From owner-freebsd-current@freebsd.org Fri Aug 24 20:32:17 2018 Return-Path: Delivered-To: freebsd-current@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 47ADE10932A3 for ; Fri, 24 Aug 2018 20:32:17 +0000 (UTC) (envelope-from freebsd@grem.de) Received: from mail.grem.de (outcast.grem.de [213.239.217.27]) by mx1.freebsd.org (Postfix) with SMTP id B809275684 for ; Fri, 24 Aug 2018 20:32:16 +0000 (UTC) (envelope-from freebsd@grem.de) Received: (qmail 64687 invoked by uid 89); 24 Aug 2018 20:32:08 -0000 Received: from unknown (HELO ?192.168.250.192?) (mg@grem.de@46.244.231.99) by mail.grem.de with ESMTPA; 24 Aug 2018 20:32:08 -0000 Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (1.0) Subject: Re: Fatal trap 12: page fault on Acer Chromebook 720 (peppy) From: Michael Gmelin X-Mailer: iPhone Mail (15G77) In-Reply-To: <20180824195947.GG2340@kib.kiev.ua> Date: Fri, 24 Aug 2018 22:32:06 +0200 Cc: John Baldwin , "freebsd-current@freebsd.org" , Matthias Apitz Content-Transfer-Encoding: quoted-printable Message-Id: <32F22868-92ED-4223-84B5-77E72C7DCF50@grem.de> References: <8726bc32-6023-bfe1-7600-5b2c706236f8@FreeBSD.org> <20180819165951.274d61b0@bsd64.grem.de> <20180819161642.GP2340@kib.kiev.ua> <20180820004512.5171fa75@bsd64.grem.de> <20180820150904.GS2340@kib.kiev.ua> <57B6DC4C-16EE-4B7B-B691-CB79D8C40289@grem.de> <20180822154603.GW2340@kib.kiev.ua> <20180822211528.GB2340@kib.kiev.ua> <1C7DACDC-36F2-4E65-8C75-7B7215BB6546@grem.de> <20180824195947.GG2340@kib.kiev.ua> To: Konstantin Belousov X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.27 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Aug 2018 20:32:17 -0000 > On 24. Aug 2018, at 21:59, Konstantin Belousov wrote= : >=20 >> On Thu, Aug 23, 2018 at 12:10:34AM +0200, Michael Gmelin wrote: >>=20 >>=20 >>>> On 22. Aug 2018, at 23:15, Konstantin Belousov wr= ote: >>>>=20 >>>> On Wed, Aug 22, 2018 at 10:03:54PM +0200, Michael Gmelin wrote: >>>>=20 >>>>=20 >>>>>> On 22. Aug 2018, at 17:46, Konstantin Belousov w= rote: >>>>>>=20 >>>>>> On Tue, Aug 21, 2018 at 12:14:35AM +0200, Michael Gmelin wrote: >>>>>>=20 >>>>>>=20 >>>>>>>> On 20. Aug 2018, at 17:09, Konstantin Belousov wrote: >>>>>>>>=20 >>>>>>>> On Mon, Aug 20, 2018 at 12:45:12AM +0200, Michael Gmelin wrote: >>>>>>>>=20 >>>>>>>> See here for a screenshot (also including the output of "show pte >>>>>>>> 0xfffff80001000000"): >>>>>>>>=20 >>>>>>>> https://gist.github.com/grembo/78d0f2a100dd4f16775b85a118769658#fil= e-ddb1-png >>>>>>> It is too early for ddb routines to register. >>>>>>> Ok can you try the following debugging patch, to verify my guess ? >>>>>>>=20 >>>>>>> diff --git a/sys/amd64/amd64/pmap.c b/sys/amd64/amd64/pmap.c >>>>>>> index 18777d23f09..cd05fdb763f 100644 >>>>>>> --- a/sys/amd64/amd64/pmap.c >>>>>>> +++ b/sys/amd64/amd64/pmap.c >>>>>>> @@ -1052,8 +1052,7 @@ create_pagetables(vm_paddr_t *firstaddr) >>>>>>> pd_p =3D (pd_entry_t *)DMPDkernphys; >>>>>>> for (i =3D 0; i < (NPDEPG * nkdmpde); i++) >>>>>>> pd_p[i] =3D (i << PDRSHIFT) | X86_PG_V | PG_PS | pg_g | >>>>>>> - X86_PG_M | X86_PG_A | pg_nx | >>>>>>> - bootaddr_rwx(i << PDRSHIFT); >>>>>>> + X86_PG_M | X86_PG_A | pg_nx | X86_PG_RW; >>>>>>> for (i =3D 0; i < nkdmpde; i++) >>>>>>> pdp_p[i] =3D (DMPDkernphys + ptoa(i)) | X86_PG_RW | >>>>>>> X86_PG_V; >>>>>>=20 >>>>>> With this change it boots okay (mptramp_pagetables is 0x1000000, as e= xpected). >>>>>=20 >>>>> Can you apply the following on top of the previous debugging patch and= show >>>>> me the line printed ? >>>>>=20 >>>>> diff --git a/sys/amd64/amd64/pmap.c b/sys/amd64/amd64/pmap.c >>>>> index 3d70532b7fd..613fa9f2165 100644 >>>>> --- a/sys/amd64/amd64/pmap.c >>>>> +++ b/sys/amd64/amd64/pmap.c >>>>> @@ -2662,6 +2662,7 @@ pmap_pinit0(pmap_t pmap) >>>>> pmap->pm_pcids[i].pm_gen =3D 1; >>>>> } >>>>> pmap_activate_boot(pmap); >>>>> +printf("bootaddr addr %#lx rwx %#lx btext %#lx _end %#lx brwsection %= #lx etext %#lx KERNBASE %#lx\n", 0x1000000UL, bootaddr_rwx(0x1000000UL), (ui= ntptr_t)btext, (uintptr_t)_end, (uintptr_t)brwsection, (uintptr_t)etext, (ui= ntptr_t)KERNBASE); >>>>> } >>>>>=20 >>>>> void >>>>=20 >>>> bootaddr addr 0x1000000 rwx 0 btext 0xffffffff80342000 _end 0xffffffff8= 23cf840 brwsection #ffffffff81a00000 etext 0xffffffff812041e4 KERNBASE 0xfff= fffff80000000 >>>>=20 >>>=20 >>> Try this, please. Revert all debugging pmap.c patches that I provided >>> before. >>>=20 >>> diff --git a/sys/amd64/amd64/mp_machdep.c b/sys/amd64/amd64/mp_machdep.c= >>> index 4ca2e07e578..2ee8f862854 100644 >>> --- a/sys/amd64/amd64/mp_machdep.c >>> +++ b/sys/amd64/amd64/mp_machdep.c >>> @@ -87,6 +87,8 @@ __FBSDID("$FreeBSD$"); >>>=20 >>> #define GiB(v) (v ## ULL << 30) >>>=20 >>> +#define AP_BOOTPT_SZ (PAGE_SIZE * 3) >>> + >>> extern struct pcpu __pcpu[]; >>>=20 >>> /* Temporary variables for init_secondary() */ >>> @@ -101,45 +103,78 @@ char *dbg_stack; >>>=20 >>> static int start_ap(int apic_id); >>>=20 >>> +static bool >>> +is_kernel_paddr(vm_paddr_t pa) >>> +{ >>> + >>> + return (pa >=3D trunc_2mpage(btext - KERNBASE) && >>> + pa < round_page(_end - KERNBASE)); >>> +} >>> + >>> +static bool >>> +is_mpboot_good(vm_paddr_t start, vm_paddr_t end) >>> +{ >>> + >>> + return (start + AP_BOOTPT_SZ <=3D GiB(4) && >>> + end >=3D start + AP_BOOTPT_SZ && atop(end) < Maxmem); >>> +} >>> + >>> /* >>> * Calculate usable address in base memory for AP trampoline code. >>> */ >>> void >>> mp_bootaddress(vm_paddr_t *physmap, unsigned int *physmap_idx) >>> { >>> + vm_paddr_t start, end; >>> unsigned int i; >>> bool allocated; >>>=20 >>> alloc_ap_trampoline(physmap, physmap_idx); >>>=20 >>> + /* >>> + * Find a memory region big enough below the 4GB boundary to >>> + * store the initial page tables. Region must be mapped by >>> + * the direct map. >>> + * >>> + * Note that it needs to be aligned to a page boundary. >>> + */ >>> allocated =3D false; >>> for (i =3D *physmap_idx; i <=3D *physmap_idx; i -=3D 2) { >>> /* >>> - * Find a memory region big enough below the 4GB >>> - * boundary to store the initial page tables. Region >>> - * must be mapped by the direct map. >>> - * >>> - * Note that it needs to be aligned to a page >>> - * boundary. >>> + * First, try to chomp at the start of the physmap region. >>> + * Kernel binary might claim it already. >>> + */ >>> + start =3D round_page(physmap[i]); >>> + end =3D trunc_page(physmap[i + 1]); >>> + if (is_mpboot_good(start, end) && >>> + !is_kernel_paddr(start) && !is_kernel_paddr(end - 1)) { >>> + allocated =3D true; >>> + physmap[i] =3D start + AP_BOOTPT_SZ; >>> + break; >>> + } >>> + >>> + /* >>> + * Second, try to chomp at the end. Again, check >>> + * against kernel. >>> */ >>> - if (physmap[i] >=3D GiB(4) || physmap[i + 1] - >>> - round_page(physmap[i]) < PAGE_SIZE * 3 || >>> - atop(physmap[i + 1]) > Maxmem) >>> - continue; >>> - >>> - allocated =3D true; >>> - mptramp_pagetables =3D round_page(physmap[i]); >>> - physmap[i] =3D round_page(physmap[i]) + (PAGE_SIZE * 3); >>> + end =3D trunc_page(physmap[i + 1]); >>> + start =3D end - AP_BOOTPT_SZ; >>> + if (start >=3D physmap[i] && is_mpboot_good(start, end) && >>> + !is_kernel_paddr(start) && !is_kernel_paddr(end - 1)) { >>> + allocated =3D true; >>> + physmap[i + 1] =3D start; >>> + break; >>> + } >>> + } >>> + if (allocated) { >>> + mptramp_pagetables =3D start; >>> if (physmap[i] =3D=3D physmap[i + 1] && *physmap_idx !=3D 0) { >>> memmove(&physmap[i], &physmap[i + 2], >>> sizeof(*physmap) * (*physmap_idx - i + 2)); >>> *physmap_idx -=3D 2; >>> } >>> - break; >>> - } >>> - >>> - if (!allocated) { >>> - mptramp_pagetables =3D trunc_page(boot_address) - (PAGE_SIZE * 3= ); >>> + } else { >>> + mptramp_pagetables =3D trunc_page(boot_address) - AP_BOOTPT_SZ;= >>> if (bootverbose) >>> printf( >>> "Cannot find enough space for the initial AP page tables, placing them a= t %#x", >>=20 >> Reverted back to r337813 and applied the patch. Unfortunately it panics j= ust like before. Adding back physmap debugging like before shows that it???s= still using pages 0x1000-0x1003 (Stopped at native_start_all_aps+0x92: movq= %rax,(%rsi)) >>=20 >=20 > Please apply the following debugging patch on top of the previous 'fix'. > You need debug.late_console=3D0. Unfortunately debug.late_console=3D0 doesn=E2=80=99t work on this machine (n= o more output on the console), I tried that earlier in this thread - hence t= he slightly complicated debugging code I had to add to see the contents of p= hysmap. I could run this code after boot (feeding it an identical physmap) to get de= bug output, would this make sense? Best, Michael >=20 > diff --git a/sys/amd64/amd64/mp_machdep.c b/sys/amd64/amd64/mp_machdep.c > index 2ee8f862854..1a14b1800b1 100644 > --- a/sys/amd64/amd64/mp_machdep.c > +++ b/sys/amd64/amd64/mp_machdep.c > @@ -130,7 +130,7 @@ mp_bootaddress(vm_paddr_t *physmap, unsigned int *phys= map_idx) > bool allocated; >=20 > alloc_ap_trampoline(physmap, physmap_idx); > - > +printf("btext %#lx _end %#lx brwsection %#lx etext %#lx KERNBASE %#lx\n",= (uintptr_t)btext, (uintptr_t)_end, (uintptr_t)brwsection, (uintptr_t)etext,= (uintptr_t)KERNBASE); > /* > * Find a memory region big enough below the 4GB boundary to > * store the initial page tables. Region must be mapped by > @@ -146,10 +146,13 @@ mp_bootaddress(vm_paddr_t *physmap, unsigned int *ph= ysmap_idx) > */ > start =3D round_page(physmap[i]); > end =3D trunc_page(physmap[i + 1]); > +printf("physmap[%d] %#lx physmap[%d] %#lx\n", i, physmap[i], i + 1, physm= ap[i + 1]); > +printf("start %#lx end %#lx is_mpboot_good %d is_kernel_paddr(start) %d i= s_kernel_paddr(end - 1) %d\n", start, end, is_mpboot_good(start, end), is_ke= rnel_paddr(start), is_kernel_paddr(end - 1)); > if (is_mpboot_good(start, end) && > !is_kernel_paddr(start) && !is_kernel_paddr(end - 1)) { > allocated =3D true; > physmap[i] =3D start + AP_BOOTPT_SZ; > +printf("allocated\n"); > break; > } >=20 > @@ -159,10 +162,12 @@ mp_bootaddress(vm_paddr_t *physmap, unsigned int *ph= ysmap_idx) > */ > end =3D trunc_page(physmap[i + 1]); > start =3D end - AP_BOOTPT_SZ; > +printf("start %#lx end %#lx is_mpboot_good %d is_kernel_paddr(start) %d i= s_kernel_paddr(end - 1) %d\n", start, end, is_mpboot_good(start, end), is_ke= rnel_paddr(start), is_kernel_paddr(end - 1)); > if (start >=3D physmap[i] && is_mpboot_good(start, end) && > !is_kernel_paddr(start) && !is_kernel_paddr(end - 1)) { > allocated =3D true; > physmap[i + 1] =3D start; > +printf("allocated\n"); > break; > } > }