From 6dd4879f59b0a0679ed8c3ebaff3d79f37930778 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sat, 6 Mar 2021 06:48:01 +0100 Subject: RISC-V: correct enum sbi_ext_rfence_fid The constants in enum sbi_ext_rfence_fid should match the SBI specification. See https://github.com/riscv/riscv-sbi-doc/blob/master/riscv-sbi.adoc#78-function-listing | Function Name | FID | EID | sbi_remote_fence_i | 0 | 0x52464E43 | sbi_remote_sfence_vma | 1 | 0x52464E43 | sbi_remote_sfence_vma_asid | 2 | 0x52464E43 | sbi_remote_hfence_gvma_vmid | 3 | 0x52464E43 | sbi_remote_hfence_gvma | 4 | 0x52464E43 | sbi_remote_hfence_vvma_asid | 5 | 0x52464E43 | sbi_remote_hfence_vvma | 6 | 0x52464E43 Fixes: ecbacc2a3efd ("RISC-V: Add SBI v0.2 extension definitions") Reported-by: Sean Anderson Signed-off-by: Heinrich Schuchardt Reviewed-by: Anup Patel Reviewed-by: Atish Patra Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/sbi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 99895d9c3bdd..d7027411dde8 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -51,10 +51,10 @@ enum sbi_ext_rfence_fid { SBI_EXT_RFENCE_REMOTE_FENCE_I = 0, SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, - SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA, SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID, - SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA, + SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA, SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID, + SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA, }; enum sbi_ext_hsm_fid { -- cgit v1.2.3 From 030f1dfa855054db5d845eca7f04c8cfda1c9f51 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:24 +0800 Subject: riscv: traps: Fix no prototype warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix all W=1 compilation warnings:'no previous prototype for' in arch/riscv/kernel/traps.c: arch/riscv/kernel/traps.c:96:15: warning: no previous prototype for ‘do_trap_unknown’ [-Wmissing-prototypes] 96 | DO_ERROR_INFO(do_trap_unknown, | ^~~~~~~~~~~~~~~ arch/riscv/kernel/traps.c:91:27: note: in definition of macro ‘DO_ERROR_INFO’ 91 | asmlinkage __visible void name(struct pt_regs *regs) \ | ^~~~ arch/riscv/kernel/traps.c:98:15: warning: no previous prototype for ‘do_trap_insn_misaligned’ [-Wmissing-prototypes] 98 | DO_ERROR_INFO(do_trap_insn_misaligned, | ^~~~~~~~~~~~~~~~~~~~~~~ arch/riscv/kernel/traps.c:91:27: note: in definition of macro ‘DO_ERROR_INFO’ 91 | asmlinkage __visible void name(struct pt_regs *regs) \ | ^~~~ arch/riscv/kernel/traps.c:100:15: warning: no previous prototype for ‘do_trap_insn_fault’ [-Wmissing-prototypes] ... Reported-by: Hulk Robot Signed-off-by: Nanyong Sun [Palmer: fix checkpatch warnings] Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/asm-prototypes.h | 16 ++++++++++++++++ arch/riscv/kernel/traps.c | 1 + 2 files changed, 17 insertions(+) (limited to 'arch') diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 27e005fca584..2a652b0c987d 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -9,4 +9,20 @@ long long __lshrti3(long long a, int b); long long __ashrti3(long long a, int b); long long __ashlti3(long long a, int b); + +#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs) + +DECLARE_DO_ERROR_INFO(do_trap_unknown); +DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_insn_fault); +DECLARE_DO_ERROR_INFO(do_trap_insn_illegal); +DECLARE_DO_ERROR_INFO(do_trap_load_fault); +DECLARE_DO_ERROR_INFO(do_trap_load_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_store_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_store_fault); +DECLARE_DO_ERROR_INFO(do_trap_ecall_u); +DECLARE_DO_ERROR_INFO(do_trap_ecall_s); +DECLARE_DO_ERROR_INFO(do_trap_ecall_m); +DECLARE_DO_ERROR_INFO(do_trap_break); + #endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 3ed2c23601a0..0879b5df11b9 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 004570c3796bfe454a9cdfb9ab5d3ea48371fe48 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:25 +0800 Subject: riscv: irq: Fix no prototype warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following W=1 kernel compilation warning: arch/riscv/kernel/irq.c:19:13: warning: no previous prototype for ‘init_IRQ’ [-Wmissing-prototypes] 19 | void __init init_IRQ(void) | ^~~~~~~~ Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/irq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h index 9807ad164015..e4c435509983 100644 --- a/arch/riscv/include/asm/irq.h +++ b/arch/riscv/include/asm/irq.h @@ -12,4 +12,6 @@ #include +extern void __init init_IRQ(void); + #endif /* _ASM_RISCV_IRQ_H */ -- cgit v1.2.3 From 56a6c37f6e3994cba01609768f5a215c85bd2f85 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:26 +0800 Subject: riscv: sbi: Fix comment of __sbi_set_timer_v01 Fix the comment of __sbi_set_timer_v01, the function name in comment is missing '__' Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sbi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f4a7db3d309e..d3bf756321a5 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -116,7 +116,7 @@ void sbi_clear_ipi(void) EXPORT_SYMBOL(sbi_clear_ipi); /** - * sbi_set_timer_v01() - Program the timer for next timer event. + * __sbi_set_timer_v01() - Program the timer for next timer event. * @stime_value: The value after which next timer event should fire. * * Return: None -- cgit v1.2.3 From e06f4ce1d4c63799eff9d3544b3f7468d5409f3e Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:27 +0800 Subject: riscv: ptrace: Fix no prototype warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following W=1 kernel compilation warnings: arch/riscv/kernel/ftrace.c:186:6: warning: no previous prototype for ‘prepare_ftrace_return’ [-Wmissing-prototypes] 186 | void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, | ^~~~~~~~~~~~~~~~~~~~~ arch/riscv/kernel/ptrace.c:239:15: warning: no previous prototype for ‘do_syscall_trace_enter’ [-Wmissing-prototypes] 239 | __visible int do_syscall_trace_enter(struct pt_regs *regs) | ^~~~~~~~~~~~~~~~~~~~~~ arch/riscv/kernel/ptrace.c:262:16: warning: no previous prototype for ‘do_syscall_trace_exit’ [-Wmissing-prototypes] 262 | __visible void do_syscall_trace_exit(struct pt_regs *regs) | ^~~~~~~~~~~~~~~~~~~~~ Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/ptrace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index cb4abb639e8d..09ad4e923510 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -119,6 +119,11 @@ extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer); +int do_syscall_trace_enter(struct pt_regs *regs); +void do_syscall_trace_exit(struct pt_regs *regs); + /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten -- cgit v1.2.3 From db2a8f9256e9a2a931edb83622d81ca73c6c8c6a Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:28 +0800 Subject: riscv: time: Fix no prototype for time_init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following W=1 compilation warning: arch/riscv/kernel/time.c:16:13: warning: no previous prototype for ‘time_init’ [-Wmissing-prototypes] 16 | void __init time_init(void) | ^~~~~~~~~ Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/timex.h | 2 ++ arch/riscv/kernel/time.c | 1 + 2 files changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index 81de51e6aa32..507cae273bc6 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -88,4 +88,6 @@ static inline int read_current_timer(unsigned long *timer_val) return 0; } +extern void time_init(void); + #endif /* _ASM_RISCV_TIMEX_H */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 8a5cf99c0776..1b432264f7ef 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -9,6 +9,7 @@ #include #include #include +#include unsigned long riscv_timebase; EXPORT_SYMBOL_GPL(riscv_timebase); -- cgit v1.2.3 From a6a58ecf98c3f6d95123ee3e66ccb6f7672c6e68 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:29 +0800 Subject: riscv: syscall_table: Reduce W=1 compilation warnings noise MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building riscv syscall table with W=1 throws the warning as following pattern: arch/riscv/kernel/syscall_table.c:14:36: warning: initialized field overwritten [-Woverride-init] 14 | #define __SYSCALL(nr, call) [nr] = (call), | ^ ./include/uapi/asm-generic/unistd.h:29:37: note: in expansion of macro ‘__SYSCALL’ 29 | #define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys) | ^~~~~~~~~ ./include/uapi/asm-generic/unistd.h:34:1: note: in expansion of macro ‘__SC_COMP’ 34 | __SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) | ^~~~~~~~~ arch/riscv/kernel/syscall_table.c:14:36: note: (near initialization for ‘sys_call_table[0]’) 14 | #define __SYSCALL(nr, call) [nr] = (call), | ^ ./include/uapi/asm-generic/unistd.h:29:37: note: in expansion of macro ‘__SYSCALL’ 29 | #define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys) | ^~~~~~~~~ ./include/uapi/asm-generic/unistd.h:34:1: note: in expansion of macro ‘__SC_COMP’ 34 | __SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) | ^~~~~~~~~ arch/riscv/kernel/syscall_table.c:14:36: warning: initialized field overwritten [-Woverride-init] ... Since we intentionally build the syscall tables this way,ignore the warning. Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/Makefile | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 3dc0abde988a..647a47f5484a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -8,6 +8,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) endif +CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) extra-y += head.o extra-y += vmlinux.lds -- cgit v1.2.3 From 86b276c1ddedfbcc0be708e73d82ce1fb2298768 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:30 +0800 Subject: riscv: process: Fix no prototype for show_regs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include header file to fix the following W=1 compilation warning: arch/riscv/kernel/process.c:78:6: warning: no previous prototype for ‘show_regs’ [-Wmissing-prototypes] 78 | void show_regs(struct pt_regs *regs) | ^~~~~~~~~ Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/process.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 6f728e731bed..f9cd57c9c67d 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 288f6775a08913e9cb5f5ae0a43c105b725be0c8 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:31 +0800 Subject: riscv: ftrace: Use ftrace_get_regs helper Use ftrace_get_regs() helper call to get pt_regs from ftrace_regs struct, this makes the code simpler. Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/probes/ftrace.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index e6372490aa0b..2dfb33fdac74 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -4,37 +4,39 @@ /* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *regs) + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct kprobe *p; + struct pt_regs *regs; struct kprobe_ctlblk *kcb; p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) return; + regs = ftrace_get_regs(fregs); kcb = get_kprobe_ctlblk(); if (kprobe_running()) { kprobes_inc_nmissed_count(p); } else { - unsigned long orig_ip = instruction_pointer(&(regs->regs)); + unsigned long orig_ip = instruction_pointer(regs); - instruction_pointer_set(&(regs->regs), ip); + instruction_pointer_set(regs, ip); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) { + if (!p->pre_handler || !p->pre_handler(p, regs)) { /* * Emulate singlestep (and also recover regs->pc) * as if there is a nop */ - instruction_pointer_set(&(regs->regs), + instruction_pointer_set(regs, (unsigned long)p->addr + MCOUNT_INSN_SIZE); if (unlikely(p->post_handler)) { kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, &(regs->regs), 0); + p->post_handler(p, regs, 0); } - instruction_pointer_set(&(regs->regs), orig_ip); + instruction_pointer_set(regs, orig_ip); } /* -- cgit v1.2.3 From 0d7588ab9ef98bad3b52ad0b91291e8258853cc1 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Fri, 5 Mar 2021 19:33:32 +0800 Subject: riscv: process: Fix no prototype for arch_dup_task_struct MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following W=1 compilation warning: arch/riscv/kernel/process.c:114:5: warning: no previous prototype for ‘arch_dup_task_struct’ [-Wmissing-prototypes] 114 | int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) | ^~~~~~~~~~~~~~~~~~~~ Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 3a240037bde2..021ed64ee608 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -71,6 +71,7 @@ int riscv_of_processor_hartid(struct device_node *node); int riscv_of_parent_hartid(struct device_node *node); extern void riscv_fill_hwcap(void); +extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 08c18b63d9656e0389087d1956d2b37fd7019172 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 9 Mar 2021 06:19:30 +0000 Subject: powerpc/vdso32: Add missing _restgpr_31_x to fix build failure With some defconfig including CONFIG_CC_OPTIMIZE_FOR_SIZE, (for instance mvme5100_defconfig and ps3_defconfig), gcc 5 generates a call to _restgpr_31_x. Until recently it went unnoticed, but commit 42ed6d56ade2 ("powerpc/vdso: Block R_PPC_REL24 relocations") made it rise to the surface. Provide that function (copied from lib/crtsavres.S) in gettimeofday.S Fixes: ab037dd87a2f ("powerpc/vdso: Switch VDSO to generic C implementation.") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a7aa198a88bcd33c6e35e99f70f86c7b7f2f9440.1615270757.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/vdso32/gettimeofday.S | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index a6e29f880e0e..d21d08140a5e 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -65,3 +65,14 @@ V_FUNCTION_END(__kernel_clock_getres) V_FUNCTION_BEGIN(__kernel_time) cvdso_call_time __c_kernel_time V_FUNCTION_END(__kernel_time) + +/* Routines for restoring integer registers, called by the compiler. */ +/* Called with r11 pointing to the stack header word of the caller of the */ +/* function, just beyond the end of the integer restore area. */ +_GLOBAL(_restgpr_31_x) +_GLOBAL(_rest32gpr_31_x) + lwz r0,4(r11) + lwz r31,-4(r11) + mtlr r0 + mr r1,r11 + blr -- cgit v1.2.3 From eed5fae00593ab9d261a0c1ffc1bdb786a87a55a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 10 Mar 2021 12:10:34 +0000 Subject: powerpc: Force inlining of cpu_has_feature() to avoid build failure The code relies on constant folding of cpu_has_feature() based on possible and always true values as defined per CPU_FTRS_ALWAYS and CPU_FTRS_POSSIBLE. Build failure is encountered with for instance book3e_all_defconfig on kisskb in the AMDGPU driver which uses cpu_has_feature(CPU_FTR_VSX_COMP) to decide whether calling kernel_enable_vsx() or not. The failure is due to cpu_has_feature() not being inlined with that configuration with gcc 4.9. In the same way as commit acdad8fb4a15 ("powerpc: Force inlining of mmu_has_feature to fix build failure"), for inlining of cpu_has_feature(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b231dfa040ce4cc37f702f5c3a595fdeabfe0462.1615378209.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/cpu_has_feature.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 7897d16e0990..727d4b321937 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -7,7 +7,7 @@ #include #include -static inline bool early_cpu_has_feature(unsigned long feature) +static __always_inline bool early_cpu_has_feature(unsigned long feature) { return !!((CPU_FTRS_ALWAYS & feature) || (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature)); @@ -46,7 +46,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature) return static_branch_likely(&cpu_feature_keys[i]); } #else -static inline bool cpu_has_feature(unsigned long feature) +static __always_inline bool cpu_has_feature(unsigned long feature) { return early_cpu_has_feature(feature); } -- cgit v1.2.3 From c79f01b6eb5dc708573002fb3ba270918bcd1d32 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 10 Mar 2021 14:26:48 +0100 Subject: s390/cpumf: disable preemption when accessing per-cpu variable The following BUG message was triggered repeatedly when complete counter sets are extracted from the CPUMF: BUG: using smp_processor_id() in preemptible [00000000] code: psvc-readsets/7759 caller is cf_diag_needspace+0x2c/0x100 CPU: 7 PID: 7759 Comm: psvc-readsets Not tainted 5.12.0 Hardware name: IBM 3906 M03 703 (LPAR) Call Trace: [<00000000c7043f78>] show_stack+0x90/0xf8 [<00000000c705776a>] dump_stack+0xba/0x108 [<00000000c705d91c>] check_preemption_disabled+0xec/0xf0 [<00000000c63eb1c4>] cf_diag_needspace+0x2c/0x100 [<00000000c63ecbcc>] cf_diag_ioctl_start+0x10c/0x240 [<00000000c63ece9a>] cf_diag_ioctl+0x19a/0x238 [<00000000c675f3f4>] __s390x_sys_ioctl+0xc4/0x100 [<00000000c63ca762>] do_syscall+0x82/0xd0 [<00000000c705bdd8>] __do_syscall+0xc0/0xd8 [<00000000c706d532>] system_call+0x72/0x98 2 locks held by psvc-readsets/7759: #0: 00000000c75a57c0 (cpu_hotplug_lock){++++}-{0:0}, at: cf_diag_ioctl+0x44/0x238 #1: 00000000c75a3078 (cf_diag_ctrset_mutex){+.+.}-{3:3}, at: cf_diag_ioctl+0x54/0x238 This issue is a missing get_cpu_ptr/put_cpu_ptr pair in function cf_diag_needspace. Add it. Fixes: cf6acb8bdb1d ("s390/cpumf: Add support for complete counter set extraction") Reviewed-by: Heiko Carstens Signed-off-by: Thomas Richter Signed-off-by: Heiko Carstens --- arch/s390/kernel/perf_cpum_cf_diag.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index bc302b86ce28..2e3e7edbe3a0 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -968,7 +968,7 @@ static int cf_diag_all_start(void) */ static size_t cf_diag_needspace(unsigned int sets) { - struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); + struct cpu_cf_events *cpuhw = get_cpu_ptr(&cpu_cf_events); size_t bytes = 0; int i; @@ -984,6 +984,7 @@ static size_t cf_diag_needspace(unsigned int sets) sizeof(((struct s390_ctrset_cpudata *)0)->no_sets)); debug_sprintf_event(cf_diag_dbg, 5, "%s bytes %ld\n", __func__, bytes); + put_cpu_ptr(&cpu_cf_events); return bytes; } -- cgit v1.2.3 From d54cb7d54877d529bc1e0e1f47a3dd082f73add3 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Wed, 10 Mar 2021 14:23:37 +0100 Subject: s390/vtime: fix increased steal time accounting Commit 152e9b8676c6e ("s390/vtime: steal time exponential moving average") inadvertently changed the input value for account_steal_time() from "cputime_to_nsecs(steal)" to just "steal", resulting in broken increased steal time accounting. Fix this by changing it back to "cputime_to_nsecs(steal)". Fixes: 152e9b8676c6e ("s390/vtime: steal time exponential moving average") Cc: # 5.1 Reported-by: Sabine Forkel Reviewed-by: Heiko Carstens Signed-off-by: Gerald Schaefer Signed-off-by: Heiko Carstens --- arch/s390/kernel/vtime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 73c7afcc0527..f216a1b2f825 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -214,7 +214,7 @@ void vtime_flush(struct task_struct *tsk) avg_steal = S390_lowcore.avg_steal_timer / 2; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; - account_steal_time(steal); + account_steal_time(cputime_to_nsecs(steal)); avg_steal += steal; } S390_lowcore.avg_steal_timer = avg_steal; -- cgit v1.2.3 From 0b13525c20febcfecccf6fc1db5969727401317d Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Wed, 10 Mar 2021 13:46:26 +0100 Subject: s390/pci: fix leak of PCI device structure In commit 05bc1be6db4b2 ("s390/pci: create zPCI bus") we removed the pci_dev_put() call matching the earlier pci_get_slot() done as part of __zpci_event_availability(). This was based on the wrong understanding that the device_put() done as part of pci_destroy_device() would counter the pci_get_slot() when it only counters the initial reference. This same understanding and existing bad example also lead to not doing a pci_dev_put() in zpci_remove_device(). Since releasing the PCI devices, unlike releasing the PCI slot, does not print any debug message for testing I added one in pci_release_dev(). This revealed that we are indeed leaking the PCI device on PCI hotunplug. Further testing also revealed another missing pci_dev_put() in disable_slot(). Fix this by adding the missing pci_dev_put() in disable_slot() and fix zpci_remove_device() with the correct pci_dev_put() calls. Also instead of calling pci_get_slot() in __zpci_event_availability() to determine if a PCI device is registered and then doing the same again in zpci_remove_device() do this once in zpci_remove_device() which makes sure that the pdev in __zpci_event_availability() is only used for the result of pci_scan_single_device() which does not need a reference count decremnt as its ownership goes to the PCI bus. Also move the check if zdev->zbus->bus is set into zpci_remove_device() since it may be that we're removing a device with devfn != 0 which never had a PCI bus. So we can still set the pdev->error_state to indicate that the device is not usable anymore, add a flag to set the error state. Fixes: 05bc1be6db4b2 ("s390/pci: create zPCI bus") Cc: # 5.8+: e1bff843cde6 s390/pci: remove superfluous zdev->zbus check Cc: # 5.8+: ba764dd703fe s390/pci: refactor zpci_create_device() Cc: # 5.8+ Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens --- arch/s390/include/asm/pci.h | 2 +- arch/s390/pci/pci.c | 28 ++++++++++++++++++++++++---- arch/s390/pci/pci_event.c | 18 ++++++------------ 3 files changed, 31 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 053fe8b8dec7..a75d94a9bcb2 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -202,7 +202,7 @@ extern unsigned int s390_pci_no_rid; ----------------------------------------------------------------------------- */ /* Base stuff */ int zpci_create_device(u32 fid, u32 fh, enum zpci_state state); -void zpci_remove_device(struct zpci_dev *zdev); +void zpci_remove_device(struct zpci_dev *zdev, bool set_error); int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 600881d894dd..91064077526d 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -682,16 +682,36 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); -void zpci_remove_device(struct zpci_dev *zdev) +/* zpci_remove_device - Removes the given zdev from the PCI core + * @zdev: the zdev to be removed from the PCI core + * @set_error: if true the device's error state is set to permanent failure + * + * Sets a zPCI device to a configured but offline state; the zPCI + * device is still accessible through its hotplug slot and the zPCI + * API but is removed from the common code PCI bus, making it + * no longer available to drivers. + */ +void zpci_remove_device(struct zpci_dev *zdev, bool set_error) { struct zpci_bus *zbus = zdev->zbus; struct pci_dev *pdev; + if (!zdev->zbus->bus) + return; + pdev = pci_get_slot(zbus->bus, zdev->devfn); if (pdev) { - if (pdev->is_virtfn) - return zpci_iov_remove_virtfn(pdev, zdev->vfn); + if (set_error) + pdev->error_state = pci_channel_io_perm_failure; + if (pdev->is_virtfn) { + zpci_iov_remove_virtfn(pdev, zdev->vfn); + /* balance pci_get_slot */ + pci_dev_put(pdev); + return; + } pci_stop_and_remove_bus_device_locked(pdev); + /* balance pci_get_slot */ + pci_dev_put(pdev); } } @@ -765,7 +785,7 @@ void zpci_release_device(struct kref *kref) struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); if (zdev->zbus->bus) - zpci_remove_device(zdev); + zpci_remove_device(zdev, false); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b4162da4e8a2..ac0c65cdd69d 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -76,13 +76,10 @@ void zpci_event_error(void *data) static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); - struct pci_dev *pdev = NULL; enum zpci_state state; + struct pci_dev *pdev; int ret; - if (zdev && zdev->zbus->bus) - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - zpci_err("avail CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); @@ -124,8 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) case 0x0303: /* Deconfiguration requested */ if (!zdev) break; - if (pdev) - zpci_remove_device(zdev); + zpci_remove_device(zdev, false); ret = zpci_disable_device(zdev); if (ret) @@ -140,12 +136,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) case 0x0304: /* Configured -> Standby|Reserved */ if (!zdev) break; - if (pdev) { - /* Give the driver a hint that the function is - * already unusable. */ - pdev->error_state = pci_channel_io_perm_failure; - zpci_remove_device(zdev); - } + /* Give the driver a hint that the function is + * already unusable. + */ + zpci_remove_device(zdev, true); zdev->fh = ccdf->fh; zpci_disable_device(zdev); -- cgit v1.2.3 From 70fb3e41a97a5fecc0aedc9a429479d702c3ab66 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 15 Mar 2021 16:38:00 -0700 Subject: KVM: x86/mmu: Fix RCU usage in handle_removed_tdp_mmu_page The pt passed into handle_removed_tdp_mmu_page does not need RCU protection, as it is not at any risk of being freed by another thread at that point. However, the implicit cast from tdp_sptep_t to u64 * dropped the __rcu annotation without a proper rcu_derefrence. Fix this by passing the pt as a tdp_ptep_t and then rcu_dereferencing it in the function. Suggested-by: Sean Christopherson Reported-by: kernel test robot Signed-off-by: Ben Gardon Message-Id: <20210315233803.2706477-2-bgardon@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d78915019b08..db2936cca4bf 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -301,11 +301,16 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp, * * Given a page table that has been removed from the TDP paging structure, * iterates through the page table to clear SPTEs and free child page tables. + * + * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU + * protection. Since this thread removed it from the paging structure, + * this thread will be responsible for ensuring the page is freed. Hence the + * early rcu_dereferences in the function. */ -static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt, +static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, bool shared) { - struct kvm_mmu_page *sp = sptep_to_sp(pt); + struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; u64 old_child_spte; @@ -318,7 +323,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = pt + i; + sptep = rcu_dereference(pt) + i; gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)); if (shared) { -- cgit v1.2.3 From 14f6fec2e8e04b83c87c339b8d8ff4cc62b23d35 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 15 Mar 2021 16:38:01 -0700 Subject: KVM: x86/mmu: Fix RCU usage when atomically zapping SPTEs Fix a missing rcu_dereference in tdp_mmu_zap_spte_atomic. Reported-by: kernel test robot Signed-off-by: Ben Gardon Message-Id: <20210315233803.2706477-3-bgardon@google.com> Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index db2936cca4bf..946da74e069c 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -543,7 +543,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, * here since the SPTE is going from non-present * to non-present. */ - WRITE_ONCE(*iter->sptep, 0); + WRITE_ONCE(*rcu_dereference(iter->sptep), 0); return true; } -- cgit v1.2.3 From b601c3bc9d5053065acdaa1481c21481d0dc3f10 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 15 Mar 2021 16:38:02 -0700 Subject: KVM: x86/mmu: Factor out tdp_iter_return_to_root In tdp_mmu_iter_cond_resched there is a call to tdp_iter_start which causes the iterator to continue its walk over the paging structure from the root. This is needed after a yield as paging structure could have been freed in the interim. The tdp_iter_start call is not very clear and something of a hack. It requires exposing tdp_iter fields not used elsewhere in tdp_mmu.c and the effect is not obvious from the function name. Factor a more aptly named function out of tdp_iter_start and call it from tdp_mmu_iter_cond_resched and tdp_iter_start. No functional change intended. Signed-off-by: Ben Gardon Message-Id: <20210315233803.2706477-4-bgardon@google.com> Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_iter.c | 24 +++++++++++++++++------- arch/x86/kvm/mmu/tdp_iter.h | 1 + arch/x86/kvm/mmu/tdp_mmu.c | 4 +--- 3 files changed, 19 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index e5f148106e20..f7f94ea65243 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -20,6 +20,21 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level) return gfn & -KVM_PAGES_PER_HPAGE(level); } +/* + * Return the TDP iterator to the root PT and allow it to continue its + * traversal over the paging structure from there. + */ +void tdp_iter_restart(struct tdp_iter *iter) +{ + iter->yielded_gfn = iter->next_last_level_gfn; + iter->level = iter->root_level; + + iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + tdp_iter_refresh_sptep(iter); + + iter->valid = true; +} + /* * Sets a TDP iterator to walk a pre-order traversal of the paging structure * rooted at root_pt, starting with the walk to translate next_last_level_gfn. @@ -31,16 +46,11 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, WARN_ON(root_level > PT64_ROOT_MAX_LEVEL); iter->next_last_level_gfn = next_last_level_gfn; - iter->yielded_gfn = iter->next_last_level_gfn; iter->root_level = root_level; iter->min_level = min_level; - iter->level = root_level; - iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt; + iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); - tdp_iter_refresh_sptep(iter); - - iter->valid = true; + tdp_iter_restart(iter); } /* diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 4cc177d75c4a..8eb424d17c91 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -63,5 +63,6 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, int min_level, gfn_t next_last_level_gfn); void tdp_iter_next(struct tdp_iter *iter); tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter); +void tdp_iter_restart(struct tdp_iter *iter); #endif /* __KVM_X86_MMU_TDP_ITER_H */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 946da74e069c..38b6b6936171 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -664,9 +664,7 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, WARN_ON(iter->gfn > iter->next_last_level_gfn); - tdp_iter_start(iter, iter->pt_path[iter->root_level - 1], - iter->root_level, iter->min_level, - iter->next_last_level_gfn); + tdp_iter_restart(iter); return true; } -- cgit v1.2.3 From 08889894cc82bc3b213bdb192f274358e5a6b78d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 15 Mar 2021 16:38:03 -0700 Subject: KVM: x86/mmu: Store the address space ID in the TDP iterator Store the address space ID in the TDP iterator so that it can be retrieved without having to bounce through the root shadow page. This streamlines the code and fixes a Sparse warning about not properly using rcu_dereference() when grabbing the ID from the root on the fly. Reported-by: kernel test robot Signed-off-by: Sean Christopherson Signed-off-by: Ben Gardon Message-Id: <20210315233803.2706477-5-bgardon@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu_internal.h | 5 +++++ arch/x86/kvm/mmu/tdp_iter.c | 6 +----- arch/x86/kvm/mmu/tdp_iter.h | 3 ++- arch/x86/kvm/mmu/tdp_mmu.c | 23 +++++------------------ 4 files changed, 13 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index ec4fc28b325a..1f6f98c76bdf 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -78,6 +78,11 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) return to_shadow_page(__pa(sptep)); } +static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) +{ + return sp->role.smm ? 1 : 0; +} + static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) { /* diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index f7f94ea65243..b3ed302c1a35 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -49,6 +49,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, iter->root_level = root_level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt; + iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt)); tdp_iter_restart(iter); } @@ -169,8 +170,3 @@ void tdp_iter_next(struct tdp_iter *iter) iter->valid = false; } -tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter) -{ - return iter->pt_path[iter->root_level - 1]; -} - diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 8eb424d17c91..b1748b988d3a 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -36,6 +36,8 @@ struct tdp_iter { int min_level; /* The iterator's current level within the paging structure */ int level; + /* The address space ID, i.e. SMM vs. regular. */ + int as_id; /* A snapshot of the value at sptep */ u64 old_spte; /* @@ -62,7 +64,6 @@ tdp_ptep_t spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, int min_level, gfn_t next_last_level_gfn); void tdp_iter_next(struct tdp_iter *iter); -tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); #endif /* __KVM_X86_MMU_TDP_ITER_H */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 38b6b6936171..462b1f71c77f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -203,11 +203,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, u64 old_spte, u64 new_spte, int level, bool shared); -static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) -{ - return sp->role.smm ? 1 : 0; -} - static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) { bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); @@ -497,10 +492,6 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - u64 *root_pt = tdp_iter_root_pt(iter); - struct kvm_mmu_page *root = sptep_to_sp(root_pt); - int as_id = kvm_mmu_page_as_id(root); - lockdep_assert_held_read(&kvm->mmu_lock); /* @@ -514,8 +505,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, new_spte) != iter->old_spte) return false; - handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte, - iter->level, true); + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, true); return true; } @@ -569,10 +560,6 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte, bool record_acc_track, bool record_dirty_log) { - tdp_ptep_t root_pt = tdp_iter_root_pt(iter); - struct kvm_mmu_page *root = sptep_to_sp(root_pt); - int as_id = kvm_mmu_page_as_id(root); - lockdep_assert_held_write(&kvm->mmu_lock); /* @@ -586,13 +573,13 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte); - __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte, - iter->level, false); + __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, false); if (record_acc_track) handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level); if (record_dirty_log) - handle_changed_spte_dirty_log(kvm, as_id, iter->gfn, + handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level); } -- cgit v1.2.3 From d88d05a9e0b6d9356e97129d4ff9942d765f46ea Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 12 Mar 2021 05:21:37 -0800 Subject: perf/x86/intel: Fix a crash caused by zero PEBS status A repeatable crash can be triggered by the perf_fuzzer on some Haswell system. https://lore.kernel.org/lkml/7170d3b-c17f-1ded-52aa-cc6d9ae999f4@maine.edu/ For some old CPUs (HSW and earlier), the PEBS status in a PEBS record may be mistakenly set to 0. To minimize the impact of the defect, the commit was introduced to try to avoid dropping the PEBS record for some cases. It adds a check in the intel_pmu_drain_pebs_nhm(), and updates the local pebs_status accordingly. However, it doesn't correct the PEBS status in the PEBS record, which may trigger the crash, especially for the large PEBS. It's possible that all the PEBS records in a large PEBS have the PEBS status 0. If so, the first get_next_pebs_record_by_bit() in the __intel_pmu_pebs_event() returns NULL. The at = NULL. Since it's a large PEBS, the 'count' parameter must > 1. The second get_next_pebs_record_by_bit() will crash. Besides the local pebs_status, correct the PEBS status in the PEBS record as well. Fixes: 01330d7288e0 ("perf/x86: Allow zero PEBS status with only single active event") Reported-by: Vince Weaver Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1615555298-140216-1-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/intel/ds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7ebae1826403..d32b302719fe 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2010,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d */ if (!pebs_status && cpuc->pebs_enabled && !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) - pebs_status = cpuc->pebs_enabled; + pebs_status = p->status = cpuc->pebs_enabled; bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); -- cgit v1.2.3 From 2dc0572f2cef87425147658698dce2600b799bd3 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 12 Mar 2021 05:21:38 -0800 Subject: perf/x86/intel: Fix unchecked MSR access error caused by VLBR_EVENT On a Haswell machine, the perf_fuzzer managed to trigger this message: [117248.075892] unchecked MSR access error: WRMSR to 0x3f1 (tried to write 0x0400000000000000) at rIP: 0xffffffff8106e4f4 (native_write_msr+0x4/0x20) [117248.089957] Call Trace: [117248.092685] intel_pmu_pebs_enable_all+0x31/0x40 [117248.097737] intel_pmu_enable_all+0xa/0x10 [117248.102210] __perf_event_task_sched_in+0x2df/0x2f0 [117248.107511] finish_task_switch.isra.0+0x15f/0x280 [117248.112765] schedule_tail+0xc/0x40 [117248.116562] ret_from_fork+0x8/0x30 A fake event called VLBR_EVENT may use the bit 58 of the PEBS_ENABLE, if the precise_ip is set. The bit 58 is reserved by the HW. Accessing the bit causes the unchecked MSR access error. The fake event doesn't support PEBS. The case should be rejected. Fixes: 097e4311cda9 ("perf/x86: Add constraint to create guest LBR event without hw counter") Reported-by: Vince Weaver Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1615555298-140216-2-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7bbb5bb98d8c..37ce38403cb8 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3659,6 +3659,9 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { + if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT) + return -EINVAL; + if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & -- cgit v1.2.3 From 66c1b6d74cd7035e85c426f0af4aede19e805c8a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:46:49 +0100 Subject: x86: Move TS_COMPAT back to asm/thread_info.h Move TS_COMPAT back to asm/thread_info.h, close to TS_I386_REGS_POKED. It was moved to asm/processor.h by b9d989c7218a ("x86/asm: Move the thread_info::status field to thread_struct"), then later 37a8f7c38339 ("x86/asm: Move 'status' from thread_struct to thread_info") moved the 'status' field back but TS_COMPAT was forgotten. Preparatory patch to fix the COMPAT case for get_nr_restart_syscall() Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174649.GA17880@redhat.com --- arch/x86/include/asm/processor.h | 9 --------- arch/x86/include/asm/thread_info.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index dc6d149bf851..f1b9ed5efaa9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -551,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, *size = fpu_kernel_xstate_size; } -/* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ - static inline void native_load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0d751d5da702..c2dc29e215ea 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -205,6 +205,15 @@ static inline int arch_within_stack_frames(const void * const stack, #endif +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ #endif -- cgit v1.2.3 From 8c150ba2fb5995c84a7a43848250d444a3329a7d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:47:09 +0100 Subject: x86: Introduce TS_COMPAT_RESTART to fix get_nr_restart_syscall() The comment in get_nr_restart_syscall() says: * The problem is that we can get here when ptrace pokes * syscall-like values into regs even if we're not in a syscall * at all. Yes, but if not in a syscall then the status & (TS_COMPAT|TS_I386_REGS_POKED) check below can't really help: - TS_COMPAT can't be set - TS_I386_REGS_POKED is only set if regs->orig_ax was changed by 32bit debugger; and even in this case get_nr_restart_syscall() is only correct if the tracee is 32bit too. Suppose that a 64bit debugger plays with a 32bit tracee and * Tracee calls sleep(2) // TS_COMPAT is set * User interrupts the tracee by CTRL-C after 1 sec and does "(gdb) call func()" * gdb saves the regs by PTRACE_GETREGS * does PTRACE_SETREGS to set %rip='func' and %orig_rax=-1 * PTRACE_CONT // TS_COMPAT is cleared * func() hits int3. * Debugger catches SIGTRAP. * Restore original regs by PTRACE_SETREGS. * PTRACE_CONT get_nr_restart_syscall() wrongly returns __NR_restart_syscall==219, the tracee calls ia32_sys_call_table[219] == sys_madvise. Add the sticky TS_COMPAT_RESTART flag which survives after return to user mode. It's going to be removed in the next step again by storing the information in the restart block. As a further cleanup it might be possible to remove also TS_I386_REGS_POKED with that. Test-case: $ cvs -d :pserver:anoncvs:anoncvs@sourceware.org:/cvs/systemtap co ptrace-tests $ gcc -o erestartsys-trap-debuggee ptrace-tests/tests/erestartsys-trap-debuggee.c --m32 $ gcc -o erestartsys-trap-debugger ptrace-tests/tests/erestartsys-trap-debugger.c -lutil $ ./erestartsys-trap-debugger Unexpected: retval 1, errno 22 erestartsys-trap-debugger: ptrace-tests/tests/erestartsys-trap-debugger.c:421 Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Reported-by: Jan Kratochvil Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174709.GA17895@redhat.com --- arch/x86/include/asm/thread_info.h | 14 +++++++++++++- arch/x86/kernel/signal.c | 24 +----------------------- 2 files changed, 14 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c2dc29e215ea..30d1d187019f 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -214,10 +214,22 @@ static inline int arch_within_stack_frames(const void * const stack, */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ +#ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ +#define TS_COMPAT_RESTART 0x0008 + +#define arch_set_restart_data arch_set_restart_data + +static inline void arch_set_restart_data(struct restart_block *restart) +{ + struct thread_info *ti = current_thread_info(); + if (ti->status & TS_COMPAT) + ti->status |= TS_COMPAT_RESTART; + else + ti->status &= ~TS_COMPAT_RESTART; +} #endif -#ifndef __ASSEMBLY__ #ifdef CONFIG_X86_32 #define in_ia32_syscall() true diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index ea794a083c44..6c26d2c3a2e4 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -766,30 +766,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { - /* - * This function is fundamentally broken as currently - * implemented. - * - * The idea is that we want to trigger a call to the - * restart_block() syscall and that we want in_ia32_syscall(), - * in_x32_syscall(), etc. to match whatever they were in the - * syscall being restarted. We assume that the syscall - * instruction at (regs->ip - 2) matches whatever syscall - * instruction we used to enter in the first place. - * - * The problem is that we can get here when ptrace pokes - * syscall-like values into regs even if we're not in a syscall - * at all. - * - * For now, we maintain historical behavior and guess based on - * stored state. We could do better by saving the actual - * syscall arch in restart_block or (with caveats on x32) by - * checking if regs->ip points to 'int $0x80'. The current - * behavior is incorrect if a tracer has a different bitness - * than the tracee. - */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & TS_COMPAT_RESTART) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI -- cgit v1.2.3 From b2e9df850c58c2b36e915e7d3bed3f6107cccba6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:47:16 +0100 Subject: x86: Introduce restart_block->arch_data to remove TS_COMPAT_RESTART Save the current_thread_info()->status of X86 in the new restart_block->arch_data field so TS_COMPAT_RESTART can be removed again. Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210201174716.GA17898@redhat.com --- arch/x86/include/asm/thread_info.h | 12 ++---------- arch/x86/kernel/signal.c | 2 +- 2 files changed, 3 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 30d1d187019f..06b740bae431 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -217,18 +217,10 @@ static inline int arch_within_stack_frames(const void * const stack, #ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ -#define TS_COMPAT_RESTART 0x0008 -#define arch_set_restart_data arch_set_restart_data +#define arch_set_restart_data(restart) \ + do { restart->arch_data = current_thread_info()->status; } while (0) -static inline void arch_set_restart_data(struct restart_block *restart) -{ - struct thread_info *ti = current_thread_info(); - if (ti->status & TS_COMPAT) - ti->status |= TS_COMPAT_RESTART; - else - ti->status &= ~TS_COMPAT_RESTART; -} #endif #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6c26d2c3a2e4..f306e85a08a6 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -767,7 +767,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & TS_COMPAT_RESTART) + if (current->restart_block.arch_data & TS_COMPAT) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI -- cgit v1.2.3 From 3f6c515d723480bc8afd456b0a52438fe79128a8 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 16 Mar 2021 15:45:15 +0000 Subject: MIPS: vmlinux.lds.S: Fix appended dtb not properly aligned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 6654111c893f ("MIPS: vmlinux.lds.S: align raw appended dtb to 8 bytes") changed the alignment from STRUCT_ALIGNMENT bytes to 8 bytes. The commit's message makes it sound like it was actually done on purpose, but this is not the case. The commit was written when raw appended dtb were not aligned at all. The STRUCT_ALIGN() was added a few days before, in commit 7a05293af39f ("MIPS: boot/compressed: Copy DTB to aligned address"). The true purpose of the commit was not to align specifically to 8 bytes, but to make sure that the generated vmlinux' size was properly padded to the alignment required for DTBs. While the switch to 8-byte alignment worked for vmlinux-appended dtb blobs, it broke vmlinuz-appended dtb blobs, as the decompress routine moves the blob to a STRUCT_ALIGNMENT aligned address. Fix this by changing the raw appended dtb blob alignment from 8 bytes back to STRUCT_ALIGNMENT bytes in vmlinux.lds.S. Fixes: 6654111c893f ("MIPS: vmlinux.lds.S: align raw appended dtb to 8 bytes") Cc: Bjørn Mork Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 1234834cc4c4..1f98947fe715 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -176,7 +176,7 @@ SECTIONS .fill : { FILL(0); BYTE(0); - . = ALIGN(8); + STRUCT_ALIGN(); } __appended_dtb = .; /* leave space for appended DTB */ -- cgit v1.2.3 From 6e9070dc2e847ef77aa1c581252a1b97eb2225b9 Mon Sep 17 00:00:00 2001 From: kernel test robot Date: Sun, 28 Feb 2021 12:10:22 +0100 Subject: riscv: fix bugon.cocci warnings Use BUG_ON instead of a if condition followed by BUG. Generated by: scripts/coccinelle/misc/bugon.cocci Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported") CC: Guo Ren Reported-by: kernel test robot Signed-off-by: kernel test robot Signed-off-by: Julia Lawall Reviewed-by: Pekka Enberg Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/probes/kprobes.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index a2ec18662fee..7e2c78e2ca6b 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -256,8 +256,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr) * normal page fault. */ regs->epc = (unsigned long) cur->addr; - if (!instruction_pointer(regs)) - BUG(); + BUG_ON(!instruction_pointer(regs)); if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); -- cgit v1.2.3 From bab1770a2ce00bf201c6ac5a013a7195db2e02b7 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 11 Mar 2021 09:40:22 +0000 Subject: ftrace: Fix spelling mistake "disabed" -> "disabled" There is a spelling mistake in a comment, fix it. Signed-off-by: Colin Ian King Signed-off-by: Palmer Dabbelt --- arch/csky/kernel/probes/ftrace.c | 2 +- arch/riscv/kernel/probes/ftrace.c | 2 +- arch/x86/kernel/kprobes/ftrace.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c index ae2b1c7b3b5c..ef2bb9bd9605 100644 --- a/arch/csky/kernel/probes/ftrace.c +++ b/arch/csky/kernel/probes/ftrace.c @@ -9,7 +9,7 @@ int arch_check_ftrace_location(struct kprobe *p) return 0; } -/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index 2dfb33fdac74..17ca5e923bb0 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -2,7 +2,7 @@ #include -/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 373e5fa3ce1f..51c7f5271aee 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -12,7 +12,7 @@ #include "common.h" -/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { -- cgit v1.2.3 From fa59030bf8555a4eb83342fd23c32e30d4f2fe7a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 Mar 2021 19:24:24 +0900 Subject: riscv: Fix compilation error with Canaan SoC When CONFIG_SOC_CANAAN is selected, the K210 sysctl driver is always compiled. Since this driver early init function calls the function k210_clk_early_init() implemented by the K210 clk driver, this driver must also always be selected for compilation ot avoid build failures. Avoid such build failures by always selecting CONFIG_COMMON_CLK and CONFIG_COMMON_CLK_K210 when CONFIG_SOC_CANAAN is enabled. Reported-by: kernel test robot Signed-off-by: Damien Le Moal Fixes: c6ca7616f7d5 ("clk: Add RISC-V Canaan Kendryte K210 clock driver") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig.socs | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 7efcece8896c..e1b2690b6e45 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -31,6 +31,8 @@ config SOC_CANAAN select SIFIVE_PLIC select ARCH_HAS_RESET_CONTROLLER select PINCTRL + select COMMON_CLK + select COMMON_CLK_K210 help This enables support for Canaan Kendryte K210 SoC platform hardware. -- cgit v1.2.3 From ce989f1472ae350e844b10c880b22543168fbc92 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 12 Mar 2021 16:46:34 +0100 Subject: RISC-V: Fix out-of-bounds accesses in init_resources() init_resources() allocates an array of resources, based on the current total number of memory regions and reserved memory regions. However, allocating this array using memblock_alloc() might increase the number of reserved memory regions. If that happens, populating the array later based on the new number of regions will cause out-of-bounds writes beyond the end of the allocated array. Fix this by allocating one more entry, which may or may not be used. Fixes: 797f0375dd2ef5cd ("RISC-V: Do not allocate memblock while iterating reserved memblocks") Signed-off-by: Geert Uytterhoeven Reviewed-by: Atish Patra Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/setup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index e85bacff1b50..f8f15332caa2 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -147,7 +147,8 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */ + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt + 1) * sizeof(*mem_res); mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); if (!mem_res) panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); -- cgit v1.2.3 From f3773dd031de7b283227f6104049688f77074a2d Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Sat, 13 Mar 2021 03:45:04 -0500 Subject: riscv: Ensure page table writes are flushed when initializing KASAN vmalloc Make sure that writes to kernel page table during KASAN vmalloc initialization are made visible by adding a sfence.vma. Signed-off-by: Alexandre Ghiti Reviewed-by: Palmer Dabbelt Fixes: e178d670f251 ("riscv/kasan: add KASAN_VMALLOC support") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/kasan_init.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 3fc18f469efb..5c35e0f71e88 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -187,6 +187,8 @@ void __init kasan_shallow_populate(void *start, void *end) } vaddr += PAGE_SIZE; } + + local_flush_tlb_all(); } void __init kasan_init(void) -- cgit v1.2.3 From 78947bdfd75211cc9482cad01f95fe103a863110 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Tue, 16 Mar 2021 22:01:04 -0700 Subject: RISC-V: kasan: Declare kasan_shallow_populate() static Without this I get a missing prototype warning. Reported-by: kernel test robot Fixes: e178d670f251 ("riscv/kasan: add KASAN_VMALLOC support") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/kasan_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 5c35e0f71e88..4f85c6d0ddf8 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -155,7 +155,7 @@ static void __init kasan_populate(void *start, void *end) memset(start, KASAN_SHADOW_INIT, end - start); } -void __init kasan_shallow_populate(void *start, void *end) +static void __init kasan_shallow_populate(void *start, void *end) { unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); -- cgit v1.2.3 From a5406a7ff56e63376c210b06072aa0ef23473366 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 15 Mar 2021 20:03:07 +0800 Subject: riscv: Correct SPARSEMEM configuration There are two issues for RV32, 1) if use FLATMEM, it is useless to enable SPARSEMEM_STATIC. 2) if use SPARSMEM, both SPARSEMEM_VMEMMAP and SPARSEMEM_STATIC is enabled. Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem") Signed-off-by: Kefeng Wang Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 85d626b8ce5e..87d7b52f278f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -93,7 +93,6 @@ config RISCV select PCI_MSI if PCI select RISCV_INTC select RISCV_TIMER if RISCV_SBI - select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK @@ -154,7 +153,8 @@ config ARCH_FLATMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool y depends on MMU - select SPARSEMEM_VMEMMAP_ENABLE + select SPARSEMEM_STATIC if 32BIT && SPARSMEM + select SPARSEMEM_VMEMMAP_ENABLE if 64BIT config ARCH_SELECT_MEMORY_MODEL def_bool ARCH_SPARSEMEM_ENABLE -- cgit v1.2.3 From d2547cf59793168b564372d75620897416cbaf87 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 16 Mar 2021 15:37:33 +0100 Subject: KVM: x86: hyper-v: Limit guest to writing zero to HV_X64_MSR_TSC_EMULATION_STATUS HV_X64_MSR_TSC_EMULATION_STATUS indicates whether TSC accesses are emulated after migration (to accommodate for a different host TSC frequency when TSC scaling is not supported; we don't implement this in KVM). Guest can use the same MSR to stop TSC access emulation by writing zero. Writing anything else is forbidden. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210316143736.964151-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 58fa8c029867..eefb85b86fe8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1229,6 +1229,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, hv->hv_tsc_emulation_control = data; break; case HV_X64_MSR_TSC_EMULATION_STATUS: + if (data && !host) + return 1; + hv->hv_tsc_emulation_status = data; break; case HV_X64_MSR_TIME_REF_COUNT: -- cgit v1.2.3 From e880c6ea55b9805294ecc100ee95e0c9860ae90e Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 16 Mar 2021 15:37:34 +0100 Subject: KVM: x86: hyper-v: Prevent using not-yet-updated TSC page by secondary CPUs When KVM_REQ_MASTERCLOCK_UPDATE request is issued (e.g. after migration) we need to make sure no vCPU sees stale values in PV clock structures and thus all vCPUs are kicked with KVM_REQ_CLOCK_UPDATE. Hyper-V TSC page clocksource is global and kvm_guest_time_update() only updates in on vCPU0 but this is not entirely correct: nothing blocks some other vCPU from entering the guest before we finish the update on CPU0 and it can read stale values from the page. Invalidate TSC page in kvm_gen_update_masterclock() to switch all vCPUs to using MSR based clocksource (HV_X64_MSR_TIME_REF_COUNT). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210316143736.964151-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 23 +++++++++++++++++++++++ arch/x86/kvm/hyperv.h | 1 + arch/x86/kvm/x86.c | 2 ++ 3 files changed, 26 insertions(+) (limited to 'arch') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index eefb85b86fe8..a0e3c49233d4 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1137,6 +1137,29 @@ out_unlock: mutex_unlock(&hv->hv_lock); } +void kvm_hv_invalidate_tsc_page(struct kvm *kvm) +{ + struct kvm_hv *hv = to_kvm_hv(kvm); + u64 gfn; + + if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + return; + + mutex_lock(&hv->hv_lock); + + if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + goto out_unlock; + + gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + + hv->tsc_ref.tsc_sequence = 0; + kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); + +out_unlock: + mutex_unlock(&hv->hv_lock); +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e951af1fcb2c..60547d5cb6d7 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -133,6 +133,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); +void kvm_hv_invalidate_tsc_page(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47e021bdcc94..a5c5b38735e1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2551,6 +2551,8 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + kvm_hv_invalidate_tsc_page(kvm); + spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ -- cgit v1.2.3 From 6417f03132a6952cd17ddd8eaddbac92b61b17e0 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 17 Mar 2021 12:45:47 +0200 Subject: module: remove never implemented MODULE_SUPPORTED_DEVICE MODULE_SUPPORTED_DEVICE was added in pre-git era and never was implemented. We can safely remove it, because the kernel has grown to have many more reliable mechanisms to determine if device is supported or not. Signed-off-by: Leon Romanovsky Signed-off-by: Linus Torvalds --- arch/x86/platform/iris/iris.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c index 1ac8578258af..b42bfdab01a9 100644 --- a/arch/x86/platform/iris/iris.c +++ b/arch/x86/platform/iris/iris.c @@ -27,7 +27,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Sébastien Hinderer "); MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille"); -MODULE_SUPPORTED_DEVICE("Eurobraille/Iris"); static bool force; -- cgit v1.2.3 From cc9cfddb0433961107bb156fa769fdd7eb6718de Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 16 Mar 2021 15:37:35 +0100 Subject: KVM: x86: hyper-v: Track Hyper-V TSC page status Create an infrastructure for tracking Hyper-V TSC page status, i.e. if it was updated from guest/host side or if we've failed to set it up (because e.g. guest wrote some garbage to HV_X64_MSR_REFERENCE_TSC) and there's no need to retry. Also, in a hypothetical situation when we are in 'always catchup' mode for TSC we can now avoid contending 'hv->hv_lock' on every guest enter by setting the state to HV_TSC_PAGE_BROKEN after compute_tsc_page_parameters() returns false. Check for HV_TSC_PAGE_SET state instead of '!hv->tsc_ref.tsc_sequence' in get_time_ref_counter() to properly handle the situation when we failed to write the updated TSC page values to the guest. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210316143736.964151-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 17 ++++++++++++++ arch/x86/kvm/hyperv.c | 49 +++++++++++++++++++++++++++++------------ 2 files changed, 52 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9bc091ecaaeb..e1b6e2edc828 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -884,12 +884,29 @@ struct kvm_hv_syndbg { u64 options; }; +/* Current state of Hyper-V TSC page clocksource */ +enum hv_tsc_page_status { + /* TSC page was not set up or disabled */ + HV_TSC_PAGE_UNSET = 0, + /* TSC page MSR was written by the guest, update pending */ + HV_TSC_PAGE_GUEST_CHANGED, + /* TSC page MSR was written by KVM userspace, update pending */ + HV_TSC_PAGE_HOST_CHANGED, + /* TSC page was properly set up and is currently active */ + HV_TSC_PAGE_SET, + /* TSC page is currently being updated and therefore is inactive */ + HV_TSC_PAGE_UPDATING, + /* TSC page was set up with an inaccessible GPA */ + HV_TSC_PAGE_BROKEN, +}; + /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; + enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index a0e3c49233d4..5c0f10a2b3ab 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -520,10 +520,10 @@ static u64 get_time_ref_counter(struct kvm *kvm) u64 tsc; /* - * The guest has not set up the TSC page or the clock isn't - * stable, fall back to get_kvmclock_ns. + * Fall back to get_kvmclock_ns() when TSC page hasn't been set up, + * is broken, disabled or being updated. */ - if (!hv->tsc_ref.tsc_sequence) + if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET) return div_u64(get_kvmclock_ns(kvm), 100); vcpu = kvm_get_vcpu(kvm, 0); @@ -1087,7 +1087,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) return; mutex_lock(&hv->hv_lock); @@ -1101,7 +1102,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, */ if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn), &tsc_seq, sizeof(tsc_seq)))) - goto out_unlock; + goto out_err; /* * While we're computing and writing the parameters, force the @@ -1110,15 +1111,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, hv->tsc_ref.tsc_sequence = 0; if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) - goto out_unlock; + goto out_err; if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref)) - goto out_unlock; + goto out_err; /* Ensure sequence is zero before writing the rest of the struct. */ smp_wmb(); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) - goto out_unlock; + goto out_err; /* * Now switch to the TSC page mechanism by writing the sequence. @@ -1131,8 +1132,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, smp_wmb(); hv->tsc_ref.tsc_sequence = tsc_seq; - kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + goto out_err; + + hv->hv_tsc_page_status = HV_TSC_PAGE_SET; + goto out_unlock; + +out_err: + hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; out_unlock: mutex_unlock(&hv->hv_lock); } @@ -1142,7 +1150,8 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) struct kvm_hv *hv = to_kvm_hv(kvm); u64 gfn; - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) return; mutex_lock(&hv->hv_lock); @@ -1150,11 +1159,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) goto out_unlock; + /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */ + if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET) + hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING; + gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; hv->tsc_ref.tsc_sequence = 0; - kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; out_unlock: mutex_unlock(&hv->hv_lock); @@ -1216,8 +1230,15 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, } case HV_X64_MSR_REFERENCE_TSC: hv->hv_tsc_page = data; - if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) + if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) { + if (!host) + hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED; + else + hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + } else { + hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET; + } break; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: return kvm_hv_msr_set_crash_data(kvm, -- cgit v1.2.3 From 0469f2f7ab4c6a6cae4b74c4f981c4da6d909411 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 16 Mar 2021 15:37:36 +0100 Subject: KVM: x86: hyper-v: Don't touch TSC page values when guest opted for re-enlightenment When guest opts for re-enlightenment notifications upon migration, it is in its right to assume that TSC page values never change (as they're only supposed to change upon migration and the host has to keep things as they are before it receives confirmation from the guest). This is mostly true until the guest is migrated somewhere. KVM userspace (e.g. QEMU) will trigger masterclock update by writing to HV_X64_MSR_REFERENCE_TSC, by calling KVM_SET_CLOCK,... and as TSC value and kvmclock reading drift apart (even slightly), the update causes TSC page values to change. The issue at hand is that when Hyper-V is migrated, it uses stale (cached) TSC page values to compute the difference between its own clocksource (provided by KVM) and its guests' TSC pages to program synthetic timers and in some cases, when TSC page is updated, this puts all stimer expirations in the past. This, in its turn, causes an interrupt storm and L2 guests not making much forward progress. Note, KVM doesn't fully implement re-enlightenment notification. Basically, the support for reenlightenment MSRs is just a stub and userspace is only expected to expose the feature when TSC scaling on the expected destination hosts is available. With TSC scaling, no real re-enlightenment is needed as TSC frequency doesn't change. With TSC scaling becoming ubiquitous, it likely makes little sense to fully implement re-enlightenment in KVM. Prevent TSC page from being updated after migration. In case it's not the guest who's initiating the change and when TSC page is already enabled, just keep it as it is: TSC value is supposed to be preserved across migration and TSC frequency can't change with re-enlightenment enabled. The guest is doomed anyway if any of this is not true. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210316143736.964151-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5c0f10a2b3ab..f98370a39936 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1077,6 +1077,21 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock, return true; } +/* + * Don't touch TSC page values if the guest has opted for TSC emulation after + * migration. KVM doesn't fully support reenlightenment notifications and TSC + * access emulation and Hyper-V is known to expect the values in TSC page to + * stay constant before TSC access emulation is disabled from guest side + * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC + * frequency and guest visible TSC value across migration (and prevent it when + * TSC scaling is unsupported). + */ +static inline bool tsc_page_update_unsafe(struct kvm_hv *hv) +{ + return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) && + hv->hv_tsc_emulation_control; +} + void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock) { @@ -1104,6 +1119,14 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, &tsc_seq, sizeof(tsc_seq)))) goto out_err; + if (tsc_seq && tsc_page_update_unsafe(hv)) { + if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) + goto out_err; + + hv->hv_tsc_page_status = HV_TSC_PAGE_SET; + goto out_unlock; + } + /* * While we're computing and writing the parameters, force the * guest to use the time reference count MSR. @@ -1151,7 +1174,8 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) u64 gfn; if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || - hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) + hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || + tsc_page_update_unsafe(hv)) return; mutex_lock(&hv->hv_lock); -- cgit v1.2.3 From b318e8decf6b9ef1bcf4ca06fae6d6a2cb5d5c5c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 16 Mar 2021 11:44:33 -0700 Subject: KVM: x86: Protect userspace MSR filter with SRCU, and set atomically-ish Fix a plethora of issues with MSR filtering by installing the resulting filter as an atomic bundle instead of updating the live filter one range at a time. The KVM_X86_SET_MSR_FILTER ioctl() isn't truly atomic, as the hardware MSR bitmaps won't be updated until the next VM-Enter, but the relevant software struct is atomically updated, which is what KVM really needs. Similar to the approach used for modifying memslots, make arch.msr_filter a SRCU-protected pointer, do all the work configuring the new filter outside of kvm->lock, and then acquire kvm->lock only when the new filter has been vetted and created. That way vCPU readers either see the old filter or the new filter in their entirety, not some half-baked state. Yuan Yao pointed out a use-after-free in ksm_msr_allowed() due to a TOCTOU bug, but that's just the tip of the iceberg... - Nothing is __rcu annotated, making it nigh impossible to audit the code for correctness. - kvm_add_msr_filter() has an unpaired smp_wmb(). Violation of kernel coding style aside, the lack of a smb_rmb() anywhere casts all code into doubt. - kvm_clear_msr_filter() has a double free TOCTOU bug, as it grabs count before taking the lock. - kvm_clear_msr_filter() also has memory leak due to the same TOCTOU bug. The entire approach of updating the live filter is also flawed. While installing a new filter is inherently racy if vCPUs are running, fixing the above issues also makes it trivial to ensure certain behavior is deterministic, e.g. KVM can provide deterministic behavior for MSRs with identical settings in the old and new filters. An atomic update of the filter also prevents KVM from getting into a half-baked state, e.g. if installing a filter fails, the existing approach would leave the filter in a half-baked state, having already committed whatever bits of the filter were already processed. [*] https://lkml.kernel.org/r/20210312083157.25403-1-yaoyuan0329os@gmail.com Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering") Cc: stable@vger.kernel.org Cc: Alexander Graf Reported-by: Yuan Yao Signed-off-by: Sean Christopherson Message-Id: <20210316184436.2544875-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 17 ++++--- arch/x86/kvm/x86.c | 109 ++++++++++++++++++++++++---------------- 2 files changed, 74 insertions(+), 52 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e1b6e2edc828..3768819693e5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -948,6 +948,12 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +struct kvm_x86_msr_filter { + u8 count; + bool default_allow:1; + struct msr_bitmap_range ranges[16]; +}; + #define APICV_INHIBIT_REASON_DISABLE 0 #define APICV_INHIBIT_REASON_HYPERV 1 #define APICV_INHIBIT_REASON_NESTED 2 @@ -1042,16 +1048,11 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled; + bool bus_lock_detection_enabled; + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; - - struct { - u8 count; - bool default_allow:1; - struct msr_bitmap_range ranges[16]; - } msr_filter; - - bool bus_lock_detection_enabled; + struct kvm_x86_msr_filter __rcu *msr_filter; struct kvm_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a5c5b38735e1..a04e78b89637 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1526,35 +1526,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { + struct kvm_x86_msr_filter *msr_filter; + struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; - u32 count = kvm->arch.msr_filter.count; - u32 i; - bool r = kvm->arch.msr_filter.default_allow; + bool allowed; int idx; + u32 i; - /* MSR filtering not set up or x2APIC enabled, allow everything */ - if (!count || (index >= 0x800 && index <= 0x8ff)) + /* x2APIC MSRs do not support filtering. */ + if (index >= 0x800 && index <= 0x8ff) return true; - /* Prevent collision with set_msr_filter */ idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < count; i++) { + msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); + if (!msr_filter) { + allowed = true; + goto out; + } + + allowed = msr_filter->default_allow; + ranges = msr_filter->ranges; + + for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { - r = !!test_bit(index - start, bitmap); + allowed = !!test_bit(index - start, bitmap); break; } } +out: srcu_read_unlock(&kvm->srcu, idx); - return r; + return allowed; } EXPORT_SYMBOL_GPL(kvm_msr_allowed); @@ -5354,25 +5363,34 @@ split_irqchip_unlock: return r; } -static void kvm_clear_msr_filter(struct kvm *kvm) +static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) +{ + struct kvm_x86_msr_filter *msr_filter; + + msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); + if (!msr_filter) + return NULL; + + msr_filter->default_allow = default_allow; + return msr_filter; +} + +static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; - u32 count = kvm->arch.msr_filter.count; - struct msr_bitmap_range ranges[16]; - mutex_lock(&kvm->lock); - kvm->arch.msr_filter.count = 0; - memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0])); - mutex_unlock(&kvm->lock); - synchronize_srcu(&kvm->srcu); + if (!msr_filter) + return; + + for (i = 0; i < msr_filter->count; i++) + kfree(msr_filter->ranges[i].bitmap); - for (i = 0; i < count; i++) - kfree(ranges[i].bitmap); + kfree(msr_filter); } -static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range) +static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, + struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; @@ -5406,11 +5424,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user goto err; } - /* Everything ok, add this range identifier to our global pool */ - ranges[kvm->arch.msr_filter.count] = range; - /* Make sure we filled the array before we tell anyone to walk it */ - smp_wmb(); - kvm->arch.msr_filter.count++; + /* Everything ok, add this range identifier. */ + msr_filter->ranges[msr_filter->count] = range; + msr_filter->count++; return 0; err: @@ -5421,10 +5437,11 @@ err: static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) { struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_x86_msr_filter *new_filter, *old_filter; struct kvm_msr_filter filter; bool default_allow; - int r = 0; bool empty = true; + int r = 0; u32 i; if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) @@ -5437,25 +5454,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (empty && !default_allow) return -EINVAL; - kvm_clear_msr_filter(kvm); - - kvm->arch.msr_filter.default_allow = default_allow; + new_filter = kvm_alloc_msr_filter(default_allow); + if (!new_filter) + return -ENOMEM; - /* - * Protect from concurrent calls to this function that could trigger - * a TOCTOU violation on kvm->arch.msr_filter.count. - */ - mutex_lock(&kvm->lock); for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(kvm, &filter.ranges[i]); - if (r) - break; + r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + if (r) { + kvm_free_msr_filter(new_filter); + return r; + } } + mutex_lock(&kvm->lock); + + /* The per-VM filter is protected by kvm->lock... */ + old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); + + rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + synchronize_srcu(&kvm->srcu); + + kvm_free_msr_filter(old_filter); + kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); mutex_unlock(&kvm->lock); - return r; + return 0; } long kvm_arch_vm_ioctl(struct file *filp, @@ -10636,8 +10660,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - u32 i; - if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, @@ -10653,8 +10675,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); } static_call_cond(kvm_x86_vm_destroy)(kvm); - for (i = 0; i < kvm->arch.msr_filter.count; i++) - kfree(kvm->arch.msr_filter.ranges[i].bitmap); + kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); -- cgit v1.2.3 From c2162e13d6e2f43e5001a356196871642de070ba Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 12 Mar 2021 10:45:51 +0800 Subject: KVM: X86: Fix missing local pCPU when executing wbinvd on all dirty pCPUs In order to deal with noncoherent DMA, we should execute wbinvd on all dirty pCPUs when guest wbinvd exits to maintain data consistency. smp_call_function_many() does not execute the provided function on the local core, therefore replace it by on_each_cpu_mask(). Reported-by: Nadav Amit Cc: Nadav Amit Signed-off-by: Wanpeng Li Message-Id: <1615517151-7465-1-git-send-email-wanpengli@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a04e78b89637..fe806e894212 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6629,7 +6629,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); - smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask, wbinvd_ipi, NULL, 1); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); -- cgit v1.2.3 From f4e61f0c9add3b00bd5f2df3c814d688849b8707 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 15 Mar 2021 14:55:28 +0800 Subject: x86/kvm: Fix broken irq restoration in kvm_wait After commit 997acaf6b4b59c (lockdep: report broken irq restoration), the guest splatting below during boot: raw_local_irq_restore() called with IRQs enabled WARNING: CPU: 1 PID: 169 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x26/0x30 Modules linked in: hid_generic usbhid hid CPU: 1 PID: 169 Comm: systemd-udevd Not tainted 5.11.0+ #25 RIP: 0010:warn_bogus_irq_restore+0x26/0x30 Call Trace: kvm_wait+0x76/0x90 __pv_queued_spin_lock_slowpath+0x285/0x2e0 do_raw_spin_lock+0xc9/0xd0 _raw_spin_lock+0x59/0x70 lockref_get_not_dead+0xf/0x50 __legitimize_path+0x31/0x60 legitimize_root+0x37/0x50 try_to_unlazy_next+0x7f/0x1d0 lookup_fast+0xb0/0x170 path_openat+0x165/0x9b0 do_filp_open+0x99/0x110 do_sys_openat2+0x1f1/0x2e0 do_sys_open+0x5c/0x80 __x64_sys_open+0x21/0x30 do_syscall_64+0x32/0x50 entry_SYSCALL_64_after_hwframe+0x44/0xae The new consistency checking, expects local_irq_save() and local_irq_restore() to be paired and sanely nested, and therefore expects local_irq_restore() to be called with irqs disabled. The irqflags handling in kvm_wait() which ends up doing: local_irq_save(flags); safe_halt(); local_irq_restore(flags); instead triggers it. This patch fixes it by using local_irq_disable()/enable() directly. Cc: Thomas Gleixner Reported-by: Dmitry Vyukov Signed-off-by: Wanpeng Li Message-Id: <1615791328-2735-1-git-send-email-wanpengli@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5e78e01ca3b4..78bb0fae3982 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -836,28 +836,25 @@ static void kvm_kick_cpu(int cpu) static void kvm_wait(u8 *ptr, u8 val) { - unsigned long flags; - if (in_nmi()) return; - local_irq_save(flags); - - if (READ_ONCE(*ptr) != val) - goto out; - /* * halt until it's our turn and kicked. Note that we do safe halt * for irq enabled case to avoid hang when lock info is overwritten * in irq spinlock slowpath and no spurious interrupt occur to save us. */ - if (arch_irqs_disabled_flags(flags)) - halt(); - else - safe_halt(); + if (irqs_disabled()) { + if (READ_ONCE(*ptr) == val) + halt(); + } else { + local_irq_disable(); -out: - local_irq_restore(flags); + if (READ_ONCE(*ptr) == val) + safe_halt(); + + local_irq_enable(); + } } #ifdef CONFIG_X86_32 -- cgit v1.2.3 From a501b048a95b79e1e34f03cac3c87ff1e9f229ad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 18 Mar 2021 20:26:47 +0100 Subject: x86/ioapic: Ignore IRQ2 again Vitaly ran into an issue with hotplugging CPU0 on an Amazon instance where the matrix allocator claimed to be out of vectors. He analyzed it down to the point that IRQ2, the PIC cascade interrupt, which is supposed to be not ever routed to the IO/APIC ended up having an interrupt vector assigned which got moved during unplug of CPU0. The underlying issue is that IRQ2 for various reasons (see commit af174783b925 ("x86: I/O APIC: Never configure IRQ2" for details) is treated as a reserved system vector by the vector core code and is not accounted as a regular vector. The Amazon BIOS has an routing entry of pin2 to IRQ2 which causes the IO/APIC setup to claim that interrupt which is granted by the vector domain because there is no sanity check. As a consequence the allocation counter of CPU0 underflows which causes a subsequent unplug to fail with: [ ... ] CPU 0 has 4294967295 vectors, 589 available. Cannot disable CPU There is another sanity check missing in the matrix allocator, but the underlying root cause is that the IO/APIC code lost the IRQ2 ignore logic during the conversion to irqdomains. For almost 6 years nobody complained about this wreckage, which might indicate that this requirement could be lifted, but for any system which actually has a PIC IRQ2 is unusable by design so any routing entry has no effect and the interrupt cannot be connected to a device anyway. Due to that and due to history biased paranoia reasons restore the IRQ2 ignore logic and treat it as non existent despite a routing entry claiming otherwise. Fixes: d32932d02e18 ("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces") Reported-by: Vitaly Kuznetsov Signed-off-by: Thomas Gleixner Tested-by: Vitaly Kuznetsov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210318192819.636943062@linutronix.de --- arch/x86/kernel/apic/io_apic.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c3b60c37c728..73ff4dd426a8 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1032,6 +1032,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; legacy = mp_is_legacy_irq(irq); + /* + * IRQ2 is unusable for historical reasons on systems which + * have a legacy PIC. See the comment vs. IRQ2 further down. + * + * If this gets removed at some point then the related code + * in lapic_assign_system_vectors() needs to be adjusted as + * well. + */ + if (legacy && irq == PIC_CASCADE_IR) + return -EINVAL; } mutex_lock(&ioapic_mutex); -- cgit v1.2.3 From dd926880da8dbbe409e709c1d3c1620729a94732 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 12 Mar 2021 10:20:33 +0100 Subject: x86/apic/of: Fix CPU devicetree-node lookups Architectures that describe the CPU topology in devicetree and do not have an identity mapping between physical and logical CPU ids must override the default implementation of arch_match_cpu_phys_id(). Failing to do so breaks CPU devicetree-node lookups using of_get_cpu_node() and of_cpu_device_node_get() which several drivers rely on. It also causes the CPU struct devices exported through sysfs to point to the wrong devicetree nodes. On x86, CPUs are described in devicetree using their APIC ids and those do not generally coincide with the logical ids, even if CPU0 typically uses APIC id 0. Add the missing implementation of arch_match_cpu_phys_id() so that CPU-node lookups work also with SMP. Apart from fixing the broken sysfs devicetree-node links this likely does not affect current users of mainline kernels on x86. Fixes: 4e07db9c8db8 ("x86/devicetree: Use CPU description from Device Tree") Signed-off-by: Johan Hovold Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210312092033.26317-1-johan@kernel.org --- arch/x86/kernel/apic/apic.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index bda4f2a36868..4f26700f314d 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2342,6 +2342,11 @@ static int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_apicid[cpu]; +} + #ifdef CONFIG_SMP /** * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread -- cgit v1.2.3