From 3ccce9340326df40ba4462d4d2a1692b6387a68e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 11 Apr 2022 16:37:03 -0700 Subject: x86/cpu: Add new Alderlake and Raptorlake CPU model numbers Intel is subdividing the mobile segment with additional models with the same codename. Using the Intel "N" and "P" suffices for these will be less confusing than trying to map to some different naming convention. Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/YlS7n7Xtso9BXZA2@agluck-desk3.sc.intel.com --- arch/x86/include/asm/intel-family.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 048b6d5aff50..def6ca121111 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -26,6 +26,7 @@ * _G - parts with extra graphics on * _X - regular server parts * _D - micro server parts + * _N,_P - other mobile parts * * Historical OPTDIFFs: * @@ -107,8 +108,10 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA /* "Small Core" Processors (Atom) */ -- cgit v1.2.3 From f9e14dbbd454581061c736bf70bf5cbb15ac927c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 19 Apr 2022 09:52:41 -0700 Subject: x86/cpu: Load microcode during restore_processor_state() When resuming from system sleep state, restore_processor_state() restores the boot CPU MSRs. These MSRs could be emulated by microcode. If microcode is not loaded yet, writing to emulated MSRs leads to unchecked MSR access error: ... PM: Calling lapic_suspend+0x0/0x210 unchecked MSR access error: WRMSR to 0x10f (tried to write 0x0...0) at rIP: ... (native_write_msr) Call Trace: ? restore_processor_state x86_acpi_suspend_lowlevel acpi_suspend_enter suspend_devices_and_enter pm_suspend.cold state_store kobj_attr_store sysfs_kf_write kernfs_fop_write_iter new_sync_write vfs_write ksys_write __x64_sys_write do_syscall_64 entry_SYSCALL_64_after_hwframe RIP: 0033:0x7fda13c260a7 To ensure microcode emulated MSRs are available for restoration, load the microcode on the boot CPU before restoring these MSRs. [ Pawan: write commit message and productize it. ] Fixes: e2a1256b17b1 ("x86/speculation: Restore speculation related MSRs during S3 resume") Reported-by: Kyle D. Pelton Signed-off-by: Borislav Petkov Signed-off-by: Pawan Gupta Tested-by: Kyle D. Pelton Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=215841 Link: https://lore.kernel.org/r/4350dfbf785cd482d3fafa72b2b49c83102df3ce.1650386317.git.pawan.kumar.gupta@linux.intel.com --- arch/x86/include/asm/microcode.h | 2 ++ arch/x86/kernel/cpu/microcode/core.c | 6 +++--- arch/x86/power/cpu.c | 10 +++++++++- 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d6bfdfb0f0af..0c3d3440fe27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool initrd_gone; +void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } +static inline void microcode_bsp_resume(void) { } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f955d25076ba..239ff5fcec6a 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = { }; /** - * mc_bp_resume - Update boot CPU microcode during resume. + * microcode_bsp_resume - Update boot CPU microcode during resume. */ -static void mc_bp_resume(void) +void microcode_bsp_resume(void) { int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -772,7 +772,7 @@ static void mc_bp_resume(void) } static struct syscore_ops mc_syscore_ops = { - .resume = mc_bp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 3822666fb73d..bb176c72891c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,6 +25,7 @@ #include #include #include +#include #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -262,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); - msr_restore_context(ctxt); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); + + microcode_bsp_resume(); + + /* + * This needs to happen after the microcode has been updated upon resume + * because some of the MSRs are "emulated" in microcode. + */ + msr_restore_context(ctxt); } /* Needed by apm.c */ -- cgit v1.2.3 From 6c8ef58a50b5fab6e364b558143490a2014e2a4f Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Tue, 19 Apr 2022 10:34:16 +0300 Subject: x86/unwind/orc: Recheck address range after stack info was updated A crash was observed in the ORC unwinder: BUG: stack guard page was hit at 000000000dd984a2 (stack is 00000000d1caafca..00000000613712f0) kernel stack overflow (page fault): 0000 [#1] SMP NOPTI CPU: 93 PID: 23787 Comm: context_switch1 Not tainted 5.4.145 #1 RIP: 0010:unwind_next_frame Call Trace: perf_callchain_kernel get_perf_callchain perf_callchain perf_prepare_sample perf_event_output_forward __perf_event_overflow perf_ibs_handle_irq perf_ibs_nmi_handler nmi_handle default_do_nmi do_nmi end_repeat_nmi This was really two bugs: 1) The perf IBS code passed inconsistent regs to the unwinder. 2) The unwinder didn't handle the bad input gracefully. Fix the latter bug. The ORC unwinder needs to be immune against bad inputs. The problem is that stack_access_ok() doesn't recheck the validity of the full range of registers after switching to the next valid stack with get_stack_info(). Fix that. [ jpoimboe: rewrote commit log ] Signed-off-by: Dmitry Monakhov Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/1650353656-956624-1-git-send-email-dmtrmonakhov@yandex-team.ru Signed-off-by: Peter Zijlstra --- arch/x86/kernel/unwind_orc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 794fdef2501a..38185aedf7d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, -- cgit v1.2.3 From 2730d3c14a85617c177337f2e2af2108bf82c4ca Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Apr 2022 11:45:54 +0200 Subject: x86,xen,objtool: Add UNWIND hint SYM_CODE_START*() doesn't get auto-validated and needs an UNWIND hint to get checked, add one. vmlinux.o: warning: objtool: pvh_start_xen()+0x0: unreachable Reported-by: Thomas Gleixner Reported-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220408094718.321246297@infradead.org --- arch/x86/platform/pvh/head.S | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 72c1e42d121d..7fe564eaf228 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,6 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) + UNWIND_HINT_EMPTY cld lgdt (_pa(gdt)) -- cgit v1.2.3 From d66e9d50ea5cd76b2c4875c758efad665283d7ad Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Apr 2022 11:45:56 +0200 Subject: x86,objtool: Explicitly mark idtentry_body()s tail REACHABLE Objtool can figure out that some \cfunc()s are noreturn and then complains about certain instances having unreachable tails: vmlinux.o: warning: objtool: asm_exc_xen_unknown_trap()+0x16: unreachable instruction Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220408094718.441854969@infradead.org --- arch/x86/entry/entry_64.S | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4faac48ebec5..73d958522b6a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -337,6 +337,9 @@ SYM_CODE_END(ret_from_fork) call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp error_return .endm -- cgit v1.2.3 From 613871cd665ab26290c5ff531dd06c3789d31319 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:22 -0700 Subject: x86/static_call: Add ANNOTATE_NOENDBR to static call trampoline The static call trampoline is never indirect-branched to, but is referenced by the static call key. Add ANNOTATE_NOENDBR. Fixes: ed53a0d97192 ("x86/alternative: Use .ibt_endbr_seal to seal indirect calls") Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1b5b54aad7d81241dabe5e0c9b40dea64b540b00.1650300597.git.jpoimboe@redhat.com --- arch/x86/include/asm/static_call.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 2455d721503e..2d8dacd02643 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -26,6 +26,7 @@ ".align 4 \n" \ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR \ insns " \n" \ ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ -- cgit v1.2.3 From 1c0513dec41e4d40eb21402dff397ad84ca13a44 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:23 -0700 Subject: x86/retpoline: Add ANNOTATE_NOENDBR for retpolines The retpolines are exported, so they're referenced by ksymtab sections. But they're never indirect-branched to, so add ANNOTATE_NOENDBR. Fixes: ed53a0d97192 ("x86/alternative: Use .ibt_endbr_seal to seal indirect calls") Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/b6ec963dfd9301b6b1d74ef7758fcb0b540d6c6c.1650300597.git.jpoimboe@redhat.com --- arch/x86/lib/retpoline.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f87bab4fb8d..b2b2366885a2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -31,6 +31,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ @@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) - ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include -- cgit v1.2.3 From 7a00829f8ac3f76b3a3aa5c28ce4ddfd2f977bbe Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:24 -0700 Subject: x86/uaccess: Add ENDBR to __put_user_nocheck*() The __put_user_nocheck*() inner labels are exported, so in keeping with the "allow exported functions to be indirectly called" policy, add ENDBR. Fixes: ed53a0d97192 ("x86/alternative: Use .ibt_endbr_seal to seal indirect calls") Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/207f02177a23031091d1a608de6049a9e5e8ff80.1650300597.git.jpoimboe@redhat.com --- arch/x86/lib/putuser.S | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index ecb2049c1273..b7dfd60243b7 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) + ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) + ENDBR ASM_STAC 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) + ENDBR ASM_STAC 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) + ENDBR ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 -- cgit v1.2.3 From 1ab80a0da4c4a4dd496fc14faabbc8bde61a605c Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:25 -0700 Subject: x86/xen: Add ANNOTATE_NOENDBR to startup_xen() The startup_xen() kernel entry point is referenced by the ".note.Xen" section, and is the real entry point of the VM. Control transfer is through IRET, which *could* set NEED_ENDBR, however Xen currently does no such thing. Add ANNOTATE_NOENDBR to silence future objtool warnings. Fixes: ed53a0d97192 ("x86/alternative: Use .ibt_endbr_seal to seal indirect calls") Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andrew Cooper Link: https://lkml.kernel.org/r/a87bd48b06d11ec4b98122a429e71e489b4e48c3.1650300597.git.jpoimboe@redhat.com --- arch/x86/xen/xen-head.S | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ac17196e2518..3a2cd93bf059 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page) __INIT SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR cld /* Clear .bss */ -- cgit v1.2.3 From 4cdfc11b2836e659c0b7b31152a8b0d976167b59 Mon Sep 17 00:00:00 2001 From: Nur Hussein Date: Mon, 18 Apr 2022 03:24:54 +0800 Subject: x86/Kconfig: fix the spelling of 'becoming' in X86_KERNEL_IBT config There is only one m in becoming. Signed-off-by: Nur Hussein Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220417192454.10247-1-hussein@unixcat.org --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0142e01002e..4bed3abf444d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1866,7 +1866,7 @@ config X86_KERNEL_IBT code with them to make this happen. In addition to building the kernel with IBT, seal all functions that - are not indirect call targets, avoiding them ever becomming one. + are not indirect call targets, avoiding them ever becoming one. This requires LTO like objtool runs and will slow down the build. It does significantly reduce the number of ENDBR instructions in the -- cgit v1.2.3 From 7e0815b3e09986d2fe651199363e135b9358132a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 28 Apr 2022 15:50:54 +0200 Subject: x86/pci/xen: Disable PCI/MSI[-X] masking for XEN_HVM guests When a XEN_HVM guest uses the XEN PIRQ/Eventchannel mechanism, then PCI/MSI[-X] masking is solely controlled by the hypervisor, but contrary to XEN_PV guests this does not disable PCI/MSI[-X] masking in the PCI/MSI layer. This can lead to a situation where the PCI/MSI layer masks an MSI[-X] interrupt and the hypervisor grants the write despite the fact that it already requested the interrupt. As a consequence interrupt delivery on the affected device is not happening ever. Set pci_msi_ignore_mask to prevent that like it's done for XEN_PV guests already. Fixes: 809f9267bbab ("xen: map MSIs into pirqs") Reported-by: Jeremi Piotrowski Reported-by: Dusty Mabe Reported-by: Salvatore Bonaccorso Signed-off-by: Thomas Gleixner Tested-by: Noah Meyerhans Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tuaduxj5.ffs@tglx --- arch/x86/pci/xen.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9bb1e2941179..b94f727251b6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -467,7 +467,6 @@ static __init void xen_setup_pci_msi(void) else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; - pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; @@ -481,6 +480,11 @@ static __init void xen_setup_pci_msi(void) * in allocating the native domain and never use it. */ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; + /* + * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely + * controlled by the hypervisor. + */ + pci_msi_ignore_mask = 1; } #else /* CONFIG_PCI_MSI */ -- cgit v1.2.3