50468e4313
== Problem == The amount of SGX memory on a system is determined by the BIOS and it varies wildly between systems. It can be as small as dozens of MB's and as large as many GB's on servers. Just like how applications need to know how much regular RAM is available, enclave builders need to know how much SGX memory an enclave can consume. == Solution == Introduce a new sysfs file: /sys/devices/system/node/nodeX/x86/sgx_total_bytes to enumerate the amount of SGX memory available in each NUMA node. This serves the same function for SGX as /proc/meminfo or /sys/devices/system/node/nodeX/meminfo does for normal RAM. 'sgx_total_bytes' is needed today to help drive the SGX selftests. SGX-specific swap code is exercised by creating overcommitted enclaves which are larger than the physical SGX memory on the system. They currently use a CPUID-based approach which can diverge from the actual amount of SGX memory available. 'sgx_total_bytes' ensures that the selftests can work efficiently and do not attempt stupid things like creating a 100,000 MB enclave on a system with 128 MB of SGX memory. == Implementation Details == Introduce CONFIG_HAVE_ARCH_NODE_DEV_GROUP opt-in flag to expose an arch specific attribute group, and add an attribute for the amount of SGX memory in bytes to each NUMA node: == ABI Design Discussion == As opposed to the per-node ABI, a single, global ABI was considered. However, this would prevent enclaves from being able to size themselves so that they fit on a single NUMA node. Essentially, a single value would rule out NUMA optimizations for enclaves. Create a new "x86/" directory inside each "nodeX/" sysfs directory. 'sgx_total_bytes' is expected to be the first of at least a few sgx-specific files to be placed in the new directory. Just scanning /proc/meminfo, these are the no-brainers that we have for RAM, but we need for SGX: MemTotal: xxxx kB // sgx_total_bytes (implemented here) MemFree: yyyy kB // sgx_free_bytes SwapTotal: zzzz kB // sgx_swapped_bytes So, at *least* three. I think we will eventually end up needing something more along the lines of a dozen. A new directory (as opposed to being in the nodeX/ "root") directory avoids cluttering the root with several "sgx_*" files. Place the new file in a new "nodeX/x86/" directory because SGX is highly x86-specific. It is very unlikely that any other architecture (or even non-Intel x86 vendor) will ever implement SGX. Using "sgx/" as opposed to "x86/" was also considered. But, there is a real chance this can get used for other arch-specific purposes. [ dhansen: rewrite changelog ] Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20211116162116.93081-2-jarkko@kernel.org
104 lines
2.7 KiB
C
104 lines
2.7 KiB
C
/* 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 <asm/sgx.h>
|
|
|
|
#undef pr_fmt
|
|
#define pr_fmt(fmt) "sgx: " fmt
|
|
|
|
#define EREMOVE_ERROR_MESSAGE \
|
|
"EREMOVE returned %d (0x%x) and an EPC page was leaked. SGX may become unusable. " \
|
|
"Refer to Documentation/x86/sgx.rst for more information."
|
|
|
|
#define SGX_MAX_EPC_SECTIONS 8
|
|
#define SGX_EEXTEND_BLOCK_SIZE 256
|
|
#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)
|
|
|
|
/* Pages on free list */
|
|
#define SGX_EPC_PAGE_IS_FREE BIT(1)
|
|
|
|
struct sgx_epc_page {
|
|
unsigned int section;
|
|
u16 flags;
|
|
u16 poison;
|
|
struct sgx_encl_page *owner;
|
|
struct list_head list;
|
|
};
|
|
|
|
/*
|
|
* Contains the tracking data for NUMA nodes having EPC pages. Most importantly,
|
|
* the free page list local to the node is stored here.
|
|
*/
|
|
struct sgx_numa_node {
|
|
struct list_head free_page_list;
|
|
struct list_head sgx_poison_page_list;
|
|
unsigned long size;
|
|
spinlock_t lock;
|
|
};
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
struct sgx_epc_section {
|
|
unsigned long phys_addr;
|
|
void *virt_addr;
|
|
struct sgx_epc_page *pages;
|
|
struct sgx_numa_node *node;
|
|
};
|
|
|
|
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);
|
|
|
|
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);
|
|
|
|
#ifdef CONFIG_X86_SGX_KVM
|
|
int __init sgx_vepc_init(void);
|
|
#else
|
|
static inline int __init sgx_vepc_init(void)
|
|
{
|
|
return -ENODEV;
|
|
}
|
|
#endif
|
|
|
|
void sgx_update_lepubkeyhash(u64 *lepubkeyhash);
|
|
|
|
#endif /* _X86_SGX_H */
|