April 2022 - Linux-kselftest-mirror

[PATCH AUTOSEL 5.15 15/15] selftest/vm: verify remap destination address in mremap_test

by Sasha Levin

From: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> [ Upstream commit 18d609daa546c919fd36b62a7b510c18de4b4af8 ] Because mremap does not have a MAP_FIXED_NOREPLACE flag, it can destroy existing mappings. This causes a segfault when regions such as text are remapped and the permissions are changed. Verify the requested mremap destination address does not overlap any existing mappings by using mmap's MAP_FIXED_NOREPLACE flag. Keep incrementing the destination address until a valid mapping is found or fail the current test once the max address is reached. Link: https://lkml.kernel.org/r/20220420215721.4868-2-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/vm/mremap_test.c | 42 ++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 2b3b4f15185f..e3ce33a9954e 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -10,6 +10,7 @@ #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -65,6 +66,30 @@ enum { .expect_failure = should_fail \ } +/* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + /* Returns mmap_min_addr sysctl tunable from procfs */ static unsigned long long get_mmap_min_addr(void) { @@ -112,8 +137,8 @@ static void *get_source_mapping(struct config c) goto retry; src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -180,9 +205,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* Don't destroy existing mappings unless expected to overlap */ + while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { + /* Check for unsigned overflow */ + if (addr + c.dest_alignment < addr) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { -- 2.35.1

2 years, 5 months

1
0
0 0

[PATCH AUTOSEL 5.15 14/15] selftest/vm: verify mmap addr in mremap_test

by Sasha Levin

From: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> [ Upstream commit 9c85a9bae267f6b5e5e374d0d023bbbe9db096d3 ] Avoid calling mmap with requested addresses that are less than the system's mmap_min_addr. When run as root, mmap returns EACCES when trying to map addresses < mmap_min_addr. This is not one of the error codes for the condition to retry the mmap in the test. Rather than arbitrarily retrying on EACCES, don't attempt an mmap until addr > vm.mmap_min_addr. Add a munmap call after an alignment check as the mappings are retained after the retry and can reach the vm.max_map_count sysctl. Link: https://lkml.kernel.org/r/20220420215721.4868-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/vm/mremap_test.c | 41 +++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 0624d1bd71b5..2b3b4f15185f 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,6 +6,7 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> @@ -64,6 +65,35 @@ enum { .expect_failure = should_fail \ } +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + /* * Returns the start address of the mapping on success, else returns * NULL on failure. @@ -72,8 +102,15 @@ static void *get_source_mapping(struct config c) { unsigned long long addr = 0ULL; void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + retry: addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, -1, 0); @@ -91,8 +128,10 @@ static void *get_source_mapping(struct config c) * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; -- 2.35.1

2 years, 5 months

1
0
0 0

[PATCH AUTOSEL 5.17 22/22] selftest/vm: verify remap destination address in mremap_test

by Sasha Levin

From: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> [ Upstream commit 18d609daa546c919fd36b62a7b510c18de4b4af8 ] Because mremap does not have a MAP_FIXED_NOREPLACE flag, it can destroy existing mappings. This causes a segfault when regions such as text are remapped and the permissions are changed. Verify the requested mremap destination address does not overlap any existing mappings by using mmap's MAP_FIXED_NOREPLACE flag. Keep incrementing the destination address until a valid mapping is found or fail the current test once the max address is reached. Link: https://lkml.kernel.org/r/20220420215721.4868-2-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/vm/mremap_test.c | 42 ++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 9a518fee6306..58775dab3cc6 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -10,6 +10,7 @@ #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -64,6 +65,30 @@ enum { .expect_failure = should_fail \ } +/* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + /* Returns mmap_min_addr sysctl tunable from procfs */ static unsigned long long get_mmap_min_addr(void) { @@ -111,8 +136,8 @@ static void *get_source_mapping(struct config c) goto retry; src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -179,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* Don't destroy existing mappings unless expected to overlap */ + while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { + /* Check for unsigned overflow */ + if (addr + c.dest_alignment < addr) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { -- 2.35.1

2 years, 5 months

1
0
0 0

[PATCH AUTOSEL 5.17 21/22] selftest/vm: verify mmap addr in mremap_test

by Sasha Levin

From: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> [ Upstream commit 9c85a9bae267f6b5e5e374d0d023bbbe9db096d3 ] Avoid calling mmap with requested addresses that are less than the system's mmap_min_addr. When run as root, mmap returns EACCES when trying to map addresses < mmap_min_addr. This is not one of the error codes for the condition to retry the mmap in the test. Rather than arbitrarily retrying on EACCES, don't attempt an mmap until addr > vm.mmap_min_addr. Add a munmap call after an alignment check as the mappings are retained after the retry and can reach the vm.max_map_count sysctl. Link: https://lkml.kernel.org/r/20220420215721.4868-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/vm/mremap_test.c | 41 +++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 7c0b0617b9f8..9a518fee6306 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,6 +6,7 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> @@ -63,6 +64,35 @@ enum { .expect_failure = should_fail \ } +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + /* * Returns the start address of the mapping on success, else returns * NULL on failure. @@ -71,8 +101,15 @@ static void *get_source_mapping(struct config c) { unsigned long long addr = 0ULL; void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + retry: addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, -1, 0); @@ -90,8 +127,10 @@ static void *get_source_mapping(struct config c) * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; -- 2.35.1

2 years, 5 months

1
0
0 0

[PATCH][V2] selftests/resctrl: Fix null pointer dereference on open failed

by Colin Ian King

Currently if opening /dev/null fails to open then file pointer fp is null and further access to fp via fprintf will cause a null pointer dereference. Fix this by returning a negative error value when a null fp is detected. Detected using cppcheck static analysis: tools/testing/selftests/resctrl/fill_buf.c:124:6: note: Assuming that condition '!fp' is not redundant if (!fp) ^ tools/testing/selftests/resctrl/fill_buf.c:126:10: note: Null pointer dereference fprintf(fp, "Sum: %d ", ret); Fixes: a2561b12fe39 ("selftests/resctrl: Add built in benchmark") Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- V2: Add cppcheck analysis information --- tools/testing/selftests/resctrl/fill_buf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 51e5cf22632f..56ccbeae0638 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -121,8 +121,10 @@ static int fill_cache_read(unsigned char *start_ptr, unsigned char *end_ptr, /* Consume read result so that reading memory is not optimized out. */ fp = fopen("/dev/null", "w"); - if (!fp) + if (!fp) { perror("Unable to write to /dev/null"); + return -1; + } fprintf(fp, "Sum: %d ", ret); fclose(fp); -- 2.35.1

2 years, 5 months

2
1
0 0

[PATCH v5 0/2] selftests/resctrl: Print a message if the result of MBM&CMT tests is failed on Intel CPU

by Shaopeng Tan

Hello, The aim of this series is to print a message to let users know a possible cause of failure, if the result of MBM&CMT tests is failed on Intel CPU. In order to detect Intel vendor, I extended AMD vendor detect function. Difference from v4: - Fixed the typos. - Changed "get_vendor() != ARCH_AMD" to "get_vendor() == ARCH_INTEL". - Reorder the declarations based on line length from longest to shortest. https://lore.kernel.org/lkml/20220316055940.292550-1-tan.shaopeng@jp.fujits… [PATCH v4] This patch series is based on v5.17. Shaopeng Tan (2): selftests/resctrl: Extend CPU vendor detection selftests/resctrl: Print a message if the result of MBM&CMT tests is failed on Intel CPU tools/testing/selftests/resctrl/cat_test.c | 2 +- tools/testing/selftests/resctrl/resctrl.h | 5 ++- .../testing/selftests/resctrl/resctrl_tests.c | 45 +++++++++++++------ tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 4 files changed, 37 insertions(+), 17 deletions(-) -- 2.27.0

2 years, 5 months

4
10
0 0

[PATCH V4 00/31] x86/sgx and selftests/sgx: Support SGX2

by Reinette Chatre

Now that the discussions surrounding the support for SGX2 is settling, the kselftest audience is added to the discussion for the first time to consider the testing of the new features. V3: https://lore.kernel.org/lkml/cover.1648847675.git.reinette.chatre@intel.com/ Changes since V3 that directly impact user space: - SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS ioctl()'s struct sgx_enclave_restrict_permissions no longer provides entire secinfo, just the new permissions in new "permissions" struct member. (Jarkko) - Rename SGX_IOC_ENCLAVE_MODIFY_TYPE ioctl() to SGX_IOC_ENCLAVE_MODIFY_TYPES. (Jarkko) - SGX_IOC_ENCLAVE_MODIFY_TYPES ioctl()'s struct sgx_enclave_modify_type no longer provides entire secinfo, just the new page type in new "page_type" struct member. (Jarkko) Details about changes since V3 that do not directly impact user space: - Add new patch to enable VA pages to be added without invoking reclaimer directly if no EPC pages are available, failing instead. This enables VA pages to be added with enclave's mutex held. Fixes an issue encountered by Haitao. More details in new patch "x86/sgx: Support VA page allocation without reclaiming". - While refactoring, change existing code to consistently use IS_ALIGNED(). (Jarkko) - Many patches received a tag from Jarkko. - Many smaller changes, please refer to individual patches. V2: https://lore.kernel.org/lkml/cover.1644274683.git.reinette.chatre@intel.com/ Changes since V2 that directly impact user space: - Maximum allowed permissions of dynamically added pages is RWX, previously limited to RW. (Jarkko) Dynamically added pages are initially created with architecturally limited EPCM permissions of RW. mmap() and mprotect() of these pages with RWX permissions would no longer be blocked by SGX driver. PROT_EXEC on dynamically added pages will be possible after running ENCLU[EMODPE] from within the enclave with appropriate VMA permissions. - The kernel no longer attempts to track the EPCM runtime permissions. (Jarkko) Consequences are: - Kernel does not modify PTEs to follow EPCM permissions. User space will receive #PF with SGX error code in cases where the V2 implementation would have resulted in regular (non-SGX) page fault error code. - SGX_IOC_ENCLAVE_RELAX_PERMISSIONS is removed. This ioctl() was used to clear PTEs after permissions were modified from within the enclave and ensure correct PTEs are installed. Since PTEs no longer track EPCM permissions the changes in EPCM permissions would not impact PTEs. As long as new permissions are within the maximum vetted permissions (vm_max_prot_bits) only ENCLU[EMODPE] from within enclave is needed, as accompanied by appropriate VMA permissions. - struct sgx_enclave_restrict_perm renamed to sgx_enclave_restrict_permissions (Jarkko) - struct sgx_enclave_modt renamed to struct sgx_enclave_modify_type to be consistent with the verbose naming of other SGX uapi structs. Details about changes since V2 that do not directly impact user space: - Kernel no longer tracks the runtime EPCM permissions with the aim of installing accurate PTEs. (Jarkko) - In support of this change the following patches were removed: Documentation/x86: Document SGX permission details x86/sgx: Support VMA permissions more relaxed than enclave permissions x86/sgx: Add pfn_mkwrite() handler for present PTEs x86/sgx: Add sgx_encl_page->vm_run_prot_bits for dynamic permission changes x86/sgx: Support relaxing of enclave page permissions - No more handling of scenarios where VMA permissions may be more relaxed than what the EPCM allows. Enclaves are not prevented from accessing such pages and the EPCM permissions are entrusted to control access as supported by the SGX error code in page faults. - No more explicit setting of protection bits in page fault handler. Protection bits are inherited from VMA similar to SGX1 support. - Selftest patches are moved to the end of the series. (Jarkko) - New patch contributed by Jarkko to avoid duplicated code: x86/sgx: Export sgx_encl_page_alloc() - New patch separating changes from existing patch. (Jarkko) x86/sgx: Export sgx_encl_{grow,shrink}() - New patch to keep one required benefit from the (now removed) kernel EPCM permission tracking: x86/sgx: Support loading enclave page without VMA permissions check - Updated cover letter to reflect architecture changes. - Many smaller changes, please refer to individual patches. V1: https://lore.kernel.org/linux-sgx/cover.1638381245.git.reinette.chatre@inte… Changes since V1 that directly impact user space: - SGX2 permission changes changed from a single ioctl() named SGX_IOC_PAGE_MODP to two new ioctl()s: SGX_IOC_ENCLAVE_RELAX_PERMISSIONS and SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS, supported by two different parameter structures (SGX_IOC_ENCLAVE_RELAX_PERMISSIONS does not support a result output parameter) (Jarkko). User space flow impact: After user space runs ENCLU[EMODPE] it needs to call SGX_IOC_ENCLAVE_RELAX_PERMISSIONS to have PTEs updated. Previously running SGX_IOC_PAGE_MODP in this scenario resulted in EPCM.PR being set but calling SGX_IOC_ENCLAVE_RELAX_PERMISSIONS will not result in EPCM.PR being set anymore and thus no need for an additional ENCLU[EACCEPT]. - SGX_IOC_ENCLAVE_RELAX_PERMISSIONS and SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS obtain new permissions from secinfo as parameter instead of the permissions directly (Jarkko). - ioctl() supporting SGX2 page type change is renamed from SGX_IOC_PAGE_MODT to SGX_IOC_ENCLAVE_MODIFY_TYPE (Jarkko). - SGX_IOC_ENCLAVE_MODIFY_TYPE obtains new page type from secinfo as parameter instead of the page type directly (Jarkko). - ioctl() supporting SGX2 page removal is renamed from SGX_IOC_PAGE_REMOVE to SGX_IOC_ENCLAVE_REMOVE_PAGES (Jarkko). - All ioctl() parameter structures have been renamed as a result of the ioctl() renaming: SGX_IOC_ENCLAVE_RELAX_PERMISSIONS => struct sgx_enclave_relax_perm SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS => struct sgx_enclave_restrict_perm SGX_IOC_ENCLAVE_MODIFY_TYPE => struct sgx_enclave_modt SGX_IOC_ENCLAVE_REMOVE_PAGES => struct sgx_enclave_remove_pages Changes since V1 that do not directly impact user space: - Number of patches in series increased from 25 to 32 primarily because of splitting the original submission: - Wrappers for the new SGX2 functions are introduced in three separate patches replacing the original "x86/sgx: Add wrappers for SGX2 functions" (Jarkko). - Moving and renaming sgx_encl_ewb_cpumask() is done with two patches replacing the original "x86/sgx: Use more generic name for enclave cpumask function" (Jarkko). - Support for SGX2 EPCM permission changes is split into two ioctls(), one for relaxing and one for restricting permissions, each introduced by a new patch replacing the original "x86/sgx: Support enclave page permission changes" (Jarkko). - Extracted code used by existing ioctls() for usage by new ioctl()s into a new utility in new patch "x86/sgx: Create utility to validate user provided offset and length" (Dave did not specifically ask for this but it addresses his review feedback). - Two new Documentation patches to support the SGX2 work ("Documentation/x86: Introduce enclave runtime management") and a dedicated section on the enclave permission management ("Documentation/x86: Document SGX permission details") (Andy). - Most patches were reworked to improve the language by: * aiming to refer to exact item instead of English rephrasing (Jarkko). * use ioctl() instead of ioctl throughout (Dave). * Use "relaxed" instead of "exceed" when referring to permissions (Dave). - Improved documentation with several additions to Documentation/x86/sgx.rst. - Many smaller changes, please refer to individual patches. Hi Everybody, The current Linux kernel support for SGX includes support for SGX1 that requires that an enclave be created with properties that accommodate all usages over its (the enclave's) lifetime. This includes properties such as permissions of enclave pages, the number of enclave pages, and the number of threads supported by the enclave. Consequences of this requirement to have the enclave be created to accommodate all usages include: * pages needing to support relocated code are required to have RWX permissions for their entire lifetime, * an enclave needs to be created with the maximum stack and heap projected to be needed during the enclave's entire lifetime which can be longer than the processes running within it, * an enclave needs to be created with support for the maximum number of threads projected to run in the enclave. Since SGX1 a few more functions were introduced, collectively called SGX2, that support modifications to an initialized enclave. Hardware supporting these functions are already available as listed on https://github.com/ayeks/SGX-hardware This series adds support for SGX2, also referred to as Enclave Dynamic Memory Management (EDMM). This includes: * Support modifying EPCM permissions of regular enclave pages belonging to an initialized enclave. Only permission restriction is supported via a new ioctl() SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS. Relaxing of EPCM permissions can only be done from within the enclave with the SGX instruction ENCLU[EMODPE]. * Support dynamic addition of regular enclave pages to an initialized enclave. At creation new pages are architecturally limited to RW EPCM permissions but will be accessible with PROT_EXEC after the enclave runs ENCLU[EMODPE] to relax EPCM permissions to RWX. Pages are dynamically added to an initialized enclave from the SGX page fault handler. * Support expanding an initialized enclave to accommodate more threads. More threads can be accommodated by an enclave with the addition of Thread Control Structure (TCS) pages that is done by changing the type of regular enclave pages to TCS pages using a new ioctl() SGX_IOC_ENCLAVE_MODIFY_TYPES. * Support removing regular and TCS pages from an initialized enclave. Removing pages is accomplished in two stages as supported by two new ioctl()s SGX_IOC_ENCLAVE_MODIFY_TYPES (same ioctl() as mentioned in previous bullet) and SGX_IOC_ENCLAVE_REMOVE_PAGES. * Tests covering all the new flows, some edge cases, and one comprehensive stress scenario. No additional work is needed to support SGX2 in a virtualized environment. All tests included in this series passed when run from a guest as tested with the recent QEMU release based on 6.2.0 that supports SGX. Patches 1 through 14 prepare the existing code for SGX2 support by introducing the SGX2 functions, refactoring code, and tracking enclave page types. Patches 15 through 21 enable the SGX2 features and include a Documentation patch. Patches 22 through 31 test several scenarios of all the enabled SGX2 features. This series is based on v5.18-rc2. Your feedback will be greatly appreciated. Regards, Reinette Jarkko Sakkinen (1): x86/sgx: Export sgx_encl_page_alloc() Reinette Chatre (30): x86/sgx: Add short descriptions to ENCLS wrappers x86/sgx: Add wrapper for SGX2 EMODPR function x86/sgx: Add wrapper for SGX2 EMODT function x86/sgx: Add wrapper for SGX2 EAUG function x86/sgx: Support loading enclave page without VMA permissions check x86/sgx: Export sgx_encl_ewb_cpumask() x86/sgx: Rename sgx_encl_ewb_cpumask() as sgx_encl_cpumask() x86/sgx: Move PTE zap code to new sgx_zap_enclave_ptes() x86/sgx: Make sgx_ipi_cb() available internally x86/sgx: Create utility to validate user provided offset and length x86/sgx: Keep record of SGX page type x86/sgx: Export sgx_encl_{grow,shrink}() x86/sgx: Support VA page allocation without reclaiming x86/sgx: Support restricting of enclave page permissions x86/sgx: Support adding of pages to an initialized enclave x86/sgx: Tighten accessible memory range after enclave initialization x86/sgx: Support modifying SGX page type x86/sgx: Support complete page removal x86/sgx: Free up EPC pages directly to support large page ranges Documentation/x86: Introduce enclave runtime management section selftests/sgx: Add test for EPCM permission changes selftests/sgx: Add test for TCS page permission changes selftests/sgx: Test two different SGX2 EAUG flows selftests/sgx: Introduce dynamic entry point selftests/sgx: Introduce TCS initialization enclave operation selftests/sgx: Test complete changing of page type flow selftests/sgx: Test faulty enclave behavior selftests/sgx: Test invalid access to removed enclave page selftests/sgx: Test reclaiming of untouched page selftests/sgx: Page removal stress test Documentation/x86/sgx.rst | 15 + arch/x86/include/asm/sgx.h | 8 + arch/x86/include/uapi/asm/sgx.h | 61 + arch/x86/kernel/cpu/sgx/encl.c | 329 +++- arch/x86/kernel/cpu/sgx/encl.h | 15 +- arch/x86/kernel/cpu/sgx/encls.h | 33 + arch/x86/kernel/cpu/sgx/ioctl.c | 640 +++++++- arch/x86/kernel/cpu/sgx/main.c | 75 +- arch/x86/kernel/cpu/sgx/sgx.h | 3 + tools/testing/selftests/sgx/defines.h | 23 + tools/testing/selftests/sgx/load.c | 41 + tools/testing/selftests/sgx/main.c | 1435 +++++++++++++++++ tools/testing/selftests/sgx/main.h | 1 + tools/testing/selftests/sgx/test_encl.c | 68 + .../selftests/sgx/test_encl_bootstrap.S | 6 + 15 files changed, 2625 insertions(+), 128 deletions(-) base-commit: ce522ba9ef7e2d9fb22a39eb3371c0c64e2a433e -- 2.25.1

2 years, 5 months

4
59
0 0

[PATCH bpf-next v2 0/6] bpf trampoline for arm64

by Xu Kuohai

Add bpf trampoline support for arm64. Most of the logic is the same as x86. Tested on qemu, result: #55 fentry_fexit:OK #56 fentry_test:OK #58 fexit_sleep:OK #59 fexit_stress:OK #60 fexit_test:OK #67 get_func_args_test:OK #68 get_func_ip_test:OK #101 modify_return:OK v2: - Add Song's ACK - Change the multi-line comment in is_valid_bpf_tramp_flags() into net style (patch 3) - Fix a deadloop issue in ftrace selftest (patch 2) - Replace pt_regs->x0 with pt_regs->orig_x0 in patch 1 commit message - Replace "bpf trampoline" with "custom trampoline" in patch 1, as ftrace direct call is not only used by bpf trampoline. v1: https://lore.kernel.org/bpf/20220413054959.1053668-1-xukuohai@huawei.com/ Xu Kuohai (6): arm64: ftrace: Add ftrace direct call support ftrace: Fix deadloop caused by direct call in ftrace selftest bpf: Move is_valid_bpf_tramp_flags() to the public trampoline code bpf, arm64: Impelment bpf_arch_text_poke() for arm64 bpf, arm64: bpf trampoline for arm64 selftests/bpf: Fix trivial typo in fentry_fexit.c arch/arm64/Kconfig | 2 + arch/arm64/include/asm/ftrace.h | 10 + arch/arm64/kernel/asm-offsets.c | 1 + arch/arm64/kernel/entry-ftrace.S | 28 +- arch/arm64/net/bpf_jit.h | 14 +- arch/arm64/net/bpf_jit_comp.c | 390 +++++++++++++++++- arch/x86/net/bpf_jit_comp.c | 20 - include/linux/bpf.h | 5 + kernel/bpf/bpf_struct_ops.c | 4 +- kernel/bpf/trampoline.c | 35 +- kernel/trace/trace_selftest.c | 4 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 4 +- 12 files changed, 482 insertions(+), 35 deletions(-) -- 2.30.2

2 years, 5 months

6
20
0 0

kselftest/next build: 8 builds: 0 failed, 8 passed (v5.18-rc3-17-g68c4844985d1f)

by kernelci.org bot

kselftest/next build: 8 builds: 0 failed, 8 passed (v5.18-rc3-17-g68c4844985d1f) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v5.18-rc3-17-g68c48… Tree: kselftest Branch: next Git Describe: v5.18-rc3-17-g68c4844985d1f Git Commit: 68c4844985d1f8c1b1a71dfcdbfacb5a30babc95 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest (arm64, clang-14) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-14) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-14) — PASS, 0 errors, 0 warnings, 0 section mismatches --- For more info write to <info(a)kernelci.org>

2 years, 5 months

1
0
0 0

kselftest/next kselftest-lkdtm: 5 runs, 1 regressions (v5.18-rc3-9-g170d1c23f2a3)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 5 runs, 1 regressions (v5.18-rc3-9-g170d1c23f2a3) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------+-------+---------------+----------+------------------------------+------------ mt8173-elm-hana | arm64 | lab-collabora | gcc-10 | defconfig+kse...4-chromebook | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v5.18-rc3-9-g170… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v5.18-rc3-9-g170d1c23f2a3 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 170d1c23f2a356932259034f73d579d0bab857d6 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------+-------+---------------+----------+------------------------------+------------ mt8173-elm-hana | arm64 | lab-collabora | gcc-10 | defconfig+kse...4-chromebook | 1 Details: https://kernelci.org/test/plan/id/626721f54303a515a1ff9459 Results: 56 PASS, 8 FAIL, 26 SKIP Full config: defconfig+kselftest+arm64-chromebook Compiler: gcc-10 (aarch64-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//kselftest/next/v5.18-rc3-9-g170d1c23f2a3/arm6… HTML log: https://storage.kernelci.org//kselftest/next/v5.18-rc3-9-g170d1c23f2a3/arm6… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bullseye-kselftest/2022042… * kselftest-lkdtm.lkdtm_READ_AFTER_FREE_sh: https://kernelci.org/test/case/id/626721f54303a515a1ff9495 failing since 20 days (last pass: v5.17-rc5-22-gf6d344cd5fa6, first fail: v5.18-rc1)

2 years, 5 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror April 2022