From 5290e88ba2c742ca77c5f5b690e5af549cfd8591 Mon Sep 17 00:00:00 2001 From: Steve Wahl Date: Mon, 7 Aug 2023 09:17:30 -0500 Subject: x86/platform/uv: Use alternate source for socket to node data The UV code attempts to build a set of tables to allow it to do bidirectional socket<=>node lookups. But when nr_cpus is set to a smaller number than actually present, the cpu_to_node() mapping information for unused CPUs is not available to build_socket_tables(). This results in skipping some nodes or sockets when creating the tables and leaving some -1's for later code to trip. over, causing oopses. The problem is that the socket<=>node lookups are created by doing a loop over all CPUs, then looking up the CPU's APICID and socket. But if a CPU is not present, there is no way to start this lookup. Instead of looping over all CPUs, take CPUs out of the equation entirely. Loop over all APICIDs which are mapped to a valid NUMA node. Then just extract the socket-id from the APICID. This avoid tripping over disabled CPUs. Fixes: 8a50c5851927 ("x86/platform/uv: UV support for sub-NUMA clustering") Signed-off-by: Steve Wahl Signed-off-by: Dave Hansen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230807141730.1117278-1-steve.wahl%40hpe.com --- arch/x86/kernel/apic/x2apic_uv_x.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d9f5d7492f83..205cee567629 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1533,7 +1533,7 @@ static void __init build_socket_tables(void) { struct uv_gam_range_entry *gre = uv_gre_table; int nums, numn, nump; - int cpu, i, lnid; + int i, lnid, apicid; int minsock = _min_socket; int maxsock = _max_socket; int minpnode = _min_pnode; @@ -1584,15 +1584,14 @@ static void __init build_socket_tables(void) /* Set socket -> node values: */ lnid = NUMA_NO_NODE; - for_each_possible_cpu(cpu) { - int nid = cpu_to_node(cpu); - int apicid, sockid; + for (apicid = 0; apicid < ARRAY_SIZE(__apicid_to_node); apicid++) { + int nid = __apicid_to_node[apicid]; + int sockid; - if (lnid == nid) + if ((nid == NUMA_NO_NODE) || (lnid == nid)) continue; lnid = nid; - apicid = per_cpu(x86_cpu_to_apicid, cpu); sockid = apicid >> uv_cpuid.socketid_shift; if (_socket_to_node[sockid - minsock] == SOCK_EMPTY) -- cgit v1.2.3 From 25e73b7e3f72a25aa30cbb2eecb49036e0acf066 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Aug 2023 12:55:46 +0200 Subject: x86/ibt: Suppress spurious ENDBR It was reported that under certain circumstances GCC emits ENDBR instructions for _THIS_IP_ usage. Specifically, when it appears at the start of a basic block -- but not elsewhere. Since _THIS_IP_ is never used for control flow, these ENDBR instructions are completely superfluous. Override the _THIS_IP_ definition for x86_64 to avoid this. Less ENDBR instructions is better. Fixes: 156ff4a544ae ("x86/ibt: Base IBT bits") Reported-by: David Kaplan Reviewed-by: Andrew Cooper Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230802110323.016197440@infradead.org --- arch/x86/include/asm/linkage.h | 8 ++++++++ include/linux/instruction_pointer.h | 5 +++++ 2 files changed, 13 insertions(+) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 97a3de7892d3..5ff49fd67732 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -8,6 +8,14 @@ #undef notrace #define notrace __attribute__((no_instrument_function)) +#ifdef CONFIG_64BIT +/* + * The generic version tends to create spurious ENDBR instructions under + * certain conditions. + */ +#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; }) +#endif + #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) #endif /* CONFIG_X86_32 */ diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h index cda1f706eaeb..aa0b3ffea935 100644 --- a/include/linux/instruction_pointer.h +++ b/include/linux/instruction_pointer.h @@ -2,7 +2,12 @@ #ifndef _LINUX_INSTRUCTION_POINTER_H #define _LINUX_INSTRUCTION_POINTER_H +#include + #define _RET_IP_ (unsigned long)__builtin_return_address(0) + +#ifndef _THIS_IP_ #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) +#endif #endif /* _LINUX_INSTRUCTION_POINTER_H */ -- cgit v1.2.3 From 7575e5a35267983dcbeb1e0d3a49d21ae3cf0b82 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Aug 2023 12:55:47 +0200 Subject: x86/ibt: Avoid duplicate ENDBR in __put_user_nocheck*() Commit cb855971d717 ("x86/putuser: Provide room for padding") changed __put_user_nocheck_*() into proper functions but failed to note that SYM_FUNC_START() already provides ENDBR, rendering the explicit ENDBR superfluous. Fixes: cb855971d717 ("x86/putuser: Provide room for padding") Reported-by: David Kaplan Reviewed-by: Andrew Cooper Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230802110323.086971726@infradead.org --- arch/x86/lib/putuser.S | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 1451e0c4ae22..235bbda6fc82 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -56,7 +56,6 @@ SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) SYM_FUNC_START(__put_user_nocheck_1) - ENDBR ASM_STAC 2: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -76,7 +75,6 @@ SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) SYM_FUNC_START(__put_user_nocheck_2) - ENDBR ASM_STAC 4: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -96,7 +94,6 @@ SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) SYM_FUNC_START(__put_user_nocheck_4) - ENDBR ASM_STAC 6: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -119,7 +116,6 @@ SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) SYM_FUNC_START(__put_user_nocheck_8) - ENDBR ASM_STAC 9: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 -- cgit v1.2.3 From f530ee95b72e77b09c141c4b1a4b94d1199ffbd9 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Sep 2023 10:02:21 +0300 Subject: x86/boot/compressed: Reserve more memory for page tables The decompressor has a hard limit on the number of page tables it can allocate. This limit is defined at compile-time and will cause boot failure if it is reached. The kernel is very strict and calculates the limit precisely for the worst-case scenario based on the current configuration. However, it is easy to forget to adjust the limit when a new use-case arises. The worst-case scenario is rarely encountered during sanity checks. In the case of enabling 5-level paging, a use-case was overlooked. The limit needs to be increased by one to accommodate the additional level. This oversight went unnoticed until Aaron attempted to run the kernel via kexec with 5-level paging and unaccepted memory enabled. Update wost-case calculations to include 5-level paging. To address this issue, let's allocate some extra space for page tables. 128K should be sufficient for any use-case. The logic can be simplified by using a single value for all kernel configurations. [ Also add a warning, should this memory run low - by Dave Hansen. ] Fixes: 34bbb0009f3b ("x86/boot/compressed: Enable 5-level paging during decompression stage") Reported-by: Aaron Lu Signed-off-by: Kirill A. Shutemov Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915070221.10266-1-kirill.shutemov@linux.intel.com --- arch/x86/boot/compressed/ident_map_64.c | 8 ++++++ arch/x86/include/asm/boot.h | 45 +++++++++++++++++++++++---------- 2 files changed, 39 insertions(+), 14 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index bcc956c17872..08f93b0401bb 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context) return NULL; } + /* Consumed more tables than expected? */ + if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) { + debug_putstr("pgt_buf running low in " __FILE__ "\n"); + debug_putstr("Need to raise BOOT_PGT_SIZE?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + } + entry = pages->pgt_buf + pages->pgt_buf_offset; pages->pgt_buf_offset += PAGE_SIZE; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4ae14339cb8c..b3a7cfb0d99e 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -40,23 +40,40 @@ #ifdef CONFIG_X86_64 # define BOOT_STACK_SIZE 0x4000 +/* + * Used by decompressor's startup_32() to allocate page tables for identity + * mapping of the 4G of RAM in 4-level paging mode: + * - 1 level4 table; + * - 1 level3 table; + * - 4 level2 table that maps everything with 2M pages; + * + * The additional level5 table needed for 5-level paging is allocated from + * trampoline_32bit memory. + */ # define BOOT_INIT_PGT_SIZE (6*4096) -# ifdef CONFIG_RANDOMIZE_BASE + /* - * Assuming all cross the 512GB boundary: - * 1 page for level4 - * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel - * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP). - * Total is 19 pages. + * Total number of page tables kernel_add_identity_map() can allocate, + * including page tables consumed by startup_32(). + * + * Worst-case scenario: + * - 5-level paging needs 1 level5 table; + * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel, + * assuming all of them cross 256T boundary: + * + 4*2 level4 table; + * + 4*2 level3 table; + * + 4*2 level2 table; + * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM): + * + 1 level4 table; + * + 1 level3 table; + * + 1 level2 table; + * Total: 28 tables + * + * Add 4 spare table in case decompressor touches anything beyond what is + * accounted above. Warn if it happens. */ -# ifdef CONFIG_X86_VERBOSE_BOOTUP -# define BOOT_PGT_SIZE (19*4096) -# else /* !CONFIG_X86_VERBOSE_BOOTUP */ -# define BOOT_PGT_SIZE (17*4096) -# endif -# else /* !CONFIG_RANDOMIZE_BASE */ -# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE -# endif +# define BOOT_PGT_SIZE_WARN (28*4096) +# define BOOT_PGT_SIZE (32*4096) #else /* !CONFIG_X86_64 */ # define BOOT_STACK_SIZE 0x1000 -- cgit v1.2.3 From 75b2f7e4c9e0fd750a5a27ca9736d1daa7a3762a Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Sep 2023 10:01:38 -0700 Subject: x86/purgatory: Remove LTO flags -flto* implies -ffunction-sections. With LTO enabled, ld.lld generates multiple .text sections for purgatory.ro: $ readelf -S purgatory.ro | grep " .text" [ 1] .text PROGBITS 0000000000000000 00000040 [ 7] .text.purgatory PROGBITS 0000000000000000 000020e0 [ 9] .text.warn PROGBITS 0000000000000000 000021c0 [13] .text.sha256_upda PROGBITS 0000000000000000 000022f0 [15] .text.sha224_upda PROGBITS 0000000000000000 00002be0 [17] .text.sha256_fina PROGBITS 0000000000000000 00002bf0 [19] .text.sha224_fina PROGBITS 0000000000000000 00002cc0 This causes WARNING from kexec_purgatory_setup_sechdrs(): WARNING: CPU: 26 PID: 110894 at kernel/kexec_file.c:919 kexec_load_purgatory+0x37f/0x390 Fix this by disabling LTO for purgatory. [ AFAICT, x86 is the only arch that supports LTO and purgatory. ] We could also fix this with an explicit linker script to rejoin .text.* sections back into .text. However, given the benefit of LTOing purgatory is small, simply disable the production of more .text.* sections for now. Fixes: b33fff07e3e3 ("x86, build: allow LTO to be selected") Signed-off-by: Song Liu Signed-off-by: Ingo Molnar Reviewed-by: Nick Desaulniers Reviewed-by: Sami Tolvanen Link: https://lore.kernel.org/r/20230914170138.995606-1-song@kernel.org --- arch/x86/purgatory/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index c2a29be35c01..08aa0f25f12a 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY # optimization flags. KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) +# When LTO is enabled, llvm emits many text sections, which is not supported +# by kexec. Remove -flto=* flags. +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib -- cgit v1.2.3