode_func(ctx, opcode32)) {
+        for (guint i = 0; i < ctx->decoders->len; ++i) {
+            riscv_cpu_decode_fn func = g_ptr_array_index(ctx->decoders, i);
+            if (func(ctx, opcode32)) {
                 return;
             }
         }
@@ -XXX,XX +XXX,XX @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     ctx->itrigger = FIELD_EX32(tb_flags, TB_FLAGS, ITRIGGER);
     ctx->zero = tcg_constant_tl(0);
     ctx->virt_inst_excp = false;
+    ctx->decoders = cpu->decoders;
 }
 
 static void riscv_tr_tb_start(DisasContextBase *db, CPUState *cpu)
-- 
2.45.1

From: Christoph Müllner <christoph.muellner@vrull.eu>

The th.sxstatus CSR can be used to identify available custom extension
on T-Head CPUs. The CSR is documented here:
  https://github.com/T-head-Semi/thead-extension-spec/blob/master/xtheadsxstatus.adoc

An important property of this patch is, that the th.sxstatus MAEE field
is not set (indicating that XTheadMae is not available).
XTheadMae is a memory attribute extension (similar to Svpbmt) which is
implemented in many T-Head CPUs (C906, C910, etc.) and utilizes bits
in PTEs that are marked as reserved. QEMU maintainers prefer to not
implement XTheadMae, so we need give kernels a mechanism to identify
if XTheadMae is available in a system or not. And this patch introduces
this mechanism in QEMU in a way that's compatible with real HW
(i.e., probing the th.sxstatus.MAEE bit).

Further context can be found on the list:
https://lists.gnu.org/archive/html/qemu-devel/2024-02/msg00775.html

Reviewed-by: LIU Zhiwei <zhiwe_liu@linux.alibaba.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Message-ID: <20240429073656.2486732-1-christoph.muellner@vrull.eu>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 MAINTAINERS              |  1 +
 target/riscv/cpu.h       |  3 ++
 target/riscv/cpu.c       |  1 +
 target/riscv/th_csr.c    | 79 ++++++++++++++++++++++++++++++++++++++++
 target/riscv/meson.build |  1 +
 5 files changed, 85 insertions(+)
 create mode 100644 target/riscv/th_csr.c

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ L: qemu-riscv@nongnu.org
 S: Supported
 F: target/riscv/insn_trans/trans_xthead.c.inc
 F: target/riscv/xthead*.decode
+F: target/riscv/th_*
 F: disas/riscv-xthead*
 
 RISC-V XVentanaCondOps extension
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -XXX,XX +XXX,XX @@ target_ulong riscv_new_csr_seed(target_ulong new_value,
 uint8_t satp_mode_max_from_map(uint32_t map);
 const char *satp_mode_str(uint8_t satp_mode, bool is_32_bit);
 
+/* Implemented in th_csr.c */
+void th_register_custom_csrs(RISCVCPU *cpu);
+
 #endif /* RISCV_CPU_H */
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void rv64_thead_c906_cpu_init(Object *obj)
     cpu->cfg.mvendorid = THEAD_VENDOR_ID;
 #ifndef CONFIG_USER_ONLY
     set_satp_mode_max_supported(cpu, VM_1_10_SV39);
+    th_register_custom_csrs(cpu);
 #endif
 
     /* inherited from parent obj via riscv_cpu_init() */
diff --git a/target/riscv/th_csr.c b/target/riscv/th_csr.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/target/riscv/th_csr.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * T-Head-specific CSRs.
+ *
+ * Copyright (c) 2024 VRULL GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2 or later, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "cpu_vendorid.h"
+
+#define CSR_TH_SXSTATUS 0x5c0
+
+/* TH_SXSTATUS bits */
+#define TH_SXSTATUS_UCME        BIT(16)
+#define TH_SXSTATUS_MAEE        BIT(21)
+#define TH_SXSTATUS_THEADISAEE  BIT(22)
+
+typedef struct {
+    int csrno;
+    int (*insertion_test)(RISCVCPU *cpu);
+    riscv_csr_operations csr_ops;
+} riscv_csr;
+
+static RISCVException smode(CPURISCVState *env, int csrno)
+{
+    if (riscv_has_ext(env, RVS)) {
+        return RISCV_EXCP_NONE;
+    }
+
+    return RISCV_EXCP_ILLEGAL_INST;
+}
+
+static int test_thead_mvendorid(RISCVCPU *cpu)
+{
+    if (cpu->cfg.mvendorid != THEAD_VENDOR_ID) {
+        return -1;
+    }
+
+    return 0;
+}
+
+static RISCVException read_th_sxstatus(CPURISCVState *env, int csrno,
+                                       target_ulong *val)
+{
+    /* We don't set MAEE here, because QEMU does not implement MAEE. */
+    *val = TH_SXSTATUS_UCME | TH_SXSTATUS_THEADISAEE;
+    return RISCV_EXCP_NONE;
+}
+
+static riscv_csr th_csr_list[] = {
+    {
+        .csrno = CSR_TH_SXSTATUS,
+        .insertion_test = test_thead_mvendorid,
+        .csr_ops = { "th.sxstatus", smode, read_th_sxstatus }
+    }
+};
+
+void th_register_custom_csrs(RISCVCPU *cpu)
+{
+    for (size_t i = 0; i < ARRAY_SIZE(th_csr_list); i++) {
+        int csrno = th_csr_list[i].csrno;
+        riscv_csr_operations *csr_ops = &th_csr_list[i].csr_ops;
+        if (!th_csr_list[i].insertion_test(cpu)) {
+            riscv_set_csr_ops(csrno, csr_ops);
+        }
+    }
+}
diff --git a/target/riscv/meson.build b/target/riscv/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/meson.build
+++ b/target/riscv/meson.build
@@ -XXX,XX +XXX,XX @@ riscv_system_ss.add(files(
   'monitor.c',
   'machine.c',
   'pmu.c',
+  'th_csr.c',
   'time_helper.c',
   'riscv-qmp-cmds.c',
 ))
-- 
2.45.1

From: Max Chou <max.chou@sifive.com>

According v spec 18.4, only the vfwcvt.f.f.v and vfncvt.f.f.w
instructions will be affected by Zvfhmin extension.
And the vfwcvt.f.f.v and vfncvt.f.f.w instructions only support the
conversions of

* From 1*SEW(16/32) to 2*SEW(32/64)
* From 2*SEW(32/64) to 1*SEW(16/32)

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240322092600.1198921-2-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

From: Max Chou <max.chou@sifive.com>

The require_scale_rvf function only checks the double width operator for
the vector floating point widen instructions, so most of the widen
checking functions need to add require_rvf for single width operator.

The vfwcvt.f.x.v and vfwcvt.f.xu.v instructions convert single width
integer to double width float, so the opfxv_widen_check function doesn’t
need require_rvf for the single width operator(integer).

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240322092600.1198921-3-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 5 +++++
 1 file changed, 5 insertions(+)

From: Max Chou <max.chou@sifive.com>

If the checking functions check both the single and double width
operators at the same time, then the single width operator checking
functions (require_rvf[min]) will check whether the SEW is 8.

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240322092600.1198921-5-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

raise_mmu_exception(), as is today, is prioritizing guest page faults by
checking first if virt_enabled && !first_stage, and then considering the
regular inst/load/store faults.

There's no mention in the spec about guest page fault being a higher
priority that PMP faults. In fact, privileged spec section 3.7.1 says:

"Attempting to fetch an instruction from a PMP region that does not have
execute permissions raises an instruction access-fault exception.
Attempting to execute a load or load-reserved instruction which accesses
a physical address within a PMP region without read permissions raises a
load access-fault exception. Attempting to execute a store,
store-conditional, or AMO instruction which accesses a physical address
within a PMP region without write permissions raises a store
access-fault exception."

So, in fact, we're doing it wrong - PMP faults should always be thrown,
regardless of also being a first or second stage fault.

The way riscv_cpu_tlb_fill() and get_physical_address() work is
adequate: a TRANSLATE_PMP_FAIL error is immediately reported and
reflected in the 'pmp_violation' flag. What we need is to change
raise_mmu_exception() to prioritize it.

Reported-by: Joseph Chan <jchan@ventanamicro.com>
Fixes: 82d53adfbb ("target/riscv/cpu_helper.c: Invalid exception on MMU translation stage")
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240413105929.7030-1-alexei.filippov@syntacore.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_helper.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -XXX,XX +XXX,XX @@ static void raise_mmu_exception(CPURISCVState *env, target_ulong address,
 
     switch (access_type) {
     case MMU_INST_FETCH:
-        if (env->virt_enabled && !first_stage) {
+        if (pmp_violation) {
+            cs->exception_index = RISCV_EXCP_INST_ACCESS_FAULT;
+        } else if (env->virt_enabled && !first_stage) {
             cs->exception_index = RISCV_EXCP_INST_GUEST_PAGE_FAULT;
         } else {
-            cs->exception_index = pmp_violation ?
-                RISCV_EXCP_INST_ACCESS_FAULT : RISCV_EXCP_INST_PAGE_FAULT;
+            cs->exception_index = RISCV_EXCP_INST_PAGE_FAULT;
         }
         break;
     case MMU_DATA_LOAD:
-        if (two_stage && !first_stage) {
+        if (pmp_violation) {
+            cs->exception_index = RISCV_EXCP_LOAD_ACCESS_FAULT;
+        } else if (two_stage && !first_stage) {
             cs->exception_index = RISCV_EXCP_LOAD_GUEST_ACCESS_FAULT;
         } else {
-            cs->exception_index = pmp_violation ?
-                RISCV_EXCP_LOAD_ACCESS_FAULT : RISCV_EXCP_LOAD_PAGE_FAULT;
+            cs->exception_index = RISCV_EXCP_LOAD_PAGE_FAULT;
         }
         break;
     case MMU_DATA_STORE:
-        if (two_stage && !first_stage) {
+        if (pmp_violation) {
+            cs->exception_index = RISCV_EXCP_STORE_AMO_ACCESS_FAULT;
+        } else if (two_stage && !first_stage) {
             cs->exception_index = RISCV_EXCP_STORE_GUEST_AMO_ACCESS_FAULT;
         } else {
-            cs->exception_index = pmp_violation ?
-                RISCV_EXCP_STORE_AMO_ACCESS_FAULT :
-                RISCV_EXCP_STORE_PAGE_FAULT;
+            cs->exception_index = RISCV_EXCP_STORE_PAGE_FAULT;
         }
         break;
     default:
-- 
2.45.1

From: Alexei Filippov <alexei.filippov@syntacore.com>

Previous patch fixed the PMP priority in raise_mmu_exception() but we're still
setting mtval2 incorrectly. In riscv_cpu_tlb_fill(), after pmp check in 2 stage
translation part, mtval2 will be set in case of successes 2 stage translation but
failed pmp check.

In this case we gonna set mtval2 via env->guest_phys_fault_addr in context of
riscv_cpu_tlb_fill(), as this was a guest-page-fault, but it didn't and mtval2
should be zero, according to RISCV privileged spec sect. 9.4.4: When a guest
page-fault is taken into M-mode, mtval2 is written with either zero or guest
physical address that faulted, shifted by 2 bits. *For other traps, mtval2
is set to zero...*

Signed-off-by: Alexei Filippov <alexei.filippov@syntacore.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240503103052.6819-1-alexei.filippov@syntacore.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_helper.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
                               __func__, pa, ret, prot_pmp, tlb_size);
 
                 prot &= prot_pmp;
-            }
-
-            if (ret != TRANSLATE_SUCCESS) {
+            } else {
                 /*
                  * Guest physical address translation failed, this is a HS
                  * level exception
                  */
                 first_stage_error = false;
-                env->guest_phys_fault_addr = (im_address |
-                                              (address &
-                                               (TARGET_PAGE_SIZE - 1))) >> 2;
+                if (ret != TRANSLATE_PMP_FAIL) {
+                    env->guest_phys_fault_addr = (im_address |
+                                                  (address &
+                                                   (TARGET_PAGE_SIZE - 1))) >> 2;
+                }
             }
         }
     } else {
-- 
2.45.1

From: Rob Bradford <rbradford@rivosinc.com>

This extension has now been ratified:
https://jira.riscv.org/browse/RVS-2006 so the "x-" prefix can be
removed.

Since this is now a ratified extension add it to the list of extensions
included in the "max" CPU variant.

Signed-off-by: Rob Bradford <rbradford@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Message-ID: <20240514110217.22516-1-rbradford@rivosinc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c         | 2 +-
 target/riscv/tcg/tcg-cpu.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const MISAExtInfo misa_ext_info_arr[] = {
     MISA_EXT_INFO(RVJ, "x-j", "Dynamic translated languages"),
     MISA_EXT_INFO(RVV, "v", "Vector operations"),
     MISA_EXT_INFO(RVG, "g", "General purpose (IMAFD_Zicsr_Zifencei)"),
-    MISA_EXT_INFO(RVB, "x-b", "Bit manipulation (Zba_Zbb_Zbs)")
+    MISA_EXT_INFO(RVB, "b", "Bit manipulation (Zba_Zbb_Zbs)")
 };
 
 static void riscv_cpu_validate_misa_mxl(RISCVCPUClass *mcc)
diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/tcg/tcg-cpu.c
+++ b/target/riscv/tcg/tcg-cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_init_max_cpu_extensions(Object *obj)
     const RISCVCPUMultiExtConfig *prop;
 
     /* Enable RVG, RVJ and RVV that are disabled by default */
-    riscv_cpu_set_misa_ext(env, env->misa_ext | RVG | RVJ | RVV);
+    riscv_cpu_set_misa_ext(env, env->misa_ext | RVB | RVG | RVJ | RVV);
 
     for (prop = riscv_cpu_extensions; prop && prop->name; prop++) {
         isa_ext_update_enabled(cpu, prop->offset, true);
-- 
2.45.1

From: Alistair Francis <alistair23@gmail.com>

When running the instruction

```
    cbo.flush 0(x0)
```

QEMU would segfault.

The issue was in cpu_gpr[a->rs1] as QEMU does not have cpu_gpr[0]
allocated.

In order to fix this let's use the existing get_address()
helper. This also has the benefit of performing pointer mask
calculations on the address specified in rs1.

The pointer masking specificiation specifically states:

"""
Cache Management Operations: All instructions in Zicbom, Zicbop and Zicboz
"""

So this is the correct behaviour and we previously have been incorrectly
not masking the address.

Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Reported-by: Fabian Thomas <fabian.thomas@cispa.de>
Fixes: e05da09b7cfd ("target/riscv: implement Zicbom extension")
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240514023910.301766-1-alistair.francis@wdc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvzicbo.c.inc | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/target/riscv/insn_trans/trans_rvzicbo.c.inc b/target/riscv/insn_trans/trans_rvzicbo.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvzicbo.c.inc
+++ b/target/riscv/insn_trans/trans_rvzicbo.c.inc
@@ -XXX,XX +XXX,XX @@
 static bool trans_cbo_clean(DisasContext *ctx, arg_cbo_clean *a)
 {
     REQUIRE_ZICBOM(ctx);
-    gen_helper_cbo_clean_flush(tcg_env, cpu_gpr[a->rs1]);
+    TCGv src = get_address(ctx, a->rs1, 0);
+
+    gen_helper_cbo_clean_flush(tcg_env, src);
     return true;
 }
 
 static bool trans_cbo_flush(DisasContext *ctx, arg_cbo_flush *a)
 {
     REQUIRE_ZICBOM(ctx);
-    gen_helper_cbo_clean_flush(tcg_env, cpu_gpr[a->rs1]);
+    TCGv src = get_address(ctx, a->rs1, 0);
+
+    gen_helper_cbo_clean_flush(tcg_env, src);
     return true;
 }
 
 static bool trans_cbo_inval(DisasContext *ctx, arg_cbo_inval *a)
 {
     REQUIRE_ZICBOM(ctx);
-    gen_helper_cbo_inval(tcg_env, cpu_gpr[a->rs1]);
+    TCGv src = get_address(ctx, a->rs1, 0);
+
+    gen_helper_cbo_inval(tcg_env, src);
     return true;
 }
 
 static bool trans_cbo_zero(DisasContext *ctx, arg_cbo_zero *a)
 {
     REQUIRE_ZICBOZ(ctx);
-    gen_helper_cbo_zero(tcg_env, cpu_gpr[a->rs1]);
+    TCGv src = get_address(ctx, a->rs1, 0);
+
+    gen_helper_cbo_zero(tcg_env, src);
     return true;
 }
-- 
2.45.1

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

In AIA spec, each hart (or each hart within a group) has a unique hart
number to locate the memory pages of interrupt files in the address
space. The number of bits required to represent any hart number is equal
to ceil(log2(hmax + 1)), where hmax is the largest hart number among
groups.

However, if the largest hart number among groups is a power of 2, QEMU
will pass an inaccurate hart-index-bit setting to Linux. For example, when
the guest OS has 4 harts, only ceil(log2(3 + 1)) = 2 bits are sufficient
to represent 4 harts, but we passes 3 to Linux. The code needs to be
updated to ensure accurate hart-index-bit settings.

Additionally, a Linux patch[1] is necessary to correctly recover the hart
index when the guest OS has only 1 hart, where the hart-index-bit is 0.

[1] https://lore.kernel.org/lkml/20240415064905.25184-1-yongxuan.wang@sifive.com/t/

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240515091129.28116-1-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/kvm/kvm-cpu.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -XXX,XX +XXX,XX @@ void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
         }
     }
 
-    hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
+
+    if (max_hart_per_socket > 1) {
+        max_hart_per_socket--;
+        hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
+    } else {
+        hart_bits = 0;
+    }
+
     ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
                             KVM_DEV_RISCV_AIA_CONFIG_HART_BITS,
                             &hart_bits, true, NULL);
-- 
2.45.1

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

Commit 33a24910ae changed 'reg_width' to use 'vlenb', i.e. vector length
in bytes, when in this context we want 'reg_width' as the length in
bits.

Fix 'reg_width' back to the value in bits like 7cb59921c05a
("target/riscv/gdbstub.c: use 'vlenb' instead of shifting 'vlen'") set
beforehand.

While we're at it, rename 'reg_width' to 'bitsize' to provide a bit more
clarity about what the variable represents. 'bitsize' is also used in
riscv_gen_dynamic_csr_feature() with the same purpose, i.e. as an input to
gdb_feature_builder_append_reg().

Cc: Akihiko Odaki <akihiko.odaki@daynix.com>
Cc: Alex Bennée <alex.bennee@linaro.org>
Reported-by: Robin Dapp <rdapp.gcc@gmail.com>
Fixes: 33a24910ae ("target/riscv: Use GDBFeature for dynamic XML")
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Acked-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240517203054.880861-2-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/gdbstub.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/target/riscv/gdbstub.c b/target/riscv/gdbstub.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/gdbstub.c
+++ b/target/riscv/gdbstub.c
@@ -XXX,XX +XXX,XX @@ static GDBFeature *riscv_gen_dynamic_csr_feature(CPUState *cs, int base_reg)
 static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
 {
     RISCVCPU *cpu = RISCV_CPU(cs);
-    int reg_width = cpu->cfg.vlenb;
+    int bitsize = cpu->cfg.vlenb << 3;
     GDBFeatureBuilder builder;
     int i;
 
@@ -XXX,XX +XXX,XX @@ static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
 
     /* First define types and totals in a whole VL */
     for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) {
-        int count = reg_width / vec_lanes[i].size;
+        int count = bitsize / vec_lanes[i].size;
         gdb_feature_builder_append_tag(
             &builder, "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>",
             vec_lanes[i].id, vec_lanes[i].gdb_type, count);
@@ -XXX,XX +XXX,XX @@ static GDBFeature *ricsv_gen_dynamic_vector_feature(CPUState *cs, int base_reg)
     /* Define vector registers */
     for (i = 0; i < 32; i++) {
         gdb_feature_builder_append_reg(&builder, g_strdup_printf("v%d", i),
-                                       reg_width, i, "riscv_vector", "vector");
+                                       bitsize, i, "riscv_vector", "vector");
     }
 
     gdb_feature_builder_end(&builder);
-- 
2.45.1

From: Alistair Francis <alistair23@gmail.com>

Previously we only listed a single pmpcfg CSR and the first 16 pmpaddr
CSRs. This patch fixes this to list all 16 pmpcfg and all 64 pmpaddr
CSRs are part of the disassembly.

Reported-by: Eric DeVolder <eric_devolder@yahoo.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Fixes: ea10325917 ("RISC-V Disassembler")
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-ID: <20240514051615.330979-1-alistair.francis@wdc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 disas/riscv.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

diff --git a/disas/riscv.c b/disas/riscv.c
index XXXXXXX..XXXXXXX 100644
--- a/disas/riscv.c
+++ b/disas/riscv.c
@@ -XXX,XX +XXX,XX @@ static const char *csr_name(int csrno)
     case 0x0383: return "mibound";
     case 0x0384: return "mdbase";
     case 0x0385: return "mdbound";
-    case 0x03a0: return "pmpcfg3";
+    case 0x03a0: return "pmpcfg0";
+    case 0x03a1: return "pmpcfg1";
+    case 0x03a2: return "pmpcfg2";
+    case 0x03a3: return "pmpcfg3";
+    case 0x03a4: return "pmpcfg4";
+    case 0x03a5: return "pmpcfg5";
+    case 0x03a6: return "pmpcfg6";
+    case 0x03a7: return "pmpcfg7";
+    case 0x03a8: return "pmpcfg8";
+    case 0x03a9: return "pmpcfg9";
+    case 0x03aa: return "pmpcfg10";
+    case 0x03ab: return "pmpcfg11";
+    case 0x03ac: return "pmpcfg12";
+    case 0x03ad: return "pmpcfg13";
+    case 0x03ae: return "pmpcfg14";
+    case 0x03af: return "pmpcfg15";
     case 0x03b0: return "pmpaddr0";
     case 0x03b1: return "pmpaddr1";
     case 0x03b2: return "pmpaddr2";
@@ -XXX,XX +XXX,XX @@ static const char *csr_name(int csrno)
     case 0x03bd: return "pmpaddr13";
     case 0x03be: return "pmpaddr14";
     case 0x03bf: return "pmpaddr15";
+    case 0x03c0: return "pmpaddr16";
+    case 0x03c1: return "pmpaddr17";
+    case 0x03c2: return "pmpaddr18";
+    case 0x03c3: return "pmpaddr19";
+    case 0x03c4: return "pmpaddr20";
+    case 0x03c5: return "pmpaddr21";
+    case 0x03c6: return "pmpaddr22";
+    case 0x03c7: return "pmpaddr23";
+    case 0x03c8: return "pmpaddr24";
+    case 0x03c9: return "pmpaddr25";
+    case 0x03ca: return "pmpaddr26";
+    case 0x03cb: return "pmpaddr27";
+    case 0x03cc: return "pmpaddr28";
+    case 0x03cd: return "pmpaddr29";
+    case 0x03ce: return "pmpaddr30";
+    case 0x03cf: return "pmpaddr31";
+    case 0x03d0: return "pmpaddr32";
+    case 0x03d1: return "pmpaddr33";
+    case 0x03d2: return "pmpaddr34";
+    case 0x03d3: return "pmpaddr35";
+    case 0x03d4: return "pmpaddr36";
+    case 0x03d5: return "pmpaddr37";
+    case 0x03d6: return "pmpaddr38";
+    case 0x03d7: return "pmpaddr39";
+    case 0x03d8: return "pmpaddr40";
+    case 0x03d9: return "pmpaddr41";
+    case 0x03da: return "pmpaddr42";
+    case 0x03db: return "pmpaddr43";
+    case 0x03dc: return "pmpaddr44";
+    case 0x03dd: return "pmpaddr45";
+    case 0x03de: return "pmpaddr46";
+    case 0x03df: return "pmpaddr47";
+    case 0x03e0: return "pmpaddr48";
+    case 0x03e1: return "pmpaddr49";
+    case 0x03e2: return "pmpaddr50";
+    case 0x03e3: return "pmpaddr51";
+    case 0x03e4: return "pmpaddr52";
+    case 0x03e5: return "pmpaddr53";
+    case 0x03e6: return "pmpaddr54";
+    case 0x03e7: return "pmpaddr55";
+    case 0x03e8: return "pmpaddr56";
+    case 0x03e9: return "pmpaddr57";
+    case 0x03ea: return "pmpaddr58";
+    case 0x03eb: return "pmpaddr59";
+    case 0x03ec: return "pmpaddr60";
+    case 0x03ed: return "pmpaddr61";
+    case 0x03ee: return "pmpaddr62";
+    case 0x03ef: return "pmpaddr63";
     case 0x0780: return "mtohost";
     case 0x0781: return "mfromhost";
     case 0x0782: return "mreset";
-- 
2.45.1

From: Yu-Ming Chang <yumin686@andestech.com>

Both CSRRS and CSRRC always read the addressed CSR and cause any read side
effects regardless of rs1 and rd fields. Note that if rs1 specifies a register
holding a zero value other than x0, the instruction will still attempt to write
the unmodified value back to the CSR and will cause any attendant side effects.

So if CSRRS or CSRRC tries to write a read-only CSR with rs1 which specifies
a register holding a zero value, an illegal instruction exception should be
raised.

Signed-off-by: Yu-Ming Chang <yumin686@andestech.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20240403070823.80897-1-yumin686@andestech.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.h       |  4 ++++
 target/riscv/csr.c       | 51 ++++++++++++++++++++++++++++++++++++----
 target/riscv/op_helper.c |  6 ++---
 3 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPURISCVState *env, vaddr *pc,
 void riscv_cpu_update_mask(CPURISCVState *env);
 bool riscv_cpu_is_32bit(RISCVCPU *cpu);
 
+RISCVException riscv_csrr(CPURISCVState *env, int csrno,
+                          target_ulong *ret_value);
 RISCVException riscv_csrrw(CPURISCVState *env, int csrno,
                            target_ulong *ret_value,
                            target_ulong new_value, target_ulong write_mask);
@@ -XXX,XX +XXX,XX @@ typedef RISCVException (*riscv_csr_op_fn)(CPURISCVState *env, int csrno,
                                           target_ulong new_value,
                                           target_ulong write_mask);
 
+RISCVException riscv_csrr_i128(CPURISCVState *env, int csrno,
+                               Int128 *ret_value);
 RISCVException riscv_csrrw_i128(CPURISCVState *env, int csrno,
                                 Int128 *ret_value,
                                 Int128 new_value, Int128 write_mask);
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException rmw_seed(CPURISCVState *env, int csrno,
 
 static inline RISCVException riscv_csrrw_check(CPURISCVState *env,
                                                int csrno,
-                                               bool write_mask)
+                                               bool write)
 {
     /* check privileges and return RISCV_EXCP_ILLEGAL_INST if check fails */
     bool read_only = get_field(csrno, 0xC00) == 3;
@@ -XXX,XX +XXX,XX @@ static inline RISCVException riscv_csrrw_check(CPURISCVState *env,
     }
 
     /* read / write check */
-    if (write_mask && read_only) {
+    if (write && read_only) {
         return RISCV_EXCP_ILLEGAL_INST;
     }
 
@@ -XXX,XX +XXX,XX @@ static RISCVException riscv_csrrw_do64(CPURISCVState *env, int csrno,
     return RISCV_EXCP_NONE;
 }
 
+RISCVException riscv_csrr(CPURISCVState *env, int csrno,
+                           target_ulong *ret_value)
+{
+    RISCVException ret = riscv_csrrw_check(env, csrno, false);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
+
+    return riscv_csrrw_do64(env, csrno, ret_value, 0, 0);
+}
+
 RISCVException riscv_csrrw(CPURISCVState *env, int csrno,
                            target_ulong *ret_value,
                            target_ulong new_value, target_ulong write_mask)
 {
-    RISCVException ret = riscv_csrrw_check(env, csrno, write_mask);
+    RISCVException ret = riscv_csrrw_check(env, csrno, true);
     if (ret != RISCV_EXCP_NONE) {
         return ret;
     }
@@ -XXX,XX +XXX,XX @@ static RISCVException riscv_csrrw_do128(CPURISCVState *env, int csrno,
     return RISCV_EXCP_NONE;
 }
 
+RISCVException riscv_csrr_i128(CPURISCVState *env, int csrno,
+                               Int128 *ret_value)
+{
+    RISCVException ret;
+
+    ret = riscv_csrrw_check(env, csrno, false);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
+
+    if (csr_ops[csrno].read128) {
+        return riscv_csrrw_do128(env, csrno, ret_value,
+                                 int128_zero(), int128_zero());
+    }
+
+    /*
+     * Fall back to 64-bit version for now, if the 128-bit alternative isn't
+     * at all defined.
+     * Note, some CSRs don't need to extend to MXLEN (64 upper bits non
+     * significant), for those, this fallback is correctly handling the
+     * accesses
+     */
+    target_ulong old_value;
+    ret = riscv_csrrw_do64(env, csrno, &old_value,
+                           (target_ulong)0,
+                           (target_ulong)0);
+    if (ret == RISCV_EXCP_NONE && ret_value) {
+        *ret_value = int128_make64(old_value);
+    }
+    return ret;
+}
+
 RISCVException riscv_csrrw_i128(CPURISCVState *env, int csrno,
                                 Int128 *ret_value,
                                 Int128 new_value, Int128 write_mask)
 {
     RISCVException ret;
 
-    ret = riscv_csrrw_check(env, csrno, int128_nz(write_mask));
+    ret = riscv_csrrw_check(env, csrno, true);
     if (ret != RISCV_EXCP_NONE) {
         return ret;
     }
diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/op_helper.c
+++ b/target/riscv/op_helper.c
@@ -XXX,XX +XXX,XX @@ target_ulong helper_csrr(CPURISCVState *env, int csr)
     }
 
     target_ulong val = 0;
-    RISCVException ret = riscv_csrrw(env, csr, &val, 0, 0);
+    RISCVException ret = riscv_csrr(env, csr, &val);
 
     if (ret != RISCV_EXCP_NONE) {
         riscv_raise_exception(env, ret, GETPC());
@@ -XXX,XX +XXX,XX @@ target_ulong helper_csrrw(CPURISCVState *env, int csr,
 target_ulong helper_csrr_i128(CPURISCVState *env, int csr)
 {
     Int128 rv = int128_zero();
-    RISCVException ret = riscv_csrrw_i128(env, csr, &rv,
-                                          int128_zero(),
-                                          int128_zero());
+    RISCVException ret = riscv_csrr_i128(env, csr, &rv);
 
     if (ret != RISCV_EXCP_NONE) {
         riscv_raise_exception(env, ret, GETPC());
-- 
2.45.1

The following changes since commit c5ea91da443b458352c1b629b490ee6631775cb4:

Merge tag 'pull-trivial-patches' of https://gitlab.com/mjt0k/qemu into staging (2023-09-08 10:06:25 -0400)

are available in the Git repository at:

https://github.com/alistair23/qemu.git tags/pull-riscv-to-apply-20230911

for you to fetch changes up to e7a03409f29e2da59297d55afbaec98c96e43e3a:

target/riscv: don't read CSR in riscv_csrrw_do64 (2023-09-11 11:45:55 +1000)

----------------------------------------------------------------
First RISC-V PR for 8.2

* Remove 'host' CPU from TCG
 * riscv_htif Fixup printing on big endian hosts
 * Add zmmul isa string
 * Add smepmp isa string
 * Fix page_check_range use in fault-only-first
 * Use existing lookup tables for MixColumns
 * Add RISC-V vector cryptographic instruction set support
 * Implement WARL behaviour for mcountinhibit/mcounteren
 * Add Zihintntl extension ISA string to DTS
 * Fix zfa fleq.d and fltq.d
 * Fix upper/lower mtime write calculation
 * Make rtc variable names consistent
 * Use abi type for linux-user target_ucontext
 * Add RISC-V KVM AIA Support
 * Fix riscv,pmu DT node path in the virt machine
 * Update CSR bits name for svadu extension
 * Mark zicond non-experimental
 * Fix satp_mode_finalize() when satp_mode.supported = 0
 * Fix non-KVM --enable-debug build
 * Add new extensions to hwprobe
 * Use accelerated helper for AES64KS1I
 * Allocate itrigger timers only once
 * Respect mseccfg.RLB for pmpaddrX changes
 * Align the AIA model to v1.0 ratified spec
 * Don't read the CSR in riscv_csrrw_do64

----------------------------------------------------------------
Akihiko Odaki (1):
      target/riscv: Allocate itrigger timers only once

Ard Biesheuvel (2):
      target/riscv: Use existing lookup tables for MixColumns
      target/riscv: Use accelerated helper for AES64KS1I

Conor Dooley (1):
      hw/riscv: virt: Fix riscv,pmu DT node path

Daniel Henrique Barboza (6):
      target/riscv/cpu.c: do not run 'host' CPU with TCG
      target/riscv/cpu.c: add zmmul isa string
      target/riscv/cpu.c: add smepmp isa string
      target/riscv: fix satp_mode_finalize() when satp_mode.supported = 0
      hw/riscv/virt.c: fix non-KVM --enable-debug build
      hw/intc/riscv_aplic.c fix non-KVM --enable-debug build

Dickon Hood (2):
      target/riscv: Refactor translation of vector-widening instruction
      target/riscv: Add Zvbb ISA extension support

Jason Chien (3):
      target/riscv: Add Zihintntl extension ISA string to DTS
      hw/intc: Fix upper/lower mtime write calculation
      hw/intc: Make rtc variable names consistent

Kiran Ostrolenk (4):
      target/riscv: Refactor some of the generic vector functionality
      target/riscv: Refactor vector-vector translation macro
      target/riscv: Refactor some of the generic vector functionality
      target/riscv: Add Zvknh ISA extension support

LIU Zhiwei (3):
      target/riscv: Fix page_check_range use in fault-only-first
      target/riscv: Fix zfa fleq.d and fltq.d
      linux-user/riscv: Use abi type for target_ucontext

Lawrence Hunter (2):
      target/riscv: Add Zvbc ISA extension support
      target/riscv: Add Zvksh ISA extension support

Leon Schuermann (1):
      target/riscv/pmp.c: respect mseccfg.RLB for pmpaddrX changes

Max Chou (3):
      crypto: Create sm4_subword
      crypto: Add SM4 constant parameter CK
      target/riscv: Add Zvksed ISA extension support

Nazar Kazakov (4):
      target/riscv: Remove redundant "cpu_vl == 0" checks
      target/riscv: Move vector translation checks
      target/riscv: Add Zvkned ISA extension support
      target/riscv: Add Zvkg ISA extension support

Nikita Shubin (1):
      target/riscv: don't read CSR in riscv_csrrw_do64

Rob Bradford (1):
      target/riscv: Implement WARL behaviour for mcountinhibit/mcounteren

Robbin Ehn (1):
      linux-user/riscv: Add new extensions to hwprobe

Thomas Huth (2):
      hw/char/riscv_htif: Fix printing of console characters on big endian hosts
      hw/char/riscv_htif: Fix the console syscall on big endian hosts

Tommy Wu (1):
      target/riscv: Align the AIA model to v1.0 ratified spec

Vineet Gupta (1):
      riscv: zicond: make non-experimental

Weiwei Li (1):
      target/riscv: Update CSR bits name for svadu extension

Yong-Xuan Wang (5):
      target/riscv: support the AIA device emulation with KVM enabled
      target/riscv: check the in-kernel irqchip support
      target/riscv: Create an KVM AIA irqchip
      target/riscv: update APLIC and IMSIC to support KVM AIA
      target/riscv: select KVM AIA in riscv virt machine

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

The 'host' CPU is available in a CONFIG_KVM build and it's currently
available for all accels, but is a KVM only CPU. This means that in a
RISC-V KVM capable host we can do things like this:

$ ./build/qemu-system-riscv64 -M virt,accel=tcg -cpu host --nographic
qemu-system-riscv64: H extension requires priv spec 1.12.0

This CPU does not have a priv spec because we don't filter its extensions
via priv spec. We shouldn't be reaching riscv_cpu_realize_tcg() at all
with the 'host' CPU.

We don't have a way to filter the 'host' CPU out of the available CPU
options (-cpu help) if the build includes both KVM and TCG. What we can
do is to error out during riscv_cpu_realize_tcg() if the user chooses
the 'host' CPU with accel=tcg:

$ ./build/qemu-system-riscv64 -M virt,accel=tcg -cpu host --nographic
qemu-system-riscv64: 'host' CPU is not compatible with TCG acceleration

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230721133411.474105-1-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_realize_tcg(DeviceState *dev, Error **errp)
     CPURISCVState *env = &cpu->env;
     Error *local_err = NULL;
 
+    if (object_dynamic_cast(OBJECT(dev), TYPE_RISCV_CPU_HOST)) {
+        error_setg(errp, "'host' CPU is not compatible with TCG acceleration");
+        return;
+    }
+
     riscv_cpu_validate_misa_mxl(cpu, &local_err);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
-- 
2.41.0

From: Thomas Huth <thuth@redhat.com>

The character that should be printed is stored in the 64 bit "payload"
variable. The code currently tries to print it by taking the address
of the variable and passing this pointer to qemu_chr_fe_write(). However,
this only works on little endian hosts where the least significant bits
are stored on the lowest address. To do this in a portable way, we have
to store the value in an uint8_t variable instead.

Fixes: 5033606780 ("RISC-V HTIF Console")
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Bin Meng <bmeng@tinylab.org>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230721094720.902454-2-thuth@redhat.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/char/riscv_htif.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/riscv_htif.c
+++ b/hw/char/riscv_htif.c
@@ -XXX,XX +XXX,XX @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
             s->tohost = 0; /* clear to indicate we read */
             return;
         } else if (cmd == HTIF_CONSOLE_CMD_PUTC) {
-            qemu_chr_fe_write(&s->chr, (uint8_t *)&payload, 1);
+            uint8_t ch = (uint8_t)payload;
+            qemu_chr_fe_write(&s->chr, &ch, 1);
             resp = 0x100 | (uint8_t)payload;
         } else {
             qemu_log("HTIF device %d: unknown command\n", device);
-- 
2.41.0

From: Thomas Huth <thuth@redhat.com>

Values that have been read via cpu_physical_memory_read() from the
guest's memory have to be swapped in case the host endianess differs
from the guest.

Fixes: a6e13e31d5 ("riscv_htif: Support console output via proxy syscall")
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Bin Meng <bmeng@tinylab.org>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-Id: <20230721094720.902454-3-thuth@redhat.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/char/riscv_htif.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/riscv_htif.c
+++ b/hw/char/riscv_htif.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/timer.h"
 #include "qemu/error-report.h"
 #include "exec/address-spaces.h"
+#include "exec/tswap.h"
 #include "sysemu/dma.h"
 
 #define RISCV_DEBUG_HTIF 0
@@ -XXX,XX +XXX,XX @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
             } else {
                 uint64_t syscall[8];
                 cpu_physical_memory_read(payload, syscall, sizeof(syscall));
-                if (syscall[0] == PK_SYS_WRITE &&
-                    syscall[1] == HTIF_DEV_CONSOLE &&
-                    syscall[3] == HTIF_CONSOLE_CMD_PUTC) {
+                if (tswap64(syscall[0]) == PK_SYS_WRITE &&
+                    tswap64(syscall[1]) == HTIF_DEV_CONSOLE &&
+                    tswap64(syscall[3]) == HTIF_CONSOLE_CMD_PUTC) {
                     uint8_t ch;
-                    cpu_physical_memory_read(syscall[2], &ch, 1);
+                    cpu_physical_memory_read(tswap64(syscall[2]), &ch, 1);
                     qemu_chr_fe_write(&s->chr, &ch, 1);
                     resp = 0x100 | (uint8_t)payload;
                 } else {
-- 
2.41.0

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

zmmul was promoted from experimental to ratified in commit 6d00ffad4e95.
Add a riscv,isa string for it.

Fixes: 6d00ffad4e95 ("target/riscv: move zmmul out of the experimental properties")
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20230720132424.371132-2-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zicsr, PRIV_VERSION_1_10_0, ext_icsr),
     ISA_EXT_DATA_ENTRY(zifencei, PRIV_VERSION_1_10_0, ext_ifencei),
     ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause),
+    ISA_EXT_DATA_ENTRY(zmmul, PRIV_VERSION_1_12_0, ext_zmmul),
     ISA_EXT_DATA_ENTRY(zawrs, PRIV_VERSION_1_12_0, ext_zawrs),
     ISA_EXT_DATA_ENTRY(zfa, PRIV_VERSION_1_12_0, ext_zfa),
     ISA_EXT_DATA_ENTRY(zfbfmin, PRIV_VERSION_1_12_0, ext_zfbfmin),
-- 
2.41.0

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

The cpu->cfg.epmp extension is still experimental, but it already has a
'smepmp' riscv,isa string. Add it.

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20230720132424.371132-3-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
     ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
     ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
+    ISA_EXT_DATA_ENTRY(smepmp, PRIV_VERSION_1_12_0, epmp),
     ISA_EXT_DATA_ENTRY(smstateen, PRIV_VERSION_1_12_0, ext_smstateen),
     ISA_EXT_DATA_ENTRY(ssaia, PRIV_VERSION_1_12_0, ext_ssaia),
     ISA_EXT_DATA_ENTRY(sscofpmf, PRIV_VERSION_1_12_0, ext_sscofpmf),
-- 
2.41.0

From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>

Commit bef6f008b98(accel/tcg: Return bool from page_check_range) converts
integer return value to bool type. However, it wrongly converted the use
of the API in riscv fault-only-first, where page_check_range < = 0, should
be converted to !page_check_range.

Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20230729031618.821-1-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/vector_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -XXX,XX +XXX,XX @@ vext_ldff(void *vd, void *v0, target_ulong base,
                                          cpu_mmu_index(env, false));
                 if (host) {
 #ifdef CONFIG_USER_ONLY
-                    if (page_check_range(addr, offset, PAGE_READ)) {
+                    if (!page_check_range(addr, offset, PAGE_READ)) {
                         vl = i;
                         goto ProbeSuccess;
                     }
-- 
2.41.0

From: Ard Biesheuvel <ardb@kernel.org>

The AES MixColumns and InvMixColumns operations are relatively
expensive 4x4 matrix multiplications in GF(2^8), which is why C
implementations usually rely on precomputed lookup tables rather than
performing the calculations on demand.

Given that we already carry those tables in QEMU, we can just grab the
right value in the implementation of the RISC-V AES32 instructions. Note
that the tables in question are permuted according to the respective
Sbox, so we can omit the Sbox lookup as well in this case.

Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
Cc: Zewen Ye <lustrew@foxmail.com>
Cc: Weiwei Li <liweiwei@iscas.ac.cn>
Cc: Junqiang Wang <wangjunqiang@iscas.ac.cn>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20230731084043.1791984-1-ardb@kernel.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 include/crypto/aes.h         |  7 +++++++
 crypto/aes.c                 |  4 ++--
 target/riscv/crypto_helper.c | 34 ++++------------------------------
 3 files changed, 13 insertions(+), 32 deletions(-)

diff --git a/include/crypto/aes.h b/include/crypto/aes.h
index XXXXXXX..XXXXXXX 100644
--- a/include/crypto/aes.h
+++ b/include/crypto/aes.h
@@ -XXX,XX +XXX,XX @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
 extern const uint8_t AES_sbox[256];
 extern const uint8_t AES_isbox[256];
 
+/*
+AES_Te0[x] = S [x].[02, 01, 01, 03];
+AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
+*/
+
+extern const uint32_t AES_Te0[256], AES_Td0[256];
+
 #endif
diff --git a/crypto/aes.c b/crypto/aes.c
index XXXXXXX..XXXXXXX 100644
--- a/crypto/aes.c
+++ b/crypto/aes.c
@@ -XXX,XX +XXX,XX @@ AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
 AES_Td4[x] = Si[x].[01, 01, 01, 01];
 */
 
-static const uint32_t AES_Te0[256] = {
+const uint32_t AES_Te0[256] = {
     0xc66363a5U, 0xf87c7c84U, 0xee777799U, 0xf67b7b8dU,
     0xfff2f20dU, 0xd66b6bbdU, 0xde6f6fb1U, 0x91c5c554U,
     0x60303050U, 0x02010103U, 0xce6767a9U, 0x562b2b7dU,
@@ -XXX,XX +XXX,XX @@ static const uint32_t AES_Te4[256] = {
     0xb0b0b0b0U, 0x54545454U, 0xbbbbbbbbU, 0x16161616U,
 };
 
-static const uint32_t AES_Td0[256] = {
+const uint32_t AES_Td0[256] = {
     0x51f4a750U, 0x7e416553U, 0x1a17a4c3U, 0x3a275e96U,
     0x3bab6bcbU, 0x1f9d45f1U, 0xacfa58abU, 0x4be30393U,
     0x2030fa55U, 0xad766df6U, 0x88cc7691U, 0xf5024c25U,
diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/crypto_helper.c
+++ b/target/riscv/crypto_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "crypto/aes-round.h"
 #include "crypto/sm4.h"
 
-#define AES_XTIME(a) \
-    ((a << 1) ^ ((a & 0x80) ? 0x1b : 0))
-
-#define AES_GFMUL(a, b) (( \
-    (((b) & 0x1) ? (a) : 0) ^ \
-    (((b) & 0x2) ? AES_XTIME(a) : 0) ^ \
-    (((b) & 0x4) ? AES_XTIME(AES_XTIME(a)) : 0) ^ \
-    (((b) & 0x8) ? AES_XTIME(AES_XTIME(AES_XTIME(a))) : 0)) & 0xFF)
-
-static inline uint32_t aes_mixcolumn_byte(uint8_t x, bool fwd)
-{
-    uint32_t u;
-
-    if (fwd) {
-        u = (AES_GFMUL(x, 3) << 24) | (x << 16) | (x << 8) |
-            (AES_GFMUL(x, 2) << 0);
-    } else {
-        u = (AES_GFMUL(x, 0xb) << 24) | (AES_GFMUL(x, 0xd) << 16) |
-            (AES_GFMUL(x, 0x9) << 8) | (AES_GFMUL(x, 0xe) << 0);
-    }
-    return u;
-}
-
 #define sext32_xlen(x) (target_ulong)(int32_t)(x)
 
 static inline target_ulong aes32_operation(target_ulong shamt,
@@ -XXX,XX +XXX,XX @@ static inline target_ulong aes32_operation(target_ulong shamt,
                                            bool enc, bool mix)
 {
     uint8_t si = rs2 >> shamt;
-    uint8_t so;
     uint32_t mixed;
     target_ulong res;
 
     if (enc) {
-        so = AES_sbox[si];
         if (mix) {
-            mixed = aes_mixcolumn_byte(so, true);
+            mixed = be32_to_cpu(AES_Te0[si]);
         } else {
-            mixed = so;
+            mixed = AES_sbox[si];
         }
     } else {
-        so = AES_isbox[si];
         if (mix) {
-            mixed = aes_mixcolumn_byte(so, false);
+            mixed = be32_to_cpu(AES_Td0[si]);
         } else {
-            mixed = so;
+            mixed = AES_isbox[si];
         }
     }
     mixed = rol32(mixed, shamt);
-- 
2.41.0

From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>

Take some functions/macros out of `vector_helper` and put them in a new
module called `vector_internals`. This ensures they can be used by both
vector and vector-crypto helpers (latter implemented in proceeding
commits).

Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230711165917.2629866-2-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/vector_internals.h | 182 +++++++++++++++++++++++++++++
 target/riscv/vector_helper.c    | 201 +-------------------------------
 target/riscv/vector_internals.c |  81 +++++++++++++
 target/riscv/meson.build        |   1 +
 4 files changed, 265 insertions(+), 200 deletions(-)
 create mode 100644 target/riscv/vector_internals.h
 create mode 100644 target/riscv/vector_internals.c

diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/target/riscv/vector_internals.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * RISC-V Vector Extension Internals
+ *
+ * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2 or later, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef TARGET_RISCV_VECTOR_INTERNALS_H
+#define TARGET_RISCV_VECTOR_INTERNALS_H
+
+#include "qemu/osdep.h"
+#include "qemu/bitops.h"
+#include "cpu.h"
+#include "tcg/tcg-gvec-desc.h"
+#include "internals.h"
+
+static inline uint32_t vext_nf(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, NF);
+}
+
+/*
+ * Note that vector data is stored in host-endian 64-bit chunks,
+ * so addressing units smaller than that needs a host-endian fixup.
+ */
+#if HOST_BIG_ENDIAN
+#define H1(x)   ((x) ^ 7)
+#define H1_2(x) ((x) ^ 6)
+#define H1_4(x) ((x) ^ 4)
+#define H2(x)   ((x) ^ 3)
+#define H4(x)   ((x) ^ 1)
+#define H8(x)   ((x))
+#else
+#define H1(x)   (x)
+#define H1_2(x) (x)
+#define H1_4(x) (x)
+#define H2(x)   (x)
+#define H4(x)   (x)
+#define H8(x)   (x)
+#endif
+
+/*
+ * Encode LMUL to lmul as following:
+ *     LMUL    vlmul    lmul
+ *      1       000       0
+ *      2       001       1
+ *      4       010       2
+ *      8       011       3
+ *      -       100       -
+ *     1/8      101      -3
+ *     1/4      110      -2
+ *     1/2      111      -1
+ */
+static inline int32_t vext_lmul(uint32_t desc)
+{
+    return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
+}
+
+static inline uint32_t vext_vm(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, VM);
+}
+
+static inline uint32_t vext_vma(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, VMA);
+}
+
+static inline uint32_t vext_vta(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, VTA);
+}
+
+static inline uint32_t vext_vta_all_1s(uint32_t desc)
+{
+    return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
+}
+
+/*
+ * Earlier designs (pre-0.9) had a varying number of bits
+ * per mask value (MLEN). In the 0.9 design, MLEN=1.
+ * (Section 4.5)
+ */
+static inline int vext_elem_mask(void *v0, int index)
+{
+    int idx = index / 64;
+    int pos = index  % 64;
+    return (((uint64_t *)v0)[idx] >> pos) & 1;
+}
+
+/*
+ * Get number of total elements, including prestart, body and tail elements.
+ * Note that when LMUL < 1, the tail includes the elements past VLMAX that
+ * are held in the same vector register.
+ */
+static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
+                                            uint32_t esz)
+{
+    uint32_t vlenb = simd_maxsz(desc);
+    uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
+    int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
+                  ctzl(esz) - ctzl(sew) + vext_lmul(desc);
+    return (vlenb << emul) / esz;
+}
+
+/* set agnostic elements to 1s */
+void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+                       uint32_t tot);
+
+/* expand macro args before macro */
+#define RVVCALL(macro, ...)  macro(__VA_ARGS__)
+
+/* (TD, T1, T2, TX1, TX2) */
+#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
+
+/* operation of two vector elements */
+typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
+
+#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
+static void do_##NAME(void *vd, void *vs1, void *vs2, int i)    \
+{                                                               \
+    TX1 s1 = *((T1 *)vs1 + HS1(i));                             \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                             \
+    *((TD *)vd + HD(i)) = OP(s2, s1);                           \
+}
+
+void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
+                CPURISCVState *env, uint32_t desc,
+                opivv2_fn *fn, uint32_t esz);
+
+/* generate the helpers for OPIVV */
+#define GEN_VEXT_VV(NAME, ESZ)                            \
+void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
+                  void *vs2, CPURISCVState *env,          \
+                  uint32_t desc)                          \
+{                                                         \
+    do_vext_vv(vd, v0, vs1, vs2, env, desc,               \
+               do_##NAME, ESZ);                           \
+}
+
+typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
+
+/*
+ * (T1)s1 gives the real operator type.
+ * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
+ */
+#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)             \
+static void do_##NAME(void *vd, target_long s1, void *vs2, int i)   \
+{                                                                   \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
+    *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1);                      \
+}
+
+void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
+                CPURISCVState *env, uint32_t desc,
+                opivx2_fn fn, uint32_t esz);
+
+/* generate the helpers for OPIVX */
+#define GEN_VEXT_VX(NAME, ESZ)                            \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
+                  void *vs2, CPURISCVState *env,          \
+                  uint32_t desc)                          \
+{                                                         \
+    do_vext_vx(vd, v0, s1, vs2, env, desc,                \
+               do_##NAME, ESZ);                           \
+}
+
+#endif /* TARGET_RISCV_VECTOR_INTERNALS_H */
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "fpu/softfloat.h"
 #include "tcg/tcg-gvec-desc.h"
 #include "internals.h"
+#include "vector_internals.h"
 #include <math.h>
 
 target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
@@ -XXX,XX +XXX,XX @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
     return vl;
 }
 
-/*
- * Note that vector data is stored in host-endian 64-bit chunks,
- * so addressing units smaller than that needs a host-endian fixup.
- */
-#if HOST_BIG_ENDIAN
-#define H1(x)   ((x) ^ 7)
-#define H1_2(x) ((x) ^ 6)
-#define H1_4(x) ((x) ^ 4)
-#define H2(x)   ((x) ^ 3)
-#define H4(x)   ((x) ^ 1)
-#define H8(x)   ((x))
-#else
-#define H1(x)   (x)
-#define H1_2(x) (x)
-#define H1_4(x) (x)
-#define H2(x)   (x)
-#define H4(x)   (x)
-#define H8(x)   (x)
-#endif
-
-static inline uint32_t vext_nf(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, NF);
-}
-
-static inline uint32_t vext_vm(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VM);
-}
-
-/*
- * Encode LMUL to lmul as following:
- *     LMUL    vlmul    lmul
- *      1       000       0
- *      2       001       1
- *      4       010       2
- *      8       011       3
- *      -       100       -
- *     1/8      101      -3
- *     1/4      110      -2
- *     1/2      111      -1
- */
-static inline int32_t vext_lmul(uint32_t desc)
-{
-    return sextract32(FIELD_EX32(simd_data(desc), VDATA, LMUL), 0, 3);
-}
-
-static inline uint32_t vext_vta(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VTA);
-}
-
-static inline uint32_t vext_vma(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VMA);
-}
-
-static inline uint32_t vext_vta_all_1s(uint32_t desc)
-{
-    return FIELD_EX32(simd_data(desc), VDATA, VTA_ALL_1S);
-}
-
 /*
  * Get the maximum number of elements can be operated.
  *
@@ -XXX,XX +XXX,XX @@ static inline uint32_t vext_max_elems(uint32_t desc, uint32_t log2_esz)
     return scale < 0 ? vlenb >> -scale : vlenb << scale;
 }
 
-/*
- * Get number of total elements, including prestart, body and tail elements.
- * Note that when LMUL < 1, the tail includes the elements past VLMAX that
- * are held in the same vector register.
- */
-static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
-                                            uint32_t esz)
-{
-    uint32_t vlenb = simd_maxsz(desc);
-    uint32_t sew = 1 << FIELD_EX64(env->vtype, VTYPE, VSEW);
-    int8_t emul = ctzl(esz) - ctzl(sew) + vext_lmul(desc) < 0 ? 0 :
-                  ctzl(esz) - ctzl(sew) + vext_lmul(desc);
-    return (vlenb << emul) / esz;
-}
-
 static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
 {
     return (addr & ~env->cur_pmmask) | env->cur_pmbase;
@@ -XXX,XX +XXX,XX @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
     }
 }
 
-/* set agnostic elements to 1s */
-static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
-                              uint32_t tot)
-{
-    if (is_agnostic == 0) {
-        /* policy undisturbed */
-        return;
-    }
-    if (tot - cnt == 0) {
-        return;
-    }
-    memset(base + cnt, -1, tot - cnt);
-}
-
 static inline void vext_set_elem_mask(void *v0, int index,
                                       uint8_t value)
 {
@@ -XXX,XX +XXX,XX @@ static inline void vext_set_elem_mask(void *v0, int index,
     ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value);
 }
 
-/*
- * Earlier designs (pre-0.9) had a varying number of bits
- * per mask value (MLEN). In the 0.9 design, MLEN=1.
- * (Section 4.5)
- */
-static inline int vext_elem_mask(void *v0, int index)
-{
-    int idx = index / 64;
-    int pos = index  % 64;
-    return (((uint64_t *)v0)[idx] >> pos) & 1;
-}
-
 /* elements operations for load and store */
 typedef void vext_ldst_elem_fn(CPURISCVState *env, abi_ptr addr,
                                uint32_t idx, void *vd, uintptr_t retaddr);
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
  * Vector Integer Arithmetic Instructions
  */
 
-/* expand macro args before macro */
-#define RVVCALL(macro, ...)  macro(__VA_ARGS__)
-
 /* (TD, T1, T2, TX1, TX2) */
 #define OP_SSS_B int8_t, int8_t, int8_t, int8_t, int8_t
 #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
 #define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
 #define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
-#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
-#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
-#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
-#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
 #define OP_SUS_B int8_t, uint8_t, int8_t, uint8_t, int8_t
 #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
 #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
 #define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
 #define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
 
-/* operation of two vector elements */
-typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
-
-#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
-static void do_##NAME(void *vd, void *vs1, void *vs2, int i)    \
-{                                                               \
-    TX1 s1 = *((T1 *)vs1 + HS1(i));                             \
-    TX2 s2 = *((T2 *)vs2 + HS2(i));                             \
-    *((TD *)vd + HD(i)) = OP(s2, s1);                           \
-}
 #define DO_SUB(N, M) (N - M)
 #define DO_RSUB(N, M) (M - N)
 
@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVV2, vsub_vv_h, OP_SSS_H, H2, H2, H2, DO_SUB)
 RVVCALL(OPIVV2, vsub_vv_w, OP_SSS_W, H4, H4, H4, DO_SUB)
 RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
 
-static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
-                       CPURISCVState *env, uint32_t desc,
-                       opivv2_fn *fn, uint32_t esz)
-{
-    uint32_t vm = vext_vm(desc);
-    uint32_t vl = env->vl;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
-    uint32_t vma = vext_vma(desc);
-    uint32_t i;
-
-    for (i = env->vstart; i < vl; i++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            /* set masked-off elements to 1s */
-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
-            continue;
-        }
-        fn(vd, vs1, vs2, i);
-    }
-    env->vstart = 0;
-    /* set tail elements to 1s */
-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
-}
-
-/* generate the helpers for OPIVV */
-#define GEN_VEXT_VV(NAME, ESZ)                            \
-void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
-                  void *vs2, CPURISCVState *env,          \
-                  uint32_t desc)                          \
-{                                                         \
-    do_vext_vv(vd, v0, vs1, vs2, env, desc,               \
-               do_##NAME, ESZ);                           \
-}
-
 GEN_VEXT_VV(vadd_vv_b, 1)
 GEN_VEXT_VV(vadd_vv_h, 2)
 GEN_VEXT_VV(vadd_vv_w, 4)
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_VV(vsub_vv_h, 2)
 GEN_VEXT_VV(vsub_vv_w, 4)
 GEN_VEXT_VV(vsub_vv_d, 8)
 
-typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
-
-/*
- * (T1)s1 gives the real operator type.
- * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
- */
-#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)             \
-static void do_##NAME(void *vd, target_long s1, void *vs2, int i)   \
-{                                                                   \
-    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
-    *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1);                      \
-}
 
 RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD)
 RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD)
@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVX2, vrsub_vx_h, OP_SSS_H, H2, H2, DO_RSUB)
 RVVCALL(OPIVX2, vrsub_vx_w, OP_SSS_W, H4, H4, DO_RSUB)
 RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
 
-static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
-                       CPURISCVState *env, uint32_t desc,
-                       opivx2_fn fn, uint32_t esz)
-{
-    uint32_t vm = vext_vm(desc);
-    uint32_t vl = env->vl;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
-    uint32_t vma = vext_vma(desc);
-    uint32_t i;
-
-    for (i = env->vstart; i < vl; i++) {
-        if (!vm && !vext_elem_mask(v0, i)) {
-            /* set masked-off elements to 1s */
-            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
-            continue;
-        }
-        fn(vd, s1, vs2, i);
-    }
-    env->vstart = 0;
-    /* set tail elements to 1s */
-    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
-}
-
-/* generate the helpers for OPIVX */
-#define GEN_VEXT_VX(NAME, ESZ)                            \
-void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
-                  void *vs2, CPURISCVState *env,          \
-                  uint32_t desc)                          \
-{                                                         \
-    do_vext_vx(vd, v0, s1, vs2, env, desc,                \
-               do_##NAME, ESZ);                           \
-}
-
 GEN_VEXT_VX(vadd_vx_b, 1)
 GEN_VEXT_VX(vadd_vx_h, 2)
 GEN_VEXT_VX(vadd_vx_w, 4)
diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/target/riscv/vector_internals.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * RISC-V Vector Extension Internals
+ *
+ * Copyright (c) 2020 T-Head Semiconductor Co., Ltd. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2 or later, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "vector_internals.h"
+
+/* set agnostic elements to 1s */
+void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
+                       uint32_t tot)
+{
+    if (is_agnostic == 0) {
+        /* policy undisturbed */
+        return;
+    }
+    if (tot - cnt == 0) {
+        return ;
+    }
+    memset(base + cnt, -1, tot - cnt);
+}
+
+void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
+                CPURISCVState *env, uint32_t desc,
+                opivv2_fn *fn, uint32_t esz)
+{
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+    uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
+    uint32_t i;
+
+    for (i = env->vstart; i < vl; i++) {
+        if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
+            continue;
+        }
+        fn(vd, vs1, vs2, i);
+    }
+    env->vstart = 0;
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+}
+
+void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
+                CPURISCVState *env, uint32_t desc,
+                opivx2_fn fn, uint32_t esz)
+{
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+    uint32_t vta = vext_vta(desc);
+    uint32_t vma = vext_vma(desc);
+    uint32_t i;
+
+    for (i = env->vstart; i < vl; i++) {
+        if (!vm && !vext_elem_mask(v0, i)) {
+            /* set masked-off elements to 1s */
+            vext_set_elems_1s(vd, vma, i * esz, (i + 1) * esz);
+            continue;
+        }
+        fn(vd, s1, vs2, i);
+    }
+    env->vstart = 0;
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);
+}
diff --git a/target/riscv/meson.build b/target/riscv/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/meson.build
+++ b/target/riscv/meson.build
@@ -XXX,XX +XXX,XX @@ riscv_ss.add(files(
   'gdbstub.c',
   'op_helper.c',
   'vector_helper.c',
+  'vector_internals.c',
   'bitmanip_helper.c',
   'translate.c',
   'm128_helper.c',
-- 
2.41.0

From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>

Refactor the non SEW-specific stuff out of `GEN_OPIVV_TRANS` into
function `opivv_trans` (similar to `opivi_trans`). `opivv_trans` will be
used in proceeding vector-crypto commits.

Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-3-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 62 +++++++++++++------------
 1 file changed, 32 insertions(+), 30 deletions(-)

From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>

Remove the redundant "vl == 0" check which is already included within the  vstart >= vl check, when vl == 0.

Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230711165917.2629866-4-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 31 +------------------------
 1 file changed, 1 insertion(+), 30 deletions(-)

diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -XXX,XX +XXX,XX @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
     TCGv_i32 desc;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
     TCGv_i32 desc;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
     TCGv_i32 desc;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
     TCGv_i32 desc;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
         return false;
     }
 
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
@@ -XXX,XX +XXX,XX @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
     uint32_t data = 0;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
     uint32_t data = 0;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
     if (checkfn(s, a)) {
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
     if (opiwv_widen_check(s, a)) {
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool opivv_trans(uint32_t vd, uint32_t vs1, uint32_t vs2, uint32_t vm,
 {
     uint32_t data = 0;
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     data = FIELD_DP32(data, VDATA, VM, vm);
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
             gen_helper_##NAME##_w,                                 \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
                 gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
             };
             TCGLabel *over = gen_new_label();
-            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
             tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
         vext_check_ss(s, a->rd, 0, 1)) {
         TCGv s1;
         TCGLabel *over = gen_new_label();
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         s1 = get_gpr(s, a->rs1, EXT_SIGN);
@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
                 gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
             };
             TCGLabel *over = gen_new_label();
-            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
             tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             s1 = tcg_constant_i64(simm);
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
     TCGv_i64 t1;
 
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
         };                                                       \
         TCGLabel *over = gen_new_label();                        \
         gen_set_rm(s, RISCV_FRM_DYN);                            \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);        \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
                                                                  \
         data = FIELD_DP32(data, VDATA, VM, a->vm);               \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
         gen_set_rm_chkfrm(s, rm);
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
                 gen_helper_vmv_v_x_d,
             };
             TCGLabel *over = gen_new_label();
-            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
             tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             t1 = tcg_temp_new_i64();
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm_chkfrm(s, FRM);                                 \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm_chkfrm(s, FRM);                                 \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm_chkfrm(s, FRM);                                 \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
@@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_r *a)                \
         uint32_t data = 0;                                         \
         gen_helper_gvec_4_ptr *fn = gen_helper_##NAME;             \
         TCGLabel *over = gen_new_label();                          \
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -XXX,XX +XXX,XX @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
         require_vm(a->vm, a->rd)) {
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -XXX,XX +XXX,XX @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
         TCGv s1;
         TCGLabel *over = gen_new_label();
 
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         t1 = tcg_temp_new_i64();
@@ -XXX,XX +XXX,XX @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
         TCGv_i64 t1;
         TCGLabel *over = gen_new_label();
 
-        /* if vl == 0 or vstart >= vl, skip vector register write back */
-        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        /* if vstart >= vl, skip vector register write back */
         tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         /* NaN-box f[rs1] */
@@ -XXX,XX +XXX,XX @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
     uint32_t data = 0;
     gen_helper_gvec_3_ptr *fn;
     TCGLabel *over = gen_new_label();
-    tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
     tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     static gen_helper_gvec_3_ptr * const fns[6][4] = {
-- 
2.41.0

From: Lawrence Hunter <lawrence.hunter@codethink.co.uk>

This commit adds support for the Zvbc vector-crypto extension, which
consists of the following instructions:

* vclmulh.[vx,vv]
* vclmul.[vx,vv]

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Co-authored-by: Max Chou <max.chou@sifive.com>
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
[max.chou@sifive.com: Exposed x-zvbc property]
Message-ID: <20230711165917.2629866-5-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |  1 +
 target/riscv/helper.h                    |  6 +++
 target/riscv/insn32.decode               |  6 +++
 target/riscv/cpu.c                       |  9 ++++
 target/riscv/translate.c                 |  1 +
 target/riscv/vcrypto_helper.c            | 59 ++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc | 62 ++++++++++++++++++++++++
 target/riscv/meson.build                 |  3 +-
 8 files changed, 146 insertions(+), 1 deletion(-)
 create mode 100644 target/riscv/vcrypto_helper.c
 create mode 100644 target/riscv/insn_trans/trans_rvvk.c.inc

From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>

Move the checks out of `do_opiv{v,x,i}_gvec{,_shift}` functions
and into the corresponding macros. This enables the functions to be
reused in proceeding commits without check duplication.

Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-6-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 28 +++++++++++--------------
 1 file changed, 12 insertions(+), 16 deletions(-)

From: Dickon Hood <dickon.hood@codethink.co.uk>

Zvbb (implemented in later commit) has a widening instruction, which
requires an extra check on the enabled extensions.  Refactor
GEN_OPIVX_WIDEN_TRANS() to take a check function to avoid reimplementing
it.

Signed-off-by: Dickon Hood <dickon.hood@codethink.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-7-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvv.c.inc | 52 +++++++++++--------------
 1 file changed, 23 insertions(+), 29 deletions(-)

From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>

Move some macros out of `vector_helper` and into `vector_internals`.
This ensures they can be used by both vector and vector-crypto helpers
(latter implemented in proceeding commits).

Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-8-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/vector_internals.h | 46 +++++++++++++++++++++++++++++++++
 target/riscv/vector_helper.c    | 42 ------------------------------
 2 files changed, 46 insertions(+), 42 deletions(-)

diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -XXX,XX +XXX,XX @@ void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
 /* expand macro args before macro */
 #define RVVCALL(macro, ...)  macro(__VA_ARGS__)
 
+/* (TD, T2, TX2) */
+#define OP_UU_B uint8_t, uint8_t, uint8_t
+#define OP_UU_H uint16_t, uint16_t, uint16_t
+#define OP_UU_W uint32_t, uint32_t, uint32_t
+#define OP_UU_D uint64_t, uint64_t, uint64_t
+
 /* (TD, T1, T2, TX1, TX2) */
 #define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
 #define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
 #define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
 #define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
 
+#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
+static void do_##NAME(void *vd, void *vs2, int i)      \
+{                                                      \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
+    *((TD *)vd + HD(i)) = OP(s2);                      \
+}
+
+#define GEN_VEXT_V(NAME, ESZ)                          \
+void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
+                  CPURISCVState *env, uint32_t desc)   \
+{                                                      \
+    uint32_t vm = vext_vm(desc);                       \
+    uint32_t vl = env->vl;                             \
+    uint32_t total_elems =                             \
+        vext_get_total_elems(env, desc, ESZ);          \
+    uint32_t vta = vext_vta(desc);                     \
+    uint32_t vma = vext_vma(desc);                     \
+    uint32_t i;                                        \
+                                                       \
+    for (i = env->vstart; i < vl; i++) {               \
+        if (!vm && !vext_elem_mask(v0, i)) {           \
+            /* set masked-off elements to 1s */        \
+            vext_set_elems_1s(vd, vma, i * ESZ,        \
+                              (i + 1) * ESZ);          \
+            continue;                                  \
+        }                                              \
+        do_##NAME(vd, vs2, i);                         \
+    }                                                  \
+    env->vstart = 0;                                   \
+    /* set tail elements to 1s */                      \
+    vext_set_elems_1s(vd, vta, vl * ESZ,               \
+                      total_elems * ESZ);              \
+}
+
 /* operation of two vector elements */
 typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
 
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
                do_##NAME, ESZ);                           \
 }
 
+/* Three of the widening shortening macros: */
+/* (TD, T1, T2, TX1, TX2) */
+#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
+#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
+#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
+
 #endif /* TARGET_RISCV_VECTOR_INTERNALS_H */
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
 #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
 #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
 #define OP_SUS_D int64_t, uint64_t, int64_t, uint64_t, int64_t
-#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
-#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
-#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
 #define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t
 #define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t
 #define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_VF(vfwnmsac_vf_h, 4)
 GEN_VEXT_VF(vfwnmsac_vf_w, 8)
 
 /* Vector Floating-Point Square-Root Instruction */
-/* (TD, T2, TX2) */
-#define OP_UU_H uint16_t, uint16_t, uint16_t
-#define OP_UU_W uint32_t, uint32_t, uint32_t
-#define OP_UU_D uint64_t, uint64_t, uint64_t
-
 #define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
 static void do_##NAME(void *vd, void *vs2, int i,      \
                       CPURISCVState *env)              \
@@ -XXX,XX +XXX,XX @@ GEN_VEXT_CMP_VF(vmfge_vf_w, uint32_t, H4, vmfge32)
 GEN_VEXT_CMP_VF(vmfge_vf_d, uint64_t, H8, vmfge64)
 
 /* Vector Floating-Point Classify Instruction */
-#define OPIVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
-static void do_##NAME(void *vd, void *vs2, int i)      \
-{                                                      \
-    TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
-    *((TD *)vd + HD(i)) = OP(s2);                      \
-}
-
-#define GEN_VEXT_V(NAME, ESZ)                          \
-void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
-                  CPURISCVState *env, uint32_t desc)   \
-{                                                      \
-    uint32_t vm = vext_vm(desc);                       \
-    uint32_t vl = env->vl;                             \
-    uint32_t total_elems =                             \
-        vext_get_total_elems(env, desc, ESZ);          \
-    uint32_t vta = vext_vta(desc);                     \
-    uint32_t vma = vext_vma(desc);                     \
-    uint32_t i;                                        \
-                                                       \
-    for (i = env->vstart; i < vl; i++) {               \
-        if (!vm && !vext_elem_mask(v0, i)) {           \
-            /* set masked-off elements to 1s */        \
-            vext_set_elems_1s(vd, vma, i * ESZ,        \
-                              (i + 1) * ESZ);          \
-            continue;                                  \
-        }                                              \
-        do_##NAME(vd, vs2, i);                         \
-    }                                                  \
-    env->vstart = 0;                                   \
-    /* set tail elements to 1s */                      \
-    vext_set_elems_1s(vd, vta, vl * ESZ,               \
-                      total_elems * ESZ);              \
-}
-
 target_ulong fclass_h(uint64_t frs1)
 {
     float16 f = frs1;
-- 
2.41.0

From: Dickon Hood <dickon.hood@codethink.co.uk>

This commit adds support for the Zvbb vector-crypto extension, which
consists of the following instructions:

* vrol.[vv,vx]
* vror.[vv,vx,vi]
* vbrev8.v
* vrev8.v
* vandn.[vv,vx]
* vbrev.v
* vclz.v
* vctz.v
* vcpop.v
* vwsll.[vv,vx,vi]

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Co-authored-by: William Salmon <will.salmon@codethink.co.uk>
Co-authored-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
[max.chou@sifive.com: Fix imm mode of vror.vi]
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: William Salmon <will.salmon@codethink.co.uk>
Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Signed-off-by: Dickon Hood <dickon.hood@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Exposed x-zvbb property]
Message-ID: <20230711165917.2629866-9-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |   1 +
 target/riscv/helper.h                    |  62 +++++++++
 target/riscv/insn32.decode               |  20 +++
 target/riscv/cpu.c                       |  12 ++
 target/riscv/vcrypto_helper.c            | 138 +++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc | 164 +++++++++++++++++++++++
 6 files changed, 397 insertions(+)

diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_cfg.h
+++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
     bool ext_zve32f;
     bool ext_zve64f;
     bool ext_zve64d;
+    bool ext_zvbb;
     bool ext_zvbc;
     bool ext_zmmul;
     bool ext_zvfbfmin;
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(vclmul_vv, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vclmul_vx, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vclmulh_vv, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vclmulh_vx, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vror_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vror_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vror_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vror_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vror_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vror_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vror_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vror_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vrol_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrol_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrol_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrol_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vrol_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrol_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrol_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrol_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_5(vrev8_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vrev8_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vrev8_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vrev8_v_d, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev8_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev8_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev8_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev8_v_d, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vbrev_v_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_5(vclz_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vclz_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vclz_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vclz_v_d, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vctz_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vctz_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vctz_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vctz_v_d, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vcpop_v_b, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vcpop_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vcpop_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vcpop_v_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vwsll_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsll_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsll_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwsll_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsll_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vwsll_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vandn_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vandn_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vandn_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vandn_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@
 %imm_u    12:s20                 !function=ex_shift_12
 %imm_bs   30:2                   !function=ex_shift_3
 %imm_rnum 20:4
+%imm_z6   26:1 15:5
 
 # Argument sets:
 &empty
@@ -XXX,XX +XXX,XX @@
 @r_vm    ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd
 @r_vm_1  ...... . ..... ..... ... ..... .......    &rmrr vm=1 %rs2 %rs1 %rd
 @r_vm_0  ...... . ..... ..... ... ..... .......    &rmrr vm=0 %rs2 %rs1 %rd
+@r2_zimm6  ..... . vm:1 ..... ..... ... ..... .......  &rmrr %rs2 rs1=%imm_z6 %rd
 @r2_zimm11 . zimm:11  ..... ... ..... ....... %rs1 %rd
 @r2_zimm10 .. zimm:10  ..... ... ..... ....... %rs1 %rd
 @r2_s    .......   ..... ..... ... ..... ....... %rs2 %rs1
@@ -XXX,XX +XXX,XX @@ vclmul_vv   001100 . ..... ..... 010 ..... 1010111 @r_vm
 vclmul_vx   001100 . ..... ..... 110 ..... 1010111 @r_vm
 vclmulh_vv  001101 . ..... ..... 010 ..... 1010111 @r_vm
 vclmulh_vx  001101 . ..... ..... 110 ..... 1010111 @r_vm
+
+# *** Zvbb vector crypto extension ***
+vrol_vv     010101 . ..... ..... 000 ..... 1010111 @r_vm
+vrol_vx     010101 . ..... ..... 100 ..... 1010111 @r_vm
+vror_vv     010100 . ..... ..... 000 ..... 1010111 @r_vm
+vror_vx     010100 . ..... ..... 100 ..... 1010111 @r_vm
+vror_vi     01010. . ..... ..... 011 ..... 1010111 @r2_zimm6
+vbrev8_v    010010 . ..... 01000 010 ..... 1010111 @r2_vm
+vrev8_v     010010 . ..... 01001 010 ..... 1010111 @r2_vm
+vandn_vv    000001 . ..... ..... 000 ..... 1010111 @r_vm
+vandn_vx    000001 . ..... ..... 100 ..... 1010111 @r_vm
+vbrev_v     010010 . ..... 01010 010 ..... 1010111 @r2_vm
+vclz_v      010010 . ..... 01100 010 ..... 1010111 @r2_vm
+vctz_v      010010 . ..... 01101 010 ..... 1010111 @r2_vm
+vcpop_v     010010 . ..... 01110 010 ..... 1010111 @r2_vm
+vwsll_vv    110101 . ..... ..... 000 ..... 1010111 @r_vm
+vwsll_vx    110101 . ..... ..... 100 ..... 1010111 @r_vm
+vwsll_vi    110101 . ..... ..... 011 ..... 1010111 @r_vm
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zksed, PRIV_VERSION_1_12_0, ext_zksed),
     ISA_EXT_DATA_ENTRY(zksh, PRIV_VERSION_1_12_0, ext_zksh),
     ISA_EXT_DATA_ENTRY(zkt, PRIV_VERSION_1_12_0, ext_zkt),
+    ISA_EXT_DATA_ENTRY(zvbb, PRIV_VERSION_1_12_0, ext_zvbb),
     ISA_EXT_DATA_ENTRY(zvbc, PRIV_VERSION_1_12_0, ext_zvbc),
     ISA_EXT_DATA_ENTRY(zve32f, PRIV_VERSION_1_10_0, ext_zve32f),
     ISA_EXT_DATA_ENTRY(zve64f, PRIV_VERSION_1_10_0, ext_zve64f),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
         return;
     }
 
+    /*
+     * In principle Zve*x would also suffice here, were they supported
+     * in qemu
+     */
+    if (cpu->cfg.ext_zvbb && !cpu->cfg.ext_zve32f) {
+        error_setg(errp,
+                   "Vector crypto extensions require V or Zve* extensions");
+        return;
+    }
+
     if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) {
         error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions");
         return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
     DEFINE_PROP_BOOL("x-zvfbfwma", RISCVCPU, cfg.ext_zvfbfwma, false),
 
     /* Vector cryptography extensions */
+    DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
     DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
 
     DEFINE_PROP_END_OF_LIST(),
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/osdep.h"
 #include "qemu/host-utils.h"
 #include "qemu/bitops.h"
+#include "qemu/bswap.h"
 #include "cpu.h"
 #include "exec/memop.h"
 #include "exec/exec-all.h"
@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVV2, vclmulh_vv, OP_UUU_D, H8, H8, H8, clmulh64)
 GEN_VEXT_VV(vclmulh_vv, 8)
 RVVCALL(OPIVX2, vclmulh_vx, OP_UUU_D, H8, H8, clmulh64)
 GEN_VEXT_VX(vclmulh_vx, 8)
+
+RVVCALL(OPIVV2, vror_vv_b, OP_UUU_B, H1, H1, H1, ror8)
+RVVCALL(OPIVV2, vror_vv_h, OP_UUU_H, H2, H2, H2, ror16)
+RVVCALL(OPIVV2, vror_vv_w, OP_UUU_W, H4, H4, H4, ror32)
+RVVCALL(OPIVV2, vror_vv_d, OP_UUU_D, H8, H8, H8, ror64)
+GEN_VEXT_VV(vror_vv_b, 1)
+GEN_VEXT_VV(vror_vv_h, 2)
+GEN_VEXT_VV(vror_vv_w, 4)
+GEN_VEXT_VV(vror_vv_d, 8)
+
+RVVCALL(OPIVX2, vror_vx_b, OP_UUU_B, H1, H1, ror8)
+RVVCALL(OPIVX2, vror_vx_h, OP_UUU_H, H2, H2, ror16)
+RVVCALL(OPIVX2, vror_vx_w, OP_UUU_W, H4, H4, ror32)
+RVVCALL(OPIVX2, vror_vx_d, OP_UUU_D, H8, H8, ror64)
+GEN_VEXT_VX(vror_vx_b, 1)
+GEN_VEXT_VX(vror_vx_h, 2)
+GEN_VEXT_VX(vror_vx_w, 4)
+GEN_VEXT_VX(vror_vx_d, 8)
+
+RVVCALL(OPIVV2, vrol_vv_b, OP_UUU_B, H1, H1, H1, rol8)
+RVVCALL(OPIVV2, vrol_vv_h, OP_UUU_H, H2, H2, H2, rol16)
+RVVCALL(OPIVV2, vrol_vv_w, OP_UUU_W, H4, H4, H4, rol32)
+RVVCALL(OPIVV2, vrol_vv_d, OP_UUU_D, H8, H8, H8, rol64)
+GEN_VEXT_VV(vrol_vv_b, 1)
+GEN_VEXT_VV(vrol_vv_h, 2)
+GEN_VEXT_VV(vrol_vv_w, 4)
+GEN_VEXT_VV(vrol_vv_d, 8)
+
+RVVCALL(OPIVX2, vrol_vx_b, OP_UUU_B, H1, H1, rol8)
+RVVCALL(OPIVX2, vrol_vx_h, OP_UUU_H, H2, H2, rol16)
+RVVCALL(OPIVX2, vrol_vx_w, OP_UUU_W, H4, H4, rol32)
+RVVCALL(OPIVX2, vrol_vx_d, OP_UUU_D, H8, H8, rol64)
+GEN_VEXT_VX(vrol_vx_b, 1)
+GEN_VEXT_VX(vrol_vx_h, 2)
+GEN_VEXT_VX(vrol_vx_w, 4)
+GEN_VEXT_VX(vrol_vx_d, 8)
+
+static uint64_t brev8(uint64_t val)
+{
+    val = ((val & 0x5555555555555555ull) << 1) |
+          ((val & 0xAAAAAAAAAAAAAAAAull) >> 1);
+    val = ((val & 0x3333333333333333ull) << 2) |
+          ((val & 0xCCCCCCCCCCCCCCCCull) >> 2);
+    val = ((val & 0x0F0F0F0F0F0F0F0Full) << 4) |
+          ((val & 0xF0F0F0F0F0F0F0F0ull) >> 4);
+
+    return val;
+}
+
+RVVCALL(OPIVV1, vbrev8_v_b, OP_UU_B, H1, H1, brev8)
+RVVCALL(OPIVV1, vbrev8_v_h, OP_UU_H, H2, H2, brev8)
+RVVCALL(OPIVV1, vbrev8_v_w, OP_UU_W, H4, H4, brev8)
+RVVCALL(OPIVV1, vbrev8_v_d, OP_UU_D, H8, H8, brev8)
+GEN_VEXT_V(vbrev8_v_b, 1)
+GEN_VEXT_V(vbrev8_v_h, 2)
+GEN_VEXT_V(vbrev8_v_w, 4)
+GEN_VEXT_V(vbrev8_v_d, 8)
+
+#define DO_IDENTITY(a) (a)
+RVVCALL(OPIVV1, vrev8_v_b, OP_UU_B, H1, H1, DO_IDENTITY)
+RVVCALL(OPIVV1, vrev8_v_h, OP_UU_H, H2, H2, bswap16)
+RVVCALL(OPIVV1, vrev8_v_w, OP_UU_W, H4, H4, bswap32)
+RVVCALL(OPIVV1, vrev8_v_d, OP_UU_D, H8, H8, bswap64)
+GEN_VEXT_V(vrev8_v_b, 1)
+GEN_VEXT_V(vrev8_v_h, 2)
+GEN_VEXT_V(vrev8_v_w, 4)
+GEN_VEXT_V(vrev8_v_d, 8)
+
+#define DO_ANDN(a, b) ((a) & ~(b))
+RVVCALL(OPIVV2, vandn_vv_b, OP_UUU_B, H1, H1, H1, DO_ANDN)
+RVVCALL(OPIVV2, vandn_vv_h, OP_UUU_H, H2, H2, H2, DO_ANDN)
+RVVCALL(OPIVV2, vandn_vv_w, OP_UUU_W, H4, H4, H4, DO_ANDN)
+RVVCALL(OPIVV2, vandn_vv_d, OP_UUU_D, H8, H8, H8, DO_ANDN)
+GEN_VEXT_VV(vandn_vv_b, 1)
+GEN_VEXT_VV(vandn_vv_h, 2)
+GEN_VEXT_VV(vandn_vv_w, 4)
+GEN_VEXT_VV(vandn_vv_d, 8)
+
+RVVCALL(OPIVX2, vandn_vx_b, OP_UUU_B, H1, H1, DO_ANDN)
+RVVCALL(OPIVX2, vandn_vx_h, OP_UUU_H, H2, H2, DO_ANDN)
+RVVCALL(OPIVX2, vandn_vx_w, OP_UUU_W, H4, H4, DO_ANDN)
+RVVCALL(OPIVX2, vandn_vx_d, OP_UUU_D, H8, H8, DO_ANDN)
+GEN_VEXT_VX(vandn_vx_b, 1)
+GEN_VEXT_VX(vandn_vx_h, 2)
+GEN_VEXT_VX(vandn_vx_w, 4)
+GEN_VEXT_VX(vandn_vx_d, 8)
+
+RVVCALL(OPIVV1, vbrev_v_b, OP_UU_B, H1, H1, revbit8)
+RVVCALL(OPIVV1, vbrev_v_h, OP_UU_H, H2, H2, revbit16)
+RVVCALL(OPIVV1, vbrev_v_w, OP_UU_W, H4, H4, revbit32)
+RVVCALL(OPIVV1, vbrev_v_d, OP_UU_D, H8, H8, revbit64)
+GEN_VEXT_V(vbrev_v_b, 1)
+GEN_VEXT_V(vbrev_v_h, 2)
+GEN_VEXT_V(vbrev_v_w, 4)
+GEN_VEXT_V(vbrev_v_d, 8)
+
+RVVCALL(OPIVV1, vclz_v_b, OP_UU_B, H1, H1, clz8)
+RVVCALL(OPIVV1, vclz_v_h, OP_UU_H, H2, H2, clz16)
+RVVCALL(OPIVV1, vclz_v_w, OP_UU_W, H4, H4, clz32)
+RVVCALL(OPIVV1, vclz_v_d, OP_UU_D, H8, H8, clz64)
+GEN_VEXT_V(vclz_v_b, 1)
+GEN_VEXT_V(vclz_v_h, 2)
+GEN_VEXT_V(vclz_v_w, 4)
+GEN_VEXT_V(vclz_v_d, 8)
+
+RVVCALL(OPIVV1, vctz_v_b, OP_UU_B, H1, H1, ctz8)
+RVVCALL(OPIVV1, vctz_v_h, OP_UU_H, H2, H2, ctz16)
+RVVCALL(OPIVV1, vctz_v_w, OP_UU_W, H4, H4, ctz32)
+RVVCALL(OPIVV1, vctz_v_d, OP_UU_D, H8, H8, ctz64)
+GEN_VEXT_V(vctz_v_b, 1)
+GEN_VEXT_V(vctz_v_h, 2)
+GEN_VEXT_V(vctz_v_w, 4)
+GEN_VEXT_V(vctz_v_d, 8)
+
+RVVCALL(OPIVV1, vcpop_v_b, OP_UU_B, H1, H1, ctpop8)
+RVVCALL(OPIVV1, vcpop_v_h, OP_UU_H, H2, H2, ctpop16)
+RVVCALL(OPIVV1, vcpop_v_w, OP_UU_W, H4, H4, ctpop32)
+RVVCALL(OPIVV1, vcpop_v_d, OP_UU_D, H8, H8, ctpop64)
+GEN_VEXT_V(vcpop_v_b, 1)
+GEN_VEXT_V(vcpop_v_h, 2)
+GEN_VEXT_V(vcpop_v_w, 4)
+GEN_VEXT_V(vcpop_v_d, 8)
+
+#define DO_SLL(N, M) (N << (M & (sizeof(N) * 8 - 1)))
+RVVCALL(OPIVV2, vwsll_vv_b, WOP_UUU_B, H2, H1, H1, DO_SLL)
+RVVCALL(OPIVV2, vwsll_vv_h, WOP_UUU_H, H4, H2, H2, DO_SLL)
+RVVCALL(OPIVV2, vwsll_vv_w, WOP_UUU_W, H8, H4, H4, DO_SLL)
+GEN_VEXT_VV(vwsll_vv_b, 2)
+GEN_VEXT_VV(vwsll_vv_h, 4)
+GEN_VEXT_VV(vwsll_vv_w, 8)
+
+RVVCALL(OPIVX2, vwsll_vx_b, WOP_UUU_B, H2, H1, DO_SLL)
+RVVCALL(OPIVX2, vwsll_vx_h, WOP_UUU_H, H4, H2, DO_SLL)
+RVVCALL(OPIVX2, vwsll_vx_w, WOP_UUU_W, H8, H4, DO_SLL)
+GEN_VEXT_VX(vwsll_vx_b, 2)
+GEN_VEXT_VX(vwsll_vx_h, 4)
+GEN_VEXT_VX(vwsll_vx_w, 8)
diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvvk.c.inc
+++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool vclmul_vx_check(DisasContext *s, arg_rmrr *a)
 
 GEN_VX_MASKED_TRANS(vclmul_vx, vclmul_vx_check)
 GEN_VX_MASKED_TRANS(vclmulh_vx, vclmul_vx_check)
+
+/*
+ * Zvbb
+ */
+
+#define GEN_OPIVI_GVEC_TRANS_CHECK(NAME, IMM_MODE, OPIVX, SUF, CHECK)   \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)              \
+    {                                                                   \
+        if (CHECK(s, a)) {                                              \
+            static gen_helper_opivx *const fns[4] = {                   \
+                gen_helper_##OPIVX##_b,                                 \
+                gen_helper_##OPIVX##_h,                                 \
+                gen_helper_##OPIVX##_w,                                 \
+                gen_helper_##OPIVX##_d,                                 \
+            };                                                          \
+            return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew], \
+                                 IMM_MODE);                             \
+        }                                                               \
+        return false;                                                   \
+    }
+
+#define GEN_OPIVV_GVEC_TRANS_CHECK(NAME, SUF, CHECK)                     \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)               \
+    {                                                                    \
+        if (CHECK(s, a)) {                                               \
+            static gen_helper_gvec_4_ptr *const fns[4] = {               \
+                gen_helper_##NAME##_b,                                   \
+                gen_helper_##NAME##_h,                                   \
+                gen_helper_##NAME##_w,                                   \
+                gen_helper_##NAME##_d,                                   \
+            };                                                           \
+            return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
+        }                                                                \
+        return false;                                                    \
+    }
+
+#define GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(NAME, SUF, CHECK)       \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)       \
+    {                                                            \
+        if (CHECK(s, a)) {                                       \
+            static gen_helper_opivx *const fns[4] = {            \
+                gen_helper_##NAME##_b,                           \
+                gen_helper_##NAME##_h,                           \
+                gen_helper_##NAME##_w,                           \
+                gen_helper_##NAME##_d,                           \
+            };                                                   \
+            return do_opivx_gvec_shift(s, a, tcg_gen_gvec_##SUF, \
+                                       fns[s->sew]);             \
+        }                                                        \
+        return false;                                            \
+    }
+
+static bool zvbb_vv_check(DisasContext *s, arg_rmrr *a)
+{
+    return opivv_check(s, a) && s->cfg_ptr->ext_zvbb == true;
+}
+
+static bool zvbb_vx_check(DisasContext *s, arg_rmrr *a)
+{
+    return opivx_check(s, a) && s->cfg_ptr->ext_zvbb == true;
+}
+
+/* vrol.v[vx] */
+GEN_OPIVV_GVEC_TRANS_CHECK(vrol_vv, rotlv, zvbb_vv_check)
+GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vrol_vx, rotls, zvbb_vx_check)
+
+/* vror.v[vxi] */
+GEN_OPIVV_GVEC_TRANS_CHECK(vror_vv, rotrv, zvbb_vv_check)
+GEN_OPIVX_GVEC_SHIFT_TRANS_CHECK(vror_vx, rotrs, zvbb_vx_check)
+GEN_OPIVI_GVEC_TRANS_CHECK(vror_vi, IMM_TRUNC_SEW, vror_vx, rotri, zvbb_vx_check)
+
+#define GEN_OPIVX_GVEC_TRANS_CHECK(NAME, SUF, CHECK)                     \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)               \
+    {                                                                    \
+        if (CHECK(s, a)) {                                               \
+            static gen_helper_opivx *const fns[4] = {                    \
+                gen_helper_##NAME##_b,                                   \
+                gen_helper_##NAME##_h,                                   \
+                gen_helper_##NAME##_w,                                   \
+                gen_helper_##NAME##_d,                                   \
+            };                                                           \
+            return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]); \
+        }                                                                \
+        return false;                                                    \
+    }
+
+/* vandn.v[vx] */
+GEN_OPIVV_GVEC_TRANS_CHECK(vandn_vv, andc, zvbb_vv_check)
+GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvbb_vx_check)
+
+#define GEN_OPIV_TRANS(NAME, CHECK)                                        \
+    static bool trans_##NAME(DisasContext *s, arg_rmr *a)                  \
+    {                                                                      \
+        if (CHECK(s, a)) {                                                 \
+            uint32_t data = 0;                                             \
+            static gen_helper_gvec_3_ptr *const fns[4] = {                 \
+                gen_helper_##NAME##_b,                                     \
+                gen_helper_##NAME##_h,                                     \
+                gen_helper_##NAME##_w,                                     \
+                gen_helper_##NAME##_d,                                     \
+            };                                                             \
+            TCGLabel *over = gen_new_label();                              \
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);     \
+                                                                           \
+            data = FIELD_DP32(data, VDATA, VM, a->vm);                     \
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                 \
+            data = FIELD_DP32(data, VDATA, VTA, s->vta);                   \
+            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \
+            data = FIELD_DP32(data, VDATA, VMA, s->vma);                   \
+            tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),         \
+                               vreg_ofs(s, a->rs2), cpu_env,               \
+                               s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, \
+                               data, fns[s->sew]);                         \
+            mark_vs_dirty(s);                                              \
+            gen_set_label(over);                                           \
+            return true;                                                   \
+        }                                                                  \
+        return false;                                                      \
+    }
+
+static bool zvbb_opiv_check(DisasContext *s, arg_rmr *a)
+{
+    return s->cfg_ptr->ext_zvbb == true &&
+           require_rvv(s) &&
+           vext_check_isa_ill(s) &&
+           vext_check_ss(s, a->rd, a->rs2, a->vm);
+}
+
+GEN_OPIV_TRANS(vbrev8_v, zvbb_opiv_check)
+GEN_OPIV_TRANS(vrev8_v, zvbb_opiv_check)
+GEN_OPIV_TRANS(vbrev_v, zvbb_opiv_check)
+GEN_OPIV_TRANS(vclz_v, zvbb_opiv_check)
+GEN_OPIV_TRANS(vctz_v, zvbb_opiv_check)
+GEN_OPIV_TRANS(vcpop_v, zvbb_opiv_check)
+
+static bool vwsll_vv_check(DisasContext *s, arg_rmrr *a)
+{
+    return s->cfg_ptr->ext_zvbb && opivv_widen_check(s, a);
+}
+
+static bool vwsll_vx_check(DisasContext *s, arg_rmrr *a)
+{
+    return s->cfg_ptr->ext_zvbb && opivx_widen_check(s, a);
+}
+
+/* OPIVI without GVEC IR */
+#define GEN_OPIVI_WIDEN_TRANS(NAME, IMM_MODE, OPIVX, CHECK)                  \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
+    {                                                                        \
+        if (CHECK(s, a)) {                                                   \
+            static gen_helper_opivx *const fns[3] = {                        \
+                gen_helper_##OPIVX##_b,                                      \
+                gen_helper_##OPIVX##_h,                                      \
+                gen_helper_##OPIVX##_w,                                      \
+            };                                                               \
+            return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, \
+                               IMM_MODE);                                    \
+        }                                                                    \
+        return false;                                                        \
+    }
+
+GEN_OPIVV_WIDEN_TRANS(vwsll_vv, vwsll_vv_check)
+GEN_OPIVX_WIDEN_TRANS(vwsll_vx, vwsll_vx_check)
+GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll_vx_check)
-- 
2.41.0

From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>

This commit adds support for the Zvkned vector-crypto extension, which
consists of the following instructions:

* vaesef.[vv,vs]
* vaesdf.[vv,vs]
* vaesdm.[vv,vs]
* vaesz.vs
* vaesem.[vv,vs]
* vaeskf1.vi
* vaeskf2.vi

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Co-authored-by: William Salmon <will.salmon@codethink.co.uk>
[max.chou@sifive.com: Replaced vstart checking by TCG op]
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: William Salmon <will.salmon@codethink.co.uk>
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Imported aes-round.h and exposed x-zvkned
property]
[max.chou@sifive.com: Fixed endian issues and replaced the vstart & vl
egs checking by helper function]
[max.chou@sifive.com: Replaced bswap32 calls in aes key expanding]
Message-ID: <20230711165917.2629866-10-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |   1 +
 target/riscv/helper.h                    |  14 ++
 target/riscv/insn32.decode               |  14 ++
 target/riscv/cpu.c                       |   4 +-
 target/riscv/vcrypto_helper.c            | 202 +++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc | 147 +++++++++++++++++
 6 files changed, 381 insertions(+), 1 deletion(-)

diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_cfg.h
+++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
     bool ext_zve64d;
     bool ext_zvbb;
     bool ext_zvbc;
+    bool ext_zvkned;
     bool ext_zmmul;
     bool ext_zvfbfmin;
     bool ext_zvfbfwma;
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_2(egs_check, void, i32, env)
+
+DEF_HELPER_4(vaesef_vv, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesef_vs, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesdf_vv, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesdf_vs, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesem_vv, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesem_vs, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesdm_vv, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32)
+DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32)
+DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@
 @r_rm    .......   ..... ..... ... ..... ....... %rs2 %rs1 %rm %rd
 @r2_rm   .......   ..... ..... ... ..... ....... %rs1 %rm %rd
 @r2      .......   ..... ..... ... ..... ....... &r2 %rs1 %rd
+@r2_vm_1 ...... . ..... ..... ... ..... ....... &rmr vm=1 %rs2 %rd
 @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
 @r2_vm   ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd
 @r1_vm   ...... vm:1 ..... ..... ... ..... ....... %rd
@@ -XXX,XX +XXX,XX @@ vcpop_v     010010 . ..... 01110 010 ..... 1010111 @r2_vm
 vwsll_vv    110101 . ..... ..... 000 ..... 1010111 @r_vm
 vwsll_vx    110101 . ..... ..... 100 ..... 1010111 @r_vm
 vwsll_vi    110101 . ..... ..... 011 ..... 1010111 @r_vm
+
+# *** Zvkned vector crypto extension ***
+vaesef_vv   101000 1 ..... 00011 010 ..... 1110111 @r2_vm_1
+vaesef_vs   101001 1 ..... 00011 010 ..... 1110111 @r2_vm_1
+vaesdf_vv   101000 1 ..... 00001 010 ..... 1110111 @r2_vm_1
+vaesdf_vs   101001 1 ..... 00001 010 ..... 1110111 @r2_vm_1
+vaesem_vv   101000 1 ..... 00010 010 ..... 1110111 @r2_vm_1
+vaesem_vs   101001 1 ..... 00010 010 ..... 1110111 @r2_vm_1
+vaesdm_vv   101000 1 ..... 00000 010 ..... 1110111 @r2_vm_1
+vaesdm_vs   101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1
+vaesz_vs    101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1
+vaeskf1_vi  100010 1 ..... ..... 010 ..... 1110111 @r_vm_1
+vaeskf2_vi  101010 1 ..... ..... 010 ..... 1110111 @r_vm_1
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma),
     ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
     ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
+    ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
     ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
     ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
     ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
      * In principle Zve*x would also suffice here, were they supported
      * in qemu
      */
-    if (cpu->cfg.ext_zvbb && !cpu->cfg.ext_zve32f) {
+    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned) && !cpu->cfg.ext_zve32f) {
         error_setg(errp,
                    "Vector crypto extensions require V or Zve* extensions");
         return;
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
     /* Vector cryptography extensions */
     DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
     DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
+    DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
 
     DEFINE_PROP_END_OF_LIST(),
 };
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/bitops.h"
 #include "qemu/bswap.h"
 #include "cpu.h"
+#include "crypto/aes.h"
+#include "crypto/aes-round.h"
 #include "exec/memop.h"
 #include "exec/exec-all.h"
 #include "exec/helper-proto.h"
@@ -XXX,XX +XXX,XX @@ RVVCALL(OPIVX2, vwsll_vx_w, WOP_UUU_W, H8, H4, DO_SLL)
 GEN_VEXT_VX(vwsll_vx_b, 2)
 GEN_VEXT_VX(vwsll_vx_h, 4)
 GEN_VEXT_VX(vwsll_vx_w, 8)
+
+void HELPER(egs_check)(uint32_t egs, CPURISCVState *env)
+{
+    uint32_t vl = env->vl;
+    uint32_t vstart = env->vstart;
+
+    if (vl % egs != 0 || vstart % egs != 0) {
+        riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+    }
+}
+
+static inline void xor_round_key(AESState *round_state, AESState *round_key)
+{
+    round_state->v = round_state->v ^ round_key->v;
+}
+
+#define GEN_ZVKNED_HELPER_VV(NAME, ...)                                   \
+    void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env,            \
+                      uint32_t desc)                                      \
+    {                                                                     \
+        uint32_t vl = env->vl;                                            \
+        uint32_t total_elems = vext_get_total_elems(env, desc, 4);        \
+        uint32_t vta = vext_vta(desc);                                    \
+                                                                          \
+        for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {        \
+            AESState round_key;                                           \
+            round_key.d[0] = *((uint64_t *)vs2 + H8(i * 2 + 0));          \
+            round_key.d[1] = *((uint64_t *)vs2 + H8(i * 2 + 1));          \
+            AESState round_state;                                         \
+            round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0));         \
+            round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1));         \
+            __VA_ARGS__;                                                  \
+            *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0];         \
+            *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1];         \
+        }                                                                 \
+        env->vstart = 0;                                                  \
+        /* set tail elements to 1s */                                     \
+        vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);              \
+    }
+
+#define GEN_ZVKNED_HELPER_VS(NAME, ...)                                   \
+    void HELPER(NAME)(void *vd, void *vs2, CPURISCVState *env,            \
+                      uint32_t desc)                                      \
+    {                                                                     \
+        uint32_t vl = env->vl;                                            \
+        uint32_t total_elems = vext_get_total_elems(env, desc, 4);        \
+        uint32_t vta = vext_vta(desc);                                    \
+                                                                          \
+        for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {        \
+            AESState round_key;                                           \
+            round_key.d[0] = *((uint64_t *)vs2 + H8(0));                  \
+            round_key.d[1] = *((uint64_t *)vs2 + H8(1));                  \
+            AESState round_state;                                         \
+            round_state.d[0] = *((uint64_t *)vd + H8(i * 2 + 0));         \
+            round_state.d[1] = *((uint64_t *)vd + H8(i * 2 + 1));         \
+            __VA_ARGS__;                                                  \
+            *((uint64_t *)vd + H8(i * 2 + 0)) = round_state.d[0];         \
+            *((uint64_t *)vd + H8(i * 2 + 1)) = round_state.d[1];         \
+        }                                                                 \
+        env->vstart = 0;                                                  \
+        /* set tail elements to 1s */                                     \
+        vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);              \
+    }
+
+GEN_ZVKNED_HELPER_VV(vaesef_vv, aesenc_SB_SR_AK(&round_state,
+                                                &round_state,
+                                                &round_key,
+                                                false);)
+GEN_ZVKNED_HELPER_VS(vaesef_vs, aesenc_SB_SR_AK(&round_state,
+                                                &round_state,
+                                                &round_key,
+                                                false);)
+GEN_ZVKNED_HELPER_VV(vaesdf_vv, aesdec_ISB_ISR_AK(&round_state,
+                                                  &round_state,
+                                                  &round_key,
+                                                  false);)
+GEN_ZVKNED_HELPER_VS(vaesdf_vs, aesdec_ISB_ISR_AK(&round_state,
+                                                  &round_state,
+                                                  &round_key,
+                                                  false);)
+GEN_ZVKNED_HELPER_VV(vaesem_vv, aesenc_SB_SR_MC_AK(&round_state,
+                                                   &round_state,
+                                                   &round_key,
+                                                   false);)
+GEN_ZVKNED_HELPER_VS(vaesem_vs, aesenc_SB_SR_MC_AK(&round_state,
+                                                   &round_state,
+                                                   &round_key,
+                                                   false);)
+GEN_ZVKNED_HELPER_VV(vaesdm_vv, aesdec_ISB_ISR_AK_IMC(&round_state,
+                                                      &round_state,
+                                                      &round_key,
+                                                      false);)
+GEN_ZVKNED_HELPER_VS(vaesdm_vs, aesdec_ISB_ISR_AK_IMC(&round_state,
+                                                      &round_state,
+                                                      &round_key,
+                                                      false);)
+GEN_ZVKNED_HELPER_VS(vaesz_vs, xor_round_key(&round_state, &round_key);)
+
+void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
+                        CPURISCVState *env, uint32_t desc)
+{
+    uint32_t *vd = vd_vptr;
+    uint32_t *vs2 = vs2_vptr;
+    uint32_t vl = env->vl;
+    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+    uint32_t vta = vext_vta(desc);
+
+    uimm &= 0b1111;
+    if (uimm > 10 || uimm == 0) {
+        uimm ^= 0b1000;
+    }
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        uint32_t rk[8], tmp;
+        static const uint32_t rcon[] = {
+            0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010,
+            0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036,
+        };
+
+        rk[0] = vs2[i * 4 + H4(0)];
+        rk[1] = vs2[i * 4 + H4(1)];
+        rk[2] = vs2[i * 4 + H4(2)];
+        rk[3] = vs2[i * 4 + H4(3)];
+        tmp = ror32(rk[3], 8);
+
+        rk[4] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) |
+                         ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) |
+                         ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) |
+                         ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0))
+                      ^ rcon[uimm - 1];
+        rk[5] = rk[1] ^ rk[4];
+        rk[6] = rk[2] ^ rk[5];
+        rk[7] = rk[3] ^ rk[6];
+
+        vd[i * 4 + H4(0)] = rk[4];
+        vd[i * 4 + H4(1)] = rk[5];
+        vd[i * 4 + H4(2)] = rk[6];
+        vd[i * 4 + H4(3)] = rk[7];
+    }
+    env->vstart = 0;
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
+}
+
+void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
+                        CPURISCVState *env, uint32_t desc)
+{
+    uint32_t *vd = vd_vptr;
+    uint32_t *vs2 = vs2_vptr;
+    uint32_t vl = env->vl;
+    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+    uint32_t vta = vext_vta(desc);
+
+    uimm &= 0b1111;
+    if (uimm > 14 || uimm < 2) {
+        uimm ^= 0b1000;
+    }
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        uint32_t rk[12], tmp;
+        static const uint32_t rcon[] = {
+            0x00000001, 0x00000002, 0x00000004, 0x00000008, 0x00000010,
+            0x00000020, 0x00000040, 0x00000080, 0x0000001B, 0x00000036,
+        };
+
+        rk[0] = vd[i * 4 + H4(0)];
+        rk[1] = vd[i * 4 + H4(1)];
+        rk[2] = vd[i * 4 + H4(2)];
+        rk[3] = vd[i * 4 + H4(3)];
+        rk[4] = vs2[i * 4 + H4(0)];
+        rk[5] = vs2[i * 4 + H4(1)];
+        rk[6] = vs2[i * 4 + H4(2)];
+        rk[7] = vs2[i * 4 + H4(3)];
+
+        if (uimm % 2 == 0) {
+            tmp = ror32(rk[7], 8);
+            rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(tmp >> 24) & 0xff] << 24) |
+                             ((uint32_t)AES_sbox[(tmp >> 16) & 0xff] << 16) |
+                             ((uint32_t)AES_sbox[(tmp >> 8) & 0xff] << 8) |
+                             ((uint32_t)AES_sbox[(tmp >> 0) & 0xff] << 0))
+                          ^ rcon[(uimm - 1) / 2];
+        } else {
+            rk[8] = rk[0] ^ (((uint32_t)AES_sbox[(rk[7] >> 24) & 0xff] << 24) |
+                             ((uint32_t)AES_sbox[(rk[7] >> 16) & 0xff] << 16) |
+                             ((uint32_t)AES_sbox[(rk[7] >> 8) & 0xff] << 8) |
+                             ((uint32_t)AES_sbox[(rk[7] >> 0) & 0xff] << 0));
+        }
+        rk[9] = rk[1] ^ rk[8];
+        rk[10] = rk[2] ^ rk[9];
+        rk[11] = rk[3] ^ rk[10];
+
+        vd[i * 4 + H4(0)] = rk[8];
+        vd[i * 4 + H4(1)] = rk[9];
+        vd[i * 4 + H4(2)] = rk[10];
+        vd[i * 4 + H4(3)] = rk[11];
+    }
+    env->vstart = 0;
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
+}
diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvvk.c.inc
+++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool vwsll_vx_check(DisasContext *s, arg_rmrr *a)
 GEN_OPIVV_WIDEN_TRANS(vwsll_vv, vwsll_vv_check)
 GEN_OPIVX_WIDEN_TRANS(vwsll_vx, vwsll_vx_check)
 GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll_vx_check)
+
+/*
+ * Zvkned
+ */
+
+#define ZVKNED_EGS 4
+
+#define GEN_V_UNMASKED_TRANS(NAME, CHECK, EGS)                                \
+    static bool trans_##NAME(DisasContext *s, arg_##NAME *a)                  \
+    {                                                                         \
+        if (CHECK(s, a)) {                                                    \
+            TCGv_ptr rd_v, rs2_v;                                             \
+            TCGv_i32 desc, egs;                                               \
+            uint32_t data = 0;                                                \
+            TCGLabel *over = gen_new_label();                                 \
+                                                                              \
+            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
+                /* save opcode for unwinding in case we throw an exception */ \
+                decode_save_opc(s);                                           \
+                egs = tcg_constant_i32(EGS);                                  \
+                gen_helper_egs_check(egs, cpu_env);                           \
+                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
+            }                                                                 \
+                                                                              \
+            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
+            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
+            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
+            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
+            rd_v = tcg_temp_new_ptr();                                        \
+            rs2_v = tcg_temp_new_ptr();                                       \
+            desc = tcg_constant_i32(                                          \
+                simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \
+            tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd));              \
+            tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2));            \
+            gen_helper_##NAME(rd_v, rs2_v, cpu_env, desc);                    \
+            mark_vs_dirty(s);                                                 \
+            gen_set_label(over);                                              \
+            return true;                                                      \
+        }                                                                     \
+        return false;                                                         \
+    }
+
+static bool vaes_check_vv(DisasContext *s, arg_rmr *a)
+{
+    int egw_bytes = ZVKNED_EGS << s->sew;
+    return s->cfg_ptr->ext_zvkned == true &&
+           require_rvv(s) &&
+           vext_check_isa_ill(s) &&
+           MAXSZ(s) >= egw_bytes &&
+           require_align(a->rd, s->lmul) &&
+           require_align(a->rs2, s->lmul) &&
+           s->sew == MO_32;
+}
+
+static bool vaes_check_overlap(DisasContext *s, int vd, int vs2)
+{
+    int8_t op_size = s->lmul <= 0 ? 1 : 1 << s->lmul;
+    return !is_overlapped(vd, op_size, vs2, 1);
+}
+
+static bool vaes_check_vs(DisasContext *s, arg_rmr *a)
+{
+    int egw_bytes = ZVKNED_EGS << s->sew;
+    return vaes_check_overlap(s, a->rd, a->rs2) &&
+           MAXSZ(s) >= egw_bytes &&
+           s->cfg_ptr->ext_zvkned == true &&
+           require_rvv(s) &&
+           vext_check_isa_ill(s) &&
+           require_align(a->rd, s->lmul) &&
+           s->sew == MO_32;
+}
+
+GEN_V_UNMASKED_TRANS(vaesef_vv, vaes_check_vv, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesef_vs, vaes_check_vs, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesdf_vv, vaes_check_vv, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesdf_vs, vaes_check_vs, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesdm_vv, vaes_check_vv, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesdm_vs, vaes_check_vs, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesz_vs, vaes_check_vs, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesem_vv, vaes_check_vv, ZVKNED_EGS)
+GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED_EGS)
+
+#define GEN_VI_UNMASKED_TRANS(NAME, CHECK, EGS)                               \
+    static bool trans_##NAME(DisasContext *s, arg_##NAME *a)                  \
+    {                                                                         \
+        if (CHECK(s, a)) {                                                    \
+            TCGv_ptr rd_v, rs2_v;                                             \
+            TCGv_i32 uimm_v, desc, egs;                                       \
+            uint32_t data = 0;                                                \
+            TCGLabel *over = gen_new_label();                                 \
+                                                                              \
+            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
+                /* save opcode for unwinding in case we throw an exception */ \
+                decode_save_opc(s);                                           \
+                egs = tcg_constant_i32(EGS);                                  \
+                gen_helper_egs_check(egs, cpu_env);                           \
+                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
+            }                                                                 \
+                                                                              \
+            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
+            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
+            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
+            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
+                                                                              \
+            rd_v = tcg_temp_new_ptr();                                        \
+            rs2_v = tcg_temp_new_ptr();                                       \
+            uimm_v = tcg_constant_i32(a->rs1);                                \
+            desc = tcg_constant_i32(                                          \
+                simd_desc(s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, data)); \
+            tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd));              \
+            tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2));            \
+            gen_helper_##NAME(rd_v, rs2_v, uimm_v, cpu_env, desc);            \
+            mark_vs_dirty(s);                                                 \
+            gen_set_label(over);                                              \
+            return true;                                                      \
+        }                                                                     \
+        return false;                                                         \
+    }
+
+static bool vaeskf1_check(DisasContext *s, arg_vaeskf1_vi *a)
+{
+    int egw_bytes = ZVKNED_EGS << s->sew;
+    return s->cfg_ptr->ext_zvkned == true &&
+           require_rvv(s) &&
+           vext_check_isa_ill(s) &&
+           MAXSZ(s) >= egw_bytes &&
+           s->sew == MO_32 &&
+           require_align(a->rd, s->lmul) &&
+           require_align(a->rs2, s->lmul);
+}
+
+static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a)
+{
+    int egw_bytes = ZVKNED_EGS << s->sew;
+    return s->cfg_ptr->ext_zvkned == true &&
+           require_rvv(s) &&
+           vext_check_isa_ill(s) &&
+           MAXSZ(s) >= egw_bytes &&
+           s->sew == MO_32 &&
+           require_align(a->rd, s->lmul) &&
+           require_align(a->rs2, s->lmul);
+}
+
+GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS)
+GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS)
-- 
2.41.0

From: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>

This commit adds support for the Zvknh vector-crypto extension, which
consists of the following instructions:

* vsha2ms.vv
* vsha2c[hl].vv

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
[max.chou@sifive.com: Replaced vstart checking by TCG op]
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Exposed x-zvknha & x-zvknhb properties]
[max.chou@sifive.com: Replaced SEW selection to happened during
translation]
Message-ID: <20230711165917.2629866-11-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |   2 +
 target/riscv/helper.h                    |   6 +
 target/riscv/insn32.decode               |   5 +
 target/riscv/cpu.c                       |  13 +-
 target/riscv/vcrypto_helper.c            | 238 +++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc | 129 ++++++++++++
 6 files changed, 390 insertions(+), 3 deletions(-)

diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_cfg.h
+++ b/target/riscv/cpu_cfg.h
@@ -XXX,XX +XXX,XX @@ struct RISCVCPUConfig {
     bool ext_zvbb;
     bool ext_zvbc;
     bool ext_zvkned;
+    bool ext_zvknha;
+    bool ext_zvknhb;
     bool ext_zmmul;
     bool ext_zvfbfmin;
     bool ext_zvfbfwma;
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32)
 DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32)
 DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32)
 DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32)
+
+DEF_HELPER_5(vsha2ms_vv, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vsha2ch32_vv, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vsha2ch64_vv, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vsha2cl32_vv, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -XXX,XX +XXX,XX @@ vaesdm_vs   101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1
 vaesz_vs    101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1
 vaeskf1_vi  100010 1 ..... ..... 010 ..... 1110111 @r_vm_1
 vaeskf2_vi  101010 1 ..... ..... 010 ..... 1110111 @r_vm_1
+
+# *** Zvknh vector crypto extension ***
+vsha2ms_vv  101101 1 ..... ..... 010 ..... 1110111 @r_vm_1
+vsha2ch_vv  101110 1 ..... ..... 010 ..... 1110111 @r_vm_1
+vsha2cl_vv  101111 1 ..... ..... 010 ..... 1110111 @r_vm_1
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
     ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
     ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
+    ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
+    ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
     ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx),
     ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin),
     ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia),
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
      * In principle Zve*x would also suffice here, were they supported
      * in qemu
      */
-    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned) && !cpu->cfg.ext_zve32f) {
+    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha) &&
+        !cpu->cfg.ext_zve32f) {
         error_setg(errp,
                    "Vector crypto extensions require V or Zve* extensions");
         return;
     }
 
-    if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) {
-        error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions");
+    if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64f) {
+        error_setg(
+            errp,
+            "Zvbc and Zvknhb extensions require V or Zve64{f,d} extensions");
         return;
     }
 
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
     DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
     DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
     DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
+    DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
+    DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),
 
     DEFINE_PROP_END_OF_LIST(),
 };
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
     /* set tail elements to 1s */
     vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4);
 }
+
+static inline uint32_t sig0_sha256(uint32_t x)
+{
+    return ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3);
+}
+
+static inline uint32_t sig1_sha256(uint32_t x)
+{
+    return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10);
+}
+
+static inline uint64_t sig0_sha512(uint64_t x)
+{
+    return ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7);
+}
+
+static inline uint64_t sig1_sha512(uint64_t x)
+{
+    return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6);
+}
+
+static inline void vsha2ms_e32(uint32_t *vd, uint32_t *vs1, uint32_t *vs2)
+{
+    uint32_t res[4];
+    res[0] = sig1_sha256(vs1[H4(2)]) + vs2[H4(1)] + sig0_sha256(vd[H4(1)]) +
+             vd[H4(0)];
+    res[1] = sig1_sha256(vs1[H4(3)]) + vs2[H4(2)] + sig0_sha256(vd[H4(2)]) +
+             vd[H4(1)];
+    res[2] =
+        sig1_sha256(res[0]) + vs2[H4(3)] + sig0_sha256(vd[H4(3)]) + vd[H4(2)];
+    res[3] =
+        sig1_sha256(res[1]) + vs1[H4(0)] + sig0_sha256(vs2[H4(0)]) + vd[H4(3)];
+    vd[H4(3)] = res[3];
+    vd[H4(2)] = res[2];
+    vd[H4(1)] = res[1];
+    vd[H4(0)] = res[0];
+}
+
+static inline void vsha2ms_e64(uint64_t *vd, uint64_t *vs1, uint64_t *vs2)
+{
+    uint64_t res[4];
+    res[0] = sig1_sha512(vs1[2]) + vs2[1] + sig0_sha512(vd[1]) + vd[0];
+    res[1] = sig1_sha512(vs1[3]) + vs2[2] + sig0_sha512(vd[2]) + vd[1];
+    res[2] = sig1_sha512(res[0]) + vs2[3] + sig0_sha512(vd[3]) + vd[2];
+    res[3] = sig1_sha512(res[1]) + vs1[0] + sig0_sha512(vs2[0]) + vd[3];
+    vd[3] = res[3];
+    vd[2] = res[2];
+    vd[1] = res[1];
+    vd[0] = res[0];
+}
+
+void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
+                        uint32_t desc)
+{
+    uint32_t sew = FIELD_EX64(env->vtype, VTYPE, VSEW);
+    uint32_t esz = sew == MO_32 ? 4 : 8;
+    uint32_t total_elems;
+    uint32_t vta = vext_vta(desc);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        if (sew == MO_32) {
+            vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4,
+                        ((uint32_t *)vs2) + i * 4);
+        } else {
+            /* If not 32 then SEW should be 64 */
+            vsha2ms_e64(((uint64_t *)vd) + i * 4, ((uint64_t *)vs1) + i * 4,
+                        ((uint64_t *)vs2) + i * 4);
+        }
+    }
+    /* set tail elements to 1s */
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
+    env->vstart = 0;
+}
+
+static inline uint64_t sum0_64(uint64_t x)
+{
+    return ror64(x, 28) ^ ror64(x, 34) ^ ror64(x, 39);
+}
+
+static inline uint32_t sum0_32(uint32_t x)
+{
+    return ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22);
+}
+
+static inline uint64_t sum1_64(uint64_t x)
+{
+    return ror64(x, 14) ^ ror64(x, 18) ^ ror64(x, 41);
+}
+
+static inline uint32_t sum1_32(uint32_t x)
+{
+    return ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25);
+}
+
+#define ch(x, y, z) ((x & y) ^ ((~x) & z))
+
+#define maj(x, y, z) ((x & y) ^ (x & z) ^ (y & z))
+
+static void vsha2c_64(uint64_t *vs2, uint64_t *vd, uint64_t *vs1)
+{
+    uint64_t a = vs2[3], b = vs2[2], e = vs2[1], f = vs2[0];
+    uint64_t c = vd[3], d = vd[2], g = vd[1], h = vd[0];
+    uint64_t W0 = vs1[0], W1 = vs1[1];
+    uint64_t T1 = h + sum1_64(e) + ch(e, f, g) + W0;
+    uint64_t T2 = sum0_64(a) + maj(a, b, c);
+
+    h = g;
+    g = f;
+    f = e;
+    e = d + T1;
+    d = c;
+    c = b;
+    b = a;
+    a = T1 + T2;
+
+    T1 = h + sum1_64(e) + ch(e, f, g) + W1;
+    T2 = sum0_64(a) + maj(a, b, c);
+    h = g;
+    g = f;
+    f = e;
+    e = d + T1;
+    d = c;
+    c = b;
+    b = a;
+    a = T1 + T2;
+
+    vd[0] = f;
+    vd[1] = e;
+    vd[2] = b;
+    vd[3] = a;
+}
+
+static void vsha2c_32(uint32_t *vs2, uint32_t *vd, uint32_t *vs1)
+{
+    uint32_t a = vs2[H4(3)], b = vs2[H4(2)], e = vs2[H4(1)], f = vs2[H4(0)];
+    uint32_t c = vd[H4(3)], d = vd[H4(2)], g = vd[H4(1)], h = vd[H4(0)];
+    uint32_t W0 = vs1[H4(0)], W1 = vs1[H4(1)];
+    uint32_t T1 = h + sum1_32(e) + ch(e, f, g) + W0;
+    uint32_t T2 = sum0_32(a) + maj(a, b, c);
+
+    h = g;
+    g = f;
+    f = e;
+    e = d + T1;
+    d = c;
+    c = b;
+    b = a;
+    a = T1 + T2;
+
+    T1 = h + sum1_32(e) + ch(e, f, g) + W1;
+    T2 = sum0_32(a) + maj(a, b, c);
+    h = g;
+    g = f;
+    f = e;
+    e = d + T1;
+    d = c;
+    c = b;
+    b = a;
+    a = T1 + T2;
+
+    vd[H4(0)] = f;
+    vd[H4(1)] = e;
+    vd[H4(2)] = b;
+    vd[H4(3)] = a;
+}
+
+void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
+                          uint32_t desc)
+{
+    const uint32_t esz = 4;
+    uint32_t total_elems;
+    uint32_t vta = vext_vta(desc);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
+                  ((uint32_t *)vs1) + 4 * i + 2);
+    }
+
+    /* set tail elements to 1s */
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
+    env->vstart = 0;
+}
+
+void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
+                          uint32_t desc)
+{
+    const uint32_t esz = 8;
+    uint32_t total_elems;
+    uint32_t vta = vext_vta(desc);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
+                  ((uint64_t *)vs1) + 4 * i + 2);
+    }
+
+    /* set tail elements to 1s */
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
+    env->vstart = 0;
+}
+
+void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
+                          uint32_t desc)
+{
+    const uint32_t esz = 4;
+    uint32_t total_elems;
+    uint32_t vta = vext_vta(desc);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
+                  (((uint32_t *)vs1) + 4 * i));
+    }
+
+    /* set tail elements to 1s */
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
+    env->vstart = 0;
+}
+
+void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env,
+                          uint32_t desc)
+{
+    uint32_t esz = 8;
+    uint32_t total_elems;
+    uint32_t vta = vext_vta(desc);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
+                  (((uint64_t *)vs1) + 4 * i));
+    }
+
+    /* set tail elements to 1s */
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz);
+    env->vstart = 0;
+}
diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvvk.c.inc
+++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -XXX,XX +XXX,XX @@ static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a)
 
 GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS)
 GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS)
+
+/*
+ * Zvknh
+ */
+
+#define ZVKNH_EGS 4
+
+#define GEN_VV_UNMASKED_TRANS(NAME, CHECK, EGS)                               \
+    static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                    \
+    {                                                                         \
+        if (CHECK(s, a)) {                                                    \
+            uint32_t data = 0;                                                \
+            TCGLabel *over = gen_new_label();                                 \
+            TCGv_i32 egs;                                                     \
+                                                                              \
+            if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {                      \
+                /* save opcode for unwinding in case we throw an exception */ \
+                decode_save_opc(s);                                           \
+                egs = tcg_constant_i32(EGS);                                  \
+                gen_helper_egs_check(egs, cpu_env);                           \
+                tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);    \
+            }                                                                 \
+                                                                              \
+            data = FIELD_DP32(data, VDATA, VM, a->vm);                        \
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);                    \
+            data = FIELD_DP32(data, VDATA, VTA, s->vta);                      \
+            data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);    \
+            data = FIELD_DP32(data, VDATA, VMA, s->vma);                      \
+                                                                              \
+            tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),       \
+                               vreg_ofs(s, a->rs2), cpu_env,                  \
+                               s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8,    \
+                               data, gen_helper_##NAME);                      \
+                                                                              \
+            mark_vs_dirty(s);                                                 \
+            gen_set_label(over);                                              \
+            return true;                                                      \
+        }                                                                     \
+        return false;                                                         \
+    }
+
+static bool vsha_check_sew(DisasContext *s)
+{
+    return (s->cfg_ptr->ext_zvknha == true && s->sew == MO_32) ||
+           (s->cfg_ptr->ext_zvknhb == true &&
+            (s->sew == MO_32 || s->sew == MO_64));
+}
+
+static bool vsha_check(DisasContext *s, arg_rmrr *a)
+{
+    int egw_bytes = ZVKNH_EGS << s->sew;
+    int mult = 1 << MAX(s->lmul, 0);
+    return opivv_check(s, a) &&
+           vsha_check_sew(s) &&
+           MAXSZ(s) >= egw_bytes &&
+           !is_overlapped(a->rd, mult, a->rs1, mult) &&
+           !is_overlapped(a->rd, mult, a->rs2, mult) &&
+           s->lmul >= 0;
+}
+
+GEN_VV_UNMASKED_TRANS(vsha2ms_vv, vsha_check, ZVKNH_EGS)
+
+static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr *a)
+{
+    if (vsha_check(s, a)) {
+        uint32_t data = 0;
+        TCGLabel *over = gen_new_label();
+        TCGv_i32 egs;
+
+        if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
+            /* save opcode for unwinding in case we throw an exception */
+            decode_save_opc(s);
+            egs = tcg_constant_i32(ZVKNH_EGS);
+            gen_helper_egs_check(egs, cpu_env);
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
+        }
+
+        data = FIELD_DP32(data, VDATA, VM, a->vm);
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+        data = FIELD_DP32(data, VDATA, VTA, s->vta);
+        data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
+        data = FIELD_DP32(data, VDATA, VMA, s->vma);
+
+        tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
+            vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8,
+            s->cfg_ptr->vlen / 8, data,
+            s->sew == MO_32 ?
+                gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv);
+
+        mark_vs_dirty(s);
+        gen_set_label(over);
+        return true;
+    }
+    return false;
+}
+
+static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr *a)
+{
+    if (vsha_check(s, a)) {
+        uint32_t data = 0;
+        TCGLabel *over = gen_new_label();
+        TCGv_i32 egs;
+
+        if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
+            /* save opcode for unwinding in case we throw an exception */
+            decode_save_opc(s);
+            egs = tcg_constant_i32(ZVKNH_EGS);
+            gen_helper_egs_check(egs, cpu_env);
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
+        }
+
+        data = FIELD_DP32(data, VDATA, VM, a->vm);
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+        data = FIELD_DP32(data, VDATA, VTA, s->vta);
+        data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);
+        data = FIELD_DP32(data, VDATA, VMA, s->vma);
+
+        tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
+            vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8,
+            s->cfg_ptr->vlen / 8, data,
+            s->sew == MO_32 ?
+                gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv);
+
+        mark_vs_dirty(s);
+        gen_set_label(over);
+        return true;
+    }
+    return false;
+}
-- 
2.41.0

From: Lawrence Hunter <lawrence.hunter@codethink.co.uk>

This commit adds support for the Zvksh vector-crypto extension, which
consists of the following instructions:

* vsm3me.vv
* vsm3c.vi

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
[max.chou@sifive.com: Replaced vstart checking by TCG op]
Signed-off-by: Kiran Ostrolenk <kiran.ostrolenk@codethink.co.uk>
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Exposed x-zvksh property]
Message-ID: <20230711165917.2629866-12-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |   1 +
 target/riscv/helper.h                    |   3 +
 target/riscv/insn32.decode               |   4 +
 target/riscv/cpu.c                       |   6 +-
 target/riscv/vcrypto_helper.c            | 134 +++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc |  31 ++++++
 6 files changed, 177 insertions(+), 2 deletions(-)

From: Nazar Kazakov <nazar.kazakov@codethink.co.uk>

This commit adds support for the Zvkg vector-crypto extension, which
consists of the following instructions:

* vgmul.vv
* vghsh.vv

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
[max.chou@sifive.com: Replaced vstart checking by TCG op]
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Exposed x-zvkg property]
[max.chou@sifive.com: Replaced uint by int for cross win32 build]
Message-ID: <20230711165917.2629866-13-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |  1 +
 target/riscv/helper.h                    |  3 +
 target/riscv/insn32.decode               |  4 ++
 target/riscv/cpu.c                       |  6 +-
 target/riscv/vcrypto_helper.c            | 72 ++++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc | 30 ++++++++++
 6 files changed, 114 insertions(+), 2 deletions(-)

From: Max Chou <max.chou@sifive.com>

Allows sharing of sm4_subword between different targets.

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-14-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 include/crypto/sm4.h           |  8 ++++++++
 target/arm/tcg/crypto_helper.c | 10 ++--------
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
index XXXXXXX..XXXXXXX 100644
--- a/include/crypto/sm4.h
+++ b/include/crypto/sm4.h
@@ -XXX,XX +XXX,XX @@
 
 extern const uint8_t sm4_sbox[256];
 
+static inline uint32_t sm4_subword(uint32_t word)
+{
+    return sm4_sbox[word & 0xff] |
+           sm4_sbox[(word >> 8) & 0xff] << 8 |
+           sm4_sbox[(word >> 16) & 0xff] << 16 |
+           sm4_sbox[(word >> 24) & 0xff] << 24;
+}
+
 #endif
diff --git a/target/arm/tcg/crypto_helper.c b/target/arm/tcg/crypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/crypto_helper.c
+++ b/target/arm/tcg/crypto_helper.c
@@ -XXX,XX +XXX,XX @@ static void do_crypto_sm4e(uint64_t *rd, uint64_t *rn, uint64_t *rm)
             CR_ST_WORD(d, (i + 3) % 4) ^
             CR_ST_WORD(n, i);
 
-        t = sm4_sbox[t & 0xff] |
-            sm4_sbox[(t >> 8) & 0xff] << 8 |
-            sm4_sbox[(t >> 16) & 0xff] << 16 |
-            sm4_sbox[(t >> 24) & 0xff] << 24;
+        t = sm4_subword(t);
 
         CR_ST_WORD(d, i) ^= t ^ rol32(t, 2) ^ rol32(t, 10) ^ rol32(t, 18) ^
                             rol32(t, 24);
@@ -XXX,XX +XXX,XX @@ static void do_crypto_sm4ekey(uint64_t *rd, uint64_t *rn, uint64_t *rm)
             CR_ST_WORD(d, (i + 3) % 4) ^
             CR_ST_WORD(m, i);
 
-        t = sm4_sbox[t & 0xff] |
-            sm4_sbox[(t >> 8) & 0xff] << 8 |
-            sm4_sbox[(t >> 16) & 0xff] << 16 |
-            sm4_sbox[(t >> 24) & 0xff] << 24;
+        t = sm4_subword(t);
 
         CR_ST_WORD(d, i) ^= t ^ rol32(t, 13) ^ rol32(t, 23);
     }
-- 
2.41.0

From: Max Chou <max.chou@sifive.com>

Adds sm4_ck constant for use in sm4 cryptography across different targets.

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-15-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 include/crypto/sm4.h |  1 +
 crypto/sm4.c         | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
index XXXXXXX..XXXXXXX 100644
--- a/include/crypto/sm4.h
+++ b/include/crypto/sm4.h
@@ -XXX,XX +XXX,XX @@
 #define QEMU_SM4_H
 
 extern const uint8_t sm4_sbox[256];
+extern const uint32_t sm4_ck[32];
 
 static inline uint32_t sm4_subword(uint32_t word)
 {
diff --git a/crypto/sm4.c b/crypto/sm4.c
index XXXXXXX..XXXXXXX 100644
--- a/crypto/sm4.c
+++ b/crypto/sm4.c
@@ -XXX,XX +XXX,XX @@ uint8_t const sm4_sbox[] = {
     0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48,
 };
 
+uint32_t const sm4_ck[] = {
+    0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269,
+    0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9,
+    0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249,
+    0x50575e65, 0x6c737a81, 0x888f969d, 0xa4abb2b9,
+    0xc0c7ced5, 0xdce3eaf1, 0xf8ff060d, 0x141b2229,
+    0x30373e45, 0x4c535a61, 0x686f767d, 0x848b9299,
+    0xa0a7aeb5, 0xbcc3cad1, 0xd8dfe6ed, 0xf4fb0209,
+    0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279
+};
-- 
2.41.0

From: Max Chou <max.chou@sifive.com>

This commit adds support for the Zvksed vector-crypto extension, which
consists of the following instructions:

* vsm4k.vi
* vsm4r.[vv,vs]

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
[lawrence.hunter@codethink.co.uk: Moved SM4 functions from
crypto_helper.c to vcrypto_helper.c]
[nazar.kazakov@codethink.co.uk: Added alignment checks, refactored code to
use macros, and minor style changes]
Signed-off-by: Max Chou <max.chou@sifive.com>
Message-ID: <20230711165917.2629866-16-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h                   |   1 +
 target/riscv/helper.h                    |   4 +
 target/riscv/insn32.decode               |   5 +
 target/riscv/cpu.c                       |   5 +-
 target/riscv/vcrypto_helper.c            | 127 +++++++++++++++++++++++
 target/riscv/insn_trans/trans_rvvk.c.inc |  43 ++++++++
 6 files changed, 184 insertions(+), 1 deletion(-)

From: Rob Bradford <rbradford@rivosinc.com>

These are WARL fields - zero out the bits for unavailable counters and
special case the TM bit in mcountinhibit which is hardwired to zero.
This patch achieves this by modifying the value written so that any use
of the field will see the correctly masked bits.

Tested by modifying OpenSBI to write max value to these CSRs and upon
subsequent read the appropriate number of bits for number of PMUs is
enabled and the TM bit is zero in mcountinhibit.

Signed-off-by: Rob Bradford <rbradford@rivosinc.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Message-ID: <20230802124906.24197-1-rbradford@rivosinc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/csr.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException write_mcountinhibit(CPURISCVState *env, int csrno,
 {
     int cidx;
     PMUCTRState *counter;
+    RISCVCPU *cpu = env_archcpu(env);
 
-    env->mcountinhibit = val;
+    /* WARL register - disable unavailable counters; TM bit is always 0 */
+    env->mcountinhibit =
+        val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_IR);
 
     /* Check if any other counter is also monitoring cycles/instructions */
     for (cidx = 0; cidx < RV_MAX_MHPMCOUNTERS; cidx++) {
@@ -XXX,XX +XXX,XX @@ static RISCVException read_mcounteren(CPURISCVState *env, int csrno,
 static RISCVException write_mcounteren(CPURISCVState *env, int csrno,
                                        target_ulong val)
 {
-    env->mcounteren = val;
+    RISCVCPU *cpu = env_archcpu(env);
+
+    /* WARL register - disable unavailable counters */
+    env->mcounteren = val & (cpu->pmu_avail_ctrs | COUNTEREN_CY | COUNTEREN_TM |
+                             COUNTEREN_IR);
     return RISCV_EXCP_NONE;
 }
 
-- 
2.41.0

From: Jason Chien <jason.chien@sifive.com>

RVA23 Profiles states:
The RVA23 profiles are intended to be used for 64-bit application
processors that will run rich OS stacks from standard binary OS
distributions and with a substantial number of third-party binary user
applications that will be supported over a considerable length of time
in the field.

The chapter 4 of the unprivileged spec introduces the Zihintntl extension
and Zihintntl is a mandatory extension presented in RVA23 Profiles, whose
purpose is to enable application and operating system portability across
different implementations. Thus the DTS should contain the Zihintntl ISA
string in order to pass to software.

The unprivileged spec states:
Like any HINTs, these instructions may be freely ignored. Hence, although
they are described in terms of cache-based memory hierarchies, they do not
mandate the provision of caches.

These instructions are encoded with non-used opcode, e.g. ADD x0, x0, x2,
which QEMU already supports, and QEMU does not emulate cache. Therefore
these instructions can be considered as a no-op, and we only need to add
a new property for the Zihintntl extension.

Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Jason Chien <jason.chien@sifive.com>
Message-ID: <20230726074049.19505-2-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_cfg.h | 1 +
 target/riscv/cpu.c     | 2 ++
 2 files changed, 3 insertions(+)

From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>

Commit a47842d ("riscv: Add support for the Zfa extension") implemented the zfa extension.
However, it has some typos for fleq.d and fltq.d. Both of them misused the fltq.s
helper function.

Fixes: a47842d ("riscv: Add support for the Zfa extension")
Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Message-ID: <20230728003906.768-1-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/insn_trans/trans_rvzfa.c.inc | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/riscv/insn_trans/trans_rvzfa.c.inc b/target/riscv/insn_trans/trans_rvzfa.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/insn_trans/trans_rvzfa.c.inc
+++ b/target/riscv/insn_trans/trans_rvzfa.c.inc
@@ -XXX,XX +XXX,XX @@ bool trans_fleq_d(DisasContext *ctx, arg_fleq_d *a)
     TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
     TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_fltq_s(dest, cpu_env, src1, src2);
+    gen_helper_fleq_d(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -XXX,XX +XXX,XX @@ bool trans_fltq_d(DisasContext *ctx, arg_fltq_d *a)
     TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
     TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_fltq_s(dest, cpu_env, src1, src2);
+    gen_helper_fltq_d(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
-- 
2.41.0

From: Jason Chien <jason.chien@sifive.com>

When writing the upper mtime, we should keep the original lower mtime
whose value is given by cpu_riscv_read_rtc() instead of
cpu_riscv_read_rtc_raw(). The same logic applies to writes to lower mtime.

Signed-off-by: Jason Chien <jason.chien@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230728082502.26439-1-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/intc/riscv_aclint.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/hw/intc/riscv_aclint.c b/hw/intc/riscv_aclint.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_aclint.c
+++ b/hw/intc/riscv_aclint.c
@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         return;
     } else if (addr == mtimer->time_base || addr == mtimer->time_base + 4) {
         uint64_t rtc_r = cpu_riscv_read_rtc_raw(mtimer->timebase_freq);
+        uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
         if (addr == mtimer->time_base) {
             if (size == 4) {
                 /* time_lo for RV32/RV64 */
-                mtimer->time_delta = ((rtc_r & ~0xFFFFFFFFULL) | value) - rtc_r;
+                mtimer->time_delta = ((rtc & ~0xFFFFFFFFULL) | value) - rtc_r;
             } else {
                 /* time for RV64 */
                 mtimer->time_delta = value - rtc_r;
@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         } else {
             if (size == 4) {
                 /* time_hi for RV32/RV64 */
-                mtimer->time_delta = (value << 32 | (rtc_r & 0xFFFFFFFF)) - rtc_r;
+                mtimer->time_delta = (value << 32 | (rtc & 0xFFFFFFFF)) - rtc_r;
             } else {
                 qemu_log_mask(LOG_GUEST_ERROR,
                               "aclint-mtimer: invalid time_hi write: %08x",
-- 
2.41.0

From: Jason Chien <jason.chien@sifive.com>

The variables whose values are given by cpu_riscv_read_rtc() should be named
"rtc". The variables whose value are given by cpu_riscv_read_rtc_raw()
should be named "rtc_r".

Signed-off-by: Jason Chien <jason.chien@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230728082502.26439-2-jason.chien@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/intc/riscv_aclint.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/hw/intc/riscv_aclint.c b/hw/intc/riscv_aclint.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_aclint.c
+++ b/hw/intc/riscv_aclint.c
@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
     uint64_t next;
     uint64_t diff;
 
-    uint64_t rtc_r = cpu_riscv_read_rtc(mtimer);
+    uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
     /* Compute the relative hartid w.r.t the socket */
     hartid = hartid - mtimer->hartid_base;
 
     mtimer->timecmp[hartid] = value;
-    if (mtimer->timecmp[hartid] <= rtc_r) {
+    if (mtimer->timecmp[hartid] <= rtc) {
         /*
          * If we're setting an MTIMECMP value in the "past",
          * immediately raise the timer interrupt
@@ -XXX,XX +XXX,XX @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
 
     /* otherwise, set up the future timer interrupt */
     qemu_irq_lower(mtimer->timer_irqs[hartid]);
-    diff = mtimer->timecmp[hartid] - rtc_r;
+    diff = mtimer->timecmp[hartid] - rtc;
     /* back to ns (note args switched in muldiv64) */
     uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq);
 
-- 
2.41.0

From: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>

We should not use types dependend on host arch for target_ucontext.
This bug is found when run rv32 applications.

Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20230811055438.1945-1-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 linux-user/riscv/signal.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/linux-user/riscv/signal.c b/linux-user/riscv/signal.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/riscv/signal.c
+++ b/linux-user/riscv/signal.c
@@ -XXX,XX +XXX,XX @@ struct target_sigcontext {
 }; /* cf. riscv-linux:arch/riscv/include/uapi/asm/ptrace.h */
 
 struct target_ucontext {
-    unsigned long uc_flags;
-    struct target_ucontext *uc_link;
+    abi_ulong uc_flags;
+    abi_ptr uc_link;
     target_stack_t uc_stack;
     target_sigset_t uc_sigmask;
     uint8_t   __unused[1024 / 8 - sizeof(target_sigset_t)];
-- 
2.41.0

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

In this patch, we create the APLIC and IMSIC FDT helper functions and
remove M mode AIA devices when using KVM acceleration.

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Jim Shu <jim.shu@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230727102439.22554-2-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/riscv/virt.c | 290 +++++++++++++++++++++++-------------------------
 1 file changed, 137 insertions(+), 153 deletions(-)

diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -XXX,XX +XXX,XX @@ static uint32_t imsic_num_bits(uint32_t count)
     return ret;
 }
 
-static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
-                             uint32_t *phandle, uint32_t *intc_phandles,
-                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
+static void create_fdt_one_imsic(RISCVVirtState *s, hwaddr base_addr,
+                                 uint32_t *intc_phandles, uint32_t msi_phandle,
+                                 bool m_mode, uint32_t imsic_guest_bits)
 {
     int cpu, socket;
     char *imsic_name;
     MachineState *ms = MACHINE(s);
     int socket_count = riscv_socket_count(ms);
-    uint32_t imsic_max_hart_per_socket, imsic_guest_bits;
+    uint32_t imsic_max_hart_per_socket;
     uint32_t *imsic_cells, *imsic_regs, imsic_addr, imsic_size;
 
-    *msi_m_phandle = (*phandle)++;
-    *msi_s_phandle = (*phandle)++;
     imsic_cells = g_new0(uint32_t, ms->smp.cpus * 2);
     imsic_regs = g_new0(uint32_t, socket_count * 4);
 
-    /* M-level IMSIC node */
     for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
         imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
+        imsic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
     }
-    imsic_max_hart_per_socket = 0;
-    for (socket = 0; socket < socket_count; socket++) {
-        imsic_addr = memmap[VIRT_IMSIC_M].base +
-                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
-        imsic_size = IMSIC_HART_SIZE(0) * s->soc[socket].num_harts;
-        imsic_regs[socket * 4 + 0] = 0;
-        imsic_regs[socket * 4 + 1] = cpu_to_be32(imsic_addr);
-        imsic_regs[socket * 4 + 2] = 0;
-        imsic_regs[socket * 4 + 3] = cpu_to_be32(imsic_size);
-        if (imsic_max_hart_per_socket < s->soc[socket].num_harts) {
-            imsic_max_hart_per_socket = s->soc[socket].num_harts;
-        }
-    }
-    imsic_name = g_strdup_printf("/soc/imsics@%lx",
-        (unsigned long)memmap[VIRT_IMSIC_M].base);
-    qemu_fdt_add_subnode(ms->fdt, imsic_name);
-    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
-        "riscv,imsics");
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
-        FDT_IMSIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
-        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
-        socket_count * sizeof(uint32_t) * 4);
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
-        VIRT_IRQCHIP_NUM_MSIS);
-    if (socket_count > 1) {
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
-            imsic_num_bits(imsic_max_hart_per_socket));
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
-            imsic_num_bits(socket_count));
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
-            IMSIC_MMIO_GROUP_MIN_SHIFT);
-    }
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_m_phandle);
-
-    g_free(imsic_name);
 
-    /* S-level IMSIC node */
-    for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
-        imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
-    }
-    imsic_guest_bits = imsic_num_bits(s->aia_guests + 1);
     imsic_max_hart_per_socket = 0;
     for (socket = 0; socket < socket_count; socket++) {
-        imsic_addr = memmap[VIRT_IMSIC_S].base +
-                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
+        imsic_addr = base_addr + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
         imsic_size = IMSIC_HART_SIZE(imsic_guest_bits) *
                      s->soc[socket].num_harts;
         imsic_regs[socket * 4 + 0] = 0;
@@ -XXX,XX +XXX,XX @@ static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
             imsic_max_hart_per_socket = s->soc[socket].num_harts;
         }
     }
-    imsic_name = g_strdup_printf("/soc/imsics@%lx",
-        (unsigned long)memmap[VIRT_IMSIC_S].base);
+
+    imsic_name = g_strdup_printf("/soc/imsics@%lx", (unsigned long)base_addr);
     qemu_fdt_add_subnode(ms->fdt, imsic_name);
-    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
-        "riscv,imsics");
+    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible", "riscv,imsics");
     qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
-        FDT_IMSIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
-        NULL, 0);
+                          FDT_IMSIC_INT_CELLS);
+    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller", NULL, 0);
+    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller", NULL, 0);
     qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
-        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
+                     imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
     qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
-        socket_count * sizeof(uint32_t) * 4);
+                     socket_count * sizeof(uint32_t) * 4);
     qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
-        VIRT_IRQCHIP_NUM_MSIS);
+                     VIRT_IRQCHIP_NUM_MSIS);
+
     if (imsic_guest_bits) {
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,guest-index-bits",
-            imsic_guest_bits);
+                              imsic_guest_bits);
     }
+
     if (socket_count > 1) {
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
-            imsic_num_bits(imsic_max_hart_per_socket));
+                              imsic_num_bits(imsic_max_hart_per_socket));
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
-            imsic_num_bits(socket_count));
+                              imsic_num_bits(socket_count));
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
-            IMSIC_MMIO_GROUP_MIN_SHIFT);
+                              IMSIC_MMIO_GROUP_MIN_SHIFT);
     }
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_s_phandle);
-    g_free(imsic_name);
+    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", msi_phandle);
 
+    g_free(imsic_name);
     g_free(imsic_regs);
     g_free(imsic_cells);
 }
 
-static void create_fdt_socket_aplic(RISCVVirtState *s,
-                                    const MemMapEntry *memmap, int socket,
-                                    uint32_t msi_m_phandle,
-                                    uint32_t msi_s_phandle,
-                                    uint32_t *phandle,
-                                    uint32_t *intc_phandles,
-                                    uint32_t *aplic_phandles)
+static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
+                             uint32_t *phandle, uint32_t *intc_phandles,
+                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
+{
+    *msi_m_phandle = (*phandle)++;
+    *msi_s_phandle = (*phandle)++;
+
+    if (!kvm_enabled()) {
+        /* M-level IMSIC node */
+        create_fdt_one_imsic(s, memmap[VIRT_IMSIC_M].base, intc_phandles,
+                             *msi_m_phandle, true, 0);
+    }
+
+    /* S-level IMSIC node */
+    create_fdt_one_imsic(s, memmap[VIRT_IMSIC_S].base, intc_phandles,
+                         *msi_s_phandle, false,
+                         imsic_num_bits(s->aia_guests + 1));
+
+}
+
+static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
+                                 unsigned long aplic_addr, uint32_t aplic_size,
+                                 uint32_t msi_phandle,
+                                 uint32_t *intc_phandles,
+                                 uint32_t aplic_phandle,
+                                 uint32_t aplic_child_phandle,
+                                 bool m_mode)
 {
     int cpu;
     char *aplic_name;
     uint32_t *aplic_cells;
-    unsigned long aplic_addr;
     MachineState *ms = MACHINE(s);
-    uint32_t aplic_m_phandle, aplic_s_phandle;
 
-    aplic_m_phandle = (*phandle)++;
-    aplic_s_phandle = (*phandle)++;
     aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2);
 
-    /* M-level APLIC node */
     for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
         aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
+        aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
     }
-    aplic_addr = memmap[VIRT_APLIC_M].base +
-                 (memmap[VIRT_APLIC_M].size * socket);
+
     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
     qemu_fdt_add_subnode(ms->fdt, aplic_name);
     qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
     qemu_fdt_setprop_cell(ms->fdt, aplic_name,
-        "#interrupt-cells", FDT_APLIC_INT_CELLS);
+                          "#interrupt-cells", FDT_APLIC_INT_CELLS);
     qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
+
     if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
         qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
-            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
+                         aplic_cells,
+                         s->soc[socket].num_harts * sizeof(uint32_t) * 2);
     } else {
-        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
-            msi_m_phandle);
+        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle);
     }
+
     qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
-        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_M].size);
+                           0x0, aplic_addr, 0x0, aplic_size);
     qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
-        VIRT_IRQCHIP_NUM_SOURCES);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
-        aplic_s_phandle);
-    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
-        aplic_s_phandle, 0x1, VIRT_IRQCHIP_NUM_SOURCES);
+                          VIRT_IRQCHIP_NUM_SOURCES);
+
+    if (aplic_child_phandle) {
+        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
+                              aplic_child_phandle);
+        qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
+                               aplic_child_phandle, 0x1,
+                               VIRT_IRQCHIP_NUM_SOURCES);
+    }
+
     riscv_socket_fdt_write_id(ms, aplic_name, socket);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_m_phandle);
+    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_phandle);
+
     g_free(aplic_name);
+    g_free(aplic_cells);
+}
 
-    /* S-level APLIC node */
-    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
-        aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
+static void create_fdt_socket_aplic(RISCVVirtState *s,
+                                    const MemMapEntry *memmap, int socket,
+                                    uint32_t msi_m_phandle,
+                                    uint32_t msi_s_phandle,
+                                    uint32_t *phandle,
+                                    uint32_t *intc_phandles,
+                                    uint32_t *aplic_phandles)
+{
+    char *aplic_name;
+    unsigned long aplic_addr;
+    MachineState *ms = MACHINE(s);
+    uint32_t aplic_m_phandle, aplic_s_phandle;
+
+    aplic_m_phandle = (*phandle)++;
+    aplic_s_phandle = (*phandle)++;
+
+    if (!kvm_enabled()) {
+        /* M-level APLIC node */
+        aplic_addr = memmap[VIRT_APLIC_M].base +
+                     (memmap[VIRT_APLIC_M].size * socket);
+        create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size,
+                             msi_m_phandle, intc_phandles,
+                             aplic_m_phandle, aplic_s_phandle,
+                             true);
     }
+
+    /* S-level APLIC node */
     aplic_addr = memmap[VIRT_APLIC_S].base +
                  (memmap[VIRT_APLIC_S].size * socket);
+    create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size,
+                         msi_s_phandle, intc_phandles,
+                         aplic_s_phandle, 0,
+                         false);
+
     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
-    qemu_fdt_add_subnode(ms->fdt, aplic_name);
-    qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name,
-        "#interrupt-cells", FDT_APLIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
-    if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
-        qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
-            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
-    } else {
-        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
-            msi_s_phandle);
-    }
-    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
-        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_S].size);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
-        VIRT_IRQCHIP_NUM_SOURCES);
-    riscv_socket_fdt_write_id(ms, aplic_name, socket);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_s_phandle);
 
     if (!socket) {
         platform_bus_add_all_fdt_nodes(ms->fdt, aplic_name,
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
 
     g_free(aplic_name);
 
-    g_free(aplic_cells);
     aplic_phandles[socket] = aplic_s_phandle;
 }
 
@@ -XXX,XX +XXX,XX @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
     int i;
     hwaddr addr;
     uint32_t guest_bits;
-    DeviceState *aplic_m;
-    bool msimode = (aia_type == VIRT_AIA_TYPE_APLIC_IMSIC) ? true : false;
+    DeviceState *aplic_s = NULL;
+    DeviceState *aplic_m = NULL;
+    bool msimode = aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
 
     if (msimode) {
-        /* Per-socket M-level IMSICs */
-        addr = memmap[VIRT_IMSIC_M].base + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
-        for (i = 0; i < hart_count; i++) {
-            riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
-                               base_hartid + i, true, 1,
-                               VIRT_IRQCHIP_NUM_MSIS);
+        if (!kvm_enabled()) {
+            /* Per-socket M-level IMSICs */
+            addr = memmap[VIRT_IMSIC_M].base +
+                   socket * VIRT_IMSIC_GROUP_MAX_SIZE;
+            for (i = 0; i < hart_count; i++) {
+                riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
+                                   base_hartid + i, true, 1,
+                                   VIRT_IRQCHIP_NUM_MSIS);
+            }
         }
 
         /* Per-socket S-level IMSICs */
@@ -XXX,XX +XXX,XX @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
         }
     }
 
-    /* Per-socket M-level APLIC */
-    aplic_m = riscv_aplic_create(
-        memmap[VIRT_APLIC_M].base + socket * memmap[VIRT_APLIC_M].size,
-        memmap[VIRT_APLIC_M].size,
-        (msimode) ? 0 : base_hartid,
-        (msimode) ? 0 : hart_count,
-        VIRT_IRQCHIP_NUM_SOURCES,
-        VIRT_IRQCHIP_NUM_PRIO_BITS,
-        msimode, true, NULL);
-
-    if (aplic_m) {
-        /* Per-socket S-level APLIC */
-        riscv_aplic_create(
-            memmap[VIRT_APLIC_S].base + socket * memmap[VIRT_APLIC_S].size,
-            memmap[VIRT_APLIC_S].size,
-            (msimode) ? 0 : base_hartid,
-            (msimode) ? 0 : hart_count,
-            VIRT_IRQCHIP_NUM_SOURCES,
-            VIRT_IRQCHIP_NUM_PRIO_BITS,
-            msimode, false, aplic_m);
+    if (!kvm_enabled()) {
+        /* Per-socket M-level APLIC */
+        aplic_m = riscv_aplic_create(memmap[VIRT_APLIC_M].base +
+                                     socket * memmap[VIRT_APLIC_M].size,
+                                     memmap[VIRT_APLIC_M].size,
+                                     (msimode) ? 0 : base_hartid,
+                                     (msimode) ? 0 : hart_count,
+                                     VIRT_IRQCHIP_NUM_SOURCES,
+                                     VIRT_IRQCHIP_NUM_PRIO_BITS,
+                                     msimode, true, NULL);
     }
 
-    return aplic_m;
+    /* Per-socket S-level APLIC */
+    aplic_s = riscv_aplic_create(memmap[VIRT_APLIC_S].base +
+                                 socket * memmap[VIRT_APLIC_S].size,
+                                 memmap[VIRT_APLIC_S].size,
+                                 (msimode) ? 0 : base_hartid,
+                                 (msimode) ? 0 : hart_count,
+                                 VIRT_IRQCHIP_NUM_SOURCES,
+                                 VIRT_IRQCHIP_NUM_PRIO_BITS,
+                                 msimode, false, aplic_m);
+
+    return kvm_enabled() ? aplic_s : aplic_m;
 }
 
 static void create_platform_bus(RISCVVirtState *s, DeviceState *irqchip)
-- 
2.41.0

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

We check the in-kernel irqchip support when using KVM acceleration.

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Jim Shu <jim.shu@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230727102439.22554-3-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/kvm.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm.c
+++ b/target/riscv/kvm.c
@@ -XXX,XX +XXX,XX @@ int kvm_arch_init(MachineState *ms, KVMState *s)
 
 int kvm_arch_irqchip_create(KVMState *s)
 {
-    return 0;
+    if (kvm_kernel_irqchip_split()) {
+        error_report("-machine kernel_irqchip=split is not supported on RISC-V.");
+        exit(1);
+    }
+
+    /*
+     * We can create the VAIA using the newer device control API.
+     */
+    return kvm_check_extension(s, KVM_CAP_DEVICE_CTRL);
 }
 
 int kvm_arch_process_async_events(CPUState *cs)
-- 
2.41.0

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

We create a vAIA chip by using the KVM_DEV_TYPE_RISCV_AIA and then set up
the chip with the KVM_DEV_RISCV_AIA_GRP_* APIs.
We also extend KVM accelerator to specify the KVM AIA mode. The "riscv-aia"
parameter is passed along with --accel in QEMU command-line.
1) "riscv-aia=emul": IMSIC is emulated by hypervisor
2) "riscv-aia=hwaccel": use hardware guest IMSIC
3) "riscv-aia=auto": use the hardware guest IMSICs whenever available
                     otherwise we fallback to software emulation.

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Jim Shu <jim.shu@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230727102439.22554-4-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/kvm_riscv.h |   4 +
 target/riscv/kvm.c       | 186 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 190 insertions(+)

diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm_riscv.h
+++ b/target/riscv/kvm_riscv.h
@@ -XXX,XX +XXX,XX @@
 void kvm_riscv_init_user_properties(Object *cpu_obj);
 void kvm_riscv_reset_vcpu(RISCVCPU *cpu);
 void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level);
+void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
+                          uint64_t aia_irq_num, uint64_t aia_msi_num,
+                          uint64_t aplic_base, uint64_t imsic_base,
+                          uint64_t guest_num);
 
 #endif
diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm.c
+++ b/target/riscv/kvm.c
@@ -XXX,XX +XXX,XX @@
 #include "exec/address-spaces.h"
 #include "hw/boards.h"
 #include "hw/irq.h"
+#include "hw/intc/riscv_imsic.h"
 #include "qemu/log.h"
 #include "hw/loader.h"
 #include "kvm_riscv.h"
@@ -XXX,XX +XXX,XX @@
 #include "chardev/char-fe.h"
 #include "migration/migration.h"
 #include "sysemu/runstate.h"
+#include "hw/riscv/numa.h"
 
 static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type,
                                  uint64_t idx)
@@ -XXX,XX +XXX,XX @@ bool kvm_arch_cpu_check_are_resettable(void)
     return true;
 }
 
+static int aia_mode;
+
+static const char *kvm_aia_mode_str(uint64_t mode)
+{
+    switch (mode) {
+    case KVM_DEV_RISCV_AIA_MODE_EMUL:
+        return "emul";
+    case KVM_DEV_RISCV_AIA_MODE_HWACCEL:
+        return "hwaccel";
+    case KVM_DEV_RISCV_AIA_MODE_AUTO:
+    default:
+        return "auto";
+    };
+}
+
+static char *riscv_get_kvm_aia(Object *obj, Error **errp)
+{
+    return g_strdup(kvm_aia_mode_str(aia_mode));
+}
+
+static void riscv_set_kvm_aia(Object *obj, const char *val, Error **errp)
+{
+    if (!strcmp(val, "emul")) {
+        aia_mode = KVM_DEV_RISCV_AIA_MODE_EMUL;
+    } else if (!strcmp(val, "hwaccel")) {
+        aia_mode = KVM_DEV_RISCV_AIA_MODE_HWACCEL;
+    } else if (!strcmp(val, "auto")) {
+        aia_mode = KVM_DEV_RISCV_AIA_MODE_AUTO;
+    } else {
+        error_setg(errp, "Invalid KVM AIA mode");
+        error_append_hint(errp, "Valid values are emul, hwaccel, and auto.\n");
+    }
+}
+
 void kvm_arch_accel_class_init(ObjectClass *oc)
 {
+    object_class_property_add_str(oc, "riscv-aia", riscv_get_kvm_aia,
+                                  riscv_set_kvm_aia);
+    object_class_property_set_description(oc, "riscv-aia",
+                                          "Set KVM AIA mode. Valid values are "
+                                          "emul, hwaccel, and auto. Default "
+                                          "is auto.");
+    object_property_set_default_str(object_class_property_find(oc, "riscv-aia"),
+                                    "auto");
+}
+
+void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
+                          uint64_t aia_irq_num, uint64_t aia_msi_num,
+                          uint64_t aplic_base, uint64_t imsic_base,
+                          uint64_t guest_num)
+{
+    int ret, i;
+    int aia_fd = -1;
+    uint64_t default_aia_mode;
+    uint64_t socket_count = riscv_socket_count(machine);
+    uint64_t max_hart_per_socket = 0;
+    uint64_t socket, base_hart, hart_count, socket_imsic_base, imsic_addr;
+    uint64_t socket_bits, hart_bits, guest_bits;
+
+    aia_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_RISCV_AIA, false);
+
+    if (aia_fd < 0) {
+        error_report("Unable to create in-kernel irqchip");
+        exit(1);
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_MODE,
+                            &default_aia_mode, false, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to get current KVM AIA mode");
+        exit(1);
+    }
+    qemu_log("KVM AIA: default mode is %s\n",
+             kvm_aia_mode_str(default_aia_mode));
+
+    if (default_aia_mode != aia_mode) {
+        ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                                KVM_DEV_RISCV_AIA_CONFIG_MODE,
+                                &aia_mode, true, NULL);
+        if (ret < 0)
+            warn_report("KVM AIA: failed to set KVM AIA mode");
+        else
+            qemu_log("KVM AIA: set current mode to %s\n",
+                     kvm_aia_mode_str(aia_mode));
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_SRCS,
+                            &aia_irq_num, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set number of input irq lines");
+        exit(1);
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_IDS,
+                            &aia_msi_num, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set number of msi");
+        exit(1);
+    }
+
+    socket_bits = find_last_bit(&socket_count, BITS_PER_LONG) + 1;
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS,
+                            &socket_bits, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set group_bits");
+        exit(1);
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT,
+                            &group_shift, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set group_shift");
+        exit(1);
+    }
+
+    guest_bits = guest_num == 0 ? 0 :
+                 find_last_bit(&guest_num, BITS_PER_LONG) + 1;
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS,
+                            &guest_bits, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set guest_bits");
+        exit(1);
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR,
+                            KVM_DEV_RISCV_AIA_ADDR_APLIC,
+                            &aplic_base, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set the base address of APLIC");
+        exit(1);
+    }
+
+    for (socket = 0; socket < socket_count; socket++) {
+        socket_imsic_base = imsic_base + socket * (1U << group_shift);
+        hart_count = riscv_socket_hart_count(machine, socket);
+        base_hart = riscv_socket_first_hartid(machine, socket);
+
+        if (max_hart_per_socket < hart_count) {
+            max_hart_per_socket = hart_count;
+        }
+
+        for (i = 0; i < hart_count; i++) {
+            imsic_addr = socket_imsic_base + i * IMSIC_HART_SIZE(guest_bits);
+            ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_ADDR,
+                                    KVM_DEV_RISCV_AIA_ADDR_IMSIC(i + base_hart),
+                                    &imsic_addr, true, NULL);
+            if (ret < 0) {
+                error_report("KVM AIA: failed to set the IMSIC address for hart %d", i);
+                exit(1);
+            }
+        }
+    }
+
+    hart_bits = find_last_bit(&max_hart_per_socket, BITS_PER_LONG) + 1;
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CONFIG,
+                            KVM_DEV_RISCV_AIA_CONFIG_HART_BITS,
+                            &hart_bits, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: failed to set hart_bits");
+        exit(1);
+    }
+
+    if (kvm_has_gsi_routing()) {
+        for (uint64_t idx = 0; idx < aia_irq_num + 1; ++idx) {
+            /* KVM AIA only has one APLIC instance */
+            kvm_irqchip_add_irq_route(kvm_state, idx, 0, idx);
+        }
+        kvm_gsi_routing_allowed = true;
+        kvm_irqchip_commit_routes(kvm_state);
+    }
+
+    ret = kvm_device_access(aia_fd, KVM_DEV_RISCV_AIA_GRP_CTRL,
+                            KVM_DEV_RISCV_AIA_CTRL_INIT,
+                            NULL, true, NULL);
+    if (ret < 0) {
+        error_report("KVM AIA: initialized fail");
+        exit(1);
+    }
+
+    kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled();
 }
-- 
2.41.0

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

KVM AIA can't emulate APLIC only. When "aia=aplic" parameter is passed,
APLIC devices is emulated by QEMU. For "aia=aplic-imsic", remove the
mmio operations of APLIC when using KVM AIA and send wired interrupt
signal via KVM_IRQ_LINE API.
After KVM AIA enabled, MSI messages are delivered by KVM_SIGNAL_MSI API
when the IMSICs receive mmio write requests.

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Jim Shu <jim.shu@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230727102439.22554-5-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/intc/riscv_aplic.c | 56 ++++++++++++++++++++++++++++++-------------
 hw/intc/riscv_imsic.c | 25 +++++++++++++++----
 2 files changed, 61 insertions(+), 20 deletions(-)

diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_aplic.c
+++ b/hw/intc/riscv_aplic.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/irq.h"
 #include "target/riscv/cpu.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/kvm.h"
 #include "migration/vmstate.h"
 
 #define APLIC_MAX_IDC                  (1UL << 14)
@@ -XXX,XX +XXX,XX @@
 
 #define APLIC_IDC_CLAIMI               0x1c
 
+/*
+ * KVM AIA only supports APLIC MSI, fallback to QEMU emulation if we want to use
+ * APLIC Wired.
+ */
+static bool is_kvm_aia(bool msimode)
+{
+    return kvm_irqchip_in_kernel() && msimode;
+}
+
 static uint32_t riscv_aplic_read_input_word(RISCVAPLICState *aplic,
                                             uint32_t word)
 {
@@ -XXX,XX +XXX,XX @@ static uint32_t riscv_aplic_idc_claimi(RISCVAPLICState *aplic, uint32_t idc)
     return topi;
 }
 
+static void riscv_kvm_aplic_request(void *opaque, int irq, int level)
+{
+    kvm_set_irq(kvm_state, irq, !!level);
+}
+
 static void riscv_aplic_request(void *opaque, int irq, int level)
 {
     bool update = false;
@@ -XXX,XX +XXX,XX @@ static void riscv_aplic_realize(DeviceState *dev, Error **errp)
     uint32_t i;
     RISCVAPLICState *aplic = RISCV_APLIC(dev);
 
-    aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
-    aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
-    aplic->state = g_new0(uint32_t, aplic->num_irqs);
-    aplic->target = g_new0(uint32_t, aplic->num_irqs);
-    if (!aplic->msimode) {
-        for (i = 0; i < aplic->num_irqs; i++) {
-            aplic->target[i] = 1;
+    if (!is_kvm_aia(aplic->msimode)) {
+        aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
+        aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
+        aplic->state = g_new0(uint32_t, aplic->num_irqs);
+        aplic->target = g_new0(uint32_t, aplic->num_irqs);
+        if (!aplic->msimode) {
+            for (i = 0; i < aplic->num_irqs; i++) {
+                aplic->target[i] = 1;
+            }
         }
-    }
-    aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
-    aplic->iforce = g_new0(uint32_t, aplic->num_harts);
-    aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
+        aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
+        aplic->iforce = g_new0(uint32_t, aplic->num_harts);
+        aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
 
-    memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops, aplic,
-                          TYPE_RISCV_APLIC, aplic->aperture_size);
-    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
+        memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops,
+                              aplic, TYPE_RISCV_APLIC, aplic->aperture_size);
+        sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
+    }
 
     /*
      * Only root APLICs have hardware IRQ lines. All non-root APLICs
      * have IRQ lines delegated by their parent APLIC.
      */
     if (!aplic->parent) {
-        qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
+        if (is_kvm_aia(aplic->msimode)) {
+            qdev_init_gpio_in(dev, riscv_kvm_aplic_request, aplic->num_irqs);
+        } else {
+            qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
+        }
     }
 
     /* Create output IRQ lines for non-MSI mode */
@@ -XXX,XX +XXX,XX @@ DeviceState *riscv_aplic_create(hwaddr addr, hwaddr size,
     qdev_prop_set_bit(dev, "mmode", mmode);
 
     sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
+
+    if (!is_kvm_aia(msimode)) {
+        sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
+    }
 
     if (parent) {
         riscv_aplic_add_child(parent, dev);
diff --git a/hw/intc/riscv_imsic.c b/hw/intc/riscv_imsic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_imsic.c
+++ b/hw/intc/riscv_imsic.c
@@ -XXX,XX +XXX,XX @@
 #include "target/riscv/cpu.h"
 #include "target/riscv/cpu_bits.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/kvm.h"
 #include "migration/vmstate.h"
 
 #define IMSIC_MMIO_PAGE_LE             0x00
@@ -XXX,XX +XXX,XX @@ static void riscv_imsic_write(void *opaque, hwaddr addr, uint64_t value,
         goto err;
     }
 
+#if defined(CONFIG_KVM)
+    if (kvm_irqchip_in_kernel()) {
+        struct kvm_msi msi;
+
+        msi.address_lo = extract64(imsic->mmio.addr + addr, 0, 32);
+        msi.address_hi = extract64(imsic->mmio.addr + addr, 32, 32);
+        msi.data = le32_to_cpu(value);
+
+        kvm_vm_ioctl(kvm_state, KVM_SIGNAL_MSI, &msi);
+
+        return;
+    }
+#endif
+
     /* Writes only supported for MSI little-endian registers */
     page = addr >> IMSIC_MMIO_PAGE_SHIFT;
     if ((addr & (IMSIC_MMIO_PAGE_SZ - 1)) == IMSIC_MMIO_PAGE_LE) {
@@ -XXX,XX +XXX,XX @@ static void riscv_imsic_realize(DeviceState *dev, Error **errp)
     CPUState *cpu = cpu_by_arch_id(imsic->hartid);
     CPURISCVState *env = cpu ? cpu->env_ptr : NULL;
 
-    imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
-    imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
-    imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
-    imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
+    if (!kvm_irqchip_in_kernel()) {
+        imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
+        imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
+        imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
+        imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
+    }
 
     memory_region_init_io(&imsic->mmio, OBJECT(dev), &riscv_imsic_ops,
                           imsic, TYPE_RISCV_IMSIC,
-- 
2.41.0

From: Yong-Xuan Wang <yongxuan.wang@sifive.com>

Select KVM AIA when the host kernel has in-kernel AIA chip support.
Since KVM AIA only has one APLIC instance, we map the QEMU APLIC
devices to KVM APLIC.

Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Jim Shu <jim.shu@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230727102439.22554-6-yongxuan.wang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/riscv/virt.c | 94 +++++++++++++++++++++++++++++++++----------------
 1 file changed, 63 insertions(+), 31 deletions(-)

diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/riscv/virt.h"
 #include "hw/riscv/boot.h"
 #include "hw/riscv/numa.h"
+#include "kvm_riscv.h"
 #include "hw/intc/riscv_aclint.h"
 #include "hw/intc/riscv_aplic.h"
 #include "hw/intc/riscv_imsic.h"
@@ -XXX,XX +XXX,XX @@
 #error "Can't accommodate all IMSIC groups in address space"
 #endif
 
+/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */
+static bool virt_use_kvm_aia(RISCVVirtState *s)
+{
+    return kvm_irqchip_in_kernel() && s->aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
+}
+
 static const MemMapEntry virt_memmap[] = {
     [VIRT_DEBUG] =        {        0x0,         0x100 },
     [VIRT_MROM] =         {     0x1000,        0xf000 },
@@ -XXX,XX +XXX,XX @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
                                  uint32_t *intc_phandles,
                                  uint32_t aplic_phandle,
                                  uint32_t aplic_child_phandle,
-                                 bool m_mode)
+                                 bool m_mode, int num_harts)
 {
     int cpu;
     char *aplic_name;
     uint32_t *aplic_cells;
     MachineState *ms = MACHINE(s);
 
-    aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2);
+    aplic_cells = g_new0(uint32_t, num_harts * 2);
 
-    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
+    for (cpu = 0; cpu < num_harts; cpu++) {
         aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
         aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
     }
@@ -XXX,XX +XXX,XX @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
 
     if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
         qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
-                         aplic_cells,
-                         s->soc[socket].num_harts * sizeof(uint32_t) * 2);
+                         aplic_cells, num_harts * sizeof(uint32_t) * 2);
     } else {
         qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle);
     }
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
                                     uint32_t msi_s_phandle,
                                     uint32_t *phandle,
                                     uint32_t *intc_phandles,
-                                    uint32_t *aplic_phandles)
+                                    uint32_t *aplic_phandles,
+                                    int num_harts)
 {
     char *aplic_name;
     unsigned long aplic_addr;
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
         create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size,
                              msi_m_phandle, intc_phandles,
                              aplic_m_phandle, aplic_s_phandle,
-                             true);
+                             true, num_harts);
     }
 
     /* S-level APLIC node */
@@ -XXX,XX +XXX,XX @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
     create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size,
                          msi_s_phandle, intc_phandles,
                          aplic_s_phandle, 0,
-                         false);
+                         false, num_harts);
 
     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
 
@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
         *msi_pcie_phandle = msi_s_phandle;
     }
 
-    phandle_pos = ms->smp.cpus;
-    for (socket = (socket_count - 1); socket >= 0; socket--) {
-        phandle_pos -= s->soc[socket].num_harts;
-
-        if (s->aia_type == VIRT_AIA_TYPE_NONE) {
-            create_fdt_socket_plic(s, memmap, socket, phandle,
-                &intc_phandles[phandle_pos], xplic_phandles);
-        } else {
-            create_fdt_socket_aplic(s, memmap, socket,
-                msi_m_phandle, msi_s_phandle, phandle,
-                &intc_phandles[phandle_pos], xplic_phandles);
+    /* KVM AIA only has one APLIC instance */
+    if (virt_use_kvm_aia(s)) {
+        create_fdt_socket_aplic(s, memmap, 0,
+                                msi_m_phandle, msi_s_phandle, phandle,
+                                &intc_phandles[0], xplic_phandles,
+                                ms->smp.cpus);
+    } else {
+        phandle_pos = ms->smp.cpus;
+        for (socket = (socket_count - 1); socket >= 0; socket--) {
+            phandle_pos -= s->soc[socket].num_harts;
+
+            if (s->aia_type == VIRT_AIA_TYPE_NONE) {
+                create_fdt_socket_plic(s, memmap, socket, phandle,
+                                       &intc_phandles[phandle_pos],
+                                       xplic_phandles);
+            } else {
+                create_fdt_socket_aplic(s, memmap, socket,
+                                        msi_m_phandle, msi_s_phandle, phandle,
+                                        &intc_phandles[phandle_pos],
+                                        xplic_phandles,
+                                        s->soc[socket].num_harts);
+            }
         }
     }
 
     g_free(intc_phandles);
 
-    for (socket = 0; socket < socket_count; socket++) {
-        if (socket == 0) {
-            *irq_mmio_phandle = xplic_phandles[socket];
-            *irq_virtio_phandle = xplic_phandles[socket];
-            *irq_pcie_phandle = xplic_phandles[socket];
-        }
-        if (socket == 1) {
-            *irq_virtio_phandle = xplic_phandles[socket];
-            *irq_pcie_phandle = xplic_phandles[socket];
-        }
-        if (socket == 2) {
-            *irq_pcie_phandle = xplic_phandles[socket];
+    if (virt_use_kvm_aia(s)) {
+        *irq_mmio_phandle = xplic_phandles[0];
+        *irq_virtio_phandle = xplic_phandles[0];
+        *irq_pcie_phandle = xplic_phandles[0];
+    } else {
+        for (socket = 0; socket < socket_count; socket++) {
+            if (socket == 0) {
+                *irq_mmio_phandle = xplic_phandles[socket];
+                *irq_virtio_phandle = xplic_phandles[socket];
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
+            if (socket == 1) {
+                *irq_virtio_phandle = xplic_phandles[socket];
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
+            if (socket == 2) {
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
         }
     }
 
@@ -XXX,XX +XXX,XX @@ static void virt_machine_init(MachineState *machine)
         }
     }
 
+    if (virt_use_kvm_aia(s)) {
+        kvm_riscv_aia_create(machine, IMSIC_MMIO_GROUP_MIN_SHIFT,
+                             VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS,
+                             memmap[VIRT_APLIC_S].base,
+                             memmap[VIRT_IMSIC_S].base,
+                             s->aia_guests);
+    }
+
     if (riscv_is_32bit(&s->soc[0])) {
 #if HOST_LONG_BITS == 64
         /* limit RAM size in a 32-bit system */
-- 
2.41.0

From: Conor Dooley <conor.dooley@microchip.com>

On a dtb dumped from the virt machine, dt-validate complains:
soc: pmu: {'riscv,event-to-mhpmcounters': [[1, 1, 524281], [2, 2, 524284], [65561, 65561, 524280], [65563, 65563, 524280], [65569, 65569, 524280]], 'compatible': ['riscv,pmu']} should not be valid under {'type': 'object'}
        from schema $id: http://devicetree.org/schemas/simple-bus.yaml#
That's pretty cryptic, but running the dtb back through dtc produces
something a lot more reasonable:
Warning (simple_bus_reg): /soc/pmu: missing or empty reg/ranges property

Moving the riscv,pmu node out of the soc bus solves the problem.

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <20230727-groom-decline-2c57ce42841c@spud>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/riscv/virt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -XXX,XX +XXX,XX @@ static void create_fdt_pmu(RISCVVirtState *s)
     MachineState *ms = MACHINE(s);
     RISCVCPU hart = s->soc[0].harts[0];
 
-    pmu_name = g_strdup_printf("/soc/pmu");
+    pmu_name = g_strdup_printf("/pmu");
     qemu_fdt_add_subnode(ms->fdt, pmu_name);
     qemu_fdt_setprop_string(ms->fdt, pmu_name, "compatible", "riscv,pmu");
     riscv_pmu_generate_fdt_node(ms->fdt, hart.cfg.pmu_num, pmu_name);
-- 
2.41.0

From: Weiwei Li <liweiwei@iscas.ac.cn>

The Svadu specification updated the name of the *envcfg bit from
HADE to ADUE.

Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Junqiang Wang <wangjunqiang@iscas.ac.cn>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Message-ID: <20230816141916.66898-1-liweiwei@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu_bits.h   |  8 ++++----
 target/riscv/cpu.c        |  4 ++--
 target/riscv/cpu_helper.c |  6 +++---
 target/riscv/csr.c        | 12 ++++++------
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_bits.h
+++ b/target/riscv/cpu_bits.h
@@ -XXX,XX +XXX,XX @@ typedef enum RISCVException {
 #define MENVCFG_CBIE                       (3UL << 4)
 #define MENVCFG_CBCFE                      BIT(6)
 #define MENVCFG_CBZE                       BIT(7)
-#define MENVCFG_HADE                       (1ULL << 61)
+#define MENVCFG_ADUE                       (1ULL << 61)
 #define MENVCFG_PBMTE                      (1ULL << 62)
 #define MENVCFG_STCE                       (1ULL << 63)
 
 /* For RV32 */
-#define MENVCFGH_HADE                      BIT(29)
+#define MENVCFGH_ADUE                      BIT(29)
 #define MENVCFGH_PBMTE                     BIT(30)
 #define MENVCFGH_STCE                      BIT(31)
 
@@ -XXX,XX +XXX,XX @@ typedef enum RISCVException {
 #define HENVCFG_CBIE                       MENVCFG_CBIE
 #define HENVCFG_CBCFE                      MENVCFG_CBCFE
 #define HENVCFG_CBZE                       MENVCFG_CBZE
-#define HENVCFG_HADE                       MENVCFG_HADE
+#define HENVCFG_ADUE                       MENVCFG_ADUE
 #define HENVCFG_PBMTE                      MENVCFG_PBMTE
 #define HENVCFG_STCE                       MENVCFG_STCE
 
 /* For RV32 */
-#define HENVCFGH_HADE                       MENVCFGH_HADE
+#define HENVCFGH_ADUE                       MENVCFGH_ADUE
 #define HENVCFGH_PBMTE                      MENVCFGH_PBMTE
 #define HENVCFGH_STCE                       MENVCFGH_STCE
 
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj)
     env->two_stage_lookup = false;
 
     env->menvcfg = (cpu->cfg.ext_svpbmt ? MENVCFG_PBMTE : 0) |
-                   (cpu->cfg.ext_svadu ? MENVCFG_HADE : 0);
+                   (cpu->cfg.ext_svadu ? MENVCFG_ADUE : 0);
     env->henvcfg = (cpu->cfg.ext_svpbmt ? HENVCFG_PBMTE : 0) |
-                   (cpu->cfg.ext_svadu ? HENVCFG_HADE : 0);
+                   (cpu->cfg.ext_svadu ? HENVCFG_ADUE : 0);
 
     /* Initialized default priorities of local interrupts. */
     for (i = 0; i < ARRAY_SIZE(env->miprio); i++) {
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -XXX,XX +XXX,XX @@ static int get_physical_address(CPURISCVState *env, hwaddr *physical,
     }
 
     bool pbmte = env->menvcfg & MENVCFG_PBMTE;
-    bool hade = env->menvcfg & MENVCFG_HADE;
+    bool adue = env->menvcfg & MENVCFG_ADUE;
 
     if (first_stage && two_stage && env->virt_enabled) {
         pbmte = pbmte && (env->henvcfg & HENVCFG_PBMTE);
-        hade = hade && (env->henvcfg & HENVCFG_HADE);
+        adue = adue && (env->henvcfg & HENVCFG_ADUE);
     }
 
     int ptshift = (levels - 1) * ptidxbits;
@@ -XXX,XX +XXX,XX @@ restart:
 
     /* Page table updates need to be atomic with MTTCG enabled */
     if (updated_pte != pte && !is_debug) {
-        if (!hade) {
+        if (!adue) {
             return TRANSLATE_FAIL;
         }
 
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException write_menvcfg(CPURISCVState *env, int csrno,
     if (riscv_cpu_mxl(env) == MXL_RV64) {
         mask |= (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) |
                 (cfg->ext_sstc ? MENVCFG_STCE : 0) |
-                (cfg->ext_svadu ? MENVCFG_HADE : 0);
+                (cfg->ext_svadu ? MENVCFG_ADUE : 0);
     }
     env->menvcfg = (env->menvcfg & ~mask) | (val & mask);
 
@@ -XXX,XX +XXX,XX @@ static RISCVException write_menvcfgh(CPURISCVState *env, int csrno,
     const RISCVCPUConfig *cfg = riscv_cpu_cfg(env);
     uint64_t mask = (cfg->ext_svpbmt ? MENVCFG_PBMTE : 0) |
                     (cfg->ext_sstc ? MENVCFG_STCE : 0) |
-                    (cfg->ext_svadu ? MENVCFG_HADE : 0);
+                    (cfg->ext_svadu ? MENVCFG_ADUE : 0);
     uint64_t valh = (uint64_t)val << 32;
 
     env->menvcfg = (env->menvcfg & ~mask) | (valh & mask);
@@ -XXX,XX +XXX,XX @@ static RISCVException read_henvcfg(CPURISCVState *env, int csrno,
      * henvcfg.stce is read_only 0 when menvcfg.stce = 0
      * henvcfg.hade is read_only 0 when menvcfg.hade = 0
      */
-    *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) |
+    *val = env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) |
                            env->menvcfg);
     return RISCV_EXCP_NONE;
 }
@@ -XXX,XX +XXX,XX @@ static RISCVException write_henvcfg(CPURISCVState *env, int csrno,
     }
 
     if (riscv_cpu_mxl(env) == MXL_RV64) {
-        mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE);
+        mask |= env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE);
     }
 
     env->henvcfg = (env->henvcfg & ~mask) | (val & mask);
@@ -XXX,XX +XXX,XX @@ static RISCVException read_henvcfgh(CPURISCVState *env, int csrno,
         return ret;
     }
 
-    *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_HADE) |
+    *val = (env->henvcfg & (~(HENVCFG_PBMTE | HENVCFG_STCE | HENVCFG_ADUE) |
                             env->menvcfg)) >> 32;
     return RISCV_EXCP_NONE;
 }
@@ -XXX,XX +XXX,XX @@ static RISCVException write_henvcfgh(CPURISCVState *env, int csrno,
                                      target_ulong val)
 {
     uint64_t mask = env->menvcfg & (HENVCFG_PBMTE | HENVCFG_STCE |
-                                    HENVCFG_HADE);
+                                    HENVCFG_ADUE);
     uint64_t valh = (uint64_t)val << 32;
     RISCVException ret;
 
-- 
2.41.0

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

In the same emulated RISC-V host, the 'host' KVM CPU takes 4 times
longer to boot than the 'rv64' KVM CPU.

The reason is an unintended behavior of riscv_cpu_satp_mode_finalize()
when satp_mode.supported = 0, i.e. when cpu_init() does not set
satp_mode_max_supported(). satp_mode_max_from_map(map) does:

31 - __builtin_clz(map)

This means that, if satp_mode.supported = 0, satp_mode_supported_max
wil be '31 - 32'. But this is C, so satp_mode_supported_max will gladly
set it to UINT_MAX (4294967295). After that, if the user didn't set a
satp_mode, set_satp_mode_default_map(cpu) will make

cfg.satp_mode.map = cfg.satp_mode.supported

So satp_mode.map = 0. And then satp_mode_map_max will be set to
satp_mode_max_from_map(cpu->cfg.satp_mode.map), i.e. also UINT_MAX. The
guard "satp_mode_map_max > satp_mode_supported_max" doesn't protect us
here since both are UINT_MAX.

And finally we have 2 loops:

for (int i = satp_mode_map_max - 1; i >= 0; --i) {

Which are, in fact, 2 loops from UINT_MAX -1 to -1. This is where the
extra delay when booting the 'host' CPU is coming from.

Commit 43d1de32f8 already set a precedence for satp_mode.supported = 0
in a different manner. We're doing the same here. If supported == 0,
interpret as 'the CPU wants the OS to handle satp mode alone' and skip
satp_mode_finalize().

We'll also put a guard in satp_mode_max_from_map() to assert out if map
is 0 since the function is not ready to deal with it.

Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Fixes: 6f23aaeb9b ("riscv: Allow user to set the satp mode")
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Message-ID: <20230817152903.694926-1-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static uint8_t satp_mode_from_str(const char *satp_mode_str)
 
 uint8_t satp_mode_max_from_map(uint32_t map)
 {
+    /*
+     * 'map = 0' will make us return (31 - 32), which C will
+     * happily overflow to UINT_MAX. There's no good result to
+     * return if 'map = 0' (e.g. returning 0 will be ambiguous
+     * with the result for 'map = 1').
+     *
+     * Assert out if map = 0. Callers will have to deal with
+     * it outside of this function.
+     */
+    g_assert(map > 0);
+
     /* map here has at least one bit set, so no problem with clz */
     return 31 - __builtin_clz(map);
 }
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
 static void riscv_cpu_satp_mode_finalize(RISCVCPU *cpu, Error **errp)
 {
     bool rv32 = riscv_cpu_mxl(&cpu->env) == MXL_RV32;
-    uint8_t satp_mode_map_max;
-    uint8_t satp_mode_supported_max =
-                        satp_mode_max_from_map(cpu->cfg.satp_mode.supported);
+    uint8_t satp_mode_map_max, satp_mode_supported_max;
+
+    /* The CPU wants the OS to decide which satp mode to use */
+    if (cpu->cfg.satp_mode.supported == 0) {
+        return;
+    }
+
+    satp_mode_supported_max =
+                    satp_mode_max_from_map(cpu->cfg.satp_mode.supported);
 
     if (cpu->cfg.satp_mode.map == 0) {
         if (cpu->cfg.satp_mode.init == 0) {
-- 
2.41.0

From: Vineet Gupta <vineetg@rivosinc.com>

zicond is now codegen supported in both llvm and gcc.

This change allows seamless enabling/testing of zicond in downstream
projects. e.g. currently riscv-gnu-toolchain parses elf attributes
to create a cmdline for qemu but fails short of enabling it because of
the "x-" prefix.

Signed-off-by: Vineet Gupta <vineetg@rivosinc.com>
Message-ID: <20230808181715.436395-1-vineetg@rivosinc.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
     DEFINE_PROP_BOOL("zcf", RISCVCPU, cfg.ext_zcf, false),
     DEFINE_PROP_BOOL("zcmp", RISCVCPU, cfg.ext_zcmp, false),
     DEFINE_PROP_BOOL("zcmt", RISCVCPU, cfg.ext_zcmt, false),
+    DEFINE_PROP_BOOL("zicond", RISCVCPU, cfg.ext_zicond, false),
 
     /* Vendor-specific custom extensions */
     DEFINE_PROP_BOOL("xtheadba", RISCVCPU, cfg.ext_xtheadba, false),
@@ -XXX,XX +XXX,XX @@ static Property riscv_cpu_extensions[] = {
     DEFINE_PROP_BOOL("xventanacondops", RISCVCPU, cfg.ext_XVentanaCondOps, false),
 
     /* These are experimental so mark with 'x-' */
-    DEFINE_PROP_BOOL("x-zicond", RISCVCPU, cfg.ext_zicond, false),
 
     /* ePMP 0.9.3 */
     DEFINE_PROP_BOOL("x-epmp", RISCVCPU, cfg.epmp, false),
-- 
2.41.0

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

A build with --enable-debug and without KVM will fail as follows:

/usr/bin/ld: libqemu-riscv64-softmmu.fa.p/hw_riscv_virt.c.o: in function `virt_machine_init':
./qemu/build/../hw/riscv/virt.c:1465: undefined reference to `kvm_riscv_aia_create'

This happens because the code block with "if virt_use_kvm_aia(s)" isn't
being ignored by the debug build, resulting in an undefined reference to
a KVM only function.

Add a 'kvm_enabled()' conditional together with virt_use_kvm_aia() will
make the compiler crop the kvm_riscv_aia_create() call entirely from a
non-KVM build. Note that adding the 'kvm_enabled()' conditional inside
virt_use_kvm_aia() won't fix the build because this function would need
to be inlined multiple times to make the compiler zero out the entire
block.

While we're at it, use kvm_enabled() in all instances where
virt_use_kvm_aia() is checked to allow the compiler to elide these other
kvm-only instances as well.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Fixes: dbdb99948e ("target/riscv: select KVM AIA in riscv virt machine")
Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20230830133503.711138-2-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 hw/riscv/virt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
     }
 
     /* KVM AIA only has one APLIC instance */
-    if (virt_use_kvm_aia(s)) {
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
         create_fdt_socket_aplic(s, memmap, 0,
                                 msi_m_phandle, msi_s_phandle, phandle,
                                 &intc_phandles[0], xplic_phandles,
@@ -XXX,XX +XXX,XX @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
 
     g_free(intc_phandles);
 
-    if (virt_use_kvm_aia(s)) {
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
         *irq_mmio_phandle = xplic_phandles[0];
         *irq_virtio_phandle = xplic_phandles[0];
         *irq_pcie_phandle = xplic_phandles[0];
@@ -XXX,XX +XXX,XX @@ static void virt_machine_init(MachineState *machine)
         }
     }
 
-    if (virt_use_kvm_aia(s)) {
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
         kvm_riscv_aia_create(machine, IMSIC_MMIO_GROUP_MIN_SHIFT,
                              VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS,
                              memmap[VIRT_APLIC_S].base,
-- 
2.41.0

From: Daniel Henrique Barboza <dbarboza@ventanamicro.com>

Commit 6df0b37e2ab breaks a --enable-debug build in a non-KVM
environment with the following error:

/usr/bin/ld: libqemu-riscv64-softmmu.fa.p/hw_intc_riscv_aplic.c.o: in function `riscv_kvm_aplic_request':
./qemu/build/../hw/intc/riscv_aplic.c:486: undefined reference to `kvm_set_irq'
collect2: error: ld returned 1 exit status

This happens because the debug build will poke into the
'if (is_kvm_aia(aplic->msimode))' block and fail to find a reference to
the KVM only function riscv_kvm_aplic_request().

There are multiple solutions to fix this. We'll go with the same
solution from the previous patch, i.e. add a kvm_enabled() conditional
to filter out the block. But there's a catch: riscv_kvm_aplic_request()
is a local function that would end up being used if the compiler crops
the block, and this won't work. Quoting Richard Henderson's explanation
in [1]:

"(...) the compiler won't eliminate entire unused functions with -O0"

We'll solve it by moving riscv_kvm_aplic_request() to kvm.c and add its
declaration in kvm_riscv.h, where all other KVM specific public
functions are already declared. Other archs handles KVM specific code in
this manner and we expect to do the same from now on.

[1] https://lore.kernel.org/qemu-riscv/d2f1ad02-eb03-138f-9d08-db676deeed05@linaro.org/

Signed-off-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20230830133503.711138-3-dbarboza@ventanamicro.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/kvm_riscv.h | 1 +
 hw/intc/riscv_aplic.c    | 8 ++------
 target/riscv/kvm.c       | 5 +++++
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm_riscv.h
+++ b/target/riscv/kvm_riscv.h
@@ -XXX,XX +XXX,XX @@ void kvm_riscv_aia_create(MachineState *machine, uint64_t group_shift,
                           uint64_t aia_irq_num, uint64_t aia_msi_num,
                           uint64_t aplic_base, uint64_t imsic_base,
                           uint64_t guest_num);
+void riscv_kvm_aplic_request(void *opaque, int irq, int level);
 
 #endif
diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/riscv_aplic.c
+++ b/hw/intc/riscv_aplic.c
@@ -XXX,XX +XXX,XX @@
 #include "target/riscv/cpu.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/kvm.h"
+#include "kvm_riscv.h"
 #include "migration/vmstate.h"
 
 #define APLIC_MAX_IDC                  (1UL << 14)
@@ -XXX,XX +XXX,XX @@ static uint32_t riscv_aplic_idc_claimi(RISCVAPLICState *aplic, uint32_t idc)
     return topi;
 }
 
-static void riscv_kvm_aplic_request(void *opaque, int irq, int level)
-{
-    kvm_set_irq(kvm_state, irq, !!level);
-}
-
 static void riscv_aplic_request(void *opaque, int irq, int level)
 {
     bool update = false;
@@ -XXX,XX +XXX,XX @@ static void riscv_aplic_realize(DeviceState *dev, Error **errp)
      * have IRQ lines delegated by their parent APLIC.
      */
     if (!aplic->parent) {
-        if (is_kvm_aia(aplic->msimode)) {
+        if (kvm_enabled() && is_kvm_aia(aplic->msimode)) {
             qdev_init_gpio_in(dev, riscv_kvm_aplic_request, aplic->num_irqs);
         } else {
             qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/kvm.c
+++ b/target/riscv/kvm.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/runstate.h"
 #include "hw/riscv/numa.h"
 
+void riscv_kvm_aplic_request(void *opaque, int irq, int level)
+{
+    kvm_set_irq(kvm_state, irq, !!level);
+}
+
 static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type,
                                  uint64_t idx)
 {
-- 
2.41.0

From: Robbin Ehn <rehn@rivosinc.com>

This patch adds the new extensions in
linux 6.5 to the hwprobe syscall.

And fixes RVC check to OR with correct value.
The previous variable contains 0 therefore it
did work.

Signed-off-by: Robbin Ehn <rehn@rivosinc.com>
Acked-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <bc82203b72d7efb30f1b4a8f9eb3d94699799dc8.camel@rivosinc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 linux-user/syscall.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -XXX,XX +XXX,XX @@ static int do_getdents64(abi_long dirfd, abi_long arg2, abi_long count)
 #define RISCV_HWPROBE_KEY_IMA_EXT_0     4
 #define     RISCV_HWPROBE_IMA_FD       (1 << 0)
 #define     RISCV_HWPROBE_IMA_C        (1 << 1)
+#define     RISCV_HWPROBE_IMA_V        (1 << 2)
+#define     RISCV_HWPROBE_EXT_ZBA      (1 << 3)
+#define     RISCV_HWPROBE_EXT_ZBB      (1 << 4)
+#define     RISCV_HWPROBE_EXT_ZBS      (1 << 5)
 
 #define RISCV_HWPROBE_KEY_CPUPERF_0     5
 #define     RISCV_HWPROBE_MISALIGNED_UNKNOWN     (0 << 0)
@@ -XXX,XX +XXX,XX @@ static void risc_hwprobe_fill_pairs(CPURISCVState *env,
                     riscv_has_ext(env, RVD) ?
                     RISCV_HWPROBE_IMA_FD : 0;
             value |= riscv_has_ext(env, RVC) ?
-                     RISCV_HWPROBE_IMA_C : pair->value;
+                     RISCV_HWPROBE_IMA_C : 0;
+            value |= riscv_has_ext(env, RVV) ?
+                     RISCV_HWPROBE_IMA_V : 0;
+            value |= cfg->ext_zba ?
+                     RISCV_HWPROBE_EXT_ZBA : 0;
+            value |= cfg->ext_zbb ?
+                     RISCV_HWPROBE_EXT_ZBB : 0;
+            value |= cfg->ext_zbs ?
+                     RISCV_HWPROBE_EXT_ZBS : 0;
             __put_user(value, &pair->value);
             break;
         case RISCV_HWPROBE_KEY_CPUPERF_0:
-- 
2.41.0

From: Ard Biesheuvel <ardb@kernel.org>

Use the accelerated SubBytes/ShiftRows/AddRoundKey AES helper to
implement the first half of the key schedule derivation. This does not
actually involve shifting rows, so clone the same value into all four
columns of the AES vector to counter that operation.

Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20230831154118.138727-1-ardb@kernel.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/crypto_helper.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/crypto_helper.c
+++ b/target/riscv/crypto_helper.c
@@ -XXX,XX +XXX,XX @@ target_ulong HELPER(aes64ks1i)(target_ulong rs1, target_ulong rnum)
 
     uint8_t enc_rnum = rnum;
     uint32_t temp = (RS1 >> 32) & 0xFFFFFFFF;
-    uint8_t rcon_ = 0;
-    target_ulong result;
+    AESState t, rc = {};
 
     if (enc_rnum != 0xA) {
         temp = ror32(temp, 8); /* Rotate right by 8 */
-        rcon_ = round_consts[enc_rnum];
+        rc.w[0] = rc.w[1] = round_consts[enc_rnum];
     }
 
-    temp = ((uint32_t)AES_sbox[(temp >> 24) & 0xFF] << 24) |
-           ((uint32_t)AES_sbox[(temp >> 16) & 0xFF] << 16) |
-           ((uint32_t)AES_sbox[(temp >> 8) & 0xFF] << 8) |
-           ((uint32_t)AES_sbox[(temp >> 0) & 0xFF] << 0);
+    t.w[0] = t.w[1] = t.w[2] = t.w[3] = temp;
+    aesenc_SB_SR_AK(&t, &t, &rc, false);
 
-    temp ^= rcon_;
-
-    result = ((uint64_t)temp << 32) | temp;
-
-    return result;
+    return t.d[0];
 }
 
 target_ulong HELPER(aes64im)(target_ulong rs1)
-- 
2.41.0

From: Akihiko Odaki <akihiko.odaki@daynix.com>

riscv_trigger_init() had been called on reset events that can happen
several times for a CPU and it allocated timers for itrigger. If old
timers were present, they were simply overwritten by the new timers,
resulting in a memory leak.

Divide riscv_trigger_init() into two functions, namely
riscv_trigger_realize() and riscv_trigger_reset() and call them in
appropriate timing. The timer allocation will happen only once for a
CPU in riscv_trigger_realize().

Fixes: 5a4ae64cac ("target/riscv: Add itrigger support when icount is enabled")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230818034059.9146-1-akihiko.odaki@daynix.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/debug.h |  3 ++-
 target/riscv/cpu.c   |  8 +++++++-
 target/riscv/debug.c | 15 ++++++++++++---
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/target/riscv/debug.h b/target/riscv/debug.h
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/debug.h
+++ b/target/riscv/debug.h
@@ -XXX,XX +XXX,XX @@ void riscv_cpu_debug_excp_handler(CPUState *cs);
 bool riscv_cpu_debug_check_breakpoint(CPUState *cs);
 bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp);
 
-void riscv_trigger_init(CPURISCVState *env);
+void riscv_trigger_realize(CPURISCVState *env);
+void riscv_trigger_reset_hold(CPURISCVState *env);
 
 bool riscv_itrigger_enabled(CPURISCVState *env);
 void riscv_itrigger_update_priv(CPURISCVState *env);
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj)
 
 #ifndef CONFIG_USER_ONLY
     if (cpu->cfg.debug) {
-        riscv_trigger_init(env);
+        riscv_trigger_reset_hold(env);
     }
 
     if (kvm_enabled()) {
@@ -XXX,XX +XXX,XX @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp)
 
     riscv_cpu_register_gdb_regs_for_features(cs);
 
+#ifndef CONFIG_USER_ONLY
+    if (cpu->cfg.debug) {
+        riscv_trigger_realize(&cpu->env);
+    }
+#endif
+
     qemu_init_vcpu(cs);
     cpu_reset(cs);
 
diff --git a/target/riscv/debug.c b/target/riscv/debug.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/debug.c
+++ b/target/riscv/debug.c
@@ -XXX,XX +XXX,XX @@ bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp)
     return false;
 }
 
-void riscv_trigger_init(CPURISCVState *env)
+void riscv_trigger_realize(CPURISCVState *env)
+{
+    int i;
+
+    for (i = 0; i < RV_MAX_TRIGGERS; i++) {
+        env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                              riscv_itrigger_timer_cb, env);
+    }
+}
+
+void riscv_trigger_reset_hold(CPURISCVState *env)
 {
     target_ulong tdata1 = build_tdata1(env, TRIGGER_TYPE_AD_MATCH, 0, 0);
     int i;
@@ -XXX,XX +XXX,XX @@ void riscv_trigger_init(CPURISCVState *env)
         env->tdata3[i] = 0;
         env->cpu_breakpoint[i] = NULL;
         env->cpu_watchpoint[i] = NULL;
-        env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                              riscv_itrigger_timer_cb, env);
+        timer_del(env->itrigger_timer[i]);
     }
 }
-- 
2.41.0

From: Leon Schuermann <leons@opentitan.org>

When the rule-lock bypass (RLB) bit is set in the mseccfg CSR, the PMP
configuration lock bits must not apply. While this behavior is
implemented for the pmpcfgX CSRs, this bit is not respected for
changes to the pmpaddrX CSRs. This patch ensures that pmpaddrX CSR
writes work even on locked regions when the global rule-lock bypass is
enabled.

Signed-off-by: Leon Schuermann <leons@opentitan.org>
Reviewed-by: Mayuresh Chitale <mchitale@ventanamicro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230829215046.1430463-1-leon@is.currently.online>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/pmp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/target/riscv/pmp.c b/target/riscv/pmp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/pmp.c
+++ b/target/riscv/pmp.c
@@ -XXX,XX +XXX,XX @@ static inline uint8_t pmp_get_a_field(uint8_t cfg)
  */
 static inline int pmp_is_locked(CPURISCVState *env, uint32_t pmp_index)
 {
+    /* mseccfg.RLB is set */
+    if (MSECCFG_RLB_ISSET(env)) {
+        return 0;
+    }
 
     if (env->pmp_state.pmp[pmp_index].cfg_reg & PMP_LOCK) {
         return 1;
-- 
2.41.0

From: Tommy Wu <tommy.wu@sifive.com>

According to the new spec, when vsiselect has a reserved value, attempts
from M-mode or HS-mode to access vsireg, or from VS-mode to access
sireg, should preferably raise an illegal instruction exception.

Signed-off-by: Tommy Wu <tommy.wu@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Message-ID: <20230816061647.600672-1-tommy.wu@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/csr.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static int rmw_iprio(target_ulong xlen,
 static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
                      target_ulong new_val, target_ulong wr_mask)
 {
-    bool virt;
+    bool virt, isel_reserved;
     uint8_t *iprio;
     int ret = -EINVAL;
     target_ulong priv, isel, vgein;
@@ -XXX,XX +XXX,XX @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
 
     /* Decode register details from CSR number */
     virt = false;
+    isel_reserved = false;
     switch (csrno) {
     case CSR_MIREG:
         iprio = env->miprio;
@@ -XXX,XX +XXX,XX @@ static int rmw_xireg(CPURISCVState *env, int csrno, target_ulong *val,
                                                   riscv_cpu_mxl_bits(env)),
                                     val, new_val, wr_mask);
         }
+    } else {
+        isel_reserved = true;
     }
 
 done:
     if (ret) {
-        return (env->virt_enabled && virt) ?
+        return (env->virt_enabled && virt && !isel_reserved) ?
                RISCV_EXCP_VIRT_INSTRUCTION_FAULT : RISCV_EXCP_ILLEGAL_INST;
     }
     return RISCV_EXCP_NONE;
-- 
2.41.0

From: Nikita Shubin <n.shubin@yadro.com>

As per ISA:

"For CSRRWI, if rd=x0, then the instruction shall not read the CSR and
shall not cause any of the side effects that might occur on a CSR read."

trans_csrrwi() and trans_csrrw() call do_csrw() if rd=x0, do_csrw() calls
riscv_csrrw_do64(), via helper_csrw() passing NULL as *ret_value.

Signed-off-by: Nikita Shubin <n.shubin@yadro.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20230808090914.17634-1-nikita.shubin@maquefel.me>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/csr.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -XXX,XX +XXX,XX @@ static RISCVException riscv_csrrw_do64(CPURISCVState *env, int csrno,
                                        target_ulong write_mask)
 {
     RISCVException ret;
-    target_ulong old_value;
+    target_ulong old_value = 0;
 
     /* execute combined read/write operation if it exists */
     if (csr_ops[csrno].op) {
         return csr_ops[csrno].op(env, csrno, ret_value, new_value, write_mask);
     }
 
-    /* if no accessor exists then return failure */
-    if (!csr_ops[csrno].read) {
-        return RISCV_EXCP_ILLEGAL_INST;
-    }
-    /* read old value */
-    ret = csr_ops[csrno].read(env, csrno, &old_value);
-    if (ret != RISCV_EXCP_NONE) {
-        return ret;
+    /*
+     * ret_value == NULL means that rd=x0 and we're coming from helper_csrw()
+     * and we can't throw side effects caused by CSR reads.
+     */
+    if (ret_value) {
+        /* if no accessor exists then return failure */
+        if (!csr_ops[csrno].read) {
+            return RISCV_EXCP_ILLEGAL_INST;
+        }
+        /* read old value */
+        ret = csr_ops[csrno].read(env, csrno, &old_value);
+        if (ret != RISCV_EXCP_NONE) {
+            return ret;
+        }
     }
 
     /* write value if writable and write mask set, otherwise drop writes */
-- 
2.41.0