From 4b6049b643f42d5744cba685d602cd5bc79f31b3 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 24 Jul 2024 10:17:12 +0530 Subject: [PATCH 01/10] arm64/mm: Drop PMD_SECT_VALID This just drops off the macro PMD_SECT_VALID which remains unused. Because macro PMD_TYPE_SECT with same value (_AT(pmdval_t, 1) << 0), gets used for creating or updating given block mappings. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Anshuman Khandual Reviewed-by: Ryan Roberts Link: https://lore.kernel.org/r/20240724044712.602210-1-anshuman.khandual@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable-hwdef.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 1f60aa1bc750..86e803ea8885 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -135,7 +135,6 @@ /* * Section */ -#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) #define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ #define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) From 6ac96d6f9a8ec3227ceb1e935aeda61bdaeb62ac Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 24 Jul 2024 09:44:28 +0530 Subject: [PATCH 02/10] arm64/mm: Drop TCR_SMP_FLAGS Earlier TCR_SMP_FLAGS gets conditionally set as TCR_SHARED with CONFIG_SMP. Currently CONFIG_SMP is always enabled on arm64 platforms, hence drop this indirection via TCR_SMP_FLAGS and instead always directly use TCR_SHARED. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Anshuman Khandual Reviewed-by: Ryan Roberts Link: https://lore.kernel.org/r/20240724041428.573748-1-anshuman.khandual@arm.com Signed-off-by: Will Deacon --- arch/arm64/mm/proc.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index f4bc6c5bac06..8abdc7fed321 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -36,8 +36,6 @@ #define TCR_KASLR_FLAGS 0 #endif -#define TCR_SMP_FLAGS TCR_SHARED - /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA @@ -469,7 +467,7 @@ SYM_FUNC_START(__cpu_setup) tcr .req x16 mov_q mair, MAIR_EL1_SET mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ - TCR_SMP_FLAGS | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ + TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS tcr_clear_errata_bits tcr, x9, x5 From fc2220c9b15828319b09384e68399b4afc6276d9 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 29 Jul 2024 16:20:05 +0100 Subject: [PATCH 03/10] arm64: signal: Fix some under-bracketed UAPI macros A few SME-related sigcontext UAPI macros leave an argument unprotected from misparsing during macro expansion. Add parentheses around references to macro arguments where appropriate. Signed-off-by: Dave Martin Fixes: ee072cf70804 ("arm64/sme: Implement signal handling for ZT") Fixes: 39782210eb7e ("arm64/sme: Implement ZA signal handling") Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20240729152005.289844-1-Dave.Martin@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/uapi/asm/sigcontext.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 8a45b7a411e0..57f76d82077e 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -320,10 +320,10 @@ struct zt_context { ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) +#define ZA_SIG_REGS_SIZE(vq) (((vq) * __SVE_VQ_BYTES) * ((vq) * __SVE_VQ_BYTES)) #define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ - (SVE_SIG_ZREG_SIZE(vq) * n)) + (SVE_SIG_ZREG_SIZE(vq) * (n))) #define ZA_SIG_CONTEXT_SIZE(vq) \ (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) @@ -334,7 +334,7 @@ struct zt_context { #define ZT_SIG_REGS_OFFSET sizeof(struct zt_context) -#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n) +#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * (n)) #define ZT_SIG_CONTEXT_SIZE(n) \ (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n)) From 5b39db6037e7cba1659f2149aef76934370aa6d5 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 29 Jul 2024 17:25:42 +0100 Subject: [PATCH 04/10] arm64: el2_setup.h: Rename some labels to be more diff-friendly A minor anti-pattern has established itself in __init_el2_fgt, where each block of instructions is skipped by jumping to a label named for the next (typically unrelated) block. This makes diffs more noisy than necessary, since appending each new block to deal with some new architecture feature now requires altering a branch destination in the existing code. Fix it by naming the affected labels based on the block that is skipping itself instead, as is done elsewhere in the el2_setup code. No functional change. Signed-off-by: Dave Martin Link: https://lore.kernel.org/r/20240729162542.367059-1-Dave.Martin@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/el2_setup.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index fd87c4b8f984..8eb113a6b452 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -165,42 +165,45 @@ mrs x1, id_aa64dfr0_el1 ubfx x1, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4 cmp x1, #3 - b.lt .Lset_debug_fgt_\@ + b.lt .Lskip_spe_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_debug_fgt_\@: +.Lskip_spe_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 mov x0, xzr mrs x1, id_aa64pfr1_el1 ubfx x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4 - cbz x1, .Lset_pie_fgt_\@ + cbz x1, .Lskip_debug_fgt_\@ /* Disable nVHE traps of TPIDR2 and SMPRI */ orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK -.Lset_pie_fgt_\@: +.Lskip_debug_fgt_\@: mrs_s x1, SYS_ID_AA64MMFR3_EL1 ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 - cbz x1, .Lset_fgt_\@ + cbz x1, .Lskip_pie_fgt_\@ /* Disable trapping of PIR_EL1 / PIRE0_EL1 */ orr x0, x0, #HFGxTR_EL2_nPIR_EL1 orr x0, x0, #HFGxTR_EL2_nPIRE0_EL1 -.Lset_fgt_\@: +.Lskip_pie_fgt_\@: msr_s SYS_HFGRTR_EL2, x0 msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU ubfx x1, x1, #ID_AA64PFR0_EL1_AMU_SHIFT, #4 - cbz x1, .Lskip_fgt_\@ + cbz x1, .Lskip_amu_fgt_\@ msr_s SYS_HAFGRTR_EL2, xzr + +.Lskip_amu_fgt_\@: + .Lskip_fgt_\@: .endm From 4960f9a5a5ac7784e03c9b5fe5456e80557e4b32 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 5 Aug 2024 22:00:38 +0800 Subject: [PATCH 05/10] arm64: mm: Remove unused declaration early_io_map() Commit bf4b558eba92 ("arm64: add early_ioremap support") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Anshuman Khandual Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20240805140038.1366033-1-yuehaibing@huawei.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/mmu.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 65977c7783c5..fc414cfd337e 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -63,7 +63,6 @@ static inline bool arm64_kernel_unmapped_at_el0(void) extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); -extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, From 93b81abc6ea9bf4eafec2af68484c6735e4f9167 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Sat, 10 Aug 2024 17:39:44 +0800 Subject: [PATCH 06/10] arm64/sve: Remove unused declaration read_smcr_features() Commit 391208485c3a ("arm64/sve: Remove SMCR pseudo register from cpufeature code") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Mark Brown Reviewed-by: Zenghui Yu Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240810093944.2587809-1-yuehaibing@huawei.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/fpsimd.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index bc69ac368d73..f2a84efc3618 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -155,8 +155,6 @@ extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); -extern u64 read_smcr_features(void); - /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the From fdfa588124b6356cd08e5d3f0c3643c4ec3d6887 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 21 Aug 2024 14:53:57 -0700 Subject: [PATCH 07/10] arm64: smp: smp_send_stop() and crash_smp_send_stop() should try non-NMI first When testing hard lockup handling on my sc7180-trogdor-lazor device with pseudo-NMI enabled, with serial console enabled and with kgdb disabled, I found that the stack crawls printed to the serial console ended up as a jumbled mess. After rebooting, the pstore-based console looked fine though. Also, enabling kgdb to trap the panic made the console look fine and avoided the mess. After a bit of tracking down, I came to the conclusion that this was what was happening: 1. The panic path was stopping all other CPUs with panic_other_cpus_shutdown(). 2. At least one of those other CPUs was in the middle of printing to the serial console and holding the console port's lock, which is grabbed with "irqsave". ...but since we were stopping with an NMI we didn't care about the "irqsave" and interrupted anyway. 3. Since we stopped the CPU while it was holding the lock it would never release it. 4. All future calls to output to the console would end up failing to get the lock in qcom_geni_serial_console_write(). This isn't _totally_ unexpected at panic time but it's a code path that's not well tested, hard to get right, and apparently doesn't work terribly well on the Qualcomm geni serial driver. The Qualcomm geni serial driver was fixed to be a bit better in commit 9e957a155005 ("serial: qcom-geni: Don't cancel/abort if we can't get the port lock") but it's nice not to get into this situation in the first place. Taking a page from what x86 appears to do in native_stop_other_cpus(), do this: 1. First, try to stop other CPUs with a normal IPI and wait a second. This gives them a chance to leave critical sections. 2. If CPUs fail to stop then retry with an NMI, but give a much lower timeout since there's no good reason for a CPU not to react quickly to a NMI. This works well and avoids the corrupted console and (presumably) could help avoid other similar issues. In order to do this, we need to do a little re-organization of our IPIs since we don't have any more free IDs. Do what was suggested in previous conversations and combine "stop" and "crash stop". That frees up an IPI so now we can have a "stop" and "stop NMI". In order to do this we also need a slight change in the way we keep track of which CPUs still need to be stopped. We need to know specifically which CPUs haven't stopped yet when we fall back to NMI but in the "crash stop" case the "cpu_online_mask" isn't updated as CPUs go down. This is why that code path had an atomic of the number of CPUs left. Solve this by also updating the "cpu_online_mask" for crash stops. All of the above lets us combine the logic for "stop" and "crash stop" code, which appeared to have a bunch of arbitrary implementation differences. Aside from the above change where we try a normal IPI and then an NMI, the combined function has a few subtle differences: * In the normal smp_send_stop(), if we fail to stop one or more CPUs then we won't include the current CPU (the one running smp_send_stop()) in the error message. * In crash_smp_send_stop(), if we fail to stop some CPUs we'll print the CPUs that we failed to stop instead of printing all _but_ the current running CPU. * In crash_smp_send_stop(), we will now only print "SMP: stopping secondary CPUs" if (system_state <= SYSTEM_RUNNING). Fixes: d7402513c935 ("arm64: smp: IPI_CPU_STOP and IPI_CPU_CRASH_STOP should try for NMI") Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20240821145353.v3.1.Id4817adef610302554b8aa42b090d57270dc119c@changeid Signed-off-by: Will Deacon --- arch/arm64/kernel/smp.c | 164 ++++++++++++++++++++++++---------------- 1 file changed, 99 insertions(+), 65 deletions(-) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 5e18fbcee9a2..33ebcac231da 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -68,7 +68,7 @@ enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, - IPI_CPU_CRASH_STOP, + IPI_CPU_STOP_NMI, IPI_TIMER, IPI_IRQ_WORK, NR_IPI, @@ -85,6 +85,8 @@ static int ipi_irq_base __ro_after_init; static int nr_ipi __ro_after_init = NR_IPI; static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init; +static bool crash_stop; + static void ipi_setup(int cpu); #ifdef CONFIG_HOTPLUG_CPU @@ -821,7 +823,7 @@ static const char *ipi_types[MAX_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNC] = "Function call interrupts", [IPI_CPU_STOP] = "CPU stop interrupts", - [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_CPU_STOP_NMI] = "CPU stop NMIs", [IPI_TIMER] = "Timer broadcast interrupts", [IPI_IRQ_WORK] = "IRQ work interrupts", [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", @@ -865,9 +867,9 @@ void arch_irq_work_raise(void) } #endif -static void __noreturn local_cpu_stop(void) +static void __noreturn local_cpu_stop(unsigned int cpu) { - set_cpu_online(smp_processor_id(), false); + set_cpu_online(cpu, false); local_daif_mask(); sdei_mask_local_cpu(); @@ -881,21 +883,26 @@ static void __noreturn local_cpu_stop(void) */ void __noreturn panic_smp_self_stop(void) { - local_cpu_stop(); + local_cpu_stop(smp_processor_id()); } -#ifdef CONFIG_KEXEC_CORE -static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); -#endif - static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) { #ifdef CONFIG_KEXEC_CORE + /* + * Use local_daif_mask() instead of local_irq_disable() to make sure + * that pseudo-NMIs are disabled. The "crash stop" code starts with + * an IRQ and falls back to NMI (which might be pseudo). If the IRQ + * finally goes through right as we're timing out then the NMI could + * interrupt us. It's better to prevent the NMI and let the IRQ + * finish since the pt_regs will be better. + */ + local_daif_mask(); + crash_save_cpu(regs, cpu); - atomic_dec(&waiting_for_crash_ipi); + set_cpu_online(cpu, false); - local_irq_disable(); sdei_mask_local_cpu(); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) @@ -960,14 +967,12 @@ static void do_handle_IPI(int ipinr) break; case IPI_CPU_STOP: - local_cpu_stop(); - break; - - case IPI_CPU_CRASH_STOP: - if (IS_ENABLED(CONFIG_KEXEC_CORE)) { + case IPI_CPU_STOP_NMI: + if (IS_ENABLED(CONFIG_KEXEC_CORE) && crash_stop) { ipi_cpu_crash_stop(cpu, get_irq_regs()); - unreachable(); + } else { + local_cpu_stop(cpu); } break; @@ -1022,8 +1027,7 @@ static bool ipi_should_be_nmi(enum ipi_msg_type ipi) return false; switch (ipi) { - case IPI_CPU_STOP: - case IPI_CPU_CRASH_STOP: + case IPI_CPU_STOP_NMI: case IPI_CPU_BACKTRACE: case IPI_KGDB_ROUNDUP: return true; @@ -1136,47 +1140,10 @@ static inline unsigned int num_other_online_cpus(void) void smp_send_stop(void) { - unsigned long timeout; - - if (num_other_online_cpus()) { - cpumask_t mask; - - cpumask_copy(&mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &mask); - - if (system_state <= SYSTEM_RUNNING) - pr_crit("SMP: stopping secondary CPUs\n"); - smp_cross_call(&mask, IPI_CPU_STOP); - } - - /* Wait up to one second for other CPUs to stop */ - timeout = USEC_PER_SEC; - while (num_other_online_cpus() && timeout--) - udelay(1); - - if (num_other_online_cpus()) - pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", - cpumask_pr_args(cpu_online_mask)); - - sdei_mask_local_cpu(); -} - -#ifdef CONFIG_KEXEC_CORE -void crash_smp_send_stop(void) -{ - static int cpus_stopped; + static unsigned long stop_in_progress; cpumask_t mask; unsigned long timeout; - /* - * This function can be called twice in panic path, but obviously - * we execute this only once. - */ - if (cpus_stopped) - return; - - cpus_stopped = 1; - /* * If this cpu is the only one alive at this point in time, online or * not, there are no stop messages to be sent around, so just back out. @@ -1184,31 +1151,98 @@ void crash_smp_send_stop(void) if (num_other_online_cpus() == 0) goto skip_ipi; + /* Only proceed if this is the first CPU to reach this code */ + if (test_and_set_bit(0, &stop_in_progress)) + return; + + /* + * Send an IPI to all currently online CPUs except the CPU running + * this code. + * + * NOTE: we don't do anything here to prevent other CPUs from coming + * online after we snapshot `cpu_online_mask`. Ideally, the calling code + * should do something to prevent other CPUs from coming up. This code + * can be called in the panic path and thus it doesn't seem wise to + * grab the CPU hotplug mutex ourselves. Worst case: + * - If a CPU comes online as we're running, we'll likely notice it + * during the 1 second wait below and then we'll catch it when we try + * with an NMI (assuming NMIs are enabled) since we re-snapshot the + * mask before sending an NMI. + * - If we leave the function and see that CPUs are still online we'll + * at least print a warning. Especially without NMIs this function + * isn't foolproof anyway so calling code will just have to accept + * the fact that there could be cases where a CPU can't be stopped. + */ cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); - atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); + if (system_state <= SYSTEM_RUNNING) + pr_crit("SMP: stopping secondary CPUs\n"); - pr_crit("SMP: stopping secondary CPUs\n"); - smp_cross_call(&mask, IPI_CPU_CRASH_STOP); - - /* Wait up to one second for other CPUs to stop */ + /* + * Start with a normal IPI and wait up to one second for other CPUs to + * stop. We do this first because it gives other processors a chance + * to exit critical sections / drop locks and makes the rest of the + * stop process (especially console flush) more robust. + */ + smp_cross_call(&mask, IPI_CPU_STOP); timeout = USEC_PER_SEC; - while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + while (num_other_online_cpus() && timeout--) udelay(1); - if (atomic_read(&waiting_for_crash_ipi) > 0) + /* + * If CPUs are still online, try an NMI. There's no excuse for this to + * be slow, so we only give them an extra 10 ms to respond. + */ + if (num_other_online_cpus() && ipi_should_be_nmi(IPI_CPU_STOP_NMI)) { + smp_rmb(); + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + pr_info("SMP: retry stop with NMI for CPUs %*pbl\n", + cpumask_pr_args(&mask)); + + smp_cross_call(&mask, IPI_CPU_STOP_NMI); + timeout = USEC_PER_MSEC * 10; + while (num_other_online_cpus() && timeout--) + udelay(1); + } + + if (num_other_online_cpus()) { + smp_rmb(); + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(&mask)); + } skip_ipi: sdei_mask_local_cpu(); +} + +#ifdef CONFIG_KEXEC_CORE +void crash_smp_send_stop(void) +{ + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + * + * We use this same boolean to tell whether the IPI we send was a + * stop or a "crash stop". + */ + if (crash_stop) + return; + crash_stop = 1; + + smp_send_stop(); + sdei_handler_abort(); } bool smp_crash_stop_failed(void) { - return (atomic_read(&waiting_for_crash_ipi) > 0); + return num_other_online_cpus() != 0; } #endif From 684fbd42d323c9c4a69a905451ea270678e36d1e Mon Sep 17 00:00:00 2001 From: Huang Xiaojia Date: Mon, 26 Aug 2024 23:12:50 +0800 Subject: [PATCH 08/10] arm64: Constify struct kobj_type 'struct kobj_type' is not modified. It is only used in kobject_init() which takes a 'const struct kobj_type *ktype' parameter. Constifying this structure moves some data to a read-only section, so increase over all security. On a x86_64, compiled with arm defconfig: Before: ====== text data bss dec hex filename 5602 548 352 6502 1966 arch/arm64/kernel/cpuinfo.o After: ====== text data bss dec hex filename 5650 500 352 6502 1966 arch/arm64/kernel/cpuinfo.o Signed-off-by: Huang Xiaojia Link: https://lore.kernel.org/r/20240826151250.3500302-1-huangxiaojia2@huawei.com Signed-off-by: Will Deacon --- arch/arm64/kernel/cpuinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 09eeaa24d456..369dd72a8b22 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -280,7 +280,7 @@ const struct seq_operations cpuinfo_op = { }; -static struct kobj_type cpuregs_kobj_type = { +static const struct kobj_type cpuregs_kobj_type = { .sysfs_ops = &kobj_sysfs_ops, }; From b6db3eb6c373b97d9e433530d748590421bbeea7 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Tue, 10 Sep 2024 11:50:16 +0300 Subject: [PATCH 09/10] arm64: esr: Define ESR_ELx_EC_* constants as UL Add explicit casting to prevent expantion of 32th bit of u32 into highest half of u64 in several places. For example, in inject_abt64: ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT = 0x24 << 26. This operation's result is int with 1 in 32th bit. While casting this value into u64 (esr is u64) 1 fills 32 highest bits. Found by Linux Verification Center (linuxtesting.org) with SVACE. Cc: Fixes: aa8eff9bfbd5 ("arm64: KVM: fault injection into a guest") Signed-off-by: Anastasia Belova Acked-by: Marc Zyngier Link: https://lore.kernel.org/stable/20240910085016.32120-1-abelova%40astralinux.ru Link: https://lore.kernel.org/r/20240910085016.32120-1-abelova@astralinux.ru Signed-off-by: Will Deacon --- arch/arm64/include/asm/esr.h | 88 ++++++++++++++++++------------------ 1 file changed, 44 insertions(+), 44 deletions(-) diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 56c148890daf..2f3d56857a97 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -10,63 +10,63 @@ #include #include -#define ESR_ELx_EC_UNKNOWN (0x00) -#define ESR_ELx_EC_WFx (0x01) +#define ESR_ELx_EC_UNKNOWN UL(0x00) +#define ESR_ELx_EC_WFx UL(0x01) /* Unallocated EC: 0x02 */ -#define ESR_ELx_EC_CP15_32 (0x03) -#define ESR_ELx_EC_CP15_64 (0x04) -#define ESR_ELx_EC_CP14_MR (0x05) -#define ESR_ELx_EC_CP14_LS (0x06) -#define ESR_ELx_EC_FP_ASIMD (0x07) -#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ -#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +#define ESR_ELx_EC_CP15_32 UL(0x03) +#define ESR_ELx_EC_CP15_64 UL(0x04) +#define ESR_ELx_EC_CP14_MR UL(0x05) +#define ESR_ELx_EC_CP14_LS UL(0x06) +#define ESR_ELx_EC_FP_ASIMD UL(0x07) +#define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */ /* Unallocated EC: 0x0A - 0x0B */ -#define ESR_ELx_EC_CP14_64 (0x0C) -#define ESR_ELx_EC_BTI (0x0D) -#define ESR_ELx_EC_ILL (0x0E) +#define ESR_ELx_EC_CP14_64 UL(0x0C) +#define ESR_ELx_EC_BTI UL(0x0D) +#define ESR_ELx_EC_ILL UL(0x0E) /* Unallocated EC: 0x0F - 0x10 */ -#define ESR_ELx_EC_SVC32 (0x11) -#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ -#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +#define ESR_ELx_EC_SVC32 UL(0x11) +#define ESR_ELx_EC_HVC32 UL(0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 UL(0x13) /* EL2 and above */ /* Unallocated EC: 0x14 */ -#define ESR_ELx_EC_SVC64 (0x15) -#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ -#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ -#define ESR_ELx_EC_SYS64 (0x18) -#define ESR_ELx_EC_SVE (0x19) -#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +#define ESR_ELx_EC_SVC64 UL(0x15) +#define ESR_ELx_EC_HVC64 UL(0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 UL(0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 UL(0x18) +#define ESR_ELx_EC_SVE UL(0x19) +#define ESR_ELx_EC_ERET UL(0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ -#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -#define ESR_ELx_EC_SME (0x1D) +#define ESR_ELx_EC_FPAC UL(0x1C) /* EL1 and above */ +#define ESR_ELx_EC_SME UL(0x1D) /* Unallocated EC: 0x1E */ -#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ -#define ESR_ELx_EC_IABT_LOW (0x20) -#define ESR_ELx_EC_IABT_CUR (0x21) -#define ESR_ELx_EC_PC_ALIGN (0x22) +#define ESR_ELx_EC_IMP_DEF UL(0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW UL(0x20) +#define ESR_ELx_EC_IABT_CUR UL(0x21) +#define ESR_ELx_EC_PC_ALIGN UL(0x22) /* Unallocated EC: 0x23 */ -#define ESR_ELx_EC_DABT_LOW (0x24) -#define ESR_ELx_EC_DABT_CUR (0x25) -#define ESR_ELx_EC_SP_ALIGN (0x26) -#define ESR_ELx_EC_MOPS (0x27) -#define ESR_ELx_EC_FP_EXC32 (0x28) +#define ESR_ELx_EC_DABT_LOW UL(0x24) +#define ESR_ELx_EC_DABT_CUR UL(0x25) +#define ESR_ELx_EC_SP_ALIGN UL(0x26) +#define ESR_ELx_EC_MOPS UL(0x27) +#define ESR_ELx_EC_FP_EXC32 UL(0x28) /* Unallocated EC: 0x29 - 0x2B */ -#define ESR_ELx_EC_FP_EXC64 (0x2C) +#define ESR_ELx_EC_FP_EXC64 UL(0x2C) /* Unallocated EC: 0x2D - 0x2E */ -#define ESR_ELx_EC_SERROR (0x2F) -#define ESR_ELx_EC_BREAKPT_LOW (0x30) -#define ESR_ELx_EC_BREAKPT_CUR (0x31) -#define ESR_ELx_EC_SOFTSTP_LOW (0x32) -#define ESR_ELx_EC_SOFTSTP_CUR (0x33) -#define ESR_ELx_EC_WATCHPT_LOW (0x34) -#define ESR_ELx_EC_WATCHPT_CUR (0x35) +#define ESR_ELx_EC_SERROR UL(0x2F) +#define ESR_ELx_EC_BREAKPT_LOW UL(0x30) +#define ESR_ELx_EC_BREAKPT_CUR UL(0x31) +#define ESR_ELx_EC_SOFTSTP_LOW UL(0x32) +#define ESR_ELx_EC_SOFTSTP_CUR UL(0x33) +#define ESR_ELx_EC_WATCHPT_LOW UL(0x34) +#define ESR_ELx_EC_WATCHPT_CUR UL(0x35) /* Unallocated EC: 0x36 - 0x37 */ -#define ESR_ELx_EC_BKPT32 (0x38) +#define ESR_ELx_EC_BKPT32 UL(0x38) /* Unallocated EC: 0x39 */ -#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +#define ESR_ELx_EC_VECTOR32 UL(0x3A) /* EL2 only */ /* Unallocated EC: 0x3B */ -#define ESR_ELx_EC_BRK64 (0x3C) +#define ESR_ELx_EC_BRK64 UL(0x3C) /* Unallocated EC: 0x3D - 0x3F */ -#define ESR_ELx_EC_MAX (0x3F) +#define ESR_ELx_EC_MAX UL(0x3F) #define ESR_ELx_EC_SHIFT (26) #define ESR_ELx_EC_WIDTH (6) From ecdd16df45649e344e38ec59a3022e13419a695a Mon Sep 17 00:00:00 2001 From: Min-Hua Chen Date: Wed, 11 Sep 2024 07:25:05 +0800 Subject: [PATCH 10/10] arm64: hibernate: Fix warning for cast from restricted gfp_t This patch fixes the following warning by adding __force to the cast: arch/arm64/kernel/hibernate.c:410:44: sparse: warning: cast from restricted gfp_t No functional change intended. Signed-off-by: Min-Hua Chen Link: https://lore.kernel.org/r/20240910232507.313555-1-minhuadotchen@gmail.com Signed-off-by: Will Deacon --- arch/arm64/kernel/hibernate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 02870beb271e..7b11d84f533c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -407,7 +407,7 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); struct trans_pgd_info trans_info = { .trans_alloc_page = hibernate_page_alloc, - .trans_alloc_arg = (void *)GFP_ATOMIC, + .trans_alloc_arg = (__force void *)GFP_ATOMIC, }; /*