On 30/12/2023 17:19, Michael Roth wrote:
> From: Brijesh Singh <brijesh.singh@xxxxxxx>
>
> The memory integrity guarantees of SEV-SNP are enforced through a new
> structure called the Reverse Map Table (RMP). The RMP is a single data
> structure shared across the system that contains one entry for every 4K
> page of DRAM that may be used by SEV-SNP VMs. APM2 section 15.36 details
> a number of steps needed to detect/enable SEV-SNP and RMP table support
> on the host:
>
> - Detect SEV-SNP support based on CPUID bit
> - Initialize the RMP table memory reported by the RMP base/end MSR
> registers and configure IOMMU to be compatible with RMP access
> restrictions
> - Set the MtrrFixDramModEn bit in SYSCFG MSR
> - Set the SecureNestedPagingEn and VMPLEn bits in the SYSCFG MSR
> - Configure IOMMU
>
> RMP table entry format is non-architectural and it can vary by
> processor. It is defined by the PPR. Restrict SNP support to CPU
> models/families which are compatible with the current RMP table entry
> format to guard against any undefined behavior when running on other
> system types. Future models/support will handle this through an
> architectural mechanism to allow for broader compatibility.
>
> SNP host code depends on CONFIG_KVM_AMD_SEV config flag, which may be
> enabled even when CONFIG_AMD_MEM_ENCRYPT isn't set, so update the
> SNP-specific IOMMU helpers used here to rely on CONFIG_KVM_AMD_SEV
> instead of CONFIG_AMD_MEM_ENCRYPT.
>
> Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
> Co-developed-by: Ashish Kalra <ashish.kalra@xxxxxxx>
> Signed-off-by: Ashish Kalra <ashish.kalra@xxxxxxx>
> Co-developed-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
> Signed-off-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
> Co-developed-by: Michael Roth <michael.roth@xxxxxxx>
> Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
> ---
> arch/x86/Kbuild | 2 +
> arch/x86/include/asm/msr-index.h | 11 +-
> arch/x86/include/asm/sev.h | 6 +
> arch/x86/kernel/cpu/amd.c | 15 +++
> arch/x86/virt/svm/Makefile | 3 +
> arch/x86/virt/svm/sev.c | 219 +++++++++++++++++++++++++++++++
> 6 files changed, 255 insertions(+), 1 deletion(-)
> create mode 100644 arch/x86/virt/svm/Makefile
> create mode 100644 arch/x86/virt/svm/sev.c
>
> diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
> index 5a83da703e87..6a1f36df6a18 100644
> --- a/arch/x86/Kbuild
> +++ b/arch/x86/Kbuild
> @@ -28,5 +28,7 @@ obj-y += net/
>
> obj-$(CONFIG_KEXEC_FILE) += purgatory/
>
> +obj-y += virt/svm/
> +
> # for cleaning
> subdir- += boot tools
> diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
> index f1bd7b91b3c6..15ce1269f270 100644
> --- a/arch/x86/include/asm/msr-index.h
> +++ b/arch/x86/include/asm/msr-index.h
> @@ -599,6 +599,8 @@
> #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
> #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
> #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
> +#define MSR_AMD64_RMP_BASE 0xc0010132
> +#define MSR_AMD64_RMP_END 0xc0010133
>
> /* SNP feature bits enabled by the hypervisor */
> #define MSR_AMD64_SNP_VTOM BIT_ULL(3)
> @@ -709,7 +711,14 @@
> #define MSR_K8_TOP_MEM2 0xc001001d
> #define MSR_AMD64_SYSCFG 0xc0010010
> #define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
> -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
> +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
> +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24
> +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT)
> +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25
> +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT)
> +#define MSR_AMD64_SYSCFG_MFDM_BIT 19
> +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT)
> +
> #define MSR_K8_INT_PENDING_MSG 0xc0010055
> /* C1E active bits in int pending message */
> #define K8_INTP_C1E_ACTIVE_MASK 0x18000000
> diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
> index 5b4a1ce3d368..1f59d8ba9776 100644
> --- a/arch/x86/include/asm/sev.h
> +++ b/arch/x86/include/asm/sev.h
> @@ -243,4 +243,10 @@ static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
> static inline u64 sev_get_status(void) { return 0; }
> #endif
>
> +#ifdef CONFIG_KVM_AMD_SEV
> +bool snp_probe_rmptable_info(void);
> +#else
> +static inline bool snp_probe_rmptable_info(void) { return false; }
> +#endif
> +
> #endif
> diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
> index 9a17165dfe84..0f0d425f0440 100644
> --- a/arch/x86/kernel/cpu/amd.c
> +++ b/arch/x86/kernel/cpu/amd.c
> @@ -20,6 +20,7 @@
> #include <asm/delay.h>
> #include <asm/debugreg.h>
> #include <asm/resctrl.h>
> +#include <asm/sev.h>
>
> #ifdef CONFIG_X86_64
> # include <asm/mmconfig.h>
> @@ -574,6 +575,20 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
> break;
> }
>
> + if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
> + /*
> + * RMP table entry format is not architectural and it can vary by processor
> + * and is defined by the per-processor PPR. Restrict SNP support on the
> + * known CPU model and family for which the RMP table entry format is
> + * currently defined for.
> + */
> + if (!(c->x86 == 0x19 && c->x86_model <= 0xaf) &&
> + !(c->x86 == 0x1a && c->x86_model <= 0xf))
> + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
> + else if (!snp_probe_rmptable_info())
> + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
Is there a really good reason to perform the snp_probe_smptable_info() check at this
point (instead of in snp_rmptable_init). snp_rmptable_init will also clear the cap
on failure, and bsp_init_amd() runs too early to allow for the kernel to allocate the
rmptable itself. I pointed out in the previous review that kernel allocation of rmptable
is necessary in SNP-host capable VMs in Azure.
> + }
> +
> return;
>
> warn:
> diff --git a/arch/x86/virt/svm/Makefile b/arch/x86/virt/svm/Makefile
> new file mode 100644
> index 000000000000..ef2a31bdcc70
> --- /dev/null
> +++ b/arch/x86/virt/svm/Makefile
> @@ -0,0 +1,3 @@
> +# SPDX-License-Identifier: GPL-2.0
> +
> +obj-$(CONFIG_KVM_AMD_SEV) += sev.o
> diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
> new file mode 100644
> index 000000000000..ce7ede9065ed
> --- /dev/null
> +++ b/arch/x86/virt/svm/sev.c
> @@ -0,0 +1,219 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * AMD SVM-SEV Host Support.
> + *
> + * Copyright (C) 2023 Advanced Micro Devices, Inc.
> + *
> + * Author: Ashish Kalra <ashish.kalra@xxxxxxx>
> + *
> + */
> +
> +#include <linux/cc_platform.h>
> +#include <linux/printk.h>
> +#include <linux/mm_types.h>
> +#include <linux/set_memory.h>
> +#include <linux/memblock.h>
> +#include <linux/kernel.h>
> +#include <linux/mm.h>
> +#include <linux/cpumask.h>
> +#include <linux/iommu.h>
> +#include <linux/amd-iommu.h>
> +
> +#include <asm/sev.h>
> +#include <asm/processor.h>
> +#include <asm/setup.h>
> +#include <asm/svm.h>
> +#include <asm/smp.h>
> +#include <asm/cpu.h>
> +#include <asm/apic.h>
> +#include <asm/cpuid.h>
> +#include <asm/cmdline.h>
> +#include <asm/iommu.h>
> +
> +/*
> + * The RMP entry format is not architectural. The format is defined in PPR
> + * Family 19h Model 01h, Rev B1 processor.
> + */
> +struct rmpentry {
> + u64 assigned : 1,
> + pagesize : 1,
> + immutable : 1,
> + rsvd1 : 9,
> + gpa : 39,
> + asid : 10,
> + vmsa : 1,
> + validated : 1,
> + rsvd2 : 1;
> + u64 rsvd3;
> +} __packed;
> +
> +/*
> + * The first 16KB from the RMP_BASE is used by the processor for the
> + * bookkeeping, the range needs to be added during the RMP entry lookup.
> + */
> +#define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000
> +
> +static u64 probed_rmp_base, probed_rmp_size;
> +static struct rmpentry *rmptable __ro_after_init;
> +static u64 rmptable_max_pfn __ro_after_init;
> +
> +#undef pr_fmt
> +#define pr_fmt(fmt) "SEV-SNP: " fmt
> +
> +static int __mfd_enable(unsigned int cpu)
> +{
> + u64 val;
> +
> + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
> + return 0;
> +
> + rdmsrl(MSR_AMD64_SYSCFG, val);
> +
> + val |= MSR_AMD64_SYSCFG_MFDM;
> +
> + wrmsrl(MSR_AMD64_SYSCFG, val);
> +
> + return 0;
> +}
> +
> +static __init void mfd_enable(void *arg)
> +{
> + __mfd_enable(smp_processor_id());
> +}
> +
> +static int __snp_enable(unsigned int cpu)
> +{
> + u64 val;
> +
> + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
> + return 0;
> +
> + rdmsrl(MSR_AMD64_SYSCFG, val);
> +
> + val |= MSR_AMD64_SYSCFG_SNP_EN;
> + val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN;
> +
> + wrmsrl(MSR_AMD64_SYSCFG, val);
> +
> + return 0;
> +}
> +
> +static __init void snp_enable(void *arg)
> +{
> + __snp_enable(smp_processor_id());
> +}
> +
> +#define RMP_ADDR_MASK GENMASK_ULL(51, 13)
> +
> +bool snp_probe_rmptable_info(void)
> +{
> + u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
> +
> + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
> + rdmsrl(MSR_AMD64_RMP_END, rmp_end);
> +
> + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) {
> + pr_err("Memory for the RMP table has not been reserved by BIOS\n");
> + return false;
> + }
> +
> + if (rmp_base > rmp_end) {
> + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end);
> + return false;
> + }
> +
> + rmp_sz = rmp_end - rmp_base + 1;
> +
> + /*
> + * Calculate the amount the memory that must be reserved by the BIOS to
> + * address the whole RAM, including the bookkeeping area. The RMP itself
> + * must also be covered.
> + */
> + max_rmp_pfn = max_pfn;
> + if (PHYS_PFN(rmp_end) > max_pfn)
> + max_rmp_pfn = PHYS_PFN(rmp_end);
> +
> + calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
> +
> + if (calc_rmp_sz > rmp_sz) {
> + pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
> + calc_rmp_sz, rmp_sz);
> + return false;
> + }
> +
> + probed_rmp_base = rmp_base;
> + probed_rmp_size = rmp_sz;
> +
> + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
> + probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
> +
> + return true;
> +}
> +
> +static int __init __snp_rmptable_init(void)
> +{
> + u64 rmptable_size;
> + void *rmptable_start;
> + u64 val;
> +
> + if (!probed_rmp_size)
> + return 1;
> +
> + rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
> + if (!rmptable_start) {
> + pr_err("Failed to map RMP table\n");
> + return 1;
> + }
> +
> + /*
> + * Check if SEV-SNP is already enabled, this can happen in case of
> + * kexec boot.
> + */
> + rdmsrl(MSR_AMD64_SYSCFG, val);
> + if (val & MSR_AMD64_SYSCFG_SNP_EN)
> + goto skip_enable;
> +
> + memset(rmptable_start, 0, probed_rmp_size);
> +
> + /* Flush the caches to ensure that data is written before SNP is enabled. */
> + wbinvd_on_all_cpus();
> +
> + /* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */
> + on_each_cpu(mfd_enable, NULL, 1);
> +
> + on_each_cpu(snp_enable, NULL, 1);
> +
> +skip_enable:
> + rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ;
> + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ;
> +
> + rmptable = (struct rmpentry *)rmptable_start;
> + rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1;
> +
> + return 0;
> +}
> +
> +static int __init snp_rmptable_init(void)
> +{
> + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
> + return 0;
> +
> + if (!amd_iommu_snp_en)
> + return 0;
Looks better - do you think it'll be OK to add a X86_FEATURE_HYPERVISOR check at this point
later to account for SNP-host capable VMs with no access to an iommu?
Jeremi
> +
> + if (__snp_rmptable_init())
> + goto nosnp;
> +
> + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL);
> +
> + return 0;
> +
> +nosnp:
> + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
> + return -ENOSYS;
> +}
> +
> +/*
> + * This must be called after the IOMMU has been initialized.
> + */
> +device_initcall(snp_rmptable_init);
