From 7697a0fe0154468f5df35c23ebd7aa48994c2cdc Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:58 +0800 Subject: [PATCH 01/16] LoongArch: Define __ARCH_WANT_NEW_STAT in unistd.h Chromium sandbox apparently wants to deny statx [1] so it could properly inspect arguments after the sandboxed process later falls back to fstat. Because there's currently not a "fd-only" version of statx, so that the sandbox has no way to ensure the path argument is empty without being able to peek into the sandboxed process's memory. For architectures able to do newfstatat though, glibc falls back to newfstatat after getting -ENOSYS for statx, then the respective SIGSYS handler [2] takes care of inspecting the path argument, transforming allowed newfstatat's into fstat instead which is allowed and has the same type of return value. But, as LoongArch is the first architecture to not have fstat nor newfstatat, the LoongArch glibc does not attempt falling back at all when it gets -ENOSYS for statx -- and you see the problem there! Actually, back when the LoongArch port was under review, people were aware of the same problem with sandboxing clone3 [3], so clone was eventually kept. Unfortunately it seemed at that time no one had noticed statx, so besides restoring fstat/newfstatat to LoongArch uapi (and postponing the problem further), it seems inevitable that we would need to tackle seccomp deep argument inspection. However, this is obviously a decision that shouldn't be taken lightly, so we just restore fstat/newfstatat by defining __ARCH_WANT_NEW_STAT in unistd.h. This is the simplest solution for now, and so we hope the community will tackle the long-standing problem of seccomp deep argument inspection in the future [4][5]. Also add "newstat" to syscall_abis_64 in Makefile.syscalls due to upstream asm-generic changes. More infomation please reading this thread [6]. [1] https://chromium-review.googlesource.com/c/chromium/src/+/2823150 [2] https://chromium.googlesource.com/chromium/src/sandbox/+/c085b51940bd/linux/seccomp-bpf-helpers/sigsys_handlers.cc#355 [3] https://lore.kernel.org/linux-arch/20220511211231.GG7074@brightrain.aerifal.cx/ [4] https://lwn.net/Articles/799557/ [5] https://lpc.events/event/4/contributions/560/attachments/397/640/deep-arg-inspection.pdf [6] https://lore.kernel.org/loongarch/20240226-granit-seilschaft-eccc2433014d@brauner/T/#t Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/unistd.h | 1 + arch/loongarch/kernel/Makefile.syscalls | 3 +-- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/include/asm/unistd.h b/arch/loongarch/include/asm/unistd.h index fc0a481a7416b..e2c0f3d86c7bd 100644 --- a/arch/loongarch/include/asm/unistd.h +++ b/arch/loongarch/include/asm/unistd.h @@ -8,6 +8,7 @@ #include +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE #define NR_syscalls (__NR_syscalls) diff --git a/arch/loongarch/kernel/Makefile.syscalls b/arch/loongarch/kernel/Makefile.syscalls index ab7d9baa29152..523bb411a3bca 100644 --- a/arch/loongarch/kernel/Makefile.syscalls +++ b/arch/loongarch/kernel/Makefile.syscalls @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -# No special ABIs on loongarch so far -syscall_abis_64 += +syscall_abis_64 += newstat From 12d3b559b85e75640b79995e1320588d6f0d5630 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:58 +0800 Subject: [PATCH 02/16] LoongArch: Always enumerate MADT and setup logical-physical CPU mapping Some drivers want to use cpu_logical_map(), early_cpu_to_node() and some other CPU mapping APIs, even if we use "nr_cpus=1" to hard limit the CPU number. This is strongly required for the multi-bridges machines. Currently, we stop parsing the MADT if the nr_cpus limit is reached, but to achieve the above goal we should always enumerate the MADT table and setup logical-physical CPU mapping whether there is a nr_cpus limit. Rework the MADT enumeration: 1. Define a flag "cpu_enumerated" to distinguish the first enumeration (cpu_enumerated=0) and the physical hotplug case (cpu_enumerated=1) for set_processor_mask(). 2. If cpu_enumerated=0, stop parsing only when NR_CPUS limit is reached, so we can setup logical-physical CPU mapping; if cpu_enumerated=1, stop parsing when nr_cpu_ids limit is reached, so we can avoid some runtime bugs. Once logical-physical CPU mapping is setup, we will let cpu_enumerated=1. 3. Use find_first_zero_bit() instead of cpumask_next_zero() to find the next zero bit (free logical CPU id) in the cpu_present_mask, because cpumask_next_zero() will stop at nr_cpu_ids. 4. Only touch cpu_possible_mask if cpu_enumerated=0, this is in order to avoid some potential crashes, because cpu_possible_mask is marked as __ro_after_init. 5. In prefill_possible_map(), clear cpu_present_mask bits greater than nr_cpu_ids, in order to avoid a CPU be "present" but not "possible". Signed-off-by: Huacai Chen --- arch/loongarch/kernel/acpi.c | 22 ++++++++++++++++------ arch/loongarch/kernel/setup.c | 4 +++- arch/loongarch/kernel/smp.c | 7 +++---- 3 files changed, 22 insertions(+), 11 deletions(-) diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 5cf59c617126b..929a497c987e8 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -57,15 +57,22 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) return ioremap_cache(phys, size); } +static int cpu_enumerated = 0; + #ifdef CONFIG_SMP static int set_processor_mask(u32 id, u32 flags) { - + int nr_cpus; int cpu, cpuid = id; - if (num_processors >= nr_cpu_ids) { - pr_warn(PREFIX "nr_cpus/possible_cpus limit of %i reached." - " processor 0x%x ignored.\n", nr_cpu_ids, cpuid); + if (!cpu_enumerated) + nr_cpus = NR_CPUS; + else + nr_cpus = nr_cpu_ids; + + if (num_processors >= nr_cpus) { + pr_warn(PREFIX "nr_cpus limit of %i reached." + " processor 0x%x ignored.\n", nr_cpus, cpuid); return -ENODEV; @@ -73,11 +80,13 @@ static int set_processor_mask(u32 id, u32 flags) if (cpuid == loongson_sysconf.boot_cpu_id) cpu = 0; else - cpu = cpumask_next_zero(-1, cpu_present_mask); + cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS); + + if (!cpu_enumerated) + set_cpu_possible(cpu, true); if (flags & ACPI_MADT_ENABLED) { num_processors++; - set_cpu_possible(cpu, true); set_cpu_present(cpu, true); __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; @@ -138,6 +147,7 @@ static void __init acpi_process_madt(void) acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, acpi_parse_eio_master, MAX_IO_PICS); + cpu_enumerated = 1; loongson_sysconf.nr_cpus = num_processors; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 3d048f1be1438..0f0740f0be274 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -576,8 +576,10 @@ static void __init prefill_possible_map(void) for (i = 0; i < possible; i++) set_cpu_possible(i, true); - for (; i < NR_CPUS; i++) + for (; i < NR_CPUS; i++) { + set_cpu_present(i, false); set_cpu_possible(i, false); + } set_nr_cpu_ids(possible); } diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 1436d2465939b..03b2b7669cf5d 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -271,11 +271,10 @@ static void __init fdt_smp_setup(void) if (cpuid >= nr_cpu_ids) continue; - if (cpuid == loongson_sysconf.boot_cpu_id) { + if (cpuid == loongson_sysconf.boot_cpu_id) cpu = 0; - } else { - cpu = cpumask_next_zero(-1, cpu_present_mask); - } + else + cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS); num_processors++; set_cpu_possible(cpu, true); From 08f417db702c5b05150b3851af7186fee96ddd46 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:58 +0800 Subject: [PATCH 03/16] LoongArch: Add irq_work support via self IPIs Add irq_work support for LoongArch via self IPIs. This make it possible to run works in hardware interrupt context, which is a prerequisite for NOHZ_FULL. Implement: - arch_irq_work_raise() - arch_irq_work_has_interrupt() Reviewed-by: Guo Ren Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/hardirq.h | 3 ++- arch/loongarch/include/asm/irq_work.h | 10 ++++++++++ arch/loongarch/include/asm/smp.h | 2 ++ arch/loongarch/kernel/paravirt.c | 6 ++++++ arch/loongarch/kernel/smp.c | 14 ++++++++++++++ 5 files changed, 34 insertions(+), 1 deletion(-) create mode 100644 arch/loongarch/include/asm/irq_work.h diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h index d41138abcf26d..1d7feb7195157 100644 --- a/arch/loongarch/include/asm/hardirq.h +++ b/arch/loongarch/include/asm/hardirq.h @@ -12,11 +12,12 @@ extern void ack_bad_irq(unsigned int irq); #define ack_bad_irq ack_bad_irq -#define NR_IPI 2 +#define NR_IPI 3 enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNCTION, + IPI_IRQ_WORK, }; typedef struct { diff --git a/arch/loongarch/include/asm/irq_work.h b/arch/loongarch/include/asm/irq_work.h new file mode 100644 index 0000000000000..d63076e9160d5 --- /dev/null +++ b/arch/loongarch/include/asm/irq_work.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_IRQ_WORK_H +#define _ASM_LOONGARCH_IRQ_WORK_H + +static inline bool arch_irq_work_has_interrupt(void) +{ + return IS_ENABLED(CONFIG_SMP); +} + +#endif /* _ASM_LOONGARCH_IRQ_WORK_H */ diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 278700cfee887..50db503f44e3c 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -69,9 +69,11 @@ extern int __cpu_logical_map[NR_CPUS]; #define ACTION_BOOT_CPU 0 #define ACTION_RESCHEDULE 1 #define ACTION_CALL_FUNCTION 2 +#define ACTION_IRQ_WORK 3 #define SMP_BOOT_CPU BIT(ACTION_BOOT_CPU) #define SMP_RESCHEDULE BIT(ACTION_RESCHEDULE) #define SMP_CALL_FUNCTION BIT(ACTION_CALL_FUNCTION) +#define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK) struct secondary_data { unsigned long stack; diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c index 1633ed4f692f6..4272d24474453 100644 --- a/arch/loongarch/kernel/paravirt.c +++ b/arch/loongarch/kernel/paravirt.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -97,6 +98,11 @@ static irqreturn_t pv_ipi_interrupt(int irq, void *dev) info->ipi_irqs[IPI_CALL_FUNCTION]++; } + if (action & SMP_IRQ_WORK) { + irq_work_run(); + info->ipi_irqs[IPI_IRQ_WORK]++; + } + return IRQ_HANDLED; } diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 03b2b7669cf5d..ca405ab86aaef 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -70,6 +71,7 @@ static DEFINE_PER_CPU(int, cpu_state); static const char *ipi_types[NR_IPI] __tracepoint_string = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNCTION] = "Function call interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", }; void show_ipi_list(struct seq_file *p, int prec) @@ -217,6 +219,13 @@ void arch_smp_send_reschedule(int cpu) } EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + mp_ops.send_ipi_single(smp_processor_id(), ACTION_IRQ_WORK); +} +#endif + static irqreturn_t loongson_ipi_interrupt(int irq, void *dev) { unsigned int action; @@ -234,6 +243,11 @@ static irqreturn_t loongson_ipi_interrupt(int irq, void *dev) per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++; } + if (action & SMP_IRQ_WORK) { + irq_work_run(); + per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++; + } + return IRQ_HANDLED; } From a0f7085f6a63f19f83f2644ce2da49a8d3cf7c0f Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Sat, 20 Jul 2024 22:40:58 +0800 Subject: [PATCH 04/16] LoongArch: Add RANDOMIZE_KSTACK_OFFSET support Add support of kernel stack offset randomization while handling syscall, the offset is defaultly limited by KSTACK_OFFSET_MAX(). In order to avoid triggering stack canaries (due to __builtin_alloca()) and slowing down the entry path, use __no_stack_protector attribute to disable stack protector for do_syscall() at function level. With this patch, the REPORT_STACK test show that: `loongarch64 bits of stack entropy: 7` Reviewed-by: Kees Cook Signed-off-by: Jinjie Ruan Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/kernel/syscall.c | 22 +++++++++++++++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index ddc042895d011..fcf6451b4e384 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -106,6 +106,7 @@ config LOONGARCH select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB if PERF_EVENTS select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index ec17cd5163b7c..ba5d0930a74f7 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -9,11 +9,14 @@ #include #include #include +#include +#include #include #include #include #include +#include #include #include #include @@ -39,7 +42,7 @@ void *sys_call_table[__NR_syscalls] = { typedef long (*sys_call_fn)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -void noinstr do_syscall(struct pt_regs *regs) +void noinstr __no_stack_protector do_syscall(struct pt_regs *regs) { unsigned long nr; sys_call_fn syscall_fn; @@ -55,11 +58,28 @@ void noinstr do_syscall(struct pt_regs *regs) nr = syscall_enter_from_user_mode(regs, nr); + add_random_kstack_offset(); + if (nr < NR_syscalls) { syscall_fn = sys_call_table[nr]; regs->regs[4] = syscall_fn(regs->orig_a0, regs->regs[5], regs->regs[6], regs->regs[7], regs->regs[8], regs->regs[9]); } + /* + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints: 16-bytes (i.e. 4-bits) + * aligned, which will remove the 4 low bits from any entropy chosen + * here. + * + * The resulting 6 bits of entropy is seen in SP[9:4]. + */ + choose_random_kstack_offset(drdtime()); + syscall_exit_to_user_mode(regs); } + +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET +STACK_FRAME_NON_STANDARD(do_syscall); +#endif From b7a2750ef268e2723acb785c4903b0b78c3dcbc6 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:59 +0800 Subject: [PATCH 05/16] LoongArch: Add ARCH_HAS_PTE_DEVMAP support In order for things like get_user_pages() to work on ZONE_DEVICE memory, we need a software PTE bit to identify device-backed PFNs. Hook this up along with the relevant helpers to join in with ARCH_HAS_PTE_DEVMAP. Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/pgtable-bits.h | 6 ++++-- arch/loongarch/include/asm/pgtable.h | 19 +++++++++++++++++++ 3 files changed, 24 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index fcf6451b4e384..be5249ebd8fc3 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -22,6 +22,7 @@ config LOONGARCH select ARCH_HAS_KERNEL_FPU_SUPPORT if CPU_HAS_FPU select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_INLINE_READ_LOCK if !PREEMPTION diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 21319c1e045c2..82cd3a9f094b8 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -22,6 +22,7 @@ #define _PAGE_PFN_SHIFT 12 #define _PAGE_SWP_EXCLUSIVE_SHIFT 23 #define _PAGE_PFN_END_SHIFT 48 +#define _PAGE_DEVMAP_SHIFT 59 #define _PAGE_PRESENT_INVALID_SHIFT 60 #define _PAGE_NO_READ_SHIFT 61 #define _PAGE_NO_EXEC_SHIFT 62 @@ -35,6 +36,7 @@ #define _PAGE_MODIFIED (_ULCAST_(1) << _PAGE_MODIFIED_SHIFT) #define _PAGE_PROTNONE (_ULCAST_(1) << _PAGE_PROTNONE_SHIFT) #define _PAGE_SPECIAL (_ULCAST_(1) << _PAGE_SPECIAL_SHIFT) +#define _PAGE_DEVMAP (_ULCAST_(1) << _PAGE_DEVMAP_SHIFT) /* We borrow bit 23 to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE (_ULCAST_(1) << _PAGE_SWP_EXCLUSIVE_SHIFT) @@ -74,8 +76,8 @@ #define __READABLE (_PAGE_VALID) #define __WRITEABLE (_PAGE_DIRTY | _PAGE_WRITE) -#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) -#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) +#define _PAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV) +#define _HPAGE_CHG_MASK (_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_NO_READ | \ _PAGE_USER | _CACHE_CC) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index af3acdf3481a6..0e821be632689 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -424,6 +424,9 @@ static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; static inline pte_t pte_mkspecial(pte_t pte) { pte_val(pte) |= _PAGE_SPECIAL; return pte; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ +static inline int pte_devmap(pte_t pte) { return !!(pte_val(pte) & _PAGE_DEVMAP); } +static inline pte_t pte_mkdevmap(pte_t pte) { pte_val(pte) |= _PAGE_DEVMAP; return pte; } + #define pte_accessible pte_accessible static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) { @@ -558,6 +561,17 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pmd; } +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} + +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + pmd_val(pmd) |= _PAGE_DEVMAP; + return pmd; +} + static inline struct page *pmd_page(pmd_t pmd) { if (pmd_trans_huge(pmd)) @@ -613,6 +627,11 @@ static inline long pmd_protnone(pmd_t pmd) #define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0) #define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define pud_devmap(pud) (0) +#define pgd_devmap(pgd) (0) +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + /* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. From 614d7e99752e02ff6f6d447a83d2929b9649b6cb Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:59 +0800 Subject: [PATCH 06/16] LoongArch: Add ARCH_HAS_DEBUG_VM_PGTABLE support Add ARCH_HAS_DEBUG_VM_PGTABLE selection in Kconfig, in order to make corresponding vm debug features usable on LoongArch. Also update the corresponding arch-support.txt document. Signed-off-by: Huacai Chen --- Documentation/features/debug/debug-vm-pgtable/arch-support.txt | 2 +- arch/loongarch/Kconfig | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt index bbf029f095cb5..156687a7436d6 100644 --- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt +++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt @@ -12,7 +12,7 @@ | arm64: | ok | | csky: | TODO | | hexagon: | TODO | - | loongarch: | TODO | + | loongarch: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index be5249ebd8fc3..0693b621ebd4b 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -16,6 +16,7 @@ config LOONGARCH select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER + select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV From 8e02c3b782ec64343f3cccc8dc5a8be2b379e80b Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:40:59 +0800 Subject: [PATCH 07/16] LoongArch: Add writecombine support for DMW-based ioremap() Currently, only TLB-based ioremap() support writecombine, so add the counterpart for DMW-based ioremap() with help of DMW2. The base address (WRITECOMBINE_BASE) is configured as 0xa000000000000000. DMW3 is unused by kernel now, however firmware may leave garbage in them and interfere kernel's address mapping. So clear it as necessary. BTW, centralize the DMW configuration to macro SETUP_DMWINS. Signed-off-by: Jiaxun Yang Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/addrspace.h | 4 ++++ arch/loongarch/include/asm/io.h | 10 ++++++++-- arch/loongarch/include/asm/loongarch.h | 10 +++++++++- arch/loongarch/include/asm/stackframe.h | 11 +++++++++++ arch/loongarch/kernel/head.S | 11 ++--------- arch/loongarch/power/suspend_asm.S | 6 +----- drivers/firmware/efi/libstub/loongarch.c | 2 ++ 7 files changed, 37 insertions(+), 17 deletions(-) diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index 7bd47d65bf7a0..fe198b473f849 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -37,6 +37,10 @@ extern unsigned long vm_map_base; #define UNCACHE_BASE CSR_DMW0_BASE #endif +#ifndef WRITECOMBINE_BASE +#define WRITECOMBINE_BASE CSR_DMW2_BASE +#endif + #define DMW_PABITS 48 #define TO_PHYS_MASK ((1ULL << DMW_PABITS) - 1) diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index c2f9979b2979e..5e95a60df1808 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -25,10 +25,16 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long prot_val) { - if (prot_val & _CACHE_CC) + switch (prot_val & _CACHE_MASK) { + case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); - else + case _CACHE_SUC: return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset); + case _CACHE_WUC: + return (void __iomem *)(unsigned long)(WRITECOMBINE_BASE + offset); + default: + return NULL; + } } #define ioremap(offset, size) \ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index eb09adda54b7c..c430df5953765 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -877,7 +877,7 @@ #define LOONGARCH_CSR_DMWIN2 0x182 /* 64 direct map win2: MEM */ #define LOONGARCH_CSR_DMWIN3 0x183 /* 64 direct map win3: MEM */ -/* Direct Map window 0/1 */ +/* Direct Map window 0/1/2/3 */ #define CSR_DMW0_PLV0 _CONST64_(1 << 0) #define CSR_DMW0_VSEG _CONST64_(0x8000) #define CSR_DMW0_BASE (CSR_DMW0_VSEG << DMW_PABITS) @@ -889,6 +889,14 @@ #define CSR_DMW1_BASE (CSR_DMW1_VSEG << DMW_PABITS) #define CSR_DMW1_INIT (CSR_DMW1_BASE | CSR_DMW1_MAT | CSR_DMW1_PLV0) +#define CSR_DMW2_PLV0 _CONST64_(1 << 0) +#define CSR_DMW2_MAT _CONST64_(2 << 4) +#define CSR_DMW2_VSEG _CONST64_(0xa000) +#define CSR_DMW2_BASE (CSR_DMW2_VSEG << DMW_PABITS) +#define CSR_DMW2_INIT (CSR_DMW2_BASE | CSR_DMW2_MAT | CSR_DMW2_PLV0) + +#define CSR_DMW3_INIT 0x0 + /* Performance Counter registers */ #define LOONGARCH_CSR_PERFCTRL0 0x200 /* 32 perf event 0 config */ #define LOONGARCH_CSR_PERFCNTR0 0x201 /* 64 perf event 0 count value */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index d9eafd3ee3d1e..66736837085b6 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -38,6 +38,17 @@ cfi_restore \reg \offset \docfi .endm + .macro SETUP_DMWINS temp + li.d \temp, CSR_DMW0_INIT # WUC, PLV0, 0x8000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN0 + li.d \temp, CSR_DMW1_INIT # CAC, PLV0, 0x9000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN1 + li.d \temp, CSR_DMW2_INIT # WUC, PLV0, 0xa000 xxxx xxxx xxxx + csrwr \temp, LOONGARCH_CSR_DMWIN2 + li.d \temp, CSR_DMW3_INIT # 0x0, unused + csrwr \temp, LOONGARCH_CSR_DMWIN3 + .endm + /* Jump to the runtime virtual address. */ .macro JUMP_VIRT_ADDR temp1 temp2 li.d \temp1, CACHE_BASE diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 4677ea8fa8e98..506a99a5bbc74 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -44,11 +44,7 @@ SYM_DATA(kernel_fsize, .long _kernel_fsize); SYM_CODE_START(kernel_entry) # kernel entry point /* Config direct window and set PG */ - li.d t0, CSR_DMW0_INIT # UC, PLV0, 0x8000 xxxx xxxx xxxx - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0, 0x9000 xxxx xxxx xxxx - csrwr t0, LOONGARCH_CSR_DMWIN1 - + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 /* Enable PG */ @@ -124,11 +120,8 @@ SYM_CODE_END(kernel_entry) * function after setting up the stack and tp registers. */ SYM_CODE_START(smpboot_entry) - li.d t0, CSR_DMW0_INIT # UC, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN1 + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 #ifdef CONFIG_PAGE_SIZE_4KB diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index e2fc3b4e31f00..c28ad52b7bafb 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -73,11 +73,7 @@ SYM_FUNC_START(loongarch_suspend_enter) * Reload all of the registers and return. */ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) - li.d t0, CSR_DMW0_INIT # UC, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN0 - li.d t0, CSR_DMW1_INIT # CA, PLV0 - csrwr t0, LOONGARCH_CSR_DMWIN1 - + SETUP_DMWINS t0 JUMP_VIRT_ADDR t0, t1 /* Enable PG */ diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index d0ef93551c44f..3782d0a187d1f 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -74,6 +74,8 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, /* Config Direct Mapping */ csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0); csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1); + csr_write64(CSR_DMW2_INIT, LOONGARCH_CSR_DMWIN2); + csr_write64(CSR_DMW3_INIT, LOONGARCH_CSR_DMWIN3); real_kernel_entry = (void *)kernel_entry_address(kernel_addr, image); From f60d251b27f6599b3407950924ac9b2c7a94b714 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:41:06 +0800 Subject: [PATCH 08/16] LoongArch: Add architectural preparation for CPUFreq Add architectural preparation for CPUFreq driver, including: Kconfig, register definition and platform device registration. Some of LoongArch processors support DVFS, their IOCSR.FEATURES has IOCSRF_FREQSCALE set. And they has a micro-core in the package called SMC (System Management Controller) to scale frequency, voltage, etc. Signed-off-by: Binbin Zhou Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/loongarch.h | 3 +++ arch/loongarch/power/platform.c | 15 +++++++++++++++ 3 files changed, 19 insertions(+) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 0693b621ebd4b..9687b1d241269 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -702,6 +702,7 @@ config ARCH_HIBERNATION_POSSIBLE source "kernel/power/Kconfig" source "drivers/acpi/Kconfig" +source "drivers/cpufreq/Kconfig" endmenu diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index c430df5953765..1501f0f8b06ee 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -1061,11 +1061,14 @@ #define LOONGARCH_IOCSR_NODECNT 0x408 #define LOONGARCH_IOCSR_MISC_FUNC 0x420 +#define IOCSR_MISC_FUNC_SOFT_INT BIT_ULL(10) #define IOCSR_MISC_FUNC_TIMER_RESET BIT_ULL(21) #define IOCSR_MISC_FUNC_EXT_IOI_EN BIT_ULL(48) #define LOONGARCH_IOCSR_CPUTEMP 0x428 +#define LOONGARCH_IOCSR_SMCMBX 0x51c + /* PerCore CSR, only accessible by local cores */ #define LOONGARCH_IOCSR_IPI_STATUS 0x1000 #define LOONGARCH_IOCSR_IPI_EN 0x1004 diff --git a/arch/loongarch/power/platform.c b/arch/loongarch/power/platform.c index 3ea8e07aa225f..a19353f7d1b07 100644 --- a/arch/loongarch/power/platform.c +++ b/arch/loongarch/power/platform.c @@ -34,6 +34,21 @@ void enable_pci_wakeup(void) acpi_write_bit_register(ACPI_BITREG_PCIEXP_WAKE_DISABLE, 0); } +static struct platform_device loongson3_cpufreq_device = { + .name = "loongson3_cpufreq", + .id = -1, +}; + +static int __init loongson_cpufreq_init(void) +{ + if (!cpu_has_scalefreq) + return -ENODEV; + + return platform_device_register(&loongson3_cpufreq_device); +} + +arch_initcall(loongson_cpufreq_init); + static int __init loongson3_acpi_suspend_init(void) { #ifdef CONFIG_ACPI From e523a5a65f34ca5bd67ccfdfdccf04689b58f0bf Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 20 Jul 2024 22:41:06 +0800 Subject: [PATCH 09/16] LoongArch: Add ACPI standard hardware register based S3 support Most LoongArch 64 machines are using custom "SADR" ACPI extension to perform ACPI S3 sleep. However the standard ACPI way to perform sleep is to write a value to ACPI PM1/SLEEP_CTL register, and this is never supported properly in kernel. Add standard S3 sleep by providing a default DoSuspend function which calls ACPI's acpi_enter_sleep_state() routine when SADR is not provided by the firmware. Also fix suspend assembly code so that ra is set properly before go into sleep routine. (Previously linked address of jirl was set to a0, some firmware do require return address in a0 but it's already set with la.pcrel before). Signed-off-by: Jiaxun Yang Signed-off-by: Huacai Chen --- arch/loongarch/power/platform.c | 22 +++++++++++++++++----- arch/loongarch/power/suspend_asm.S | 2 +- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/arch/loongarch/power/platform.c b/arch/loongarch/power/platform.c index a19353f7d1b07..0909729dc2e15 100644 --- a/arch/loongarch/power/platform.c +++ b/arch/loongarch/power/platform.c @@ -49,22 +49,34 @@ static int __init loongson_cpufreq_init(void) arch_initcall(loongson_cpufreq_init); +static void default_suspend_addr(void) +{ + acpi_enter_sleep_state(ACPI_STATE_S3); +} + static int __init loongson3_acpi_suspend_init(void) { #ifdef CONFIG_ACPI acpi_status status; uint64_t suspend_addr = 0; - if (acpi_disabled || acpi_gbl_reduced_hardware) + if (acpi_disabled) + return 0; + + if (!acpi_gbl_reduced_hardware) + acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1); + + if (!acpi_sleep_state_supported(ACPI_STATE_S3)) return 0; - acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1); status = acpi_evaluate_integer(NULL, "\\SADR", NULL, &suspend_addr); if (ACPI_FAILURE(status) || !suspend_addr) { - pr_err("ACPI S3 is not support!\n"); - return -1; + pr_info("ACPI S3 supported with hardware register default\n"); + loongson_sysconf.suspend_addr = (u64)default_suspend_addr; + } else { + pr_info("ACPI S3 supported with Loongson ACPI SADR extension\n"); + loongson_sysconf.suspend_addr = (u64)phys_to_virt(PHYSADDR(suspend_addr)); } - loongson_sysconf.suspend_addr = (u64)phys_to_virt(PHYSADDR(suspend_addr)); #endif return 0; } diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index c28ad52b7bafb..9fe28d5a02703 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -66,7 +66,7 @@ SYM_FUNC_START(loongarch_suspend_enter) la.pcrel a0, loongarch_wakeup_start la.pcrel t0, loongarch_suspend_addr ld.d t0, t0, 0 - jirl a0, t0, 0 /* Call BIOS's STR sleep routine */ + jirl ra, t0, 0 /* Call BIOS's STR sleep routine */ /* * This is where we return upon wakeup. From 67e6b115ddcf8f03108cedcf66261153904ce4fb Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:41:06 +0800 Subject: [PATCH 10/16] LoongArch: Automatically disable KASLR for hibernation Hibernation assumes the memory layout after resume be the same as that before sleep, so it expects the kernel is loaded at the same position. To achieve this goal we automatically disable KASLR if user explicitly requests hibernation via the "resume=" command line. Since "nohibernate" and "noresume" have higher priorities than "resume=", we only disable KASLR if there is no "nohibernate" and "noresume". Signed-off-by: Huacai Chen --- arch/loongarch/kernel/relocate.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 1acfa704c8d09..6834d627ff20d 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -123,6 +123,32 @@ static inline __init bool kaslr_disabled(void) if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) return true; +#ifdef CONFIG_HIBERNATION + str = strstr(builtin_cmdline, "nohibernate"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return false; + + str = strstr(boot_command_line, "nohibernate"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return false; + + str = strstr(builtin_cmdline, "noresume"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return false; + + str = strstr(boot_command_line, "noresume"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return false; + + str = strstr(builtin_cmdline, "resume="); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return true; + + str = strstr(boot_command_line, "resume="); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return true; +#endif + return false; } From 0124fbb4c6dba23dbdf80c829be68adbccde2722 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 11/16] LoongArch: Use correct API to map cmdline in relocate_kernel() fw_arg1 is in memory space rather than I/O space, so we should use early_memremap_ro() instead of early_ioremap() to map the cmdline. Moreover, we should unmap it after using. Suggested-by: Jiaxun Yang Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- arch/loongarch/kernel/relocate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 6834d627ff20d..d142061c61d42 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -196,7 +197,7 @@ unsigned long __init relocate_kernel(void) unsigned long kernel_length; unsigned long random_offset = 0; void *location_new = _text; /* Default to original kernel start */ - char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ + char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); @@ -208,6 +209,7 @@ unsigned long __init relocate_kernel(void) random_offset = (unsigned long)location_new - (unsigned long)(_text); #endif reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS; + early_memunmap(cmdline, COMMAND_LINE_SIZE); if (random_offset) { kernel_length = (long)(_end) - (long)(_text); From 0ad158e4ef769c5f261cbf791e0005d69fc3b785 Mon Sep 17 00:00:00 2001 From: Xi Ruoyao Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 12/16] LoongArch: Remove a redundant checking in relocator With our linker script "relocated_addr >= VMLINUX_LOAD_ADDRESS" should be always true. Signed-off-by: Xi Ruoyao Signed-off-by: Huacai Chen --- arch/loongarch/kernel/relocate.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index d142061c61d42..e3836f0b9bd85 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -35,9 +35,7 @@ static inline void __init relocate_relative(void) if (rela->r_info != R_LARCH_RELATIVE) continue; - if (relocated_addr >= VMLINUX_LOAD_ADDRESS) - relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); - + relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); *(Elf64_Addr *)RELOCATED(addr) = relocated_addr; } } From e05d4cd9b895c503dcf19c0ed9ebb8d393b220ec Mon Sep 17 00:00:00 2001 From: Xi Ruoyao Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 13/16] LoongArch: Add support for relocating the kernel with RELR relocation RELR as a relocation packing format for relative relocations for reducing the size of relative relocation records. In a position independent executable there are often many relative relocation records, and our vmlinux is a PIE. The LLD linker (since 17.0.0) and the BFD linker (since 2.43) supports packing the relocations in the RELR format for LoongArch, with the flag -z pack-relative-relocs. Commits 5cf896fb6be3eff ("arm64: Add support for relocating the kernel with RELR relocations") and ccb2d173b983984bfa ("Makefile: use -z pack-relative-relocs") have already added the framework to use RELR. We just need to wire it up and process the RELR relocation records in relocate_relative() in addition to the RELA relocation records. A ".p2align 3" directive is added to la_abs macro or the BFD linker cannot pack the relocation records against the .la_abs section (the ". = ALIGN(8);" directive in vmlinux.lds.S is too late in the linking process). With defconfig and CONFIG_RELR vmlinux.efi is 2.1 MiB (6%) smaller, and vmlinuz.efi (using gzip compression) is 384 KiB (2.8%) smaller. Link: https://groups.google.com/d/topic/generic-abi/bX460iggiKg Link: https://reviews.llvm.org/D138135#4531389 Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d89ecf33ab6d Signed-off-by: Xi Ruoyao Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/asmmacro.h | 1 + arch/loongarch/include/asm/setup.h | 5 +++++ arch/loongarch/kernel/relocate.c | 18 ++++++++++++++++++ arch/loongarch/kernel/vmlinux.lds.S | 8 ++++++++ 5 files changed, 33 insertions(+) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 9687b1d241269..f5df69ad70a66 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -610,6 +610,7 @@ config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION config RELOCATABLE bool "Relocatable kernel" + select ARCH_HAS_RELR help This builds the kernel as a Position Independent Executable (PIE), which retains all relocation metadata required, so as to relocate diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index 655db7d7a4279..8d7f501b0a124 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -609,6 +609,7 @@ lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 .pushsection ".la_abs", "aw", %progbits + .p2align 3 .dword 766b .dword \sym .popsection diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index ee52fb1e99631..3c2fb16b11b64 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -34,6 +34,11 @@ extern long __la_abs_end; extern long __rela_dyn_begin; extern long __rela_dyn_end; +#ifdef CONFIG_RELR +extern long __relr_dyn_begin; +extern long __relr_dyn_end; +#endif + extern unsigned long __init relocate_kernel(void); #endif diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index e3836f0b9bd85..50c469067f3aa 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -38,6 +38,24 @@ static inline void __init relocate_relative(void) relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); *(Elf64_Addr *)RELOCATED(addr) = relocated_addr; } + +#ifdef CONFIG_RELR + u64 *addr = NULL; + u64 *relr = (u64 *)&__relr_dyn_begin; + u64 *relr_end = (u64 *)&__relr_dyn_end; + + for ( ; relr < relr_end; relr++) { + if ((*relr & 1) == 0) { + addr = (u64 *)(*relr + reloc_offset); + *addr++ += reloc_offset; + } else { + for (u64 *p = addr, r = *relr >> 1; r; p++, r >>= 1) + if (r & 1) + *p += reloc_offset; + addr += 63; + } + } +#endif } static inline void __init relocate_absolute(long random_offset) diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 3c7595342730e..08ea921cdec16 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -113,6 +113,14 @@ SECTIONS __rela_dyn_end = .; } +#ifdef CONFIG_RELR + .relr.dyn : ALIGN(8) { + __relr_dyn_begin = .; + *(.relr.dyn) + __relr_dyn_end = .; + } +#endif + .data.rel : { *(.data.rel*) } #ifdef CONFIG_RELOCATABLE From 0d3a6322021b8c98527842518eeb685f3a8761c8 Mon Sep 17 00:00:00 2001 From: WANG Rui Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 14/16] LoongArch: Use rustc option -Zdirect-access-external-data -Zdirect-access-external-data is a new Rust compiler option added in Rust 1.78, which we use to optimize the access of external data in the Linux kernel's Rust code. This patch modifies the Rust code in vmlinux to directly access externa data, using PC-REL instead of GOT. However, Rust code whithin modules is constrained by the PC-REL addressing range and is explicitly set to use an indirect method. Acked-by: Miguel Ojeda Signed-off-by: WANG Rui Signed-off-by: Huacai Chen --- arch/loongarch/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 8674e7e24c4a6..ae3f80622f4c6 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -105,7 +105,8 @@ KBUILD_CFLAGS += -fno-jump-tables endif KBUILD_RUSTFLAGS += --target=loongarch64-unknown-none-softfloat -KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic +KBUILD_RUSTFLAGS_KERNEL += -Zdirect-access-external-data=yes +KBUILD_RUSTFLAGS_MODULE += -Zdirect-access-external-data=no ifeq ($(CONFIG_RELOCATABLE),y) KBUILD_CFLAGS_KERNEL += -fPIE From 3892b11eac5aaaeefbf717f1953288b77759d9e2 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 15/16] LoongArch: Check TIF_LOAD_WATCH to enable user space watchpoint Currently, there are some places to set CSR.PRMD.PWE, the first one is in hw_breakpoint_thread_switch() to enable user space singlestep via checking TIF_SINGLESTEP, the second one is in hw_breakpoint_control() to enable user space watchpoint. For the latter case, it should also check TIF_LOAD_WATCH to make the logic correct and clear. Fixes: c8e57ab0995c ("LoongArch: Trigger user-space watchpoints correctly") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/kernel/hw_breakpoint.c | 2 +- arch/loongarch/kernel/ptrace.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index 621ad7634df71..a6e4b605bfa8d 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -221,7 +221,7 @@ static int hw_breakpoint_control(struct perf_event *bp, } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); - if (bp->hw.target) + if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH)) regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index 200109de1971a..19dc6eff45ccc 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -589,6 +589,7 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; + struct thread_info *ti = task_thread_info(tsk); bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) @@ -613,8 +614,10 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, if (err) return err; attr.disabled = 0; + set_ti_thread_flag(ti, TIF_LOAD_WATCH); } else { attr.disabled = 1; + clear_ti_thread_flag(ti, TIF_LOAD_WATCH); } return modify_user_hw_breakpoint(bp, &attr); From 998b17d4440b8559a8bf4926e86f493101995519 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 20 Jul 2024 22:41:07 +0800 Subject: [PATCH 16/16] LoongArch: Make the users of larch_insn_gen_break() constant LoongArch defines UPROBE_SWBP_INSN as a function call and this breaks arch_uprobe_trampoline() which uses it to initialize a static variable. Add the new "__builtin_constant_p" helper, __emit_break(), and redefine the current users of larch_insn_gen_break() to use it. Fixes: ff474a78cef5 ("uprobe: Add uretprobe syscall to speed up return probe") Reported-by: Nathan Chancellor Closes: https://lore.kernel.org/all/20240614174822.GA1185149@thelio-3990X/ Suggested-by: Andrii Nakryiko Tested-by: Tiezhu Yang Signed-off-by: Oleg Nesterov Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/inst.h | 3 +++ arch/loongarch/include/asm/uprobes.h | 4 ++-- arch/loongarch/kernel/kprobes.c | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index c3993fd88abaa..944482063f14e 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -532,6 +532,9 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \ DEF_EMIT_REG0I15_FORMAT(break, break_op) +/* like emit_break(imm) but returns a constant expression */ +#define __emit_break(imm) ((u32)((imm) | (break_op << 15))) + #define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ int offset) \ diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h index c8f59983f702d..99a0d198927f8 100644 --- a/arch/loongarch/include/asm/uprobes.h +++ b/arch/loongarch/include/asm/uprobes.h @@ -9,10 +9,10 @@ typedef u32 uprobe_opcode_t; #define MAX_UINSN_BYTES 8 #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES -#define UPROBE_SWBP_INSN larch_insn_gen_break(BRK_UPROBE_BP) +#define UPROBE_SWBP_INSN __emit_break(BRK_UPROBE_BP) #define UPROBE_SWBP_INSN_SIZE LOONGARCH_INSN_SIZE -#define UPROBE_XOLBP_INSN larch_insn_gen_break(BRK_UPROBE_XOLBP) +#define UPROBE_XOLBP_INSN __emit_break(BRK_UPROBE_XOLBP) struct arch_uprobe { unsigned long resume_era; diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 17b040bd6067c..8ba391cfabb00 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -4,8 +4,8 @@ #include #include -#define KPROBE_BP_INSN larch_insn_gen_break(BRK_KPROBE_BP) -#define KPROBE_SSTEPBP_INSN larch_insn_gen_break(BRK_KPROBE_SSTEPBP) +#define KPROBE_BP_INSN __emit_break(BRK_KPROBE_BP) +#define KPROBE_SSTEPBP_INSN __emit_break(BRK_KPROBE_SSTEPBP) DEFINE_PER_CPU(struct kprobe *, current_kprobe); DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);