linux/arch/x86/kernel/cpu/sgx/sgx.h

87 lines
2.3 KiB
C
Raw Normal View History

x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _X86_SGX_H
#define _X86_SGX_H
#include <linux/bitops.h>
#include <linux/err.h>
#include <linux/io.h>
#include <linux/rwsem.h>
#include <linux/types.h>
#include <asm/asm.h>
#include "arch.h"
#undef pr_fmt
#define pr_fmt(fmt) "sgx: " fmt
#define SGX_MAX_EPC_SECTIONS 8
#define SGX_EEXTEND_BLOCK_SIZE 256
x86/sgx: Add a page reclaimer Just like normal RAM, there is a limited amount of enclave memory available and overcommitting it is a very valuable tool to reduce resource use. Introduce a simple reclaim mechanism for enclave pages. In contrast to normal page reclaim, the kernel cannot directly access enclave memory. To get around this, the SGX architecture provides a set of functions to help. Among other things, these functions copy enclave memory to and from normal memory, encrypting it and protecting its integrity in the process. Implement a page reclaimer by using these functions. Picks victim pages in LRU fashion from all the enclaves running in the system. A new kernel thread (ksgxswapd) reclaims pages in the background based on watermarks, similar to normal kswapd. All enclave pages can be reclaimed, architecturally. But, there are some limits to this, such as the special SECS metadata page which must be reclaimed last. The page version array (used to mitigate replaying old reclaimed pages) is also architecturally reclaimable, but not yet implemented. The end result is that the vast majority of enclave pages are currently reclaimable. Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org
2020-11-12 22:01:32 +00:00
#define SGX_NR_TO_SCAN 16
#define SGX_NR_LOW_PAGES 32
#define SGX_NR_HIGH_PAGES 64
/* Pages, which are being tracked by the page reclaimer. */
#define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0)
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
struct sgx_epc_page {
unsigned int section;
x86/sgx: Add a page reclaimer Just like normal RAM, there is a limited amount of enclave memory available and overcommitting it is a very valuable tool to reduce resource use. Introduce a simple reclaim mechanism for enclave pages. In contrast to normal page reclaim, the kernel cannot directly access enclave memory. To get around this, the SGX architecture provides a set of functions to help. Among other things, these functions copy enclave memory to and from normal memory, encrypting it and protecting its integrity in the process. Implement a page reclaimer by using these functions. Picks victim pages in LRU fashion from all the enclaves running in the system. A new kernel thread (ksgxswapd) reclaims pages in the background based on watermarks, similar to normal kswapd. All enclave pages can be reclaimed, architecturally. But, there are some limits to this, such as the special SECS metadata page which must be reclaimed last. The page version array (used to mitigate replaying old reclaimed pages) is also architecturally reclaimable, but not yet implemented. The end result is that the vast majority of enclave pages are currently reclaimable. Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org
2020-11-12 22:01:32 +00:00
unsigned int flags;
struct sgx_encl_page *owner;
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
struct list_head list;
};
/*
* The firmware can define multiple chunks of EPC to the different areas of the
* physical memory e.g. for memory areas of the each node. This structure is
* used to store EPC pages for one EPC section and virtual memory area where
* the pages have been mapped.
x86/sgx: Clarify 'laundry_list' locking Short Version: The SGX section->laundry_list structure is effectively thread-local, but declared next to some shared structures. Its semantics are clear as mud. Fix that. No functional changes. Compile tested only. Long Version: The SGX hardware keeps per-page metadata. This can provide things like permissions, integrity and replay protection. It also prevents things like having an enclave page mapped multiple times or shared between enclaves. But, that presents a problem for kexec()'d kernels (or any other kernel that does not run immediately after a hardware reset). This is because the last kernel may have been rude and forgotten to reset pages, which would trigger the "shared page" sanity check. To fix this, the SGX code "launders" the pages by running the EREMOVE instruction on all pages at boot. This is slow and can take a long time, so it is performed off in the SGX-specific ksgxd instead of being synchronous at boot. The init code hands the list of pages to launder in a per-SGX-section list: ->laundry_list. The only code to touch this list is the init code and ksgxd. This means that no locking is necessary for ->laundry_list. However, a lock is required for section->page_list, which is accessed while creating enclaves and by ksgxd. This lock (section->lock) is acquired by ksgxd while also processing ->laundry_list. It is easy to confuse the purpose of the locking as being for ->laundry_list and ->page_list. Rename ->laundry_list to ->init_laundry_list to make it clear that this is not normally used at runtime. Also add some comments clarifying the locking, and reorganize 'sgx_epc_section' to put 'lock' near the things it protects. Note: init_laundry_list is 128 bytes of wasted space at runtime. It could theoretically be dynamically allocated and then freed after the laundering process. But it would take nearly 128 bytes of extra instructions to do that. Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20201116222531.4834-1-dave.hansen@intel.com
2020-11-16 22:25:31 +00:00
*
* 'lock' must be held before accessing 'page_list' or 'free_cnt'.
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
*/
struct sgx_epc_section {
unsigned long phys_addr;
void *virt_addr;
struct sgx_epc_page *pages;
x86/sgx: Clarify 'laundry_list' locking Short Version: The SGX section->laundry_list structure is effectively thread-local, but declared next to some shared structures. Its semantics are clear as mud. Fix that. No functional changes. Compile tested only. Long Version: The SGX hardware keeps per-page metadata. This can provide things like permissions, integrity and replay protection. It also prevents things like having an enclave page mapped multiple times or shared between enclaves. But, that presents a problem for kexec()'d kernels (or any other kernel that does not run immediately after a hardware reset). This is because the last kernel may have been rude and forgotten to reset pages, which would trigger the "shared page" sanity check. To fix this, the SGX code "launders" the pages by running the EREMOVE instruction on all pages at boot. This is slow and can take a long time, so it is performed off in the SGX-specific ksgxd instead of being synchronous at boot. The init code hands the list of pages to launder in a per-SGX-section list: ->laundry_list. The only code to touch this list is the init code and ksgxd. This means that no locking is necessary for ->laundry_list. However, a lock is required for section->page_list, which is accessed while creating enclaves and by ksgxd. This lock (section->lock) is acquired by ksgxd while also processing ->laundry_list. It is easy to confuse the purpose of the locking as being for ->laundry_list and ->page_list. Rename ->laundry_list to ->init_laundry_list to make it clear that this is not normally used at runtime. Also add some comments clarifying the locking, and reorganize 'sgx_epc_section' to put 'lock' near the things it protects. Note: init_laundry_list is 128 bytes of wasted space at runtime. It could theoretically be dynamically allocated and then freed after the laundering process. But it would take nearly 128 bytes of extra instructions to do that. Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20201116222531.4834-1-dave.hansen@intel.com
2020-11-16 22:25:31 +00:00
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
spinlock_t lock;
x86/sgx: Clarify 'laundry_list' locking Short Version: The SGX section->laundry_list structure is effectively thread-local, but declared next to some shared structures. Its semantics are clear as mud. Fix that. No functional changes. Compile tested only. Long Version: The SGX hardware keeps per-page metadata. This can provide things like permissions, integrity and replay protection. It also prevents things like having an enclave page mapped multiple times or shared between enclaves. But, that presents a problem for kexec()'d kernels (or any other kernel that does not run immediately after a hardware reset). This is because the last kernel may have been rude and forgotten to reset pages, which would trigger the "shared page" sanity check. To fix this, the SGX code "launders" the pages by running the EREMOVE instruction on all pages at boot. This is slow and can take a long time, so it is performed off in the SGX-specific ksgxd instead of being synchronous at boot. The init code hands the list of pages to launder in a per-SGX-section list: ->laundry_list. The only code to touch this list is the init code and ksgxd. This means that no locking is necessary for ->laundry_list. However, a lock is required for section->page_list, which is accessed while creating enclaves and by ksgxd. This lock (section->lock) is acquired by ksgxd while also processing ->laundry_list. It is easy to confuse the purpose of the locking as being for ->laundry_list and ->page_list. Rename ->laundry_list to ->init_laundry_list to make it clear that this is not normally used at runtime. Also add some comments clarifying the locking, and reorganize 'sgx_epc_section' to put 'lock' near the things it protects. Note: init_laundry_list is 128 bytes of wasted space at runtime. It could theoretically be dynamically allocated and then freed after the laundering process. But it would take nearly 128 bytes of extra instructions to do that. Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20201116222531.4834-1-dave.hansen@intel.com
2020-11-16 22:25:31 +00:00
struct list_head page_list;
unsigned long free_cnt;
/*
* Pages which need EREMOVE run on them before they can be
* used. Only safe to be accessed in ksgxd and init code.
* Not protected by locks.
*/
struct list_head init_laundry_list;
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
};
extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
static inline unsigned long sgx_get_epc_phys_addr(struct sgx_epc_page *page)
{
struct sgx_epc_section *section = &sgx_epc_sections[page->section];
unsigned long index;
index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page);
return section->phys_addr + index * PAGE_SIZE;
}
static inline void *sgx_get_epc_virt_addr(struct sgx_epc_page *page)
{
struct sgx_epc_section *section = &sgx_epc_sections[page->section];
unsigned long index;
index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page);
return section->virt_addr + index * PAGE_SIZE;
}
struct sgx_epc_page *__sgx_alloc_epc_page(void);
void sgx_free_epc_page(struct sgx_epc_page *page);
x86/sgx: Add a page reclaimer Just like normal RAM, there is a limited amount of enclave memory available and overcommitting it is a very valuable tool to reduce resource use. Introduce a simple reclaim mechanism for enclave pages. In contrast to normal page reclaim, the kernel cannot directly access enclave memory. To get around this, the SGX architecture provides a set of functions to help. Among other things, these functions copy enclave memory to and from normal memory, encrypting it and protecting its integrity in the process. Implement a page reclaimer by using these functions. Picks victim pages in LRU fashion from all the enclaves running in the system. A new kernel thread (ksgxswapd) reclaims pages in the background based on watermarks, similar to normal kswapd. All enclave pages can be reclaimed, architecturally. But, there are some limits to this, such as the special SECS metadata page which must be reclaimed last. The page version array (used to mitigate replaying old reclaimed pages) is also architecturally reclaimable, but not yet implemented. The end result is that the vast majority of enclave pages are currently reclaimable. Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org
2020-11-12 22:01:32 +00:00
void sgx_mark_page_reclaimable(struct sgx_epc_page *page);
int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave. Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’. Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs. Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Co-developed-by: Serge Ayoun <serge.ayoun@intel.com> Signed-off-by: Serge Ayoun <serge.ayoun@intel.com> Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org
2020-11-12 22:01:16 +00:00
#endif /* _X86_SGX_H */