From c739f930be1dd5fd949030e3475a884fe06dae9b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 12 Dec 2017 07:56:36 -0800 Subject: x86/espfix/64: Fix espfix double-fault handling on 5-level systems Using PGDIR_SHIFT to identify espfix64 addresses on 5-level systems was wrong, and it resulted in panics due to unhandled double faults. Use P4D_SHIFT instead, which is correct on 4-level and 5-level machines. This fixes a panic when running x86 selftests on 5-level machines. Signed-off-by: Andy Lutomirski Acked-by: Kirill A. Shutemov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: David Laight Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: 1d33b219563f ("x86/espfix: Add support for 5-level paging") Link: http://lkml.kernel.org/r/24c898b4f44fdf8c22d93703850fb384ef87cfdc.1513035461.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b7b0f74a2150..c751518936ac 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -355,7 +355,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * * No need for ist_enter here because we don't use RCU. */ - if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY && regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { -- cgit v1.2.3 From 5f0e3fe6b1504d4e6530294ec87c473aa6d2d02f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 09:10:11 -0500 Subject: x86/build: Make isoimage work on Debian Debian does not ship a 'mkisofs' symlink to genisoimage. All modern distros ship genisoimage, so just use that directly. That requires renaming the 'genisoimage' function. Also neaten up the 'for' loop while I'm in here. Signed-off-by: Matthew Wilcox Cc: Changbin Du Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/boot/genimage.sh | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index c9e8499fbfe7..6a10d52a4145 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -80,39 +80,43 @@ genfdimage288() { mcopy $FBZIMAGE w:linux } -genisoimage() { +geniso() { tmp_dir=`dirname $FIMAGE`/isoimage rm -rf $tmp_dir mkdir $tmp_dir - for i in lib lib64 share end ; do + for i in lib lib64 share ; do for j in syslinux ISOLINUX ; do if [ -f /usr/$i/$j/isolinux.bin ] ; then isolinux=/usr/$i/$j/isolinux.bin - cp $isolinux $tmp_dir fi done for j in syslinux syslinux/modules/bios ; do if [ -f /usr/$i/$j/ldlinux.c32 ]; then ldlinux=/usr/$i/$j/ldlinux.c32 - cp $ldlinux $tmp_dir fi done if [ -n "$isolinux" -a -n "$ldlinux" ] ; then break fi - if [ $i = end -a -z "$isolinux" ] ; then - echo 'Need an isolinux.bin file, please install syslinux/isolinux.' - exit 1 - fi done + if [ -z "$isolinux" ] ; then + echo 'Need an isolinux.bin file, please install syslinux/isolinux.' + exit 1 + fi + if [ -z "$ldlinux" ] ; then + echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.' + exit 1 + fi + cp $isolinux $tmp_dir + cp $ldlinux $tmp_dir cp $FBZIMAGE $tmp_dir/linux echo "$KCMDLINE" > $tmp_dir/isolinux.cfg if [ -f "$FDINITRD" ] ; then cp "$FDINITRD" $tmp_dir/initrd.img fi - mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \ - -c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \ - $tmp_dir + genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \ + -b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \ + -boot-info-table $tmp_dir isohybrid $FIMAGE 2>/dev/null || true rm -rf $tmp_dir } @@ -121,6 +125,6 @@ case $1 in bzdisk) genbzdisk;; fdimage144) genfdimage144;; fdimage288) genfdimage288;; - isoimage) genisoimage;; + isoimage) geniso;; *) echo 'Unknown image format'; exit 1; esac -- cgit v1.2.3 From 9d5f38ba6c82359b7cec31fb27fb78ecc02f3946 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 15 Dec 2017 10:20:12 -0600 Subject: x86/mm: Unbreak modules that use the DMA API Commit d8aa7eea78a1 ("x86/mm: Add Secure Encrypted Virtualization (SEV) support") changed sme_active() from an inline function that referenced sme_me_mask to a non-inlined function in order to make the sev_enabled variable a static variable. This function was marked EXPORT_SYMBOL_GPL because at the time the patch was submitted, sme_me_mask was marked EXPORT_SYMBOL_GPL. Commit 87df26175e67 ("x86/mm: Unbreak modules that rely on external PAGE_KERNEL availability") changed sme_me_mask variable from EXPORT_SYMBOL_GPL to EXPORT_SYMBOL, allowing external modules the ability to build with CONFIG_AMD_MEM_ENCRYPT=y. Now, however, with sev_active() no longer an inline function and marked as EXPORT_SYMBOL_GPL, external modules that use the DMA API are once again broken in 4.15. Since the DMA API is meant to be used by external modules, this needs to be changed. Change the sme_active() and sev_active() functions from EXPORT_SYMBOL_GPL to EXPORT_SYMBOL. Signed-off-by: Tom Lendacky Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: Brijesh Singh Link: https://lkml.kernel.org/r/20171215162011.14125.7113.stgit@tlendack-t1.amdoffice.net --- arch/x86/mm/mem_encrypt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index d9a9e9fc75dd..391b13402e40 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -405,13 +405,13 @@ bool sme_active(void) { return sme_me_mask && !sev_enabled; } -EXPORT_SYMBOL_GPL(sme_active); +EXPORT_SYMBOL(sme_active); bool sev_active(void) { return sme_me_mask && sev_enabled; } -EXPORT_SYMBOL_GPL(sev_active); +EXPORT_SYMBOL(sev_active); static const struct dma_map_ops sev_dma_ops = { .alloc = sev_alloc, -- cgit v1.2.3 From 6454b3bdd138dfc640deb5e7b9a0668fca2d55dd Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Dec 2017 15:13:44 -0600 Subject: x86/stacktrace: Make zombie stack traces reliable Commit: 1959a60182f4 ("x86/dumpstack: Pin the target stack when dumping it") changed the behavior of stack traces for zombies. Before that commit, /proc//stack reported the last execution path of the zombie before it died: [] do_exit+0x6f7/0xa80 [] do_group_exit+0x39/0xa0 [] __wake_up_parent+0x0/0x30 [] system_call_fastpath+0x16/0x1b [<00007fd128f9c4f9>] 0x7fd128f9c4f9 [] 0xffffffffffffffff After the commit, it just reports an empty stack trace. The new behavior is actually probably more correct. If the stack refcount has gone down to zero, then the task has already gone through do_exit() and isn't going to run anymore. The stack could be freed at any time and is basically gone, so reporting an empty stack makes sense. However, save_stack_trace_tsk_reliable() treats such a missing stack condition as an error. That can cause livepatch transition stalls if there are any unreaped zombies. Instead, just treat it as a reliable, empty stack. Reported-and-tested-by: Miroslav Benes Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Fixes: af085d9084b4 ("stacktrace/x86: add function for detecting reliable stack traces") Link: http://lkml.kernel.org/r/e4b09e630e99d0c1080528f0821fc9d9dbaeea82.1513631620.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/stacktrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 77835bc021c7..20161ef53537 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -164,8 +164,12 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk, { int ret; + /* + * If the task doesn't have a stack (e.g., a zombie), the stack is + * "reliably" empty. + */ if (!try_get_task_stack(tsk)) - return -EINVAL; + return 0; ret = __save_stack_trace_reliable(trace, tsk); -- cgit v1.2.3 From 7ac139eaa6bbdb07c547b6916a808eab3897e0e3 Mon Sep 17 00:00:00 2001 From: rodrigosiqueira Date: Fri, 15 Dec 2017 11:15:33 -0200 Subject: x86: Remove unused parameter of prepare_switch_to Commit e37e43a497d5 ("x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y)") added prepare_switch_to with one extra parameter which is not used by the function, remove it. Signed-off-by: Rodrigo Siqueira Signed-off-by: Thomas Gleixner Cc: kernel-janitors@vger.kernel.org Link: https://lkml.kernel.org/r/20171215131533.hp6kqebw45o7uvsb@smtp.gmail.com --- arch/x86/include/asm/switch_to.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8c6bd6863db9..1008d4622709 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); /* This runs runs on the previous thread's stack. */ -static inline void prepare_switch_to(struct task_struct *prev, - struct task_struct *next) +static inline void prepare_switch_to(struct task_struct *next) { #ifdef CONFIG_VMAP_STACK /* @@ -70,7 +69,7 @@ struct fork_frame { #define switch_to(prev, next, last) \ do { \ - prepare_switch_to(prev, next); \ + prepare_switch_to(next); \ \ ((last) = __switch_to_asm((prev), (next))); \ } while (0) -- cgit v1.2.3 From ac461122c88a10b7d775de2f56467f097c9e627a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 27 Dec 2017 11:48:50 -0800 Subject: x86-32: Fix kexec with stack canary (CONFIG_CC_STACKPROTECTOR) Commit e802a51ede91 ("x86/idt: Consolidate IDT invalidation") cleaned up and unified the IDT invalidation that existed in a couple of places. It changed no actual real code. Despite not changing any actual real code, it _did_ change code generation: by implementing the common idt_invalidate() function in archx86/kernel/idt.c, it made the use of the function in arch/x86/kernel/machine_kexec_32.c be a real function call rather than an (accidental) inlining of the function. That, in turn, exposed two issues: - in load_segments(), we had incorrectly reset all the segment registers, which then made the stack canary load (which gcc does using offset of %gs) cause a trap. Instead of %gs pointing to the stack canary, it will be the normal zero-based kernel segment, and the stack canary load will take a page fault at address 0x14. - to make this even harder to debug, we had invalidated the GDT just before calling idt_invalidate(), which meant that the fault happened with an invalid GDT, which in turn causes a triple fault and immediate reboot. Fix this by (a) not reloading the special segments in load_segments(). We currently don't do any percpu accesses (which would require %fs on x86-32) in this area, but there's no reason to think that we might not want to do them, and like %gs, it's pointless to break it. (b) doing idt_invalidate() before invalidating the GDT, to keep things at least _slightly_ more debuggable for a bit longer. Without a IDT, traps will not work. Without a GDT, traps also will not work, but neither will any segment loads etc. So in a very real sense, the GDT is even more core than the IDT. Fixes: e802a51ede91 ("x86/idt: Consolidate IDT invalidation") Reported-and-tested-by: Alexandru Chirvasitu Signed-off-by: Linus Torvalds Signed-off-by: Thomas Gleixner Cc: Denys Vlasenko Cc: Peter Zijlstra Cc: Brian Gerst Cc: Steven Rostedt Cc: Borislav Petkov Cc: Andy Lutomirski Cc: Josh Poimboeuf Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.LFD.2.21.1712271143180.8572@i7.lan --- arch/x86/kernel/machine_kexec_32.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 00bc751c861c..edfede768688 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -48,8 +48,6 @@ static void load_segments(void) "\tmovl $"STR(__KERNEL_DS)",%%eax\n" "\tmovl %%eax,%%ds\n" "\tmovl %%eax,%%es\n" - "\tmovl %%eax,%%fs\n" - "\tmovl %%eax,%%gs\n" "\tmovl %%eax,%%ss\n" : : : "eax", "memory"); #undef STR @@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image) * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0), 0); idt_invalidate(phys_to_virt(0)); + set_gdt(phys_to_virt(0), 0); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, -- cgit v1.2.3 From 4fcab6693445cfb84f2b65868c58043535090e52 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Mon, 4 Dec 2017 12:03:12 +0800 Subject: x86/apic: Avoid wrong warning when parsing 'apic=' in X86-32 case There are two consumers of apic=: apic_set_verbosity() for setting the APIC debug level; parse_apic() for registering APIC driver by hand. X86-32 supports both of them, but sometimes, kernel issues a weird warning. eg: when kernel was booted up with 'apic=bigsmp' in command line, early_param would warn like that: ... [ 0.000000] APIC Verbosity level bigsmp not recognised use apic=verbose or apic=debug [ 0.000000] Malformed early option 'apic' ... Wrap the warning code in CONFIG_X86_64 case to avoid this. Signed-off-by: Dou Liyang Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: rdunlap@infradead.org Cc: corbet@lwn.net Link: https://lkml.kernel.org/r/20171204040313.24824-1-douly.fnst@cn.fujitsu.com --- arch/x86/kernel/apic/apic.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6e272f3ea984..880441f24146 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2626,11 +2626,13 @@ static int __init apic_set_verbosity(char *arg) apic_verbosity = APIC_DEBUG; else if (strcmp("verbose", arg) == 0) apic_verbosity = APIC_VERBOSE; +#ifdef CONFIG_X86_64 else { pr_warning("APIC Verbosity level %s not recognised" " use apic=verbose or apic=debug\n", arg); return -EINVAL; } +#endif return 0; } -- cgit v1.2.3 From a31e58e129f73ab5b04016330b13ed51fde7a961 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 28 Dec 2017 11:33:33 +0100 Subject: x86/apic: Switch all APICs to Fixed delivery mode Some of the APIC incarnations are operating in lowest priority delivery mode. This worked as long as the vector management code allocated the same vector on all possible CPUs for each interrupt. Lowest priority delivery mode does not necessarily respect the affinity setting and may redirect to some other online CPU. This was documented somewhere in the old code and the conversion to single target delivery missed to update the delivery mode of the affected APIC drivers which results in spurious interrupts on some of the affected CPU/Chipset combinations. Switch the APIC drivers over to Fixed delivery mode and remove all leftovers of lowest priority delivery mode. Switching to Fixed delivery mode is not a problem on these CPUs because the kernel already uses Fixed delivery mode for IPIs. The reason for this is that th SDM explicitely forbids lowest prio mode for IPIs. The reason is obvious: If the irq routing does not honor destination targets in lowest prio mode then an IPI targeted at CPU1 might end up on CPU0, which would be a fatal problem in many cases. As a consequence of this change, the apic::irq_delivery_mode field is now pointless, but this needs to be cleaned up in a separate patch. Fixes: fdba46ffb4c2 ("x86/apic: Get rid of multi CPU affinity") Reported-by: vcaputo@pengaru.com Signed-off-by: Thomas Gleixner Tested-by: vcaputo@pengaru.com Cc: Pavel Machek Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712281140440.1688@nanos --- arch/x86/kernel/apic/apic_flat_64.c | 2 +- arch/x86/kernel/apic/apic_noop.c | 2 +- arch/x86/kernel/apic/msi.c | 8 ++------ arch/x86/kernel/apic/probe_32.c | 2 +- arch/x86/kernel/apic/x2apic_cluster.c | 2 +- 5 files changed, 6 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index aa85690e9b64..25a87028cb3f 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -151,7 +151,7 @@ static struct apic apic_flat __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 1, /* logical */ .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 7b659c4480c9..5078b5ce63a7 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = noop_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 9b18be764422..ce503c99f5c4 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) ((apic->irq_dest_mode == 0) ? MSI_ADDR_DEST_MODE_PHYSICAL : MSI_ADDR_DEST_MODE_LOGICAL) | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - MSI_ADDR_REDIRECTION_CPU : - MSI_ADDR_REDIRECTION_LOWPRI) | + MSI_ADDR_REDIRECTION_CPU | MSI_ADDR_DEST_ID(cfg->dest_apicid); msg->data = MSI_DATA_TRIGGER_EDGE | MSI_DATA_LEVEL_ASSERT | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - MSI_DATA_DELIVERY_FIXED : - MSI_DATA_DELIVERY_LOWPRI) | + MSI_DATA_DELIVERY_FIXED | MSI_DATA_VECTOR(cfg->vector); } diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index fa22017de806..02e8acb134f8 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = default_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 622f13ca8a94..8b04234e010b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 1, /* logical */ .disable_esr = 0, -- cgit v1.2.3