diff options
86 files changed, 931 insertions, 684 deletions
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 68d9b74fd751..2735462d5958 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -58,13 +58,14 @@ stable kernels. | ARM | Cortex-A72 | #853709 | N/A | | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | | ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | -| ARM | Cortex-A76 | #1188873 | ARM64_ERRATUM_1188873 | +| ARM | Cortex-A76 | #1188873,1418040| ARM64_ERRATUM_1418040 | | ARM | Cortex-A76 | #1165522 | ARM64_ERRATUM_1165522 | | ARM | Cortex-A76 | #1286807 | ARM64_ERRATUM_1286807 | -| ARM | Neoverse-N1 | #1188873 | ARM64_ERRATUM_1188873 | -| ARM | MMU-500 | #841119,#826419 | N/A | +| ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +| ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +| ARM | MMU-500 | #841119,826419 | N/A | | | | | | -| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | +| Cavium | ThunderX ITS | #22375,24313 | CAVIUM_ERRATUM_22375 | | Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 | | Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | | Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | diff --git a/Documentation/driver-api/generic-counter.rst b/Documentation/driver-api/generic-counter.rst index f51db893f595..0c161b1a3be6 100644 --- a/Documentation/driver-api/generic-counter.rst +++ b/Documentation/driver-api/generic-counter.rst @@ -251,7 +251,7 @@ for defining a counter device. .. kernel-doc:: include/linux/counter.h :internal: -.. kernel-doc:: drivers/counter/generic-counter.c +.. kernel-doc:: drivers/counter/counter.c :export: Implementation diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 51814450a7f8..3162eeb8c262 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -410,7 +410,7 @@ Notes on loading the dump-capture kernel: * Boot parameter "1" boots the dump-capture kernel into single-user mode without networking. If you want networking, use "3". -* We generally don' have to bring up a SMP kernel just to capture the +* We generally don't have to bring up a SMP kernel just to capture the dump. Hence generally it is useful either to build a UP dump-capture kernel or specify maxcpus=1 option while loading dump-capture kernel. Note, though maxcpus always works, you had better replace it with diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 725b8bea58a7..14fe93049d28 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -560,10 +560,10 @@ tcp_comp_sack_delay_ns - LONG INTEGER Default : 1,000,000 ns (1 ms) tcp_comp_sack_nr - INTEGER - Max numer of SACK that can be compressed. + Max number of SACK that can be compressed. Using 0 disables SACK compression. - Detault : 44 + Default : 44 tcp_slow_start_after_idle - BOOLEAN If set, provide RFC2861 behavior and time out the congestion diff --git a/Documentation/networking/segmentation-offloads.rst b/Documentation/networking/segmentation-offloads.rst index 89d1ee933e9f..085e8fab03fd 100644 --- a/Documentation/networking/segmentation-offloads.rst +++ b/Documentation/networking/segmentation-offloads.rst @@ -18,7 +18,7 @@ The following technologies are described: * Generic Segmentation Offload - GSO * Generic Receive Offload - GRO * Partial Generic Segmentation Offload - GSO_PARTIAL - * SCTP accelleration with GSO - GSO_BY_FRAGS + * SCTP acceleration with GSO - GSO_BY_FRAGS TCP Segmentation Offload @@ -148,7 +148,7 @@ that the IPv4 ID field is incremented in the case that a given header does not have the DF bit set. -SCTP accelleration with GSO +SCTP acceleration with GSO =========================== SCTP - despite the lack of hardware support - can still take advantage of diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 76f6e4765f49..697ea0510729 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -69,7 +69,7 @@ config ARM64 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG select ARCH_SUPPORTS_NUMA_BALANCING - select ARCH_WANT_COMPAT_IPC_PARSE_VERSION + select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_FRAME_POINTERS select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA @@ -476,16 +476,15 @@ config ARM64_ERRATUM_1024718 If unsure, say Y. -config ARM64_ERRATUM_1188873 +config ARM64_ERRATUM_1418040 bool "Cortex-A76/Neoverse-N1: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result" default y depends on COMPAT - select ARM_ARCH_TIMER_OOL_WORKAROUND help This option adds a workaround for ARM Cortex-A76/Neoverse-N1 - erratum 1188873. + errata 1188873 and 1418040. - Affected Cortex-A76/Neoverse-N1 cores (r0p0, r1p0, r2p0) could + Affected Cortex-A76/Neoverse-N1 cores (r0p0 to r3p1) could cause register corruption when accessing the timer registers from AArch32 userspace. @@ -521,6 +520,24 @@ config ARM64_ERRATUM_1286807 If unsure, say Y. +config ARM64_ERRATUM_1463225 + bool "Cortex-A76: Software Step might prevent interrupt recognition" + default y + help + This option adds a workaround for Arm Cortex-A76 erratum 1463225. + + On the affected Cortex-A76 cores (r0p0 to r3p1), software stepping + of a system call instruction (SVC) can prevent recognition of + subsequent interrupts when software stepping is disabled in the + exception handler of the system call and either kernel debugging + is enabled or VHE is in use. + + Work around the erratum by triggering a dummy step exception + when handling a system call from a task that is being stepped + in a VHE configuration of the kernel. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -1406,6 +1423,7 @@ config ARM64_MODULE_PLTS config ARM64_PSEUDO_NMI bool "Support for NMI-like interrupts" + depends on BROKEN # 1556553607-46531-1-git-send-email-julien.thierry@arm.com select CONFIG_ARM_GIC_V3 help Adds support for mimicking Non-Maskable Interrupts through the use of diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 039fbd822ec6..92b6b7cf67dd 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -718,12 +718,11 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * the output section, any use of such directives is undefined. * * The yield itself consists of the following: - * - Check whether the preempt count is exactly 1, in which case disabling - * preemption once will make the task preemptible. If this is not the case, - * yielding is pointless. - * - Check whether TIF_NEED_RESCHED is set, and if so, disable and re-enable - * kernel mode NEON (which will trigger a reschedule), and branch to the - * yield fixup code. + * - Check whether the preempt count is exactly 1 and a reschedule is also + * needed. If so, calling of preempt_enable() in kernel_neon_end() will + * trigger a reschedule. If it is not the case, yielding is pointless. + * - Disable and re-enable kernel mode NEON, and branch to the yield fixup + * code. * * This macro sequence may clobber all CPU state that is not guaranteed by the * AAPCS to be preserved across an ordinary function call. diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index defdc67d9ab4..33401ebc187c 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -53,7 +53,7 @@ #define ARM64_HAS_STAGE2_FWB 32 #define ARM64_HAS_CRC32 33 #define ARM64_SSBS 34 -#define ARM64_WORKAROUND_1188873 35 +#define ARM64_WORKAROUND_1418040 35 #define ARM64_HAS_SB 36 #define ARM64_WORKAROUND_1165522 37 #define ARM64_HAS_ADDRESS_AUTH_ARCH 38 @@ -62,7 +62,8 @@ #define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41 #define ARM64_HAS_IRQ_PRIO_MASKING 42 #define ARM64_HAS_DCPODP 43 +#define ARM64_WORKAROUND_1463225 44 -#define ARM64_NCAPS 44 +#define ARM64_NCAPS 45 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index ec894de0ed4e..87fdfba13a30 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -18,6 +18,7 @@ */ #ifndef __ASM_INSN_H #define __ASM_INSN_H +#include <linux/build_bug.h> #include <linux/types.h> /* A64 instructions are always 32 bits. */ @@ -266,18 +267,23 @@ enum aarch64_insn_adr_type { AARCH64_INSN_ADR_TYPE_ADR, }; -#define __AARCH64_INSN_FUNCS(abbr, mask, val) \ -static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ -{ return (code & (mask)) == (val); } \ -static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ -{ return (val); } +#define __AARCH64_INSN_FUNCS(abbr, mask, val) \ +static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ +{ \ + BUILD_BUG_ON(~(mask) & (val)); \ + return (code & (mask)) == (val); \ +} \ +static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ +{ \ + return (val); \ +} __AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000) __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) -__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0xB8200000) +__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e88d4e7bdfc7..d61beedba101 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -502,6 +502,22 @@ static const struct midr_range arm64_ssb_cpus[] = { {}, }; +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static bool +has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + /* Cortex-A76 r0p0 - r3p1 */ + struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode(); +} +#endif + static void __maybe_unused cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) { @@ -682,12 +698,16 @@ static const struct midr_range workaround_clean_cache[] = { }; #endif -#ifdef CONFIG_ARM64_ERRATUM_1188873 -static const struct midr_range erratum_1188873_list[] = { - /* Cortex-A76 r0p0 to r2p0 */ - MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), - /* Neoverse-N1 r0p0 to r2p0 */ - MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 2, 0), +#ifdef CONFIG_ARM64_ERRATUM_1418040 +/* + * - 1188873 affects r0p0 to r2p0 + * - 1418040 affects r0p0 to r3p1 + */ +static const struct midr_range erratum_1418040_list[] = { + /* Cortex-A76 r0p0 to r3p1 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), + /* Neoverse-N1 r0p0 to r3p1 */ + MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1), {}, }; #endif @@ -809,11 +829,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_ssbd_mitigation, .midr_range_list = arm64_ssb_cpus, }, -#ifdef CONFIG_ARM64_ERRATUM_1188873 +#ifdef CONFIG_ARM64_ERRATUM_1418040 { - .desc = "ARM erratum 1188873", - .capability = ARM64_WORKAROUND_1188873, - ERRATA_MIDR_RANGE_LIST(erratum_1188873_list), + .desc = "ARM erratum 1418040", + .capability = ARM64_WORKAROUND_1418040, + ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), }, #endif #ifdef CONFIG_ARM64_ERRATUM_1165522 @@ -824,6 +844,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1463225 + { + .desc = "ARM erratum 1463225", + .capability = ARM64_WORKAROUND_1463225, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_cortex_a76_erratum_1463225, + }, +#endif { } }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 1a7811b7e3c4..cd0c7af8e4a8 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -336,8 +336,8 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: -#ifdef CONFIG_ARM64_ERRATUM_1188873 -alternative_if_not ARM64_WORKAROUND_1188873 +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if_not ARM64_WORKAROUND_1418040 b 4f alternative_else_nop_endif /* diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index b09b6f75f759..06941c1fe418 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -145,15 +145,15 @@ u64 __init kaslr_early_init(u64 dt_phys) if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { /* - * Randomize the module region over a 4 GB window covering the + * Randomize the module region over a 2 GB window covering the * kernel. This reduces the risk of modules leaking information * about the address of the kernel itself, but results in * branches between modules and the core kernel that are * resolved via PLTs. (Branches between modules will be * resolved normally.) */ - module_range = SZ_4G - (u64)(_end - _stext); - module_alloc_base = max((u64)_end + offset - SZ_4G, + module_range = SZ_2G - (u64)(_end - _stext); + module_alloc_base = max((u64)_end + offset - SZ_2G, (u64)MODULES_VADDR); } else { /* diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f713e2fc4d75..f32359cffb01 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -56,7 +56,7 @@ void *module_alloc(unsigned long size) * can simply omit this fallback in that case. */ p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_base + SZ_4G, GFP_KERNEL, + module_alloc_base + SZ_2G, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); @@ -96,15 +96,27 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) { s64 sval = do_reloc(op, place, val); + /* + * The ELF psABI for AArch64 documents the 16-bit and 32-bit place + * relative relocations as having a range of [-2^15, 2^16) or + * [-2^31, 2^32), respectively. However, in order to be able to detect + * overflows reliably, we have to choose whether we interpret such + * quantities as signed or as unsigned, and stick with it. + * The way we organize our address space requires a signed + * interpretation of 32-bit relative references, so let's use that + * for all R_AARCH64_PRELxx relocations. This means our upper + * bound for overflow detection should be Sxx_MAX rather than Uxx_MAX. + */ + switch (len) { case 16: *(s16 *)place = sval; - if (sval < S16_MIN || sval > U16_MAX) + if (sval < S16_MIN || sval > S16_MAX) return -ERANGE; break; case 32: *(s32 *)place = sval; - if (sval < S32_MIN || sval > U32_MAX) + if (sval < S32_MIN || sval > S32_MAX) return -ERANGE; break; case 64: diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 5610ac01c1ec..871c739f060a 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm/daifflags.h> +#include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -60,6 +61,35 @@ static inline bool has_syscall_work(unsigned long flags) int syscall_trace_enter(struct pt_regs *regs); void syscall_trace_exit(struct pt_regs *regs); +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static void cortex_a76_erratum_1463225_svc_handler(void) +{ + u32 reg, val; + + if (!unlikely(test_thread_flag(TIF_SINGLESTEP))) + return; + + if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225))) + return; + + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1); + reg = read_sysreg(mdscr_el1); + val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE; + write_sysreg(val, mdscr_el1); + asm volatile("msr daifclr, #8"); + isb(); + + /* We will have taken a single-step exception by this point */ + + write_sysreg(reg, mdscr_el1); + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); +} +#else +static void cortex_a76_erratum_1463225_svc_handler(void) { } +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, const syscall_fn_t syscall_table[]) { @@ -68,6 +98,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, regs->orig_x0 = regs->regs[0]; regs->syscallno = scno; + cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); user_exit(); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index ade32046f3fe..e6be1a6efc0a 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -168,7 +168,6 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) static int __die(const char *str, int err, struct pt_regs *regs) { - struct task_struct *tsk = current; static int die_counter; int ret; @@ -181,9 +180,6 @@ static int __die(const char *str, int err, struct pt_regs *regs) return ret; print_modules(); - pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", - TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), - end_of_stack(tsk)); show_regs(regs); if (!user_mode(regs)) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 744b9dbaba03..fa230ff09aa1 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -12,8 +12,8 @@ obj-vdso := gettimeofday.o note.o sigreturn.o targets := $(obj-vdso) vdso.so vdso.so.dbg obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 \ - $(call ld-option, --hash-style=sysv) -n -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + --build-id -n -T # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 78c0a72f822c..674860e3e478 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -249,6 +249,11 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; + if (!is_vmalloc_addr(cpu_addr)) { + unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr)); + return __swiotlb_mmap_pfn(vma, pfn, size); + } + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { /* * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, @@ -272,6 +277,11 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct vm_struct *area = find_vm_area(cpu_addr); + if (!is_vmalloc_addr(cpu_addr)) { + struct page *page = virt_to_page(cpu_addr); + return __swiotlb_get_sgtable_page(sgt, page, size); + } + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { /* * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0cb0e09995e1..a30818ed9c60 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -171,9 +171,10 @@ static void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - mm == &init_mm ? VA_BITS : (int) vabits_user, mm->pgd); + mm == &init_mm ? VA_BITS : (int)vabits_user, + (unsigned long)virt_to_phys(mm->pgd)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -810,6 +811,36 @@ void __init hook_debug_fault_code(int nr, debug_fault_info[nr].name = name; } +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + if (user_mode(regs)) + return 0; + + if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) + return 0; + + /* + * We've taken a dummy step exception from the kernel to ensure + * that interrupts are re-enabled on the syscall path. Return back + * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions + * masked so that we can safely restore the mdscr and get on with + * handling the syscall. + */ + regs->pstate |= PSR_D_BIT; + return 1; +} +#else +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + return 0; +} +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs) @@ -817,6 +848,9 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); + if (cortex_a76_erratum_1463225_debug_handler(regs)) + return; + /* * Tell lockdep we disabled irqs in entry.S. Do nothing if they were * already disabled to preserve the last enabled/disabled addresses. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a170c6369a68..a1bfc4413982 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -955,13 +955,18 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) int __init arch_ioremap_pud_supported(void) { - /* only 4k granule supports level 1 block mappings */ - return IS_ENABLED(CONFIG_ARM64_4K_PAGES); + /* + * Only 4k granule supports level 1 block mappings. + * SW table walks can't handle removal of intermediate entries. + */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && + !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int __init arch_ioremap_pmd_supported(void) { - return 1; + /* See arch_ioremap_pud_supported() */ + return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9058cb084b91..b5390b4c9ade 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -753,31 +753,6 @@ static int __maybe_unused __get_pci_rid(struct pci_dev *pdev, u16 alias, return 0; } -static int arm_smmu_iort_xlate(struct device *dev, u32 streamid, - struct fwnode_handle *fwnode, - const struct iommu_ops *ops) -{ - int ret = iommu_fwspec_init(dev, fwnode, ops); - - if (!ret) - ret = iommu_fwspec_add_ids(dev, &streamid, 1); - - return ret; -} - -static inline bool iort_iommu_driver_enabled(u8 type) -{ - switch (type) { - case ACPI_IORT_NODE_SMMU_V3: - return IS_BUILTIN(CONFIG_ARM_SMMU_V3); - case ACPI_IORT_NODE_SMMU: - return IS_BUILTIN(CONFIG_ARM_SMMU); - default: - pr_warn("IORT node type %u does not describe an SMMU\n", type); - return false; - } -} - #ifdef CONFIG_IOMMU_API static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev) { @@ -878,15 +853,39 @@ int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) return (resv == its->its_count) ? resv : -ENODEV; } -#else -static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev) -{ return NULL; } -static inline int iort_add_device_replay(const struct iommu_ops *ops, - struct device *dev) -{ return 0; } -int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) -{ return 0; } -#endif + +static inline bool iort_iommu_driver_enabled(u8 type) +{ + switch (type) { + case ACPI_IORT_NODE_SMMU_V3: + return IS_BUILTIN(CONFIG_ARM_SMMU_V3); + case ACPI_IORT_NODE_SMMU: + return IS_BUILTIN(CONFIG_ARM_SMMU); + default: + pr_warn("IORT node type %u does not describe an SMMU\n", type); + return false; + } +} + +static int arm_smmu_iort_xlate(struct device *dev, u32 streamid, + struct fwnode_handle *fwnode, + const struct iommu_ops *ops) +{ + int ret = iommu_fwspec_init(dev, fwnode, ops); + + if (!ret) + ret = iommu_fwspec_add_ids(dev, &streamid, 1); + + return ret; +} + +static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node) +{ + struct acpi_iort_root_complex *pci_rc; + + pci_rc = (struct acpi_iort_root_complex *)node->node_data; + return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED; +} static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node, u32 streamid) @@ -933,6 +932,93 @@ static int iort_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) return iort_iommu_xlate(info->dev, parent, streamid); } +/** + * iort_iommu_configure - Set-up IOMMU configuration for a device. + * + * @dev: device to configure + * + * Returns: iommu_ops pointer on configuration success + * NULL on configuration failure + */ +const struct iommu_ops *iort_iommu_configure(struct device *dev) +{ + struct acpi_iort_node *node, *parent; + const struct iommu_ops *ops; + u32 streamid = 0; + int err = -ENODEV; + + /* + * If we already translated the fwspec there + * is nothing left to do, return the iommu_ops. + */ + ops = iort_fwspec_iommu_ops(dev); + if (ops) + return ops; + + if (dev_is_pci(dev)) { + struct pci_bus *bus = to_pci_dev(dev)->bus; + struct iort_pci_alias_info info = { .dev = dev }; + + node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX, + iort_match_node_callback, &bus->dev); + if (!node) + return NULL; + + info.node = node; + err = pci_for_each_dma_alias(to_pci_dev(dev), + iort_pci_iommu_init, &info); + + if (!err && iort_pci_rc_supports_ats(node)) + dev->iommu_fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; + } else { + int i = 0; + + node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT, + iort_match_node_callback, dev); + if (!node) + return NULL; + + do { + parent = iort_node_map_platform_id(node, &streamid, + IORT_IOMMU_TYPE, + i++); + + if (parent) + err = iort_iommu_xlate(dev, parent, streamid); + } while (parent && !err); + } + + /* + * If we have reason to believe the IOMMU driver missed the initial + * add_device callback for dev, replay it to get things in order. + */ + if (!err) { + ops = iort_fwspec_iommu_ops(dev); + err = iort_add_device_replay(ops, dev); + } + + /* Ignore all other errors apart from EPROBE_DEFER */ + if (err == -EPROBE_DEFER) { + ops = ERR_PTR(err); + } else if (err) { + dev_dbg(dev, "Adding to IOMMU failed: %d\n", err); + ops = NULL; + } + + return ops; +} +#else +static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev) +{ return NULL; } +static inline int iort_add_device_replay(const struct iommu_ops *ops, + struct device *dev) +{ return 0; } +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) +{ return 0; } +const struct iommu_ops *iort_iommu_configure(struct device *dev) +{ return NULL; } +#endif + static int nc_dma_get_range(struct device *dev, u64 *size) { struct acpi_iort_node *node; @@ -1031,90 +1117,6 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset); } -static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node) -{ - struct acpi_iort_root_complex *pci_rc; - - pci_rc = (struct acpi_iort_root_complex *)node->node_data; - return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED; -} - -/** - * iort_iommu_configure - Set-up IOMMU configuration for a device. - * - * @dev: device to configure - * - * Returns: iommu_ops pointer on configuration success - * NULL on configuration failure - */ -const struct iommu_ops *iort_iommu_configure(struct device *dev) -{ - struct acpi_iort_node *node, *parent; - const struct iommu_ops *ops; - u32 streamid = 0; - int err = -ENODEV; - - /* - * If we already translated the fwspec there - * is nothing left to do, return the iommu_ops. - */ - ops = iort_fwspec_iommu_ops(dev); - if (ops) - return ops; - - if (dev_is_pci(dev)) { - struct pci_bus *bus = to_pci_dev(dev)->bus; - struct iort_pci_alias_info info = { .dev = dev }; - - node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX, - iort_match_node_callback, &bus->dev); - if (!node) - return NULL; - - info.node = node; - err = pci_for_each_dma_alias(to_pci_dev(dev), - iort_pci_iommu_init, &info); - - if (!err && iort_pci_rc_supports_ats(node)) - dev->iommu_fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; - } else { - int i = 0; - - node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT, - iort_match_node_callback, dev); - if (!node) - return NULL; - - do { - parent = iort_node_map_platform_id(node, &streamid, - IORT_IOMMU_TYPE, - i++); - - if (parent) - err = iort_iommu_xlate(dev, parent, streamid); - } while (parent && !err); - } - - /* - * If we have reason to believe the IOMMU driver missed the initial - * add_device callback for dev, replay it to get things in order. - */ - if (!err) { - ops = iort_fwspec_iommu_ops(dev); - err = iort_add_device_replay(ops, dev); - } - - /* Ignore all other errors apart from EPROBE_DEFER */ - if (err == -EPROBE_DEFER) { - ops = ERR_PTR(err); - } else if (err) { - dev_dbg(dev, "Adding to IOMMU failed: %d\n", err); - ops = NULL; - } - - return ops; -} - static void __init acpi_iort_register_irq(int hwirq, const char *name, int trigger, struct resource *res) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 05897b05766b..86cc24b2e0aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -877,13 +877,16 @@ static int psp_load_fw(struct amdgpu_device *adev) if (!psp->cmd) return -ENOMEM; - ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG, - AMDGPU_GEM_DOMAIN_GTT, - &psp->fw_pri_bo, - &psp->fw_pri_mc_addr, - &psp->fw_pri_buf); - if (ret) - goto failed; + /* this fw pri bo is not used under SRIOV */ + if (!amdgpu_sriov_vf(psp->adev)) { + ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG, + AMDGPU_GEM_DOMAIN_GTT, + &psp->fw_pri_bo, + &psp->fw_pri_mc_addr, + &psp->fw_pri_buf); + if (ret) + goto failed; + } ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 3fd79e07944d..3b7370d914a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -626,6 +626,7 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev) case CHIP_VEGA10: return true; case CHIP_RAVEN: + return (adev->pdev->device == 0x15d8); case CHIP_VEGA12: case CHIP_VEGA20: default: @@ -812,8 +813,16 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) int chansize, numchan; int r; - if (amdgpu_emu_mode != 1) + if (amdgpu_sriov_vf(adev)) { + /* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN, + * and DF related registers is not readable, seems hardcord is the + * only way to set the correct vram_width + */ + adev->gmc.vram_width = 2048; + } else if (amdgpu_emu_mode != 1) { adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev); + } + if (!adev->gmc.vram_width) { /* hbm memory channel size */ if (adev->flags & AMD_IS_APU) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 4900e4958dec..b7e594c2bfb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -730,6 +730,11 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev) { u32 sol_reg; + /* Just return false for soc15 GPUs. Reset does not seem to + * be necessary. + */ + return false; + if (adev->flags & AMD_IS_APU) return false; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index c1e4d44d6137..765b58a17dc7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -355,6 +355,7 @@ static const struct kfd_deviceid supported_devices[] = { { 0x67CF, &polaris10_device_info }, /* Polaris10 */ { 0x67D0, &polaris10_vf_device_info }, /* Polaris10 vf*/ { 0x67DF, &polaris10_device_info }, /* Polaris10 */ + { 0x6FDF, &polaris10_device_info }, /* Polaris10 */ { 0x67E0, &polaris11_device_info }, /* Polaris11 */ { 0x67E1, &polaris11_device_info }, /* Polaris11 */ { 0x67E3, &polaris11_device_info }, /* Polaris11 */ @@ -462,6 +463,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, kfd->pdev = pdev; kfd->init_complete = false; kfd->kfd2kgd = f2g; + atomic_set(&kfd->compute_profile, 0); mutex_init(&kfd->doorbell_mutex); memset(&kfd->doorbell_available_index, 0, @@ -1036,6 +1038,21 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd) atomic_inc(&kfd->sram_ecc_flag); } +void kfd_inc_compute_active(struct kfd_dev *kfd) +{ + if (atomic_inc_return(&kfd->compute_profile) == 1) + amdgpu_amdkfd_set_compute_idle(kfd->kgd, false); +} + +void kfd_dec_compute_active(struct kfd_dev *kfd) +{ + int count = atomic_dec_return(&kfd->compute_profile); + + if (count == 0) + amdgpu_amdkfd_set_compute_idle(kfd->kgd, true); + WARN_ONCE(count < 0, "Compute profile ref. count error"); +} + #if defined(CONFIG_DEBUG_FS) /* This function will send a package to HIQ to hang the HWS diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index c6c9530e704e..ae381450601c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -811,8 +811,8 @@ static int register_process(struct device_queue_manager *dqm, retval = dqm->asic_ops.update_qpd(dqm, qpd); - if (dqm->processes_count++ == 0) - amdgpu_amdkfd_set_compute_idle(dqm->dev->kgd, false); + dqm->processes_count++; + kfd_inc_compute_active(dqm->dev); dqm_unlock(dqm); @@ -835,9 +835,8 @@ static int unregister_process(struct device_queue_manager *dqm, if (qpd == cur->qpd) { list_del(&cur->list); kfree(cur); - if (--dqm->processes_count == 0) - amdgpu_amdkfd_set_compute_idle( - dqm->dev->kgd, true); + dqm->processes_count--; + kfd_dec_compute_active(dqm->dev); goto out; } } @@ -1539,6 +1538,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm, list_del(&cur->list); kfree(cur); dqm->processes_count--; + kfd_dec_compute_active(dqm->dev); break; } } @@ -1626,6 +1626,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, list_del(&cur->list); kfree(cur); dqm->processes_count--; + kfd_dec_compute_active(dqm->dev); break; } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9e0230965675..487d5da337c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -279,6 +279,9 @@ struct kfd_dev { /* SRAM ECC flag */ atomic_t sram_ecc_flag; + + /* Compute Profile ref. count */ + atomic_t compute_profile; }; enum kfd_mempool { @@ -978,6 +981,10 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p); bool kfd_is_locked(void); +/* Compute profile */ +void kfd_inc_compute_active(struct kfd_dev *dev); +void kfd_dec_compute_active(struct kfd_dev *dev); + /* Debugfs */ #if defined(CONFIG_DEBUG_FS) diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 34d6fdcb32e2..4c8ce7938f01 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -138,13 +138,14 @@ #endif #define RAVEN_UNKNOWN 0xFF -#if defined(CONFIG_DRM_AMD_DC_DCN1_01) -#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0)) -#endif /* DCN1_01 */ #define ASIC_REV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) #define RAVEN1_F0 0xF0 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN)) +#if defined(CONFIG_DRM_AMD_DC_DCN1_01) +#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0)) +#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0)) +#endif /* DCN1_01 */ #define FAMILY_RV 142 /* DCN 1*/ diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index c058c784180e..eec329ab6037 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -280,7 +280,7 @@ int smu_feature_set_supported(struct smu_context *smu, int feature_id, WARN_ON(feature_id > feature->feature_num); - mutex_unlock(&feature->mutex); + mutex_lock(&feature->mutex); if (enable) test_and_set_bit(feature_id, feature->supported); else diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index de9531caaca0..9c8446184b17 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -594,6 +594,9 @@ void cdv_intel_lvds_init(struct drm_device *dev, int pipe; u8 pin; + if (!dev_priv->lvds_enabled_in_vbt) + return; + pin = GMBUS_PORT_PANEL; if (!lvds_is_present_in_vbt(dev, &pin)) { DRM_DEBUG_KMS("LVDS is not present in VBT\n"); diff --git a/drivers/gpu/drm/gma500/intel_bios.c b/drivers/gpu/drm/gma500/intel_bios.c index 63bde4e86c6a..e019ea271ffc 100644 --- a/drivers/gpu/drm/gma500/intel_bios.c +++ b/drivers/gpu/drm/gma500/intel_bios.c @@ -436,6 +436,9 @@ parse_driver_features(struct drm_psb_private *dev_priv, if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP) dev_priv->edp.support = 1; + dev_priv->lvds_enabled_in_vbt = driver->lvds_config != 0; + DRM_DEBUG_KMS("LVDS VBT config bits: 0x%x\n", driver->lvds_config); + /* This bit means to use 96Mhz for DPLL_A or not */ if (driver->primary_lfp_id) dev_priv->dplla_96mhz = true; diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index 941b238bdcc9..bc608ddc3bd1 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -537,6 +537,7 @@ struct drm_psb_private { int lvds_ssc_freq; bool is_lvds_on; bool is_mipi_on; + bool lvds_enabled_in_vbt; u32 mipi_ctrl_display; unsigned int core_freq; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index ab002cfd3cab..5cb59c0b4bbe 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -896,12 +896,16 @@ static int cmd_reg_handler(struct parser_exec_state *s, } /* TODO - * Right now only scan LRI command on KBL and in inhibit context. - * It's good enough to support initializing mmio by lri command in - * vgpu inhibit context on KBL. + * In order to let workload with inhibit context to generate + * correct image data into memory, vregs values will be loaded to + * hw via LRIs in the workload with inhibit context. But as + * indirect context is loaded prior to LRIs in workload, we don't + * want reg values specified in indirect context overwritten by + * LRIs in workloads. So, when scanning an indirect context, we + * update reg values in it into vregs, so LRIs in workload with + * inhibit context will restore with correct values */ - if ((IS_KABYLAKE(s->vgpu->gvt->dev_priv) - || IS_COFFEELAKE(s->vgpu->gvt->dev_priv)) && + if (IS_GEN(gvt->dev_priv, 9) && intel_gvt_mmio_is_in_ctx(gvt, offset) && !strncmp(cmd, "lri", 3)) { intel_gvt_hypervisor_read_gpa(s->vgpu, diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 08c74e65836b..244ad1729764 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1076,8 +1076,10 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry( } else { int type = get_next_pt_type(we->type); - if (!gtt_type_is_pt(type)) + if (!gtt_type_is_pt(type)) { + ret = -EINVAL; goto err; + } spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips); if (IS_ERR(spt)) { diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 90673fca792f..e09bd6e0cc4d 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1364,7 +1364,6 @@ static int dma_ctrl_write(struct intel_vgpu *vgpu, unsigned int offset, static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; u32 trtte = *(u32 *)p_data; if ((trtte & 1) && (trtte & (1 << 1)) == 0) { @@ -1373,11 +1372,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset, return -EINVAL; } write_vreg(vgpu, offset, p_data, bytes); - /* TRTTE is not per-context */ - - mmio_hw_access_pre(dev_priv); - I915_WRITE(_MMIO(offset), vgpu_vreg(vgpu, offset)); - mmio_hw_access_post(dev_priv); return 0; } @@ -1385,15 +1379,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset, static int gen9_trtt_chicken_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - u32 val = *(u32 *)p_data; - - if (val & 1) { - /* unblock hw logic */ - mmio_hw_access_pre(dev_priv); - I915_WRITE(_MMIO(offset), val); - mmio_hw_access_post(dev_priv); - } write_vreg(vgpu, offset, p_data, bytes); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index edf6d646eb25..90bb3df0db50 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -108,12 +108,13 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */ {RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */ {RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */ - {RCS0, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */ - {RCS0, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */ - {RCS0, TRNULLDETCT, 0, false}, /* 0x4de8 */ - {RCS0, TRINVTILEDETCT, 0, false}, /* 0x4dec */ - {RCS0, TRVADR, 0, false}, /* 0x4df0 */ - {RCS0, TRTTE, 0, false}, /* 0x4df4 */ + {RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */ + {RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */ + {RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */ + {RCS0, TRINVTILEDETCT, 0, true}, /* 0x4dec */ + {RCS0, TRVADR, 0, true}, /* 0x4df0 */ + {RCS0, TRTTE, 0, true}, /* 0x4df4 */ + {RCS0, _MMIO(0x4dfc), 0, true}, {BCS0, RING_GFX_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2229c */ {BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */ @@ -392,10 +393,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next, if (WARN_ON(ring_id >= ARRAY_SIZE(regs))) return; - if (ring_id == RCS0 && - (IS_KABYLAKE(dev_priv) || - IS_BROXTON(dev_priv) || - IS_COFFEELAKE(dev_priv))) + if (ring_id == RCS0 && IS_GEN(dev_priv, 9)) return; if (!pre && !gen9_render_mocs.initialized) @@ -470,11 +468,10 @@ static void switch_mmio(struct intel_vgpu *pre, continue; /* * No need to do save or restore of the mmio which is in context - * state image on kabylake, it's initialized by lri command and + * state image on gen9, it's initialized by lri command and * save or restore with context together. */ - if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv) - || IS_COFFEELAKE(dev_priv)) && mmio->in_context) + if (IS_GEN(dev_priv, 9) && mmio->in_context) continue; // save diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 7c99bbc3e2b8..13632dba8b2a 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -298,12 +298,29 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) struct i915_request *req = workload->req; void *shadow_ring_buffer_va; u32 *cs; + int err; - if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915) - || IS_COFFEELAKE(req->i915)) - && is_inhibit_context(req->hw_context)) + if (IS_GEN(req->i915, 9) && is_inhibit_context(req->hw_context)) intel_vgpu_restore_inhibit_context(vgpu, req); + /* + * To track whether a request has started on HW, we can emit a + * breadcrumb at the beginning of the request and check its + * timeline's HWSP to see if the breadcrumb has advanced past the + * start of this request. Actually, the request must have the + * init_breadcrumb if its timeline set has_init_bread_crumb, or the + * scheduler might get a wrong state of it during reset. Since the + * requests from gvt always set the has_init_breadcrumb flag, here + * need to do the emit_init_breadcrumb for all the requests. + */ + if (req->engine->emit_init_breadcrumb) { + err = req->engine->emit_init_breadcrumb(req); + if (err) { + gvt_vgpu_err("fail to emit init breadcrumb\n"); + return err; + } + } + /* allocate shadow ring buffer */ cs = intel_ring_begin(workload->req, workload->rb_len / sizeof(u32)); if (IS_ERR(cs)) { diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h index cc44ebd3b553..49709de69875 100644 --- a/drivers/gpu/drm/i915/i915_priolist_types.h +++ b/drivers/gpu/drm/i915/i915_priolist_types.h @@ -20,15 +20,14 @@ enum { I915_PRIORITY_INVALID = INT_MIN }; -#define I915_USER_PRIORITY_SHIFT 3 +#define I915_USER_PRIORITY_SHIFT 2 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT) #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT) #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1) #define I915_PRIORITY_WAIT ((u8)BIT(0)) -#define I915_PRIORITY_NEWCLIENT ((u8)BIT(1)) -#define I915_PRIORITY_NOSEMAPHORE ((u8)BIT(2)) +#define I915_PRIORITY_NOSEMAPHORE ((u8)BIT(1)) #define __NO_PREEMPTION (I915_PRIORITY_WAIT) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index f6c78c0fa74b..c88e538b2ef4 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -502,15 +502,6 @@ void __i915_request_unsubmit(struct i915_request *request) /* We may be recursing from the signal callback of another i915 fence */ spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - /* - * As we do not allow WAIT to preempt inflight requests, - * once we have executed a request, along with triggering - * any execution callbacks, we must preserve its ordering - * within the non-preemptible FIFO. - */ - BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); /* only internal */ - request->sched.attr.priority |= __NO_PREEMPTION; - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags)) i915_request_cancel_breadcrumb(request); @@ -582,18 +573,7 @@ semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) switch (state) { case FENCE_COMPLETE: - /* - * We only check a small portion of our dependencies - * and so cannot guarantee that there remains no - * semaphore chain across all. Instead of opting - * for the full NOSEMAPHORE boost, we go for the - * smaller (but still preempting) boost of - * NEWCLIENT. This will be enough to boost over - * a busywaiting request (as that cannot be - * NEWCLIENT) without accidentally boosting - * a busywait over real work elsewhere. - */ - i915_schedule_bump_priority(request, I915_PRIORITY_NEWCLIENT); + i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE); break; case FENCE_FREE: @@ -874,12 +854,6 @@ emit_semaphore_wait(struct i915_request *to, if (err < 0) return err; - err = i915_sw_fence_await_dma_fence(&to->semaphore, - &from->fence, 0, - I915_FENCE_GFP); - if (err < 0) - return err; - /* We need to pin the signaler's HWSP until we are finished reading. */ err = i915_timeline_read_hwsp(from, to, &hwsp_offset); if (err) @@ -945,8 +919,18 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) &from->fence, 0, I915_FENCE_GFP); } + if (ret < 0) + return ret; - return ret < 0 ? ret : 0; + if (to->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN) { + ret = i915_sw_fence_await_dma_fence(&to->semaphore, + &from->fence, 0, + I915_FENCE_GFP); + if (ret < 0) + return ret; + } + + return 0; } int @@ -1237,7 +1221,7 @@ void i915_request_add(struct i915_request *request) * the bulk clients. (FQ_CODEL) */ if (list_empty(&request->sched.signalers_list)) - attr.priority |= I915_PRIORITY_NEWCLIENT; + attr.priority |= I915_PRIORITY_WAIT; engine->schedule(request, &attr); } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 39bc4f54e272..108f52e1bf35 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -35,109 +35,6 @@ static inline bool node_signaled(const struct i915_sched_node *node) return i915_request_completed(node_to_request(node)); } -void i915_sched_node_init(struct i915_sched_node *node) -{ - INIT_LIST_HEAD(&node->signalers_list); - INIT_LIST_HEAD(&node->waiters_list); - INIT_LIST_HEAD(&node->link); - node->attr.priority = I915_PRIORITY_INVALID; - node->semaphores = 0; - node->flags = 0; -} - -static struct i915_dependency * -i915_dependency_alloc(void) -{ - return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL); -} - -static void -i915_dependency_free(struct i915_dependency *dep) -{ - kmem_cache_free(global.slab_dependencies, dep); -} - -bool __i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal, - struct i915_dependency *dep, - unsigned long flags) -{ - bool ret = false; - - spin_lock_irq(&schedule_lock); - - if (!node_signaled(signal)) { - INIT_LIST_HEAD(&dep->dfs_link); - list_add(&dep->wait_link, &signal->waiters_list); - list_add(&dep->signal_link, &node->signalers_list); - dep->signaler = signal; - dep->flags = flags; - - /* Keep track of whether anyone on this chain has a semaphore */ - if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN && - !node_started(signal)) - node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN; - - ret = true; - } - - spin_unlock_irq(&schedule_lock); - - return ret; -} - -int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) -{ - struct i915_dependency *dep; - - dep = i915_dependency_alloc(); - if (!dep) - return -ENOMEM; - - if (!__i915_sched_node_add_dependency(node, signal, dep, - I915_DEPENDENCY_ALLOC)) - i915_dependency_free(dep); - - return 0; -} - -void i915_sched_node_fini(struct i915_sched_node *node) -{ - struct i915_dependency *dep, *tmp; - - GEM_BUG_ON(!list_empty(&node->link)); - - spin_lock_irq(&schedule_lock); - - /* - * Everyone we depended upon (the fences we wait to be signaled) - * should retire before us and remove themselves from our list. - * However, retirement is run independently on each timeline and - * so we may be called out-of-order. - */ - list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) { - GEM_BUG_ON(!node_signaled(dep->signaler)); - GEM_BUG_ON(!list_empty(&dep->dfs_link)); - - list_del(&dep->wait_link); - if (dep->flags & I915_DEPENDENCY_ALLOC) - i915_dependency_free(dep); - } - - /* Remove ourselves from everyone who depends upon us */ - list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) { - GEM_BUG_ON(dep->signaler != node); - GEM_BUG_ON(!list_empty(&dep->dfs_link)); - - list_del(&dep->signal_link); - if (dep->flags & I915_DEPENDENCY_ALLOC) - i915_dependency_free(dep); - } - - spin_unlock_irq(&schedule_lock); -} - static inline struct i915_priolist *to_priolist(struct rb_node *rb) { return rb_entry(rb, struct i915_priolist, node); @@ -239,6 +136,11 @@ out: return &p->requests[idx]; } +void __i915_priolist_free(struct i915_priolist *p) +{ + kmem_cache_free(global.slab_priorities, p); +} + struct sched_cache { struct list_head *priolist; }; @@ -273,7 +175,7 @@ static bool inflight(const struct i915_request *rq, return active->hw_context == rq->hw_context; } -static void __i915_schedule(struct i915_request *rq, +static void __i915_schedule(struct i915_sched_node *node, const struct i915_sched_attr *attr) { struct intel_engine_cs *engine; @@ -287,13 +189,13 @@ static void __i915_schedule(struct i915_request *rq, lockdep_assert_held(&schedule_lock); GEM_BUG_ON(prio == I915_PRIORITY_INVALID); - if (i915_request_completed(rq)) + if (node_signaled(node)) return; - if (prio <= READ_ONCE(rq->sched.attr.priority)) + if (prio <= READ_ONCE(node->attr.priority)) return; - stack.signaler = &rq->sched; + stack.signaler = node; list_add(&stack.dfs_link, &dfs); /* @@ -344,9 +246,9 @@ static void __i915_schedule(struct i915_request *rq, * execlists_submit_request()), we can set our own priority and skip * acquiring the engine locks. */ - if (rq->sched.attr.priority == I915_PRIORITY_INVALID) { - GEM_BUG_ON(!list_empty(&rq->sched.link)); - rq->sched.attr = *attr; + if (node->attr.priority == I915_PRIORITY_INVALID) { + GEM_BUG_ON(!list_empty(&node->link)); + node->attr = *attr; if (stack.dfs_link.next == stack.dfs_link.prev) return; @@ -355,15 +257,14 @@ static void __i915_schedule(struct i915_request *rq, } memset(&cache, 0, sizeof(cache)); - engine = rq->engine; + engine = node_to_request(node)->engine; spin_lock(&engine->timeline.lock); /* Fifo and depth-first replacement ensure our deps execute before us */ list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) { - struct i915_sched_node *node = dep->signaler; - INIT_LIST_HEAD(&dep->dfs_link); + node = dep->signaler; engine = sched_lock_engine(node, engine, &cache); lockdep_assert_held(&engine->timeline.lock); @@ -413,13 +314,20 @@ static void __i915_schedule(struct i915_request *rq, void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr) { spin_lock_irq(&schedule_lock); - __i915_schedule(rq, attr); + __i915_schedule(&rq->sched, attr); spin_unlock_irq(&schedule_lock); } +static void __bump_priority(struct i915_sched_node *node, unsigned int bump) +{ + struct i915_sched_attr attr = node->attr; + + attr.priority |= bump; + __i915_schedule(node, &attr); +} + void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump) { - struct i915_sched_attr attr; unsigned long flags; GEM_BUG_ON(bump & ~I915_PRIORITY_MASK); @@ -428,17 +336,122 @@ void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump) return; spin_lock_irqsave(&schedule_lock, flags); + __bump_priority(&rq->sched, bump); + spin_unlock_irqrestore(&schedule_lock, flags); +} - attr = rq->sched.attr; - attr.priority |= bump; - __i915_schedule(rq, &attr); +void i915_sched_node_init(struct i915_sched_node *node) +{ + INIT_LIST_HEAD(&node->signalers_list); + INIT_LIST_HEAD(&node->waiters_list); + INIT_LIST_HEAD(&node->link); + node->attr.priority = I915_PRIORITY_INVALID; + node->semaphores = 0; + node->flags = 0; +} - spin_unlock_irqrestore(&schedule_lock, flags); +static struct i915_dependency * +i915_dependency_alloc(void) +{ + return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL); } -void __i915_priolist_free(struct i915_priolist *p) +static void +i915_dependency_free(struct i915_dependency *dep) { - kmem_cache_free(global.slab_priorities, p); + kmem_cache_free(global.slab_dependencies, dep); +} + +bool __i915_sched_node_add_dependency(struct i915_sched_node *node, + struct i915_sched_node *signal, + struct i915_dependency *dep, + unsigned long flags) +{ + bool ret = false; + + spin_lock_irq(&schedule_lock); + + if (!node_signaled(signal)) { + INIT_LIST_HEAD(&dep->dfs_link); + list_add(&dep->wait_link, &signal->waiters_list); + list_add(&dep->signal_link, &node->signalers_list); + dep->signaler = signal; + dep->flags = flags; + + /* Keep track of whether anyone on this chain has a semaphore */ + if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN && + !node_started(signal)) + node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN; + + /* + * As we do not allow WAIT to preempt inflight requests, + * once we have executed a request, along with triggering + * any execution callbacks, we must preserve its ordering + * within the non-preemptible FIFO. + */ + BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); + if (flags & I915_DEPENDENCY_EXTERNAL) + __bump_priority(signal, __NO_PREEMPTION); + + ret = true; + } + + spin_unlock_irq(&schedule_lock); + + return ret; +} + +int i915_sched_node_add_dependency(struct i915_sched_node *node, + struct i915_sched_node *signal) +{ + struct i915_dependency *dep; + + dep = i915_dependency_alloc(); + if (!dep) + return -ENOMEM; + + if (!__i915_sched_node_add_dependency(node, signal, dep, + I915_DEPENDENCY_EXTERNAL | + I915_DEPENDENCY_ALLOC)) + i915_dependency_free(dep); + + return 0; +} + +void i915_sched_node_fini(struct i915_sched_node *node) +{ + struct i915_dependency *dep, *tmp; + + GEM_BUG_ON(!list_empty(&node->link)); + + spin_lock_irq(&schedule_lock); + + /* + * Everyone we depended upon (the fences we wait to be signaled) + * should retire before us and remove themselves from our list. + * However, retirement is run independently on each timeline and + * so we may be called out-of-order. + */ + list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) { + GEM_BUG_ON(!node_signaled(dep->signaler)); + GEM_BUG_ON(!list_empty(&dep->dfs_link)); + + list_del(&dep->wait_link); + if (dep->flags & I915_DEPENDENCY_ALLOC) + i915_dependency_free(dep); + } + + /* Remove ourselves from everyone who depends upon us */ + list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) { + GEM_BUG_ON(dep->signaler != node); + GEM_BUG_ON(!list_empty(&dep->dfs_link)); + + list_del(&dep->signal_link); + if (dep->flags & I915_DEPENDENCY_ALLOC) + i915_dependency_free(dep); + } + + spin_unlock_irq(&schedule_lock); } static void i915_global_scheduler_shrink(void) diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index f1af3916a808..4f2b2eb7c3e5 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -66,7 +66,8 @@ struct i915_dependency { struct list_head wait_link; struct list_head dfs_link; unsigned long flags; -#define I915_DEPENDENCY_ALLOC BIT(0) +#define I915_DEPENDENCY_ALLOC BIT(0) +#define I915_DEPENDENCY_EXTERNAL BIT(1) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 4e0a351bfbca..11e5a86610bf 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -164,7 +164,7 @@ #define WA_TAIL_DWORDS 2 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS) -#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT | I915_PRIORITY_NOSEMAPHORE) +#define ACTIVE_PRIORITY (I915_PRIORITY_NOSEMAPHORE) static int execlists_context_deferred_alloc(struct intel_context *ce, struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index fbee030db940..e8b0b5dbcb2c 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -99,12 +99,14 @@ static int live_busywait_preempt(void *arg) ctx_hi = kernel_context(i915); if (!ctx_hi) goto err_unlock; - ctx_hi->sched.priority = INT_MAX; + ctx_hi->sched.priority = + I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY); ctx_lo = kernel_context(i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->sched.priority = INT_MIN; + ctx_lo->sched.priority = + I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY); obj = i915_gem_object_create_internal(i915, PAGE_SIZE); if (IS_ERR(obj)) { @@ -954,12 +956,14 @@ static int live_preempt_hang(void *arg) ctx_hi = kernel_context(i915); if (!ctx_hi) goto err_spin_lo; - ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; + ctx_hi->sched.priority = + I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY); ctx_lo = kernel_context(i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; + ctx_lo->sched.priority = + I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY); for_each_engine(engine, i915, id) { struct i915_request *rq; diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig index 591611dc4e34..81963e964b0f 100644 --- a/drivers/gpu/drm/panfrost/Kconfig +++ b/drivers/gpu/drm/panfrost/Kconfig @@ -9,6 +9,7 @@ config DRM_PANFROST select IOMMU_SUPPORT select IOMMU_IO_PGTABLE_LPAE select DRM_GEM_SHMEM_HELPER + select PM_DEVFREQ help DRM driver for ARM Mali Midgard (T6xx, T7xx, T8xx) and Bifrost (G3x, G5x, G7x) GPUs. diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index 238bd1d89d43..29fcffdf2d57 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -140,8 +140,8 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev) return 0; ret = dev_pm_opp_of_add_table(&pfdev->pdev->dev); - if (ret == -ENODEV) /* Optional, continue without devfreq */ - return 0; + if (ret) + return ret; panfrost_devfreq_reset(pfdev); @@ -170,9 +170,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev) { int i; - if (!pfdev->devfreq.devfreq) - return; - panfrost_devfreq_reset(pfdev); for (i = 0; i < NUM_JOB_SLOTS; i++) pfdev->devfreq.slot[i].busy = false; @@ -182,9 +179,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev) void panfrost_devfreq_suspend(struct panfrost_device *pfdev) { - if (!pfdev->devfreq.devfreq) - return; - devfreq_suspend_device(pfdev->devfreq.devfreq); } @@ -194,9 +188,6 @@ static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, i ktime_t now; ktime_t last; - if (!pfdev->devfreq.devfreq) - return; - now = ktime_get(); last = pfdev->devfreq.slot[slot].time_last_update; diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 6ff585055a07..bfa7e2b146df 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -457,8 +457,9 @@ static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi, u16 delay = 50 - 1; if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { - delay = (mode->htotal - mode->hdisplay) * 150; - delay /= (mode->clock / 1000) * 8; + u32 hsync_porch = (mode->htotal - mode->hdisplay) * 150; + + delay = (hsync_porch / ((mode->clock / 1000) * 8)); delay -= 50; } diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 66ea3a902e36..43643ad31730 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -293,7 +293,8 @@ static int sun8i_hdmi_phy_config_h3(struct dw_hdmi *hdmi, SUN8I_HDMI_PHY_ANA_CFG2_REG_BIGSW | SUN8I_HDMI_PHY_ANA_CFG2_REG_SLV(4); ana_cfg3_init |= SUN8I_HDMI_PHY_ANA_CFG3_REG_AMPCK(9) | - SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13); + SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13) | + SUN8I_HDMI_PHY_ANA_CFG3_REG_EMP(3); } regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_ANA_CFG1_REG, @@ -672,22 +673,13 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) goto err_put_clk_pll0; } } - - ret = sun8i_phy_clk_create(phy, dev, - phy->variant->has_second_pll); - if (ret) { - dev_err(dev, "Couldn't create the PHY clock\n"); - goto err_put_clk_pll1; - } - - clk_prepare_enable(phy->clk_phy); } phy->rst_phy = of_reset_control_get_shared(node, "phy"); if (IS_ERR(phy->rst_phy)) { dev_err(dev, "Could not get phy reset control\n"); ret = PTR_ERR(phy->rst_phy); - goto err_disable_clk_phy; + goto err_put_clk_pll1; } ret = reset_control_deassert(phy->rst_phy); @@ -708,18 +700,29 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) goto err_disable_clk_bus; } + if (phy->variant->has_phy_clk) { + ret = sun8i_phy_clk_create(phy, dev, + phy->variant->has_second_pll); + if (ret) { + dev_err(dev, "Couldn't create the PHY clock\n"); + goto err_disable_clk_mod; + } + + clk_prepare_enable(phy->clk_phy); + } + hdmi->phy = phy; return 0; +err_disable_clk_mod: + clk_disable_unprepare(phy->clk_mod); err_disable_clk_bus: clk_disable_unprepare(phy->clk_bus); err_deassert_rst_phy: reset_control_assert(phy->rst_phy); err_put_rst_phy: reset_control_put(phy->rst_phy); -err_disable_clk_phy: - clk_disable_unprepare(phy->clk_phy); err_put_clk_pll1: clk_put(phy->clk_pll1); err_put_clk_pll0: diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 36990b80e790..16077785ad47 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -174,7 +174,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile, kref_init(&base->refcount); idr_preload(GFP_KERNEL); spin_lock(&tdev->object_lock); - ret = idr_alloc(&tdev->idr, base, 0, 0, GFP_NOWAIT); + ret = idr_alloc(&tdev->idr, base, 1, 0, GFP_NOWAIT); spin_unlock(&tdev->object_lock); idr_preload_end(); if (ret < 0) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index bf6c3500d363..4ff11a0077e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1239,7 +1239,13 @@ static int vmw_master_set(struct drm_device *dev, } dev_priv->active_master = vmaster; - drm_sysfs_hotplug_event(dev); + + /* + * Inform a new master that the layout may have changed while + * it was gone. + */ + if (!from_open) + drm_sysfs_hotplug_event(dev); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 96983c47fb40..366dcfc1f9bb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -296,7 +296,7 @@ struct vmw_sg_table { struct vmw_piter { struct page **pages; const dma_addr_t *addrs; - struct sg_page_iter iter; + struct sg_dma_page_iter iter; unsigned long i; unsigned long num_pages; bool (*next)(struct vmw_piter *); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 2ff7ba04d8c8..33533d126277 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2010,6 +2010,11 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv, return 0; if (cmd->body.shid != SVGA3D_INVALID_ID) { + /* + * This is the compat shader path - Per device guest-backed + * shaders, but user-space thinks it's per context host- + * backed shaders. + */ res = vmw_shader_lookup(vmw_context_res_man(ctx), cmd->body.shid, cmd->body.type); if (!IS_ERR(res)) { @@ -2017,6 +2022,14 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv, VMW_RES_DIRTY_NONE); if (unlikely(ret != 0)) return ret; + + ret = vmw_resource_relocation_add + (sw_context, res, + vmw_ptr_diff(sw_context->buf_start, + &cmd->body.shid), + vmw_res_rel_normal); + if (unlikely(ret != 0)) + return ret; } } @@ -2193,7 +2206,8 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, cmd = container_of(header, typeof(*cmd), header); - if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX) { + if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX || + cmd->body.type < SVGA3D_SHADERTYPE_MIN) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; @@ -2414,6 +2428,10 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, return -EINVAL; cmd = container_of(header, typeof(*cmd), header); + if (unlikely(cmd->sid == SVGA3D_INVALID_ID)) { + VMW_DEBUG_USER("Invalid surface id.\n"); + return -EINVAL; + } ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, VMW_RES_DIRTY_NONE, user_surface_converter, &cmd->sid, &srf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index a3357ff7540d..a6ea75b58a83 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -266,7 +266,9 @@ static bool __vmw_piter_non_sg_next(struct vmw_piter *viter) static bool __vmw_piter_sg_next(struct vmw_piter *viter) { - return __sg_page_iter_next(&viter->iter); + bool ret = __vmw_piter_non_sg_next(viter); + + return __sg_page_iter_dma_next(&viter->iter) && ret; } @@ -284,12 +286,6 @@ static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter) return viter->pages[viter->i]; } -static struct page *__vmw_piter_sg_page(struct vmw_piter *viter) -{ - return sg_page_iter_page(&viter->iter); -} - - /** * Helper functions to return the DMA address of the current page. * @@ -311,13 +307,7 @@ static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter) static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter) { - /* - * FIXME: This driver wrongly mixes DMA and CPU SG list iteration and - * needs revision. See - * https://lore.kernel.org/lkml/20190104223531.GA1705@ziepe.ca/ - */ - return sg_page_iter_dma_address( - container_of(&viter->iter, struct sg_dma_page_iter, base)); + return sg_page_iter_dma_address(&viter->iter); } @@ -336,26 +326,23 @@ void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt, { viter->i = p_offset - 1; viter->num_pages = vsgt->num_pages; + viter->page = &__vmw_piter_non_sg_page; + viter->pages = vsgt->pages; switch (vsgt->mode) { case vmw_dma_phys: viter->next = &__vmw_piter_non_sg_next; viter->dma_address = &__vmw_piter_phys_addr; - viter->page = &__vmw_piter_non_sg_page; - viter->pages = vsgt->pages; break; case vmw_dma_alloc_coherent: viter->next = &__vmw_piter_non_sg_next; viter->dma_address = &__vmw_piter_dma_addr; - viter->page = &__vmw_piter_non_sg_page; viter->addrs = vsgt->addrs; - viter->pages = vsgt->pages; break; case vmw_dma_map_populate: case vmw_dma_map_bind: viter->next = &__vmw_piter_sg_next; viter->dma_address = &__vmw_piter_sg_addr; - viter->page = &__vmw_piter_sg_page; - __sg_page_iter_start(&viter->iter, vsgt->sgt->sgl, + __sg_page_iter_start(&viter->iter.base, vsgt->sgt->sgl, vsgt->sgt->orig_nents, p_offset); break; default: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1fb1333fefec..997385c1ca54 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1469,7 +1469,7 @@ static unsigned get_num_write_zeroes_bios(struct dm_target *ti) static int __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, unsigned num_bios) { - unsigned len = ci->sector_count; + unsigned len; /* * Even though the device advertised support for this type of @@ -1480,6 +1480,8 @@ static int __send_changing_extent_only(struct clone_info *ci, struct dm_target * if (!num_bios) return -EOPNOTSUPP; + len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti)); + __send_duplicate_bios(ci, ti, num_bios, &len); ci->sector += len; diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c index 9d12c06c7fd6..2feb4ef32035 100644 --- a/drivers/mmc/host/sdhci-iproc.c +++ b/drivers/mmc/host/sdhci-iproc.c @@ -196,7 +196,8 @@ static const struct sdhci_ops sdhci_iproc_32only_ops = { }; static const struct sdhci_pltfm_data sdhci_iproc_cygnus_pltfm_data = { - .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK, + .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | + SDHCI_QUIRK_NO_HISPD_BIT, .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN | SDHCI_QUIRK2_HOST_OFF_CARD_ON, .ops = &sdhci_iproc_32only_ops, }; @@ -219,7 +220,8 @@ static const struct sdhci_iproc_data iproc_cygnus_data = { static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = { .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12 | + SDHCI_QUIRK_NO_HISPD_BIT, .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN, .ops = &sdhci_iproc_ops, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d290f0787dfb..94c59939a8cf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2010,6 +2010,8 @@ static int mlx4_en_set_tunable(struct net_device *dev, return ret; } +#define MLX4_EEPROM_PAGE_LEN 256 + static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -2044,7 +2046,7 @@ static int mlx4_en_get_module_info(struct net_device *dev, break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 10fcc22f4590..ba6ac31a339d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -2077,11 +2077,6 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, size -= offset + size - I2C_PAGE_SIZE; i2c_addr = I2C_ADDR_LOW; - if (offset >= I2C_PAGE_SIZE) { - /* Reset offset to high page */ - i2c_addr = I2C_ADDR_HIGH; - offset -= I2C_PAGE_SIZE; - } cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 3c749c327cbd..e09522c5509a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -460,7 +460,7 @@ stmmac_get_pauseparam(struct net_device *netdev, } else { if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, netdev->phydev->supported) || - linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + !linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, netdev->phydev->supported)) return; } @@ -491,7 +491,7 @@ stmmac_set_pauseparam(struct net_device *netdev, } else { if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phy->supported) || - linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + !linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phy->supported)) return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5678b869cbff..2a1052704885 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2208,6 +2208,10 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) if (priv->plat->axi) stmmac_axi(priv, priv->ioaddr, priv->plat->axi); + /* DMA CSR Channel configuration */ + for (chan = 0; chan < dma_csr_ch; chan++) + stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); + /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { rx_q = &priv->rx_queue[chan]; @@ -2233,10 +2237,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) tx_q->tx_tail_addr, chan); } - /* DMA CSR Channel configuration */ - for (chan = 0; chan < dma_csr_ch; chan++) - stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); - return ret; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index c337400485da..011adae32b89 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -484,6 +484,11 @@ static inline u32 axienet_ior(struct axienet_local *lp, off_t offset) return in_be32(lp->regs + offset); } +static inline u32 axinet_ior_read_mcr(struct axienet_local *lp) +{ + return axienet_ior(lp, XAE_MDIO_MCR_OFFSET); +} + /** * axienet_iow - Memory mapped Axi Ethernet register write * @lp: Pointer to axienet local structure diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 757a3b37ae8a..704babdbc8a2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -11,6 +11,7 @@ #include <linux/of_address.h> #include <linux/of_mdio.h> #include <linux/jiffies.h> +#include <linux/iopoll.h> #include "xilinx_axienet.h" @@ -20,16 +21,11 @@ /* Wait till MDIO interface is ready to accept a new transaction.*/ int axienet_mdio_wait_until_ready(struct axienet_local *lp) { - unsigned long end = jiffies + 2; - while (!(axienet_ior(lp, XAE_MDIO_MCR_OFFSET) & - XAE_MDIO_MCR_READY_MASK)) { - if (time_before_eq(end, jiffies)) { - WARN_ON(1); - return -ETIMEDOUT; - } - udelay(1); - } - return 0; + u32 val; + + return readx_poll_timeout(axinet_ior_read_mcr, lp, + val, val & XAE_MDIO_MCR_READY_MASK, + 1, 20000); } /** diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 6886270da695..c409bab63bd3 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -27,6 +27,7 @@ #include <linux/of_net.h> #include <linux/phy.h> #include <linux/interrupt.h> +#include <linux/iopoll.h> #define DRIVER_NAME "xilinx_emaclite" @@ -714,20 +715,15 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id) static int xemaclite_mdio_wait(struct net_local *lp) { - unsigned long end = jiffies + 2; + u32 val; /* wait for the MDIO interface to not be busy or timeout * after some time. */ - while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & - XEL_MDIOCTRL_MDIOSTS_MASK) { - if (time_before_eq(end, jiffies)) { - WARN_ON(1); - return -ETIMEDOUT; - } - msleep(1); - } - return 0; + return readx_poll_timeout(xemaclite_readl, + lp->base_addr + XEL_MDIOCTRL_OFFSET, + val, !(val & XEL_MDIOCTRL_MDIOSTS_MASK), + 1000, 20000); } /** diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c index abbe309051d9..3d0f417e8586 100644 --- a/drivers/net/fddi/skfp/hwmtm.c +++ b/drivers/net/fddi/skfp/hwmtm.c @@ -1206,7 +1206,7 @@ void process_receive(struct s_smc *smc) } /* * SUPERNET 3 Bug: FORMAC delivers status words - * of aborded frames to the BMU + * of aborted frames to the BMU */ if (len <= 4) { DB_RX(2, "Frame length = 0"); @@ -1343,7 +1343,7 @@ void process_receive(struct s_smc *smc) break ; default : /* - * unknown FC abord the frame + * unknown FC abort the frame */ DB_RX(2, "unknown FC error"); smt_free_mbuf(smc,mb) ; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 92efa93649f0..61550122b563 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -838,6 +838,7 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (!net_eq(dev_net(dev), &init_net)) break; + /* fall through */ case SIOCGHWTSTAMP: if (netif_device_present(real_dev) && ops->ndo_do_ioctl) err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 89750c7dfd6f..74983593834b 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -422,28 +422,21 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_INBAND: phylink_get_mac_state(pl, &link_state); - if (pl->phydev) { - bool changed = false; - - link_state.link = link_state.link && - pl->phy_state.link; - - if (pl->phy_state.interface != - link_state.interface) { - link_state.interface = pl->phy_state.interface; - changed = true; - } - - /* Propagate the flow control from the PHY - * to the MAC. Also propagate the interface - * if changed. - */ - if (pl->phy_state.link || changed) { - link_state.pause |= pl->phy_state.pause; - phylink_resolve_flow(pl, &link_state); - - phylink_mac_config(pl, &link_state); - } + + /* If we have a phy, the "up" state is the union of + * both the PHY and the MAC */ + if (pl->phydev) + link_state.link &= pl->phy_state.link; + + /* Only update if the PHY link is up */ + if (pl->phydev && pl->phy_state.link) { + link_state.interface = pl->phy_state.interface; + + /* If we have a PHY, we need to update with + * the pause mode bits. */ + link_state.pause |= pl->phy_state.pause; + phylink_resolve_flow(pl, &link_state); + phylink_mac_config(pl, &link_state); } break; } diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index c247aed2dceb..8c01fbf68a89 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -383,17 +383,18 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net) dev); dev->tx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + netif_stop_queue(net); retval = usb_submit_urb(dev->tx_urb, GFP_ATOMIC); if (retval) { dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n", __func__, retval); dev->net->stats.tx_errors++; dev_kfree_skb_any(skb); + netif_wake_queue(net); } else { dev->net->stats.tx_packets++; dev->net->stats.tx_bytes += skb->len; dev_consume_skb_any(skb); - netif_stop_queue(net); } return NETDEV_TX_OK; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 66f0e0f51711..72514c46b478 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -494,6 +494,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) if (netif_running (dev->net) && netif_device_present (dev->net) && + test_bit(EVENT_DEV_OPEN, &dev->flags) && !test_bit (EVENT_RX_HALT, &dev->flags) && !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { @@ -1419,6 +1420,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, spin_unlock_irqrestore(&dev->txq.lock, flags); goto drop; } + if (netif_queue_stopped(net)) { + usb_autopm_put_interface_async(dev->intf); + spin_unlock_irqrestore(&dev->txq.lock, flags); + goto drop; + } #ifdef CONFIG_PM /* if this triggers the device is still a sleep */ diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 7cb766dafe85..e120f933412a 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -855,16 +855,8 @@ static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages, if (!pglist) goto out_free_buf; - for (i = 0; i < nr_pages; ++i) { - struct page *page = virt_to_page(pages[i]); - - if (PagePrivate(page)) { - pr_warn("unexpected high-order page for auxbuf!"); - goto out_free_pglist; - } - + for (i = 0; i < nr_pages; ++i) pglist[i] = virt_to_page(pages[i]); - } buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL); if (!buf->base) diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index c7039f52ad51..b1d804376237 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -398,12 +398,45 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc) */ static const struct dmi_system_id critclk_systems[] = { { + /* pmc_plt_clk0 is used for an external HSIC USB HUB */ .ident = "MPL CEC1x", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MPL AG"), DMI_MATCH(DMI_PRODUCT_NAME, "CEC10 Family"), }, }, + { + /* pmc_plt_clk0 - 3 are used for the 4 ethernet controllers */ + .ident = "Lex 3I380D", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lex BayTrail"), + DMI_MATCH(DMI_PRODUCT_NAME, "3I380D"), + }, + }, + { + /* pmc_plt_clk* - are used for ethernet controllers */ + .ident = "Beckhoff CB3163", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"), + DMI_MATCH(DMI_BOARD_NAME, "CB3163"), + }, + }, + { + /* pmc_plt_clk* - are used for ethernet controllers */ + .ident = "Beckhoff CB6263", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"), + DMI_MATCH(DMI_BOARD_NAME, "CB6263"), + }, + }, + { + /* pmc_plt_clk* - are used for ethernet controllers */ + .ident = "Beckhoff CB6363", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"), + DMI_MATCH(DMI_BOARD_NAME, "CB6363"), + }, + }, { /*sentinel*/ } }; diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c index 83f306265ee1..a56463308694 100644 --- a/drivers/thermal/rcar_gen3_thermal.c +++ b/drivers/thermal/rcar_gen3_thermal.c @@ -62,6 +62,13 @@ #define TSC_MAX_NUM 3 +/* default THCODE values if FUSEs are missing */ +static const int thcode[TSC_MAX_NUM][3] = { + { 3397, 2800, 2221 }, + { 3393, 2795, 2216 }, + { 3389, 2805, 2237 }, +}; + /* Structure for thermal temperature calculation */ struct equation_coefs { int a1; @@ -76,6 +83,8 @@ struct rcar_gen3_thermal_tsc { struct equation_coefs coef; int low; int high; + int tj_t; + int id; /* thermal channel id */ }; struct rcar_gen3_thermal_priv { @@ -122,30 +131,28 @@ static inline void rcar_gen3_thermal_write(struct rcar_gen3_thermal_tsc *tsc, #define RCAR3_THERMAL_GRAN 500 /* mili Celsius */ /* no idea where these constants come from */ -#define TJ_1 116 #define TJ_3 -41 -static void rcar_gen3_thermal_calc_coefs(struct equation_coefs *coef, - int *ptat, int *thcode) +static void rcar_gen3_thermal_calc_coefs(struct rcar_gen3_thermal_tsc *tsc, + int *ptat, const int *thcode, + int ths_tj_1) { - int tj_2; - /* TODO: Find documentation and document constant calculation formula */ /* * Division is not scaled in BSP and if scaled it might overflow * the dividend (4095 * 4095 << 14 > INT_MAX) so keep it unscaled */ - tj_2 = (FIXPT_INT((ptat[1] - ptat[2]) * 157) - / (ptat[0] - ptat[2])) - FIXPT_INT(41); + tsc->tj_t = (FIXPT_INT((ptat[1] - ptat[2]) * 157) + / (ptat[0] - ptat[2])) + FIXPT_INT(TJ_3); - coef->a1 = FIXPT_DIV(FIXPT_INT(thcode[1] - thcode[2]), - tj_2 - FIXPT_INT(TJ_3)); - coef->b1 = FIXPT_INT(thcode[2]) - coef->a1 * TJ_3; + tsc->coef.a1 = FIXPT_DIV(FIXPT_INT(thcode[1] - thcode[2]), + tsc->tj_t - FIXPT_INT(TJ_3)); + tsc->coef.b1 = FIXPT_INT(thcode[2]) - tsc->coef.a1 * TJ_3; - coef->a2 = FIXPT_DIV(FIXPT_INT(thcode[1] - thcode[0]), - tj_2 - FIXPT_INT(TJ_1)); - coef->b2 = FIXPT_INT(thcode[0]) - coef->a2 * TJ_1; + tsc->coef.a2 = FIXPT_DIV(FIXPT_INT(thcode[1] - thcode[0]), + tsc->tj_t - FIXPT_INT(ths_tj_1)); + tsc->coef.b2 = FIXPT_INT(thcode[0]) - tsc->coef.a2 * ths_tj_1; } static int rcar_gen3_thermal_round(int temp) @@ -161,15 +168,19 @@ static int rcar_gen3_thermal_round(int temp) static int rcar_gen3_thermal_get_temp(void *devdata, int *temp) { struct rcar_gen3_thermal_tsc *tsc = devdata; - int mcelsius, val1, val2; + int mcelsius, val; u32 reg; /* Read register and convert to mili Celsius */ reg = rcar_gen3_thermal_read(tsc, REG_GEN3_TEMP) & CTEMP_MASK; - val1 = FIXPT_DIV(FIXPT_INT(reg) - tsc->coef.b1, tsc->coef.a1); - val2 = FIXPT_DIV(FIXPT_INT(reg) - tsc->coef.b2, tsc->coef.a2); - mcelsius = FIXPT_TO_MCELSIUS((val1 + val2) / 2); + if (reg <= thcode[tsc->id][1]) + val = FIXPT_DIV(FIXPT_INT(reg) - tsc->coef.b1, + tsc->coef.a1); + else + val = FIXPT_DIV(FIXPT_INT(reg) - tsc->coef.b2, + tsc->coef.a2); + mcelsius = FIXPT_TO_MCELSIUS(val); /* Make sure we are inside specifications */ if ((mcelsius < MCELSIUS(-40)) || (mcelsius > MCELSIUS(125))) @@ -184,13 +195,15 @@ static int rcar_gen3_thermal_get_temp(void *devdata, int *temp) static int rcar_gen3_thermal_mcelsius_to_temp(struct rcar_gen3_thermal_tsc *tsc, int mcelsius) { - int celsius, val1, val2; + int celsius, val; celsius = DIV_ROUND_CLOSEST(mcelsius, 1000); - val1 = celsius * tsc->coef.a1 + tsc->coef.b1; - val2 = celsius * tsc->coef.a2 + tsc->coef.b2; + if (celsius <= INT_FIXPT(tsc->tj_t)) + val = celsius * tsc->coef.a1 + tsc->coef.b1; + else + val = celsius * tsc->coef.a2 + tsc->coef.b2; - return INT_FIXPT((val1 + val2) / 2); + return INT_FIXPT(val); } static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high) @@ -294,12 +307,29 @@ static void rcar_gen3_thermal_init(struct rcar_gen3_thermal_tsc *tsc) usleep_range(1000, 2000); } +static const int rcar_gen3_ths_tj_1 = 126; +static const int rcar_gen3_ths_tj_1_m3_w = 116; static const struct of_device_id rcar_gen3_thermal_dt_ids[] = { - { .compatible = "renesas,r8a774a1-thermal", }, - { .compatible = "renesas,r8a7795-thermal", }, - { .compatible = "renesas,r8a7796-thermal", }, - { .compatible = "renesas,r8a77965-thermal", }, - { .compatible = "renesas,r8a77980-thermal", }, + { + .compatible = "renesas,r8a774a1-thermal", + .data = &rcar_gen3_ths_tj_1_m3_w, + }, + { + .compatible = "renesas,r8a7795-thermal", + .data = &rcar_gen3_ths_tj_1, + }, + { + .compatible = "renesas,r8a7796-thermal", + .data = &rcar_gen3_ths_tj_1_m3_w, + }, + { + .compatible = "renesas,r8a77965-thermal", + .data = &rcar_gen3_ths_tj_1, + }, + { + .compatible = "renesas,r8a77980-thermal", + .data = &rcar_gen3_ths_tj_1, + }, {}, }; MODULE_DEVICE_TABLE(of, rcar_gen3_thermal_dt_ids); @@ -328,6 +358,7 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev) { struct rcar_gen3_thermal_priv *priv; struct device *dev = &pdev->dev; + const int *rcar_gen3_ths_tj_1 = of_device_get_match_data(dev); struct resource *res; struct thermal_zone_device *zone; int ret, irq, i; @@ -336,11 +367,6 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev) /* default values if FUSEs are missing */ /* TODO: Read values from hardware on supported platforms */ int ptat[3] = { 2631, 1509, 435 }; - int thcode[TSC_MAX_NUM][3] = { - { 3397, 2800, 2221 }, - { 3393, 2795, 2216 }, - { 3389, 2805, 2237 }, - }; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -395,11 +421,13 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev) ret = PTR_ERR(tsc->base); goto error_unregister; } + tsc->id = i; priv->tscs[i] = tsc; priv->thermal_init(tsc); - rcar_gen3_thermal_calc_coefs(&tsc->coef, ptat, thcode[i]); + rcar_gen3_thermal_calc_coefs(tsc, ptat, thcode[i], + *rcar_gen3_ths_tj_1); zone = devm_thermal_zone_of_sensor_register(dev, i, tsc, &rcar_gen3_tz_of_ops); diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c index bda1ca199abd..7ef9c7efe950 100644 --- a/drivers/thermal/rockchip_thermal.c +++ b/drivers/thermal/rockchip_thermal.c @@ -172,9 +172,6 @@ struct rockchip_thermal_data { int tshut_temp; enum tshut_mode tshut_mode; enum tshut_polarity tshut_polarity; - struct pinctrl *pinctrl; - struct pinctrl_state *gpio_state; - struct pinctrl_state *otp_state; }; /** @@ -1283,8 +1280,6 @@ static int rockchip_thermal_probe(struct platform_device *pdev) return error; } - thermal->chip->control(thermal->regs, false); - error = clk_prepare_enable(thermal->clk); if (error) { dev_err(&pdev->dev, "failed to enable converter clock: %d\n", @@ -1310,30 +1305,6 @@ static int rockchip_thermal_probe(struct platform_device *pdev) thermal->chip->initialize(thermal->grf, thermal->regs, thermal->tshut_polarity); - if (thermal->tshut_mode == TSHUT_MODE_GPIO) { - thermal->pinctrl = devm_pinctrl_get(&pdev->dev); - if (IS_ERR(thermal->pinctrl)) { - dev_err(&pdev->dev, "failed to find thermal pinctrl\n"); - return PTR_ERR(thermal->pinctrl); - } - - thermal->gpio_state = pinctrl_lookup_state(thermal->pinctrl, - "gpio"); - if (IS_ERR_OR_NULL(thermal->gpio_state)) { - dev_err(&pdev->dev, "failed to find thermal gpio state\n"); - return -EINVAL; - } - - thermal->otp_state = pinctrl_lookup_state(thermal->pinctrl, - "otpout"); - if (IS_ERR_OR_NULL(thermal->otp_state)) { - dev_err(&pdev->dev, "failed to find thermal otpout state\n"); - return -EINVAL; - } - - pinctrl_select_state(thermal->pinctrl, thermal->otp_state); - } - for (i = 0; i < thermal->chip->chn_num; i++) { error = rockchip_thermal_register_sensor(pdev, thermal, &thermal->sensors[i], @@ -1404,8 +1375,8 @@ static int __maybe_unused rockchip_thermal_suspend(struct device *dev) clk_disable(thermal->pclk); clk_disable(thermal->clk); - if (thermal->tshut_mode == TSHUT_MODE_GPIO) - pinctrl_select_state(thermal->pinctrl, thermal->gpio_state); + + pinctrl_pm_select_sleep_state(dev); return 0; } @@ -1450,8 +1421,7 @@ static int __maybe_unused rockchip_thermal_resume(struct device *dev) for (i = 0; i < thermal->chip->chn_num; i++) rockchip_thermal_toggle_sensor(&thermal->sensors[i], true); - if (thermal->tshut_mode == TSHUT_MODE_GPIO) - pinctrl_select_state(thermal->pinctrl, thermal->otp_state); + pinctrl_pm_select_default_state(dev); return 0; } diff --git a/drivers/thermal/tegra/tegra210-soctherm.c b/drivers/thermal/tegra/tegra210-soctherm.c index d31b50050faa..d0ff793f18c5 100644 --- a/drivers/thermal/tegra/tegra210-soctherm.c +++ b/drivers/thermal/tegra/tegra210-soctherm.c @@ -208,7 +208,7 @@ static const struct tegra_soctherm_fuse tegra210_soctherm_fuse = { .fuse_spare_realignment = 0, }; -struct tsensor_group_thermtrips tegra210_tsensor_thermtrips[] = { +static struct tsensor_group_thermtrips tegra210_tsensor_thermtrips[] = { {.id = TEGRA124_SOCTHERM_SENSOR_NUM}, {.id = TEGRA124_SOCTHERM_SENSOR_NUM}, {.id = TEGRA124_SOCTHERM_SENSOR_NUM}, diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 31df26ed7854..69bd1597bacf 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -31,9 +31,10 @@ * @delta is the difference between the current rtt sample and the * running average srtt. We add 1/8 of that to the srtt in order to * update the current srtt estimate. The variance estimate is a bit - * more complicated. We subtract the abs value of the @delta from - * the current variance estimate and add 1/4 of that to the running - * total. + * more complicated. We subtract the current variance estimate from + * the abs value of the @delta and add 1/4 of that to the running + * total. That's equivalent to 3/4 of the current variance + * estimate plus 1/4 of the abs of @delta. * * Note that the index points at the array entry containing the smoothed * mean value, and the variance is always in the following entry @@ -49,7 +50,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); + s->stats[index] += (s64)(abs(delta) - s->stats[index]) >> 2; } /** diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 1080381ff243..bc2dfacd2f4a 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -549,6 +549,15 @@ xfs_inobt_max_size( if (mp->m_inobt_mxr[0] == 0) return 0; + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + return xfs_btree_calc_size(mp->m_inobt_mnr, (uint64_t)agblocks * mp->m_sb.sb_inopblock / XFS_INODES_PER_CHUNK); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 6f47ab876d90..5d9de9b21726 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -427,6 +427,15 @@ xfs_refcountbt_calc_reserves( tree_len = be32_to_cpu(agf->agf_refcount_blocks); xfs_trans_brelse(tp, agbp); + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + *ask += xfs_refcountbt_max_size(mp, agblocks); *used += tree_len; diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 5738e11055e6..5d1f8884c888 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -578,6 +578,15 @@ xfs_rmapbt_calc_reserves( tree_len = be32_to_cpu(agf->agf_rmap_blocks); xfs_trans_brelse(tp, agbp); + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + /* Reserve 1% of the AG or enough for 1 block per record. */ *ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks)); *used += tree_len; diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 4b2c93b1934c..4955e1a9f1bc 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -307,8 +307,10 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) tlv_ptr = (struct tlv_desc *)tlv; tlv_ptr->tlv_type = htons(type); tlv_ptr->tlv_len = htons(tlv_len); - if (len && data) - memcpy(TLV_DATA(tlv_ptr), data, tlv_len); + if (len && data) { + memcpy(TLV_DATA(tlv_ptr), data, len); + memset(TLV_DATA(tlv_ptr) + len, 0, TLV_SPACE(len) - tlv_len); + } return TLV_SPACE(len); } @@ -405,8 +407,10 @@ static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags, tcm_hdr->tcm_len = htonl(msg_len); tcm_hdr->tcm_type = htons(cmd); tcm_hdr->tcm_flags = htons(flags); - if (data_len && data) + if (data_len && data) { memcpy(TCM_DATA(msg), data, data_len); + memset(TCM_DATA(msg) + data_len, 0, TCM_SPACE(data_len) - msg_len); + } return TCM_SPACE(data_len); } diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h index feb1acc54611..46b71af8eef2 100644 --- a/kernel/locking/lock_events.h +++ b/kernel/locking/lock_events.h @@ -31,12 +31,50 @@ enum lock_events { DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]); /* + * The purpose of the lock event counting subsystem is to provide a low + * overhead way to record the number of specific locking events by using + * percpu counters. It is the percpu sum that matters, not specifically + * how many of them happens in each cpu. + * + * It is possible that the same percpu counter may be modified in both + * the process and interrupt contexts. For architectures that perform + * percpu operation with multiple instructions, it is possible to lose + * count if a process context percpu update is interrupted in the middle + * and the same counter is updated in the interrupt context. Therefore, + * the generated percpu sum may not be precise. The error, if any, should + * be small and insignificant. + * + * For those architectures that do multi-instruction percpu operation, + * preemption in the middle and moving the task to another cpu may cause + * a larger error in the count. Again, this will be few and far between. + * Given the imprecise nature of the count and the possibility of resetting + * the count and doing the measurement again, this is not really a big + * problem. + * + * To get a better picture of what is happening under the hood, it is + * suggested that a few measurements should be taken with the counts + * reset in between to stamp out outliner because of these possible + * error conditions. + * + * To minimize overhead, we use __this_cpu_*() in all cases except when + * CONFIG_DEBUG_PREEMPT is defined. In this particular case, this_cpu_*() + * will be used to avoid the appearance of unwanted BUG messages. + */ +#ifdef CONFIG_DEBUG_PREEMPT +#define lockevent_percpu_inc(x) this_cpu_inc(x) +#define lockevent_percpu_add(x, v) this_cpu_add(x, v) +#else +#define lockevent_percpu_inc(x) __this_cpu_inc(x) +#define lockevent_percpu_add(x, v) __this_cpu_add(x, v) +#endif + +/* * Increment the PV qspinlock statistical counters */ static inline void __lockevent_inc(enum lock_events event, bool cond) { if (cond) - __this_cpu_inc(lockevents[event]); + lockevent_percpu_inc(lockevents[event]); } #define lockevent_inc(ev) __lockevent_inc(LOCKEVENT_ ##ev, true) @@ -44,7 +82,7 @@ static inline void __lockevent_inc(enum lock_events event, bool cond) static inline void __lockevent_add(enum lock_events event, int inc) { - __this_cpu_add(lockevents[event], inc); + lockevent_percpu_add(lockevents[event], inc); } #define lockevent_add(ev, c) __lockevent_add(LOCKEVENT_ ##ev, c) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 2a9a60733594..c546c4228075 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -373,6 +373,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCSHWTSTAMP: if (!net_eq(dev_net(dev), &init_net)) break; + /* fall through */ case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 84dbe21b71e5..96a3559f2a09 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -287,7 +287,9 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; + } + if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 801872a2e7aa..05fa058bee59 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -733,8 +733,8 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sock *sk = sock->sk; struct qrtr_node *node; struct sk_buff *skb; - u32 type = 0; size_t plen; + u32 type; int rc; if (msg->msg_flags & ~(MSG_DONTWAIT)) @@ -809,9 +809,9 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* control messages already require the type as 'command' */ skb_copy_bits(skb, 0, &qrtr_type, 4); - type = le32_to_cpu(qrtr_type); } + type = le32_to_cpu(qrtr_type); rc = enqueue_fn(node, skb, type, &ipc->us, addr); if (rc >= 0) rc = len; diff --git a/net/tipc/core.c b/net/tipc/core.c index ddd2e0f67c07..ed536c05252a 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -77,9 +77,6 @@ static int __net_init tipc_init_net(struct net *net) goto out_nametbl; INIT_LIST_HEAD(&tn->dist_queue); - err = tipc_topsrv_start(net); - if (err) - goto out_subscr; err = tipc_bcast_init(net); if (err) @@ -88,8 +85,6 @@ static int __net_init tipc_init_net(struct net *net) return 0; out_bclink: - tipc_bcast_stop(net); -out_subscr: tipc_nametbl_stop(net); out_nametbl: tipc_sk_rht_destroy(net); @@ -99,7 +94,6 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { - tipc_topsrv_stop(net); tipc_net_stop(net); tipc_bcast_stop(net); tipc_nametbl_stop(net); @@ -113,6 +107,11 @@ static struct pernet_operations tipc_net_ops = { .size = sizeof(struct tipc_net), }; +static struct pernet_operations tipc_topsrv_net_ops = { + .init = tipc_topsrv_init_net, + .exit = tipc_topsrv_exit_net, +}; + static int __init tipc_init(void) { int err; @@ -143,6 +142,10 @@ static int __init tipc_init(void) if (err) goto out_socket; + err = register_pernet_subsys(&tipc_topsrv_net_ops); + if (err) + goto out_pernet_topsrv; + err = tipc_bearer_setup(); if (err) goto out_bearer; @@ -150,6 +153,8 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: + unregister_pernet_subsys(&tipc_topsrv_net_ops); +out_pernet_topsrv: tipc_socket_stop(); out_socket: unregister_pernet_subsys(&tipc_net_ops); @@ -167,6 +172,7 @@ out_netlink: static void __exit tipc_exit(void) { tipc_bearer_cleanup(); + unregister_pernet_subsys(&tipc_topsrv_net_ops); tipc_socket_stop(); unregister_pernet_subsys(&tipc_net_ops); tipc_netlink_stop(); diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index d793b4343885..aa015c233898 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -77,8 +77,9 @@ void tipc_sub_report_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port, u32 node, u32 scope, int must); -int tipc_topsrv_start(struct net *net); -void tipc_topsrv_stop(struct net *net); + +int __net_init tipc_topsrv_init_net(struct net *net); +void __net_exit tipc_topsrv_exit_net(struct net *net); void tipc_sub_put(struct tipc_subscription *subscription); void tipc_sub_get(struct tipc_subscription *subscription); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index b45932d78004..f345662890a6 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -635,7 +635,7 @@ static void tipc_topsrv_work_stop(struct tipc_topsrv *s) destroy_workqueue(s->send_wq); } -int tipc_topsrv_start(struct net *net) +static int tipc_topsrv_start(struct net *net) { struct tipc_net *tn = tipc_net(net); const char name[] = "topology_server"; @@ -668,7 +668,7 @@ int tipc_topsrv_start(struct net *net) return ret; } -void tipc_topsrv_stop(struct net *net) +static void tipc_topsrv_stop(struct net *net) { struct tipc_topsrv *srv = tipc_topsrv(net); struct socket *lsock = srv->listener; @@ -693,3 +693,13 @@ void tipc_topsrv_stop(struct net *net) idr_destroy(&srv->conn_idr); kfree(srv); } + +int __net_init tipc_topsrv_init_net(struct net *net) +{ + return tipc_topsrv_start(net); +} + +void __net_exit tipc_topsrv_exit_net(struct net *net) +{ + tipc_topsrv_stop(net); +} diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 4fe392e507fb..33df646618e2 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -32,7 +32,7 @@ class SPDXdata(object): def read_spdxdata(repo): # The subdirectories of LICENSES in the kernel source - license_dirs = [ "preferred", "other", "exceptions" ] + license_dirs = [ "preferred", "deprecated", "exceptions", "dual" ] lictree = repo.head.commit.tree['LICENSES'] spdx = SPDXdata() diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index c61787b15f27..3ec702cf46ca 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4637,6 +4637,14 @@ static int selinux_socket_connect_helper(struct socket *sock, err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; + if (addrlen < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + + /* connect(AF_UNSPEC) has special handling, as it is a documented + * way to disconnect the socket + */ + if (address->sa_family == AF_UNSPEC) + return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission @@ -4657,8 +4665,6 @@ static int selinux_socket_connect_helper(struct socket *sock, * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ - if (addrlen < offsetofend(struct sockaddr, sa_family)) - return -EINVAL; switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 4b7e107865bf..a93e6b690e06 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -15,6 +15,7 @@ GW_IP6=2001:db8:1::2 SRC_IP6=2001:db8:1::3 DEV_ADDR=192.51.100.1 +DEV_ADDR6=2001:db8:1::1 DEV=dummy0 log_test() @@ -55,8 +56,8 @@ setup() $IP link add dummy0 type dummy $IP link set dev dummy0 up - $IP address add 198.51.100.1/24 dev dummy0 - $IP -6 address add 2001:db8:1::1/64 dev dummy0 + $IP address add $DEV_ADDR/24 dev dummy0 + $IP -6 address add $DEV_ADDR6/64 dev dummy0 set +e } @@ -186,8 +187,13 @@ fib_rule4_test() match="oif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table" + # need enable forwarding and disable rp_filter temporarily as all the + # addresses are in the same subnet and egress device == ingress device. + ip netns exec testns sysctl -w net.ipv4.ip_forward=1 + ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" + ip netns exec testns sysctl -w net.ipv4.ip_forward=0 match="tos 0x10" fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index f8c1c2985fb4..bd4a7247b44f 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -50,30 +50,6 @@ static clockid_t get_clockid(int fd) return (((unsigned int) ~fd) << 3) | CLOCKFD; } -static void handle_alarm(int s) -{ - printf("received signal %d\n", s); -} - -static int install_handler(int signum, void (*handler)(int)) -{ - struct sigaction action; - sigset_t mask; - - /* Unblock the signal. */ - sigemptyset(&mask); - sigaddset(&mask, signum); - sigprocmask(SIG_UNBLOCK, &mask, NULL); - - /* Install the signal handler. */ - action.sa_handler = handler; - action.sa_flags = 0; - sigemptyset(&action.sa_mask); - sigaction(signum, &action, NULL); - - return 0; -} - static long ppb_to_scaled_ppm(int ppb) { /* @@ -99,8 +75,6 @@ static void usage(char *progname) { fprintf(stderr, "usage: %s [options]\n" - " -a val request a one-shot alarm after 'val' seconds\n" - " -A val request a periodic alarm every 'val' seconds\n" " -c query the ptp clock's capabilities\n" " -d name device to open\n" " -e val read 'val' external time stamp events\n" @@ -135,15 +109,9 @@ int main(int argc, char *argv[]) struct ptp_pin_desc desc; struct timespec ts; struct timex tx; - - static timer_t timerid; - struct itimerspec timeout; - struct sigevent sigevent; - struct ptp_clock_time *pct; struct ptp_sys_offset *sysoff; - char *progname; unsigned int i; int c, cnt, fd; @@ -157,10 +125,8 @@ int main(int argc, char *argv[]) int gettime = 0; int index = 0; int list_pins = 0; - int oneshot = 0; int pct_offset = 0; int n_samples = 0; - int periodic = 0; int perout = -1; int pin_index = -1, pin_func; int pps = -1; @@ -172,14 +138,8 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghi:k:lL:p:P:sSt:T:v"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:v"))) { switch (c) { - case 'a': - oneshot = atoi(optarg); - break; - case 'A': - periodic = atoi(optarg); - break; case 'c': capabilities = 1; break; @@ -380,49 +340,6 @@ int main(int argc, char *argv[]) } } - if (oneshot) { - install_handler(SIGALRM, handle_alarm); - /* Create a timer. */ - sigevent.sigev_notify = SIGEV_SIGNAL; - sigevent.sigev_signo = SIGALRM; - if (timer_create(clkid, &sigevent, &timerid)) { - perror("timer_create"); - return -1; - } - /* Start the timer. */ - memset(&timeout, 0, sizeof(timeout)); - timeout.it_value.tv_sec = oneshot; - if (timer_settime(timerid, 0, &timeout, NULL)) { - perror("timer_settime"); - return -1; - } - pause(); - timer_delete(timerid); - } - - if (periodic) { - install_handler(SIGALRM, handle_alarm); - /* Create a timer. */ - sigevent.sigev_notify = SIGEV_SIGNAL; - sigevent.sigev_signo = SIGALRM; - if (timer_create(clkid, &sigevent, &timerid)) { - perror("timer_create"); - return -1; - } - /* Start the timer. */ - memset(&timeout, 0, sizeof(timeout)); - timeout.it_interval.tv_sec = periodic; - timeout.it_value.tv_sec = periodic; - if (timer_settime(timerid, 0, &timeout, NULL)) { - perror("timer_settime"); - return -1; - } - while (1) { - pause(); - } - timer_delete(timerid); - } - if (perout >= 0) { if (clock_gettime(clkid, &ts)) { perror("clock_gettime"); |