From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AH8x224EYUadZKz15nrBSuzLQFwX0VYge38jntSSnRaY7z9Nmy9/hHgo04Et7c/nrXY0c+ZK9ntK ARC-Seal: i=1; a=rsa-sha256; t=1518168358; cv=none; d=google.com; s=arc-20160816; b=p1CIqhpVLGnhGV2xzGqFIgYFOqhL35Oy74Z7uPyeIE3IPZcZKLtX4DaNYXzGk086tq uB7wtz4A9/RRBaVxABFlFiho3VNhKrOR3s8CvC1K5SfBdlzz0oQD1DLFebiVQGtN+6ye o0Y3qaZ3HHvOGOhL5zbGggn8SIxTkzHuB42Ex0JQ8Y/MIMRhj+JHAB8dC6fbnNL59V4y qIPICALrlEN/ROMG3COLQ4V9xySLlXL+LRyf9+fokrfKSs9CuTqQp6IWFMRXreOLUdYZ XrR3/gb2QhM2sotMyxziP8HHVuWY+rXVGjgB7h809Y93ckUqhGCNSfVqDNQAnWbCGACu 1Cqg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=references:in-reply-to:message-id:date:subject:cc:to:from :dkim-signature:arc-authentication-results; bh=DrqeQNOm0g8Mc4vr7QAR9T+xeBlp8SjMqmZj74xwEDw=; b=XqkAkveFydukdDL3ZPVZpGv7yy3d2aOfMgsQFfG5WoXKms6TTIkROSHxkFkXNy5ll9 mODxfhs/d6dc5S8lMUajQW1f48dpPaEWFy+BTuimYDMjOOXV3HmdRuErePvLKuBJl1/H MoNIQ9FO68srPLjZ3LbhEjYCyO4KdtXXS7U/ulmqiBZsOO0+DrFNUGTC/E3KRtCakLa2 IEmBEmKmilyu2kt+SedtyiQGVW8HEgJjuQcAKbDEGxaXMlWcNwRQHbQGnDiPw5wP28RO DiTXhXXTsAFJNaACQYR4VUjwe32IqJKKr9tmjMN2gqStQveIfrbhK0GG0uUkPm9Ee9lc UhKw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass (test mode) header.i=@8bytes.org header.s=mail-1 header.b=CNLxIxPL; spf=pass (google.com: domain of joro@8bytes.org designates 2a01:238:4383:600:38bc:a715:4b6d:a889 as permitted sender) smtp.mailfrom=joro@8bytes.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=8bytes.org Authentication-Results: mx.google.com; dkim=pass (test mode) header.i=@8bytes.org header.s=mail-1 header.b=CNLxIxPL; spf=pass (google.com: domain of joro@8bytes.org designates 2a01:238:4383:600:38bc:a715:4b6d:a889 as permitted sender) smtp.mailfrom=joro@8bytes.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=8bytes.org From: Joerg Roedel To: Thomas Gleixner , Ingo Molnar , "H . Peter Anvin" Cc: x86@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Linus Torvalds , Andy Lutomirski , Dave Hansen , Josh Poimboeuf , Juergen Gross , Peter Zijlstra , Borislav Petkov , Jiri Kosina , Boris Ostrovsky , Brian Gerst , David Laight , Denys Vlasenko , Eduardo Valentin , Greg KH , Will Deacon , aliguori@amazon.com, daniel.gruss@iaik.tugraz.at, hughd@google.com, keescook@google.com, Andrea Arcangeli , Waiman Long , Pavel Machek , jroedel@suse.de, joro@8bytes.org Subject: [PATCH 13/31] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack Date: Fri, 9 Feb 2018 10:25:22 +0100 Message-Id: <1518168340-9392-14-git-send-email-joro@8bytes.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1518168340-9392-1-git-send-email-joro@8bytes.org> References: <1518168340-9392-1-git-send-email-joro@8bytes.org> X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1591914904806211394?= X-GMAIL-MSGID: =?utf-8?q?1591914904806211394?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: From: Joerg Roedel It can happen that we enter the kernel from kernel-mode and on the entry-stack. The most common way this happens is when we get an exception while loading the user-space segment registers on the kernel-to-userspace exit path. The segment loading needs to be done after the entry-stack switch, because the stack-switch needs kernel %fs for per_cpu access. When this happens, we need to make sure that we leave the kernel with the entry-stack again, so that the interrupted code-path runs on the right stack when switching to the user-cr3. We do this by detecting this condition on kernel-entry by checking CS.RPL and %esp, and if it happens, we copy over the complete content of the entry stack to the task-stack. This needs to be done because once we enter the exception handlers we might be scheduled out or even migrated to a different CPU, so that we can't rely on the entry-stack contents. We also leave a marker in the stack-frame to detect this condition on the exit path. On the exit path the copy is reversed, we copy all of the remaining task-stack back to the entry-stack and switch to it. Signed-off-by: Joerg Roedel --- arch/x86/entry/entry_32.S | 109 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 108 insertions(+), 1 deletion(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index b5ef003..d94dab6 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -358,6 +358,9 @@ * copied there. So allocate the stack-frame on the task-stack and * switch to it before we do any copying. */ + +#define CS_FROM_ENTRY_STACK (1 << 31) + .macro SWITCH_TO_KERNEL_STACK ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV @@ -381,6 +384,10 @@ /* Load top of task-stack into %edi */ movl TSS_entry_stack(%edi), %edi + /* Special case - entry from kernel mode via entry stack */ + testl $SEGMENT_RPL_MASK, PT_CS(%esp) + jz .Lentry_from_kernel_\@ + /* Bytes to copy */ movl $PTREGS_SIZE, %ecx @@ -394,8 +401,8 @@ */ addl $(4 * 4), %ecx -.Lcopy_pt_regs_\@: #endif +.Lcopy_pt_regs_\@: /* Allocate frame on task-stack */ subl %ecx, %edi @@ -410,6 +417,56 @@ cld rep movsb + jmp .Lend_\@ + +.Lentry_from_kernel_\@: + + /* + * This handles the case when we enter the kernel from + * kernel-mode and %esp points to the entry-stack. When this + * happens we need to switch to the task-stack to run C code, + * but switch back to the entry-stack again when we approach + * iret and return to the interrupted code-path. This usually + * happens when we hit an exception while restoring user-space + * segment registers on the way back to user-space. + * + * When we switch to the task-stack here, we can't trust the + * contents of the entry-stack anymore, as the exception handler + * might be scheduled out or moved to another CPU. Therefore we + * copy the complete entry-stack to the task-stack and set a + * marker in the iret-frame (bit 31 of the CS dword) to detect + * what we've done on the iret path. + * + * On the iret path we copy everything back and switch to the + * entry-stack, so that the interrupted kernel code-path + * continues on the same stack it was interrupted with. + * + * Be aware that an NMI can happen anytime in this code. + * + * %esi: Entry-Stack pointer (same as %esp) + * %edi: Top of the task stack + */ + + /* Calculate number of bytes on the entry stack in %ecx */ + movl %esi, %ecx + + /* %ecx to the top of entry-stack */ + andl $(MASK_entry_stack), %ecx + addl $(SIZEOF_entry_stack), %ecx + + /* Number of bytes on the entry stack to %ecx */ + sub %esi, %ecx + + /* Mark stackframe as coming from entry stack */ + orl $CS_FROM_ENTRY_STACK, PT_CS(%esp) + + /* + * %esi and %edi are unchanged, %ecx contains the number of + * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate + * the stack-frame on task-stack and copy everything over + */ + jmp .Lcopy_pt_regs_\@ + .Lend_\@: .endm @@ -467,6 +524,55 @@ .endm /* + * This macro handles the case when we return to kernel-mode on the iret + * path and have to switch back to the entry stack. + * + * See the comments below the .Lentry_from_kernel_\@ label in the + * SWITCH_TO_KERNEL_STACK macro for more details. + */ +.macro PARANOID_EXIT_TO_KERNEL_MODE + + /* + * Test if we entered the kernel with the entry-stack. Most + * likely we did not, because this code only runs on the + * return-to-kernel path. + */ + testl $CS_FROM_ENTRY_STACK, PT_CS(%esp) + jz .Lend_\@ + + /* Unlikely slow-path */ + + /* Clear marker from stack-frame */ + andl $(~CS_FROM_ENTRY_STACK), PT_CS(%esp) + + /* Copy the remaining task-stack contents to entry-stack */ + movl %esp, %esi + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi + + /* Bytes on the task-stack to ecx */ + movl PER_CPU_VAR(cpu_current_top_of_stack), %ecx + subl %esi, %ecx + + /* Allocate stack-frame on entry-stack */ + subl %ecx, %edi + + /* + * Save future stack-pointer, we must not switch until the + * copy is done, otherwise the NMI handler could destroy the + * contents of the task-stack we are about to copy. + */ + movl %edi, %ebx + + /* Do the copy */ + cld + rep movsb + + /* Safe to switch to entry-stack now */ + movl %ebx, %esp + +.Lend_\@: +.endm +/* * %eax: prev task * %edx: next task */ @@ -837,6 +943,7 @@ restore_all: restore_all_kernel: TRACE_IRQS_IRET + PARANOID_EXIT_TO_KERNEL_MODE RESTORE_REGS 4 jmp .Lirq_return -- 2.7.4