search for: initial_gs

....S > @@ -78,6 +78,14 @@ SYM_CODE_START_NOALIGN(startup_64) > call startup_64_setup_env > popq %rsi > > + /* > + * Setup %gs here already to make stack-protector work - it needs to be > + * setup again after the switch to kernel addresses. The address read > + * from initial_gs is a kernel address, so it needs to be adjusted first > + * for the identity mapping. > + */ > + movl $MSR_GS_BASE,%ecx I'm confused: is this missing those three lines: movl initial_gs(%rip),%eax movl initial_gs+4(%rip),%edx wrmsr as it is done in sec...

...eax,%gs + + /* Set up %gs. + * + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. + */ + movl $MSR_GS_BASE,%ecx + movl initial_gs(%rip),%eax + movl initial_gs+4(%rip),%edx + wrmsr + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid @@ -201,32 +227,6 @@ SYM_CODE_START(secondary_startup_64) pushq $0 popfq - /* set up data segments */ - xorl %eax,%eax - movl %eax,%ds - movl %eax,%ss - movl %eax,%es - - /*...

...igned long physbase) asm volatile("movl %%eax, %%ds\n" "movl %%eax, %%ss\n" "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); + + /* Setup GS_BASE - needed for stack protector */ + gsbase = (unsigned long)fixup_pointer((void *)initial_gs, physbase); + __wrmsr(MSR_GS_BASE, (u32)gsbase, (u32)(gsbase >> 32)); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 2b2e91627221..800053219054 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -78,6 +78,14 @@ SYM_CODE_START_NOALIGN(startup...

...igned long physbase) asm volatile("movl %%eax, %%ds\n" "movl %%eax, %%ss\n" "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); + + /* Setup GS_BASE - needed for stack protector */ + gsbase = (unsigned long)fixup_pointer((void *)initial_gs, physbase); + __wrmsr(MSR_GS_BASE, (u32)gsbase, (u32)(gsbase >> 32)); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 2b2e91627221..800053219054 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -78,6 +78,14 @@ SYM_CODE_START_NOALIGN(startup...

...rch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b35030eeec36..96118fb041b8 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -57,6 +57,9 @@ extern unsigned char real_mode_blob_end[]; extern unsigned long initial_code; extern unsigned long initial_gs; extern unsigned long initial_stack; +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern unsigned long initial_vc_handler; +#endif extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 517920928989....

...| 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 057c7bd3eeb6..a5e1939d1dc9 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -200,6 +200,12 @@ SYM_CODE_START(secondary_startup_64) movl initial_gs+4(%rip),%edx wrmsr + /* + * Setup a boot time stack - Any secondary CPU will have lost its stack + * by now because the cr3-switch above unmaps the real-mode stack + */ + movq initial_stack(%rip), %rsp + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid @@ -220,9 +226,6 @@...

...; /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index ce2d8284edb9..b26a7f1bd6fe 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -545,3 +545,14 @@ void __head startup_64_setup_env(unsigned long physbase) gsbase = (unsigned long)fixup_pointer((void *)initial_gs, physbase); __wrmsr(MSR_GS_BASE, (u32)gsbase, (u32)(gsbase >> 32)); } + +void __head early_load_tss(void) +{ + struct desc_struct *gdt = (struct desc_struct *)early_gdt_descr.address; + tss_desc tss; + + /* Load TSS only if entry in GDT is marked present */ + memcpy(&tss, &gdt[GDT_...

From: Joerg Roedel <jroedel at suse.de> Hi, here is the new version of the SEV-ES client enabling patch-set. It is based on the latest tip/master branch and contains the necessary changes. In particular those ar: - Enabling CR4.FSGSBASE early on supported processors so that early #VC exceptions on APs can be handled. - Add another patch (patch 1) to fix a KVM frame-size build

From: Joerg Roedel <jroedel at suse.de> Hi, here is a new version of the SEV-ES Guest Support patches for x86. The previous versions can be found as a linked list starting here: https://lore.kernel.org/lkml/20200824085511.7553-1-joro at 8bytes.org/ I updated the patch-set based on ther review comments I got and the discussions around it. Another important change is that the early IDT

From: Joerg Roedel <jroedel at suse.de> Hi, here is a new version of the SEV-ES Guest Support patches for x86. The previous versions can be found as a linked list starting here: https://lore.kernel.org/lkml/20200824085511.7553-1-joro at 8bytes.org/ I updated the patch-set based on ther review comments I got and the discussions around it. Another important change is that the early IDT

From: Joerg Roedel <jroedel at suse.de> Hi, here is a rebased version of the latest SEV-ES patches. They are now based on latest tip/master instead of upstream Linux and include the necessary changes. Changes to v4 are in particular: - Moved early IDT setup code to idt.c, because the idt_descr and the idt_table are now static - This required to make stack protector work early (or

Hi, here is the first public post of the patch-set to enable Linux to run under SEV-ES enabled hypervisors. The code is mostly feature-complete, but there are still a couple of bugs to fix. Nevertheless, given the size of the patch-set, I think it is about time to ask for initial feedback of the changes that come with it. To better understand the code here is a quick explanation of SEV-ES first.

Hi, here is the first public post of the patch-set to enable Linux to run under SEV-ES enabled hypervisors. The code is mostly feature-complete, but there are still a couple of bugs to fix. Nevertheless, given the size of the patch-set, I think it is about time to ask for initial feedback of the changes that come with it. To better understand the code here is a quick explanation of SEV-ES first.

From: Joerg Roedel <jroedel at suse.de> Hi, here is the fourth version of the SEV-ES Guest Support patches. I addressed the review comments sent to me for the previous version and rebased the code v5.8-rc5. The biggest change in this version is the IST handling code for the #VC handler. I adapted the entry code for the #VC handler to the big pile of entry code changes merged into

From: Joerg Roedel <jroedel at suse.de> Hi, here is the fourth version of the SEV-ES Guest Support patches. I addressed the review comments sent to me for the previous version and rebased the code v5.8-rc5. The biggest change in this version is the IST handling code for the #VC handler. I adapted the entry code for the #VC handler to the big pile of entry code changes merged into

Hi, here is the next version of changes to enable Linux to run as an SEV-ES guest. The code was rebased to v5.7-rc3 and got a fair number of changes since the last version. What is SEV-ES ============== SEV-ES is an acronym for 'Secure Encrypted Virtualization - Encrypted State' and means a hardware feature of AMD processors which hides the register state of VCPUs to the hypervisor by

Hi, here is the next version of changes to enable Linux to run as an SEV-ES guest. The code was rebased to v5.7-rc3 and got a fair number of changes since the last version. What is SEV-ES ============== SEV-ES is an acronym for 'Secure Encrypted Virtualization - Encrypted State' and means a hardware feature of AMD processors which hides the register state of VCPUs to the hypervisor by

Changes: - patch v2: - Adapt patch to work post KPTI and compiler changes - Redo all performance testing with latest configs and compilers - Simplify mov macro on PIE (MOVABS now) - Reduce GOT footprint - patch v1: - Simplify ftrace implementation. - Use gcc mstack-protector-guard-reg=%gs with PIE when possible. - rfc v3: - Use --emit-relocs instead of -pie to reduce

Changes: - patch v2: - Adapt patch to work post KPTI and compiler changes - Redo all performance testing with latest configs and compilers - Simplify mov macro on PIE (MOVABS now) - Reduce GOT footprint - patch v1: - Simplify ftrace implementation. - Use gcc mstack-protector-guard-reg=%gs with PIE when possible. - rfc v3: - Use --emit-relocs instead of -pie to reduce

These patches make the changes necessary to build the kernel as Position Independent Executable (PIE) on x86_64. A PIE kernel can be relocated below the top 2G of the virtual address space. It allows to optionally extend the KASLR randomization range from 1G to 3G. Thanks a lot to Ard Biesheuvel & Kees Cook on their feedback on compiler changes, PIE support and KASLR in general. Thanks to