From 124049decbb121ec32742c94fb5d9d6bed8f24d8 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 27 Jun 2018 23:26:13 -0700 Subject: x86/e820: put !E820_TYPE_RAM regions into memblock.reserved There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages within the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch utilizes it to cover all unavailable ranges by putting them into memblock.reserved. Link: http://lkml.kernel.org/r/20180615072947.GB23273@hori1.linux.bs1.fc.nec.co.jp Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Tested-by: Oscar Salvador Tested-by: "Herton R. Krzesinski" Acked-by: Michal Hocko Reviewed-by: Pavel Tatashin Cc: Steven Sistare Cc: Daniel Jordan Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/e820.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d1f25c831447..c88c23c658c1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1248,6 +1248,7 @@ void __init e820__memblock_setup(void) { int i; u64 end; + u64 addr = 0; /* * The bootstrap memblock region count maximum is 128 entries @@ -1264,13 +1265,21 @@ void __init e820__memblock_setup(void) struct e820_entry *entry = &e820_table->entries[i]; end = entry->addr + entry->size; + if (addr < entry->addr) + memblock_reserve(addr, entry->addr - addr); + addr = end; if (end != (resource_size_t)end) continue; + /* + * all !E820_TYPE_RAM ranges (including gap ranges) are put + * into memblock.reserved to make sure that struct pages in + * such regions are not left uninitialized after bootup. + */ if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) - continue; - - memblock_add(entry->addr, entry->size); + memblock_reserve(entry->addr, entry->size); + else + memblock_add(entry->addr, entry->size); } /* Throw away partial pages: */ -- cgit v1.2.3 From 4fb5f58e8d191f7c81637ad81284e4848afb4244 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Mon, 2 Jul 2018 23:49:54 -0700 Subject: x86/mm/32: Initialize the CR4 shadow before __flush_tlb_all() On 32-bit kernels, __flush_tlb_all() may have read the CR4 shadow before the initialization of CR4 shadow in cpu_init(). Fix it by adding an explicit cr4_init_shadow() call into start_secondary() which is the first function called on non-boot SMP CPUs - ahead of the __flush_tlb_all() call. ( This is somewhat of a layering violation, but start_secondary() does CR4 bootstrap in the PCID case anyway. ) Signed-off-by: Zhenzhong Duan Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/b07b6ae9-4b57-4b40-b9bc-50c2c67f1d91@default Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2f7d1d2a5c3..db9656e13ea0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -221,6 +221,11 @@ static void notrace start_secondary(void *unused) #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); + /* + * Initialize the CR4 shadow before doing anything that could + * try to read it. + */ + cr4_init_shadow(); __flush_tlb_all(); #endif load_current_idt(); -- cgit v1.2.3 From 845d382bb15c6e7dc5026c0ff919c5b13fc7e11b Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 2 Jul 2018 16:35:53 -0500 Subject: x86/bugs: Update when to check for the LS_CFG SSBD mitigation If either the X86_FEATURE_AMD_SSBD or X86_FEATURE_VIRT_SSBD features are present, then there is no need to perform the check for the LS_CFG SSBD mitigation support. Signed-off-by: Tom Lendacky Cc: Borislav Petkov Cc: David Woodhouse Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180702213553.29202.21089.stgit@tlendack-t1.amdoffice.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 082d7875cef8..38915fbfae73 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -543,7 +543,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) nodes_per_socket = ((value >> 3) & 7) + 1; } - if (c->x86 >= 0x15 && c->x86 <= 0x17) { + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && + c->x86 >= 0x15 && c->x86 <= 0x17) { unsigned int bit; switch (c->x86) { -- cgit v1.2.3 From 612bc3b3d4be749f73a513a17d9b3ee1330d3487 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 2 Jul 2018 16:36:02 -0500 Subject: x86/bugs: Fix the AMD SSBD usage of the SPEC_CTRL MSR On AMD, the presence of the MSR_SPEC_CTRL feature does not imply that the SSBD mitigation support should use the SPEC_CTRL MSR. Other features could have caused the MSR_SPEC_CTRL feature to be set, while a different SSBD mitigation option is in place. Update the SSBD support to check for the actual SSBD features that will use the SPEC_CTRL MSR. Signed-off-by: Tom Lendacky Cc: Borislav Petkov Cc: David Woodhouse Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 6ac2f49edb1e ("x86/bugs: Add AMD's SPEC_CTRL MSR usage") Link: http://lkml.kernel.org/r/20180702213602.29202.33151.stgit@tlendack-t1.amdoffice.net Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/bugs.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 404df26b7de8..5c0ea39311fe 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -155,7 +155,8 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) hostval |= ssbd_tif_to_spec_ctrl(ti->flags); if (hostval != guestval) { @@ -533,9 +534,10 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may * use a completely different MSR and bit dependent on family. */ - if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !static_cpu_has(X86_FEATURE_AMD_SSBD)) { x86_amd_ssb_disable(); - else { + } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); -- cgit v1.2.3 From d0a8d9378d16eb3c69bd8e6d23779fbdbee3a8c7 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 21 Jun 2018 09:23:24 -0700 Subject: x86/paravirt: Make native_save_fl() extern inline native_save_fl() is marked static inline, but by using it as a function pointer in arch/x86/kernel/paravirt.c, it MUST be outlined. paravirt's use of native_save_fl() also requires that no GPRs other than %rax are clobbered. Compilers have different heuristics which they use to emit stack guard code, the emittance of which can break paravirt's callee saved assumption by clobbering %rcx. Marking a function definition extern inline means that if this version cannot be inlined, then the out-of-line version will be preferred. By having the out-of-line version be implemented in assembly, it cannot be instrumented with a stack protector, which might violate custom calling conventions that code like paravirt rely on. The semantics of extern inline has changed since gnu89. This means that folks using GCC versions >= 5.1 may see symbol redefinition errors at link time for subdirs that override KBUILD_CFLAGS (making the C standard used implicit) regardless of this patch. This has been cleaned up earlier in the patch set, but is left as a note in the commit message for future travelers. Reports: https://lkml.org/lkml/2018/5/7/534 https://github.com/ClangBuiltLinux/linux/issues/16 Discussion: https://bugs.llvm.org/show_bug.cgi?id=37512 https://lkml.org/lkml/2018/5/24/1371 Thanks to the many folks that participated in the discussion. Debugged-by: Alistair Strachan Debugged-by: Matthias Kaehlcke Suggested-by: Arnd Bergmann Suggested-by: H. Peter Anvin Suggested-by: Tom Stellar Reported-by: Sedat Dilek Tested-by: Sedat Dilek Signed-off-by: Nick Desaulniers Acked-by: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@redhat.com Cc: akataria@vmware.com Cc: akpm@linux-foundation.org Cc: andrea.parri@amarulasolutions.com Cc: ard.biesheuvel@linaro.org Cc: aryabinin@virtuozzo.com Cc: astrachan@google.com Cc: boris.ostrovsky@oracle.com Cc: brijesh.singh@amd.com Cc: caoj.fnst@cn.fujitsu.com Cc: geert@linux-m68k.org Cc: ghackmann@google.com Cc: gregkh@linuxfoundation.org Cc: jan.kiszka@siemens.com Cc: jarkko.sakkinen@linux.intel.com Cc: joe@perches.com Cc: jpoimboe@redhat.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: kstewart@linuxfoundation.org Cc: linux-efi@vger.kernel.org Cc: linux-kbuild@vger.kernel.org Cc: manojgupta@google.com Cc: mawilcox@microsoft.com Cc: michal.lkml@markovi.net Cc: mjg59@google.com Cc: mka@chromium.org Cc: pombredanne@nexb.com Cc: rientjes@google.com Cc: rostedt@goodmis.org Cc: thomas.lendacky@amd.com Cc: tweek@google.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: yamada.masahiro@socionext.com Link: http://lkml.kernel.org/r/20180621162324.36656-4-ndesaulniers@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/Makefile | 1 + arch/x86/kernel/irqflags.S | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) create mode 100644 arch/x86/kernel/irqflags.S (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02d6f5cf4e70..8824d01c0c35 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -61,6 +61,7 @@ obj-y += alternative.o i8253.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-y += irqflags.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S new file mode 100644 index 000000000000..ddeeaac8adda --- /dev/null +++ b/arch/x86/kernel/irqflags.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include +#include + +/* + * unsigned long native_save_fl(void) + */ +ENTRY(native_save_fl) + pushf + pop %_ASM_AX + ret +ENDPROC(native_save_fl) +EXPORT_SYMBOL(native_save_fl) + +/* + * void native_restore_fl(unsigned long flags) + * %eax/%rdi: flags + */ +ENTRY(native_restore_fl) + push %_ASM_ARG1 + popf + ret +ENDPROC(native_restore_fl) +EXPORT_SYMBOL(native_restore_fl) -- cgit v1.2.3 From 15279df6f26cf2013d713904b4a0c957ae8abb96 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 6 Jul 2018 23:50:03 +0200 Subject: x86/mtrr: Don't copy out-of-bounds data in mtrr_write Don't access the provided buffer out of bounds - this can cause a kernel out-of-bounds read when invoked through sys_splice() or other things that use kernel_write()/__kernel_write(). Fixes: 7f8ec5a4f01a ("x86/mtrr: Convert to use strncpy_from_user() helper") Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Cc: Andy Shevchenko Cc: "H. Peter Anvin" Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180706215003.156702-1-jannh@google.com --- arch/x86/kernel/cpu/mtrr/if.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4021d3859499..40eee6cc4124 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -106,7 +106,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) memset(line, 0, LINE_SIZE); - length = strncpy_from_user(line, buf, LINE_SIZE - 1); + len = min_t(size_t, len, LINE_SIZE - 1); + length = strncpy_from_user(line, buf, len); if (length < 0) return length; -- cgit v1.2.3