diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-22 04:41:38 +0100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-22 04:41:38 +0100 |
commit | a135c717d5cdb311cff7661af4c17fef0562e590 (patch) | |
tree | 830a276ee80b95f02ae243c641690c9f2014922d /arch/mips/kernel | |
parent | Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/... (diff) | |
parent | MIPS: sead3: Corrected get_c0_perfcount_int (diff) | |
download | linux-a135c717d5cdb311cff7661af4c17fef0562e590.tar.xz linux-a135c717d5cdb311cff7661af4c17fef0562e590.zip |
Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus
Pull MIPS updates from Ralf Baechle:
"This is the main pull request for MIPS:
- a number of fixes that didn't make the 3.19 release.
- a number of cleanups.
- preliminary support for Cavium's Octeon 3 SOCs which feature up to
48 MIPS64 R3 cores with FPU and hardware virtualization.
- support for MIPS R6 processors.
Revision 6 of the MIPS architecture is a major revision of the MIPS
architecture which does away with many of original sins of the
architecture such as branch delay slots. This and other changes in
R6 require major changes throughout the entire MIPS core
architecture code and make up for the lion share of this pull
request.
- finally some preparatory work for eXtendend Physical Address
support, which allows support of up to 40 bit of physical address
space on 32 bit processors"
[ Ahh, MIPS can't leave the PAE brain damage alone. It's like
every CPU architect has to make that mistake, but pee in the snow
by changing the TLA. But whether it's called PAE, LPAE or XPA,
it's horrid crud - Linus ]
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (114 commits)
MIPS: sead3: Corrected get_c0_perfcount_int
MIPS: mm: Remove dead macro definitions
MIPS: OCTEON: irq: add CIB and other fixes
MIPS: OCTEON: Don't do acknowledge operations for level triggered irqs.
MIPS: OCTEON: More OCTEONIII support
MIPS: OCTEON: Remove setting of processor specific CVMCTL icache bits.
MIPS: OCTEON: Core-15169 Workaround and general CVMSEG cleanup.
MIPS: OCTEON: Update octeon-model.h code for new SoCs.
MIPS: OCTEON: Implement DCache errata workaround for all CN6XXX
MIPS: OCTEON: Add little-endian support to asm/octeon/octeon.h
MIPS: OCTEON: Implement the core-16057 workaround
MIPS: OCTEON: Delete unused COP2 saving code
MIPS: OCTEON: Use correct instruction to read 64-bit COP0 register
MIPS: OCTEON: Save and restore CP2 SHA3 state
MIPS: OCTEON: Fix FP context save.
MIPS: OCTEON: Save/Restore wider multiply registers in OCTEON III CPUs
MIPS: boot: Provide more uImage options
MIPS: Remove unneeded #ifdef __KERNEL__ from asm/processor.h
MIPS: ip22-gio: Remove legacy suspend/resume support
mips: pci: Add ifdef around pci_proc_domain
...
Diffstat (limited to 'arch/mips/kernel')
-rw-r--r-- | arch/mips/kernel/Makefile | 3 | ||||
-rw-r--r-- | arch/mips/kernel/asm-offsets.c | 2 | ||||
-rw-r--r-- | arch/mips/kernel/branch.c | 288 | ||||
-rw-r--r-- | arch/mips/kernel/cevt-r4k.c | 8 | ||||
-rw-r--r-- | arch/mips/kernel/cps-vec.S | 16 | ||||
-rw-r--r-- | arch/mips/kernel/cpu-bugs64.c | 11 | ||||
-rw-r--r-- | arch/mips/kernel/cpu-probe.c | 33 | ||||
-rw-r--r-- | arch/mips/kernel/elf.c | 301 | ||||
-rw-r--r-- | arch/mips/kernel/entry.S | 23 | ||||
-rw-r--r-- | arch/mips/kernel/genex.S | 2 | ||||
-rw-r--r-- | arch/mips/kernel/idle.c | 1 | ||||
-rw-r--r-- | arch/mips/kernel/mips-r2-to-r6-emul.c | 2378 | ||||
-rw-r--r-- | arch/mips/kernel/mips_ksyms.c | 12 | ||||
-rw-r--r-- | arch/mips/kernel/octeon_switch.S | 218 | ||||
-rw-r--r-- | arch/mips/kernel/proc.c | 8 | ||||
-rw-r--r-- | arch/mips/kernel/process.c | 96 | ||||
-rw-r--r-- | arch/mips/kernel/r4k_fpu.S | 12 | ||||
-rw-r--r-- | arch/mips/kernel/r4k_switch.S | 14 | ||||
-rw-r--r-- | arch/mips/kernel/spram.c | 1 | ||||
-rw-r--r-- | arch/mips/kernel/syscall.c | 2 | ||||
-rw-r--r-- | arch/mips/kernel/traps.c | 60 | ||||
-rw-r--r-- | arch/mips/kernel/unaligned.c | 390 |
22 files changed, 3598 insertions, 281 deletions
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 92987d1bbe5f..d3d2ff2d76dc 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -52,7 +52,7 @@ obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o obj-$(CONFIG_MIPS_CMP) += smp-cmp.o obj-$(CONFIG_MIPS_CPS) += smp-cps.o cps-vec.o obj-$(CONFIG_MIPS_GIC_IPI) += smp-gic.o -obj-$(CONFIG_CPU_MIPSR2) += spram.o +obj-$(CONFIG_MIPS_SPRAM) += spram.o obj-$(CONFIG_MIPS_VPE_LOADER) += vpe.o obj-$(CONFIG_MIPS_VPE_LOADER_CMP) += vpe-cmp.o @@ -90,6 +90,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_EARLY_PRINTK_8250) += early_printk_8250.o obj-$(CONFIG_SPINLOCK_TEST) += spinlock_test.o obj-$(CONFIG_MIPS_MACHINE) += mips_machine.o +obj-$(CONFIG_MIPSR2_TO_R6_EMULATOR) += mips-r2-to-r6-emul.o CFLAGS_cpu-bugs64.o = $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/null -x c /dev/null >/dev/null 2>&1; then echo "-DHAVE_AS_SET_DADDI"; fi) diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 3b2dfdb4865f..750d67ac41e9 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -97,6 +97,7 @@ void output_thread_info_defines(void) OFFSET(TI_TP_VALUE, thread_info, tp_value); OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); + OFFSET(TI_R2_EMUL_RET, thread_info, r2_emul_return); OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit); OFFSET(TI_REGS, thread_info, regs); DEFINE(_THREAD_SIZE, THREAD_SIZE); @@ -381,6 +382,7 @@ void output_octeon_cop2_state_defines(void) OFFSET(OCTEON_CP2_GFM_RESULT, octeon_cop2_state, cop2_gfm_result); OFFSET(OCTEON_CP2_HSH_DATW, octeon_cop2_state, cop2_hsh_datw); OFFSET(OCTEON_CP2_HSH_IVW, octeon_cop2_state, cop2_hsh_ivw); + OFFSET(OCTEON_CP2_SHA3, octeon_cop2_state, cop2_sha3); OFFSET(THREAD_CP2, task_struct, thread.cp2); OFFSET(THREAD_CVMSEG, task_struct, thread.cvmseg.cvmseg); BLANK(); diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 4d7d99d601cc..c2e0f45ddf6c 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -16,6 +16,7 @@ #include <asm/fpu.h> #include <asm/fpu_emulator.h> #include <asm/inst.h> +#include <asm/mips-r2-to-r6-emul.h> #include <asm/ptrace.h> #include <asm/uaccess.h> @@ -399,11 +400,21 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * @returns: -EFAULT on error and forces SIGBUS, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. + * + * MIPS R6 Compact branches and forbidden slots: + * Compact branches do not throw exceptions because they do + * not have delay slots. The forbidden slot instruction ($PC+4) + * is only executed if the branch was not taken. Otherwise the + * forbidden slot is skipped entirely. This means that the + * only possible reason to be here because of a MIPS R6 compact + * branch instruction is that the forbidden slot has thrown one. + * In that case the branch was not taken, so the EPC can be safely + * set to EPC + 8. */ int __compute_return_epc_for_insn(struct pt_regs *regs, union mips_instruction insn) { - unsigned int bit, fcr31, dspcontrol; + unsigned int bit, fcr31, dspcontrol, reg; long epc = regs->cp0_epc; int ret = 0; @@ -417,6 +428,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->regs[insn.r_format.rd] = epc + 8; /* Fall through */ case jr_op: + if (NO_R6EMU && insn.r_format.func == jr_op) + goto sigill_r6; regs->cp0_epc = regs->regs[insn.r_format.rs]; break; } @@ -429,8 +442,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, */ case bcond_op: switch (insn.i_format.rt) { - case bltz_op: case bltzl_op: + if (NO_R6EMU) + goto sigill_r6; + case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); if (insn.i_format.rt == bltzl_op) @@ -440,8 +455,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->cp0_epc = epc; break; - case bgez_op: case bgezl_op: + if (NO_R6EMU) + goto sigill_r6; + case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); if (insn.i_format.rt == bgezl_op) @@ -453,7 +470,29 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bltzal_op: case bltzall_op: + if (NO_R6EMU && (insn.i_format.rs || + insn.i_format.rt == bltzall_op)) { + ret = -SIGILL; + break; + } regs->regs[31] = epc + 8; + /* + * OK we are here either because we hit a NAL + * instruction or because we are emulating an + * old bltzal{,l} one. Lets figure out what the + * case really is. + */ + if (!insn.i_format.rs) { + /* + * NAL or BLTZAL with rs == 0 + * Doesn't matter if we are R6 or not. The + * result is the same + */ + regs->cp0_epc += 4 + + (insn.i_format.simmediate << 2); + break; + } + /* Now do the real thing for non-R6 BLTZAL{,L} */ if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); if (insn.i_format.rt == bltzall_op) @@ -465,7 +504,29 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezal_op: case bgezall_op: + if (NO_R6EMU && (insn.i_format.rs || + insn.i_format.rt == bgezall_op)) { + ret = -SIGILL; + break; + } regs->regs[31] = epc + 8; + /* + * OK we are here either because we hit a BAL + * instruction or because we are emulating an + * old bgezal{,l} one. Lets figure out what the + * case really is. + */ + if (!insn.i_format.rs) { + /* + * BAL or BGEZAL with rs == 0 + * Doesn't matter if we are R6 or not. The + * result is the same + */ + regs->cp0_epc += 4 + + (insn.i_format.simmediate << 2); + break; + } + /* Now do the real thing for non-R6 BGEZAL{,L} */ if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); if (insn.i_format.rt == bgezall_op) @@ -477,7 +538,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bposge32_op: if (!cpu_has_dsp) - goto sigill; + goto sigill_dsp; dspcontrol = rddsp(0x01); @@ -508,8 +569,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * These are conditional and in i_format. */ - case beq_op: case beql_op: + if (NO_R6EMU) + goto sigill_r6; + case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -520,8 +583,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->cp0_epc = epc; break; - case bne_op: case bnel_op: + if (NO_R6EMU) + goto sigill_r6; + case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -532,8 +597,31 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->cp0_epc = epc; break; - case blez_op: /* not really i_format */ - case blezl_op: + case blezl_op: /* not really i_format */ + if (NO_R6EMU) + goto sigill_r6; + case blez_op: + /* + * Compact branches for R6 for the + * blez and blezl opcodes. + * BLEZ | rs = 0 | rt != 0 == BLEZALC + * BLEZ | rs = rt != 0 == BGEZALC + * BLEZ | rs != 0 | rt != 0 == BGEUC + * BLEZL | rs = 0 | rt != 0 == BLEZC + * BLEZL | rs = rt != 0 == BGEZC + * BLEZL | rs != 0 | rt != 0 == BGEC + * + * For real BLEZ{,L}, rt is always 0. + */ + + if (cpu_has_mips_r6 && insn.i_format.rt) { + if ((insn.i_format.opcode == blez_op) && + ((!insn.i_format.rs && insn.i_format.rt) || + (insn.i_format.rs == insn.i_format.rt))) + regs->regs[31] = epc + 4; + regs->cp0_epc += 8; + break; + } /* rt field assumed to be zero */ if ((long)regs->regs[insn.i_format.rs] <= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -544,8 +632,32 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->cp0_epc = epc; break; - case bgtz_op: case bgtzl_op: + if (NO_R6EMU) + goto sigill_r6; + case bgtz_op: + /* + * Compact branches for R6 for the + * bgtz and bgtzl opcodes. + * BGTZ | rs = 0 | rt != 0 == BGTZALC + * BGTZ | rs = rt != 0 == BLTZALC + * BGTZ | rs != 0 | rt != 0 == BLTUC + * BGTZL | rs = 0 | rt != 0 == BGTZC + * BGTZL | rs = rt != 0 == BLTZC + * BGTZL | rs != 0 | rt != 0 == BLTC + * + * *ZALC varint for BGTZ &&& rt != 0 + * For real GTZ{,L}, rt is always 0. + */ + if (cpu_has_mips_r6 && insn.i_format.rt) { + if ((insn.i_format.opcode == blez_op) && + ((!insn.i_format.rs && insn.i_format.rt) || + (insn.i_format.rs == insn.i_format.rt))) + regs->regs[31] = epc + 4; + regs->cp0_epc += 8; + break; + } + /* rt field assumed to be zero */ if ((long)regs->regs[insn.i_format.rs] > 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -560,40 +672,83 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, * And now the FPA/cp1 branch instructions. */ case cop1_op: - preempt_disable(); - if (is_fpu_owner()) - fcr31 = read_32bit_cp1_register(CP1_STATUS); - else - fcr31 = current->thread.fpu.fcr31; - preempt_enable(); - - bit = (insn.i_format.rt >> 2); - bit += (bit != 0); - bit += 23; - switch (insn.i_format.rt & 3) { - case 0: /* bc1f */ - case 2: /* bc1fl */ - if (~fcr31 & (1 << bit)) { - epc = epc + 4 + (insn.i_format.simmediate << 2); - if (insn.i_format.rt == 2) - ret = BRANCH_LIKELY_TAKEN; - } else + if (cpu_has_mips_r6 && + ((insn.i_format.rs == bc1eqz_op) || + (insn.i_format.rs == bc1nez_op))) { + if (!used_math()) { /* First time FPU user */ + ret = init_fpu(); + if (ret && NO_R6EMU) { + ret = -ret; + break; + } + ret = 0; + set_used_math(); + } + lose_fpu(1); /* Save FPU state for the emulator. */ + reg = insn.i_format.rt; + bit = 0; + switch (insn.i_format.rs) { + case bc1eqz_op: + /* Test bit 0 */ + if (get_fpr32(¤t->thread.fpu.fpr[reg], 0) + & 0x1) + bit = 1; + break; + case bc1nez_op: + /* Test bit 0 */ + if (!(get_fpr32(¤t->thread.fpu.fpr[reg], 0) + & 0x1)) + bit = 1; + break; + } + own_fpu(1); + if (bit) + epc = epc + 4 + + (insn.i_format.simmediate << 2); + else epc += 8; regs->cp0_epc = epc; + break; + } else { - case 1: /* bc1t */ - case 3: /* bc1tl */ - if (fcr31 & (1 << bit)) { - epc = epc + 4 + (insn.i_format.simmediate << 2); - if (insn.i_format.rt == 3) - ret = BRANCH_LIKELY_TAKEN; - } else - epc += 8; - regs->cp0_epc = epc; + preempt_disable(); + if (is_fpu_owner()) + fcr31 = read_32bit_cp1_register(CP1_STATUS); + else + fcr31 = current->thread.fpu.fcr31; + preempt_enable(); + + bit = (insn.i_format.rt >> 2); + bit += (bit != 0); + bit += 23; + switch (insn.i_format.rt & 3) { + case 0: /* bc1f */ + case 2: /* bc1fl */ + if (~fcr31 & (1 << bit)) { + epc = epc + 4 + + (insn.i_format.simmediate << 2); + if (insn.i_format.rt == 2) + ret = BRANCH_LIKELY_TAKEN; + } else + epc += 8; + regs->cp0_epc = epc; + break; + + case 1: /* bc1t */ + case 3: /* bc1tl */ + if (fcr31 & (1 << bit)) { + epc = epc + 4 + + (insn.i_format.simmediate << 2); + if (insn.i_format.rt == 3) + ret = BRANCH_LIKELY_TAKEN; + } else + epc += 8; + regs->cp0_epc = epc; + break; + } break; } - break; #ifdef CONFIG_CPU_CAVIUM_OCTEON case lwc2_op: /* This is bbit0 on Octeon */ if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) @@ -626,15 +781,72 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, epc += 8; regs->cp0_epc = epc; break; +#else + case bc6_op: + /* Only valid for MIPS R6 */ + if (!cpu_has_mips_r6) { + ret = -SIGILL; + break; + } + regs->cp0_epc += 8; + break; + case balc6_op: + if (!cpu_has_mips_r6) { + ret = -SIGILL; + break; + } + /* Compact branch: BALC */ + regs->regs[31] = epc + 4; + epc += 4 + (insn.i_format.simmediate << 2); + regs->cp0_epc = epc; + break; + case beqzcjic_op: + if (!cpu_has_mips_r6) { + ret = -SIGILL; + break; + } + /* Compact branch: BEQZC || JIC */ + regs->cp0_epc += 8; + break; + case bnezcjialc_op: + if (!cpu_has_mips_r6) { + ret = -SIGILL; + break; + } + /* Compact branch: BNEZC || JIALC */ + if (insn.i_format.rs) + regs->regs[31] = epc + 4; + regs->cp0_epc += 8; + break; #endif + case cbcond0_op: + case cbcond1_op: + /* Only valid for MIPS R6 */ + if (!cpu_has_mips_r6) { + ret = -SIGILL; + break; + } + /* + * Compact branches: + * bovc, beqc, beqzalc, bnvc, bnec, bnezlac + */ + if (insn.i_format.rt && !insn.i_format.rs) + regs->regs[31] = epc + 4; + regs->cp0_epc += 8; + break; } return ret; -sigill: +sigill_dsp: printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm); force_sig(SIGBUS, current); return -EFAULT; +sigill_r6: + pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); + return -EFAULT; } EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn); diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 6acaad0480af..82bd2b278a24 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -11,7 +11,6 @@ #include <linux/percpu.h> #include <linux/smp.h> #include <linux/irq.h> -#include <linux/irqchip/mips-gic.h> #include <asm/time.h> #include <asm/cevt-r4k.h> @@ -40,7 +39,7 @@ int cp0_timer_irq_installed; irqreturn_t c0_compare_interrupt(int irq, void *dev_id) { - const int r2 = cpu_has_mips_r2; + const int r2 = cpu_has_mips_r2_r6; struct clock_event_device *cd; int cpu = smp_processor_id(); @@ -85,10 +84,7 @@ void mips_event_handler(struct clock_event_device *dev) */ static int c0_compare_int_pending(void) { -#ifdef CONFIG_MIPS_GIC - if (gic_present) - return gic_get_timer_pending(); -#endif + /* When cpu_has_mips_r2, this checks Cause.TI instead of Cause.IP7 */ return (read_c0_cause() >> cp0_compare_irq_shift) & (1ul << CAUSEB_IP); } diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 0384b05ab5a0..55b759a0019e 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -99,11 +99,11 @@ not_nmi: xori t2, t1, 0x7 beqz t2, 1f li t3, 32 - addi t1, t1, 1 + addiu t1, t1, 1 sllv t1, t3, t1 1: /* At this point t1 == I-cache sets per way */ _EXT t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ - addi t2, t2, 1 + addiu t2, t2, 1 mul t1, t1, t0 mul t1, t1, t2 @@ -126,11 +126,11 @@ icache_done: xori t2, t1, 0x7 beqz t2, 1f li t3, 32 - addi t1, t1, 1 + addiu t1, t1, 1 sllv t1, t3, t1 1: /* At this point t1 == D-cache sets per way */ _EXT t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ - addi t2, t2, 1 + addiu t2, t2, 1 mul t1, t1, t0 mul t1, t1, t2 @@ -250,7 +250,7 @@ LEAF(mips_cps_core_init) mfc0 t0, CP0_MVPCONF0 srl t0, t0, MVPCONF0_PVPE_SHIFT andi t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT) - addi t7, t0, 1 + addiu t7, t0, 1 /* If there's only 1, we're done */ beqz t0, 2f @@ -280,7 +280,7 @@ LEAF(mips_cps_core_init) mttc0 t0, CP0_TCHALT /* Next VPE */ - addi t5, t5, 1 + addiu t5, t5, 1 slt t0, t5, t7 bnez t0, 1b nop @@ -317,7 +317,7 @@ LEAF(mips_cps_boot_vpes) mfc0 t1, CP0_MVPCONF0 srl t1, t1, MVPCONF0_PVPE_SHIFT andi t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT - addi t1, t1, 1 + addiu t1, t1, 1 /* Calculate a mask for the VPE ID from EBase.CPUNum */ clz t1, t1 @@ -424,7 +424,7 @@ LEAF(mips_cps_boot_vpes) /* Next VPE */ 2: srl t6, t6, 1 - addi t5, t5, 1 + addiu t5, t5, 1 bnez t6, 1b nop diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index 2d80b5f1aeae..09f4034f239f 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -244,7 +244,7 @@ static inline void check_daddi(void) panic(bug64hit, !DADDI_WAR ? daddiwar : nowar); } -int daddiu_bug = -1; +int daddiu_bug = config_enabled(CONFIG_CPU_MIPSR6) ? 0 : -1; static inline void check_daddiu(void) { @@ -314,11 +314,14 @@ static inline void check_daddiu(void) void __init check_bugs64_early(void) { - check_mult_sh(); - check_daddiu(); + if (!config_enabled(CONFIG_CPU_MIPSR6)) { + check_mult_sh(); + check_daddiu(); + } } void __init check_bugs64(void) { - check_daddi(); + if (!config_enabled(CONFIG_CPU_MIPSR6)) + check_daddi(); } diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 5342674842f5..48dfb9de853d 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -237,6 +237,13 @@ static void set_isa(struct cpuinfo_mips *c, unsigned int isa) c->isa_level |= MIPS_CPU_ISA_II | MIPS_CPU_ISA_III; break; + /* R6 incompatible with everything else */ + case MIPS_CPU_ISA_M64R6: + c->isa_level |= MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6; + case MIPS_CPU_ISA_M32R6: + c->isa_level |= MIPS_CPU_ISA_M32R6; + /* Break here so we don't add incompatible ISAs */ + break; case MIPS_CPU_ISA_M32R2: c->isa_level |= MIPS_CPU_ISA_M32R2; case MIPS_CPU_ISA_M32R1: @@ -326,6 +333,9 @@ static inline unsigned int decode_config0(struct cpuinfo_mips *c) case 1: set_isa(c, MIPS_CPU_ISA_M32R2); break; + case 2: + set_isa(c, MIPS_CPU_ISA_M32R6); + break; default: goto unknown; } @@ -338,6 +348,9 @@ static inline unsigned int decode_config0(struct cpuinfo_mips *c) case 1: set_isa(c, MIPS_CPU_ISA_M64R2); break; + case 2: + set_isa(c, MIPS_CPU_ISA_M64R6); + break; default: goto unknown; } @@ -424,8 +437,10 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c) if (config3 & MIPS_CONF3_MSA) c->ases |= MIPS_ASE_MSA; /* Only tested on 32-bit cores */ - if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT)) + if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT)) { + c->htw_seq = 0; c->options |= MIPS_CPU_HTW; + } return config3 & MIPS_CONF_M; } @@ -499,6 +514,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c) c->options |= MIPS_CPU_EVA; if (config5 & MIPS_CONF5_MRP) c->options |= MIPS_CPU_MAAR; + if (config5 & MIPS_CONF5_LLB) + c->options |= MIPS_CPU_RW_LLB; return config5 & MIPS_CONF_M; } @@ -533,7 +550,7 @@ static void decode_configs(struct cpuinfo_mips *c) if (cpu_has_rixi) { /* Enable the RIXI exceptions */ - write_c0_pagegrain(read_c0_pagegrain() | PG_IEC); + set_c0_pagegrain(PG_IEC); back_to_back_c0_hazard(); /* Verify the IEC bit is set */ if (read_c0_pagegrain() & PG_IEC) @@ -541,7 +558,7 @@ static void decode_configs(struct cpuinfo_mips *c) } #ifndef CONFIG_MIPS_CPS - if (cpu_has_mips_r2) { + if (cpu_has_mips_r2_r6) { c->core = get_ebase_cpunum(); if (cpu_has_mipsmt) c->core >>= fls(core_nvpes()) - 1; @@ -896,6 +913,11 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) { c->writecombine = _CACHE_UNCACHED_ACCELERATED; switch (c->processor_id & PRID_IMP_MASK) { + case PRID_IMP_QEMU_GENERIC: + c->writecombine = _CACHE_UNCACHED; + c->cputype = CPU_QEMU_GENERIC; + __cpu_name[cpu] = "MIPS GENERIC QEMU"; + break; case PRID_IMP_4KC: c->cputype = CPU_4KC; c->writecombine = _CACHE_UNCACHED; @@ -1345,8 +1367,7 @@ void cpu_probe(void) if (c->options & MIPS_CPU_FPU) { c->fpu_id = cpu_get_fpu_id(); - if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | - MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) { + if (c->isa_level & cpu_has_mips_r) { if (c->fpu_id & MIPS_FPIR_3D) c->ases |= MIPS_ASE_MIPS3D; if (c->fpu_id & MIPS_FPIR_FREP) @@ -1354,7 +1375,7 @@ void cpu_probe(void) } } - if (cpu_has_mips_r2) { + if (cpu_has_mips_r2_r6) { c->srsets = ((read_c0_srsctl() >> 26) & 0x0f) + 1; /* R2 has Performance Counter Interrupt indicator */ c->options |= MIPS_CPU_PCI; diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index a5b5b56485c1..d2c09f6475c5 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -11,29 +11,112 @@ #include <linux/elf.h> #include <linux/sched.h> +/* FPU modes */ enum { - FP_ERROR = -1, - FP_DOUBLE_64A = -2, + FP_FRE, + FP_FR0, + FP_FR1, }; +/** + * struct mode_req - ABI FPU mode requirements + * @single: The program being loaded needs an FPU but it will only issue + * single precision instructions meaning that it can execute in + * either FR0 or FR1. + * @soft: The soft(-float) requirement means that the program being + * loaded needs has no FPU dependency at all (i.e. it has no + * FPU instructions). + * @fr1: The program being loaded depends on FPU being in FR=1 mode. + * @frdefault: The program being loaded depends on the default FPU mode. + * That is FR0 for O32 and FR1 for N32/N64. + * @fre: The program being loaded depends on FPU with FRE=1. This mode is + * a bridge which uses FR=1 whilst still being able to maintain + * full compatibility with pre-existing code using the O32 FP32 + * ABI. + * + * More information about the FP ABIs can be found here: + * + * https://dmz-portal.mips.com/wiki/MIPS_O32_ABI_-_FR0_and_FR1_Interlinking#10.4.1._Basic_mode_set-up + * + */ + +struct mode_req { + bool single; + bool soft; + bool fr1; + bool frdefault; + bool fre; +}; + +static const struct mode_req fpu_reqs[] = { + [MIPS_ABI_FP_ANY] = { true, true, true, true, true }, + [MIPS_ABI_FP_DOUBLE] = { false, false, false, true, true }, + [MIPS_ABI_FP_SINGLE] = { true, false, false, false, false }, + [MIPS_ABI_FP_SOFT] = { false, true, false, false, false }, + [MIPS_ABI_FP_OLD_64] = { false, false, false, false, false }, + [MIPS_ABI_FP_XX] = { false, false, true, true, true }, + [MIPS_ABI_FP_64] = { false, false, true, false, false }, + [MIPS_ABI_FP_64A] = { false, false, true, false, true } +}; + +/* + * Mode requirements when .MIPS.abiflags is not present in the ELF. + * Not present means that everything is acceptable except FR1. + */ +static struct mode_req none_req = { true, true, false, true, true }; + int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, bool is_interp, struct arch_elf_state *state) { - struct elf32_hdr *ehdr = _ehdr; - struct elf32_phdr *phdr = _phdr; + struct elf32_hdr *ehdr32 = _ehdr; + struct elf32_phdr *phdr32 = _phdr; + struct elf64_phdr *phdr64 = _phdr; struct mips_elf_abiflags_v0 abiflags; int ret; - if (config_enabled(CONFIG_64BIT) && - (ehdr->e_ident[EI_CLASS] != ELFCLASS32)) - return 0; - if (phdr->p_type != PT_MIPS_ABIFLAGS) - return 0; - if (phdr->p_filesz < sizeof(abiflags)) - return -EINVAL; + /* Lets see if this is an O32 ELF */ + if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) { + /* FR = 1 for N32 */ + if (ehdr32->e_flags & EF_MIPS_ABI2) + state->overall_fp_mode = FP_FR1; + else + /* Set a good default FPU mode for O32 */ + state->overall_fp_mode = cpu_has_mips_r6 ? + FP_FRE : FP_FR0; + + if (ehdr32->e_flags & EF_MIPS_FP64) { + /* + * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it + * later if needed + */ + if (is_interp) + state->interp_fp_abi = MIPS_ABI_FP_OLD_64; + else + state->fp_abi = MIPS_ABI_FP_OLD_64; + } + if (phdr32->p_type != PT_MIPS_ABIFLAGS) + return 0; + + if (phdr32->p_filesz < sizeof(abiflags)) + return -EINVAL; + + ret = kernel_read(elf, phdr32->p_offset, + (char *)&abiflags, + sizeof(abiflags)); + } else { + /* FR=1 is really the only option for 64-bit */ + state->overall_fp_mode = FP_FR1; + + if (phdr64->p_type != PT_MIPS_ABIFLAGS) + return 0; + if (phdr64->p_filesz < sizeof(abiflags)) + return -EINVAL; + + ret = kernel_read(elf, phdr64->p_offset, + (char *)&abiflags, + sizeof(abiflags)); + } - ret = kernel_read(elf, phdr->p_offset, (char *)&abiflags, - sizeof(abiflags)); if (ret < 0) return ret; if (ret != sizeof(abiflags)) @@ -48,35 +131,30 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, return 0; } -static inline unsigned get_fp_abi(struct elf32_hdr *ehdr, int in_abi) +static inline unsigned get_fp_abi(int in_abi) { /* If the ABI requirement is provided, simply return that */ - if (in_abi != -1) + if (in_abi != MIPS_ABI_FP_UNKNOWN) return in_abi; - /* If the EF_MIPS_FP64 flag was set, return MIPS_ABI_FP_64 */ - if (ehdr->e_flags & EF_MIPS_FP64) - return MIPS_ABI_FP_64; - - /* Default to MIPS_ABI_FP_DOUBLE */ - return MIPS_ABI_FP_DOUBLE; + /* Unknown ABI */ + return MIPS_ABI_FP_UNKNOWN; } int arch_check_elf(void *_ehdr, bool has_interpreter, struct arch_elf_state *state) { struct elf32_hdr *ehdr = _ehdr; - unsigned fp_abi, interp_fp_abi, abi0, abi1; + struct mode_req prog_req, interp_req; + int fp_abi, interp_fp_abi, abi0, abi1, max_abi; - /* Ignore non-O32 binaries */ - if (config_enabled(CONFIG_64BIT) && - (ehdr->e_ident[EI_CLASS] != ELFCLASS32)) + if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) return 0; - fp_abi = get_fp_abi(ehdr, state->fp_abi); + fp_abi = get_fp_abi(state->fp_abi); if (has_interpreter) { - interp_fp_abi = get_fp_abi(ehdr, state->interp_fp_abi); + interp_fp_abi = get_fp_abi(state->interp_fp_abi); abi0 = min(fp_abi, interp_fp_abi); abi1 = max(fp_abi, interp_fp_abi); @@ -84,108 +162,103 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, abi0 = abi1 = fp_abi; } - state->overall_abi = FP_ERROR; - - if (abi0 == abi1) { - state->overall_abi = abi0; - } else if (abi0 == MIPS_ABI_FP_ANY) { - state->overall_abi = abi1; - } else if (abi0 == MIPS_ABI_FP_DOUBLE) { - switch (abi1) { - case MIPS_ABI_FP_XX: - state->overall_abi = MIPS_ABI_FP_DOUBLE; - break; - - case MIPS_ABI_FP_64A: - state->overall_abi = FP_DOUBLE_64A; - break; - } - } else if (abi0 == MIPS_ABI_FP_SINGLE || - abi0 == MIPS_ABI_FP_SOFT) { - /* Cannot link with other ABIs */ - } else if (abi0 == MIPS_ABI_FP_OLD_64) { - switch (abi1) { - case MIPS_ABI_FP_XX: - case MIPS_ABI_FP_64: - case MIPS_ABI_FP_64A: - state->overall_abi = MIPS_ABI_FP_64; - break; - } - } else if (abi0 == MIPS_ABI_FP_XX || - abi0 == MIPS_ABI_FP_64 || - abi0 == MIPS_ABI_FP_64A) { - state->overall_abi = MIPS_ABI_FP_64; - } + /* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */ + max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) && + (!(ehdr->e_flags & EF_MIPS_ABI2))) ? + MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT; - switch (state->overall_abi) { - case MIPS_ABI_FP_64: - case MIPS_ABI_FP_64A: - case FP_DOUBLE_64A: - if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) - return -ELIBBAD; - break; + if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) || + (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN)) + return -ELIBBAD; + + /* It's time to determine the FPU mode requirements */ + prog_req = (abi0 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi0]; + interp_req = (abi1 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi1]; - case FP_ERROR: + /* + * Check whether the program's and interp's ABIs have a matching FPU + * mode requirement. + */ + prog_req.single = interp_req.single && prog_req.single; + prog_req.soft = interp_req.soft && prog_req.soft; + prog_req.fr1 = interp_req.fr1 && prog_req.fr1; + prog_req.frdefault = interp_req.frdefault && prog_req.frdefault; + prog_req.fre = interp_req.fre && prog_req.fre; + + /* + * Determine the desired FPU mode + * + * Decision making: + * + * - We want FR_FRE if FRE=1 and both FR=1 and FR=0 are false. This + * means that we have a combination of program and interpreter + * that inherently require the hybrid FP mode. + * - If FR1 and FRDEFAULT is true, that means we hit the any-abi or + * fpxx case. This is because, in any-ABI (or no-ABI) we have no FPU + * instructions so we don't care about the mode. We will simply use + * the one preferred by the hardware. In fpxx case, that ABI can + * handle both FR=1 and FR=0, so, again, we simply choose the one + * preferred by the hardware. Next, if we only use single-precision + * FPU instructions, and the default ABI FPU mode is not good + * (ie single + any ABI combination), we set again the FPU mode to the + * one is preferred by the hardware. Next, if we know that the code + * will only use single-precision instructions, shown by single being + * true but frdefault being false, then we again set the FPU mode to + * the one that is preferred by the hardware. + * - We want FP_FR1 if that's the only matching mode and the default one + * is not good. + * - Return with -ELIBADD if we can't find a matching FPU mode. + */ + if (prog_req.fre && !prog_req.frdefault && !prog_req.fr1) + state->overall_fp_mode = FP_FRE; + else if ((prog_req.fr1 && prog_req.frdefault) || + (prog_req.single && !prog_req.frdefault)) + /* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */ + state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) && + cpu_has_mips_r2_r6) ? + FP_FR1 : FP_FR0; + else if (prog_req.fr1) + state->overall_fp_mode = FP_FR1; + else if (!prog_req.fre && !prog_req.frdefault && + !prog_req.fr1 && !prog_req.single && !prog_req.soft) return -ELIBBAD; - } return 0; } -void mips_set_personality_fp(struct arch_elf_state *state) +static inline void set_thread_fp_mode(int hybrid, int regs32) { - if (config_enabled(CONFIG_FP32XX_HYBRID_FPRS)) { - /* - * Use hybrid FPRs for all code which can correctly execute - * with that mode. - */ - switch (state->overall_abi) { - case MIPS_ABI_FP_DOUBLE: - case MIPS_ABI_FP_SINGLE: - case MIPS_ABI_FP_SOFT: - case MIPS_ABI_FP_XX: - case MIPS_ABI_FP_ANY: - /* FR=1, FRE=1 */ - clear_thread_flag(TIF_32BIT_FPREGS); - set_thread_flag(TIF_HYBRID_FPREGS); - return; - } - } - - switch (state->overall_abi) { - case MIPS_ABI_FP_DOUBLE: - case MIPS_ABI_FP_SINGLE: - case MIPS_ABI_FP_SOFT: - /* FR=0 */ - set_thread_flag(TIF_32BIT_FPREGS); + if (hybrid) + set_thread_flag(TIF_HYBRID_FPREGS); + else clear_thread_flag(TIF_HYBRID_FPREGS); - break; - - case FP_DOUBLE_64A: - /* FR=1, FRE=1 */ + if (regs32) + set_thread_flag(TIF_32BIT_FPREGS); + else clear_thread_flag(TIF_32BIT_FPREGS); - set_thread_flag(TIF_HYBRID_FPREGS); - break; +} - case MIPS_ABI_FP_64: - case MIPS_ABI_FP_64A: - /* FR=1, FRE=0 */ - clear_thread_flag(TIF_32BIT_FPREGS); - clear_thread_flag(TIF_HYBRID_FPREGS); - break; +void mips_set_personality_fp(struct arch_elf_state *state) +{ + /* + * This function is only ever called for O32 ELFs so we should + * not be worried about N32/N64 binaries. + */ - case MIPS_ABI_FP_XX: - case MIPS_ABI_FP_ANY: - if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) - set_thread_flag(TIF_32BIT_FPREGS); - else - clear_thread_flag(TIF_32BIT_FPREGS); + if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) + return; - clear_thread_flag(TIF_HYBRID_FPREGS); + switch (state->overall_fp_mode) { + case FP_FRE: + set_thread_fp_mode(1, 0); + break; + case FP_FR0: + set_thread_fp_mode(0, 1); + break; + case FP_FR1: + set_thread_fp_mode(0, 0); break; - default: - case FP_ERROR: BUG(); } } diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 4353d323f017..af41ba6db960 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -46,6 +46,11 @@ resume_userspace: local_irq_disable # make sure we dont miss an # interrupt setting need_resched # between sampling and return +#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR + lw k0, TI_R2_EMUL_RET($28) + bnez k0, restore_all_from_r2_emul +#endif + LONG_L a2, TI_FLAGS($28) # current->work andi t0, a2, _TIF_WORK_MASK # (ignoring syscall_trace) bnez t0, work_pending @@ -114,6 +119,19 @@ restore_partial: # restore partial frame RESTORE_SP_AND_RET .set at +#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR +restore_all_from_r2_emul: # restore full frame + .set noat + sw zero, TI_R2_EMUL_RET($28) # reset it + RESTORE_TEMP + RESTORE_AT + RESTORE_STATIC + RESTORE_SOME + LONG_L sp, PT_R29(sp) + eretnc + .set at +#endif + work_pending: andi t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS beqz t0, work_notifysig @@ -158,7 +176,8 @@ syscall_exit_work: jal syscall_trace_leave b resume_userspace -#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT) +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) || \ + defined(CONFIG_MIPS_MT) /* * MIPS32R2 Instruction Hazard Barrier - must be called @@ -171,4 +190,4 @@ LEAF(mips_ihb) nop END(mips_ihb) -#endif /* CONFIG_CPU_MIPSR2 or CONFIG_MIPS_MT */ +#endif /* CONFIG_CPU_MIPSR2 or CONFIG_CPU_MIPSR6 or CONFIG_MIPS_MT */ diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index a5e26dd90592..2ebaabe3af15 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -125,7 +125,7 @@ LEAF(__r4k_wait) nop nop #endif - .set arch=r4000 + .set MIPS_ISA_ARCH_LEVEL_RAW wait /* end of rollback region (the region size must be power of two) */ 1: diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 0b9082b6b683..368c88b7eb6c 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -186,6 +186,7 @@ void __init check_wait(void) case CPU_PROAPTIV: case CPU_P5600: case CPU_M5150: + case CPU_QEMU_GENERIC: cpu_wait = r4k_wait; if (read_c0_config7() & MIPS_CONF7_WII) cpu_wait = r4k_wait_irqoff; diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c new file mode 100644 index 000000000000..64d17e41093b --- /dev/null +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -0,0 +1,2378 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2014 Imagination Technologies Ltd. + * Author: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> + * Author: Markos Chandras <markos.chandras@imgtec.com> + * + * MIPS R2 user space instruction emulator for MIPS R6 + * + */ +#include <linux/bug.h> +#include <linux/compiler.h> +#include <linux/debugfs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/ptrace.h> +#include <linux/seq_file.h> + +#include <asm/asm.h> +#include <asm/branch.h> +#include <asm/break.h> +#include <asm/fpu.h> +#include <asm/fpu_emulator.h> +#include <asm/inst.h> +#include <asm/mips-r2-to-r6-emul.h> +#include <asm/local.h> +#include <asm/ptrace.h> +#include <asm/uaccess.h> + +#ifdef CONFIG_64BIT +#define ADDIU "daddiu " +#define INS "dins " +#define EXT "dext " +#else +#define ADDIU "addiu " +#define INS "ins " +#define EXT "ext " +#endif /* CONFIG_64BIT */ + +#define SB "sb " +#define LB "lb " +#define LL "ll " +#define SC "sc " + +DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2emustats); +DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2bdemustats); +DEFINE_PER_CPU(struct mips_r2br_emulator_stats, mipsr2bremustats); + +extern const unsigned int fpucondbit[8]; + +#define MIPS_R2_EMUL_TOTAL_PASS 10 + +int mipsr2_emulation = 0; + +static int __init mipsr2emu_enable(char *s) +{ + mipsr2_emulation = 1; + + pr_info("MIPS R2-to-R6 Emulator Enabled!"); + + return 1; +} +__setup("mipsr2emu", mipsr2emu_enable); + +/** + * mipsr6_emul - Emulate some frequent R2/R5/R6 instructions in delay slot + * for performance instead of the traditional way of using a stack trampoline + * which is rather slow. + * @regs: Process register set + * @ir: Instruction + */ +static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) +{ + switch (MIPSInst_OPCODE(ir)) { + case addiu_op: + if (MIPSInst_RT(ir)) + regs->regs[MIPSInst_RT(ir)] = + (s32)regs->regs[MIPSInst_RS(ir)] + + (s32)MIPSInst_SIMM(ir); + return 0; + case daddiu_op: + if (config_enabled(CONFIG_32BIT)) + break; + + if (MIPSInst_RT(ir)) + regs->regs[MIPSInst_RT(ir)] = + (s64)regs->regs[MIPSInst_RS(ir)] + + (s64)MIPSInst_SIMM(ir); + return 0; + case lwc1_op: + case swc1_op: + case cop1_op: + case cop1x_op: + /* FPU instructions in delay slot */ + return -SIGFPE; + case spec_op: + switch (MIPSInst_FUNC(ir)) { + case or_op: + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + regs->regs[MIPSInst_RS(ir)] | + regs->regs[MIPSInst_RT(ir)]; + return 0; + case sll_op: + if (MIPSInst_RS(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s32)(((u32)regs->regs[MIPSInst_RT(ir)]) << + MIPSInst_FD(ir)); + return 0; + case srl_op: + if (MIPSInst_RS(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s32)(((u32)regs->regs[MIPSInst_RT(ir)]) >> + MIPSInst_FD(ir)); + return 0; + case addu_op: + if (MIPSInst_FD(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s32)((u32)regs->regs[MIPSInst_RS(ir)] + + (u32)regs->regs[MIPSInst_RT(ir)]); + return 0; + case subu_op: + if (MIPSInst_FD(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s32)((u32)regs->regs[MIPSInst_RS(ir)] - + (u32)regs->regs[MIPSInst_RT(ir)]); + return 0; + case dsll_op: + if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s64)(((u64)regs->regs[MIPSInst_RT(ir)]) << + MIPSInst_FD(ir)); + return 0; + case dsrl_op: + if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s64)(((u64)regs->regs[MIPSInst_RT(ir)]) >> + MIPSInst_FD(ir)); + return 0; + case daddu_op: + if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (u64)regs->regs[MIPSInst_RS(ir)] + + (u64)regs->regs[MIPSInst_RT(ir)]; + return 0; + case dsubu_op: + if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir)) + break; + + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = + (s64)((u64)regs->regs[MIPSInst_RS(ir)] - + (u64)regs->regs[MIPSInst_RT(ir)]); + return 0; + } + break; + default: + pr_debug("No fastpath BD emulation for instruction 0x%08x (op: %02x)\n", + ir, MIPSInst_OPCODE(ir)); + } + + return SIGILL; +} + +/** + * movt_func - Emulate a MOVT instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int movf_func(struct pt_regs *regs, u32 ir) +{ + u32 csr; + u32 cond; + + csr = current->thread.fpu.fcr31; + cond = fpucondbit[MIPSInst_RT(ir) >> 2]; + if (((csr & cond) == 0) && MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)]; + MIPS_R2_STATS(movs); + return 0; +} + +/** + * movt_func - Emulate a MOVT instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int movt_func(struct pt_regs *regs, u32 ir) +{ + u32 csr; + u32 cond; + + csr = current->thread.fpu.fcr31; + cond = fpucondbit[MIPSInst_RT(ir) >> 2]; + + if (((csr & cond) != 0) && MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)]; + + MIPS_R2_STATS(movs); + + return 0; +} + +/** + * jr_func - Emulate a JR instruction. + * @pt_regs: Process register set + * @ir: Instruction + * + * Returns SIGILL if JR was in delay slot, SIGEMT if we + * can't compute the EPC, SIGSEGV if we can't access the + * userland instruction or 0 on success. + */ +static int jr_func(struct pt_regs *regs, u32 ir) +{ + int err; + unsigned long cepc, epc, nepc; + u32 nir; + + if (delay_slot(regs)) + return SIGILL; + + /* EPC after the RI/JR instruction */ + nepc = regs->cp0_epc; + /* Roll back to the reserved R2 JR instruction */ + regs->cp0_epc -= 4; + epc = regs->cp0_epc; + err = __compute_return_epc(regs); + + if (err < 0) + return SIGEMT; + + + /* Computed EPC */ + cepc = regs->cp0_epc; + + /* Get DS instruction */ + err = __get_user(nir, (u32 __user *)nepc); + if (err) + return SIGSEGV; + + MIPS_R2BR_STATS(jrs); + + /* If nir == 0(NOP), then nothing else to do */ + if (nir) { + /* + * Negative err means FPU instruction in BD-slot, + * Zero err means 'BD-slot emulation done' + * For anything else we go back to trampoline emulation. + */ + err = mipsr6_emul(regs, nir); + if (err > 0) { + regs->cp0_epc = nepc; + err = mips_dsemul(regs, nir, cepc); + if (err == SIGILL) + err = SIGEMT; + MIPS_R2_STATS(dsemul); + } + } + + return err; +} + +/** + * movz_func - Emulate a MOVZ instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int movz_func(struct pt_regs *regs, u32 ir) +{ + if (((regs->regs[MIPSInst_RT(ir)]) == 0) && MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)]; + MIPS_R2_STATS(movs); + + return 0; +} + +/** + * movn_func - Emulate a MOVZ instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int movn_func(struct pt_regs *regs, u32 ir) +{ + if (((regs->regs[MIPSInst_RT(ir)]) != 0) && MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)]; + MIPS_R2_STATS(movs); + + return 0; +} + +/** + * mfhi_func - Emulate a MFHI instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mfhi_func(struct pt_regs *regs, u32 ir) +{ + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->hi; + + MIPS_R2_STATS(hilo); + + return 0; +} + +/** + * mthi_func - Emulate a MTHI instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mthi_func(struct pt_regs *regs, u32 ir) +{ + regs->hi = regs->regs[MIPSInst_RS(ir)]; + + MIPS_R2_STATS(hilo); + + return 0; +} + +/** + * mflo_func - Emulate a MFLO instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mflo_func(struct pt_regs *regs, u32 ir) +{ + if (MIPSInst_RD(ir)) + regs->regs[MIPSInst_RD(ir)] = regs->lo; + + MIPS_R2_STATS(hilo); + + return 0; +} + +/** + * mtlo_func - Emulate a MTLO instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mtlo_func(struct pt_regs *regs, u32 ir) +{ + regs->lo = regs->regs[MIPSInst_RS(ir)]; + + MIPS_R2_STATS(hilo); + + return 0; +} + +/** + * mult_func - Emulate a MULT instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mult_func(struct pt_regs *regs, u32 ir) +{ + s64 res; + s32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (s64)rt * (s64)rs; + + rs = res; + regs->lo = (s64)rs; + rt = res >> 32; + res = (s64)rt; + regs->hi = res; + + MIPS_R2_STATS(muls); + + return 0; +} + +/** + * multu_func - Emulate a MULTU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int multu_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (u64)rt * (u64)rs; + rt = res; + regs->lo = (s64)rt; + regs->hi = (s64)(res >> 32); + + MIPS_R2_STATS(muls); + + return 0; +} + +/** + * div_func - Emulate a DIV instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int div_func(struct pt_regs *regs, u32 ir) +{ + s32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + + regs->lo = (s64)(rs / rt); + regs->hi = (s64)(rs % rt); + + MIPS_R2_STATS(divs); + + return 0; +} + +/** + * divu_func - Emulate a DIVU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int divu_func(struct pt_regs *regs, u32 ir) +{ + u32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + + regs->lo = (s64)(rs / rt); + regs->hi = (s64)(rs % rt); + + MIPS_R2_STATS(divs); + + return 0; +} + +/** + * dmult_func - Emulate a DMULT instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 on success or SIGILL for 32-bit kernels. + */ +static int dmult_func(struct pt_regs *regs, u32 ir) +{ + s64 res; + s64 rt, rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = rt * rs; + + regs->lo = res; + __asm__ __volatile__( + "dmuh %0, %1, %2\t\n" + : "=r"(res) + : "r"(rt), "r"(rs)); + + regs->hi = res; + + MIPS_R2_STATS(muls); + + return 0; +} + +/** + * dmultu_func - Emulate a DMULTU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 on success or SIGILL for 32-bit kernels. + */ +static int dmultu_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u64 rt, rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = rt * rs; + + regs->lo = res; + __asm__ __volatile__( + "dmuhu %0, %1, %2\t\n" + : "=r"(res) + : "r"(rt), "r"(rs)); + + regs->hi = res; + + MIPS_R2_STATS(muls); + + return 0; +} + +/** + * ddiv_func - Emulate a DDIV instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 on success or SIGILL for 32-bit kernels. + */ +static int ddiv_func(struct pt_regs *regs, u32 ir) +{ + s64 rt, rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + + regs->lo = rs / rt; + regs->hi = rs % rt; + + MIPS_R2_STATS(divs); + + return 0; +} + +/** + * ddivu_func - Emulate a DDIVU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 on success or SIGILL for 32-bit kernels. + */ +static int ddivu_func(struct pt_regs *regs, u32 ir) +{ + u64 rt, rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + + regs->lo = rs / rt; + regs->hi = rs % rt; + + MIPS_R2_STATS(divs); + + return 0; +} + +/* R6 removed instructions for the SPECIAL opcode */ +static struct r2_decoder_table spec_op_table[] = { + { 0xfc1ff83f, 0x00000008, jr_func }, + { 0xfc00ffff, 0x00000018, mult_func }, + { 0xfc00ffff, 0x00000019, multu_func }, + { 0xfc00ffff, 0x0000001c, dmult_func }, + { 0xfc00ffff, 0x0000001d, dmultu_func }, + { 0xffff07ff, 0x00000010, mfhi_func }, + { 0xfc1fffff, 0x00000011, mthi_func }, + { 0xffff07ff, 0x00000012, mflo_func }, + { 0xfc1fffff, 0x00000013, mtlo_func }, + { 0xfc0307ff, 0x00000001, movf_func }, + { 0xfc0307ff, 0x00010001, movt_func }, + { 0xfc0007ff, 0x0000000a, movz_func }, + { 0xfc0007ff, 0x0000000b, movn_func }, + { 0xfc00ffff, 0x0000001a, div_func }, + { 0xfc00ffff, 0x0000001b, divu_func }, + { 0xfc00ffff, 0x0000001e, ddiv_func }, + { 0xfc00ffff, 0x0000001f, ddivu_func }, + {} +}; + +/** + * madd_func - Emulate a MADD instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int madd_func(struct pt_regs *regs, u32 ir) +{ + s64 res; + s32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (s64)rt * (s64)rs; + rt = regs->hi; + rs = regs->lo; + res += ((((s64)rt) << 32) | (u32)rs); + + rt = res; + regs->lo = (s64)rt; + rs = res >> 32; + regs->hi = (s64)rs; + + MIPS_R2_STATS(dsps); + + return 0; +} + +/** + * maddu_func - Emulate a MADDU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int maddu_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (u64)rt * (u64)rs; + rt = regs->hi; + rs = regs->lo; + res += ((((s64)rt) << 32) | (u32)rs); + + rt = res; + regs->lo = (s64)rt; + rs = res >> 32; + regs->hi = (s64)rs; + + MIPS_R2_STATS(dsps); + + return 0; +} + +/** + * msub_func - Emulate a MSUB instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int msub_func(struct pt_regs *regs, u32 ir) +{ + s64 res; + s32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (s64)rt * (s64)rs; + rt = regs->hi; + rs = regs->lo; + res = ((((s64)rt) << 32) | (u32)rs) - res; + + rt = res; + regs->lo = (s64)rt; + rs = res >> 32; + regs->hi = (s64)rs; + + MIPS_R2_STATS(dsps); + + return 0; +} + +/** + * msubu_func - Emulate a MSUBU instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int msubu_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u32 rt, rs; + + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (u64)rt * (u64)rs; + rt = regs->hi; + rs = regs->lo; + res = ((((s64)rt) << 32) | (u32)rs) - res; + + rt = res; + regs->lo = (s64)rt; + rs = res >> 32; + regs->hi = (s64)rs; + + MIPS_R2_STATS(dsps); + + return 0; +} + +/** + * mul_func - Emulate a MUL instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int mul_func(struct pt_regs *regs, u32 ir) +{ + s64 res; + s32 rt, rs; + + if (!MIPSInst_RD(ir)) + return 0; + rt = regs->regs[MIPSInst_RT(ir)]; + rs = regs->regs[MIPSInst_RS(ir)]; + res = (s64)rt * (s64)rs; + + rs = res; + regs->regs[MIPSInst_RD(ir)] = (s64)rs; + + MIPS_R2_STATS(muls); + + return 0; +} + +/** + * clz_func - Emulate a CLZ instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int clz_func(struct pt_regs *regs, u32 ir) +{ + u32 res; + u32 rs; + + if (!MIPSInst_RD(ir)) + return 0; + + rs = regs->regs[MIPSInst_RS(ir)]; + __asm__ __volatile__("clz %0, %1" : "=r"(res) : "r"(rs)); + regs->regs[MIPSInst_RD(ir)] = res; + + MIPS_R2_STATS(bops); + + return 0; +} + +/** + * clo_func - Emulate a CLO instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ + +static int clo_func(struct pt_regs *regs, u32 ir) +{ + u32 res; + u32 rs; + + if (!MIPSInst_RD(ir)) + return 0; + + rs = regs->regs[MIPSInst_RS(ir)]; + __asm__ __volatile__("clo %0, %1" : "=r"(res) : "r"(rs)); + regs->regs[MIPSInst_RD(ir)] = res; + + MIPS_R2_STATS(bops); + + return 0; +} + +/** + * dclz_func - Emulate a DCLZ instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int dclz_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u64 rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + if (!MIPSInst_RD(ir)) + return 0; + + rs = regs->regs[MIPSInst_RS(ir)]; + __asm__ __volatile__("dclz %0, %1" : "=r"(res) : "r"(rs)); + regs->regs[MIPSInst_RD(ir)] = res; + + MIPS_R2_STATS(bops); + + return 0; +} + +/** + * dclo_func - Emulate a DCLO instruction + * @regs: Process register set + * @ir: Instruction + * + * Returns 0 since it always succeeds. + */ +static int dclo_func(struct pt_regs *regs, u32 ir) +{ + u64 res; + u64 rs; + + if (config_enabled(CONFIG_32BIT)) + return SIGILL; + + if (!MIPSInst_RD(ir)) + return 0; + + rs = regs->regs[MIPSInst_RS(ir)]; + __asm__ __volatile__("dclo %0, %1" : "=r"(res) : "r"(rs)); + regs->regs[MIPSInst_RD(ir)] = res; + + MIPS_R2_STATS(bops); + + return 0; +} + +/* R6 removed instructions for the SPECIAL2 opcode */ +static struct r2_decoder_table spec2_op_table[] = { + { 0xfc00ffff, 0x70000000, madd_func }, + { 0xfc00ffff, 0x70000001, maddu_func }, + { 0xfc0007ff, 0x70000002, mul_func }, + { 0xfc00ffff, 0x70000004, msub_func }, + { 0xfc00ffff, 0x70000005, msubu_func }, + { 0xfc0007ff, 0x70000020, clz_func }, + { 0xfc0007ff, 0x70000021, clo_func }, + { 0xfc0007ff, 0x70000024, dclz_func }, + { 0xfc0007ff, 0x70000025, dclo_func }, + { } +}; + +static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst, + struct r2_decoder_table *table) +{ + struct r2_decoder_table *p; + int err; + + for (p = table; p->func; p++) { + if ((inst & p->mask) == p->code) { + err = (p->func)(regs, inst); + return err; + } + } + return SIGILL; +} + +/** + * mipsr2_decoder: Decode and emulate a MIPS R2 instruction + * @regs: Process register set + * @inst: Instruction to decode and emulate + */ +int mipsr2_decoder(struct pt_regs *regs, u32 inst) +{ + int err = 0; + unsigned long vaddr; + u32 nir; + unsigned long cpc, epc, nepc, r31, res, rs, rt; + + void __user *fault_addr = NULL; + int pass = 0; + +repeat: + r31 = regs->regs[31]; + epc = regs->cp0_epc; + err = compute_return_epc(regs); + if (err < 0) { + BUG(); + return SIGEMT; + } + pr_debug("Emulating the 0x%08x R2 instruction @ 0x%08lx (pass=%d))\n", + inst, epc, pass); + + switch (MIPSInst_OPCODE(inst)) { + case spec_op: + err = mipsr2_find_op_func(regs, inst, spec_op_table); + if (err < 0) { + /* FPU instruction under JR */ + regs->cp0_cause |= CAUSEF_BD; + goto fpu_emul; + } + break; + case spec2_op: + err = mipsr2_find_op_func(regs, inst, spec2_op_table); + break; + case bcond_op: + rt = MIPSInst_RT(inst); + rs = MIPSInst_RS(inst); + switch (rt) { + case tgei_op: + if ((long)regs->regs[rs] >= MIPSInst_SIMM(inst)) + do_trap_or_bp(regs, 0, "TGEI"); + + MIPS_R2_STATS(traps); + + break; + case tgeiu_op: + if (regs->regs[rs] >= MIPSInst_UIMM(inst)) + do_trap_or_bp(regs, 0, "TGEIU"); + + MIPS_R2_STATS(traps); + + break; + case tlti_op: + if ((long)regs->regs[rs] < MIPSInst_SIMM(inst)) + do_trap_or_bp(regs, 0, "TLTI"); + + MIPS_R2_STATS(traps); + + break; + case tltiu_op: + if (regs->regs[rs] < MIPSInst_UIMM(inst)) + do_trap_or_bp(regs, 0, "TLTIU"); + + MIPS_R2_STATS(traps); + + break; + case teqi_op: + if (regs->regs[rs] == MIPSInst_SIMM(inst)) + do_trap_or_bp(regs, 0, "TEQI"); + + MIPS_R2_STATS(traps); + + break; + case tnei_op: + if (regs->regs[rs] != MIPSInst_SIMM(inst)) + do_trap_or_bp(regs, 0, "TNEI"); + + MIPS_R2_STATS(traps); + + break; + case bltzl_op: + case bgezl_op: + case bltzall_op: + case bgezall_op: + if (delay_slot(regs)) { + err = SIGILL; + break; + } + regs->regs[31] = r31; + regs->cp0_epc = epc; + err = __compute_return_epc(regs); + if (err < 0) + return SIGEMT; + if (err != BRANCH_LIKELY_TAKEN) + break; + cpc = regs->cp0_epc; + nepc = epc + 4; + err = __get_user(nir, (u32 __user *)nepc); + if (err) { + err = SIGSEGV; + break; + } + /* + * This will probably be optimized away when + * CONFIG_DEBUG_FS is not enabled + */ + switch (rt) { + case bltzl_op: + MIPS_R2BR_STATS(bltzl); + break; + case bgezl_op: + MIPS_R2BR_STATS(bgezl); + break; + case bltzall_op: + MIPS_R2BR_STATS(bltzall); + break; + case bgezall_op: + MIPS_R2BR_STATS(bgezall); + break; + } + + switch (MIPSInst_OPCODE(nir)) { + case cop1_op: + case cop1x_op: + case lwc1_op: + case swc1_op: + regs->cp0_cause |= CAUSEF_BD; + goto fpu_emul; + } + if (nir) { + err = mipsr6_emul(regs, nir); + if (err > 0) { + err = mips_dsemul(regs, nir, cpc); + if (err == SIGILL) + err = SIGEMT; + MIPS_R2_STATS(dsemul); + } + } + break; + case bltzal_op: + case bgezal_op: + if (delay_slot(regs)) { + err = SIGILL; + break; + } + regs->regs[31] = r31; + regs->cp0_epc = epc; + err = __compute_return_epc(regs); + if (err < 0) + return SIGEMT; + cpc = regs->cp0_epc; + nepc = epc + 4; + err = __get_user(nir, (u32 __user *)nepc); + if (err) { + err = SIGSEGV; + break; + } + /* + * This will probably be optimized away when + * CONFIG_DEBUG_FS is not enabled + */ + switch (rt) { + case bltzal_op: + MIPS_R2BR_STATS(bltzal); + break; + case bgezal_op: + MIPS_R2BR_STATS(bgezal); + break; + } + + switch (MIPSInst_OPCODE(nir)) { + case cop1_op: + case cop1x_op: + case lwc1_op: + case swc1_op: + regs->cp0_cause |= CAUSEF_BD; + goto fpu_emul; + } + if (nir) { + err = mipsr6_emul(regs, nir); + if (err > 0) { + err = mips_dsemul(regs, nir, cpc); + if (err == SIGILL) + err = SIGEMT; + MIPS_R2_STATS(dsemul); + } + } + break; + default: + regs->regs[31] = r31; + regs->cp0_epc = epc; + err = SIGILL; + break; + } + break; + + case beql_op: + case bnel_op: + case blezl_op: + case bgtzl_op: + if (delay_slot(regs)) { + err = SIGILL; + break; + } + regs->regs[31] = r31; + regs->cp0_epc = epc; + err = __compute_return_epc(regs); + if (err < 0) + return SIGEMT; + if (err != BRANCH_LIKELY_TAKEN) + break; + cpc = regs->cp0_epc; + nepc = epc + 4; + err = __get_user(nir, (u32 __user *)nepc); + if (err) { + err = SIGSEGV; + break; + } + /* + * This will probably be optimized away when + * CONFIG_DEBUG_FS is not enabled + */ + switch (MIPSInst_OPCODE(inst)) { + case beql_op: + MIPS_R2BR_STATS(beql); + break; + case bnel_op: + MIPS_R2BR_STATS(bnel); + break; + case blezl_op: + MIPS_R2BR_STATS(blezl); + break; + case bgtzl_op: + MIPS_R2BR_STATS(bgtzl); + break; + } + + switch (MIPSInst_OPCODE(nir)) { + case cop1_op: + case cop1x_op: + case lwc1_op: + case swc1_op: + regs->cp0_cause |= CAUSEF_BD; + goto fpu_emul; + } + if (nir) { + err = mipsr6_emul(regs, nir); + if (err > 0) { + err = mips_dsemul(regs, nir, cpc); + if (err == SIGILL) + err = SIGEMT; + MIPS_R2_STATS(dsemul); + } + } + break; + case lwc1_op: + case swc1_op: + case cop1_op: + case cop1x_op: +fpu_emul: + regs->regs[31] = r31; + regs->cp0_epc = epc; + if (!used_math()) { /* First time FPU user. */ + err = init_fpu(); + set_used_math(); + } + lose_fpu(1); /* Save FPU state for the emulator. */ + + err = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0, + &fault_addr); + + /* + * this is a tricky issue - lose_fpu() uses LL/SC atomics + * if FPU is owned and effectively cancels user level LL/SC. + * So, it could be logical to don't restore FPU ownership here. + * But the sequence of multiple FPU instructions is much much + * more often than LL-FPU-SC and I prefer loop here until + * next scheduler cycle cancels FPU ownership + */ + own_fpu(1); /* Restore FPU state. */ + + if (err) + current->thread.cp0_baduaddr = (unsigned long)fault_addr; + + MIPS_R2_STATS(fpus); + + break; + + case lwl_op: + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_READ, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + "1:" LB "%1, 0(%2)\n" + INS "%0, %1, 24, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "2:" LB "%1, 0(%2)\n" + INS "%0, %1, 16, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "3:" LB "%1, 0(%2)\n" + INS "%0, %1, 8, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "4:" LB "%1, 0(%2)\n" + INS "%0, %1, 0, 8\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + "1:" LB "%1, 0(%2)\n" + INS "%0, %1, 24, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "2:" LB "%1, 0(%2)\n" + INS "%0, %1, 16, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "3:" LB "%1, 0(%2)\n" + INS "%0, %1, 8, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "4:" LB "%1, 0(%2)\n" + INS "%0, %1, 0, 8\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9: sll %0, %0, 0\n" + "10:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 10b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV)); + + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = rt; + + MIPS_R2_STATS(loads); + + break; + + case lwr_op: + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_READ, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + "1:" LB "%1, 0(%2)\n" + INS "%0, %1, 0, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "2:" LB "%1, 0(%2)\n" + INS "%0, %1, 8, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "3:" LB "%1, 0(%2)\n" + INS "%0, %1, 16, 8\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + "4:" LB "%1, 0(%2)\n" + INS "%0, %1, 24, 8\n" + " sll %0, %0, 0\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + "1:" LB "%1, 0(%2)\n" + INS "%0, %1, 0, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "2:" LB "%1, 0(%2)\n" + INS "%0, %1, 8, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "3:" LB "%1, 0(%2)\n" + INS "%0, %1, 16, 8\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + "4:" LB "%1, 0(%2)\n" + INS "%0, %1, 24, 8\n" + " sll %0, %0, 0\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + "10:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 10b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV)); + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = rt; + + MIPS_R2_STATS(loads); + + break; + + case swl_op: + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_WRITE, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + EXT "%1, %0, 24, 8\n" + "1:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 16, 8\n" + "2:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 8, 8\n" + "3:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 0, 8\n" + "4:" SB "%1, 0(%2)\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + EXT "%1, %0, 24, 8\n" + "1:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 16, 8\n" + "2:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 8, 8\n" + "3:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 0, 8\n" + "4:" SB "%1, 0(%2)\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV) + : "memory"); + + MIPS_R2_STATS(stores); + + break; + + case swr_op: + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_WRITE, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + EXT "%1, %0, 0, 8\n" + "1:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 8, 8\n" + "2:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 16, 8\n" + "3:" SB "%1, 0(%2)\n" + ADDIU "%2, %2, 1\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + EXT "%1, %0, 24, 8\n" + "4:" SB "%1, 0(%2)\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + EXT "%1, %0, 0, 8\n" + "1:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 8, 8\n" + "2:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 16, 8\n" + "3:" SB "%1, 0(%2)\n" + " andi %1, %2, 0x3\n" + " beq $0, %1, 9f\n" + ADDIU "%2, %2, -1\n" + EXT "%1, %0, 24, 8\n" + "4:" SB "%1, 0(%2)\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV) + : "memory"); + + MIPS_R2_STATS(stores); + + break; + + case ldl_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_READ, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + "1: lb %1, 0(%2)\n" + " dinsu %0, %1, 56, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "2: lb %1, 0(%2)\n" + " dinsu %0, %1, 48, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "3: lb %1, 0(%2)\n" + " dinsu %0, %1, 40, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "4: lb %1, 0(%2)\n" + " dinsu %0, %1, 32, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "5: lb %1, 0(%2)\n" + " dins %0, %1, 24, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "6: lb %1, 0(%2)\n" + " dins %0, %1, 16, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "7: lb %1, 0(%2)\n" + " dins %0, %1, 8, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "0: lb %1, 0(%2)\n" + " dins %0, %1, 0, 8\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + "1: lb %1, 0(%2)\n" + " dinsu %0, %1, 56, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "2: lb %1, 0(%2)\n" + " dinsu %0, %1, 48, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "3: lb %1, 0(%2)\n" + " dinsu %0, %1, 40, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "4: lb %1, 0(%2)\n" + " dinsu %0, %1, 32, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "5: lb %1, 0(%2)\n" + " dins %0, %1, 24, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "6: lb %1, 0(%2)\n" + " dins %0, %1, 16, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "7: lb %1, 0(%2)\n" + " dins %0, %1, 8, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "0: lb %1, 0(%2)\n" + " dins %0, %1, 0, 8\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .word 5b,8b\n" + " .word 6b,8b\n" + " .word 7b,8b\n" + " .word 0b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV)); + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = rt; + + MIPS_R2_STATS(loads); + break; + + case ldr_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_READ, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + "1: lb %1, 0(%2)\n" + " dins %0, %1, 0, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "2: lb %1, 0(%2)\n" + " dins %0, %1, 8, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "3: lb %1, 0(%2)\n" + " dins %0, %1, 16, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "4: lb %1, 0(%2)\n" + " dins %0, %1, 24, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "5: lb %1, 0(%2)\n" + " dinsu %0, %1, 32, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "6: lb %1, 0(%2)\n" + " dinsu %0, %1, 40, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "7: lb %1, 0(%2)\n" + " dinsu %0, %1, 48, 8\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + "0: lb %1, 0(%2)\n" + " dinsu %0, %1, 56, 8\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + "1: lb %1, 0(%2)\n" + " dins %0, %1, 0, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "2: lb %1, 0(%2)\n" + " dins %0, %1, 8, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "3: lb %1, 0(%2)\n" + " dins %0, %1, 16, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "4: lb %1, 0(%2)\n" + " dins %0, %1, 24, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "5: lb %1, 0(%2)\n" + " dinsu %0, %1, 32, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "6: lb %1, 0(%2)\n" + " dinsu %0, %1, 40, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "7: lb %1, 0(%2)\n" + " dinsu %0, %1, 48, 8\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + "0: lb %1, 0(%2)\n" + " dinsu %0, %1, 56, 8\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .word 5b,8b\n" + " .word 6b,8b\n" + " .word 7b,8b\n" + " .word 0b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV)); + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = rt; + + MIPS_R2_STATS(loads); + break; + + case sdl_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_WRITE, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + " dextu %1, %0, 56, 8\n" + "1: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 48, 8\n" + "2: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 40, 8\n" + "3: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 32, 8\n" + "4: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 24, 8\n" + "5: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 16, 8\n" + "6: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 8, 8\n" + "7: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 0, 8\n" + "0: sb %1, 0(%2)\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + " dextu %1, %0, 56, 8\n" + "1: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 48, 8\n" + "2: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 40, 8\n" + "3: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 32, 8\n" + "4: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 24, 8\n" + "5: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 16, 8\n" + "6: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 8, 8\n" + "7: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 0, 8\n" + "0: sb %1, 0(%2)\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .word 5b,8b\n" + " .word 6b,8b\n" + " .word 7b,8b\n" + " .word 0b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV) + : "memory"); + + MIPS_R2_STATS(stores); + break; + + case sdr_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + rt = regs->regs[MIPSInst_RT(inst)]; + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (!access_ok(VERIFY_WRITE, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGSEGV; + break; + } + __asm__ __volatile__( + " .set push\n" + " .set reorder\n" +#ifdef CONFIG_CPU_LITTLE_ENDIAN + " dext %1, %0, 0, 8\n" + "1: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 8, 8\n" + "2: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 16, 8\n" + "3: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dext %1, %0, 24, 8\n" + "4: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 32, 8\n" + "5: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 40, 8\n" + "6: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 48, 8\n" + "7: sb %1, 0(%2)\n" + " daddiu %2, %2, 1\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " dextu %1, %0, 56, 8\n" + "0: sb %1, 0(%2)\n" +#else /* !CONFIG_CPU_LITTLE_ENDIAN */ + " dext %1, %0, 0, 8\n" + "1: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 8, 8\n" + "2: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 16, 8\n" + "3: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dext %1, %0, 24, 8\n" + "4: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 32, 8\n" + "5: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 40, 8\n" + "6: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 48, 8\n" + "7: sb %1, 0(%2)\n" + " andi %1, %2, 0x7\n" + " beq $0, %1, 9f\n" + " daddiu %2, %2, -1\n" + " dextu %1, %0, 56, 8\n" + "0: sb %1, 0(%2)\n" +#endif /* CONFIG_CPU_LITTLE_ENDIAN */ + "9:\n" + " .insn\n" + " .section .fixup,\"ax\"\n" + "8: li %3,%4\n" + " j 9b\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .word 1b,8b\n" + " .word 2b,8b\n" + " .word 3b,8b\n" + " .word 4b,8b\n" + " .word 5b,8b\n" + " .word 6b,8b\n" + " .word 7b,8b\n" + " .word 0b,8b\n" + " .previous\n" + " .set pop\n" + : "+&r"(rt), "=&r"(rs), + "+&r"(vaddr), "+&r"(err) + : "i"(SIGSEGV) + : "memory"); + + MIPS_R2_STATS(stores); + + break; + case ll_op: + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (vaddr & 0x3) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + if (!access_ok(VERIFY_READ, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + + if (!cpu_has_rw_llb) { + /* + * An LL/SC block can't be safely emulated without + * a Config5/LLB availability. So it's probably time to + * kill our process before things get any worse. This is + * because Config5/LLB allows us to use ERETNC so that + * the LLAddr/LLB bit is not cleared when we return from + * an exception. MIPS R2 LL/SC instructions trap with an + * RI exception so once we emulate them here, we return + * back to userland with ERETNC. That preserves the + * LLAddr/LLB so the subsequent SC instruction will + * succeed preserving the atomic semantics of the LL/SC + * block. Without that, there is no safe way to emulate + * an LL/SC block in MIPSR2 userland. + */ + pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n"); + err = SIGKILL; + break; + } + + __asm__ __volatile__( + "1:\n" + "ll %0, 0(%2)\n" + "2:\n" + ".insn\n" + ".section .fixup,\"ax\"\n" + "3:\n" + "li %1, %3\n" + "j 2b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + ".word 1b, 3b\n" + ".previous\n" + : "=&r"(res), "+&r"(err) + : "r"(vaddr), "i"(SIGSEGV) + : "memory"); + + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = res; + MIPS_R2_STATS(llsc); + + break; + + case sc_op: + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (vaddr & 0x3) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + if (!access_ok(VERIFY_WRITE, vaddr, 4)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + + if (!cpu_has_rw_llb) { + /* + * An LL/SC block can't be safely emulated without + * a Config5/LLB availability. So it's probably time to + * kill our process before things get any worse. This is + * because Config5/LLB allows us to use ERETNC so that + * the LLAddr/LLB bit is not cleared when we return from + * an exception. MIPS R2 LL/SC instructions trap with an + * RI exception so once we emulate them here, we return + * back to userland with ERETNC. That preserves the + * LLAddr/LLB so the subsequent SC instruction will + * succeed preserving the atomic semantics of the LL/SC + * block. Without that, there is no safe way to emulate + * an LL/SC block in MIPSR2 userland. + */ + pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n"); + err = SIGKILL; + break; + } + + res = regs->regs[MIPSInst_RT(inst)]; + + __asm__ __volatile__( + "1:\n" + "sc %0, 0(%2)\n" + "2:\n" + ".insn\n" + ".section .fixup,\"ax\"\n" + "3:\n" + "li %1, %3\n" + "j 2b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + ".word 1b, 3b\n" + ".previous\n" + : "+&r"(res), "+&r"(err) + : "r"(vaddr), "i"(SIGSEGV)); + + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = res; + + MIPS_R2_STATS(llsc); + + break; + + case lld_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (vaddr & 0x7) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + if (!access_ok(VERIFY_READ, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + + if (!cpu_has_rw_llb) { + /* + * An LL/SC block can't be safely emulated without + * a Config5/LLB availability. So it's probably time to + * kill our process before things get any worse. This is + * because Config5/LLB allows us to use ERETNC so that + * the LLAddr/LLB bit is not cleared when we return from + * an exception. MIPS R2 LL/SC instructions trap with an + * RI exception so once we emulate them here, we return + * back to userland with ERETNC. That preserves the + * LLAddr/LLB so the subsequent SC instruction will + * succeed preserving the atomic semantics of the LL/SC + * block. Without that, there is no safe way to emulate + * an LL/SC block in MIPSR2 userland. + */ + pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n"); + err = SIGKILL; + break; + } + + __asm__ __volatile__( + "1:\n" + "lld %0, 0(%2)\n" + "2:\n" + ".insn\n" + ".section .fixup,\"ax\"\n" + "3:\n" + "li %1, %3\n" + "j 2b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + ".word 1b, 3b\n" + ".previous\n" + : "=&r"(res), "+&r"(err) + : "r"(vaddr), "i"(SIGSEGV) + : "memory"); + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = res; + + MIPS_R2_STATS(llsc); + + break; + + case scd_op: + if (config_enabled(CONFIG_32BIT)) { + err = SIGILL; + break; + } + + vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst); + if (vaddr & 0x7) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + if (!access_ok(VERIFY_WRITE, vaddr, 8)) { + current->thread.cp0_baduaddr = vaddr; + err = SIGBUS; + break; + } + + if (!cpu_has_rw_llb) { + /* + * An LL/SC block can't be safely emulated without + * a Config5/LLB availability. So it's probably time to + * kill our process before things get any worse. This is + * because Config5/LLB allows us to use ERETNC so that + * the LLAddr/LLB bit is not cleared when we return from + * an exception. MIPS R2 LL/SC instructions trap with an + * RI exception so once we emulate them here, we return + * back to userland with ERETNC. That preserves the + * LLAddr/LLB so the subsequent SC instruction will + * succeed preserving the atomic semantics of the LL/SC + * block. Without that, there is no safe way to emulate + * an LL/SC block in MIPSR2 userland. + */ + pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n"); + err = SIGKILL; + break; + } + + res = regs->regs[MIPSInst_RT(inst)]; + + __asm__ __volatile__( + "1:\n" + "scd %0, 0(%2)\n" + "2:\n" + ".insn\n" + ".section .fixup,\"ax\"\n" + "3:\n" + "li %1, %3\n" + "j 2b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + ".word 1b, 3b\n" + ".previous\n" + : "+&r"(res), "+&r"(err) + : "r"(vaddr), "i"(SIGSEGV)); + + if (MIPSInst_RT(inst) && !err) + regs->regs[MIPSInst_RT(inst)] = res; + + MIPS_R2_STATS(llsc); + + break; + case pref_op: + /* skip it */ + break; + default: + err = SIGILL; + } + + /* + * Lets not return to userland just yet. It's constly and + * it's likely we have more R2 instructions to emulate + */ + if (!err && (pass++ < MIPS_R2_EMUL_TOTAL_PASS)) { + regs->cp0_cause &= ~CAUSEF_BD; + err = get_user(inst, (u32 __user *)regs->cp0_epc); + if (!err) + goto repeat; + + if (err < 0) + err = SIGSEGV; + } + + if (err && (err != SIGEMT)) { + regs->regs[31] = r31; + regs->cp0_epc = epc; + } + + /* Likely a MIPS R6 compatible instruction */ + if (pass && (err == SIGILL)) + err = 0; + + return err; +} + +#ifdef CONFIG_DEBUG_FS + +static int mipsr2_stats_show(struct seq_file *s, void *unused) +{ + + seq_printf(s, "Instruction\tTotal\tBDslot\n------------------------------\n"); + seq_printf(s, "movs\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.movs), + (unsigned long)__this_cpu_read(mipsr2bdemustats.movs)); + seq_printf(s, "hilo\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.hilo), + (unsigned long)__this_cpu_read(mipsr2bdemustats.hilo)); + seq_printf(s, "muls\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.muls), + (unsigned long)__this_cpu_read(mipsr2bdemustats.muls)); + seq_printf(s, "divs\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.divs), + (unsigned long)__this_cpu_read(mipsr2bdemustats.divs)); + seq_printf(s, "dsps\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.dsps), + (unsigned long)__this_cpu_read(mipsr2bdemustats.dsps)); + seq_printf(s, "bops\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.bops), + (unsigned long)__this_cpu_read(mipsr2bdemustats.bops)); + seq_printf(s, "traps\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.traps), + (unsigned long)__this_cpu_read(mipsr2bdemustats.traps)); + seq_printf(s, "fpus\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.fpus), + (unsigned long)__this_cpu_read(mipsr2bdemustats.fpus)); + seq_printf(s, "loads\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.loads), + (unsigned long)__this_cpu_read(mipsr2bdemustats.loads)); + seq_printf(s, "stores\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.stores), + (unsigned long)__this_cpu_read(mipsr2bdemustats.stores)); + seq_printf(s, "llsc\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.llsc), + (unsigned long)__this_cpu_read(mipsr2bdemustats.llsc)); + seq_printf(s, "dsemul\t\t%ld\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2emustats.dsemul), + (unsigned long)__this_cpu_read(mipsr2bdemustats.dsemul)); + seq_printf(s, "jr\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.jrs)); + seq_printf(s, "bltzl\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bltzl)); + seq_printf(s, "bgezl\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bgezl)); + seq_printf(s, "bltzll\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bltzll)); + seq_printf(s, "bgezll\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bgezll)); + seq_printf(s, "bltzal\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bltzal)); + seq_printf(s, "bgezal\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bgezal)); + seq_printf(s, "beql\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.beql)); + seq_printf(s, "bnel\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bnel)); + seq_printf(s, "blezl\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.blezl)); + seq_printf(s, "bgtzl\t\t%ld\n", + (unsigned long)__this_cpu_read(mipsr2bremustats.bgtzl)); + + return 0; +} + +static int mipsr2_stats_clear_show(struct seq_file *s, void *unused) +{ + mipsr2_stats_show(s, unused); + + __this_cpu_write((mipsr2emustats).movs, 0); + __this_cpu_write((mipsr2bdemustats).movs, 0); + __this_cpu_write((mipsr2emustats).hilo, 0); + __this_cpu_write((mipsr2bdemustats).hilo, 0); + __this_cpu_write((mipsr2emustats).muls, 0); + __this_cpu_write((mipsr2bdemustats).muls, 0); + __this_cpu_write((mipsr2emustats).divs, 0); + __this_cpu_write((mipsr2bdemustats).divs, 0); + __this_cpu_write((mipsr2emustats).dsps, 0); + __this_cpu_write((mipsr2bdemustats).dsps, 0); + __this_cpu_write((mipsr2emustats).bops, 0); + __this_cpu_write((mipsr2bdemustats).bops, 0); + __this_cpu_write((mipsr2emustats).traps, 0); + __this_cpu_write((mipsr2bdemustats).traps, 0); + __this_cpu_write((mipsr2emustats).fpus, 0); + __this_cpu_write((mipsr2bdemustats).fpus, 0); + __this_cpu_write((mipsr2emustats).loads, 0); + __this_cpu_write((mipsr2bdemustats).loads, 0); + __this_cpu_write((mipsr2emustats).stores, 0); + __this_cpu_write((mipsr2bdemustats).stores, 0); + __this_cpu_write((mipsr2emustats).llsc, 0); + __this_cpu_write((mipsr2bdemustats).llsc, 0); + __this_cpu_write((mipsr2emustats).dsemul, 0); + __this_cpu_write((mipsr2bdemustats).dsemul, 0); + __this_cpu_write((mipsr2bremustats).jrs, 0); + __this_cpu_write((mipsr2bremustats).bltzl, 0); + __this_cpu_write((mipsr2bremustats).bgezl, 0); + __this_cpu_write((mipsr2bremustats).bltzll, 0); + __this_cpu_write((mipsr2bremustats).bgezll, 0); + __this_cpu_write((mipsr2bremustats).bltzal, 0); + __this_cpu_write((mipsr2bremustats).bgezal, 0); + __this_cpu_write((mipsr2bremustats).beql, 0); + __this_cpu_write((mipsr2bremustats).bnel, 0); + __this_cpu_write((mipsr2bremustats).blezl, 0); + __this_cpu_write((mipsr2bremustats).bgtzl, 0); + + return 0; +} + +static int mipsr2_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, mipsr2_stats_show, inode->i_private); +} + +static int mipsr2_stats_clear_open(struct inode *inode, struct file *file) +{ + return single_open(file, mipsr2_stats_clear_show, inode->i_private); +} + +static const struct file_operations mipsr2_emul_fops = { + .open = mipsr2_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations mipsr2_clear_fops = { + .open = mipsr2_stats_clear_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + + +static int __init mipsr2_init_debugfs(void) +{ + extern struct dentry *mips_debugfs_dir; + struct dentry *mipsr2_emul; + + if (!mips_debugfs_dir) + return -ENODEV; + + mipsr2_emul = debugfs_create_file("r2_emul_stats", S_IRUGO, + mips_debugfs_dir, NULL, + &mipsr2_emul_fops); + if (!mipsr2_emul) + return -ENOMEM; + + mipsr2_emul = debugfs_create_file("r2_emul_stats_clear", S_IRUGO, + mips_debugfs_dir, NULL, + &mipsr2_clear_fops); + if (!mipsr2_emul) + return -ENOMEM; + + return 0; +} + +device_initcall(mipsr2_init_debugfs); + +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 17eaf0cf760c..291af0b5c482 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -14,6 +14,8 @@ #include <linux/mm.h> #include <asm/uaccess.h> #include <asm/ftrace.h> +#include <asm/fpu.h> +#include <asm/msa.h> extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_kernel_nocheck_asm(char *__to, @@ -32,6 +34,14 @@ extern long __strnlen_user_nocheck_asm(const char *s); extern long __strnlen_user_asm(const char *s); /* + * Core architecture code + */ +EXPORT_SYMBOL_GPL(_save_fp); +#ifdef CONFIG_CPU_HAS_MSA +EXPORT_SYMBOL_GPL(_save_msa); +#endif + +/* * String functions */ EXPORT_SYMBOL(memset); @@ -67,11 +77,13 @@ EXPORT_SYMBOL(__strnlen_kernel_asm); EXPORT_SYMBOL(__strnlen_user_nocheck_asm); EXPORT_SYMBOL(__strnlen_user_asm); +#ifndef CONFIG_CPU_MIPSR6 EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_nocheck); EXPORT_SYMBOL(__csum_partial_copy_kernel); EXPORT_SYMBOL(__csum_partial_copy_to_user); EXPORT_SYMBOL(__csum_partial_copy_from_user); +#endif EXPORT_SYMBOL(invalid_pte_table); #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index f6547680c81c..423ae83af1fb 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -31,15 +31,11 @@ /* * check if we need to save FPU registers */ - PTR_L t3, TASK_THREAD_INFO(a0) - LONG_L t0, TI_FLAGS(t3) - li t1, _TIF_USEDFPU - and t2, t0, t1 - beqz t2, 1f - nor t1, zero, t1 - - and t0, t0, t1 - LONG_S t0, TI_FLAGS(t3) + .set push + .set noreorder + beqz a3, 1f + PTR_L t3, TASK_THREAD_INFO(a0) + .set pop /* * clear saved user stack CU1 bit @@ -56,36 +52,9 @@ .set pop 1: - /* check if we need to save COP2 registers */ - PTR_L t2, TASK_THREAD_INFO(a0) - LONG_L t0, ST_OFF(t2) - bbit0 t0, 30, 1f - - /* Disable COP2 in the stored process state */ - li t1, ST0_CU2 - xor t0, t1 - LONG_S t0, ST_OFF(t2) - - /* Enable COP2 so we can save it */ - mfc0 t0, CP0_STATUS - or t0, t1 - mtc0 t0, CP0_STATUS - - /* Save COP2 */ - daddu a0, THREAD_CP2 - jal octeon_cop2_save - dsubu a0, THREAD_CP2 - - /* Disable COP2 now that we are done */ - mfc0 t0, CP0_STATUS - li t1, ST0_CU2 - xor t0, t1 - mtc0 t0, CP0_STATUS - -1: #if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 /* Check if we need to store CVMSEG state */ - mfc0 t0, $11,7 /* CvmMemCtl */ + dmfc0 t0, $11,7 /* CvmMemCtl */ bbit0 t0, 6, 3f /* Is user access enabled? */ /* Store the CVMSEG state */ @@ -109,9 +78,9 @@ .set reorder /* Disable access to CVMSEG */ - mfc0 t0, $11,7 /* CvmMemCtl */ + dmfc0 t0, $11,7 /* CvmMemCtl */ xori t0, t0, 0x40 /* Bit 6 is CVMSEG user enable */ - mtc0 t0, $11,7 /* CvmMemCtl */ + dmtc0 t0, $11,7 /* CvmMemCtl */ #endif 3: @@ -147,6 +116,8 @@ * void octeon_cop2_save(struct octeon_cop2_state *a0) */ .align 7 + .set push + .set noreorder LEAF(octeon_cop2_save) dmfc0 t9, $9,7 /* CvmCtl register. */ @@ -157,17 +128,17 @@ dmfc2 t2, 0x0200 sd t0, OCTEON_CP2_CRC_IV(a0) sd t1, OCTEON_CP2_CRC_LENGTH(a0) - sd t2, OCTEON_CP2_CRC_POLY(a0) /* Skip next instructions if CvmCtl[NODFA_CP2] set */ bbit1 t9, 28, 1f + sd t2, OCTEON_CP2_CRC_POLY(a0) /* Save the LLM state */ dmfc2 t0, 0x0402 dmfc2 t1, 0x040A sd t0, OCTEON_CP2_LLM_DAT(a0) - sd t1, OCTEON_CP2_LLM_DAT+8(a0) 1: bbit1 t9, 26, 3f /* done if CvmCtl[NOCRYPTO] set */ + sd t1, OCTEON_CP2_LLM_DAT+8(a0) /* Save the COP2 crypto state */ /* this part is mostly common to both pass 1 and later revisions */ @@ -198,18 +169,20 @@ sd t2, OCTEON_CP2_AES_KEY+16(a0) dmfc2 t2, 0x0101 sd t3, OCTEON_CP2_AES_KEY+24(a0) - mfc0 t3, $15,0 /* Get the processor ID register */ + mfc0 v0, $15,0 /* Get the processor ID register */ sd t0, OCTEON_CP2_AES_KEYLEN(a0) - li t0, 0x000d0000 /* This is the processor ID of Octeon Pass1 */ + li v1, 0x000d0000 /* This is the processor ID of Octeon Pass1 */ sd t1, OCTEON_CP2_AES_RESULT(a0) - sd t2, OCTEON_CP2_AES_RESULT+8(a0) /* Skip to the Pass1 version of the remainder of the COP2 state */ - beq t3, t0, 2f + beq v0, v1, 2f + sd t2, OCTEON_CP2_AES_RESULT+8(a0) /* the non-pass1 state when !CvmCtl[NOCRYPTO] */ dmfc2 t1, 0x0240 dmfc2 t2, 0x0241 + ori v1, v1, 0x9500 /* lowest OCTEON III PrId*/ dmfc2 t3, 0x0242 + subu v1, v0, v1 /* prid - lowest OCTEON III PrId */ dmfc2 t0, 0x0243 sd t1, OCTEON_CP2_HSH_DATW(a0) dmfc2 t1, 0x0244 @@ -262,8 +235,16 @@ sd t1, OCTEON_CP2_GFM_MULT+8(a0) sd t2, OCTEON_CP2_GFM_POLY(a0) sd t3, OCTEON_CP2_GFM_RESULT(a0) - sd t0, OCTEON_CP2_GFM_RESULT+8(a0) + bltz v1, 4f + sd t0, OCTEON_CP2_GFM_RESULT+8(a0) + /* OCTEON III things*/ + dmfc2 t0, 0x024F + dmfc2 t1, 0x0050 + sd t0, OCTEON_CP2_SHA3(a0) + sd t1, OCTEON_CP2_SHA3+8(a0) +4: jr ra + nop 2: /* pass 1 special stuff when !CvmCtl[NOCRYPTO] */ dmfc2 t3, 0x0040 @@ -289,7 +270,9 @@ 3: /* pass 1 or CvmCtl[NOCRYPTO] set */ jr ra + nop END(octeon_cop2_save) + .set pop /* * void octeon_cop2_restore(struct octeon_cop2_state *a0) @@ -354,9 +337,9 @@ ld t2, OCTEON_CP2_AES_RESULT+8(a0) mfc0 t3, $15,0 /* Get the processor ID register */ dmtc2 t0, 0x0110 - li t0, 0x000d0000 /* This is the processor ID of Octeon Pass1 */ + li v0, 0x000d0000 /* This is the processor ID of Octeon Pass1 */ dmtc2 t1, 0x0100 - bne t0, t3, 3f /* Skip the next stuff for non-pass1 */ + bne v0, t3, 3f /* Skip the next stuff for non-pass1 */ dmtc2 t2, 0x0101 /* this code is specific for pass 1 */ @@ -384,6 +367,7 @@ 3: /* this is post-pass1 code */ ld t2, OCTEON_CP2_HSH_DATW(a0) + ori v0, v0, 0x9500 /* lowest OCTEON III PrId*/ ld t0, OCTEON_CP2_HSH_DATW+8(a0) ld t1, OCTEON_CP2_HSH_DATW+16(a0) dmtc2 t2, 0x0240 @@ -437,9 +421,15 @@ dmtc2 t2, 0x0259 ld t2, OCTEON_CP2_GFM_RESULT+8(a0) dmtc2 t0, 0x025E + subu v0, t3, v0 /* prid - lowest OCTEON III PrId */ dmtc2 t1, 0x025A - dmtc2 t2, 0x025B - + bltz v0, done_restore + dmtc2 t2, 0x025B + /* OCTEON III things*/ + ld t0, OCTEON_CP2_SHA3(a0) + ld t1, OCTEON_CP2_SHA3+8(a0) + dmtc2 t0, 0x0051 + dmtc2 t1, 0x0050 done_restore: jr ra nop @@ -450,18 +440,23 @@ done_restore: * void octeon_mult_save() * sp is assumed to point to a struct pt_regs * - * NOTE: This is called in SAVE_SOME in stackframe.h. It can only - * safely modify k0 and k1. + * NOTE: This is called in SAVE_TEMP in stackframe.h. It can + * safely modify v1,k0, k1,$10-$15, and $24. It will + * be overwritten with a processor specific version of the code. */ - .align 7 + .p2align 7 .set push .set noreorder LEAF(octeon_mult_save) - dmfc0 k0, $9,7 /* CvmCtl register. */ - bbit1 k0, 27, 1f /* Skip CvmCtl[NOMUL] */ + jr ra nop + .space 30 * 4, 0 +octeon_mult_save_end: + EXPORT(octeon_mult_save_end) + END(octeon_mult_save) - /* Save the multiplier state */ + LEAF(octeon_mult_save2) + /* Save the multiplier state OCTEON II and earlier*/ v3mulu k0, $0, $0 v3mulu k1, $0, $0 sd k0, PT_MTP(sp) /* PT_MTP has P0 */ @@ -476,44 +471,107 @@ done_restore: sd k0, PT_MPL+8(sp) /* PT_MPL+8 has MPL1 */ jr ra sd k1, PT_MPL+16(sp) /* PT_MPL+16 has MPL2 */ - -1: /* Resume here if CvmCtl[NOMUL] */ +octeon_mult_save2_end: + EXPORT(octeon_mult_save2_end) + END(octeon_mult_save2) + + LEAF(octeon_mult_save3) + /* Save the multiplier state OCTEON III */ + v3mulu $10, $0, $0 /* read P0 */ + v3mulu $11, $0, $0 /* read P1 */ + v3mulu $12, $0, $0 /* read P2 */ + sd $10, PT_MTP+(0*8)(sp) /* store P0 */ + v3mulu $10, $0, $0 /* read P3 */ + sd $11, PT_MTP+(1*8)(sp) /* store P1 */ + v3mulu $11, $0, $0 /* read P4 */ + sd $12, PT_MTP+(2*8)(sp) /* store P2 */ + ori $13, $0, 1 + v3mulu $12, $0, $0 /* read P5 */ + sd $10, PT_MTP+(3*8)(sp) /* store P3 */ + v3mulu $13, $13, $0 /* P4-P0 = MPL5-MPL1, $13 = MPL0 */ + sd $11, PT_MTP+(4*8)(sp) /* store P4 */ + v3mulu $10, $0, $0 /* read MPL1 */ + sd $12, PT_MTP+(5*8)(sp) /* store P5 */ + v3mulu $11, $0, $0 /* read MPL2 */ + sd $13, PT_MPL+(0*8)(sp) /* store MPL0 */ + v3mulu $12, $0, $0 /* read MPL3 */ + sd $10, PT_MPL+(1*8)(sp) /* store MPL1 */ + v3mulu $10, $0, $0 /* read MPL4 */ + sd $11, PT_MPL+(2*8)(sp) /* store MPL2 */ + v3mulu $11, $0, $0 /* read MPL5 */ + sd $12, PT_MPL+(3*8)(sp) /* store MPL3 */ + sd $10, PT_MPL+(4*8)(sp) /* store MPL4 */ jr ra - END(octeon_mult_save) + sd $11, PT_MPL+(5*8)(sp) /* store MPL5 */ +octeon_mult_save3_end: + EXPORT(octeon_mult_save3_end) + END(octeon_mult_save3) .set pop /* * void octeon_mult_restore() * sp is assumed to point to a struct pt_regs * - * NOTE: This is called in RESTORE_SOME in stackframe.h. + * NOTE: This is called in RESTORE_TEMP in stackframe.h. */ - .align 7 + .p2align 7 .set push .set noreorder LEAF(octeon_mult_restore) - dmfc0 k1, $9,7 /* CvmCtl register. */ - ld v0, PT_MPL(sp) /* MPL0 */ - ld v1, PT_MPL+8(sp) /* MPL1 */ - ld k0, PT_MPL+16(sp) /* MPL2 */ - bbit1 k1, 27, 1f /* Skip CvmCtl[NOMUL] */ - /* Normally falls through, so no time wasted here */ - nop + jr ra + nop + .space 30 * 4, 0 +octeon_mult_restore_end: + EXPORT(octeon_mult_restore_end) + END(octeon_mult_restore) + LEAF(octeon_mult_restore2) + ld v0, PT_MPL(sp) /* MPL0 */ + ld v1, PT_MPL+8(sp) /* MPL1 */ + ld k0, PT_MPL+16(sp) /* MPL2 */ /* Restore the multiplier state */ - ld k1, PT_MTP+16(sp) /* P2 */ - MTM0 v0 /* MPL0 */ + ld k1, PT_MTP+16(sp) /* P2 */ + mtm0 v0 /* MPL0 */ ld v0, PT_MTP+8(sp) /* P1 */ - MTM1 v1 /* MPL1 */ - ld v1, PT_MTP(sp) /* P0 */ - MTM2 k0 /* MPL2 */ - MTP2 k1 /* P2 */ - MTP1 v0 /* P1 */ + mtm1 v1 /* MPL1 */ + ld v1, PT_MTP(sp) /* P0 */ + mtm2 k0 /* MPL2 */ + mtp2 k1 /* P2 */ + mtp1 v0 /* P1 */ jr ra - MTP0 v1 /* P0 */ - -1: /* Resume here if CvmCtl[NOMUL] */ + mtp0 v1 /* P0 */ +octeon_mult_restore2_end: + EXPORT(octeon_mult_restore2_end) + END(octeon_mult_restore2) + + LEAF(octeon_mult_restore3) + ld $12, PT_MPL+(0*8)(sp) /* read MPL0 */ + ld $13, PT_MPL+(3*8)(sp) /* read MPL3 */ + ld $10, PT_MPL+(1*8)(sp) /* read MPL1 */ + ld $11, PT_MPL+(4*8)(sp) /* read MPL4 */ + .word 0x718d0008 + /* mtm0 $12, $13 restore MPL0 and MPL3 */ + ld $12, PT_MPL+(2*8)(sp) /* read MPL2 */ + .word 0x714b000c + /* mtm1 $10, $11 restore MPL1 and MPL4 */ + ld $13, PT_MPL+(5*8)(sp) /* read MPL5 */ + ld $10, PT_MTP+(0*8)(sp) /* read P0 */ + ld $11, PT_MTP+(3*8)(sp) /* read P3 */ + .word 0x718d000d + /* mtm2 $12, $13 restore MPL2 and MPL5 */ + ld $12, PT_MTP+(1*8)(sp) /* read P1 */ + .word 0x714b0009 + /* mtp0 $10, $11 restore P0 and P3 */ + ld $13, PT_MTP+(4*8)(sp) /* read P4 */ + ld $10, PT_MTP+(2*8)(sp) /* read P2 */ + ld $11, PT_MTP+(5*8)(sp) /* read P5 */ + .word 0x718d000a + /* mtp1 $12, $13 restore P1 and P4 */ jr ra - nop - END(octeon_mult_restore) + .word 0x714b000b + /* mtp2 $10, $11 restore P2 and P5 */ + +octeon_mult_restore3_end: + EXPORT(octeon_mult_restore3_end) + END(octeon_mult_restore3) .set pop diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 097fc8d14e42..130af7d26a9c 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -82,7 +82,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "]\n"); } - seq_printf(m, "isa\t\t\t: mips1"); + seq_printf(m, "isa\t\t\t:"); + if (cpu_has_mips_r1) + seq_printf(m, " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); if (cpu_has_mips_3) @@ -95,10 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "%s", " mips32r1"); if (cpu_has_mips32r2) seq_printf(m, "%s", " mips32r2"); + if (cpu_has_mips32r6) + seq_printf(m, "%s", " mips32r6"); if (cpu_has_mips64r1) seq_printf(m, "%s", " mips64r1"); if (cpu_has_mips64r2) seq_printf(m, "%s", " mips64r2"); + if (cpu_has_mips64r6) + seq_printf(m, "%s", " mips64r6"); seq_printf(m, "\n"); seq_printf(m, "ASEs implemented\t:"); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 85bff5d513e5..bf85cc180d91 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/completion.h> #include <linux/kallsyms.h> #include <linux/random.h> +#include <linux/prctl.h> #include <asm/asm.h> #include <asm/bootinfo.h> @@ -562,3 +563,98 @@ void arch_trigger_all_cpu_backtrace(bool include_self) { smp_call_function(arch_dump_stack, NULL, 1); } + +int mips_get_process_fp_mode(struct task_struct *task) +{ + int value = 0; + + if (!test_tsk_thread_flag(task, TIF_32BIT_FPREGS)) + value |= PR_FP_MODE_FR; + if (test_tsk_thread_flag(task, TIF_HYBRID_FPREGS)) + value |= PR_FP_MODE_FRE; + + return value; +} + +int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) +{ + const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE; + unsigned long switch_count; + struct task_struct *t; + + /* Check the value is valid */ + if (value & ~known_bits) + return -EOPNOTSUPP; + + /* Avoid inadvertently triggering emulation */ + if ((value & PR_FP_MODE_FR) && cpu_has_fpu && + !(current_cpu_data.fpu_id & MIPS_FPIR_F64)) + return -EOPNOTSUPP; + if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre) + return -EOPNOTSUPP; + + /* FR = 0 not supported in MIPS R6 */ + if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6) + return -EOPNOTSUPP; + + /* Save FP & vector context, then disable FPU & MSA */ + if (task->signal == current->signal) + lose_fpu(1); + + /* Prevent any threads from obtaining live FP context */ + atomic_set(&task->mm->context.fp_mode_switching, 1); + smp_mb__after_atomic(); + + /* + * If there are multiple online CPUs then wait until all threads whose + * FP mode is about to change have been context switched. This approach + * allows us to only worry about whether an FP mode switch is in + * progress when FP is first used in a tasks time slice. Pretty much all + * of the mode switch overhead can thus be confined to cases where mode + * switches are actually occuring. That is, to here. However for the + * thread performing the mode switch it may take a while... + */ + if (num_online_cpus() > 1) { + spin_lock_irq(&task->sighand->siglock); + + for_each_thread(task, t) { + if (t == current) + continue; + + switch_count = t->nvcsw + t->nivcsw; + + do { + spin_unlock_irq(&task->sighand->siglock); + cond_resched(); + spin_lock_irq(&task->sighand->siglock); + } while ((t->nvcsw + t->nivcsw) == switch_count); + } + + spin_unlock_irq(&task->sighand->siglock); + } + + /* + * There are now no threads of the process with live FP context, so it + * is safe to proceed with the FP mode switch. + */ + for_each_thread(task, t) { + /* Update desired FP register width */ + if (value & PR_FP_MODE_FR) { + clear_tsk_thread_flag(t, TIF_32BIT_FPREGS); + } else { + set_tsk_thread_flag(t, TIF_32BIT_FPREGS); + clear_tsk_thread_flag(t, TIF_MSA_CTX_LIVE); + } + + /* Update desired FP single layout */ + if (value & PR_FP_MODE_FRE) + set_tsk_thread_flag(t, TIF_HYBRID_FPREGS); + else + clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS); + } + + /* Allow threads to use FP again */ + atomic_set(&task->mm->context.fp_mode_switching, 0); + + return 0; +} diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index 6c160c67984c..676c5030a953 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -34,7 +34,7 @@ .endm .set noreorder - .set arch=r4000 + .set MIPS_ISA_ARCH_LEVEL_RAW LEAF(_save_fp_context) .set push @@ -42,7 +42,8 @@ LEAF(_save_fp_context) cfc1 t1, fcr31 .set pop -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ + defined(CONFIG_CPU_MIPS32_R6) .set push SET_HARDFLOAT #ifdef CONFIG_CPU_MIPS32_R2 @@ -105,10 +106,12 @@ LEAF(_save_fp_context32) SET_HARDFLOAT cfc1 t1, fcr31 +#ifndef CONFIG_CPU_MIPS64_R6 mfc0 t0, CP0_STATUS sll t0, t0, 5 bgez t0, 1f # skip storing odd if FR=0 nop +#endif /* Store the 16 odd double precision registers */ EX sdc1 $f1, SC32_FPREGS+8(a0) @@ -163,7 +166,8 @@ LEAF(_save_fp_context32) LEAF(_restore_fp_context) EX lw t1, SC_FPC_CSR(a0) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ + defined(CONFIG_CPU_MIPS32_R6) .set push SET_HARDFLOAT #ifdef CONFIG_CPU_MIPS32_R2 @@ -223,10 +227,12 @@ LEAF(_restore_fp_context32) SET_HARDFLOAT EX lw t1, SC32_FPC_CSR(a0) +#ifndef CONFIG_CPU_MIPS64_R6 mfc0 t0, CP0_STATUS sll t0, t0, 5 bgez t0, 1f # skip loading odd if FR=0 nop +#endif EX ldc1 $f1, SC32_FPREGS+8(a0) EX ldc1 $f3, SC32_FPREGS+24(a0) diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S index 64591e671878..3b1a36f13a7d 100644 --- a/arch/mips/kernel/r4k_switch.S +++ b/arch/mips/kernel/r4k_switch.S @@ -115,7 +115,8 @@ * Save a thread's fp context. */ LEAF(_save_fp) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ + defined(CONFIG_CPU_MIPS32_R6) mfc0 t0, CP0_STATUS #endif fpu_save_double a0 t0 t1 # clobbers t1 @@ -126,7 +127,8 @@ LEAF(_save_fp) * Restore a thread's fp context. */ LEAF(_restore_fp) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ + defined(CONFIG_CPU_MIPS32_R6) mfc0 t0, CP0_STATUS #endif fpu_restore_double a0 t0 t1 # clobbers t1 @@ -240,9 +242,9 @@ LEAF(_init_fpu) mtc1 t1, $f30 mtc1 t1, $f31 -#ifdef CONFIG_CPU_MIPS32_R2 +#if defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) .set push - .set mips32r2 + .set MIPS_ISA_LEVEL_RAW .set fp=64 sll t0, t0, 5 # is Status.FR set? bgez t0, 1f # no: skip setting upper 32b @@ -280,9 +282,9 @@ LEAF(_init_fpu) mthc1 t1, $f30 mthc1 t1, $f31 1: .set pop -#endif /* CONFIG_CPU_MIPS32_R2 */ +#endif /* CONFIG_CPU_MIPS32_R2 || CONFIG_CPU_MIPS32_R6 */ #else - .set arch=r4000 + .set MIPS_ISA_ARCH_LEVEL_RAW dmtc1 t1, $f0 dmtc1 t1, $f2 dmtc1 t1, $f4 diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c index 67f2495def1c..d1168d7c31e8 100644 --- a/arch/mips/kernel/spram.c +++ b/arch/mips/kernel/spram.c @@ -208,6 +208,7 @@ void spram_config(void) case CPU_INTERAPTIV: case CPU_PROAPTIV: case CPU_P5600: + case CPU_QEMU_GENERIC: config0 = read_c0_config(); /* FIXME: addresses are Malta specific */ if (config0 & (1<<24)) { diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 604b558809c4..53a7ef9a8f32 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -136,7 +136,7 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) : "memory"); } else if (cpu_has_llsc) { __asm__ __volatile__ ( - " .set arch=r4000 \n" + " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" "1: ll %[old], (%[addr]) \n" " move %[tmp], %[new] \n" diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index c3b41e24c05a..33984c04b60b 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -46,6 +46,7 @@ #include <asm/fpu.h> #include <asm/fpu_emulator.h> #include <asm/idle.h> +#include <asm/mips-r2-to-r6-emul.h> #include <asm/mipsregs.h> #include <asm/mipsmtregs.h> #include <asm/module.h> @@ -837,7 +838,7 @@ out: exception_exit(prev_state); } -static void do_trap_or_bp(struct pt_regs *regs, unsigned int code, +void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { siginfo_t info; @@ -1027,7 +1028,34 @@ asmlinkage void do_ri(struct pt_regs *regs) unsigned int opcode = 0; int status = -1; + /* + * Avoid any kernel code. Just emulate the R2 instruction + * as quickly as possible. + */ + if (mipsr2_emulation && cpu_has_mips_r6 && + likely(user_mode(regs))) { + if (likely(get_user(opcode, epc) >= 0)) { + status = mipsr2_decoder(regs, opcode); + switch (status) { + case 0: + case SIGEMT: + task_thread_info(current)->r2_emul_return = 1; + return; + case SIGILL: + goto no_r2_instr; + default: + process_fpemu_return(status, + ¤t->thread.cp0_baduaddr); + task_thread_info(current)->r2_emul_return = 1; + return; + } + } + } + +no_r2_instr: + prev_state = exception_enter(); + if (notify_die(DIE_RI, "RI Fault", regs, 0, regs_to_trapnr(regs), SIGILL) == NOTIFY_STOP) goto out; @@ -1134,10 +1162,29 @@ static int default_cu2_call(struct notifier_block *nfb, unsigned long action, return NOTIFY_OK; } +static int wait_on_fp_mode_switch(atomic_t *p) +{ + /* + * The FP mode for this task is currently being switched. That may + * involve modifications to the format of this tasks FP context which + * make it unsafe to proceed with execution for the moment. Instead, + * schedule some other task. + */ + schedule(); + return 0; +} + static int enable_restore_fp_context(int msa) { int err, was_fpu_owner, prior_msa; + /* + * If an FP mode switch is currently underway, wait for it to + * complete before proceeding. + */ + wait_on_atomic_t(¤t->mm->context.fp_mode_switching, + wait_on_fp_mode_switch, TASK_KILLABLE); + if (!used_math()) { /* First time FP context user. */ preempt_disable(); @@ -1541,6 +1588,7 @@ static inline void parity_protection_init(void) case CPU_INTERAPTIV: case CPU_PROAPTIV: case CPU_P5600: + case CPU_QEMU_GENERIC: { #define ERRCTL_PE 0x80000000 #define ERRCTL_L2P 0x00800000 @@ -1630,7 +1678,7 @@ asmlinkage void cache_parity_error(void) printk("Decoded c0_cacheerr: %s cache fault in %s reference.\n", reg_val & (1<<30) ? "secondary" : "primary", reg_val & (1<<31) ? "data" : "insn"); - if (cpu_has_mips_r2 && + if ((cpu_has_mips_r2_r6) && ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) { pr_err("Error bits: %s%s%s%s%s%s%s%s\n", reg_val & (1<<29) ? "ED " : "", @@ -1670,7 +1718,7 @@ asmlinkage void do_ftlb(void) unsigned int reg_val; /* For the moment, report the problem and hang. */ - if (cpu_has_mips_r2 && + if ((cpu_has_mips_r2_r6) && ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) { pr_err("FTLB error exception, cp0_ecc=0x%08x:\n", read_c0_ecc()); @@ -1959,7 +2007,7 @@ static void configure_hwrena(void) { unsigned int hwrena = cpu_hwrena_impl_bits; - if (cpu_has_mips_r2) + if (cpu_has_mips_r2_r6) hwrena |= 0x0000000f; if (!noulri && cpu_has_userlocal) @@ -2003,7 +2051,7 @@ void per_cpu_trap_init(bool is_boot_cpu) * o read IntCtl.IPTI to determine the timer interrupt * o read IntCtl.IPPCI to determine the performance counter interrupt */ - if (cpu_has_mips_r2) { + if (cpu_has_mips_r2_r6) { cp0_compare_irq_shift = CAUSEB_TI - CAUSEB_IP; cp0_compare_irq = (read_c0_intctl() >> INTCTLB_IPTI) & 7; cp0_perfcount_irq = (read_c0_intctl() >> INTCTLB_IPPCI) & 7; @@ -2094,7 +2142,7 @@ void __init trap_init(void) #else ebase = CKSEG0; #endif - if (cpu_has_mips_r2) + if (cpu_has_mips_r2_r6) ebase += (read_c0_ebase() & 0x3ffff000); } diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index e11906dff885..bbb69695a0a1 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -129,6 +129,7 @@ extern void show_registers(struct pt_regs *regs); : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#ifndef CONFIG_CPU_MIPSR6 #define LoadW(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_lwl("%0", "(%2)")"\n" \ @@ -146,6 +147,39 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#else +/* MIPSR6 has no lwl instruction */ +#define LoadW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n" \ + ".set\tnoat\n\t" \ + "1:"user_lb("%0", "0(%2)")"\n\t" \ + "2:"user_lbu("$1", "1(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:"user_lbu("$1", "2(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:"user_lbu("$1", "3(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); +#endif /* CONFIG_CPU_MIPSR6 */ #define LoadHWU(addr, value, res) \ __asm__ __volatile__ ( \ @@ -169,6 +203,7 @@ extern void show_registers(struct pt_regs *regs); : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#ifndef CONFIG_CPU_MIPSR6 #define LoadWU(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_lwl("%0", "(%2)")"\n" \ @@ -206,6 +241,87 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#else +/* MIPSR6 has not lwl and ldl instructions */ +#define LoadWU(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:"user_lbu("%0", "0(%2)")"\n\t" \ + "2:"user_lbu("$1", "1(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:"user_lbu("$1", "2(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:"user_lbu("$1", "3(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); + +#define LoadDW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:lb\t%0, 0(%2)\n\t" \ + "2:lbu\t $1, 1(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:lbu\t$1, 2(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:lbu\t$1, 3(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "5:lbu\t$1, 4(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "6:lbu\t$1, 5(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "7:lbu\t$1, 6(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "8:lbu\t$1, 7(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n\t" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR)"\t5b, 11b\n\t" \ + STR(PTR)"\t6b, 11b\n\t" \ + STR(PTR)"\t7b, 11b\n\t" \ + STR(PTR)"\t8b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); +#endif /* CONFIG_CPU_MIPSR6 */ + #define StoreHW(addr, value, res) \ __asm__ __volatile__ ( \ @@ -228,6 +344,7 @@ extern void show_registers(struct pt_regs *regs); : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); +#ifndef CONFIG_CPU_MIPSR6 #define StoreW(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_swl("%1", "(%2)")"\n" \ @@ -263,9 +380,82 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); -#endif +#else +/* MIPSR6 has no swl and sdl instructions */ +#define StoreW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:"user_sb("%1", "3(%2)")"\n\t" \ + "srl\t$1, %1, 0x8\n\t" \ + "2:"user_sb("$1", "2(%2)")"\n\t" \ + "srl\t$1, $1, 0x8\n\t" \ + "3:"user_sb("$1", "1(%2)")"\n\t" \ + "srl\t$1, $1, 0x8\n\t" \ + "4:"user_sb("$1", "0(%2)")"\n\t" \ + ".set\tpop\n\t" \ + "li\t%0, 0\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%0, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (res) \ + : "r" (value), "r" (addr), "i" (-EFAULT) \ + : "memory"); + +#define StoreDW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:sb\t%1, 7(%2)\n\t" \ + "dsrl\t$1, %1, 0x8\n\t" \ + "2:sb\t$1, 6(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "3:sb\t$1, 5(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "4:sb\t$1, 4(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "5:sb\t$1, 3(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "6:sb\t$1, 2(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "7:sb\t$1, 1(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "8:sb\t$1, 0(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + ".set\tpop\n\t" \ + "li\t%0, 0\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%0, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR)"\t5b, 11b\n\t" \ + STR(PTR)"\t6b, 11b\n\t" \ + STR(PTR)"\t7b, 11b\n\t" \ + STR(PTR)"\t8b, 11b\n\t" \ + ".previous" \ + : "=&r" (res) \ + : "r" (value), "r" (addr), "i" (-EFAULT) \ + : "memory"); +#endif /* CONFIG_CPU_MIPSR6 */ + +#else /* __BIG_ENDIAN */ -#ifdef __LITTLE_ENDIAN #define LoadHW(addr, value, res) \ __asm__ __volatile__ (".set\tnoat\n" \ "1:\t"user_lb("%0", "1(%2)")"\n" \ @@ -286,6 +476,7 @@ extern void show_registers(struct pt_regs *regs); : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#ifndef CONFIG_CPU_MIPSR6 #define LoadW(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_lwl("%0", "3(%2)")"\n" \ @@ -303,6 +494,40 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#else +/* MIPSR6 has no lwl instruction */ +#define LoadW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n" \ + ".set\tnoat\n\t" \ + "1:"user_lb("%0", "3(%2)")"\n\t" \ + "2:"user_lbu("$1", "2(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:"user_lbu("$1", "1(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:"user_lbu("$1", "0(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); +#endif /* CONFIG_CPU_MIPSR6 */ + #define LoadHWU(addr, value, res) \ __asm__ __volatile__ ( \ @@ -326,6 +551,7 @@ extern void show_registers(struct pt_regs *regs); : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#ifndef CONFIG_CPU_MIPSR6 #define LoadWU(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_lwl("%0", "3(%2)")"\n" \ @@ -363,6 +589,86 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); +#else +/* MIPSR6 has not lwl and ldl instructions */ +#define LoadWU(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:"user_lbu("%0", "3(%2)")"\n\t" \ + "2:"user_lbu("$1", "2(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:"user_lbu("$1", "1(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:"user_lbu("$1", "0(%2)")"\n\t" \ + "sll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); + +#define LoadDW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:lb\t%0, 7(%2)\n\t" \ + "2:lbu\t$1, 6(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "3:lbu\t$1, 5(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "4:lbu\t$1, 4(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "5:lbu\t$1, 3(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "6:lbu\t$1, 2(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "7:lbu\t$1, 1(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "8:lbu\t$1, 0(%2)\n\t" \ + "dsll\t%0, 0x8\n\t" \ + "or\t%0, $1\n\t" \ + "li\t%1, 0\n" \ + ".set\tpop\n\t" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%1, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR)"\t5b, 11b\n\t" \ + STR(PTR)"\t6b, 11b\n\t" \ + STR(PTR)"\t7b, 11b\n\t" \ + STR(PTR)"\t8b, 11b\n\t" \ + ".previous" \ + : "=&r" (value), "=r" (res) \ + : "r" (addr), "i" (-EFAULT)); +#endif /* CONFIG_CPU_MIPSR6 */ #define StoreHW(addr, value, res) \ __asm__ __volatile__ ( \ @@ -384,7 +690,7 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); - +#ifndef CONFIG_CPU_MIPSR6 #define StoreW(addr, value, res) \ __asm__ __volatile__ ( \ "1:\t"user_swl("%1", "3(%2)")"\n" \ @@ -420,6 +726,79 @@ extern void show_registers(struct pt_regs *regs); ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); +#else +/* MIPSR6 has no swl and sdl instructions */ +#define StoreW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:"user_sb("%1", "0(%2)")"\n\t" \ + "srl\t$1, %1, 0x8\n\t" \ + "2:"user_sb("$1", "1(%2)")"\n\t" \ + "srl\t$1, $1, 0x8\n\t" \ + "3:"user_sb("$1", "2(%2)")"\n\t" \ + "srl\t$1, $1, 0x8\n\t" \ + "4:"user_sb("$1", "3(%2)")"\n\t" \ + ".set\tpop\n\t" \ + "li\t%0, 0\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%0, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + ".previous" \ + : "=&r" (res) \ + : "r" (value), "r" (addr), "i" (-EFAULT) \ + : "memory"); + +#define StoreDW(addr, value, res) \ + __asm__ __volatile__ ( \ + ".set\tpush\n\t" \ + ".set\tnoat\n\t" \ + "1:sb\t%1, 0(%2)\n\t" \ + "dsrl\t$1, %1, 0x8\n\t" \ + "2:sb\t$1, 1(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "3:sb\t$1, 2(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "4:sb\t$1, 3(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "5:sb\t$1, 4(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "6:sb\t$1, 5(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "7:sb\t$1, 6(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + "8:sb\t$1, 7(%2)\n\t" \ + "dsrl\t$1, $1, 0x8\n\t" \ + ".set\tpop\n\t" \ + "li\t%0, 0\n" \ + "10:\n\t" \ + ".insn\n\t" \ + ".section\t.fixup,\"ax\"\n\t" \ + "11:\tli\t%0, %3\n\t" \ + "j\t10b\n\t" \ + ".previous\n\t" \ + ".section\t__ex_table,\"a\"\n\t" \ + STR(PTR)"\t1b, 11b\n\t" \ + STR(PTR)"\t2b, 11b\n\t" \ + STR(PTR)"\t3b, 11b\n\t" \ + STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR)"\t5b, 11b\n\t" \ + STR(PTR)"\t6b, 11b\n\t" \ + STR(PTR)"\t7b, 11b\n\t" \ + STR(PTR)"\t8b, 11b\n\t" \ + ".previous" \ + : "=&r" (res) \ + : "r" (value), "r" (addr), "i" (-EFAULT) \ + : "memory"); +#endif /* CONFIG_CPU_MIPSR6 */ #endif static void emulate_load_store_insn(struct pt_regs *regs, @@ -703,10 +1082,13 @@ static void emulate_load_store_insn(struct pt_regs *regs, break; return; +#ifndef CONFIG_CPU_MIPSR6 /* * COP2 is available to implementor for application specific use. * It's up to applications to register a notifier chain and do * whatever they have to do, including possible sending of signals. + * + * This instruction has been reallocated in Release 6 */ case lwc2_op: cu2_notifier_call_chain(CU2_LWC2_OP, regs); @@ -723,7 +1105,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, case sdc2_op: cu2_notifier_call_chain(CU2_SDC2_OP, regs); break; - +#endif default: /* * Pheeee... We encountered an yet unknown instruction or |