diff options
| author | Paolo Bonzini | 2020-09-22 06:43:17 -0400 |
|---|---|---|
| committer | Paolo Bonzini | 2020-09-22 06:43:17 -0400 |
| commit | bf3c0e5e7102f5787d693379d9d384b813fe890b (patch) | |
| tree | aa48fc57dee9ecdf99918affa38d1b06be41419a /arch | |
| parent | 32251b07d532174d66941488c112ec046f646157 (diff) | |
| parent | 976bc5e2aceedef13e0ba1f0e6e372a22164aa0c (diff) | |
Merge branch 'x86-seves-for-paolo' of https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into HEAD
Diffstat (limited to 'arch')
246 files changed, 1643 insertions, 1109 deletions
diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index ac110ae8f978..5b60c248de9e 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -212,7 +212,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, STO_ALPHA_STD_GPLOAD) /* Omit the prologue. */ value += 8; - /* FALLTHRU */ + fallthrough; case R_ALPHA_BRADDR: value -= (u64)location + 4; if (value & 3) diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index a813020d2f11..15bc9d1e79f4 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -453,7 +453,7 @@ syscall_restart(unsigned long r0, unsigned long r19, regs->r0 = EINTR; break; } - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->r0 = r0; /* reset v0 and a3 and replay syscall */ regs->r19 = r19; diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 49754e07e04f..921d4b6e4d95 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -883,7 +883,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, case 0x26: /* sts */ fake_reg = s_reg_to_mem(alpha_read_fp_reg(reg)); - /* FALLTHRU */ + fallthrough; case 0x2c: /* stl */ __asm__ __volatile__( @@ -911,7 +911,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, case 0x27: /* stt */ fake_reg = alpha_read_fp_reg(reg); - /* FALLTHRU */ + fallthrough; case 0x2d: /* stq */ __asm__ __volatile__( diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 9acbeba832c0..dcaa44e408ac 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -88,6 +88,8 @@ arcpct: pct { compatible = "snps,archs-pct"; + interrupt-parent = <&cpu_intc>; + interrupts = <20>; }; /* TIMER0 with interrupt for clockevent */ @@ -208,7 +210,7 @@ reg = <0x8000 0x2000>; interrupts = <10>; interrupt-names = "macirq"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; snps,pbl = <32>; snps,multicast-filter-bins = <256>; clocks = <&gmacclk>; @@ -226,7 +228,7 @@ #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; - phy0: ethernet-phy@0 { + phy0: ethernet-phy@0 { /* Micrel KSZ9031 */ reg = <0>; }; }; diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index b747f2ec2928..6147db925248 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -18,10 +18,10 @@ * vineetg: April 2010 * -Switched pgtable_t from being struct page * to unsigned long * =Needed so that Page Table allocator (pte_alloc_one) is not forced to - * to deal with struct page. Thay way in future we can make it allocate + * deal with struct page. That way in future we can make it allocate * multiple PG Tbls in one Page Frame * =sweet side effect is avoiding calls to ugly page_address( ) from the - * pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate + * pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate) * * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 */ diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index d04837d91b40..03f8b1be0c3a 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -339,7 +339,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_LDWX_S: /* LDWX_S c, [b, u6] */ state->x = 1; - /* intentional fall-through */ + fallthrough; case op_LDW_S: /* LDW_S c, [b, u6] */ state->zz = 2; diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 661fd842ea97..79849f37e782 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) { struct arc_reg_pct_build pct_bcr; struct arc_reg_cc_build cc_bcr; - int i, has_interrupts; + int i, has_interrupts, irq; int counter_size; /* in bits */ union cc_name { @@ -637,13 +637,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .attr_groups = arc_pmu->attr_groups, }; - if (has_interrupts) { - int irq = platform_get_irq(pdev, 0); - - if (irq < 0) { - pr_err("Cannot get IRQ number for the platform\n"); - return -ENODEV; - } + if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) { arc_pmu->irq = irq; @@ -652,9 +646,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev) this_cpu_ptr(&arc_pmu_cpu)); on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); - - } else + } else { arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + } /* * perf parser doesn't really like '-' symbol in events name, so let's diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 3d57ed0d8535..8222f8c54690 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -321,7 +321,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs) regs->r0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: /* diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 28e8bf04b253..a331bb5d8319 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -18,44 +18,37 @@ #define ARC_PATH_MAX 256 -/* - * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25) - * -Prints 3 regs per line and a CR. - * -To continue, callee regs right after scratch, special handling of CR - */ -static noinline void print_reg_file(long *reg_rev, int start_num) +static noinline void print_regs_scratch(struct pt_regs *regs) { - unsigned int i; - char buf[512]; - int n = 0, len = sizeof(buf); - - for (i = start_num; i < start_num + 13; i++) { - n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t", - i, (unsigned long)*reg_rev); - - if (((i + 1) % 3) == 0) - n += scnprintf(buf + n, len - n, "\n"); - - /* because pt_regs has regs reversed: r12..r0, r25..r13 */ - if (is_isa_arcv2() && start_num == 0) - reg_rev++; - else - reg_rev--; - } - - if (start_num != 0) - n += scnprintf(buf + n, len - n, "\n\n"); + pr_cont("BTA: 0x%08lx\n SP: 0x%08lx FP: 0x%08lx BLK: %pS\n", + regs->bta, regs->sp, regs->fp, (void *)regs->blink); + pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", + regs->lp_start, regs->lp_end, regs->lp_count); - /* To continue printing callee regs on same line as scratch regs */ - if (start_num == 0) - pr_info("%s", buf); - else - pr_cont("%s\n", buf); + pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n" \ + "r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n" \ + "r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n" \ + "r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n" \ + "r12: 0x%08lx\t", + regs->r0, regs->r1, regs->r2, + regs->r3, regs->r4, regs->r5, + regs->r6, regs->r7, regs->r8, + regs->r9, regs->r10, regs->r11, + regs->r12); } -static void show_callee_regs(struct callee_regs *cregs) +static void print_regs_callee(struct callee_regs *regs) { - print_reg_file(&(cregs->r13), 13); + pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n" \ + "r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n" \ + "r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n" \ + "r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n" \ + "r24: 0x%08lx\tr25: 0x%08lx\n", + regs->r13, regs->r14, + regs->r15, regs->r16, regs->r17, + regs->r18, regs->r19, regs->r20, + regs->r21, regs->r22, regs->r23, + regs->r24, regs->r25); } static void print_task_path_n_nm(struct task_struct *tsk) @@ -175,7 +168,7 @@ static void show_ecr_verbose(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { struct task_struct *tsk = current; - struct callee_regs *cregs; + struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg; /* * generic code calls us with preemption disabled, but some calls @@ -204,25 +197,15 @@ void show_regs(struct pt_regs *regs) STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" [%2s%2s%2s%2s]", + pr_cont(" [%2s%2s%2s%2s] ", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_cont(" BTA: 0x%08lx\n SP: 0x%08lx FP: 0x%08lx BLK: %pS\n", - regs->bta, regs->sp, regs->fp, (void *)regs->blink); - pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", - regs->lp_start, regs->lp_end, regs->lp_count); - - /* print regs->r0 thru regs->r12 - * Sequential printing was generating horrible code - */ - print_reg_file(&(regs->r0), 0); - /* If Callee regs were saved, display them too */ - cregs = (struct callee_regs *)current->thread.callee_reg; + print_regs_scratch(regs); if (cregs) - show_callee_regs(cregs); + print_regs_callee(cregs); preempt_disable(); } diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index f87758a6851b..74ad4256022e 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -572,7 +572,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, #else BUILD_BUG_ON(sizeof(u32) != sizeof(value)); #endif - /* Fall through */ + fallthrough; case DW_EH_PE_native: if (end < (const void *)(ptr.pul + 1)) return 0; @@ -827,7 +827,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, case DW_CFA_def_cfa: state->cfa.reg = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg); - /* fall through */ + fallthrough; case DW_CFA_def_cfa_offset: state->cfa.offs = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa_offset: 0x%lx ", @@ -835,7 +835,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, break; case DW_CFA_def_cfa_sf: state->cfa.reg = get_uleb128(&ptr.p8, end); - /* fall through */ + fallthrough; case DW_CFA_def_cfa_offset_sf: state->cfa.offs = get_sleb128(&ptr.p8, end) * state->dataAlign; diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index f886ac69d8ad..3a35b82a718e 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -26,8 +26,8 @@ static unsigned long low_mem_sz; #ifdef CONFIG_HIGHMEM static unsigned long min_high_pfn, max_high_pfn; -static u64 high_mem_start; -static u64 high_mem_sz; +static phys_addr_t high_mem_start; +static phys_addr_t high_mem_sz; #endif #ifdef CONFIG_DISCONTIGMEM @@ -69,6 +69,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) high_mem_sz = size; in_use = 1; memblock_add_node(base, size, 1); + memblock_reserve(base, size); #endif } @@ -157,7 +158,7 @@ void __init setup_arch_memory(void) min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); - max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; + max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn; high_memory = (void *)(min_high_pfn << PAGE_SHIFT); kmap_init(); @@ -166,22 +167,26 @@ void __init setup_arch_memory(void) free_area_init(max_zone_pfn); } -/* - * mem_init - initializes memory - * - * Frees up bootmem - * Calculates and displays memory available/used - */ -void __init mem_init(void) +static void __init highmem_init(void) { #ifdef CONFIG_HIGHMEM unsigned long tmp; - reset_all_zones_managed_pages(); + memblock_free(high_mem_start, high_mem_sz); for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif +} +/* + * mem_init - initializes memory + * + * Frees up bootmem + * Calculates and displays memory available/used + */ +void __init mem_init(void) +{ memblock_free_all(); + highmem_init(); mem_init_print_info(NULL); } diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index a4a61531c7fb..77712c5ffe84 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -33,7 +33,6 @@ #define CTOP_AUX_DPC (CTOP_AUX_BASE + 0x02C) #define CTOP_AUX_LPC (CTOP_AUX_BASE + 0x030) #define CTOP_AUX_EFLAGS (CTOP_AUX_BASE + 0x080) -#define CTOP_AUX_IACK (CTOP_AUX_BASE + 0x088) #define CTOP_AUX_GPA1 (CTOP_AUX_BASE + 0x08C) #define CTOP_AUX_UDMC (CTOP_AUX_BASE + 0x300) diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 7fff88e61252..7a4853b1213a 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -547,7 +547,7 @@ static int arch_build_bp_info(struct perf_event *bp, if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) && max_watchpoint_len >= 8) break; - /* Else, fall through */ + fallthrough; default: return -EINVAL; } @@ -612,12 +612,12 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; - /* Else, fall through */ + fallthrough; case 3: /* Allow single byte watchpoint. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; - /* Else, fall through */ + fallthrough; default: ret = -EINVAL; goto out; @@ -884,7 +884,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, break; case ARM_ENTRY_ASYNC_WATCHPOINT: WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n"); - /* Fall through */ + fallthrough; case ARM_ENTRY_SYNC_WATCHPOINT: watchpoint_handler(addr, fsr, regs); break; @@ -933,7 +933,7 @@ static bool core_has_os_save_restore(void) ARM_DBG_READ(c1, c1, 4, oslsr); if (oslsr & ARM_OSLSR_OSLM0) return true; - /* Else, fall through */ + fallthrough; default: return false; } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index c9dc912b83f0..c1892f733f20 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -596,7 +596,7 @@ static int do_signal(struct pt_regs *regs, int syscall) switch (retval) { case -ERESTART_RESTARTBLOCK: restart -= 2; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/arm/mach-ep93xx/crunch.c b/arch/arm/mach-ep93xx/crunch.c index 1c05c5bf7e5c..757032d82f63 100644 --- a/arch/arm/mach-ep93xx/crunch.c +++ b/arch/arm/mach-ep93xx/crunch.c @@ -49,7 +49,7 @@ static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t) * FALLTHROUGH: Ensure we don't try to overwrite our newly * initialised state information on the first fault. */ - /* Fall through */ + fallthrough; case THREAD_NOTIFY_EXIT: crunch_task_release(thread); diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c index 2d86381e152d..7a6f74c32d42 100644 --- a/arch/arm/mach-mmp/pm-mmp2.c +++ b/arch/arm/mach-mmp/pm-mmp2.c @@ -123,19 +123,19 @@ void mmp2_pm_enter_lowpower_mode(int state) case POWER_MODE_SYS_SLEEP: apcr |= MPMU_PCR_PJ_SLPEN; /* set the SLPEN bit */ apcr |= MPMU_PCR_PJ_VCTCXOSD; /* set VCTCXOSD */ - /* fall through */ + fallthrough; case POWER_MODE_CHIP_SLEEP: apcr |= MPMU_PCR_PJ_SLPEN; - /* fall through */ + fallthrough; case POWER_MODE_APPS_SLEEP: apcr |= MPMU_PCR_PJ_APBSD; /* set APBSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_IDLE: apcr |= MPMU_PCR_PJ_AXISD; /* set AXISDD bit */ apcr |= MPMU_PCR_PJ_DDRCORSD; /* set DDRCORSD bit */ idle_cfg |= APMU_PJ_IDLE_CFG_PJ_PWRDWN; /* PJ power down */ apcr |= MPMU_PCR_PJ_SPSD; - /* fall through */ + fallthrough; case POWER_MODE_CORE_EXTIDLE: idle_cfg |= APMU_PJ_IDLE_CFG_PJ_IDLE; /* set the IDLE bit */ idle_cfg &= ~APMU_PJ_IDLE_CFG_ISO_MODE_CNTRL_MASK; diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c index 69ebe18ff209..1d71d73c1862 100644 --- a/arch/arm/mach-mmp/pm-pxa910.c +++ b/arch/arm/mach-mmp/pm-pxa910.c @@ -145,23 +145,23 @@ void pxa910_pm_enter_lowpower_mode(int state) case POWER_MODE_UDR: /* only shutdown APB in UDR */ apcr |= MPMU_APCR_STBYEN | MPMU_APCR_APBSD; - /* fall through */ + fallthrough; case POWER_MODE_SYS_SLEEP: apcr |= MPMU_APCR_SLPEN; /* set the SLPEN bit */ apcr |= MPMU_APCR_VCTCXOSD; /* set VCTCXOSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_SLEEP: apcr |= MPMU_APCR_DDRCORSD; /* set DDRCORSD */ - /* fall through */ + fallthrough; case POWER_MODE_APPS_IDLE: apcr |= MPMU_APCR_AXISD; /* set AXISDD bit */ - /* fall through */ + fallthrough; case POWER_MODE_CORE_EXTIDLE: idle_cfg |= APMU_MOH_IDLE_CFG_MOH_IDLE; idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWRDWN; idle_cfg |= APMU_MOH_IDLE_CFG_MOH_PWR_SW(3) | APMU_MOH_IDLE_CFG_MOH_L2_PWR_SW(3); - /* fall through */ + fallthrough; case POWER_MODE_CORE_INTIDLE: break; } diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 1d119b974f5f..59755b5a1ad7 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -396,7 +396,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "3.1"; break; case 7: - /* FALLTHROUGH */ default: /* Use the latest known revision as default */ omap_revision = OMAP3430_REV_ES3_1_2; @@ -416,7 +415,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.0"; break; case 1: - /* FALLTHROUGH */ default: omap_revision = AM35XX_REV_ES1_1; cpu_rev = "1.1"; @@ -435,7 +433,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.1"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = OMAP3630_REV_ES1_2; cpu_rev = "1.2"; @@ -456,7 +453,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 3: - /* FALLTHROUGH */ default: omap_revision = TI8168_REV_ES2_1; cpu_rev = "2.1"; @@ -473,7 +469,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = AM335X_REV_ES2_1; cpu_rev = "2.1"; @@ -491,7 +486,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "1.1"; break; case 2: - /* FALLTHROUGH */ default: omap_revision = AM437X_REV_ES1_2; cpu_rev = "1.2"; @@ -502,7 +496,6 @@ void __init omap3xxx_check_revision(void) case 0xb968: switch (rev) { case 0: - /* FALLTHROUGH */ case 1: omap_revision = TI8148_REV_ES1_0; cpu_rev = "1.0"; @@ -512,7 +505,6 @@ void __init omap3xxx_check_revision(void) cpu_rev = "2.0"; break; case 3: - /* FALLTHROUGH */ default: omap_revision = TI8148_REV_ES2_1; cpu_rev = "2.1"; diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 6b4548f3b57f..fc7bb2ca1672 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -240,7 +240,7 @@ static int _omap_device_notifier_call(struct notifier_block *nb, if (pdev->dev.of_node) omap_device_build_from_dt(pdev); omap_auxdata_legacy_init(dev); - /* fall through */ + fallthrough; default: od = to_omap_device(pdev); if (od) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 6df395fff971..f5dfddf492e2 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -298,11 +298,7 @@ static void omap3_pm_idle(void) if (omap_irq_pending()) return; - trace_cpu_idle_rcuidle(1, smp_processor_id()); - omap_sram_idle(); - - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_SUSPEND diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index d13344b2ddcd..87cb47220e82 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -624,7 +624,7 @@ static void __init dns323_init(void) dns323ab_leds[0].active_low = 1; gpio_request(DNS323_GPIO_LED_POWER1, "Power Led Enable"); gpio_direction_output(DNS323_GPIO_LED_POWER1, 0); - /* Fall through */ + fallthrough; case DNS323_REV_B1: i2c_register_board_info(0, dns323ab_i2c_devices, ARRAY_SIZE(dns323ab_i2c_devices)); diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index ea2c84214bac..d23970bd638d 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -46,7 +46,7 @@ static int __init parse_tag_acorn(const struct tag *tag) switch (tag->u.acorn.vram_pages) { case 512: vram_size += PAGE_SIZE * 256; - /* Fall through - ??? */ + fallthrough; /* ??? */ case 256: vram_size += PAGE_SIZE * 256; default: diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c index 76a65df42d10..d5c805adf7a8 100644 --- a/arch/arm/mach-tegra/reset.c +++ b/arch/arm/mach-tegra/reset.c @@ -70,7 +70,7 @@ static void __init tegra_cpu_reset_handler_enable(void) switch (err) { case -ENOSYS: tegra_cpu_reset_handler_set(reset_address); - /* fall through */ + fallthrough; case 0: is_enabled = true; break; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index f4bfc1cac91a..ea81e89e7740 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -694,7 +694,7 @@ thumb2arm(u16 tinstr) return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] | (tinstr & 255); /* register_list */ } - /* Else, fall through - for illegal instruction case */ + fallthrough; /* for illegal instruction case */ default: return BAD_INSTR; @@ -750,7 +750,7 @@ do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs, case 0xe8e0: case 0xe9e0: poffset->un = (tinst2 & 0xff) << 2; - /* Fall through */ + fallthrough; case 0xe940: case 0xe9c0: diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index c0fbfca5da8b..114c05ab4dd9 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -71,7 +71,7 @@ static void cpu_v7_spectre_init(void) /* Other ARM CPUs require no workaround */ if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) break; - /* fallthrough */ + fallthrough; /* Cortex A57/A72 require firmware workaround */ case ARM_CPU_PART_CORTEX_A57: case ARM_CPU_PART_CORTEX_A72: { diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c index b2e9e822426f..1eb59003bdec 100644 --- a/arch/arm/plat-omap/dma.c +++ b/arch/arm/plat-omap/dma.c @@ -309,14 +309,14 @@ void omap_set_dma_src_burst_mode(int lch, enum omap_dma_burst_mode burst_mode) * not supported by current hardware on OMAP1 * w |= (0x03 << 7); */ - /* fall through */ + fallthrough; case OMAP_DMA_DATA_BURST_16: if (dma_omap2plus()) { burst = 0x3; break; } /* OMAP1 don't support burst 16 */ - /* fall through */ + fallthrough; default: BUG(); } @@ -393,7 +393,7 @@ void omap_set_dma_dest_burst_mode(int lch, enum omap_dma_burst_mode burst_mode) break; } /* OMAP1 don't support burst 16 */ - /* fall through */ + fallthrough; default: printk(KERN_ERR "Invalid DMA burst mode\n"); BUG(); diff --git a/arch/arm/probes/decode.c b/arch/arm/probes/decode.c index fe81a9c21f2d..c84053a81358 100644 --- a/arch/arm/probes/decode.c +++ b/arch/arm/probes/decode.c @@ -307,7 +307,7 @@ static bool __kprobes decode_regs(probes_opcode_t *pinsn, u32 regs, bool modify) case REG_TYPE_NOPCWB: if (!is_writeback(insn)) break; /* No writeback, so any register is OK */ - /* fall through... */ + fallthrough; case REG_TYPE_NOPC: case REG_TYPE_NOPCX: /* Reject PC (R15) */ diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index 90b5bc723c83..feefa2055eba 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -280,7 +280,7 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* A nested probe was hit in FIQ, it is a BUG */ pr_warn("Unrecoverable kprobe detected.\n"); dump_kprobe(p); - /* fall through */ + fallthrough; default: /* impossible cases */ BUG(); diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 55bc8546d9c7..130569f90c54 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -82,8 +82,8 @@ endif # compiler to generate them and consequently to break the single image contract # we pass it only to the assembler. This option is utilized only in case of non # integrated assemblers. -ifneq ($(CONFIG_AS_HAS_ARMV8_4), y) -branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a +ifeq ($(CONFIG_AS_HAS_PAC), y) +asm-arch := armv8.3-a endif endif @@ -91,7 +91,12 @@ KBUILD_CFLAGS += $(branch-prot-flags-y) ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) # make sure to pass the newest target architecture to -march. -KBUILD_CFLAGS += -Wa,-march=armv8.4-a +asm-arch := armv8.4-a +endif + +ifdef asm-arch +KBUILD_CFLAGS += -Wa,-march=$(asm-arch) \ + -DARM64_ASM_ARCH='"$(asm-arch)"' endif ifeq ($(CONFIG_SHADOW_CALL_STACK), y) @@ -165,6 +170,8 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ + $(if $(CONFIG_COMPAT_VDSO), \ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 1a39e0ef776b..5b9ec032ce8d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -686,6 +686,8 @@ clocks = <&pericfg CLK_PERI_MSDC30_0_PD>, <&topckgen CLK_TOP_MSDC50_0_SEL>; clock-names = "source", "hclk"; + resets = <&pericfg MT7622_PERI_MSDC0_SW_RST>; + reset-names = "hrst"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 34d249d85da7..8eb61dd9921e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -337,8 +337,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03400000 0x0 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC1>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRA &emc>, @@ -366,8 +367,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03420000 0x0 0x10000>; interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC2>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC2>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCRAA &emc>, @@ -390,8 +392,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03440000 0x0 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC3>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA186_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA186_MEMORY_CLIENT_SDMMCR &emc>, @@ -416,8 +419,9 @@ compatible = "nvidia,tegra186-sdhci"; reg = <0x0 0x03460000 0x0 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA186_CLK_SDMMC4>, + <&bpmp TEGRA186_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA186_CLK_SDMMC4>, <&bpmp TEGRA186_CLK_PLLC4_VCO>; assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLC4_VCO>; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 48160f48003a..ca5cb6aef5ee 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -460,8 +460,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03400000 0x10000>; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC1>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC1>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCRA &emc>, @@ -485,8 +486,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03440000 0x10000>; interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC3>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; resets = <&bpmp TEGRA194_RESET_SDMMC3>; reset-names = "sdhci"; interconnects = <&mc TEGRA194_MEMORY_CLIENT_SDMMCR &emc>, @@ -511,8 +513,9 @@ compatible = "nvidia,tegra194-sdhci"; reg = <0x03460000 0x10000>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA194_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&bpmp TEGRA194_CLK_SDMMC4>, + <&bpmp TEGRA194_CLK_SDMMC_LEGACY_TM>; + clock-names = "sdhci", "tmclk"; assigned-clocks = <&bpmp TEGRA194_CLK_SDMMC4>, <&bpmp TEGRA194_CLK_PLLC4>; assigned-clock-parents = diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 829f786af133..8cca2166a446 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -1194,8 +1194,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0000 0x0 0x200>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC1>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC1>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 14>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1222,8 +1223,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0200 0x0 0x200>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC2>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC2>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 9>; reset-names = "sdhci"; pinctrl-names = "sdmmc-1v8-drv"; @@ -1239,8 +1241,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0400 0x0 0x200>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC3>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC3>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 69>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3", "sdmmc-1v8", @@ -1262,8 +1265,9 @@ compatible = "nvidia,tegra210-sdhci"; reg = <0x0 0x700b0600 0x0 0x200>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&tegra_car TEGRA210_CLK_SDMMC4>; - clock-names = "sdhci"; + clocks = <&tegra_car TEGRA210_CLK_SDMMC4>, + <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>; + clock-names = "sdhci", "tmclk"; resets = <&tegra_car 15>; reset-names = "sdhci"; pinctrl-names = "sdmmc-3v3-drv", "sdmmc-1v8-drv"; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index 9edfae5944f7..24ef18fe77df 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -417,10 +417,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x1>; + ti,sci-dev-id = <100>; + ti,interrupt-ranges = <0 392 32>; }; main_navss { @@ -438,10 +438,11 @@ ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x0>, <0x2>; + ti,sci-dev-id = <182>; + ti,interrupt-ranges = <0 64 64>, + <64 448 64>; }; inta_main_udmass: interrupt-controller@33d00000 { @@ -452,8 +453,7 @@ msi-controller; ti,sci = <&dmsc>; ti,sci-dev-id = <179>; - ti,sci-rm-range-vint = <0x0>; - ti,sci-rm-range-global-event = <0x1>; + ti,interrupt-ranges = <0 0 256>; }; secure_proxy_main: mailbox@32c00000 { @@ -589,7 +589,7 @@ <0x0 0x33000000 0x0 0x40000>; reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target"; ti,num-rings = <818>; - ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */ + ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */ ti,dma-ring-reset-quirk; ti,sci = <&dmsc>; ti,sci-dev-id = <187>; @@ -609,11 +609,11 @@ ti,sci-dev-id = <188>; ti,ringacc = <&ringacc>; - ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */ - <0x2>; /* TX_CHAN */ - ti,sci-rm-range-rchan = <0x4>, /* RX_HCHAN */ - <0x5>; /* RX_CHAN */ - ti,sci-rm-range-rflow = <0x6>; /* GP RFLOW */ + ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */ + <0xd>; /* TX_CHAN */ + ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */ + <0xa>; /* RX_CHAN */ + ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */ }; cpts@310d0000 { @@ -622,7 +622,7 @@ reg-names = "cpts"; clocks = <&main_cpts_mux>; clock-names = "cpts"; - interrupts-extended = <&intr_main_navss 163 0>; + interrupts-extended = <&intr_main_navss 391>; interrupt-names = "cpts"; ti,cpts-periodic-outputs = <6>; ti,cpts-ext-ts-inputs = <8>; @@ -645,8 +645,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_main_gpio>; - interrupts = <57 256>, <57 257>, <57 258>, <57 259>, <57 260>, - <57 261>; + interrupts = <192>, <193>, <194>, <195>, <196>, <197>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <96>; @@ -661,8 +660,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_main_gpio>; - interrupts = <58 256>, <58 257>, <58 258>, <58 259>, <58 260>, - <58 261>; + interrupts = <200>, <201>, <202>, <203>, <204>, <205>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <90>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi index 8c1abcfe0860..51ca4b4d4c21 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi @@ -134,7 +134,7 @@ <0x0 0x2a500000 0x0 0x40000>; reg-names = "rt", "fifos", "proxy_gcfg", "proxy_target"; ti,num-rings = <286>; - ti,sci-rm-range-gp-rings = <0x2>; /* GP ring range */ + ti,sci-rm-range-gp-rings = <0x1>; /* GP ring range */ ti,dma-ring-reset-quirk; ti,sci = <&dmsc>; ti,sci-dev-id = <195>; @@ -154,11 +154,11 @@ ti,sci-dev-id = <194>; ti,ringacc = <&mcu_ringacc>; - ti,sci-rm-range-tchan = <0x1>, /* TX_HCHAN */ - <0x2>; /* TX_CHAN */ - ti,sci-rm-range-rchan = <0x3>, /* RX_HCHAN */ - <0x4>; /* RX_CHAN */ - ti,sci-rm-range-rflow = <0x5>; /* GP RFLOW */ + ti,sci-rm-range-tchan = <0xf>, /* TX_HCHAN */ + <0xd>; /* TX_CHAN */ + ti,sci-rm-range-rchan = <0xb>, /* RX_HCHAN */ + <0xa>; /* RX_CHAN */ + ti,sci-rm-range-rflow = <0x0>; /* GP RFLOW */ }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi index 5f55b9e82cf1..a1ffe88d9664 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi @@ -74,10 +74,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <56>; - ti,sci-rm-range-girq = <0x4>; + ti,sci-dev-id = <156>; + ti,interrupt-ranges = <0 712 16>; }; wkup_gpio0: wkup_gpio0@42110000 { @@ -86,7 +86,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&intr_wkup_gpio>; - interrupts = <59 128>, <59 129>, <59 130>, <59 131>; + interrupts = <60>, <61>, <62>, <63>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <56>; diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts index 611e66207010..b8a8a0fcb8af 100644 --- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts +++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts @@ -384,7 +384,7 @@ }; &mailbox0_cluster0 { - interrupts = <164 0>; + interrupts = <436>; mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 { ti,mbox-tx = <1 0 0>; @@ -393,7 +393,7 @@ }; &mailbox0_cluster1 { - interrupts = <165 0>; + interrupts = <432>; mbox_mcu_r5fss0_core1: mbox-mcu-r5fss0-core1 { ti,mbox-tx = <1 0 0>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts index 8bc1e6ecc50e..e8fc01d97ada 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts @@ -287,7 +287,7 @@ }; &mailbox0_cluster0 { - interrupts = <214 0>; + interrupts = <436>; mbox_mcu_r5fss0_core0: mbox-mcu-r5fss0-core0 { ti,mbox-rx = <0 0 0>; @@ -301,7 +301,7 @@ }; &mailbox0_cluster1 { - interrupts = <215 0>; + interrupts = <432>; mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 { ti,mbox-rx = <0 0 0>; @@ -315,7 +315,7 @@ }; &mailbox0_cluster2 { - interrupts = <216 0>; + interrupts = <428>; mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 { ti,mbox-rx = <0 0 0>; @@ -329,7 +329,7 @@ }; &mailbox0_cluster3 { - interrupts = <217 0>; + interrupts = <424>; mbox_c66_0: mbox-c66-0 { ti,mbox-rx = <0 0 0>; @@ -343,7 +343,7 @@ }; &mailbox0_cluster4 { - interrupts = <218 0>; + interrupts = <420>; mbox_c71_0: mbox-c71-0 { ti,mbox-rx = <0 0 0>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi index d14060207f00..12ceea9b3c9a 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi @@ -80,10 +80,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0x1>; + ti,sci-dev-id = <131>; + ti,interrupt-ranges = <8 392 56>; }; main_navss { @@ -101,10 +101,12 @@ ti,intr-trigger-type = <4>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0>, <2>; + ti,sci-dev-id = <213>; + ti,interrupt-ranges = <0 64 64>, + <64 448 64>, + <128 672 64>; }; main_udmass_inta: interrupt-controller@33d00000 { @@ -115,8 +117,7 @@ msi-controller; ti,sci = <&dmsc>; ti,sci-dev-id = <209>; - ti,sci-rm-range-vint = <0xa>; - ti,sci-rm-range-global-event = <0xd>; + ti,interrupt-ranges = <0 0 256>; }; secure_proxy_main: mailbox@32c00000 { @@ -296,7 +297,7 @@ reg-names = "cpts"; clocks = <&k3_clks 201 1>; clock-names = "cpts"; - interrupts-extended = <&main_navss_intr 201 0>; + interrupts-extended = <&main_navss_intr 391>; interrupt-names = "cpts"; ti,cpts-periodic-outputs = <6>; ti,cpts-ext-ts-inputs = <8>; @@ -688,8 +689,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <105 0>, <105 1>, <105 2>, <105 3>, - <105 4>, <105 5>, <105 6>, <105 7>; + interrupts = <256>, <257>, <258>, <259>, + <260>, <261>, <262>, <263>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -705,7 +706,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <106 0>, <106 1>, <106 2>; + interrupts = <288>, <289>, <290>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -721,8 +722,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <107 0>, <107 1>, <107 2>, <107 3>, - <107 4>, <107 5>, <107 6>, <107 7>; + interrupts = <264>, <265>, <266>, <267>, + <268>, <269>, <270>, <271>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -738,7 +739,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <108 0>, <108 1>, <108 2>; + interrupts = <292>, <293>, <294>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -754,8 +755,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <109 0>, <109 1>, <109 2>, <109 3>, - <109 4>, <109 5>, <109 6>, <109 7>; + interrupts = <272>, <273>, <274>, <275>, + <276>, <277>, <278>, <279>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -771,7 +772,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <110 0>, <110 1>, <110 2>; + interrupts = <296>, <297>, <298>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; @@ -787,8 +788,8 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <111 0>, <111 1>, <111 2>, <111 3>, - <111 4>, <111 5>, <111 6>, <111 7>; + interrupts = <280>, <281>, <282>, <283>, + <284>, <285>, <286>, <287>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <128>; @@ -804,7 +805,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&main_gpio_intr>; - interrupts = <112 0>, <112 1>, <112 2>; + interrupts = <300>, <301>, <302>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <36>; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi index 30a735bcd0c8..c4a48e8d420a 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi @@ -101,10 +101,10 @@ ti,intr-trigger-type = <1>; interrupt-controller; interrupt-parent = <&gic500>; - #interrupt-cells = <2>; + #interrupt-cells = <1>; ti,sci = <&dmsc>; - ti,sci-dst-id = <14>; - ti,sci-rm-range-girq = <0x5>; + ti,sci-dev-id = <137>; + ti,interrupt-ranges = <16 960 16>; }; wkup_gpio0: gpio@42110000 { @@ -113,8 +113,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&wkup_gpio_intr>; - interrupts = <113 0>, <113 1>, <113 2>, - <113 3>, <113 4>, <113 5>; + interrupts = <103>, <104>, <105>, <106>, <107>, <108>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <84>; @@ -130,8 +129,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-parent = <&wkup_gpio_intr>; - interrupts = <114 0>, <114 1>, <114 2>, - <114 3>, <114 4>, <114 5>; + interrupts = <112>, <113>, <114>, <115>, <116>, <117>; interrupt-controller; #interrupt-cells = <2>; ti,ngpio = <84>; diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index 51a7ce87cdfe..6fb2e6bcc392 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -2,6 +2,12 @@ #ifndef __ASM_COMPILER_H #define __ASM_COMPILER_H +#ifdef ARM64_ASM_ARCH +#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n" +#else +#define ARM64_ASM_PREAMBLE +#endif + /* * The EL0/EL1 pointer bits used by a pointer authentication code. * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply. diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index aa4b6521ef14..ff328e5bbb75 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -95,6 +95,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) return res; } +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + static inline unsigned long arch_local_irq_save(void) { unsigned long flags; diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 51c1d9918999..1da8e3dc4455 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -71,11 +71,12 @@ * IMO: Override CPSR.I and enable signaling with VI * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO) + HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index fb1a922b31ba..6f98fbd0ac81 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -169,6 +169,34 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -193,6 +221,21 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index d493174415db..cc3f5a33ff9c 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -28,14 +28,16 @@ * not. The macros handles invoking the asm with or without the * register argument as appropriate. */ -#define __TLBI_0(op, arg) asm ("tlbi " #op "\n" \ +#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op "\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op, \ ARM64_WORKAROUND_REPEAT_TLBI, \ CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) -#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n" \ +#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op ", %0\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op ", %0", \ ARM64_WORKAROUND_REPEAT_TLBI, \ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 455966401102..a85174d05473 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -322,7 +322,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) */ if (memblock_is_map_memory(phys)) return (void __iomem *)__phys_to_virt(phys); - /* fall through */ + fallthrough; default: if (region->attribute & EFI_MEMORY_WB) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6bd1d3ad037a..c332d49780dc 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), + .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a389b999482e..6424584be01e 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -686,7 +686,7 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_HIGHER_OR_ZERO_SAFE: if (!cur || !new) break; - /* Fallthrough */ + fallthrough; case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 393c6fb1f1cb..d0076c2159e6 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -327,7 +327,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) set_bit(ICACHEF_VPIPT, &__icache_flags); break; default: - /* Fallthrough */ case ICACHE_POLICY_VIPT: /* Assume aliasing */ set_bit(ICACHEF_ALIASING, &__icache_flags); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2646178c8329..55af8b504b65 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -170,19 +170,6 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 - .if \regsize == 32 - /* - * If we're returning from a 32-bit task on a system affected by - * 1418040 then re-enable userspace access to the virtual counter. - */ -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 @@ -294,14 +281,6 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index af234a1e08b7..712e97c03e54 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -257,7 +257,7 @@ static int hw_breakpoint_control(struct perf_event *bp, * level. */ enable_debug_monitors(dbg_el); - /* Fall through */ + fallthrough; case HW_BREAKPOINT_RESTORE: /* Setup the address register. */ write_wb_reg(val_reg, i, info->address); @@ -541,13 +541,13 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; - /* Fallthrough */ + fallthrough; case 3: /* Allow single byte watchpoint. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; - /* Fallthrough */ + fallthrough; default: return -EINVAL; } diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 9e897c500237..8982b68289b7 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -103,6 +103,10 @@ KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); KVM_NVHE_ALIAS(gic_pmr_sync); #endif +/* EL2 exception handling */ +KVM_NVHE_ALIAS(__start___kvm_ex_table); +KVM_NVHE_ALIAS(__stop___kvm_ex_table); + #endif /* CONFIG_KVM */ #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 0ce3a28e3347..2e224435c024 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -305,8 +305,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, mod->arch.core.plt_shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt")) mod->arch.init.plt_shndx = i; - else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(secstrings + sechdrs[i].sh_name, + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".text.ftrace_trampoline")) tramp = sechdrs + i; else if (sechdrs[i].sh_type == SHT_SYMTAB) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 1cd1a4d0ed30..2a1ad95d9b2c 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -315,21 +315,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* MOVW instruction relocations. */ case R_AARCH64_MOVW_UABS_G0_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, AARCH64_INSN_IMM_MOVKZ); @@ -397,7 +397,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; - /* Fall through */ + fallthrough; case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 84ec630b8ab5..f1804496b935 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -123,10 +123,8 @@ void arch_cpu_idle(void) * This should do all the clock switching and wait for interrupt * tricks */ - trace_cpu_idle_rcuidle(1, smp_processor_id()); cpu_do_idle(); local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_HOTPLUG_CPU @@ -516,6 +514,39 @@ static void entry_task_switch(struct task_struct *next) } /* + * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. + * Assuming the virtual counter is enabled at the beginning of times: + * + * - disable access when switching from a 64bit task to a 32bit task + * - enable access when switching from a 32bit task to a 64bit task + */ +static void erratum_1418040_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + bool prev32, next32; + u64 val; + + if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + return; + + prev32 = is_compat_thread(task_thread_info(prev)); + next32 = is_compat_thread(task_thread_info(next)); + + if (prev32 == next32) + return; + + val = read_sysreg(cntkctl_el1); + + if (!next32) + val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + else + val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + + write_sysreg(val, cntkctl_el1); +} + +/* * Thread switching. */ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, @@ -530,6 +561,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); + erratum_1418040_thread_switch(prev, next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 77c4c9bad1b8..53acbeca4f57 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -280,7 +280,6 @@ u64 cpu_logical_map(int cpu) { return __cpu_logical_map[cpu]; } -EXPORT_SYMBOL_GPL(cpu_logical_map); void __init __no_sanitize_address setup_arch(char **cmdline_p) { diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 03957a1ae6c0..355ee9eed4dd 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -151,7 +151,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) break; } pr_crit("CPU%u: may not have shut down cleanly\n", cpu); - /* Fall through */ + fallthrough; case CPU_STUCK_IN_KERNEL: pr_crit("CPU%u: is stuck in kernel\n", cpu); if (status & CPU_STUCK_REASON_52_BIT_VA) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 5139a5f19256..d6adb4677c25 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ # Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ +quiet_cmd_vdso_install = INSTALL32 $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so vdso.so: $(obj)/vdso.so.dbg diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index ec8e894684a7..7cba7623fcec 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -20,6 +20,13 @@ ENTRY(_text) jiffies = jiffies_64; + +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + __start___kvm_ex_table = .; \ + *(__kvm_ex_table) \ + __stop___kvm_ex_table = .; + #define HYPERVISOR_TEXT \ /* \ * Align to 4 KB so that \ @@ -35,6 +42,7 @@ jiffies = jiffies_64; __hyp_idmap_text_end = .; \ __hyp_text_start = .; \ *(.hyp.text) \ + HYPERVISOR_EXTABLE \ __hyp_text_end = .; #define IDMAP_TEXT \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 57876b0b870b..b588c3b5c2f0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1643,6 +1643,10 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)) + kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ + "Only trusted guests should be used on this system.\n"); + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index fe6c7d79309d..5d690d60ccad 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -128,7 +128,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_WATCHPT_LOW: run->debug.arch.far = vcpu->arch.fault.far_el2; - /* fall through */ + fallthrough; case ESR_ELx_EC_SOFTSTP_LOW: case ESR_ELx_EC_BREAKPT_LOW: case ESR_ELx_EC_BKPT32: diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index ee32a7743389..76e7eaf4675e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -196,20 +196,23 @@ alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask // it, and at the latest just after the ISB. - .global abort_guest_exit_start abort_guest_exit_start: isb - .global abort_guest_exit_end abort_guest_exit_end: msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) - // If the exception took place, restore the EL1 exception - // context so that we can report some information. - // Merge the exception code with the SError pending bit. - tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. msr elr_el2, x2 msr esr_el2, x3 msr spsr_el2, x4 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 689fccbc9de7..46b4dab933d0 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -15,6 +15,30 @@ #include <asm/kvm_mmu.h> #include <asm/mmu.h> +.macro save_caller_saved_regs_vect + /* x0 and x1 were saved in the vector entry */ + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + .text .macro do_el2_call @@ -143,13 +167,19 @@ el1_error: b __guest_exit el2_sync: - /* Check for illegal exception return, otherwise panic */ + /* Check for illegal exception return */ mrs x0, spsr_el2 + tbnz x0, #20, 1f - /* if this was something else, then panic! */ - tst x0, #PSR_IL_BIT - b.eq __hyp_panic + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + eret + +1: /* Let's attempt a recovery from the illegal exception return */ get_vcpu_ptr x1, x0 mov x0, #ARM_EXCEPTION_IL @@ -157,27 +187,14 @@ el2_sync: el2_error: - ldp x0, x1, [sp], #16 + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect - /* - * Only two possibilities: - * 1) Either we come from the exit path, having just unmasked - * PSTATE.A: change the return code to an EL2 fault, and - * carry on, as we're already in a sane state to handle it. - * 2) Or we come from anywhere else, and that's a bug: we panic. - * - * For (1), x0 contains the original return code and x1 doesn't - * contain anything meaningful at that stage. We can reuse them - * as temp registers. - * For (2), who cares? - */ - mrs x0, elr_el2 - adr x1, abort_guest_exit_start - cmp x0, x1 - adr x1, abort_guest_exit_end - ccmp x0, x1, #4, ne - b.ne __hyp_panic - mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) eret sb diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h index 0297dc63988c..5e28ea6aa097 100644 --- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h @@ -21,70 +21,70 @@ #define save_debug(ptr,reg,nr) \ switch (nr) { \ case 15: ptr[15] = read_debug(reg, 15); \ - /* Fall through */ \ + fallthrough; \ case 14: ptr[14] = read_debug(reg, 14); \ - /* Fall through */ \ + fallthrough; \ case 13: ptr[13] = read_debug(reg, 13); \ - /* Fall through */ \ + fallthrough; \ case 12: ptr[12] = read_debug(reg, 12); \ - /* Fall through */ \ + fallthrough; \ case 11: ptr[11] = read_debug(reg, 11); \ - /* Fall through */ \ + fallthrough; \ case 10: ptr[10] = read_debug(reg, 10); \ - /* Fall through */ \ + fallthrough; \ case 9: ptr[9] = read_debug(reg, 9); \ - /* Fall through */ \ + fallthrough; \ case 8: ptr[8] = read_debug(reg, 8); \ - /* Fall through */ \ + fallthrough; \ case 7: ptr[7] = read_debug(reg, 7); \ - /* Fall through */ \ + fallthrough; \ case 6: ptr[6] = read_debug(reg, 6); \ - /* Fall through */ \ + fallthrough; \ case 5: ptr[5] = read_debug(reg, 5); \ - /* Fall through */ \ + fallthrough; \ case 4: ptr[4] = read_debug(reg, 4); \ - /* Fall through */ \ + fallthrough; \ case 3: ptr[3] = read_debug(reg, 3); \ - /* Fall through */ \ + fallthrough; \ case 2: ptr[2] = read_debug(reg, 2); \ - /* Fall through */ \ + fallthrough; \ case 1: ptr[1] = read_debug(reg, 1); \ - /* Fall through */ \ + fallthrough; \ default: ptr[0] = read_debug(reg, 0); \ } #define restore_debug(ptr,reg,nr) \ switch (nr) { \ case 15: write_debug(ptr[15], reg, 15); \ - /* Fall through */ \ + fallthrough; \ case 14: write_debug(ptr[14], reg, 14); \ - /* Fall through */ \ + fallthrough; \ case 13: write_debug(ptr[13], reg, 13); \ - /* Fall through */ \ + fallthrough; \ case 12: write_debug(ptr[12], reg, 12); \ - /* Fall through */ \ + fallthrough; \ case 11: write_debug(ptr[11], reg, 11); \ - /* Fall through */ \ + fallthrough; \ case 10: write_debug(ptr[10], reg, 10); \ - /* Fall through */ \ + fallthrough; \ case 9: write_debug(ptr[9], reg, 9); \ - /* Fall through */ \ + fallthrough; \ case 8: write_debug(ptr[8], reg, 8); \ - /* Fall through */ \ + fallthrough; \ case 7: write_debug(ptr[7], reg, 7); \ - /* Fall through */ \ + fallthrough; \ case 6: write_debug(ptr[6], reg, 6); \ - /* Fall through */ \ + fallthrough; \ case 5: write_debug(ptr[5], reg, 5); \ - /* Fall through */ \ + fallthrough; \ case 4: write_debug(ptr[4], reg, 4); \ - /* Fall through */ \ + fallthrough; \ case 3: write_debug(ptr[3], reg, 3); \ - /* Fall through */ \ + fallthrough; \ case 2: write_debug(ptr[2], reg, 2); \ - /* Fall through */ \ + fallthrough; \ case 1: write_debug(ptr[1], reg, 1); \ - /* Fall through */ \ + fallthrough; \ default: write_debug(ptr[0], reg, 0); \ } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index d64c5d56c860..0261308bf944 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -17,6 +17,7 @@ #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/extable.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> @@ -29,6 +30,9 @@ extern const char __hyp_panic_string[]; +extern struct exception_table_entry __start___kvm_ex_table; +extern struct exception_table_entry __stop___kvm_ex_table; + /* Check whether the FP regs were dirtied while in the host-side run loop: */ static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) { @@ -142,10 +146,10 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); + if (!__kvm_at("s1e1r", far)) + tmp = read_sysreg(par_el1); + else + tmp = SYS_PAR_EL1_F; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & SYS_PAR_EL1_F)) @@ -508,4 +512,31 @@ static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) #endif } +static inline void __kvm_unexpected_el2_exception(void) +{ + unsigned long addr, fixup; + struct kvm_cpu_context *host_ctxt; + struct exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = hyp_symbol_addr(__start___kvm_ex_table); + end = hyp_symbol_addr(__stop___kvm_ex_table); + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + hyp_panic(host_ctxt); +} + #endif /* __ARM64_KVM_HYP_SWITCH_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 341be2f2f312..0970442d2dbc 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -270,3 +270,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) read_sysreg(hpfar_el2), par, vcpu); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 5a0073511efb..452f4cacd674 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -340,10 +340,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); - /* Fall through */ + fallthrough; case 6: cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); - /* Fall through */ + fallthrough; default: cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); } @@ -352,10 +352,10 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); - /* Fall through */ + fallthrough; case 6: cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); - /* Fall through */ + fallthrough; default: cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); } @@ -373,10 +373,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); - /* Fall through */ + fallthrough; case 6: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); - /* Fall through */ + fallthrough; default: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); } @@ -385,10 +385,10 @@ void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) case 7: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); - /* Fall through */ + fallthrough; case 6: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); - /* Fall through */ + fallthrough; default: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); } diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index c52d714e0d75..c1da4f86ccac 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -217,3 +217,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) __hyp_call_panic(spsr, elr, par, host_ctxt); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index a206655a39a5..9b11c096a042 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -45,7 +45,7 @@ static u32 get_cpu_asid_bits(void) default: pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n", smp_processor_id(), fld); - /* Fallthrough */ + fallthrough; case 0: asid = 8; break; diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c index e456652facce..d05c78eace1b 100644 --- a/arch/c6x/kernel/signal.c +++ b/arch/c6x/kernel/signal.c @@ -220,7 +220,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->a4 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->a4 = regs->orig_a4; @@ -252,7 +252,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs, break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a4 = regs->orig_a4; regs->pc -= 4; diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 9452d6570b7e..970895df75ec 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -194,7 +194,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->a0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a0 = regs->orig_a0; regs->pc -= TRAP0_SIZE; diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 38d335488a54..69e68949787f 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -227,7 +227,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka) regs->er0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->er0 = regs->orig_er0; diff --git a/arch/hexagon/kernel/module.c b/arch/hexagon/kernel/module.c index cf99fb79a124..cb3bf19b0640 100644 --- a/arch/hexagon/kernel/module.c +++ b/arch/hexagon/kernel/module.c @@ -120,7 +120,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, } case R_HEXAGON_HI16: value = (value>>16) & 0xffff; - /* fallthrough */ + fallthrough; case R_HEXAGON_LO16: *location &= ~0x00c03fff; *location |= value & 0x3fff; diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c index d48864c48e5a..94cc7ff52dce 100644 --- a/arch/hexagon/kernel/signal.c +++ b/arch/hexagon/kernel/signal.c @@ -155,7 +155,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->r00 = -EINTR; break; } - /* Fall through */ + fallthrough; case -ERESTARTNOINTR: regs->r06 = regs->syscall_nr; pt_set_elr(regs, pt_elr(regs) - 4); diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 10850897a91c..779b6972aa84 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -366,6 +366,15 @@ pgd_index (unsigned long address) } #define pgd_index pgd_index +/* + * In the kernel's mapped region we know everything is in region number 5, so + * as an optimisation its PGD already points to the area for that region. + * However, this also means that we cannot use pgd_index() and we must + * never add the region here. + */ +#define pgd_offset_k(addr) \ + (init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))) + /* Look up a pgd entry in the gate area. On IA-64, the gate-area resides in the kernel-mapped segment, hence we use pgd_offset_k() here. */ diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index bec762a9b418..fec70d662d0c 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -163,7 +163,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) case DIE_INIT_MONARCH_LEAVE: if (!kdump_freeze_monarch) break; - /* fall through */ + fallthrough; case DIE_INIT_SLAVE_LEAVE: case DIE_INIT_MONARCH_ENTER: case DIE_MCA_RENDZVOUS_LEAVE: diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index b49fe6f618ed..f8150ee74f29 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -3,7 +3,7 @@ * Architecture-specific kernel symbols */ -#ifdef CONFIG_VIRTUAL_MEM_MAP +#if defined(CONFIG_VIRTUAL_MEM_MAP) || defined(CONFIG_DISCONTIGMEM) #include <linux/compiler.h> #include <linux/export.h> #include <linux/memblock.h> diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 1a42ba885188..00a496cb346f 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -654,7 +654,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, } } else if (!is_internal(mod, val)) val = get_plt(mod, location, val, &ok); - /* FALL THROUGH */ + fallthrough; default: val -= bundle(location); break; diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 971f166873aa..0dc3611e7971 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -3472,7 +3472,7 @@ pfm_restart(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs) break; case PFM_CTX_LOADED: if (CTX_HAS_SMPL(ctx) && fmt->fmt_restart_active) break; - /* fall through */ + fallthrough; case PFM_CTX_UNLOADED: case PFM_CTX_ZOMBIE: DPRINT(("invalid state=%d\n", state)); diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index d07ed65c9c6e..e67b22fc3c60 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -374,7 +374,7 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) /* note: scr->pt.r10 is already -1 */ break; } - /*FALLTHRU*/ + fallthrough; case ERESTARTNOINTR: ia64_decrement_ip(&scr->pt); restart = 0; /* don't restart twice if handle_signal() fails... */ diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index 2d4e65ba5c3e..6c1a8951dfbb 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -1431,7 +1431,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case LDS_IMM_OP: case LDSA_IMM_OP: case LDFS_OP: @@ -1459,7 +1459,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case LD_IMM_OP: case LDA_IMM_OP: case LDBIAS_IMM_OP: @@ -1475,7 +1475,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) if (u.insn.x) /* oops, really a semaphore op (cmpxchg, etc) */ goto failure; - /*FALLTHRU*/ + fallthrough; case ST_IMM_OP: case STREL_IMM_OP: ret = emulate_store_int(ifa, u.insn, regs); diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index 7601fe0622d2..6bd64c35e691 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -324,7 +324,7 @@ unw_access_gr (struct unw_frame_info *info, int regnum, unsigned long *val, char return 0; } } - /* fall through */ + fallthrough; case UNW_NAT_NONE: dummy_nat = 0; nat_addr = &dummy_nat; diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c index 37091898adb3..5e0e682f9c61 100644 --- a/arch/m68k/atari/atakeyb.c +++ b/arch/m68k/atari/atakeyb.c @@ -207,7 +207,7 @@ repeat: self_test_last_rcv = jiffies; break; } - /* FALL THROUGH */ + fallthrough; default: break_flag = scancode & BREAK_MASK; diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index fc034fd19798..a98fca977073 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -1067,7 +1067,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->d0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: regs->d0 = regs->orig_d0; diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 5c9f3a2d6538..a621fcc1a576 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -1018,7 +1018,7 @@ int __init mac_platform_init(void) */ platform_device_register_simple("mac_scsi", 1, mac_scsi_duo_rsrc, ARRAY_SIZE(mac_scsi_duo_rsrc)); - /* fall through */ + fallthrough; case MAC_SCSI_OLD: /* Addresses from Developer Notes for Duo System, * PowerBook 180 & 160, 140 & 170, Macintosh IIsi diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c index 1f0fad2a98a0..ac77d73af19a 100644 --- a/arch/m68k/mac/via.c +++ b/arch/m68k/mac/via.c @@ -370,7 +370,7 @@ void via_nubus_irq_startup(int irq) /* Allow NuBus slots 9 through F. */ via2[vDirA] &= 0x80 | ~(1 << irq_idx); } - /* fall through */ + fallthrough; case MAC_VIA_IICI: via_irq_enable(irq); break; diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 795f483b1050..ef46e77e97a5 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -118,7 +118,7 @@ good_area: pr_debug("do_page_fault: good_area\n"); switch (error_code & 3) { default: /* 3: write, present */ - /* fall through */ + fallthrough; case 2: /* write, not present */ if (!(vma->vm_flags & VM_WRITE)) goto acc_err; diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index 65bf5fd8d473..4a96b59f0bee 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -249,7 +249,7 @@ handle_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) regs->r3 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: do_restart: /* offset of 4 bytes to re-execute trap (brki) instruction */ diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 0880a003573d..3344d4a1fe89 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -46,6 +46,9 @@ unsigned long memory_size; EXPORT_SYMBOL(memory_size); unsigned long lowmem_size; +EXPORT_SYMBOL(min_low_pfn); +EXPORT_SYMBOL(max_low_pfn); + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; EXPORT_SYMBOL(kmap_pte); diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h index 47a8ffc0b413..f5b8300f4573 100644 --- a/arch/mips/include/asm/irqflags.h +++ b/arch/mips/include/asm/irqflags.h @@ -137,6 +137,11 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) return !(flags & 1); } +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + #endif /* #ifndef __ASSEMBLY__ */ /* diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index b6e9c99b85a5..eb181224eb4c 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -26,7 +26,6 @@ #define cpu_has_counter 1 #define cpu_has_dc_aliases (PAGE_SIZE < 0x4000) #define cpu_has_divec 0 -#define cpu_has_ejtag 0 #define cpu_has_inclusive_pcaches 1 #define cpu_has_llsc 1 #define cpu_has_mcheck 0 @@ -42,7 +41,6 @@ #define cpu_has_veic 0 #define cpu_has_vint 0 #define cpu_has_vtag_icache 0 -#define cpu_has_watch 1 #define cpu_has_wsbh 1 #define cpu_has_ic_fills_f_dc 1 #define cpu_hwrena_impl_bits 0xc0000000 diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index f5e362f79701..bf2480923154 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -2,8 +2,6 @@ #ifndef __ASM_MACH_LOONGSON64_IRQ_H_ #define __ASM_MACH_LOONGSON64_IRQ_H_ -#include <boot_param.h> - /* cpu core interrupt numbers */ #define NR_IRQS_LEGACY 16 #define NR_MIPS_CPU_IRQS 8 diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 3a25dbd3b3e9..5eaca4fe3f92 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -9,7 +9,6 @@ #ifndef _ASM_MACH_LOONGSON64_MMZONE_H #define _ASM_MACH_LOONGSON64_MMZONE_H -#include <boot_param.h> #define NODE_ADDRSPACE_SHIFT 44 #define NODE0_ADDRSPACE_OFFSET 0x000000000000UL #define NODE1_ADDRSPACE_OFFSET 0x100000000000UL diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h index 7dd4a80e05d6..6f4ac854b12d 100644 --- a/arch/mips/include/asm/unroll.h +++ b/arch/mips/include/asm/unroll.h @@ -28,38 +28,38 @@ BUILD_BUG_ON(!__builtin_constant_p(times)); \ \ switch (times) { \ - case 32: fn(__VA_ARGS__); /* fall through */ \ - case 31: fn(__VA_ARGS__); /* fall through */ \ - case 30: fn(__VA_ARGS__); /* fall through */ \ - case 29: fn(__VA_ARGS__); /* fall through */ \ - case 28: fn(__VA_ARGS__); /* fall through */ \ - case 27: fn(__VA_ARGS__); /* fall through */ \ - case 26: fn(__VA_ARGS__); /* fall through */ \ - case 25: fn(__VA_ARGS__); /* fall through */ \ - case 24: fn(__VA_ARGS__); /* fall through */ \ - case 23: fn(__VA_ARGS__); /* fall through */ \ - case 22: fn(__VA_ARGS__); /* fall through */ \ - case 21: fn(__VA_ARGS__); /* fall through */ \ - case 20: fn(__VA_ARGS__); /* fall through */ \ - case 19: fn(__VA_ARGS__); /* fall through */ \ - case 18: fn(__VA_ARGS__); /* fall through */ \ - case 17: fn(__VA_ARGS__); /* fall through */ \ - case 16: fn(__VA_ARGS__); /* fall through */ \ - case 15: fn(__VA_ARGS__); /* fall through */ \ - case 14: fn(__VA_ARGS__); /* fall through */ \ - case 13: fn(__VA_ARGS__); /* fall through */ \ - case 12: fn(__VA_ARGS__); /* fall through */ \ - case 11: fn(__VA_ARGS__); /* fall through */ \ - case 10: fn(__VA_ARGS__); /* fall through */ \ - case 9: fn(__VA_ARGS__); /* fall through */ \ - case 8: fn(__VA_ARGS__); /* fall through */ \ - case 7: fn(__VA_ARGS__); /* fall through */ \ - case 6: fn(__VA_ARGS__); /* fall through */ \ - case 5: fn(__VA_ARGS__); /* fall through */ \ - case 4: fn(__VA_ARGS__); /* fall through */ \ - case 3: fn(__VA_ARGS__); /* fall through */ \ - case 2: fn(__VA_ARGS__); /* fall through */ \ - case 1: fn(__VA_ARGS__); /* fall through */ \ + case 32: fn(__VA_ARGS__); fallthrough; \ + case 31: fn(__VA_ARGS__); fallthrough; \ + case 30: fn(__VA_ARGS__); fallthrough; \ + case 29: fn(__VA_ARGS__); fallthrough; \ + case 28: fn(__VA_ARGS__); fallthrough; \ + case 27: fn(__VA_ARGS__); fallthrough; \ + case 26: fn(__VA_ARGS__); fallthrough; \ + case 25: fn(__VA_ARGS__); fallthrough; \ + case 24: fn(__VA_ARGS__); fallthrough; \ + case 23: fn(__VA_ARGS__); fallthrough; \ + case 22: fn(__VA_ARGS__); fallthrough; \ + case 21: fn(__VA_ARGS__); fallthrough; \ + case 20: fn(__VA_ARGS__); fallthrough; \ + case 19: fn(__VA_ARGS__); fallthrough; \ + case 18: fn(__VA_ARGS__); fallthrough; \ + case 17: fn(__VA_ARGS__); fallthrough; \ + case 16: fn(__VA_ARGS__); fallthrough; \ + case 15: fn(__VA_ARGS__); fallthrough; \ + case 14: fn(__VA_ARGS__); fallthrough; \ + case 13: fn(__VA_ARGS__); fallthrough; \ + case 12: fn(__VA_ARGS__); fallthrough; \ + case 11: fn(__VA_ARGS__); fallthrough; \ + case 10: fn(__VA_ARGS__); fallthrough; \ + case 9: fn(__VA_ARGS__); fallthrough; \ + case 8: fn(__VA_ARGS__); fallthrough; \ + case 7: fn(__VA_ARGS__); fallthrough; \ + case 6: fn(__VA_ARGS__); fallthrough; \ + case 5: fn(__VA_ARGS__); fallthrough; \ + case 4: fn(__VA_ARGS__); fallthrough; \ + case 3: fn(__VA_ARGS__); fallthrough; \ + case 2: fn(__VA_ARGS__); fallthrough; \ + case 1: fn(__VA_ARGS__); fallthrough; \ case 0: break; \ \ default: \ diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index efce5defcc5c..011eb6bbf81a 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1898,8 +1898,8 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) (base_id >= 64 && base_id < 90) || (base_id >= 128 && base_id < 164) || (base_id >= 192 && base_id < 200) || - (base_id >= 256 && base_id < 274) || - (base_id >= 320 && base_id < 358) || + (base_id >= 256 && base_id < 275) || + (base_id >= 320 && base_id < 361) || (base_id >= 384 && base_id < 574)) break; diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 2f513506a3d5..1dbfb5aadffd 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -239,6 +239,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle) */ static void bmips_init_secondary(void) { + bmips_cpu_setup(); + switch (current_cpu_type()) { case CPU_BMIPS4350: case CPU_BMIPS4380: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 38aa07ccdbcc..cf788591f091 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1287,6 +1287,18 @@ static int enable_restore_fp_context(int msa) err = own_fpu_inatomic(1); if (msa && !err) { enable_msa(); + /* + * with MSA enabled, userspace can see MSACSR + * and MSA regs, but the values in them are from + * other task before current task, restore them + * from saved fp/msa context + */ + write_msa_csr(current->thread.fpu.msacsr); + /* + * own_fpu_inatomic(1) just restore low 64bit, + * fix the high 64bit + */ + init_msa_upper(); set_thread_flag(TIF_USEDMSA); set_thread_flag(TIF_MSA_CTX_LIVE); } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index fc5a6d25f74f..0ef717093262 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1712,7 +1712,11 @@ static void setup_scache(void) printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n", scache_size >> 10, way_string[c->scache.ways], c->scache.linesz); + + if (current_cpu_type() == CPU_BMIPS5000) + c->options |= MIPS_CPU_INCLUSIVE_CACHES; } + #else if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT)) panic("Dunno how to handle MIPS32 / MIPS64 second level cache"); diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 1493c49ca47a..55d7b7fd18b6 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -245,7 +245,6 @@ static int mipsxx_perfcount_handler(void) switch (counters) { #define HANDLE_COUNTER(n) \ - fallthrough; \ case n + 1: \ control = r_c0_perfctrl ## n(); \ counter = r_c0_perfcntr ## n(); \ @@ -256,8 +255,11 @@ static int mipsxx_perfcount_handler(void) handled = IRQ_HANDLED; \ } HANDLE_COUNTER(3) + fallthrough; HANDLE_COUNTER(2) + fallthrough; HANDLE_COUNTER(1) + fallthrough; HANDLE_COUNTER(0) } diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index 0ecffb65fd6d..b09dc844985a 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -222,8 +222,8 @@ void __init sni_a20r_irq_init(void) irq_set_chip_and_handler(i, &a20r_irq_type, handle_level_irq); sni_hwint = a20r_hwint; change_c0_status(ST0_IM, IE_IRQ0); - if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, 0, "ISA", - NULL)) + if (request_irq(SNI_A20R_IRQ_BASE + 3, sni_isa_irq_handler, + IRQF_SHARED, "ISA", sni_isa_irq_handler)) pr_err("Failed to register ISA interrupt\n"); } diff --git a/arch/nds32/include/asm/irqflags.h b/arch/nds32/include/asm/irqflags.h index fb45ec46bb1b..51ef800bb301 100644 --- a/arch/nds32/include/asm/irqflags.h +++ b/arch/nds32/include/asm/irqflags.h @@ -34,3 +34,8 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) { return !flags; } + +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c index 62bdafbc53f4..9edd7ed7d7bf 100644 --- a/arch/nds32/kernel/fpu.c +++ b/arch/nds32/kernel/fpu.c @@ -45,7 +45,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP32_DP16_reg: asm volatile ("fsdi $fd15, [%0+0x78]\n\t" "fsdi $fd14, [%0+0x70]\n\t" @@ -58,7 +58,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP16_DP8_reg: asm volatile ("fsdi $fd7, [%0+0x38]\n\t" "fsdi $fd6, [%0+0x30]\n\t" @@ -67,7 +67,7 @@ void save_fpu(struct task_struct *tsk) : /* no output */ : "r" (&tsk->thread.fpu) : "memory"); - /* fall through */ + fallthrough; case SP8_DP4_reg: asm volatile ("fsdi $fd3, [%1+0x18]\n\t" "fsdi $fd2, [%1+0x10]\n\t" @@ -108,7 +108,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd16, [%0+0x80]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP32_DP16_reg: asm volatile ("fldi $fd15, [%0+0x78]\n\t" "fldi $fd14, [%0+0x70]\n\t" @@ -120,7 +120,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd8, [%0+0x40]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP16_DP8_reg: asm volatile ("fldi $fd7, [%0+0x38]\n\t" "fldi $fd6, [%0+0x30]\n\t" @@ -128,7 +128,7 @@ void load_fpu(const struct fpu_struct *fpregs) "fldi $fd4, [%0+0x20]\n\t" : /* no output */ : "r" (fpregs)); - /* fall through */ + fallthrough; case SP8_DP4_reg: asm volatile ("fldi $fd3, [%1+0x18]\n\t" "fldi $fd2, [%1+0x10]\n\t" diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c index 330b19fcd990..36e25a410bb0 100644 --- a/arch/nds32/kernel/signal.c +++ b/arch/nds32/kernel/signal.c @@ -316,7 +316,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->uregs[0] = -EINTR; break; } - /* Else, fall through */ + fallthrough; case -ERESTARTNOINTR: regs->uregs[0] = regs->orig_r0; regs->ipc -= 4; @@ -361,7 +361,7 @@ static void do_signal(struct pt_regs *regs) switch (regs->uregs[0]) { case -ERESTART_RESTARTBLOCK: regs->uregs[15] = __NR_restart_syscall; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 97804f21a40c..c779364f0cd0 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -244,7 +244,7 @@ int do_signal(struct pt_regs *regs, int syscall) switch (retval) { case -ERESTART_RESTARTBLOCK: restart = -2; - /* Fall through */ + fallthrough; case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 5df5d4cd5d4c..3c037fc96038 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -502,7 +502,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) regs->gr[28] = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: check_syscallno_in_delay_branch(regs); break; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 43875c289723..a52c7abf2ca4 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -437,7 +437,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o break; default: - /* Fall through */ break; } @@ -644,12 +643,12 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 15: /* Data TLB miss fault/Data page fault */ - /* Fall through */ + fallthrough; case 16: /* Non-access instruction TLB miss fault */ /* The instruction TLB entry needed for the target address of the FIC is absent, and hardware can't find it, so we get to cleanup */ - /* Fall through */ + fallthrough; case 17: /* Non-access data TLB miss fault/Non-access data page fault */ /* FIXME: @@ -673,7 +672,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) handle_unaligned(regs); return; } - /* Fall Through */ + fallthrough; case 26: /* PCXL: Data memory access rights trap */ fault_address = regs->ior; @@ -683,7 +682,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 19: /* Data memory break trap */ regs->gr[0] |= PSW_X; /* So we can single-step over the trap */ - /* fall thru */ + fallthrough; case 21: /* Page reference trap */ handle_gdb_break(regs, TRAP_HWBKPT); @@ -730,7 +729,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) } mmap_read_unlock(current->mm); } - /* Fall Through */ + fallthrough; case 27: /* Data memory protection ID trap */ if (code == 27 && !user_mode(regs) && diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 4bfe2da9fbe3..716960f5d92e 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -67,7 +67,7 @@ parisc_acctyp(unsigned long code, unsigned int inst) case 0x30000000: /* coproc2 */ if (bit22set(inst)) return VM_WRITE; - /* fall through */ + fallthrough; case 0x0: /* indexed/memory management */ if (bit22set(inst)) { @@ -370,7 +370,7 @@ bad_area: } /* probably address is outside of mapped file */ - /* fall through */ + fallthrough; case 17: /* NA data TLB miss / page fault */ case 18: /* Unaligned access - PCXS only */ signo = SIGBUS; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1f48bbfb3ce9..65bed1fdeaad 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT If unsure, say N here. +config PPC_PROT_SAO_LPAR + bool "Support PROT_SAO mappings in LPARs" + depends on PPC_BOOK3S_64 + help + This option adds support for PROT_SAO mappings from userspace + inside LPARs on supported CPUs. + + This may cause issues when performing guest migration from + a CPU that supports SAO to one that does not. + + If unsure, say N here. + config PPC_COPRO_BASE bool diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 6de56c3b33c4..495fc0ccb453 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -20,13 +20,9 @@ #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) #define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ - -#define _PAGE_CACHE_CTL 0x00030 /* Bits for the folowing cache modes */ - /* No bits set is normal cacheable memory */ - /* 0x00010 unused, is SAO bit on radix POWER9 */ +#define _PAGE_SAO 0x00010 /* Strong access order */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ #define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ - #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ /* @@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, return hash__set_pte_at(mm, addr, ptep, pte, percpu); } +#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fdddb822d564..32a15dc49e8c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,6 +9,11 @@ #ifndef __ASSEMBLY__ +/* + * Added to include __machine_check_early_realmode_* functions + */ +#include <asm/mce.h> + /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ @@ -191,7 +196,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_SPURR LONG_ASM_CONST(0x0000000001000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0000000002000000) #define CPU_FTR_VSX LONG_ASM_CONST(0x0000000004000000) -// Free LONG_ASM_CONST(0x0000000008000000) +#define CPU_FTR_SAO LONG_ASM_CONST(0x0000000008000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0000000010000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0000000020000000) #define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0000000040000000) @@ -436,7 +441,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \ + CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX ) @@ -445,7 +450,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ @@ -456,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ @@ -474,7 +479,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 925cf89cbf4b..6bfc87915d5d 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 3a0db7b0b46e..35060be09073 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -200,17 +200,14 @@ static inline bool arch_irqs_disabled(void) #define powerpc_local_irq_pmu_save(flags) \ do { \ raw_local_irq_pmu_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while(0) #define powerpc_local_irq_pmu_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_pmu_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_pmu_restore(flags); \ - } \ + raw_local_irq_pmu_restore(flags); \ } while(0) #else #define powerpc_local_irq_pmu_save(flags) \ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index d635b96c7ea6..7355ed05e65e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -15,11 +15,18 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index adf2cda67f9a..89aa8248a57d 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,6 +210,9 @@ struct mce_error_info { #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 7c07728af300..7cb6d18f5cd6 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,20 +13,43 @@ #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> -#ifdef CONFIG_PPC_MEM_KEYS static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { - return pkey_to_vmflag_bits(pkey); +#ifdef CONFIG_PPC_MEM_KEYS + return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey)); +#else + return ((prot & PROT_SAO) ? VM_SAO : 0); +#endif } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) { - return __pgprot(vmflag_to_pte_pkey_bits(vm_flags)); +#ifdef CONFIG_PPC_MEM_KEYS + return (vm_flags & VM_SAO) ? + __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : + __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); +#else + return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); +#endif } #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) -#endif + +static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) +{ + if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) + return false; + if (prot & PROT_SAO) { + if (!cpu_has_feature(CPU_FTR_SAO)) + return false; + if (firmware_has_feature(FW_FEATURE_LPAR) && + !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR)) + return false; + } + return true; +} +#define arch_validate_prot arch_validate_prot #endif /* CONFIG_PPC64 */ #endif /* _ASM_POWERPC_MMAN_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 59ee9fa4ae09..6cb8aa357191 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -82,6 +82,8 @@ */ #include <asm/nohash/pte-book3e.h> +#define _PAGE_SAO 0 + #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) /* diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 1e8b2e1ec1db..daec64d41b44 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; } /* To support perf_regs sier update */ extern bool is_sier_available(void); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 86c9eb064b22..f6acabb6c9be 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -62,6 +62,11 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; }; /* diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 3a700351feca..c0c737215b00 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -11,7 +11,7 @@ #include <asm-generic/mman-common.h> -#define PROT_SAO 0x10 /* Unsupported since v5.9 */ +#define PROT_SAO 0x10 /* Strong Access Ordering */ #define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */ #define MAP_NORESERVE 0x40 /* don't reserve swap pages */ diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..bdf5f10f8b9f 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,24 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + /* Max regs without the extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */ +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK) +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */ +#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK) + +#define PERF_REG_MAX_ISA_300 (PERF_REG_POWERPC_MMCR2 + 1) +#define PERF_REG_MAX_ISA_31 (PERF_REG_POWERPC_SIER3 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3d406a9626e8..2aa89c6b2896 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power10(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power10", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 6f8c0c6b937a..f204ad79b6b5 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -64,10 +64,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -extern long __machine_check_early_realmode_p10(struct pt_regs *regs); - static int hv_mode; static struct { @@ -657,7 +653,7 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, {"no-execute", feat_enable, 0}, - /* strong-access-ordering is unused */ + {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, {"coprocessor-icswx", feat_enable, 0}, {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0}, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 33a42e42c56f..733e40eba4eb 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -113,6 +113,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) ld r11,exception_marker@toc(r2) std r11,-16(r10) /* "regshere" marker */ +BEGIN_FTR_SECTION + HMT_MEDIUM +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + /* * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which * would clobber syscall parameters. Also we always enter with IRQs diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 016bd831908e..73a57043ee66 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -548,7 +548,7 @@ void notrace restore_math(struct pt_regs *regs) * are live for the user thread). */ if ((!(msr & MSR_FP)) && should_restore_fp()) - new_msr |= MSR_FP | current->thread.fpexc_mode; + new_msr |= MSR_FP; if ((!(msr & MSR_VEC)) && should_restore_altivec()) new_msr |= MSR_VEC; @@ -559,11 +559,17 @@ void notrace restore_math(struct pt_regs *regs) } if (new_msr) { + unsigned long fpexc_mode = 0; + msr_check_and_set(new_msr); - if (new_msr & MSR_FP) + if (new_msr & MSR_FP) { do_restore_fp(); + // This also covers VSX, because VSX implies FP + fpexc_mode = current->thread.fpexc_mode; + } + if (new_msr & MSR_VEC) do_restore_altivec(); @@ -572,7 +578,7 @@ void notrace restore_math(struct pt_regs *regs) msr_check_and_clear(new_msr); - regs->msr |= new_msr; + regs->msr |= new_msr | fpexc_mode; } } #endif diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b198b0ff25bc..808ec9fab605 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) min = pvr & 0xFF; break; case 0x004e: /* POWER9 bits 12-15 give chip type */ + case 0x0080: /* POWER10 bit 12 gives SMT8/4 */ maj = (pvr >> 8) & 0x0F; min = pvr & 0xFF; break; diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index c0162911f6cb..d426eaf76bb0 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr) { if (!IS_ENABLED(CONFIG_MODULES)) return false; +#ifdef MODULES_VADDR + if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M)) + return false; + if (addr > ALIGN(MODULES_END, SZ_256M) - 1) + return false; +#else if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) return false; - if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1) return false; +#endif return true; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 1da9dbba9217..c663e7ba801f 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= HPTE_R_I; else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); else /* * Add memory coherence if cache inhibited is not set @@ -1115,8 +1117,10 @@ void hash__early_init_mmu_secondary(void) && cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); - if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY)) +#ifdef CONFIG_PPC_MEM_KEYS + if (mmu_has_feature(MMU_FTR_PKEY)) mtspr(SPRN_UAMOR, default_uamor); +#endif } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 16d09b36fe06..78d61f97371e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - /* Fall through */ + fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 78fe34986594..08643cba1494 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1557,9 +1557,16 @@ nocheck: ret = 0; out: if (has_branch_stack(event)) { - power_pmu_bhrb_enable(event); - cpuhw->bhrb_filter = ppmu->bhrb_filter_map( - event->attr.branch_sample_type); + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if (bhrb_filter != -1) { + cpuhw->bhrb_filter = bhrb_filter; + power_pmu_bhrb_enable(event); + } } perf_pmu_enable(event->pmu); @@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event) int n; int err; struct cpu_hw_events *cpuhw; - u64 bhrb_filter; if (!ppmu) return -ENOENT; @@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event) err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { - bhrb_filter = ppmu->bhrb_filter_map( + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); if (bhrb_filter == -1) { @@ -2141,6 +2150,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } @@ -2323,6 +2336,7 @@ int register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV /* diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cdb7bfbd157e..6e7e820508df 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, @@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, - &dev_attr_cpumask.attr, NULL, }; @@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = { &event_desc_group, &event_long_desc_group, &if_group, + &cpumask_attr_group, NULL, }; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index a45d694a5d5d..62d0b54086f8 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc = 0; if (cpu_has_feature(CPU_FTR_ARCH_31)) { - switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) { + switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) { case 0:/* when MSR HV and PR not set in the trace-record */ header->misc |= PERF_RECORD_MISC_GUEST_KERNEL; break; @@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc |= PERF_RECORD_MISC_GUEST_USER; break; case 2: /* MSR HV is 1 and PR is 0 */ - header->misc |= PERF_RECORD_MISC_HYPERVISOR; + header->misc |= PERF_RECORD_MISC_KERNEL; break; case 3: /* MSR HV is 1 and PR is 1 */ header->misc |= PERF_RECORD_MISC_USER; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index a213a0aa5d25..8e53f2fc3fe0 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -13,9 +13,11 @@ #include <asm/ptrace.h> #include <asm/perf_regs.h> +u64 PERF_REG_EXTENDED_MASK; + #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) -#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1)) +#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK)) static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]), @@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; +/* Function to return the extended register values */ +static u64 get_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_POWERPC_MMCR0: + return mfspr(SPRN_MMCR0); + case PERF_REG_POWERPC_MMCR1: + return mfspr(SPRN_MMCR1); + case PERF_REG_POWERPC_MMCR2: + return mfspr(SPRN_MMCR2); +#ifdef CONFIG_PPC64 + case PERF_REG_POWERPC_MMCR3: + return mfspr(SPRN_MMCR3); + case PERF_REG_POWERPC_SIER2: + return mfspr(SPRN_SIER2); + case PERF_REG_POWERPC_SIER3: + return mfspr(SPRN_SIER3); +#endif + default: return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) - return 0; + u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + perf_reg_extended_max = PERF_REG_MAX_ISA_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + perf_reg_extended_max = PERF_REG_MAX_ISA_300; if (idx == PERF_REG_POWERPC_SIER && (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || @@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) IS_ENABLED(CONFIG_PPC32))) return 0; + if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max) + return get_ext_regs_value(idx); + + /* + * If the idx is referring to value beyond the + * supported registers, return 0 with a warning + */ + if (WARN_ON_ONCE(idx >= perf_reg_extended_max)) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f7cff7f36a1c..83148656b524 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -87,6 +87,8 @@ #define POWER10_MMCRA_IFM3 0x00000000C0000000UL #define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { { PM_RUN_CYC_ALT, PM_RUN_CYC }, @@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = { .cache_events = &power10_cache_events, .attr_groups = power10_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power10_pmu(void) @@ -408,6 +411,9 @@ int init_power10_pmu(void) strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) return -ENODEV; + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + rc = register_power_pmu(&power10_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 05dae38b969a..2a57e93a79dc 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -90,6 +90,8 @@ enum { #define POWER9_MMCRA_IFM3 0x00000000C0000000UL #define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = { .cache_events = &power9_cache_events, .attr_groups = power9_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power9_pmu(void) @@ -457,6 +460,9 @@ int init_power9_pmu(void) } } + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300; + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 87737ec86d39..1dc9d3c81872 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -36,7 +36,7 @@ config PPC_BOOK3S_6xx select PPC_HAVE_PMU_SUPPORT select PPC_HAVE_KUEP select PPC_HAVE_KUAP - select HAVE_ARCH_VMAP_STACK + select HAVE_ARCH_VMAP_STACK if !ADB_PMU config PPC_BOOK3S_601 bool "PowerPC 601" diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 77513a80cef9..345ab062b21a 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1223,7 +1223,7 @@ static void __init pnv_probe_idle_states(void) return; } - if (pvr_version_is(PVR_POWER9)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) pnv_power9_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c9c25fb0783c..023a4f987bb2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (pe->dma_setup_done) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index c6e0d8abf75e..7a974ed6b240 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -107,22 +107,28 @@ static int pseries_cpu_disable(void) */ static void pseries_cpu_die(unsigned int cpu) { - int tries; int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); + unsigned long timeout = jiffies + msecs_to_jiffies(120000); - for (tries = 0; tries < 25; tries++) { + while (true) { cpu_status = smp_query_cpu_stopped(pcpu); if (cpu_status == QCSS_STOPPED || cpu_status == QCSS_HARDWARE_ERROR) break; - cpu_relax(); + if (time_after(jiffies, timeout)) { + pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n", + cpu, pcpu); + timeout = jiffies + msecs_to_jiffies(120000); + } + + cond_resched(); } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); + if (cpu_status == QCSS_HARDWARE_ERROR) { + pr_warn("CPU %i (hwid %i) reported error while dying\n", + cpu, pcpu); } /* Isolation and deallocation are definitely done by diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f3736fcd98fc..13c86a292c6d 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7b5905529146..df18372861d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -81,7 +81,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_INTC - select RISCV_TIMER + select RISCV_TIMER if RISCV_SBI select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6c88148f1b9b..8a55f6156661 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -12,6 +12,7 @@ config SOC_SIFIVE config SOC_VIRT bool "QEMU Virt Machine" + select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -24,6 +25,7 @@ config SOC_VIRT config SOC_KENDRYTE bool "Kendryte K210 SoC" depends on !MMU + select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index f27596e9663e..e046a0babde4 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -26,6 +26,7 @@ CONFIG_EXPERT=y CONFIG_SLOB=y # CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set +CONFIG_SOC_VIRT=y CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" @@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set -# CONFIG_DEVMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y @@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1 CONFIG_SERIAL_8250_RUNTIME_UARTS=1 CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_SIFIVE_PLIC=y -# CONFIG_VALIDATE_FS_PARSER is not set CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 3a55f0e00d6c..2c2cda6cc1c5 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y @@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y @@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h deleted file mode 100644 index a279b17a6aad..000000000000 --- a/arch/riscv/include/asm/clint.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_RISCV_CLINT_H -#define _ASM_RISCV_CLINT_H 1 - -#include <linux/io.h> -#include <linux/smp.h> - -#ifdef CONFIG_RISCV_M_MODE -extern u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void); - -static inline void clint_send_ipi_single(unsigned long hartid) -{ - writel(1, clint_ipi_base + hartid); -} - -static inline void clint_send_ipi_mask(const struct cpumask *mask) -{ - int cpu; - - for_each_cpu(cpu, mask) - clint_send_ipi_single(cpuid_to_hartid_map(cpu)); -} - -static inline void clint_clear_ipi(unsigned long hartid) -{ - writel(0, clint_ipi_base + hartid); -} -#else /* CONFIG_RISCV_M_MODE */ -#define clint_init_boot_cpu() do { } while (0) - -/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */ -void clint_send_ipi_single(unsigned long hartid); -void clint_send_ipi_mask(const struct cpumask *hartid_mask); -void clint_clear_ipi(unsigned long hartid); -#endif /* CONFIG_RISCV_M_MODE */ - -#endif /* _ASM_RISCV_CLINT_H */ diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 6dfd2a1446d5..df1f7c4cd433 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -15,6 +15,11 @@ struct seq_file; extern unsigned long boot_cpu_hartid; +struct riscv_ipi_ops { + void (*ipi_inject)(const struct cpumask *target); + void (*ipi_clear)(void); +}; + #ifdef CONFIG_SMP /* * Mapping between linux logical cpu index and hartid. @@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu); int riscv_hartid_to_cpuid(int hartid); void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out); +/* Set custom IPI operations */ +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops); + +/* Clear IPI for current CPU */ +void riscv_clear_ipi(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); @@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in, cpumask_set_cpu(boot_cpu_hartid, out); } +static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ +} + +static inline void riscv_clear_ipi(void) +{ +} + #endif /* CONFIG_SMP */ #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index bad2a7c2cda5..a3fb85d505d4 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -7,41 +7,27 @@ #define _ASM_RISCV_TIMEX_H #include <asm/csr.h> -#include <asm/mmio.h> typedef unsigned long cycles_t; -extern u64 __iomem *riscv_time_val; -extern u64 __iomem *riscv_time_cmp; - -#ifdef CONFIG_64BIT -#define mmio_get_cycles() readq_relaxed(riscv_time_val) -#else -#define mmio_get_cycles() readl_relaxed(riscv_time_val) -#define mmio_get_cycles_hi() readl_relaxed(((u32 *)riscv_time_val) + 1) -#endif - static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIME); - return mmio_get_cycles(); + return csr_read(CSR_TIME); } #define get_cycles get_cycles +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { return get_cycles(); } #else /* CONFIG_64BIT */ -static inline u32 get_cycles_hi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIMEH); - return mmio_get_cycles_hi(); -} - static inline u64 get_cycles64(void) { u32 hi, lo; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a5287ab9f7f2..dc93710f0b2f 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,7 @@ obj-y += cacheinfo.o obj-y += patch.o obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o traps_misaligned.o +obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f383ef5672b2..226ccce0f9e0 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } +static void sbi_send_cpumask_ipi(const struct cpumask *target) +{ + struct cpumask hartid_mask; + + riscv_cpuid_to_hartid_mask(target, &hartid_mask); + + sbi_send_ipi(cpumask_bits(&hartid_mask)); +} + +static struct riscv_ipi_ops sbi_ipi_ops = { + .ipi_inject = sbi_send_cpumask_ipi +}; int __init sbi_init(void) { @@ -587,5 +599,7 @@ int __init sbi_init(void) __sbi_rfence = __sbi_rfence_v01; } + riscv_set_ipi_ops(&sbi_ipi_ops); + return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f04373be54a6..2c6dd329312b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -18,7 +18,6 @@ #include <linux/swiotlb.h> #include <linux/smp.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/setup.h> #include <asm/sections.h> @@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - clint_init_boot_cpu(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 17ba190e84a5..e996e08f1061 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -250,7 +250,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->a0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->a0 = regs->orig_a0; regs->epc -= 0x4; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 554b0fb47060..ea028d9e0d24 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -18,7 +18,6 @@ #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/clint.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> @@ -86,9 +85,25 @@ static void ipi_stop(void) wait_for_interrupt(); } +static struct riscv_ipi_ops *ipi_ops; + +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ + ipi_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_ipi_ops); + +void riscv_clear_ipi(void) +{ + if (ipi_ops && ipi_ops->ipi_clear) + ipi_ops->ipi_clear(); + + csr_clear(CSR_IP, IE_SIE); +} +EXPORT_SYMBOL_GPL(riscv_clear_ipi); + static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - struct cpumask hartid_mask; int cpu; smp_mb__before_atomic(); @@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(mask); else - clint_send_ipi_mask(mask); + pr_warn("SMP: IPI inject method not available\n"); } static void send_ipi_single(int cpu, enum ipi_message_type op) { - int hartid = cpuid_to_hartid_map(cpu); - smp_mb__before_atomic(); set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); -} - -static inline void clear_ipi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(cpumask_of(cpu)); else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + pr_warn("SMP: IPI inject method not available\n"); } #ifdef CONFIG_IRQ_WORK @@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs) irq_enter(); - clear_ipi(); + riscv_clear_ipi(); while (true) { unsigned long ops; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 356825a57551..96167d55ed98 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/irq.h> #include <asm/mmu_context.h> @@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void) struct mm_struct *mm = &init_mm; unsigned int curr_cpuid = smp_processor_id(); - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + riscv_clear_ipi(); /* All kernel threads share the same mm context. */ mmgrab(mm); diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index bc5f2204693f..579575f9cdae 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1020,7 +1020,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_zext64(dst, ctx); break; } - /* Fallthrough. */ + fallthrough; case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_X: @@ -1079,7 +1079,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case 16: emit(rv_slli(lo(rd), lo(rd), 16), ctx); emit(rv_srli(lo(rd), lo(rd), 16), ctx); - /* Fallthrough. */ + fallthrough; case 32: if (!ctx->prog->aux->verifier_zext) emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3d86e12e8e3c..b29fcc66ec39 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS def_bool y config GENERIC_LOCKBREAK - def_bool y if PREEMPTTION + def_bool y if PREEMPTION config PGSTE def_bool y if KVM diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0cf9a82326a8..7228aabe9da6 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -626,6 +626,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -807,6 +808,7 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 # CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y @@ -818,6 +820,7 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m @@ -829,6 +832,7 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 5df9759e8ff6..fab03b7a6932 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -617,6 +617,7 @@ CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -763,6 +764,7 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y @@ -771,6 +773,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 4091c50449cd..8f67c55625f9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -74,5 +74,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 +# CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 50b4ce8cddfd..918f0ba4f4d2 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -29,7 +29,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ prev__ = *ptr__; \ do { \ @@ -37,7 +37,7 @@ new__ = old__ op (val); \ prev__ = cmpxchg(ptr__, old__, new__); \ } while (prev__ != old__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ new__; \ }) @@ -68,7 +68,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ if (__builtin_constant_p(val__) && \ ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ @@ -84,7 +84,7 @@ : [val__] "d" (val__) \ : "cc"); \ } \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) @@ -95,14 +95,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ old__ + val__; \ }) @@ -114,14 +114,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") @@ -136,10 +136,10 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ ret__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = cmpxchg(ptr__, oval, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -152,10 +152,10 @@ ({ \ typeof(pcp) *ptr__; \ typeof(pcp) ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = xchg(ptr__, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -171,11 +171,11 @@ typeof(pcp1) *p1__; \ typeof(pcp2) *p2__; \ int ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ p1__ = raw_cpu_ptr(&(pcp1)); \ p2__ = raw_cpu_ptr(&(pcp2)); \ ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 88bb42ca5008..c73f50649e7e 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,14 +33,13 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - trace_cpu_idle_rcuidle(1, smp_processor_id()); local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); local_irq_restore(flags); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); /* Account time spent with enabled wait psw loaded as idle time. */ + /* XXX seqcount has tracepoints that require RCU */ write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 11d2f7d05f91..a76dd27fb2e8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 1aed1a4dfc2d..eddf71c22875 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -402,6 +402,7 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end, pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY); if (!pud) goto out; + p4d_populate(&init_mm, p4d, pud); } ret = modify_pud_table(p4d, addr, next, add, direct); if (ret) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3902c9f6f2d6..4b62d6b55024 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); +void zpci_remove_device(struct zpci_dev *zdev) +{ + struct zpci_bus *zbus = zdev->zbus; + struct pci_dev *pdev; + + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (pdev) { + if (pdev->is_virtfn) + return zpci_remove_virtfn(pdev, zdev->vfn); + pci_stop_and_remove_bus_device_locked(pdev); + } +} + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - if (zdev->zbus->bus) { - struct pci_dev *pdev; - - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); - } + if (zdev->zbus->bus) + zpci_remove_device(zdev); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 642a99384688..5967f3014156 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev, { int rc; - virtfn->physfn = pci_dev_get(pdev); rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) { - pci_dev_put(pdev); - virtfn->physfn = NULL; + if (rc) return rc; - } + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + return 0; } @@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ int rc = 0; - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - WARN_ON(vfid < 0); + if (!zbus->multifunction) + return 0; + /* If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what @@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, zdev = zbus->function[i]; if (zdev && zdev->is_physfn) { pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); if (cand_devfn == virtfn->devfn) { rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); break; } + /* balance pci_get_slot() */ + pci_dev_put(pdev); } } return rc; @@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) { - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; return 0; } #endif +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + /* + * With pdev->no_vf_scan the common PCI probing code does not + * perform PF/VF linking. + */ + if (zdev->vfn) + zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + +} + static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { struct pci_bus *bus; @@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) } pdev = pci_scan_single_device(bus, zdev->devfn); - if (pdev) { - if (!zdev->is_physfn) { - rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn); - if (rc) - goto failed_with_pdev; - } + if (pdev) pci_bus_add_device(pdev); - } - return 0; -failed_with_pdev: - pci_stop_and_remove_bus_device(pdev); - pci_dev_put(pdev); - return rc; + return 0; } static void zpci_bus_add_devices(struct zpci_bus *zbus) diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 89be3c354b7b..4972433df458 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } + +#ifdef CONFIG_PCI_IOV +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} +#else /* CONFIG_PCI_IOV */ +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} +#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index fdebd286f402..9a3a291cad43 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1); break; } + /* the configuration request may be stale */ + if (zdev->state != ZPCI_FN_STATE_STANDBY) + break; zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; ret = zpci_enable_device(zdev); @@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) break; if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); ret = zpci_disable_device(zdev); if (ret) @@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* Give the driver a hint that the function is * already unusable. */ pdev->error_state = pci_channel_io_perm_failure; - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); } zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c index f3dc3f25b3ff..143747c45206 100644 --- a/arch/sh/drivers/platform_early.c +++ b/arch/sh/drivers/platform_early.c @@ -246,7 +246,7 @@ static int __init sh_early_platform_driver_probe_id(char *class_str, case EARLY_PLATFORM_ID_ERROR: pr_warn("%s: unable to parse %s parameter\n", class_str, epdrv->pdrv->driver.name); - /* fall-through */ + fallthrough; case EARLY_PLATFORM_ID_UNSET: match = NULL; break; diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c index 08e1af63edd9..34e25a439c81 100644 --- a/arch/sh/kernel/disassemble.c +++ b/arch/sh/kernel/disassemble.c @@ -486,7 +486,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) pr_cont("xd%d", rn & ~1); break; } - /* else, fall through */ + fallthrough; case D_REG_N: pr_cont("dr%d", rn); break; @@ -495,7 +495,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) pr_cont("xd%d", rm & ~1); break; } - /* else, fall through */ + fallthrough; case D_REG_M: pr_cont("dr%d", rm); break; diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c index 0d5f3c9d52f3..e4147efa9ec6 100644 --- a/arch/sh/kernel/kgdb.c +++ b/arch/sh/kernel/kgdb.c @@ -266,7 +266,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->pc = addr; - /* fallthrough */ + fallthrough; case 'D': case 'k': atomic_set(&kgdb_cpu_doing_single_step, -1); diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index a0fbb8427b39..4fe3f00137bc 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -418,7 +418,7 @@ handle_syscall_restart(unsigned long save_r0, struct pt_regs *regs, case -ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->regs[0] = save_r0; regs->pc -= instruction_size(__raw_readw(regs->pc - 4)); diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index 4843f48bfe85..774a82b0c649 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -87,7 +87,6 @@ void auxio_set_lte(int on) __auxio_sbus_set_lte(on); break; case AUXIO_TYPE_EBUS: - /* FALL-THROUGH */ default: break; } diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index bfae98ab8638..23f8838dd96e 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -55,7 +55,7 @@ static int clock_board_calc_nslots(struct clock_board *p) else return 5; } - /* Fallthrough */ + fallthrough; default: return 4; } diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c index 7580775a14b9..58ad3f7de1fb 100644 --- a/arch/sparc/kernel/kgdb_32.c +++ b/arch/sparc/kernel/kgdb_32.c @@ -122,7 +122,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->pc = addr; linux_regs->npc = addr + 4; } - /* fall through */ + fallthrough; case 'D': case 'k': diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index 5d6c2d287e85..177746ae2c81 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -148,7 +148,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->tpc = addr; linux_regs->tnpc = addr + 4; } - /* fall through */ + fallthrough; case 'D': case 'k': diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index c0886b400dad..2a12c86af956 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -359,7 +359,7 @@ int __init pcr_arch_init(void) * counter overflow interrupt so we can't make use of * their hardware currently. */ - /* fallthrough */ + fallthrough; default: err = -ENODEV; goto out_unregister; diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index da8902295c8c..3df960c137f7 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -224,7 +224,7 @@ void __init of_console_init(void) case PROMDEV_TTYB: skip = 1; - /* FALLTHRU */ + fallthrough; case PROMDEV_TTYA: type = "serial"; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index e2c6f0abda00..e9695a06492f 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -646,7 +646,7 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; @@ -686,7 +686,7 @@ void do_signal32(struct pt_regs * regs) regs->tpc -= 4; regs->tnpc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index f1f8c8ebe641..d0e0025ee3ba 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -440,7 +440,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->pc -= 4; @@ -506,7 +506,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->pc -= 4; regs->npc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->pc -= 4; diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 6937339a272c..255264bcb46a 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -461,7 +461,7 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, case ERESTARTSYS: if (!(sa->sa_flags & SA_RESTART)) goto no_system_call_restart; - /* fallthrough */ + fallthrough; case ERESTARTNOINTR: regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; @@ -532,7 +532,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->tpc -= 4; regs->tnpc -= 4; pt_regs_clear_syscall(regs); - /* fall through */ + fallthrough; case ERESTART_RESTARTBLOCK: regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index 72e560ef4a09..d5beec856146 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -359,7 +359,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); @@ -380,7 +380,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); @@ -408,13 +408,13 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) *pfsr |= (6 << 14); return 0; /* simulate invalid_fp_register exception */ } - /* fall through */ + fallthrough; case 2: if (freg & 1) { /* doublewords must have bit 5 zeroed */ *pfsr |= (6 << 14); return 0; } - /* fall through */ + fallthrough; case 1: rd = (void *)&fregs[freg]; break; diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index c8eabb973b86..b1dbf2fa8c0a 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -491,7 +491,7 @@ void bpf_jit_compile(struct bpf_prog *fp) } else { emit_loadimm(K, r_A); } - /* Fallthrough */ + fallthrough; case BPF_RET | BPF_A: if (seen_or_pass0) { if (i != flen - 1) { diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 3d57c71c532e..88cd9b5c1b74 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -70,7 +70,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) PT_REGS_SYSCALL_RET(regs) = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: PT_REGS_RESTART_SYSCALL(regs); PT_REGS_ORIG_SYSCALL(regs) = PT_REGS_SYSCALL_NR(regs); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index 4ff01176c1cc..21d56ae83cdf 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -54,7 +54,7 @@ int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *b /* else */ state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if (c == '=' && !*opptr) { @@ -129,7 +129,7 @@ int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option) state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 0048269180d5..877970d76249 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -36,6 +36,10 @@ #define STATIC #include <linux/decompress/mm.h> +#define _SETUP +#include <asm/setup.h> /* For COMMAND_LINE_SIZE */ +#undef _SETUP + #ifdef CONFIG_X86_5LEVEL unsigned int __pgtable_l5_enabled; unsigned int pgdir_shift __ro_after_init = 39; @@ -87,8 +91,11 @@ static unsigned long get_boot_seed(void) static bool memmap_too_large; -/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ -static unsigned long long mem_limit = ULLONG_MAX; +/* + * Store memory limit: MAXMEM on 64-bit and KERNEL_IMAGE_SIZE on 32-bit. + * It may be reduced by "mem=nn[KMG]" or "memmap=nn[KMG]" command line options. + */ +static u64 mem_limit; /* Number of immovable memory regions */ static int num_immovable_mem; @@ -131,8 +138,7 @@ enum parse_mode { }; static int -parse_memmap(char *p, unsigned long long *start, unsigned long long *size, - enum parse_mode mode) +parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode) { char *oldp; @@ -162,7 +168,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size, */ *size = 0; } else { - unsigned long long flags; + u64 flags; /* * efi_fake_mem=nn@ss:attr the attr specifies @@ -178,7 +184,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size, } *size = 0; } - /* Fall through */ + fallthrough; default: /* * If w/o offset, only size specified, memmap=nn[KMG] has the @@ -201,7 +207,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str) while (str && (i < MAX_MEMMAP_REGIONS)) { int rc; - unsigned long long start, size; + u64 start, size; char *k = strchr(str, ','); if (k) @@ -214,7 +220,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str) if (start == 0) { /* Store the specified memory limit if size > 0 */ - if (size > 0) + if (size > 0 && size < mem_limit) mem_limit = size; continue; @@ -261,15 +267,15 @@ static void parse_gb_huge_pages(char *param, char *val) static void handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); - size_t len = strlen((char *)args); + size_t len; char *tmp_cmdline; char *param, *val; u64 mem_size; - if (!strstr(args, "memmap=") && !strstr(args, "mem=") && - !strstr(args, "hugepages")) + if (!args) return; + len = strnlen(args, COMMAND_LINE_SIZE-1); tmp_cmdline = malloc(len + 1); if (!tmp_cmdline) error("Failed to allocate space for tmp_cmdline"); @@ -284,14 +290,12 @@ static void handle_mem_options(void) while (*args) { args = next_arg(args, ¶m, &val); /* Stop at -- */ - if (!val && strcmp(param, "--") == 0) { - warn("Only '--' specified in cmdline"); - goto out; - } + if (!val && strcmp(param, "--") == 0) + break; if (!strcmp(param, "memmap")) { mem_avoid_memmap(PARSE_MEMMAP, val); - } else if (strstr(param, "hugepages")) { + } else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) { parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { char *p = val; @@ -300,21 +304,23 @@ static void handle_mem_options(void) continue; mem_size = memparse(p, &p); if (mem_size == 0) - goto out; + break; - mem_limit = mem_size; + if (mem_size < mem_limit) + mem_limit = mem_size; } else if (!strcmp(param, "efi_fake_mem")) { mem_avoid_memmap(PARSE_EFI, val); } } -out: free(tmp_cmdline); return; } /* - * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). + * In theory, KASLR can put the kernel anywhere in the range of [16M, MAXMEM) + * on 64-bit, and [16M, KERNEL_IMAGE_SIZE) on 32-bit. + * * The mem_avoid array is used to store the ranges that need to be avoided * when KASLR searches for an appropriate random address. We must avoid any * regions that are unsafe to overlap with during decompression, and other @@ -392,8 +398,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, { unsigned long init_size = boot_params->hdr.init_size; u64 initrd_start, initrd_size; - u64 cmd_line, cmd_line_size; - char *ptr; + unsigned long cmd_line, cmd_line_size; /* * Avoid the region that is unsafe to overlap during @@ -414,16 +419,15 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* No need to set mapping for initrd, it will be handled in VO. */ /* Avoid kernel command line. */ - cmd_line = (u64)boot_params->ext_cmd_line_ptr << 32; - cmd_line |= boot_params->hdr.cmd_line_ptr; + cmd_line = get_cmd_line_ptr(); /* Calculate size of cmd_line. */ - ptr = (char *)(unsigned long)cmd_line; - for (cmd_line_size = 0; ptr[cmd_line_size++];) - ; - mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; - mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; - add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, - mem_avoid[MEM_AVOID_CMDLINE].size); + if (cmd_line) { + cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1; + mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; + mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; + add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, + mem_avoid[MEM_AVOID_CMDLINE].size); + } /* Avoid boot parameters. */ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; @@ -454,7 +458,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, { int i; struct setup_data *ptr; - unsigned long earliest = img->start + img->size; + u64 earliest = img->start + img->size; bool is_overlapping = false; for (i = 0; i < MEM_AVOID_MAX; i++) { @@ -499,18 +503,16 @@ static bool mem_avoid_overlap(struct mem_vector *img, } struct slot_area { - unsigned long addr; - int num; + u64 addr; + unsigned long num; }; #define MAX_SLOT_AREA 100 static struct slot_area slot_areas[MAX_SLOT_AREA]; - +static unsigned int slot_area_index; static unsigned long slot_max; -static unsigned long slot_area_index; - static void store_slot_info(struct mem_vector *region, unsigned long image_size) { struct slot_area slot_area; @@ -519,13 +521,10 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) return; slot_area.addr = region->start; - slot_area.num = (region->size - image_size) / - CONFIG_PHYSICAL_ALIGN + 1; + slot_area.num = 1 + (region->size - image_size) / CONFIG_PHYSICAL_ALIGN; - if (slot_area.num > 0) { - slot_areas[slot_area_index++] = slot_area; - slot_max += slot_area.num; - } + slot_areas[slot_area_index++] = slot_area; + slot_max += slot_area.num; } /* @@ -535,57 +534,53 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) static void process_gb_huge_pages(struct mem_vector *region, unsigned long image_size) { - unsigned long addr, size = 0; + u64 pud_start, pud_end; + unsigned long gb_huge_pages; struct mem_vector tmp; - int i = 0; - if (!max_gb_huge_pages) { + if (!IS_ENABLED(CONFIG_X86_64) || !max_gb_huge_pages) { store_slot_info(region, image_size); return; } - addr = ALIGN(region->start, PUD_SIZE); - /* Did we raise the address above the passed in memory entry? */ - if (addr < region->start + region->size) - size = region->size - (addr - region->start); - - /* Check how many 1GB huge pages can be filtered out: */ - while (size > PUD_SIZE && max_gb_huge_pages) { - size -= PUD_SIZE; - max_gb_huge_pages--; - i++; - } + /* Are there any 1GB pages in the region? */ + pud_start = ALIGN(region->start, PUD_SIZE); + pud_end = ALIGN_DOWN(region->start + region->size, PUD_SIZE); /* No good 1GB huge pages found: */ - if (!i) { + if (pud_start >= pud_end) { store_slot_info(region, image_size); return; } - /* - * Skip those 'i'*1GB good huge pages, and continue checking and - * processing the remaining head or tail part of the passed region - * if available. - */ - - if (addr >= region->start + image_size) { + /* Check if the head part of the region is usable. */ + if (pud_start >= region->start + image_size) { tmp.start = region->start; - tmp.size = addr - region->start; + tmp.size = pud_start - region->start; store_slot_info(&tmp, image_size); } - size = region->size - (addr - region->start) - i * PUD_SIZE; - if (size >= image_size) { - tmp.start = addr + i * PUD_SIZE; - tmp.size = size; + /* Skip the good 1GB pages. */ + gb_huge_pages = (pud_end - pud_start) >> PUD_SHIFT; + if (gb_huge_pages > max_gb_huge_pages) { + pud_end = pud_start + (max_gb_huge_pages << PUD_SHIFT); + max_gb_huge_pages = 0; + } else { + max_gb_huge_pages -= gb_huge_pages; + } + + /* Check if the tail part of the region is usable. */ + if (region->start + region->size >= pud_end + image_size) { + tmp.start = pud_end; + tmp.size = region->start + region->size - pud_end; store_slot_info(&tmp, image_size); } } -static unsigned long slots_fetch_random(void) +static u64 slots_fetch_random(void) { unsigned long slot; - int i; + unsigned int i; /* Handle case of no slots stored. */ if (slot_max == 0) @@ -598,7 +593,7 @@ static unsigned long slots_fetch_random(void) slot -= slot_areas[i].num; continue; } - return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN; + return slot_areas[i].addr + ((u64)slot * CONFIG_PHYSICAL_ALIGN); } if (i == slot_area_index) @@ -611,49 +606,23 @@ static void __process_mem_region(struct mem_vector *entry, unsigned long image_size) { struct mem_vector region, overlap; - unsigned long start_orig, end; - struct mem_vector cur_entry; - - /* On 32-bit, ignore entries entirely above our maximum. */ - if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE) - return; + u64 region_end; - /* Ignore entries entirely below our minimum. */ - if (entry->start + entry->size < minimum) - return; - - /* Ignore entries above memory limit */ - end = min(entry->size + entry->start, mem_limit); - if (entry->start >= end) - return; - cur_entry.start = entry->start; - cur_entry.size = end - entry->start; - - region.start = cur_entry.start; - region.size = cur_entry.size; + /* Enforce minimum and memory limit. */ + region.start = max_t(u64, entry->start, minimum); + region_end = min(entry->start + entry->size, mem_limit); /* Give up if slot area array is full. */ while (slot_area_index < MAX_SLOT_AREA) { - start_orig = region.start; - - /* Potentially raise address to minimum location. */ - if (region.start < minimum) - region.start = minimum; - /* Potentially raise address to meet alignment needs. */ region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); /* Did we raise the address above the passed in memory entry? */ - if (region.start > cur_entry.start + cur_entry.size) + if (region.start > region_end) return; /* Reduce size by any delta from the original address. */ - region.size -= region.start - start_orig; - - /* On 32-bit, reduce region size to fit within max size. */ - if (IS_ENABLED(CONFIG_X86_32) && - region.start + region.size > KERNEL_IMAGE_SIZE) - region.size = KERNEL_IMAGE_SIZE - region.start; + region.size = region_end - region.start; /* Return if region can't contain decompressed kernel */ if (region.size < image_size) @@ -666,27 +635,19 @@ static void __process_mem_region(struct mem_vector *entry, } /* Store beginning of region if holds at least image_size. */ - if (overlap.start > region.start + image_size) { - struct mem_vector beginning; - - beginning.start = region.start; - beginning.size = overlap.start - region.start; - process_gb_huge_pages(&beginning, image_size); + if (overlap.start >= region.start + image_size) { + region.size = overlap.start - region.start; + process_gb_huge_pages(®ion, image_size); } - /* Return if overlap extends to or past end of region. */ - if (overlap.start + overlap.size >= region.start + region.size) - return; - /* Clip off the overlapping region and start over. */ - region.size -= overlap.start - region.start + overlap.size; region.start = overlap.start + overlap.size; } } static bool process_mem_region(struct mem_vector *region, - unsigned long long minimum, - unsigned long long image_size) + unsigned long minimum, + unsigned long image_size) { int i; /* @@ -709,7 +670,7 @@ static bool process_mem_region(struct mem_vector *region, * immovable memory and @region. */ for (i = 0; i < num_immovable_mem; i++) { - unsigned long long start, end, entry_end, region_end; + u64 start, end, entry_end, region_end; struct mem_vector entry; if (!mem_overlaps(region, &immovable_mem[i])) @@ -736,8 +697,8 @@ static bool process_mem_region(struct mem_vector *region, #ifdef CONFIG_EFI /* - * Returns true if mirror region found (and must have been processed - * for slots adding) + * Returns true if we processed the EFI memmap, which we prefer over the E820 + * table if it is available. */ static bool process_efi_entries(unsigned long minimum, unsigned long image_size) @@ -839,20 +800,30 @@ static void process_e820_entries(unsigned long minimum, static unsigned long find_random_phys_addr(unsigned long minimum, unsigned long image_size) { + u64 phys_addr; + + /* Bail out early if it's impossible to succeed. */ + if (minimum + image_size > mem_limit) + return 0; + /* Check if we had too many memmaps. */ if (memmap_too_large) { debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n"); return 0; } - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + if (!process_efi_entries(minimum, image_size)) + process_e820_entries(minimum, image_size); - if (process_efi_entries(minimum, image_size)) - return slots_fetch_random(); + phys_addr = slots_fetch_random(); - process_e820_entries(minimum, image_size); - return slots_fetch_random(); + /* Perform a final check to make sure the address is in range. */ + if (phys_addr < minimum || phys_addr + image_size > mem_limit) { + warn("Invalid physical address chosen!\n"); + return 0; + } + + return (unsigned long)phys_addr; } static unsigned long find_random_virt_addr(unsigned long minimum, @@ -860,18 +831,12 @@ static unsigned long find_random_virt_addr(unsigned long minimum, { unsigned long slots, random_addr; - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); - /* Align image_size for easy slot calculations. */ - image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN); - /* * There are how many CONFIG_PHYSICAL_ALIGN-sized slots * that can hold image_size within the range of minimum to * KERNEL_IMAGE_SIZE? */ - slots = (KERNEL_IMAGE_SIZE - minimum - image_size) / - CONFIG_PHYSICAL_ALIGN + 1; + slots = 1 + (KERNEL_IMAGE_SIZE - minimum - image_size) / CONFIG_PHYSICAL_ALIGN; random_addr = kaslr_get_random_long("Virtual") % slots; @@ -908,6 +873,11 @@ void choose_random_location(unsigned long input, /* Prepare to add new identity pagetables on demand. */ initialize_identity_maps(); + if (IS_ENABLED(CONFIG_X86_32)) + mem_limit = KERNEL_IMAGE_SIZE; + else + mem_limit = MAXMEM; + /* Record the various known unsafe memory ranges. */ mem_avoid_init(input, input_size, *output); @@ -917,6 +887,8 @@ void choose_random_location(unsigned long input, * location: */ min_addr = min(*output, 512UL << 20); + /* Make sure minimum is aligned. */ + min_addr = ALIGN(min_addr, CONFIG_PHYSICAL_ALIGN); /* Walk available memory entries to find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 726e264410ff..3efce27ba35c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -70,8 +70,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize); int cmdline_find_option_bool(const char *option); struct mem_vector { - unsigned long long start; - unsigned long long size; + u64 start; + u64 size; }; #if CONFIG_RANDOMIZE_BASE diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 48512c7944e7..2f84c7ca74ea 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -60,16 +60,10 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs) { - unsigned int nr = (unsigned int)regs->orig_ax; - if (IS_ENABLED(CONFIG_IA32_EMULATION)) current_thread_info()->status |= TS_COMPAT; - /* - * Subtlety here: if ptrace pokes something larger than 2^32-1 into - * orig_ax, the unsigned int return value truncates it. This may - * or may not be necessary, but it matches the old asm behavior. - */ - return (unsigned int)syscall_enter_from_user_mode(regs, nr); + + return (unsigned int)regs->orig_ax; } /* @@ -91,15 +85,29 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { unsigned int nr = syscall_32_enter(regs); + /* + * Subtlety here: if ptrace pokes something larger than 2^32-1 into + * orig_ax, the unsigned int return value truncates it. This may + * or may not be necessary, but it matches the old asm behavior. + */ + nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); } static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { - unsigned int nr = syscall_32_enter(regs); + unsigned int nr = syscall_32_enter(regs); int res; + /* + * This cannot use syscall_enter_from_user_mode() as it has to + * fetch EBP before invoking any of the syscall entry work + * functions. + */ + syscall_enter_from_user_mode_prepare(regs); + instrumentation_begin(); /* Fetch EBP from where the vDSO stashed it. */ if (IS_ENABLED(CONFIG_X86_64)) { @@ -122,6 +130,9 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) return false; } + /* The case truncates any ptrace induced syscall nr > 2^32 -1 */ + nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr); + /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 3a07ce3ec70b..f1f96d4d8cd6 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -29,11 +29,6 @@ SYM_CODE_START_NOALIGN(\name) SYM_CODE_END(\name) .endm -#ifdef CONFIG_TRACE_IRQFLAGS - THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1 - THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 -#endif - #ifdef CONFIG_PREEMPTION THUNK preempt_schedule_thunk, preempt_schedule THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 50963472ee85..31e6887d24f1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4682,7 +4682,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_CORE2_MEROM: x86_add_quirk(intel_clovertown_quirk); - /* fall through */ + fallthrough; case INTEL_FAM6_CORE2_MEROM_L: case INTEL_FAM6_CORE2_PENRYN: @@ -5062,7 +5062,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_SKYLAKE_L: case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_KABYLAKE_L: @@ -5114,7 +5114,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_D: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: case INTEL_FAM6_TIGERLAKE_L: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 63f58bdf556c..8961653c5dd2 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1268,7 +1268,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_ZERO_CALL; break; } - /* fall through */ + fallthrough; case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2901d5df4366..83fc9d38eb1f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -368,6 +368,7 @@ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index a8f9315b9eae..6fe54b2813c1 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -18,8 +18,16 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * state, not the interrupt state as imagined by Xen. */ unsigned long flags = native_save_fl(); - WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | - X86_EFLAGS_NT)); + unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT; + + /* + * For !SMAP hardware we patch out CLAC on entry. + */ + if (boot_cpu_has(X86_FEATURE_SMAP) || + (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + mask |= X86_EFLAGS_AC; + + WARN_ON_ONCE(flags & mask); /* We think we came from user mode. Make sure pt_regs agrees. */ WARN_ON_ONCE(!user_mode(regs)); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 0a460f2a3f90..21a8b5259477 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -602,9 +602,7 @@ static inline u64 xgetbv(u32 index) { u32 eax, edx; - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ - : "=a" (eax), "=d" (edx) - : "c" (index)); + asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); return eax + ((u64)edx << 32); } @@ -613,8 +611,7 @@ static inline void xsetbv(u32 index, u64 value) u32 eax = value; u32 edx = value >> 32; - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ - : : "a" (eax), "d" (edx), "c" (index)); + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } #endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 0a301ad0b02f..9257667d13c5 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -59,5 +59,6 @@ typedef struct { } void leave_mm(int cpu); +#define leave_mm leave_mm #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 40aa69d04862..d8324a236696 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -327,8 +327,8 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), - offsetof(struct pt_regs, cx), offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 59a3e13204c3..5999b0b3dd4a 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -234,6 +234,12 @@ static inline void clwb(volatile void *__p) #define nop() asm volatile ("nop") +static inline void serialize(void) +{ + /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ + asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); +} + #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 8a1f5382a4ea..cf13f9e78585 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -150,14 +150,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) -struct __attribute__ ((__packed__)) vmcb_seg { +struct vmcb_seg { u16 selector; u16 attrib; u32 limit; u64 base; -}; +} __packed; -struct __attribute__ ((__packed__)) vmcb_save_area { +struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; struct vmcb_seg ss; @@ -200,20 +200,67 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 br_to; u64 last_excp_from; u64 last_excp_to; -}; + /* + * The following part of the save area is valid only for + * SEV-ES guests when referenced through the GHCB. + */ + u8 reserved_7[104]; + u64 reserved_8; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_9; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_10[16]; + u64 sw_exit_code; + u64 sw_exit_info_1; + u64 sw_exit_info_2; + u64 sw_scratch; + u8 reserved_11[56]; + u64 xcr0; + u8 valid_bitmap[16]; + u64 x87_state_gpa; +} __packed; + +struct ghcb { + struct vmcb_save_area save; + u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + + u8 shared_buffer[2032]; + + u8 reserved_1[10]; + u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ + u32 ghcb_usage; +} __packed; + + +#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 256 +#define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) { - BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298); - BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256); + BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } -struct __attribute__ ((__packed__)) vmcb { +struct vmcb { struct vmcb_control_area control; u8 reserved_control[1024 - sizeof(struct vmcb_control_area)]; struct vmcb_save_area save; -}; +} __packed; #define SVM_CPUID_FUNC 0x8000000a @@ -298,4 +345,47 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) +/* GHCB Accessor functions */ + +#define GHCB_BITMAP_IDX(field) \ + (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + +#define DEFINE_GHCB_ACCESSORS(field) \ + static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + } \ + \ + static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + __set_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + ghcb->save.field = value; \ + } + +DEFINE_GHCB_ACCESSORS(cpl) +DEFINE_GHCB_ACCESSORS(rip) +DEFINE_GHCB_ACCESSORS(rsp) +DEFINE_GHCB_ACCESSORS(rax) +DEFINE_GHCB_ACCESSORS(rcx) +DEFINE_GHCB_ACCESSORS(rdx) +DEFINE_GHCB_ACCESSORS(rbx) +DEFINE_GHCB_ACCESSORS(rbp) +DEFINE_GHCB_ACCESSORS(rsi) +DEFINE_GHCB_ACCESSORS(rdi) +DEFINE_GHCB_ACCESSORS(r8) +DEFINE_GHCB_ACCESSORS(r9) +DEFINE_GHCB_ACCESSORS(r10) +DEFINE_GHCB_ACCESSORS(r11) +DEFINE_GHCB_ACCESSORS(r12) +DEFINE_GHCB_ACCESSORS(r13) +DEFINE_GHCB_ACCESSORS(r14) +DEFINE_GHCB_ACCESSORS(r15) +DEFINE_GHCB_ACCESSORS(sw_exit_code) +DEFINE_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_GHCB_ACCESSORS(sw_scratch) +DEFINE_GHCB_ACCESSORS(xcr0) + #endif diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index fdb5b356e59b..0fd4a9dfb29c 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -5,6 +5,7 @@ #include <linux/preempt.h> #include <asm/processor.h> #include <asm/cpufeature.h> +#include <asm/special_insns.h> #ifdef CONFIG_X86_32 static inline void iret_to_self(void) @@ -46,22 +47,34 @@ static inline void iret_to_self(void) * * b) Text was modified on a different CPU, may subsequently be * executed on this CPU, and you want to make sure the new version - * gets executed. This generally means you're calling this in a IPI. + * gets executed. This generally means you're calling this in an IPI. * * If you're calling this for a different reason, you're probably doing * it wrong. + * + * Like all of Linux's memory ordering operations, this is a + * compiler barrier as well. */ static inline void sync_core(void) { /* - * There are quite a few ways to do this. IRET-to-self is nice - * because it works on every CPU, at any CPL (so it's compatible - * with paravirtualization), and it never exits to a hypervisor. - * The only down sides are that it's a bit slow (it seems to be - * a bit more than 2x slower than the fastest options) and that - * it unmasks NMIs. The "push %cs" is needed because, in - * paravirtual environments, __KERNEL_CS may not be a valid CS - * value when we do IRET directly. + * The SERIALIZE instruction is the most straightforward way to + * do this, but it is not universally available. + */ + if (static_cpu_has(X86_FEATURE_SERIALIZE)) { + serialize(); + return; + } + + /* + * For all other processors, there are quite a few ways to do this. + * IRET-to-self is nice because it works on every CPU, at any CPL + * (so it's compatible with paravirtualization), and it never exits + * to a hypervisor. The only downsides are that it's a bit slow + * (it seems to be a bit more than 2x slower than the fastest + * options) and that it unmasks NMIs. The "push %cs" is needed, + * because in paravirtual environments __KERNEL_CS may not be a + * valid CS value when we do IRET directly. * * In case NMI unmasking or performance ever becomes a problem, * the next best option appears to be MOV-to-CR2 and an @@ -71,9 +84,6 @@ static inline void sync_core(void) * CPUID is the conventional way, but it's nasty: it doesn't * exist on some 486-like CPUs, and it usually exits to a * hypervisor. - * - * Like all of Linux's memory ordering operations, this is a - * compiler barrier as well. */ iret_to_self(); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c3daf0aaa0ee..cdaab30880b9 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -239,7 +239,7 @@ void __init arch_init_ideal_nops(void) return; } - /* fall through */ + fallthrough; default: #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 21325a4a78b9..779a89e31c4c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -800,7 +800,7 @@ static int irq_polarity(int idx) return IOAPIC_POL_HIGH; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); - /* fall through */ + fallthrough; case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_POL_LOW; @@ -848,7 +848,7 @@ static int irq_trigger(int idx) return IOAPIC_EDGE; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); - /* fall through */ + fallthrough; case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_LEVEL; diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7bda71def557..99ee61c9ba54 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -149,7 +149,7 @@ void __init default_setup_apic_routing(void) break; } /* P4 and above */ - /* fall through */ + fallthrough; case X86_VENDOR_HYGON: case X86_VENDOR_AMD: def_to_bigsmp = 1; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index dae32d948bf2..f8a56b5dc29f 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; + WARN_ON_ONCE(apicd->cpu == newcpu); } else { irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, managed); @@ -910,7 +911,7 @@ void send_cleanup_vector(struct irq_cfg *cfg) __send_cleanup_vector(apicd); } -static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) +void irq_complete_move(struct irq_cfg *cfg) { struct apic_chip_data *apicd; @@ -918,15 +919,16 @@ static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) if (likely(!apicd->move_in_progress)) return; - if (vector == apicd->vector && apicd->cpu == smp_processor_id()) + /* + * If the interrupt arrived on the new target CPU, cleanup the + * vector on the old target CPU. A vector check is not required + * because an interrupt can never move from one vector to another + * on the same CPU. + */ + if (apicd->cpu == smp_processor_id()) __send_cleanup_vector(apicd); } -void irq_complete_move(struct irq_cfg *cfg) -{ - __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); -} - /* * Called from fixup_irqs() with @desc->lock held and interrupts disabled. */ diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c7503be92f35..57074cf3ad7c 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -248,7 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, switch (leaf) { case 1: l1 = &l1i; - /* fall through */ + fallthrough; case 0: if (!l1->val) return; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 7843ab3fde09..3a44346f2276 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -199,7 +199,7 @@ static int raise_local(void) * calling irq_enter, but the necessary * machinery isn't exported currently. */ - /*FALL THROUGH*/ + fallthrough; case MCJ_CTX_PROCESS: raise_exception(m, NULL); break; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index d8f9230d2034..abe9fe0fb851 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -193,7 +193,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); - /* FALLTHROUGH */ + fallthrough; case CMCI_STORM_SUBSIDED: /* diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 72182809b333..ca670919b561 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -98,7 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) case 7: if (size < 0x40) break; - /* Else, fall through */ + fallthrough; case 6: case 5: case 4: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8cdf29ffd95f..b98ff620ba77 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -349,7 +349,7 @@ static int arch_build_bp_info(struct perf_event *bp, hw->len = X86_BREAKPOINT_LEN_X; return 0; } - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 68acd30c6b87..c2f02f308ecf 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -450,7 +450,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->ip = addr; - /* fall through */ + fallthrough; case 'D': case 'k': /* clear the trace bit */ @@ -539,7 +539,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) * a system call which should be ignored */ return NOTIFY_DONE; - /* fall through */ + fallthrough; default: if (user_mode(regs)) return NOTIFY_DONE; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 411af4aa7b51..baa21090c9be 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -312,7 +312,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) case 2: if (i == 0 || i == 13) continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ + fallthrough; default: if (i == 2) continue; /* IRQ2 is never connected */ @@ -356,7 +356,7 @@ static void __init construct_ioapic_table(int mpc_default_type) default: pr_err("???\nUnknown standard configuration %d\n", mpc_default_type); - /* fall through */ + fallthrough; case 1: case 5: memcpy(bus.bustype, "ISA ", 6); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 994d8393f2f7..13ce616cc7af 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -684,9 +684,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -792,7 +790,6 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -804,7 +801,6 @@ static __cpuidle void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 5679aa3fdcb8..e7537c5440bb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -204,7 +204,7 @@ static int set_segment_reg(struct task_struct *task, case offsetof(struct user_regs_struct, ss): if (unlikely(value == 0)) return -EIO; - /* Else, fall through */ + fallthrough; default: *pt_regs_access(task_pt_regs(task), offset) = value; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0ec7ced727fe..a515e2d230b7 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -654,7 +654,7 @@ static void native_machine_emergency_restart(void) case BOOT_CF9_FORCE: port_cf9_safe = true; - /* Fall through */ + fallthrough; case BOOT_CF9_SAFE: if (port_cf9_safe) { diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d5fa494c2304..be0d7d4152ec 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -726,7 +726,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->ax = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 27aa04a95702..f5ef689dd62a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1594,14 +1594,28 @@ int native_cpu_disable(void) if (ret) return ret; - /* - * Disable the local APIC. Otherwise IPI broadcasts will reach - * it. It still responds normally to INIT, NMI, SMI, and SIPI - * messages. - */ - apic_soft_disable(); cpu_disable_common(); + /* + * Disable the local APIC. Otherwise IPI broadcasts will reach + * it. It still responds normally to INIT, NMI, SMI, and SIPI + * messages. + * + * Disabling the APIC must happen after cpu_disable_common() + * which invokes fixup_irqs(). + * + * Disabling the APIC preserves already set bits in IRR, but + * an interrupt arriving after disabling the local APIC does not + * set the corresponding IRR bit. + * + * fixup_irqs() scans IRR for set bits so it can raise a not + * yet handled interrupt on the new destination CPU via an IPI + * but obviously it can't do so for IRR bits which are not set. + * IOW, interrupts arriving after disabling the local APIC will + * be lost. + */ + apic_soft_disable(); + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1f66d2d1e998..81a2fb711091 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -729,20 +729,9 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) +static __always_inline unsigned long debug_read_clear_dr6(void) { - /* - * Disable breakpoints during exception handling; recursive exceptions - * are exceedingly 'fun'. - * - * Since this function is NOKPROBE, and that also applies to - * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a - * HW_BREAKPOINT_W on our stack) - * - * Entry text is excluded for HW_BP_X and cpu_entry_area, which - * includes the entry stack is excluded for everything. - */ - *dr7 = local_db_save(); + unsigned long dr6; /* * The Intel SDM says: @@ -755,15 +744,12 @@ static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) * * Keep it simple: clear DR6 immediately. */ - get_debugreg(*dr6, 6); + get_debugreg(dr6, 6); set_debugreg(0, 6); /* Filter out all the reserved bits which are preset to 1 */ - *dr6 &= ~DR6_RESERVED; -} + dr6 &= ~DR6_RESERVED; -static __always_inline void debug_exit(unsigned long dr7) -{ - local_db_restore(dr7); + return dr6; } /* @@ -863,6 +849,18 @@ out: static __always_inline void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6) { + /* + * Disable breakpoints during exception handling; recursive exceptions + * are exceedingly 'fun'. + * + * Since this function is NOKPROBE, and that also applies to + * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a + * HW_BREAKPOINT_W on our stack) + * + * Entry text is excluded for HW_BP_X and cpu_entry_area, which + * includes the entry stack is excluded for everything. + */ + unsigned long dr7 = local_db_save(); bool irq_state = idtentry_enter_nmi(regs); instrumentation_begin(); @@ -883,6 +881,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, instrumentation_end(); idtentry_exit_nmi(regs, irq_state); + + local_db_restore(dr7); } static __always_inline void exc_debug_user(struct pt_regs *regs, @@ -894,6 +894,15 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, */ WARN_ON_ONCE(!user_mode(regs)); + /* + * NB: We can't easily clear DR7 here because + * idtentry_exit_to_usermode() can invoke ptrace, schedule, access + * user memory, etc. This means that a recursive #DB is possible. If + * this happens, that #DB will hit exc_debug_kernel() and clear DR7. + * Since we're not on the IST stack right now, everything will be + * fine. + */ + irqentry_enter_from_user_mode(regs); instrumentation_begin(); @@ -907,36 +916,24 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); - exc_debug_kernel(regs, dr6); - debug_exit(dr7); + exc_debug_kernel(regs, debug_read_clear_dr6()); } /* User entry, runs on regular task stack */ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); - exc_debug_user(regs, dr6); - debug_exit(dr7); + exc_debug_user(regs, debug_read_clear_dr6()); } #else /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); + unsigned long dr6 = debug_read_clear_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); else exc_debug_kernel(regs, dr6); - - debug_exit(dr7); } #endif diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 8d5cbe1bbb3b..2c304fd0bb1a 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -45,11 +45,12 @@ * value that, lies close to the top of the kernel memory. The limit for the GDT * and the IDT are set to zero. * - * Given that SLDT and STR are not commonly used in programs that run on WineHQ - * or DOSEMU2, they are not emulated. - * - * The instruction smsw is emulated to return the value that the register CR0 + * The instruction SMSW is emulated to return the value that the register CR0 * has at boot time as set in the head_32. + * SLDT and STR are emulated to return the values that the kernel programmatically + * assigns: + * - SLDT returns (GDT_ENTRY_LDT * 8) if an LDT has been set, 0 if not. + * - STR returns (GDT_ENTRY_TSS * 8). * * Emulation is provided for both 32-bit and 64-bit processes. * @@ -244,16 +245,34 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, *data_size += UMIP_GDT_IDT_LIMIT_SIZE; memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE); - } else if (umip_inst == UMIP_INST_SMSW) { - unsigned long dummy_value = CR0_STATE; + } else if (umip_inst == UMIP_INST_SMSW || umip_inst == UMIP_INST_SLDT || + umip_inst == UMIP_INST_STR) { + unsigned long dummy_value; + + if (umip_inst == UMIP_INST_SMSW) { + dummy_value = CR0_STATE; + } else if (umip_inst == UMIP_INST_STR) { + dummy_value = GDT_ENTRY_TSS * 8; + } else if (umip_inst == UMIP_INST_SLDT) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL + down_read(¤t->mm->context.ldt_usr_sem); + if (current->mm->context.ldt) + dummy_value = GDT_ENTRY_LDT * 8; + else + dummy_value = 0; + up_read(¤t->mm->context.ldt_usr_sem); +#else + dummy_value = 0; +#endif + } /* - * Even though the CR0 register has 4 bytes, the number + * For these 3 instructions, the number * of bytes to be copied in the result buffer is determined * by whether the operand is a register or a memory location. * If operand is a register, return as many bytes as the operand * size. If operand is memory, return only the two least - * siginificant bytes of CR0. + * siginificant bytes. */ if (X86_MODRM_MOD(insn->modrm.value) == 3) *data_size = insn->opnd_bytes; @@ -261,7 +280,6 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, *data_size = 2; memcpy(data, &dummy_value, *data_size); - /* STR and SLDT are not emulated */ } else { return -EINVAL; } @@ -383,10 +401,6 @@ bool fixup_umip_exception(struct pt_regs *regs) umip_pr_warn(regs, "%s instruction cannot be used by applications.\n", umip_insns[umip_inst]); - /* Do not emulate (spoof) SLDT or STR. */ - if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT) - return false; - umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n"); if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size, diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 15e5aad8ac2c..3fdaa042823d 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -735,7 +735,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * OPCODE1() of the "short" jmp which checks the same condition. */ opc1 = OPCODE2(insn) - 0x10; - /* fall through */ + fallthrough; default: if (!is_cond_jmp_opcode(opc1)) return -ENOSYS; @@ -892,7 +892,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, fix_ip_or_call = 0; break; } - /* fall through */ + fallthrough; default: riprel_analyze(auprobe, &insn); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3fd6eec202d7..7456f9ad424b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -371,7 +371,7 @@ void kvm_set_cpu_caps(void) F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | - F(SERIALIZE) + F(SERIALIZE) | F(TSXLDTRK) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1d450d7710d6..2f6510de6b0c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3028,7 +3028,7 @@ static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) case 0xa4: /* movsb */ case 0xa5: /* movsd/w */ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; - /* fall through */ + fallthrough; case 0xaa: /* stosb */ case 0xab: /* stosd/w */ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 814d3aee5cef..1d330564eed8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1779,7 +1779,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); if (ret != HV_STATUS_INVALID_PORT_ID) break; - /* fall through - maybe userspace knows this conn_id. */ + fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) { diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index c47d2acec529..4aa1c2e00e2a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -285,7 +285,7 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->u.irqchip.irqchip) { case KVM_IRQCHIP_PIC_SLAVE: e->irqchip.pin += PIC_NUM_PINS / 2; - /* fall through */ + fallthrough; case KVM_IRQCHIP_PIC_MASTER: if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) return -EINVAL; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5ccbee7165a2..35cca2e0c802 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1053,7 +1053,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, switch (delivery_mode) { case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; - /* fall through */ + fallthrough; case APIC_DM_FIXED: if (unlikely(trig_mode && !level)) break; @@ -1341,7 +1341,7 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) break; case APIC_TASKPRI: report_tpr_access(apic, false); - /* fall thru */ + fallthrough; default: val = kvm_lapic_get_reg(apic, offset); break; @@ -2027,7 +2027,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - /* fall through */ + fallthrough; case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 76c5826e29a2..71aa3da2a0b7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4422,7 +4422,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; - /* fall through */ + fallthrough; case PT64_ROOT_4LEVEL: rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | nonleaf_bit8_rsvd | rsvd_bits(7, 7) | diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index e90bc436f584..598a769f1961 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1062,10 +1062,14 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, struct vmcb *hsave = svm->nested.hsave; struct vmcb __user *user_vmcb = (struct vmcb __user *) &user_kvm_nested_state->data.svm[0]; - struct vmcb_control_area ctl; - struct vmcb_save_area save; + struct vmcb_control_area *ctl; + struct vmcb_save_area *save; + int ret; u32 cr0; + BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) > + KVM_STATE_NESTED_SVM_VMCB_SIZE); + if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM) return -EINVAL; @@ -1097,13 +1101,22 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE) return -EINVAL; - if (copy_from_user(&ctl, &user_vmcb->control, sizeof(ctl))) - return -EFAULT; - if (copy_from_user(&save, &user_vmcb->save, sizeof(save))) - return -EFAULT; - if (!nested_vmcb_check_controls(&ctl)) - return -EINVAL; + ret = -ENOMEM; + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + save = kzalloc(sizeof(*save), GFP_KERNEL); + if (!ctl || !save) + goto out_free; + + ret = -EFAULT; + if (copy_from_user(ctl, &user_vmcb->control, sizeof(*ctl))) + goto out_free; + if (copy_from_user(save, &user_vmcb->save, sizeof(*save))) + goto out_free; + + ret = -EINVAL; + if (!nested_vmcb_check_controls(ctl)) + goto out_free; /* * Processor state contains L2 state. Check that it is @@ -1111,15 +1124,15 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ cr0 = kvm_read_cr0(vcpu); if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW)) - return -EINVAL; + goto out_free; /* * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). * TODO: validate reserved bits for all saved state. */ - if (!(save.cr0 & X86_CR0_PG)) - return -EINVAL; + if (!(save->cr0 & X86_CR0_PG)) + goto out_free; /* * All checks done, we can enter guest mode. L1 control fields @@ -1128,10 +1141,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * contains saved L1 state. */ copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); - hsave->save = save; + hsave->save = *save; svm->nested.vmcb = kvm_state->hdr.svm.vmcb_pa; - load_nested_vmcb_control(svm, &ctl); + load_nested_vmcb_control(svm, ctl); nested_prepare_vmcb_control(svm); if (!nested_svm_vmrun_msrpm(svm)) @@ -1139,7 +1152,13 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, out_set_gif: svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); - return 0; + + ret = 0; +out_free: + kfree(save); + kfree(ctl); + + return ret; } struct kvm_x86_nested_ops svm_nested_ops = { diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5764b87379cf..c91acabf18d0 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2668,7 +2668,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); - /* Fall through */ + fallthrough; default: return kvm_set_msr_common(vcpu, msr); } @@ -4170,6 +4170,8 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static int __init svm_init(void) { + __unused_size_checks(); + return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), THIS_MODULE); } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75cd720c9e8c..8646a797b7a8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4654,7 +4654,7 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return false; - /* fall through */ + fallthrough; case DB_VECTOR: return !(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); @@ -4827,7 +4827,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) } kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); - /* fall through */ + fallthrough; case BP_VECTOR: /* * Update instruction length as we may reinject #BP from @@ -5257,7 +5257,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) error_code = vmcs_read32(IDT_VECTORING_ERROR_CODE); } - /* fall through */ + fallthrough; case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; @@ -5610,7 +5610,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) * keeping track of global entries in shadow page tables. */ - /* fall-through */ + fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: kvm_mmu_unload(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -6579,7 +6579,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); @@ -6589,7 +6589,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_EXT_INTR: kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e3de0fe5af37..1994602a0851 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1116,14 +1116,12 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) vcpu->arch.eff_db[dr] = val; break; case 4: - /* fall through */ case 6: if (!kvm_dr6_valid(val)) return -1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: - /* fall through */ default: /* 7 */ if (!kvm_dr7_valid(val)) return -1; /* #GP */ @@ -1154,12 +1152,10 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: - /* fall through */ case 6: *val = vcpu->arch.dr6; break; case 5: - /* fall through */ default: /* 7 */ *val = vcpu->arch.dr7; break; @@ -3051,7 +3047,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; /* fall through */ + pr = true; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) @@ -4362,7 +4359,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; - /* fall through */ + fallthrough; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) @@ -8675,7 +8672,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - /* fall through */ + fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index d46fff11f06f..aa067859a70b 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_cmdline.o = -pg endif -CFLAGS_cmdline.o := -fno-stack-protector +CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables endif inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 4f1719e22d3c..b6da09339308 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -58,7 +58,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) { @@ -89,7 +89,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (!c) @@ -151,7 +151,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if ((c == '=') && !*opptr) { @@ -172,7 +172,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (myisspace(c)) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 31600d851fd8..5e69603ff63f 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -179,7 +179,7 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) if (insn->addr_bytes == 2) return -EINVAL; - /* fall through */ + fallthrough; case -EDOM: case offsetof(struct pt_regs, bx): @@ -362,7 +362,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_GS: return vm86regs->gs; case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -386,7 +385,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) */ return get_user_gs(regs); case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -786,7 +784,7 @@ int insn_get_code_seg_params(struct pt_regs *regs) */ return INSN_CODE_SEG_PARAMS(4, 8); case 3: /* Invalid setting. CS.L=1, CS.D=1 */ - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 73dc66d887f3..ec071cbb0804 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -186,7 +186,7 @@ void FPU_printall(void) case TAG_Special: /* Update tagi for the printk below */ tagi = FPU_Special(r); - /* fall through */ + fallthrough; case TAG_Valid: printk("st(%d) %c .%04lx %04lx %04lx %04lx e%+-6d ", i, getsign(r) ? '-' : '+', diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index 127ea54122d7..4a9887851ad8 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -1352,7 +1352,7 @@ static void fyl2xp1(FPU_REG *st0_ptr, u_char st0_tag) case TW_Denormal: if (denormal_operand() < 0) return; - /* fall through */ + fallthrough; case TAG_Zero: case TAG_Valid: setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr)); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 35f1498e9832..6e3e8a124903 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,6 +190,53 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } +/* + * Handle a fault on the vmalloc or module mapping area + * + * This is needed because there is a race condition between the time + * when the vmalloc mapping code updates the PMD to the point in time + * where it synchronizes this update with the other page-tables in the + * system. + * + * In this race window another thread/CPU can map an area on the same + * PMD, finds it already present and does not synchronize it with the + * rest of the system yet. As a result v[mz]alloc might return areas + * which are not mapped in every page-table in the system, causing an + * unhandled page-fault when they are accessed. + */ +static noinline int vmalloc_fault(unsigned long address) +{ + unsigned long pgd_paddr; + pmd_t *pmd_k; + pte_t *pte_k; + + /* Make sure we are in vmalloc area: */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "current" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + pgd_paddr = read_cr3_pa(); + pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); + if (!pmd_k) + return -1; + + if (pmd_large(*pmd_k)) + return 0; + + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + return -1; + + return 0; +} +NOKPROBE_SYMBOL(vmalloc_fault); + void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; @@ -1110,6 +1157,37 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); +#ifdef CONFIG_X86_32 + /* + * We can fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + * + * Before doing this on-demand faulting, ensure that the + * fault is not any of the following: + * 1. A fault on a PTE with a reserved bit set. + * 2. A fault caused by a user-mode access. (Do not demand- + * fault kernel memory due to user-mode accesses). + * 3. A fault caused by a page-level protection violation. + * (A demand fault would be on a non-present page which + * would have X86_PF_PROT==0). + * + * This is only needed to close a race condition on x86-32 in + * the vmalloc mapping/unmapping code. See the comment above + * vmalloc_fault() for details. On x86-64 the race does not + * exist as the vmalloc mappings don't need to be synchronized + * there. + */ + if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { + if (vmalloc_fault(address) >= 0) + return; + } +#endif + /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 84d85dbd1dad..9e5ccc56f8e0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -574,7 +574,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, /* For SEV, these areas are encrypted */ if (sev_active()) break; - /* Fallthrough */ + fallthrough; case E820_TYPE_PRAM: return true; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index c5174b4e318b..683cd12f4793 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -321,7 +321,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, u64 addr, u64 max_addr, u64 size) { return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, NUMA_NO_NODE); + 0, NULL, 0); } static int __init setup_emu2phys_nid(int *dfl_phys_nid) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1a3569b43aa5..0951b47e64c1 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); load_new_mm_cr3(next->pgd, new_asid, true); - /* - * NB: This gets called via leave_mm() in the idle path - * where RCU functions differently. Tracing normally - * uses RCU, so we need to use the _rcuidle variant. - * - * (There is no good reason for this. The idle code should - * be rearranged to call this before rcu_idle_enter().) - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ load_new_mm_cr3(next->pgd, new_asid, false); - /* See above wrt _rcuidle. */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } /* Make sure we write CR3 before loaded_mm. */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 76cee341507b..b3b17d6c50f0 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -448,7 +448,7 @@ static void do_signal(struct pt_regs *regs) regs->areg[2] = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->areg[2] = regs->syscall; regs->pc -= 3; |