From: Ira Weiny ira.weiny@intel.com

Protection Keys User (PKU) and Protection Keys Supervisor (PKS) work in similar fashions and can share common defines. Specifically PKS and PKU each have:

1. A single control register 2. The same number of keys 3. The same number of bits in the register per key 4. Access and Write disable in the same bit locations

Given the above, share all the macros that synthesize and manipulate register values between the two features. Unlike PKU the PKS definitions are needed in both pgtable.h and pkeys.h. Create a common header for those 2 headers to share. The alternative, including pgtable.h in pkeys.h, triggers complex header dependencies.

Share these defines by moving them into a new header, change their names to reflect the common use, and include the header where needed.

Reviewed-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Ira Weiny ira.weiny@intel.com

--- NOTE: The initialization of init_pkru_value cause checkpatch errors because of the space after the '(' in the macros. We leave this as is because it is more readable in this format. And it was existing code.

--- Changes from V3: From Dan Williams Fix guard macro names Reword commit message.

Changes from RFC V3 Per Dave Hansen Update commit message Add comment to PKR_AD_KEY macro --- arch/x86/include/asm/pgtable.h | 13 ++++++------- arch/x86/include/asm/pkeys.h | 2 ++ arch/x86/include/asm/pkeys_common.h | 15 +++++++++++++++ arch/x86/kernel/fpu/xstate.c | 8 ++++---- arch/x86/mm/pkeys.c | 14 ++++++-------- 5 files changed, 33 insertions(+), 19 deletions(-) create mode 100644 arch/x86/include/asm/pkeys_common.h

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a02c67291cfc..bfbfb951fe65 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1360,9 +1360,7 @@ static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */

-#define PKRU_AD_BIT 0x1 -#define PKRU_WD_BIT 0x2 -#define PKRU_BITS_PER_PKEY 2 +#include <asm/pkeys_common.h>

#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; @@ -1372,18 +1370,19 @@ extern u32 init_pkru_value;

static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { - int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; - return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); + int pkru_pkey_bits = pkey * PKR_BITS_PER_PKEY; + + return !(pkru & (PKR_AD_BIT << pkru_pkey_bits)); }

static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { - int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; + int pkru_pkey_bits = pkey * PKR_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ - return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); + return !(pkru & ((PKR_AD_BIT|PKR_WD_BIT) << pkru_pkey_bits)); }

static inline u16 pte_flags_pkey(unsigned long pte_flags) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 2ff9b98812b7..f9feba80894b 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H

+#include <asm/pkeys_common.h> + #define ARCH_DEFAULT_PKEY 0

/* diff --git a/arch/x86/include/asm/pkeys_common.h b/arch/x86/include/asm/pkeys_common.h new file mode 100644 index 000000000000..e40b0ced733f --- /dev/null +++ b/arch/x86/include/asm/pkeys_common.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PKEYS_COMMON_H +#define _ASM_X86_PKEYS_COMMON_H + +#define PKR_AD_BIT 0x1 +#define PKR_WD_BIT 0x2 +#define PKR_BITS_PER_PKEY 2 + +/* + * Generate an Access-Disable mask for the given pkey. Several of these can be + * OR'd together to generate pkey register values. + */ +#define PKR_AD_KEY(pkey) (PKR_AD_BIT << ((pkey) * PKR_BITS_PER_PKEY)) + +#endif /*_ASM_X86_PKEYS_COMMON_H */ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 683749b80ae2..face29dab0e3 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -995,7 +995,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { u32 old_pkru; - int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); + int pkey_shift = (pkey * PKR_BITS_PER_PKEY); u32 new_pkru_bits = 0;

/* @@ -1014,16 +1014,16 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,

/* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) - new_pkru_bits |= PKRU_AD_BIT; + new_pkru_bits |= PKR_AD_BIT; if (init_val & PKEY_DISABLE_WRITE) - new_pkru_bits |= PKRU_WD_BIT; + new_pkru_bits |= PKR_WD_BIT;

/* Shift the bits in to the correct place in PKRU for pkey: */ new_pkru_bits <<= pkey_shift;

/* Get old PKRU and mask off any old bits in place: */ old_pkru = read_pkru(); - old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); + old_pkru &= ~((PKR_AD_BIT|PKR_WD_BIT) << pkey_shift);

/* Write old part along with new part: */ write_pkru(old_pkru | new_pkru_bits); diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 8873ed1438a9..f5efb4007e74 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -111,19 +111,17 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey return vma_pkey(vma); }

-#define PKRU_AD_KEY(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY)) - /* * Make the default PKRU value (at execve() time) as restrictive * as possible. This ensures that any threads clone()'d early * in the process's lifetime will not accidentally get access * to data which is pkey-protected later on. */ -u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | - PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) | - PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) | - PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) | - PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15); +u32 init_pkru_value = PKR_AD_KEY( 1) | PKR_AD_KEY( 2) | PKR_AD_KEY( 3) | + PKR_AD_KEY( 4) | PKR_AD_KEY( 5) | PKR_AD_KEY( 6) | + PKR_AD_KEY( 7) | PKR_AD_KEY( 8) | PKR_AD_KEY( 9) | + PKR_AD_KEY(10) | PKR_AD_KEY(11) | PKR_AD_KEY(12) | + PKR_AD_KEY(13) | PKR_AD_KEY(14) | PKR_AD_KEY(15);

/* * Called from the FPU code when creating a fresh set of FPU @@ -173,7 +171,7 @@ static ssize_t init_pkru_write_file(struct file *file, * up immediately if someone attempts to disable access * or writes to pkey 0. */ - if (new_init_pkru & (PKRU_AD_BIT|PKRU_WD_BIT)) + if (new_init_pkru & (PKR_AD_BIT|PKR_WD_BIT)) return -EINVAL;

WRITE_ONCE(init_pkru_value, new_init_pkru);

From: Ira Weiny ira.weiny@intel.com

Avoid open coding shift and mask operations by defining and using helper macros for PKey operations.

Reviewed-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Ira Weiny ira.weiny@intel.com

--- Changes from V3: new patch suggested by Dan Williams to use macros better. --- arch/x86/include/asm/pgtable.h | 7 ++----- arch/x86/include/asm/pkeys_common.h | 11 ++++++++--- arch/x86/mm/pkeys.c | 8 +++----- 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index bfbfb951fe65..b1529b44a996 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1370,19 +1370,16 @@ extern u32 init_pkru_value;

static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { - int pkru_pkey_bits = pkey * PKR_BITS_PER_PKEY; - - return !(pkru & (PKR_AD_BIT << pkru_pkey_bits)); + return !(pkru & PKR_AD_KEY(pkey)); }

static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { - int pkru_pkey_bits = pkey * PKR_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ - return !(pkru & ((PKR_AD_BIT|PKR_WD_BIT) << pkru_pkey_bits)); + return !(pkru & (PKR_AD_KEY(pkey) | PKR_WD_KEY(pkey))); }

static inline u16 pte_flags_pkey(unsigned long pte_flags) diff --git a/arch/x86/include/asm/pkeys_common.h b/arch/x86/include/asm/pkeys_common.h index e40b0ced733f..0681522974ba 100644 --- a/arch/x86/include/asm/pkeys_common.h +++ b/arch/x86/include/asm/pkeys_common.h @@ -6,10 +6,15 @@ #define PKR_WD_BIT 0x2 #define PKR_BITS_PER_PKEY 2

+#define PKR_PKEY_SHIFT(pkey) (pkey * PKR_BITS_PER_PKEY) +#define PKR_PKEY_MASK(pkey) (((1 << PKR_BITS_PER_PKEY) - 1) << PKR_PKEY_SHIFT(pkey)) + /* - * Generate an Access-Disable mask for the given pkey. Several of these can be - * OR'd together to generate pkey register values. + * Generate an Access-Disable and Write-Disable mask for the given pkey. + * Several of the AD's are OR'd together to generate a default pkey register + * value. */ -#define PKR_AD_KEY(pkey) (PKR_AD_BIT << ((pkey) * PKR_BITS_PER_PKEY)) +#define PKR_AD_KEY(pkey) (PKR_AD_BIT << PKR_PKEY_SHIFT(pkey)) +#define PKR_WD_KEY(pkey) (PKR_WD_BIT << PKR_PKEY_SHIFT(pkey))

#endif /*_ASM_X86_PKEYS_COMMON_H */ diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index d1dfe743e79f..fc8c7e2bb21b 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -218,16 +218,14 @@ __setup("init_pkru=", setup_init_pkru); */ u32 update_pkey_val(u32 pk_reg, int pkey, unsigned int flags) { - int pkey_shift = pkey * PKR_BITS_PER_PKEY; - /* Mask out old bit values */ - pk_reg &= ~(((1 << PKR_BITS_PER_PKEY) - 1) << pkey_shift); + pk_reg &= ~PKR_PKEY_MASK(pkey);

/* Or in new values */ if (flags & PKEY_DISABLE_ACCESS) - pk_reg |= PKR_AD_BIT << pkey_shift; + pk_reg |= PKR_AD_KEY(pkey); if (flags & PKEY_DISABLE_WRITE) - pk_reg |= PKR_WD_BIT << pkey_shift; + pk_reg |= PKR_WD_KEY(pkey);

return pk_reg; }

From: Ira Weiny ira.weiny@intel.com

Protection Keys for Supervisor pages (PKS) enables fast, hardware thread specific, manipulation of permission restrictions on supervisor page mappings. It uses the same mechanism of Protection Keys as those on User mappings but applies that mechanism to supervisor mappings using a supervisor specific MSR.

Add setup code and the lowest level of PKS MSR write support. The write value is cached per-cpu to avoid the overhead of the MSR write if the value has not changed.

That said, it should be noted that the underlying WRMSR(MSR_IA32_PKRS) is not serializing but still maintains ordering properties similar to WRPKRU. The current SDM section on PKRS needs updating but should be the same as that of WRPKRU. So to quote from the WRPKRU text:

WRPKRU will never execute transiently. Memory accesses affected by PKRU register will not execute (even transiently) until all prior executions of WRPKRU have completed execution and updated the PKRU register.

write_pkrs() contributed by Peter Zijlstra.

Introduce asm/pks.h to declare setup_pks() as an internal function call. Later patches will also need this new header as a place to declare internal structures and functions.

Reviewed-by: Dan Williams dan.j.williams@intel.com Co-developed-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Peter Zijlstra peterz@infradead.org Co-developed-by: Fenghua Yu fenghua.yu@intel.com Signed-off-by: Fenghua Yu fenghua.yu@intel.com Signed-off-by: Ira Weiny ira.weiny@intel.com

--- Changes from V3: From Dan Williams: Update commit message Add pks.h to hold ifdefery out of *.c files s/ARCH_HAS.../SUPERVISOR_PKEYS move setup_pks to pkeys.c (remove more ifdefery) Remove 'domain' language from commit message Clarify comment in fault handler Move the removal of the WARN_ON_ONCE in the fault path to this patch. Previously it was in: [07/10] x86/fault: Report the PKRS state on fault

Changes from V2 From Thomas: Make this patch last so PKS is not enabled until all the PKS mechanisms are in place. Specifically: 1) Modify setup_pks() to call write_pkrs() to properly set up the initial value when enabled.

2) Split this patch into two. 1) a precursor patch with the required defines/config options and 2) this patch which actually enables feature on CPUs which support it.

Changes since RFC V3 Per Dave Hansen Update comment Add X86_FEATURE_PKS to disabled-features.h Rebase based on latest TIP tree --- arch/x86/include/asm/pks.h | 15 +++++++++++ arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/mm/pkeys.c | 48 ++++++++++++++++++++++++++++++++++++ 3 files changed, 65 insertions(+) create mode 100644 arch/x86/include/asm/pks.h

diff --git a/arch/x86/include/asm/pks.h b/arch/x86/include/asm/pks.h new file mode 100644 index 000000000000..5d7067ada8fb --- /dev/null +++ b/arch/x86/include/asm/pks.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PKS_H +#define _ASM_X86_PKS_H + +#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS + +void setup_pks(void); + +#else /* !CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */ + +static inline void setup_pks(void) { } + +#endif /* CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */ + +#endif /* _ASM_X86_PKS_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ab640abe26b6..de49d0c0f4e0 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -58,6 +58,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> +#include <asm/pks.h>

#include "cpu.h"

@@ -1594,6 +1595,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)

x86_init_rdrand(c); setup_pku(c); + setup_pks();

/* * Clear/Set all flags overridden by options, need do it diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index fc8c7e2bb21b..f6a3a54b8d7d 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -229,3 +229,51 @@ u32 update_pkey_val(u32 pk_reg, int pkey, unsigned int flags)

return pk_reg; } + +#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS + +static DEFINE_PER_CPU(u32, pkrs_cache); + +/* + * write_pkrs() optimizes MSR writes by maintaining a per cpu cache which can + * be checked quickly. + * + * It should also be noted that the underlying WRMSR(MSR_IA32_PKRS) is not + * serializing but still maintains ordering properties similar to WRPKRU. + * The current SDM section on PKRS needs updating but should be the same as + * that of WRPKRU. So to quote from the WRPKRU text: + * + * WRPKRU will never execute transiently. Memory accesses + * affected by PKRU register will not execute (even transiently) + * until all prior executions of WRPKRU have completed execution + * and updated the PKRU register. + */ +void write_pkrs(u32 new_pkrs) +{ + u32 *pkrs; + + if (!static_cpu_has(X86_FEATURE_PKS)) + return; + + pkrs = get_cpu_ptr(&pkrs_cache); + if (*pkrs != new_pkrs) { + *pkrs = new_pkrs; + wrmsrl(MSR_IA32_PKRS, new_pkrs); + } + put_cpu_ptr(pkrs); +} + +/* + * PKS is independent of PKU and either or both may be supported on a CPU. + * Configure PKS if the CPU supports the feature. + */ +void setup_pks(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_PKS)) + return; + + write_pkrs(INIT_PKRS_VALUE); + cr4_set_bits(X86_CR4_PKS); +} + +#endif

From: Fenghua Yu fenghua.yu@intel.com

PKS allows kernel users to define domains of page mappings which have additional protections beyond the paging protections.

Add an API to allocate, use, and free a protection key which identifies such a domain. Export 5 new symbols pks_key_alloc(), pks_mk_noaccess(), pks_mk_readonly(), pks_mk_readwrite(), and pks_key_free(). Add 2 new macros; PAGE_KERNEL_PKEY(key) and _PAGE_PKEY(pkey).

Update the protection key documentation to cover pkeys on supervisor pages.

Reviewed-by: Dan Williams dan.j.williams@intel.com Co-developed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: Ira Weiny ira.weiny@intel.com Signed-off-by: Fenghua Yu fenghua.yu@intel.com

--- Changes from V3: From Dan Williams Remove flags from pks_key_alloc() Convert to ARCH_ENABLE_SUPERVISOR_PKEYS remove export of update_pkey_val() Update documentation change __clear_bit to clear_bit_unlock remove cpu_feature_enabled from pks_key_free remove pr_err stubs when CONFIG_HAS_SUPERVISOR_PKEYS=n clarify pks_key_alloc flags parameter with enum Update documentation for ARCH_ENABLE_SUPERVISOR_PKEYS No need to export write_pkrs Correct Kernel Doc for API functions From Randy Dunlap: Fix grammatical errors in doc

Changes from V2 From Greg KH Replace all WARN_ON_ONCE() uses with pr_err() From Dan Williams Add __must_check to pks_key_alloc() to help ensure users are using the API correctly

Changes from V1 Per Dave Hansen Add flags to pks_key_alloc() to help future proof the interface if/when the key space is exhausted.

Changes from RFC V3 Per Dave Hansen Put WARN_ON_ONCE in pks_key_free() s/pks_mknoaccess/pks_mk_noaccess/ s/pks_mkread/pks_mk_readonly/ s/pks_mkrdwr/pks_mk_readwrite/ Change return pks_key_alloc() to EOPNOTSUPP when not supported or configured Per Peter Zijlstra Remove unneeded preempt disable/enable --- Documentation/core-api/protection-keys.rst | 108 +++++++++++++--- arch/x86/include/asm/pgtable_types.h | 12 ++ arch/x86/include/asm/pks.h | 4 + arch/x86/mm/pkeys.c | 137 ++++++++++++++++++++- include/linux/pgtable.h | 4 + include/linux/pkeys.h | 17 +++ 6 files changed, 263 insertions(+), 19 deletions(-)

diff --git a/Documentation/core-api/protection-keys.rst b/Documentation/core-api/protection-keys.rst index ec575e72d0b2..6d6c4f25080c 100644 --- a/Documentation/core-api/protection-keys.rst +++ b/Documentation/core-api/protection-keys.rst @@ -4,25 +4,30 @@ Memory Protection Keys ======================

-Memory Protection Keys for Userspace (PKU aka PKEYs) is a feature -which is found on Intel's Skylake (and later) "Scalable Processor" -Server CPUs. It will be available in future non-server Intel parts -and future AMD processors. +Memory Protection Keys provide a mechanism for enforcing page-based +protections, but without requiring modification of the page tables +when an application changes protection domains.

-For anyone wishing to test or use this feature, it is available in -Amazon's EC2 C5 instances and is known to work there using an Ubuntu -17.04 image. +PKeys Userspace (PKU) is a feature which is found on Intel's Skylake "Scalable +Processor" Server CPUs and later. And it will be available in future +non-server Intel parts and future AMD processors.

-Memory Protection Keys provides a mechanism for enforcing page-based -protections, but without requiring modification of the page tables -when an application changes protection domains. It works by -dedicating 4 previously ignored bits in each page table entry to a -"protection key", giving 16 possible keys. +Protection Keys for Supervisor pages (PKS) is available in the SDM since May +2020. + +pkeys work by dedicating 4 previously Reserved bits in each page table entry to +a "protection key", giving 16 possible keys. User and Supervisor pages are +treated separately.

-There is also a new user-accessible register (PKRU) with two separate -bits (Access Disable and Write Disable) for each key. Being a CPU -register, PKRU is inherently thread-local, potentially giving each -thread a different set of protections from every other thread. +Protections for each page are controlled with per-CPU registers for each type +of page User and Supervisor. Each of these 32-bit register stores two separate +bits (Access Disable and Write Disable) for each key. + +For Userspace the register is user-accessible (rdpkru/wrpkru). For +Supervisor, the register (MSR_IA32_PKRS) is accessible only to the kernel. + +Being a CPU register, pkeys are inherently thread-local, potentially giving +each thread an independent set of protections from every other thread.

There are two new instructions (RDPKRU/WRPKRU) for reading and writing to the new register. The feature is only available in 64-bit mode, @@ -30,8 +35,11 @@ even though there is theoretically space in the PAE PTEs. These permissions are enforced on data access only and have no effect on instruction fetches.

-Syscalls -======== +For kernel space rdmsr/wrmsr are used to access the kernel MSRs. + + +Syscalls for user space keys +============================

There are 3 system calls which directly interact with pkeys::

@@ -98,3 +106,67 @@ with a read():: The kernel will send a SIGSEGV in both cases, but si_code will be set to SEGV_PKERR when violating protection keys versus SEGV_ACCERR when the plain mprotect() permissions are violated. + + +Kernel API for PKS support +========================== + +Similar to user space pkeys, supervisor pkeys allow additional protections to +be defined for a supervisor mappings. + +The following interface is used to allocate, use, and free a pkey which defines +a 'protection domain' within the kernel. Setting a pkey value in a supervisor +PTE adds this additional protection to the page. + +Kernel users intending to use PKS support should check (depend on) +ARCH_HAS_SUPERVISOR_PKEYS and add their config to ARCH_ENABLE_SUPERVISOR_PKEYS +to turn on this support within the core. + + int pks_key_alloc(const char * const pkey_user); + #define PAGE_KERNEL_PKEY(pkey) + #define _PAGE_KEY(pkey) + void pks_mk_noaccess(int pkey); + void pks_mk_readonly(int pkey); + void pks_mk_readwrite(int pkey); + void pks_key_free(int pkey); + +pks_key_alloc() allocates keys dynamically to allow better use of the limited +key space. + +Callers of pks_key_alloc() _must_ be prepared for it to fail and take +appropriate action. This is due mainly to the fact that PKS may not be +available on all arch's. Failure to check the return of pks_key_alloc() and +using any of the rest of the API is undefined. + +Keys are allocated with 'No Access' permissions. If other permissions are +required before the pkey is used, the pks_mk*() family of calls, documented +below, can be used prior to setting the pkey within the page table entries. + +Kernel users must set the pkey in the page table entries for the mappings they +want to protect. This can be done with PAGE_KERNEL_PKEY() or _PAGE_KEY(). + +The pks_mk*() family of calls allows kernel users to change the protections for +the domain identified by the pkey parameter. 3 states are available: +pks_mk_noaccess(), pks_mk_readonly(), and pks_mk_readwrite() which set the +access to none, read, and read/write respectively. + +Finally, pks_key_free() allows a user to return the key to the allocator for +use by others. + +The interface maintains pks_mk_noaccess() (Access Disabled (AD=1)) for all keys +not currently allocated. Therefore, the user can depend on access being +disabled when pks_key_alloc() returns a key and the user should remove mappings +from the domain (remove the pkey from the PTE) prior to calling pks_key_free(). + +It should be noted that the underlying WRMSR(MSR_IA32_PKRS) is not serializing +but still maintains ordering properties similar to WRPKRU. Thus it is safe to +immediately use a mapping when the pks_mk*() functions return. + +Older versions of the SDM on PKRS may be wrong with regard to this +serialization. The text should be the same as that of WRPKRU. From the WRPKRU +text: + + WRPKRU will never execute transiently. Memory accesses + affected by PKRU register will not execute (even transiently) + until all prior executions of WRPKRU have completed execution + and updated the PKRU register. diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f24d7ef8fffa..a3cb274351d9 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -73,6 +73,12 @@ _PAGE_PKEY_BIT2 | \ _PAGE_PKEY_BIT3)

+#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS +#define _PAGE_PKEY(pkey) (_AT(pteval_t, pkey) << _PAGE_BIT_PKEY_BIT0) +#else +#define _PAGE_PKEY(pkey) (_AT(pteval_t, 0)) +#endif + #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED) #else @@ -228,6 +234,12 @@ enum page_cache_mode { #define PAGE_KERNEL_IO __pgprot_mask(__PAGE_KERNEL_IO) #define PAGE_KERNEL_IO_NOCACHE __pgprot_mask(__PAGE_KERNEL_IO_NOCACHE)

+#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS +#define PAGE_KERNEL_PKEY(pkey) __pgprot_mask(__PAGE_KERNEL | _PAGE_PKEY(pkey)) +#else +#define PAGE_KERNEL_PKEY(pkey) PAGE_KERNEL +#endif + #endif /* __ASSEMBLY__ */

/* xwr */ diff --git a/arch/x86/include/asm/pks.h b/arch/x86/include/asm/pks.h index bfa638e17620..4891c9aa8fc7 100644 --- a/arch/x86/include/asm/pks.h +++ b/arch/x86/include/asm/pks.h @@ -4,6 +4,10 @@

#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS

+/* PKS supports 16 keys. Key 0 is reserved for the kernel. */ +#define PKS_KERN_DEFAULT_KEY 0 +#define PKS_NUM_KEYS 16 + struct extended_pt_regs { u32 thread_pkrs; /* Keep stack 8 byte aligned */ diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index f6a3a54b8d7d..47d29707ac39 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -3,6 +3,9 @@ * Intel Memory Protection Keys management * Copyright (c) 2015, Intel Corporation. */ +#undef pr_fmt +#define pr_fmt(fmt) "x86/pkeys: " fmt + #include <linux/debugfs.h> /* debugfs_create_u32() */ #include <linux/mm_types.h> /* mm_struct, vma, etc... */ #include <linux/pkeys.h> /* PKEY_* */ @@ -11,6 +14,7 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/fpu/internal.h> /* init_fpstate */ +#include <asm/pks.h>

int __execute_only_pkey(struct mm_struct *mm) { @@ -276,4 +280,135 @@ void setup_pks(void) cr4_set_bits(X86_CR4_PKS); }

-#endif +/* + * Do not call this directly, see pks_mk*() below. + * + * @pkey: Key for the domain to change + * @protection: protection bits to be used + * + * Protection utilizes the same protection bits specified for User pkeys + * PKEY_DISABLE_ACCESS + * PKEY_DISABLE_WRITE + * + */ +static inline void pks_update_protection(int pkey, unsigned long protection) +{ + current->thread.saved_pkrs = update_pkey_val(current->thread.saved_pkrs, + pkey, protection); + write_pkrs(current->thread.saved_pkrs); +} + +/** + * pks_mk_noaccess() - Disable all access to the domain + * @pkey the pkey for which the access should change. + * + * Disable all access to the domain specified by pkey. This is a global + * update and only affects the current running thread. + * + * It is a bug for users to call this without a valid pkey returned from + * pks_key_alloc() + */ +void pks_mk_noaccess(int pkey) +{ + pks_update_protection(pkey, PKEY_DISABLE_ACCESS); +} +EXPORT_SYMBOL_GPL(pks_mk_noaccess); + +/** + * pks_mk_readonly() - Make the domain Read only + * @pkey the pkey for which the access should change. + * + * Allow read access to the domain specified by pkey. This is a global update + * and only affects the current running thread. + * + * It is a bug for users to call this without a valid pkey returned from + * pks_key_alloc() + */ +void pks_mk_readonly(int pkey) +{ + pks_update_protection(pkey, PKEY_DISABLE_WRITE); +} +EXPORT_SYMBOL_GPL(pks_mk_readonly); + +/** + * pks_mk_readwrite() - Make the domain Read/Write + * @pkey the pkey for which the access should change. + * + * Allow all access, read and write, to the domain specified by pkey. This is + * a global update and only affects the current running thread. + * + * It is a bug for users to call this without a valid pkey returned from + * pks_key_alloc() + */ +void pks_mk_readwrite(int pkey) +{ + pks_update_protection(pkey, 0); +} +EXPORT_SYMBOL_GPL(pks_mk_readwrite); + +static const char pks_key_user0[] = "kernel"; + +/* Store names of allocated keys for debug. Key 0 is reserved for the kernel. */ +static const char *pks_key_users[PKS_NUM_KEYS] = { + pks_key_user0 +}; + +/* + * Each key is represented by a bit. Bit 0 is set for key 0 and reserved for + * its use. We use ulong for the bit operations but only 16 bits are used. + */ +static unsigned long pks_key_allocation_map = 1 << PKS_KERN_DEFAULT_KEY; + +/** + * pks_key_alloc() - Allocate a PKS key + * @pkey_user: String stored for debugging of key exhaustion. The caller is + * responsible to maintain this memory until pks_key_free(). + * + * Return: pkey if success + * -EOPNOTSUPP if pks is not supported or not enabled + * -ENOSPC if no keys are available + */ +__must_check int pks_key_alloc(const char * const pkey_user) +{ + int nr; + + if (!cpu_feature_enabled(X86_FEATURE_PKS)) + return -EOPNOTSUPP; + + while (1) { + nr = find_first_zero_bit(&pks_key_allocation_map, PKS_NUM_KEYS); + if (nr >= PKS_NUM_KEYS) { + pr_info("Cannot allocate supervisor key for %s.\n", + pkey_user); + return -ENOSPC; + } + if (!test_and_set_bit_lock(nr, &pks_key_allocation_map)) + break; + } + + /* for debugging key exhaustion */ + pks_key_users[nr] = pkey_user; + + return nr; +} +EXPORT_SYMBOL_GPL(pks_key_alloc); + +/** + * pks_key_free() - Free a previously allocate PKS key + * @pkey: Key to be free'ed + */ +void pks_key_free(int pkey) +{ + if (pkey >= PKS_NUM_KEYS || pkey <= PKS_KERN_DEFAULT_KEY) { + pr_err("Invalid PKey value: %d\n", pkey); + return; + } + + /* Restore to default of no access */ + pks_mk_noaccess(pkey); + pks_key_users[pkey] = NULL; + clear_bit_unlock(pkey, &pks_key_allocation_map); +} +EXPORT_SYMBOL_GPL(pks_key_free); + +#endif /* CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index cdfc4e9f253e..1e5f4a253e82 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1460,6 +1460,10 @@ static inline bool arch_has_pfn_modify_check(void) # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif

+#ifndef PAGE_KERNEL_PKEY +#define PAGE_KERNEL_PKEY(pkey) PAGE_KERNEL +#endif + /* * Page Table Modification bits for pgtbl_mod_mask. * diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index a3d17a8e4e81..6659404af876 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -56,6 +56,13 @@ static inline void copy_init_pkru_to_fpregs(void) void pkrs_save_set_irq(struct pt_regs *regs, u32 val); void pkrs_restore_irq(struct pt_regs *regs);

+__must_check int pks_key_alloc(const char *const pkey_user); +void pks_key_free(int pkey); + +void pks_mk_noaccess(int pkey); +void pks_mk_readonly(int pkey); +void pks_mk_readwrite(int pkey); + #else /* !CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */

#ifndef INIT_PKRS_VALUE @@ -65,6 +72,16 @@ void pkrs_restore_irq(struct pt_regs *regs); static inline void pkrs_save_set_irq(struct pt_regs *regs, u32 val) { } static inline void pkrs_restore_irq(struct pt_regs *regs) { }

+static inline __must_check int pks_key_alloc(const char * const pkey_user) +{ + return -EOPNOTSUPP; +} + +static inline void pks_key_free(int pkey) {} +static inline void pks_mk_noaccess(int pkey) {} +static inline void pks_mk_readonly(int pkey) {} +static inline void pks_mk_readwrite(int pkey) {} + #endif /* CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */

#endif /* _LINUX_PKEYS_H */

From: Ira Weiny ira.weiny@intel.com

The core PKS functionality provides an interface for kernel users to reserve keys to their domains set up the page tables with those keys and control access to those domains when needed.

Define test code which exercises the core functionality of PKS via a debugfs entry. Basic checks can be triggered on boot with a kernel command line option while both basic and preemption checks can be triggered with separate debugfs values.

debugfs controls are:

'0' -- Run access tests with a single pkey '1' -- Set up the pkey register with no access for the pkey allocated to this fd '2' -- Check that the pkey register updated in '1' is still the same. (To be used after a forced context switch.) '3' -- Allocate all pkeys possible and run tests on each pkey allocated. DEFAULT when run at boot.

Closing the fd will cleanup and release the pkey, therefore to exercise context switch testing a user space program is provided in:

.../tools/testing/selftests/x86/test_pks.c

Reviewed-by: Dan Williams dan.j.williams@intel.com Reviewed-by: Dave Hansen dave.hansen@linux.intel.com Co-developed-by: Fenghua Yu fenghua.yu@intel.com Signed-off-by: Fenghua Yu fenghua.yu@intel.com Signed-off-by: Ira Weiny ira.weiny@intel.com

--- Changes from V3 Add test into ARCH_ENABLE_SUPERVISOR_PKEYS Fix allocate context error handling Callback must now take pt_regs instead of irq_state Use pipes to ensure code switches contexts Add more verbose output Add --debug opt to trigger more kernel debug output Reduce kernel output by default Use #defines for the various options Add ability to chose cpu for testing Work out how to make pkrs_cache global when CONFIG_PKS_TEST=y Comments from Dan Williams: Remove walk_table in favor of follow_pte Adjust for new MASK and SHIFT macros Remove unneeded pkey.h header Handle_pks_testing -> handle_pks_test Retain static pkrs_cache when not test s/PKS_TESTING/PKS_TEST/ Put pks_test_callback declaration in pks_common.h Don't export pks_test_callback Add comment explaining context creation Remove module boilerplate

Changes for V2 Fix compilation errors

Changes for V1 Update for new pks_key_alloc()

Changes from RFC V3 Comments from Dave Hansen clean up whitespace dmanage Clean up Kconfig help Clean up user test error output s/pks_mknoaccess/pks_mk_noaccess/ s/pks_mkread/pks_mk_readonly/ s/pks_mkrdwr/pks_mk_readwrite/ Comments from Jing Han Remove duplicate stdio.h --- Documentation/core-api/protection-keys.rst | 5 +- arch/x86/include/asm/pks.h | 19 + arch/x86/mm/fault.c | 15 + arch/x86/mm/pkeys.c | 2 +- lib/Kconfig.debug | 11 + lib/Makefile | 3 + lib/pks/Makefile | 3 + lib/pks/pks_test.c | 693 +++++++++++++++++++++ mm/Kconfig | 3 +- tools/testing/selftests/x86/Makefile | 3 +- tools/testing/selftests/x86/test_pks.c | 150 +++++ 11 files changed, 903 insertions(+), 4 deletions(-) create mode 100644 lib/pks/Makefile create mode 100644 lib/pks/pks_test.c create mode 100644 tools/testing/selftests/x86/test_pks.c

diff --git a/Documentation/core-api/protection-keys.rst b/Documentation/core-api/protection-keys.rst index 6d6c4f25080c..2bcbb991231b 100644 --- a/Documentation/core-api/protection-keys.rst +++ b/Documentation/core-api/protection-keys.rst @@ -120,7 +120,8 @@ PTE adds this additional protection to the page.

Kernel users intending to use PKS support should check (depend on) ARCH_HAS_SUPERVISOR_PKEYS and add their config to ARCH_ENABLE_SUPERVISOR_PKEYS -to turn on this support within the core. +to turn on this support within the core. See the test configuration option +'PKS_TEST' for an example.

int pks_key_alloc(const char * const pkey_user); #define PAGE_KERNEL_PKEY(pkey) @@ -170,3 +171,5 @@ text: affected by PKRU register will not execute (even transiently) until all prior executions of WRPKRU have completed execution and updated the PKRU register. + +Example code can be found in lib/pks/pks_test.c diff --git a/arch/x86/include/asm/pks.h b/arch/x86/include/asm/pks.h index 4891c9aa8fc7..9e71322b0cf2 100644 --- a/arch/x86/include/asm/pks.h +++ b/arch/x86/include/asm/pks.h @@ -32,4 +32,23 @@ static inline void show_extended_regs_oops(struct pt_regs *regs,

#endif /* CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS */

+ +#ifdef CONFIG_PKS_TEST + +#define __static_or_pks_test + +bool handle_pks_test(unsigned long hw_error_code, struct pt_regs *regs); +bool pks_test_callback(struct pt_regs *regs); + +#else /* !CONFIG_PKS_TEST */ + +#define __static_or_pks_test static + +static inline bool handle_pks_test(unsigned long hw_error_code, struct pt_regs *regs) +{ + return false; +} + +#endif /* CONFIG_PKS_TEST */ + #endif /* _ASM_X86_PKS_H */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 0c36ce2f6abf..764d2fbb6c72 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1134,6 +1134,19 @@ bool fault_in_kernel_space(unsigned long address) return address >= TASK_SIZE_MAX; }

+#ifdef CONFIG_PKS_TEST +bool handle_pks_test(unsigned long hw_error_code, struct pt_regs *regs) +{ + /* + * If we get a protection key exception it could be because we + * are running the PKS test. If so, pks_test_callback() will + * clear the protection mechanism and return true to indicate + * the fault was handled. + */ + return (hw_error_code & X86_PF_PK) && pks_test_callback(regs); +} +#endif + /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that @@ -1150,6 +1163,8 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, if (!cpu_feature_enabled(X86_FEATURE_PKS)) WARN_ON_ONCE(hw_error_code & X86_PF_PK);

+ if (handle_pks_test(hw_error_code, regs)) + return;

#ifdef CONFIG_X86_32 /* diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 47d29707ac39..2dd1feeff9f6 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -236,7 +236,7 @@ u32 update_pkey_val(u32 pk_reg, int pkey, unsigned int flags)

#ifdef CONFIG_ARCH_ENABLE_SUPERVISOR_PKEYS

-static DEFINE_PER_CPU(u32, pkrs_cache); +__static_or_pks_test DEFINE_PER_CPU(u32, pkrs_cache);

/* * write_pkrs() optimizes MSR writes by maintaining a per cpu cache which can diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..b7728ed139f9 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2535,6 +2535,17 @@ config HYPERV_TESTING help Select this option to enable Hyper-V vmbus testing.

+config PKS_TEST + bool "PKey (S)upervisor testing" + depends on ARCH_HAS_SUPERVISOR_PKEYS + help + Select this option to enable testing of PKS core software and + hardware. The PKS core provides a mechanism to allocate keys as well + as maintain the protection settings across context switches. + Answer N if you don't know what supervisor keys are. + + If unsure, say N. + endmenu # "Kernel Testing and Coverage"

source "Documentation/Kconfig" diff --git a/lib/Makefile b/lib/Makefile index b5307d3eec1a..3606b97e12e0 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -354,3 +354,6 @@ obj-$(CONFIG_BITS_TEST) += test_bits.o obj-$(CONFIG_CMDLINE_KUNIT_TEST) += cmdline_kunit.o

obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o + +# PKS test +obj-y += pks/ diff --git a/lib/pks/Makefile b/lib/pks/Makefile new file mode 100644 index 000000000000..9daccba4f7c4 --- /dev/null +++ b/lib/pks/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_PKS_TEST) += pks_test.o diff --git a/lib/pks/pks_test.c b/lib/pks/pks_test.c new file mode 100644 index 000000000000..ca308f3ff5aa --- /dev/null +++ b/lib/pks/pks_test.c @@ -0,0 +1,693 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright(c) 2020 Intel Corporation. All rights reserved. + * + * Implement PKS testing + * Access to run this test can be with a command line parameter + * ("pks-test-on-boot") or more detailed tests can be triggered through: + * + * /sys/kernel/debug/x86/run_pks + * + * debugfs controls are: + * + * '0' -- Run access tests with a single pkey + * + * '1' -- Set up the pkey register with no access for the pkey allocated to + * this fd + * '2' -- Check that the pkey register updated in '1' is still the same. (To + * be used after a forced context switch.) + * + * '3' -- Allocate all pkeys possible and run tests on each pkey allocated. + * DEFAULT when run at boot. + * + * Closing the fd will cleanup and release the pkey. + * + * A companion user space program is provided in: + * + * .../tools/testing/selftests/x86/test_pks.c + * + * which will better test the context switching. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/entry-common.h> +#include <linux/fs.h> +#include <linux/list.h> +#include <linux/mman.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu-defs.h> +#include <linux/pgtable.h> +#include <linux/pkeys.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#include <asm/ptrace.h> /* for struct pt_regs */ +#include <asm/pkeys_common.h> +#include <asm/processor.h> +#include <asm/pks.h> + +#define PKS_TEST_MEM_SIZE (PAGE_SIZE) + +#define RUN_ALLOCATE "0" +#define ARM_CTX_SWITCH "1" +#define CHECK_CTX_SWITCH "2" +#define RUN_ALLOCATE_ALL "3" +#define RUN_ALLOCATE_DEBUG "4" +#define RUN_ALLOCATE_ALL_DEBUG "5" +#define RUN_CRASH_TEST "9" + +DECLARE_PER_CPU(u32, pkrs_cache); + +/* + * run_on_boot default '= false' which checkpatch complains about initializing; + * so we don't + */ +static bool run_on_boot; +static struct dentry *pks_test_dentry; +static bool run_9; + +/* + * We must lock the following globals for brief periods while the fault handler + * checks/updates them. + */ +static DEFINE_SPINLOCK(test_lock); +static int test_armed_key; +static unsigned long prev_cnt; +static unsigned long fault_cnt; + +struct pks_test_ctx { + bool pass; + bool pks_cpu_enabled; + bool debug; + int pkey; + char data[64]; +}; +static struct pks_test_ctx *test_exception_ctx; + +static bool check_pkey_val(u32 pk_reg, int pkey, u32 expected) +{ + pk_reg = (pk_reg & PKR_PKEY_MASK(pkey)) >> PKR_PKEY_SHIFT(pkey); + return (pk_reg == expected); +} + +/* + * Check if the register @pkey value matches @expected value + * + * Both the cached and actual MSR must match. + */ +static bool check_pkrs(int pkey, u32 expected) +{ + bool ret = true; + u64 pkrs; + u32 *tmp_cache; + + tmp_cache = get_cpu_ptr(&pkrs_cache); + if (!check_pkey_val(*tmp_cache, pkey, expected)) + ret = false; + put_cpu_ptr(tmp_cache); + + rdmsrl(MSR_IA32_PKRS, pkrs); + if (!check_pkey_val(pkrs, pkey, expected)) + ret = false; + + return ret; +} + +static void check_exception(u32 thread_pkrs) +{ + /* Check the thread saved state */ + if (!check_pkey_val(thread_pkrs, test_armed_key, PKEY_DISABLE_WRITE)) { + pr_err(" FAIL: checking ept_regs->thread_pkrs\n"); + test_exception_ctx->pass = false; + } + + /* Check the exception state */ + if (!check_pkrs(test_armed_key, PKEY_DISABLE_ACCESS)) { + pr_err(" FAIL: PKRS cache and MSR\n"); + test_exception_ctx->pass = false; + } + + /* + * Check we can update the value during exception without affecting the + * calling thread. The calling thread is checked after exception... + */ + pks_mk_readwrite(test_armed_key); + if (!check_pkrs(test_armed_key, 0)) { + pr_err(" FAIL: exception did not change register to 0\n"); + test_exception_ctx->pass = false; + } + pks_mk_noaccess(test_armed_key); + if (!check_pkrs(test_armed_key, PKEY_DISABLE_ACCESS)) { + pr_err(" FAIL: exception did not change register to 0x%x\n", + PKEY_DISABLE_ACCESS); + test_exception_ctx->pass = false; + } +} + +/** + * pks_test_callback() is exported so that the fault handler can detect + * and report back status of intentional faults. + * + * NOTE: It clears the protection key from the page such that the fault handler + * will not re-trigger. + */ +bool pks_test_callback(struct pt_regs *regs) +{ + struct extended_pt_regs *ept_regs = extended_pt_regs(regs); + bool armed = (test_armed_key != 0); + + if (test_exception_ctx) { + check_exception(ept_regs->thread_pkrs); + /* + * We stop this check within the exception because the + * fault handler clean up code will call us 2x while checking + * the PMD entry and we don't need to check this again + */ + test_exception_ctx = NULL; + } + + if (armed) { + /* Enable read and write to stop faults */ + ept_regs->thread_pkrs = update_pkey_val(ept_regs->thread_pkrs, + test_armed_key, 0); + fault_cnt++; + } + + return armed; +} + +static bool exception_caught(void) +{ + bool ret = (fault_cnt != prev_cnt); + + prev_cnt = fault_cnt; + return ret; +} + +static void report_pkey_settings(void *info) +{ + u8 pkey; + unsigned long long msr = 0; + unsigned int cpu = smp_processor_id(); + struct pks_test_ctx *ctx = info; + + rdmsrl(MSR_IA32_PKRS, msr); + + pr_info("for CPU %d : 0x%llx\n", cpu, msr); + + if (ctx->debug) { + for (pkey = 0; pkey < PKS_NUM_KEYS; pkey++) { + int ad, wd; + + ad = (msr >> PKR_PKEY_SHIFT(pkey)) & PKEY_DISABLE_ACCESS; + wd = (msr >> PKR_PKEY_SHIFT(pkey)) & PKEY_DISABLE_WRITE; + pr_info(" %u: A:%d W:%d\n", pkey, ad, wd); + } + } +} + +enum pks_access_mode { + PKS_TEST_NO_ACCESS, + PKS_TEST_RDWR, + PKS_TEST_RDONLY +}; + +static char *get_mode_str(enum pks_access_mode mode) +{ + switch (mode) { + case PKS_TEST_NO_ACCESS: + return "No Access"; + case PKS_TEST_RDWR: + return "Read Write"; + case PKS_TEST_RDONLY: + return "Read Only"; + default: + pr_err("BUG in test invalid mode\n"); + break; + } + + return ""; +} + +struct pks_access_test { + enum pks_access_mode mode; + bool write; + bool exception; +}; + +static struct pks_access_test pkey_test_ary[] = { + /* disable both */ + { PKS_TEST_NO_ACCESS, true, true }, + { PKS_TEST_NO_ACCESS, false, true }, + + /* enable both */ + { PKS_TEST_RDWR, true, false }, + { PKS_TEST_RDWR, false, false }, + + /* enable read only */ + { PKS_TEST_RDONLY, true, true }, + { PKS_TEST_RDONLY, false, false }, +}; + +static int test_it(struct pks_test_ctx *ctx, struct pks_access_test *test, void *ptr) +{ + bool exception; + int ret = 0; + + spin_lock(&test_lock); + WRITE_ONCE(test_armed_key, ctx->pkey); + + if (test->write) + memcpy(ptr, ctx->data, 8); + else + memcpy(ctx->data, ptr, 8); + + exception = exception_caught(); + + WRITE_ONCE(test_armed_key, 0); + spin_unlock(&test_lock); + + if (test->exception != exception) { + pr_err("pkey test FAILED: mode %s; write %s; exception %s != %s\n", + get_mode_str(test->mode), + test->write ? "TRUE" : "FALSE", + test->exception ? "TRUE" : "FALSE", + exception ? "TRUE" : "FALSE"); + ret = -EFAULT; + } + + return ret; +} + +static int run_access_test(struct pks_test_ctx *ctx, + struct pks_access_test *test, + void *ptr) +{ + switch (test->mode) { + case PKS_TEST_NO_ACCESS: + pks_mk_noaccess(ctx->pkey); + break; + case PKS_TEST_RDWR: + pks_mk_readwrite(ctx->pkey); + break; + case PKS_TEST_RDONLY: + pks_mk_readonly(ctx->pkey); + break; + default: + pr_err("BUG in test invalid mode\n"); + break; + } + + return test_it(ctx, test, ptr); +} + +static void *alloc_test_page(int pkey) +{ + return __vmalloc_node_range(PKS_TEST_MEM_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_PKEY(pkey), 0, + NUMA_NO_NODE, __builtin_return_address(0)); +} + +static void test_mem_access(struct pks_test_ctx *ctx) +{ + int i, rc; + u8 pkey; + void *ptr = NULL; + pte_t *ptep = NULL; + spinlock_t *ptl; + + ptr = alloc_test_page(ctx->pkey); + if (!ptr) { + pr_err("Failed to vmalloc page???\n"); + ctx->pass = false; + return; + } + + if (follow_pte(&init_mm, (unsigned long)ptr, &ptep, &ptl)) { + pr_err("Failed to walk table???\n"); + ctx->pass = false; + goto done; + } + + pkey = pte_flags_pkey(ptep->pte); + pr_info("ptep flags 0x%lx pkey %u\n", + (unsigned long)ptep->pte, pkey); + pte_unmap_unlock(ptep, ptl); + + if (pkey != ctx->pkey) { + pr_err("invalid pkey found: %u, test_pkey: %u\n", + pkey, ctx->pkey); + ctx->pass = false; + goto done; + } + + if (!ctx->pks_cpu_enabled) { + pr_err("not CPU enabled; skipping access tests...\n"); + ctx->pass = true; + goto done; + } + + for (i = 0; i < ARRAY_SIZE(pkey_test_ary); i++) { + rc = run_access_test(ctx, &pkey_test_ary[i], ptr); + + /* only save last error is fine */ + if (rc) + ctx->pass = false; + } + +done: + vfree(ptr); +} + +static void pks_run_test(struct pks_test_ctx *ctx) +{ + ctx->pass = true; + + pr_info("\n"); + pr_info("\n"); + pr_info(" ***** BEGIN: Testing (CPU enabled : %s) *****\n", + ctx->pks_cpu_enabled ? "TRUE" : "FALSE"); + + if (ctx->pks_cpu_enabled) + on_each_cpu(report_pkey_settings, ctx, 1); + + pr_info(" BEGIN: pkey %d Testing\n", ctx->pkey); + test_mem_access(ctx); + pr_info(" END: PAGE_KERNEL_PKEY Testing : %s\n", + ctx->pass ? "PASS" : "FAIL"); + + pr_info(" ***** END: Testing *****\n"); + pr_info("\n"); + pr_info("\n"); +} + +static ssize_t pks_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct pks_test_ctx *ctx = file->private_data; + char buf[32]; + unsigned int len; + + if (!ctx) + len = sprintf(buf, "not run\n"); + else + len = sprintf(buf, "%s\n", ctx->pass ? "PASS" : "FAIL"); + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +static struct pks_test_ctx *alloc_ctx(const char *name) +{ + struct pks_test_ctx *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + + if (!ctx) { + pr_err("Failed to allocate memory for test context\n"); + return ERR_PTR(-ENOMEM); + } + + ctx->pkey = pks_key_alloc(name); + if (ctx->pkey <= 0) { + pr_err("Failed to allocate memory for test context\n"); + kfree(ctx); + return ERR_PTR(-ENOMEM); + } + + ctx->pks_cpu_enabled = cpu_feature_enabled(X86_FEATURE_PKS); + sprintf(ctx->data, "%s", "DEADBEEF"); + return ctx; +} + +static void free_ctx(struct pks_test_ctx *ctx) +{ + pks_key_free(ctx->pkey); + kfree(ctx); +} + +static void run_exception_test(void) +{ + void *ptr = NULL; + bool pass = true; + struct pks_test_ctx *ctx; + + pr_info(" ***** BEGIN: exception checking\n"); + + ctx = alloc_ctx("Exception test"); + if (IS_ERR(ctx)) { + pr_err(" FAIL: no context\n"); + pass = false; + goto result; + } + ctx->pass = true; + + ptr = alloc_test_page(ctx->pkey); + if (!ptr) { + pr_err(" FAIL: no vmalloc page\n"); + pass = false; + goto free_context; + } + + pks_mk_readonly(ctx->pkey); + + spin_lock(&test_lock); + WRITE_ONCE(test_exception_ctx, ctx); + WRITE_ONCE(test_armed_key, ctx->pkey); + + memcpy(ptr, ctx->data, 8); + + if (!exception_caught()) { + pr_err(" FAIL: did not get an exception\n"); + pass = false; + } + + /* + * NOTE The exception code has to enable access (b00) to keep the + * fault from looping forever. So we don't see the write disabled + * restored but rather full access restored. Also note that as part + * of this test the exception callback attempted to disable access + * completely (b11) and so we ensure that we are seeing the proper + * thread value restored here. + */ + if (!check_pkrs(test_armed_key, 0)) { + pr_err(" FAIL: PKRS not restored\n"); + pass = false; + } + + if (!ctx->pass) + pass = false; + + WRITE_ONCE(test_armed_key, 0); + spin_unlock(&test_lock); + + vfree(ptr); +free_context: + free_ctx(ctx); +result: + pr_info(" ***** END: exception checking : %s\n", + pass ? "PASS" : "FAIL"); +} + +static void run_all(bool debug) +{ + struct pks_test_ctx *ctx[PKS_NUM_KEYS]; + static char name[PKS_NUM_KEYS][64]; + int i; + + for (i = 1; i < PKS_NUM_KEYS; i++) { + sprintf(name[i], "pks ctx %d", i); + ctx[i] = alloc_ctx((const char *)name[i]); + if (!IS_ERR(ctx[i])) + ctx[i]->debug = debug; + } + + for (i = 1; i < PKS_NUM_KEYS; i++) { + if (!IS_ERR(ctx[i])) + pks_run_test(ctx[i]); + } + + for (i = 1; i < PKS_NUM_KEYS; i++) { + if (!IS_ERR(ctx[i])) + free_ctx(ctx[i]); + } + + run_exception_test(); +} + +static void crash_it(void) +{ + struct pks_test_ctx *ctx; + void *ptr; + + pr_warn(" ***** BEGIN: Unhandled fault test *****\n"); + + ctx = alloc_ctx("crashing kernel\n"); + if (IS_ERR(ctx)) { + pr_err("Failed to allocate context???\n"); + return; + } + + ptr = alloc_test_page(ctx->pkey); + if (!ptr) { + pr_err("Failed to vmalloc page???\n"); + ctx->pass = false; + return; + } + + pks_mk_noaccess(ctx->pkey); + + spin_lock(&test_lock); + WRITE_ONCE(test_armed_key, 0); + /* This purposely faults */ + memcpy(ptr, ctx->data, 8); + spin_unlock(&test_lock); + + vfree(ptr); + free_ctx(ctx); +} + +static ssize_t pks_write_file(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[2]; + struct pks_test_ctx *ctx = file->private_data; + + if (copy_from_user(buf, user_buf, 1)) + return -EFAULT; + buf[1] = '\0'; + + /* + * WARNING: Test "9" will crash the kernel. + * + * So we arm the test and print a warning. A second "9" will run the + * test. + */ + if (!strcmp(buf, RUN_CRASH_TEST)) { + if (run_9) { + crash_it(); + run_9 = false; + } else { + pr_warn("CAUTION: Test 9 will crash in the kernel.\n"); + pr_warn(" Specify 9 a second time to run\n"); + pr_warn(" run any other test to clear\n"); + run_9 = true; + } + } else { + run_9 = false; + } + + /* + * Test "3" will test allocating all keys. Do it first without + * using "ctx". + */ + if (!strcmp(buf, RUN_ALLOCATE_ALL)) + run_all(false); + if (!strcmp(buf, RUN_ALLOCATE_ALL_DEBUG)) + run_all(true); + + /* + * This context is only required if the file is held open for the below + * tests. Otherwise the context just get's freed in pks_release_file. + */ + if (!ctx) { + ctx = alloc_ctx("pks test"); + if (IS_ERR(ctx)) + return -ENOMEM; + file->private_data = ctx; + } + + if (!strcmp(buf, RUN_ALLOCATE)) { + ctx->debug = false; + pks_run_test(ctx); + } + if (!strcmp(buf, RUN_ALLOCATE_DEBUG)) { + ctx->debug = true; + pks_run_test(ctx); + } + + /* start of context switch test */ + if (!strcmp(buf, ARM_CTX_SWITCH)) { + unsigned long reg_pkrs; + int access; + + /* Ensure a known state to test context switch */ + pks_mk_readwrite(ctx->pkey); + + rdmsrl(MSR_IA32_PKRS, reg_pkrs); + + access = (reg_pkrs >> PKR_PKEY_SHIFT(ctx->pkey)) & + PKEY_ACCESS_MASK; + pr_info("Context switch armed : pkey %d: 0x%x reg: 0x%lx\n", + ctx->pkey, access, reg_pkrs); + } + + /* After context switch msr should be restored */ + if (!strcmp(buf, CHECK_CTX_SWITCH) && ctx->pks_cpu_enabled) { + unsigned long reg_pkrs; + int access; + + rdmsrl(MSR_IA32_PKRS, reg_pkrs); + + access = (reg_pkrs >> PKR_PKEY_SHIFT(ctx->pkey)) & + PKEY_ACCESS_MASK; + if (access != 0) { + ctx->pass = false; + pr_err("Context switch check failed: pkey %d: 0x%x reg: 0x%lx\n", + ctx->pkey, access, reg_pkrs); + } else { + pr_err("Context switch check passed: pkey %d: 0x%x reg: 0x%lx\n", + ctx->pkey, access, reg_pkrs); + } + } + + return count; +} + +static int pks_release_file(struct inode *inode, struct file *file) +{ + struct pks_test_ctx *ctx = file->private_data; + + if (!ctx) + return 0; + + free_ctx(ctx); + return 0; +} + +static const struct file_operations fops_init_pks = { + .read = pks_read_file, + .write = pks_write_file, + .llseek = default_llseek, + .release = pks_release_file, +}; + +static int __init parse_pks_test_options(char *str) +{ + run_on_boot = true; + + return 0; +} +early_param("pks-test-on-boot", parse_pks_test_options); + +static int __init pks_test_init(void) +{ + if (cpu_feature_enabled(X86_FEATURE_PKS)) { + if (run_on_boot) + run_all(true); + + pks_test_dentry = debugfs_create_file("run_pks", 0600, arch_debugfs_dir, + NULL, &fops_init_pks); + } + + return 0; +} +late_initcall(pks_test_init); + +static void __exit pks_test_exit(void) +{ + debugfs_remove(pks_test_dentry); + pr_info("test exit\n"); +} diff --git a/mm/Kconfig b/mm/Kconfig index c7d1fc780358..463e95ea0df1 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -811,7 +811,8 @@ config ARCH_HAS_PKEYS config ARCH_HAS_SUPERVISOR_PKEYS bool config ARCH_ENABLE_SUPERVISOR_PKEYS - bool + def_bool y + depends on PKS_TEST

config PERCPU_STATS bool "Collect percpu memory statistics" diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..32fe0414c6af 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,8 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore test_pks + TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/test_pks.c b/tools/testing/selftests/x86/test_pks.c new file mode 100644 index 000000000000..62146cd59eb5 --- /dev/null +++ b/tools/testing/selftests/x86/test_pks.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> +#include <getopt.h> +#include <unistd.h> +#include <assert.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <stdbool.h> + +#define PKS_TEST_FILE "/sys/kernel/debug/x86/run_pks" + +#define RUN_ALLOCATE "0" +#define SETUP_CTX_SWITCH "1" +#define CHECK_CTX_SWITCH "2" +#define RUN_ALLOCATE_ALL "3" +#define RUN_ALLOCATE_DEBUG "4" +#define RUN_ALLOCATE_ALL_DEBUG "5" +#define RUN_CRASH_TEST "9" + +int main(int argc, char *argv[]) +{ + cpu_set_t cpuset; + char result[32]; + pid_t pid; + int fd; + int setup_done[2]; + int switch_done[2]; + int cpu = 0; + int rc = 0; + int c; + bool debug = false; + + while (1) { + int option_index = 0; + static struct option long_options[] = { + {"debug", no_argument, 0, 0 }, + {0, 0, 0, 0 } + }; + + c = getopt_long(argc, argv, "", long_options, &option_index); + if (c == -1) + break; + + switch (c) { + case 0: + debug = true; + break; + } + } + + if (optind < argc) + cpu = strtoul(argv[optind], NULL, 0); + + if (cpu >= sysconf(_SC_NPROCESSORS_ONLN)) { + printf("CPU %d is invalid\n", cpu); + cpu = sysconf(_SC_NPROCESSORS_ONLN) - 1; + printf(" running on max CPU: %d\n", cpu); + } + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + /* Two processes run on CPU 0 so that they go through context switch. */ + sched_setaffinity(getpid(), sizeof(cpu_set_t), &cpuset); + + if (pipe(setup_done)) + printf("Failed to create pipe\n"); + if (pipe(switch_done)) + printf("Failed to create pipe\n"); + + pid = fork(); + if (pid == 0) { + char done = 'y'; + + fd = open(PKS_TEST_FILE, O_RDWR); + if (fd < 0) { + printf("cannot open %s\n", PKS_TEST_FILE); + return -1; + } + + cpu = sched_getcpu(); + printf("Child running on cpu %d...\n", cpu); + + /* Allocate test_pkey1 and run test. */ + if (debug) + write(fd, RUN_ALLOCATE_DEBUG, 1); + else + write(fd, RUN_ALLOCATE, 1); + + /* Arm for context switch test */ + write(fd, SETUP_CTX_SWITCH, 1); + + printf(" tell parent to go\n"); + write(setup_done[1], &done, sizeof(done)); + + /* Context switch out... */ + printf(" Waiting for parent...\n"); + read(switch_done[0], &done, sizeof(done)); + + /* Check msr restored */ + printf("Checking result\n"); + write(fd, CHECK_CTX_SWITCH, 1); + + read(fd, result, 10); + printf(" #PF, context switch, pkey allocation and free tests: %s\n", result); + if (!strncmp(result, "PASS", 10)) { + rc = -1; + done = 'F'; + } + + /* Signal result */ + write(setup_done[1], &done, sizeof(done)); + } else { + char done = 'y'; + + read(setup_done[0], &done, sizeof(done)); + cpu = sched_getcpu(); + printf("Parent running on cpu %d\n", cpu); + + fd = open(PKS_TEST_FILE, O_RDWR); + if (fd < 0) { + printf("cannot open %s\n", PKS_TEST_FILE); + return -1; + } + + /* run test with alternate pkey */ + if (debug) + write(fd, RUN_ALLOCATE_DEBUG, 1); + else + write(fd, RUN_ALLOCATE, 1); + + /* Signal child we are done. */ + printf(" Telling child we are done.\n"); + write(switch_done[1], &done, sizeof(done)); + + /* Wait for result */ + read(setup_done[0], &done, sizeof(done)); + if (done == 'F') + rc = -1; + } + + close(fd); + + return rc; +}