Early sharing needs direct-mapped per-CPU storage. In TDX, a private direct-map alias of a shared page can terminate the guest, including through load_unaligned_zeropad(). Require embed rather than adding early vmalloc conversion and alias synchronization.
Warn when overriding percpu_alloc=page and let embed failures reach the existing panic. Restrict this policy to encrypted guests, leaving host SME allocation unchanged. Suggested-by: Kiryl Shutsemau <[email protected]> Link: https://lore.kernel.org/r/aqvxQoIoYhJTZpAC@thinkstation Signed-off-by: Zack Rusin <[email protected]> --- Documentation/admin-guide/kernel-parameters.txt | 3 +++ arch/x86/kernel/setup_percpu.c | 12 ++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 33cd30996e47..8ba881af3520 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5347,6 +5347,9 @@ Kernel parameters See comments in mm/percpu.c for details on each allocator. This parameter is primarily for debugging and performance comparison. + On x86 encrypted guests, only "embed" is supported; + "page" is ignored with a warning. An embed allocation + failure is fatal instead of falling back to "page". pirq= [SMP,APIC] Manual mp-table setup See Documentation/arch/x86/i386/IO-APIC.rst. diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index bfa48e7a32a2..c83c61e0b20a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -8,6 +8,7 @@ #include <linux/percpu.h> #include <linux/kexec.h> #include <linux/crash_dump.h> +#include <linux/cc_platform.h> #include <linux/smp.h> #include <linux/topology.h> #include <linux/pfn.h> @@ -112,6 +113,7 @@ void __init setup_per_cpu_areas(void) { unsigned int cpu; unsigned long delta; + bool encrypted = cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT); int rc; pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%u\n", @@ -127,6 +129,12 @@ void __init setup_per_cpu_areas(void) if (pcpu_chosen_fc == PCPU_FC_AUTO && pcpu_need_numa()) pcpu_chosen_fc = PCPU_FC_PAGE; #endif + if (encrypted) { + if (pcpu_chosen_fc == PCPU_FC_PAGE) + pr_warn("Ignoring percpu_alloc=page in an encrypted guest\n"); + pcpu_chosen_fc = PCPU_FC_EMBED; + } + rc = -EINVAL; if (pcpu_chosen_fc != PCPU_FC_PAGE) { const size_t dyn_size = PERCPU_MODULE_RESERVE + @@ -149,11 +157,11 @@ void __init setup_per_cpu_areas(void) dyn_size, atom_size, pcpu_cpu_distance, pcpu_cpu_to_node); - if (rc < 0) + if (rc < 0 && !encrypted) pr_warn("%s allocator failed (%d), falling back to page size\n", pcpu_fc_names[pcpu_chosen_fc], rc); } - if (rc < 0) + if (rc < 0 && !encrypted) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, pcpu_cpu_to_node); if (rc < 0) -- 2.53.0
